Merge branch 'client-insert-context'

Previously, we could get empty intervals anyway by having a non-empty
interval and removing a smaller interval around each piece of data.
Turns out that empty intervals are OK and needed in some situations,
so explicitly allow and test for it.

.coveragerc

@@ -0,0 +1,10 @@
+# -*- conf -*-
+
+[run]
+# branch = True
+
+[report]
+exclude_lines =
+	pragma: no cover
+	if 0:
+omit = nilmdb/utils/datetime_tz*,nilmdb/scripts,nilmdb/_version.py

.gitattributes

@@ -0,0 +1 @@
+nilmdb/_version.py export-subst

.gitignore

@@ -0,0 +1,27 @@
+# Tests
+tests/*testdb/
+.coverage
+db/
+
+# Compiled / cythonized files
+docs/*.html
+build/
+*.pyc
+nilmdb/server/interval.c
+nilmdb/server/interval.so
+nilmdb/server/layout.c
+nilmdb/server/layout.so
+nilmdb/server/rbtree.c
+nilmdb/server/rbtree.so
+
+# Setup junk
+dist/
+nilmdb.egg-info/
+
+# This gets generated as needed by setup.py
+MANIFEST.in
+MANIFEST
+
+# Misc
+timeit*out
+

.pylintrc

@@ -0,0 +1,250 @@
+# -*- conf -*-
+[MASTER]
+
+# Specify a configuration file.
+#rcfile=
+
+# Python code to execute, usually for sys.path manipulation such as
+# pygtk.require().
+#init-hook=
+
+# Profiled execution.
+profile=no
+
+# Add files or directories to the blacklist. They should be base names, not
+# paths.
+ignore=datetime_tz
+
+# Pickle collected data for later comparisons.
+persistent=no
+
+# List of plugins (as comma separated values of python modules names) to load,
+# usually to register additional checkers.
+load-plugins=
+
+
+[MESSAGES CONTROL]
+
+# Enable the message, report, category or checker with the given id(s). You can
+# either give multiple identifier separated by comma (,) or put this option
+# multiple time.
+#enable=
+
+# Disable the message, report, category or checker with the given id(s). You
+# can either give multiple identifier separated by comma (,) or put this option
+# multiple time (only on the command line, not in the configuration file where
+# it should appear only once).
+disable=C0111,R0903,R0201,R0914,R0912,W0142,W0703,W0702
+
+
+[REPORTS]
+
+# Set the output format. Available formats are text, parseable, colorized, msvs
+# (visual studio) and html
+output-format=parseable
+
+# Include message's id in output
+include-ids=yes
+
+# Put messages in a separate file for each module / package specified on the
+# command line instead of printing them on stdout. Reports (if any) will be
+# written in a file name "pylint_global.[txt|html]".
+files-output=no
+
+# Tells whether to display a full report or only the messages
+reports=yes
+
+# Python expression which should return a note less than 10 (10 is the highest
+# note). You have access to the variables errors warning, statement which
+# respectively contain the number of errors / warnings messages and the total
+# number of statements analyzed. This is used by the global evaluation report
+# (RP0004).
+evaluation=10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10)
+
+# Add a comment according to your evaluation note. This is used by the global
+# evaluation report (RP0004).
+comment=no
+
+
+[SIMILARITIES]
+
+# Minimum lines number of a similarity.
+min-similarity-lines=4
+
+# Ignore comments when computing similarities.
+ignore-comments=yes
+
+# Ignore docstrings when computing similarities.
+ignore-docstrings=yes
+
+
+[TYPECHECK]
+
+# Tells whether missing members accessed in mixin class should be ignored. A
+# mixin class is detected if its name ends with "mixin" (case insensitive).
+ignore-mixin-members=yes
+
+# List of classes names for which member attributes should not be checked
+# (useful for classes with attributes dynamically set).
+ignored-classes=SQLObject
+
+# When zope mode is activated, add a predefined set of Zope acquired attributes
+# to generated-members.
+zope=no
+
+# List of members which are set dynamically and missed by pylint inference
+# system, and so shouldn't trigger E0201 when accessed. Python regular
+# expressions are accepted.
+generated-members=REQUEST,acl_users,aq_parent
+
+
+[FORMAT]
+
+# Maximum number of characters on a single line.
+max-line-length=80
+
+# Maximum number of lines in a module
+max-module-lines=1000
+
+# String used as indentation unit. This is usually " " (4 spaces) or "\t" (1
+# tab).
+indent-string='    '
+
+
+[MISCELLANEOUS]
+
+# List of note tags to take in consideration, separated by a comma.
+notes=FIXME,XXX,TODO
+
+
+[VARIABLES]
+
+# Tells whether we should check for unused import in __init__ files.
+init-import=no
+
+# A regular expression matching the beginning of the name of dummy variables
+# (i.e. not used).
+dummy-variables-rgx=_|dummy
+
+# List of additional names supposed to be defined in builtins. Remember that
+# you should avoid to define new builtins when possible.
+additional-builtins=
+
+
+[BASIC]
+
+# Required attributes for module, separated by a comma
+required-attributes=
+
+# List of builtins function names that should not be used, separated by a comma
+bad-functions=apply,input
+
+# Regular expression which should only match correct module names
+module-rgx=(([a-z_][a-z0-9_]*)|([A-Z][a-zA-Z0-9]+))$
+
+# Regular expression which should only match correct module level names
+const-rgx=(([A-Z_][A-Z0-9_]*)|(__.*__)|version)$
+
+# Regular expression which should only match correct class names
+class-rgx=[A-Z_][a-zA-Z0-9]+$
+
+# Regular expression which should only match correct function names
+function-rgx=[a-z_][a-z0-9_]{0,30}$
+
+# Regular expression which should only match correct method names
+method-rgx=[a-z_][a-z0-9_]{0,30}$
+
+# Regular expression which should only match correct instance attribute names
+attr-rgx=[a-z_][a-z0-9_]{0,30}$
+
+# Regular expression which should only match correct argument names
+argument-rgx=[a-z_][a-z0-9_]{0,30}$
+
+# Regular expression which should only match correct variable names
+variable-rgx=[a-z_][a-z0-9_]{0,30}$
+
+# Regular expression which should only match correct list comprehension /
+# generator expression variable names
+inlinevar-rgx=[A-Za-z_][A-Za-z0-9_]*$
+
+# Good variable names which should always be accepted, separated by a comma
+good-names=i,j,k,ex,Run,_
+
+# Bad variable names which should always be refused, separated by a comma
+bad-names=foo,bar,baz,toto,tutu,tata
+
+# Regular expression which should only match functions or classes name which do
+# not require a docstring
+no-docstring-rgx=__.*__
+
+
+[CLASSES]
+
+# List of interface methods to ignore, separated by a comma. This is used for
+# instance to not check methods defines in Zope's Interface base class.
+ignore-iface-methods=isImplementedBy,deferred,extends,names,namesAndDescriptions,queryDescriptionFor,getBases,getDescriptionFor,getDoc,getName,getTaggedValue,getTaggedValueTags,isEqualOrExtendedBy,setTaggedValue,isImplementedByInstancesOf,adaptWith,is_implemented_by
+
+# List of method names used to declare (i.e. assign) instance attributes.
+defining-attr-methods=__init__,__new__,setUp
+
+# List of valid names for the first argument in a class method.
+valid-classmethod-first-arg=cls
+
+
+[DESIGN]
+
+# Maximum number of arguments for function / method
+max-args=5
+
+# Argument names that match this expression will be ignored. Default to name
+# with leading underscore
+ignored-argument-names=_.*
+
+# Maximum number of locals for function / method body
+max-locals=15
+
+# Maximum number of return / yield for function / method body
+max-returns=6
+
+# Maximum number of branch for function / method body
+max-branchs=12
+
+# Maximum number of statements in function / method body
+max-statements=50
+
+# Maximum number of parents for a class (see R0901).
+max-parents=7
+
+# Maximum number of attributes for a class (see R0902).
+max-attributes=7
+
+# Minimum number of public methods for a class (see R0903).
+min-public-methods=2
+
+# Maximum number of public methods for a class (see R0904).
+max-public-methods=20
+
+
+[IMPORTS]
+
+# Deprecated modules which should not be used, separated by a comma
+deprecated-modules=regsub,string,TERMIOS,Bastion,rexec
+
+# Create a graph of every (i.e. internal and external) dependencies in the
+# given file (report RP0402 must not be disabled)
+import-graph=
+
+# Create a graph of external dependencies in the given file (report RP0402 must
+# not be disabled)
+ext-import-graph=
+
+# Create a graph of internal dependencies in the given file (report RP0402 must
+# not be disabled)
+int-import-graph=
+
+
+[EXCEPTIONS]
+
+# Exceptions that will emit a warning when being caught. Defaults to
+# "Exception"
+overgeneral-exceptions=Exception

Makefile

@@ -1,2 +1,36 @@
-all:
-	nosetests
+# By default, run the tests.
+all: test
+
+version:
+	python setup.py version
+
+build:
+	python setup.py build_ext --inplace
+
+dist: sdist
+sdist:
+	python setup.py sdist
+
+install:
+	python setup.py install
+
+docs:
+	make -C docs
+
+lint:
+	pylint --rcfile=.pylintrc nilmdb
+
+test:
+	python tests/runtests.py
+
+clean::
+	find . -name '*pyc' | xargs rm -f
+	rm -f .coverage
+	rm -rf tests/*testdb*
+	rm -rf nilmdb.egg-info/ build/ nilmdb/server/*.so MANIFEST.in
+	make -C docs clean
+
+gitclean::
+	git clean -dXf
+
+.PHONY: all build dist sdist install docs lint test clean

README.txt

@@ -1,4 +1,22 @@
-To install, 
+nilmdb: Non-Intrusive Load Monitor Database
+by Jim Paris <jim@jtan.com>
 
-   python seutp.py install
+Prerequisites:
 
+  # Runtime and build environments
+  sudo apt-get install python2.7 python2.7-dev python-setuptools cython
+
+  # Base NilmDB dependencies
+  sudo apt-get install python-cherrypy3 python-decorator python-simplejson python-pycurl python-dateutil python-tz python-psutil
+
+  # Tools for running tests
+  sudo apt-get install python-nose python-coverage
+
+Install:
+
+  python setup.py install
+
+Usage:
+
+  nilmdb-server --help
+  nilmtool --help

bin/nilm-test.py

@@ -1,26 +0,0 @@
-#!/usr/bin/python
-
-from nilmdb import Interval
-from optparse import OptionParser
-import sys
-
-version = "1.0"
-
-parser = OptionParser()
-parser.add_option("-d", "--db", dest="database", metavar="DATABASE",
-                  help="location of sqlite database")
-parser.add_option("-V", "--version", dest="version", default=False, action="store_true",
-                  help="print version then exit")
-
-(options, args) = parser.parse_args()
-
-if (options.version):
-    print "This script version: " + version
-    sys.exit(0)
-
-if options.database is None:
-    print "Error: database is mandatory"
-    sys.exit(1)
-
-print "Database is " + options.database
-

docs/Makefile

@@ -0,0 +1,9 @@
+ALL_DOCS = $(wildcard *.md)
+
+all: $(ALL_DOCS:.md=.html)
+
+%.html: %.md
+	pandoc -s $< > $@
+
+clean:
+	rm -f *.html

docs/TODO.md

@@ -0,0 +1,5 @@
+- Documentation
+
+- Machine-readable information in OverflowError, parser errors.
+  Maybe subclass `cherrypy.HTTPError` and override `set_response`
+  to add another JSON field?

docs/design.md

@@ -0,0 +1,268 @@
+Structure
+---------
+nilmdb.nilmdb is the NILM database interface.  A nilmdb.BulkData
+interface stores data in flat files, and a SQL database tracks
+metadata and ranges.
+
+Access to the nilmdb must be single-threaded.  This is handled with
+the nilmdb.serializer class.  In the future this could probably
+be turned into a per-path serialization.
+
+nilmdb.server is a HTTP server that provides an interface to talk,
+thorugh the serialization layer, to the nilmdb object.
+
+nilmdb.client is a HTTP client that connects to this.
+
+Sqlite performance
+------------------
+
+Committing a transaction in the default sync mode (PRAGMA synchronous=FULL)
+takes about 125msec.  sqlite3 will commit transactions at 3 times:
+
+1. explicit con.commit()
+
+2. between a series of DML commands and non-DML commands, e.g.
+   after a series of INSERT, SELECT, but before a CREATE TABLE or
+   PRAGMA.
+
+3. at the end of an explicit transaction, e.g. "with self.con as con:"
+
+To speed up testing, or if this transaction speed becomes an issue,
+the sync=False option to NilmDB will set PRAGMA synchronous=OFF.
+
+
+Inserting streams
+-----------------
+
+We need to send the contents of "data" as POST.  Do we need chunked
+transfer?
+
+- Don't know the size in advance, so we would need to use chunked if
+  we send the entire thing in one request.
+- But we shouldn't send one chunk per line, so we need to buffer some
+  anyway; why not just make new requests?
+- Consider the infinite-streaming case, we might want to send it
+  immediately?  Not really -- server still should do explicit inserts
+  of fixed-size chunks.
+- Even chunked encoding needs the size of each chunk beforehand, so
+  everything still gets buffered.  Just a tradeoff of buffer size.
+
+Before timestamps are added:
+
+- Raw data is about 440 kB/s    (9 channels)
+- Prep data is about 12.5 kB/s  (1 phase)
+- How do we know how much data to send?
+
+    - Remember that we can only do maybe 8-50 transactions per second on
+      the sqlite database.  So if one block of inserted data is one
+      transaction, we'd need the raw case to be around 64kB per request,
+      ideally more.
+    - Maybe use a range, based on how long it's taking to read the data
+        - If no more data, send it
+        - If data > 1 MB, send it
+    - If more than 10 seconds have elapsed, send it
+    - Should those numbers come from the server?
+
+Converting from ASCII to PyTables:
+
+- For each row getting added, we need to set attributes on a PyTables
+  Row object and call table.append().  This means that there isn't a
+  particularly efficient way of converting from ascii.
+- Could create a function like nilmdb.layout.Layout("foo".fillRow(asciiline)
+    - But this means we're doing parsing on the serialized side
+    - Let's keep parsing on the threaded server side so we can detect
+      errors better, and not block the serialized nilmdb for a slow
+      parsing process.
+- Client sends ASCII data
+- Server converts this ACSII data to a list of values
+    - Maybe:
+
+            # threaded side creates this object
+            parser = nilmdb.layout.Parser("layout_name")
+            # threaded side parses and fills it with data
+            parser.parse(textdata)
+            # serialized side pulls out rows
+            for n in xrange(parser.nrows):
+                parser.fill_row(rowinstance, n)
+                table.append()
+
+
+Inserting streams, inside nilmdb
+--------------------------------
+
+- First check that the new stream doesn't overlap.
+    - Get minimum timestamp, maximum timestamp from data parser.
+        - (extend parser to verify monotonicity and track extents)
+    - Get all intervals for this stream in the database
+    - See if new interval overlaps any existing ones
+        - If so, bail
+    - Question: should we cache intervals inside NilmDB?
+        - Assume database is fast for now, and always rebuild fom DB.
+        - Can add a caching layer later if we need to.
+    - `stream_get_ranges(path)` -> return IntervalSet?
+
+Speed
+-----
+
+- First approach was quadratic.  Adding four hours of data:
+
+        $ time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s 20110513-110000 /bpnilm/1/raw
+        real    24m31.093s
+        $ time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s 20110513-120001 /bpnilm/1/raw
+        real    43m44.528s
+        $ time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s 20110513-130002 /bpnilm/1/raw
+        real    93m29.713s
+        $ time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s 20110513-140003 /bpnilm/1/raw
+        real    166m53.007s
+
+- Disabling pytables indexing didn't help:
+
+        real    31m21.492s
+        real    52m51.963s
+        real    102m8.151s
+        real    176m12.469s
+
+- Server RAM usage is constant.
+
+- Speed problems were due to IntervalSet speed, of parsing intervals
+  from the database and adding the new one each time.
+
+    - First optimization is to cache result of `nilmdb:_get_intervals`,
+      which gives the best speedup.
+
+    - Also switched to internally using bxInterval from bx-python package.
+      Speed of `tests/test_interval:TestIntervalSpeed` is pretty decent
+      and seems to be growing logarithmically now.  About 85μs per insertion
+      for inserting 131k entries.
+
+    - Storing the interval data in SQL might be better, with a scheme like:
+      http://www.logarithmic.net/pfh/blog/01235197474
+
+- Next slowdown target is nilmdb.layout.Parser.parse().
+    - Rewrote parsers using cython and sscanf
+    - Stats (rev 10831), with _add_interval disabled
+
+        layout.pyx.Parser.parse:128        6303 sec, 262k calls
+         layout.pyx.parse:63               13913 sec, 5.1g calls
+        numpy:records.py.fromrecords:569   7410 sec, 262k calls
+
+- Probably OK for now.
+
+- After all updates, now takes about 8.5 minutes to insert an hour of
+  data, constant after adding 171 hours (4.9 billion data points)
+
+- Data set size: 98 gigs = 20 bytes per data point.
+  6 uint16 data + 1 uint32 timestamp = 16 bytes per point
+  So compression must be off -- will retry with compression forced on.
+
+IntervalSet speed
+-----------------
+- Initial implementation was pretty slow, even with binary search in
+  sorted list
+
+- Replaced with bxInterval; now takes about log n time for an insertion
+    - TestIntervalSpeed with range(17,18) and profiling
+        - 85 μs each
+        - 131072 calls to `__iadd__`
+        - 131072 to bx.insert_interval
+        - 131072 to bx.insert:395
+        - 2355835 to bx.insert:106  (18x as many?)
+
+- Tried blist too, worse than bxinterval.
+
+- Might be algorithmic improvements to be made in Interval.py,
+  like in `__and__`
+
+- Replaced again with rbtree.  Seems decent.  Numbers are time per
+  insert for 2**17 insertions, followed by total wall time and RAM
+  usage for running "make test" with `test_rbtree` and `test_interval`
+  with range(5,20):
+    - old values with bxinterval:
+      20.2 μS, total 20 s, 177 MB RAM
+    - rbtree, plain python:
+      97 μS, total 105 s, 846 MB RAM
+    - rbtree converted to cython:
+      26 μS, total 29 s, 320 MB RAM
+    - rbtree and interval converted to cython:
+      8.4 μS, total 12 s, 134 MB RAM
+
+Layouts
+-------
+Current/old design has specific layouts: RawData, PrepData, RawNotchedData.
+Let's get rid of this entirely and switch to simpler data types that are
+just collections and counts of a single type.  We'll still use strings
+to describe them, with format:
+
+    type_count
+
+where type is "uint16", "float32", or "float64", and count is an integer.
+
+nilmdb.layout.named() will parse these strings into the appropriate
+handlers.  For compatibility:
+
+    "RawData" == "uint16_6"
+    "RawNotchedData" == "uint16_9"
+    "PrepData" == "float32_8"
+
+
+BulkData design
+---------------
+
+BulkData is a custom bulk data storage system that was written to
+replace PyTables.  The general structure is a `data` subdirectory in
+the main NilmDB directory.  Within `data`, paths are created for each
+created stream.  These locations are called tables.  For example,
+tables might be located at
+
+    nilmdb/data/newton/raw/
+    nilmdb/data/newton/prep/
+    nilmdb/data/cottage/raw/
+
+Each table contains:
+
+- An unchanging `_format` file (Python pickle format) that describes
+  parameters of how the data is broken up, like files per directory,
+  rows per file, and the binary data format
+
+- Hex named subdirectories `("%04x", although more than 65536 can exist)`
+
+- Hex named files within those subdirectories, like:
+
+        /nilmdb/data/newton/raw/000b/010a
+
+    The data format of these files is raw binary, interpreted by the
+    Python `struct` module according to the format string in the
+    `_format` file.
+
+- Same as above, with `.removed` suffix, is an optional file (Python
+  pickle format) containing a list of row numbers that have been
+  logically removed from the file.  If this range covers the entire
+  file, the entire file will be removed.
+
+- Note that the `bulkdata.nrows` variable is calculated once in
+  `BulkData.__init__()`, and only ever incremented during use.  Thus,
+  even if all data is removed, `nrows` can remain high.  However, if
+  the server is restarted, the newly calculated `nrows` may be lower
+  than in a previous run due to deleted data.  To be specific, this
+  sequence of events:
+
+    - insert data
+    - remove all data
+    - insert data
+
+    will result in having different row numbers in the database, and
+    differently numbered files on the filesystem, than the sequence:
+
+    - insert data
+    - remove all data
+    - restart server
+    - insert data
+
+    This is okay!  Everything should remain consistent both in the
+    `BulkData` and `NilmDB`.  Not attempting to readjust `nrows` during
+    deletion makes the code quite a bit simpler.
+
+- Similarly, data files are never truncated shorter.  Removing data
+  from the end of the file will not shorten it; it will only be
+  deleted when it has been fully filled and all of the data has been
+  subsequently removed.

nilmdb/__init__.py

@@ -1,2 +1,8 @@
-from nilmdb.interval import *
-from nilmdb.fileinterval import *
+"""Main NilmDB import"""
+
+from nilmdb.server import NilmDB, Server
+from nilmdb.client import Client
+
+from nilmdb._version import get_versions
+__version__ = get_versions()['version']
+del get_versions

nilmdb/_version.py

@@ -0,0 +1,197 @@
+
+IN_LONG_VERSION_PY = True
+# This file helps to compute a version number in source trees obtained from
+# git-archive tarball (such as those provided by githubs download-from-tag
+# feature). Distribution tarballs (build by setup.py sdist) and build
+# directories (produced by setup.py build) will contain a much shorter file
+# that just contains the computed version number.
+
+# This file is released into the public domain. Generated by
+# versioneer-0.7+ (https://github.com/warner/python-versioneer)
+
+# these strings will be replaced by git during git-archive
+git_refnames = "$Format:%d$"
+git_full = "$Format:%H$"
+
+
+import subprocess
+import sys
+
+def run_command(args, cwd=None, verbose=False):
+    try:
+        # remember shell=False, so use git.cmd on windows, not just git
+        p = subprocess.Popen(args, stdout=subprocess.PIPE, cwd=cwd)
+    except EnvironmentError:
+        e = sys.exc_info()[1]
+        if verbose:
+            print("unable to run %s" % args[0])
+            print(e)
+        return None
+    stdout = p.communicate()[0].strip()
+    if sys.version >= '3':
+        stdout = stdout.decode()
+    if p.returncode != 0:
+        if verbose:
+            print("unable to run %s (error)" % args[0])
+        return None
+    return stdout
+
+
+import sys
+import re
+import os.path
+
+def get_expanded_variables(versionfile_source):
+    # the code embedded in _version.py can just fetch the value of these
+    # variables. When used from setup.py, we don't want to import
+    # _version.py, so we do it with a regexp instead. This function is not
+    # used from _version.py.
+    variables = {}
+    try:
+        for line in open(versionfile_source,"r").readlines():
+            if line.strip().startswith("git_refnames ="):
+                mo = re.search(r'=\s*"(.*)"', line)
+                if mo:
+                    variables["refnames"] = mo.group(1)
+            if line.strip().startswith("git_full ="):
+                mo = re.search(r'=\s*"(.*)"', line)
+                if mo:
+                    variables["full"] = mo.group(1)
+    except EnvironmentError:
+        pass
+    return variables
+
+def versions_from_expanded_variables(variables, tag_prefix, verbose=False):
+    refnames = variables["refnames"].strip()
+    if refnames.startswith("$Format"):
+        if verbose:
+            print("variables are unexpanded, not using")
+        return {} # unexpanded, so not in an unpacked git-archive tarball
+    refs = set([r.strip() for r in refnames.strip("()").split(",")])
+    for ref in list(refs):
+        if not re.search(r'\d', ref):
+            if verbose:
+                print("discarding '%s', no digits" % ref)
+            refs.discard(ref)
+            # Assume all version tags have a digit. git's %d expansion
+            # behaves like git log --decorate=short and strips out the
+            # refs/heads/ and refs/tags/ prefixes that would let us
+            # distinguish between branches and tags. By ignoring refnames
+            # without digits, we filter out many common branch names like
+            # "release" and "stabilization", as well as "HEAD" and "master".
+    if verbose:
+        print("remaining refs: %s" % ",".join(sorted(refs)))
+    for ref in sorted(refs):
+        # sorting will prefer e.g. "2.0" over "2.0rc1"
+        if ref.startswith(tag_prefix):
+            r = ref[len(tag_prefix):]
+            if verbose:
+                print("picking %s" % r)
+            return { "version": r,
+                     "full": variables["full"].strip() }
+    # no suitable tags, so we use the full revision id
+    if verbose:
+        print("no suitable tags, using full revision id")
+    return { "version": variables["full"].strip(),
+             "full": variables["full"].strip() }
+
+def versions_from_vcs(tag_prefix, versionfile_source, verbose=False):
+    # this runs 'git' from the root of the source tree. That either means
+    # someone ran a setup.py command (and this code is in versioneer.py, so
+    # IN_LONG_VERSION_PY=False, thus the containing directory is the root of
+    # the source tree), or someone ran a project-specific entry point (and
+    # this code is in _version.py, so IN_LONG_VERSION_PY=True, thus the
+    # containing directory is somewhere deeper in the source tree). This only
+    # gets called if the git-archive 'subst' variables were *not* expanded,
+    # and _version.py hasn't already been rewritten with a short version
+    # string, meaning we're inside a checked out source tree.
+
+    try:
+        here = os.path.abspath(__file__)
+    except NameError:
+        # some py2exe/bbfreeze/non-CPython implementations don't do __file__
+        return {} # not always correct
+
+    # versionfile_source is the relative path from the top of the source tree
+    # (where the .git directory might live) to this file. Invert this to find
+    # the root from __file__.
+    root = here
+    if IN_LONG_VERSION_PY:
+        for i in range(len(versionfile_source.split("/"))):
+            root = os.path.dirname(root)
+    else:
+        root = os.path.dirname(here)
+    if not os.path.exists(os.path.join(root, ".git")):
+        if verbose:
+            print("no .git in %s" % root)
+        return {}
+
+    GIT = "git"
+    if sys.platform == "win32":
+        GIT = "git.cmd"
+    stdout = run_command([GIT, "describe", "--tags", "--dirty", "--always"],
+                         cwd=root)
+    if stdout is None:
+        return {}
+    if not stdout.startswith(tag_prefix):
+        if verbose:
+            print("tag '%s' doesn't start with prefix '%s'" % (stdout, tag_prefix))
+        return {}
+    tag = stdout[len(tag_prefix):]
+    stdout = run_command([GIT, "rev-parse", "HEAD"], cwd=root)
+    if stdout is None:
+        return {}
+    full = stdout.strip()
+    if tag.endswith("-dirty"):
+        full += "-dirty"
+    return {"version": tag, "full": full}
+
+
+def versions_from_parentdir(parentdir_prefix, versionfile_source, verbose=False):
+    if IN_LONG_VERSION_PY:
+        # We're running from _version.py. If it's from a source tree
+        # (execute-in-place), we can work upwards to find the root of the
+        # tree, and then check the parent directory for a version string. If
+        # it's in an installed application, there's no hope.
+        try:
+            here = os.path.abspath(__file__)
+        except NameError:
+            # py2exe/bbfreeze/non-CPython don't have __file__
+            return {} # without __file__, we have no hope
+        # versionfile_source is the relative path from the top of the source
+        # tree to _version.py. Invert this to find the root from __file__.
+        root = here
+        for i in range(len(versionfile_source.split("/"))):
+            root = os.path.dirname(root)
+    else:
+        # we're running from versioneer.py, which means we're running from
+        # the setup.py in a source tree. sys.argv[0] is setup.py in the root.
+        here = os.path.abspath(sys.argv[0])
+        root = os.path.dirname(here)
+
+    # Source tarballs conventionally unpack into a directory that includes
+    # both the project name and a version string.
+    dirname = os.path.basename(root)
+    if not dirname.startswith(parentdir_prefix):
+        if verbose:
+            print("guessing rootdir is '%s', but '%s' doesn't start with prefix '%s'" %
+                  (root, dirname, parentdir_prefix))
+        return None
+    return {"version": dirname[len(parentdir_prefix):], "full": ""}
+
+tag_prefix = "nilmdb-"
+parentdir_prefix = "nilmdb-"
+versionfile_source = "nilmdb/_version.py"
+
+def get_versions(default={"version": "unknown", "full": ""}, verbose=False):
+    variables = { "refnames": git_refnames, "full": git_full }
+    ver = versions_from_expanded_variables(variables, tag_prefix, verbose)
+    if not ver:
+        ver = versions_from_vcs(tag_prefix, versionfile_source, verbose)
+    if not ver:
+        ver = versions_from_parentdir(parentdir_prefix, versionfile_source,
+                                      verbose)
+    if not ver:
+        ver = default
+    return ver
+

nilmdb/client/__init__.py

@@ -0,0 +1,4 @@
+"""nilmdb.client"""
+
+from nilmdb.client.client import Client
+from nilmdb.client.errors import ClientError, ServerError, Error

nilmdb/client/client.py

@@ -0,0 +1,379 @@
+# -*- coding: utf-8 -*-
+
+"""Class for performing HTTP client requests via libcurl"""
+
+import nilmdb
+import nilmdb.utils
+import nilmdb.client.httpclient
+
+import time
+import simplejson as json
+import contextlib
+
+def float_to_string(f):
+    """Use repr to maintain full precision in the string output."""
+    return repr(float(f))
+
+def extract_timestamp(line):
+    """Extract just the timestamp from a line of data text"""
+    return float(line.split()[0])
+
+class Client(object):
+    """Main client interface to the Nilm database."""
+
+    def __init__(self, url):
+        self.http = nilmdb.client.httpclient.HTTPClient(url)
+
+    # __enter__/__exit__ allow this class to be a context manager
+    def __enter__(self):
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        self.close()
+
+    def _json_param(self, data):
+        """Return compact json-encoded version of parameter"""
+        return json.dumps(data, separators=(',',':'))
+
+    def close(self):
+        """Close the connection; safe to call multiple times"""
+        self.http.close()
+
+    def geturl(self):
+        """Return the URL we're using"""
+        return self.http.baseurl
+
+    def version(self):
+        """Return server version"""
+        return self.http.get("version")
+
+    def dbinfo(self):
+        """Return server database info (path, size, free space)
+        as a dictionary."""
+        return self.http.get("dbinfo")
+
+    def stream_list(self, path = None, layout = None):
+        params = {}
+        if path is not None:
+            params["path"] = path
+        if layout is not None:
+            params["layout"] = layout
+        return self.http.get("stream/list", params)
+
+    def stream_get_metadata(self, path, keys = None):
+        params = { "path": path }
+        if keys is not None:
+            params["key"] = keys
+        return self.http.get("stream/get_metadata", params)
+
+    def stream_set_metadata(self, path, data):
+        """Set stream metadata from a dictionary, replacing all existing
+        metadata."""
+        params = {
+            "path": path,
+            "data": self._json_param(data)
+            }
+        return self.http.get("stream/set_metadata", params)
+
+    def stream_update_metadata(self, path, data):
+        """Update stream metadata from a dictionary"""
+        params = {
+            "path": path,
+            "data": self._json_param(data)
+            }
+        return self.http.get("stream/update_metadata", params)
+
+    def stream_create(self, path, layout):
+        """Create a new stream"""
+        params = { "path": path,
+                   "layout" : layout }
+        return self.http.get("stream/create", params)
+
+    def stream_destroy(self, path):
+        """Delete stream and its contents"""
+        params = { "path": path }
+        return self.http.get("stream/destroy", params)
+
+    def stream_remove(self, path, start = None, end = None):
+        """Remove data from the specified time range"""
+        params = {
+            "path": path
+        }
+        if start is not None:
+            params["start"] = float_to_string(start)
+        if end is not None:
+            params["end"] = float_to_string(end)
+        return self.http.get("stream/remove", params)
+
+    @contextlib.contextmanager
+    def stream_insert_context(self, path, start = None, end = None):
+        """Return a context manager that allows data to be efficiently
+        inserted into a stream in a piecewise manner.  Data is be provided
+        as single lines, and is aggregated and sent to the server in larger
+        chunks as necessary.  Data lines must match the database layout for
+        the given path, and end with a newline.
+
+        Example:
+          with client.stream_insert_context('/path', start, end) as ctx:
+            ctx.insert_line('1234567890.0 1 2 3 4\\n')
+            ctx.insert_line('1234567891.0 1 2 3 4\\n')
+
+        For more details, see help for nilmdb.client.client.StreamInserter
+
+        This may make multiple requests to the server, if the data is
+        large enough or enough time has passed between insertions.
+        """
+        ctx = StreamInserter(self, path, start, end)
+        yield ctx
+        ctx.finalize()
+
+    def stream_insert(self, path, data, start = None, end = None):
+        """Insert rows of data into a stream.  data should be an
+        iterable object that provides ASCII data that matches the
+        database layout for path.  See stream_insert_context for
+        details on the 'start' and 'end' parameters."""
+        with self.stream_insert_context(path, start, end) as ctx:
+            ctx.insert_iter(data)
+        return ctx.last_response
+
+    def stream_insert_block(self, path, block, start, end):
+        """Insert an entire block of data into a stream.  Like
+        stream_insert, except 'block' contains multiple lines of ASCII
+        text and is sent in one single chunk."""
+        params = { "path": path,
+                   "start": float_to_string(start),
+                   "end": float_to_string(end) }
+        return self.http.put("stream/insert", block, params)
+
+    def stream_intervals(self, path, start = None, end = None):
+        """
+        Return a generator that yields each stream interval.
+        """
+        params = {
+            "path": path
+        }
+        if start is not None:
+            params["start"] = float_to_string(start)
+        if end is not None:
+            params["end"] = float_to_string(end)
+        return self.http.get_gen("stream/intervals", params, retjson = True)
+
+    def stream_extract(self, path, start = None, end = None, count = False):
+        """
+        Extract data from a stream.  Returns a generator that yields
+        lines of ASCII-formatted data that matches the database
+        layout for the given path.
+
+        Specify count = True to return a count of matching data points
+        rather than the actual data.  The output format is unchanged.
+        """
+        params = {
+            "path": path,
+        }
+        if start is not None:
+            params["start"] = float_to_string(start)
+        if end is not None:
+            params["end"] = float_to_string(end)
+        if count:
+            params["count"] = 1
+
+        return self.http.get_gen("stream/extract", params, retjson = False)
+
+    def stream_count(self, path, start = None, end = None):
+        """
+        Return the number of rows of data in the stream that satisfy
+        the given timestamps.
+        """
+        counts = list(self.stream_extract(path, start, end, count = True))
+        return int(counts[0])
+
+class StreamInserter(object):
+    """Object returned by stream_insert_context() that manages
+    the insertion of rows of data into a particular path.
+
+    The basic data flow is that we are filling a contiguous interval
+    on the server, with no gaps, that extends from timestamp 'start'
+    to timestamp 'end'.  Data timestamps satisfy 'start <= t < end'.
+    Data is provided by the user one line at a time with
+    .insert_line() or .insert_iter().
+
+    1. The first inserted line begins a new interval that starts at
+    'start'.  If 'start' is not given, it is deduced from the first
+    line's timestamp.
+
+    2. Subsequent lines go into the same contiguous interval.  As lines
+    are inserted, this routine may make multiple insertion requests to
+    the server, but will structure the timestamps to leave no gaps.
+
+    3. The current contiguous interval can be completed by manually
+    calling .finalize(), which the context manager will also do
+    automatically.  This will send any remaining data to the server,
+    using the 'end' timestamp to end the interval.
+
+    After a .finalize(), inserting new data goes back to step 1.
+
+    .update_start() can be called before step 1 to change the start
+    time for the interval.  .update_end() can be called before step 3
+    to change the end time for the interval.
+    """
+
+    # See design.md for a discussion of how much data to send.
+    # These are soft limits -- actual data might be rounded up.
+    # We send when we have a certain amount of data queued, or
+    # when a certain amount of time has passed since the last send.
+    _max_data = 1048576
+    _max_time = 30
+
+    # Delta to add to the final timestamp, if "end" wasn't given
+    _end_epsilon = 1e-6
+
+    def __init__(self, client, path, start = None, end = None):
+        """'http' is the httpclient object.  'path' is the database
+        path to insert to.  'start' and 'end' are used for the first
+        contiguous interval."""
+        self.last_response = None
+
+        self._client = client
+        self._path = path
+
+        # Start and end for the overall contiguous interval we're
+        # filling
+        self._interval_start = start
+        self._interval_end = end
+
+        # Data for the specific block we're building up to send
+        self._block_data = []
+        self._block_len = 0
+        self._block_start = None
+
+        # Time of last request
+        self._last_time = time.time()
+
+        # We keep a buffer of the two most recently inserted lines.
+        # Only the older one actually gets processed; the newer one
+        # is used to "look-ahead" to the next timestamp if we need
+        # to internally split an insertion into two requests.
+        self._line_old = None
+        self._line_new = None
+
+    def insert_iter(self, iter):
+        """Insert all lines of ASCII formatted data from the given
+        iterable.  Lines must be terminated with '\\n'."""
+        for line in iter:
+            self.insert_line(line)
+
+    def insert_line(self, line, allow_intermediate = True):
+        """Insert a single line of ASCII formatted data.  Line
+        must be terminated with '\\n'."""
+        if line and (len(line) < 1 or line[-1] != '\n'):
+            raise ValueError("lines must end in with a newline character")
+
+        # Store this new line, but process the previous (old) one.
+        # This lets us "look ahead" to the next line.
+        self._line_old = self._line_new
+        self._line_new = line
+        if self._line_old is None:
+            return
+
+        # If starting a new block, pull out the timestamp if needed.
+        if self._block_start is None:
+            if self._interval_start is not None:
+                # User provided a start timestamp.  Use it once, then
+                # clear it for the next block.
+                self._block_start = self._interval_start
+                self._interval_start = None
+            else:
+                # Extract timestamp from the first row
+                self._block_start = extract_timestamp(self._line_old)
+
+        # Save the line
+        self._block_data.append(self._line_old)
+        self._block_len += len(self._line_old)
+
+        if allow_intermediate:
+            # Send an intermediate block to the server if needed.
+            elapsed = time.time() - self._last_time
+            if (self._block_len > self._max_data) or (elapsed > self._max_time):
+                self._send_block_intermediate()
+
+    def update_start(self, start):
+        """Update the start time for the next contiguous interval.
+        Call this before starting to insert data for a new interval,
+        for example, after .finalize()"""
+        self._interval_start = start
+
+    def update_end(self, end):
+        """Update the end time for the current contiguous interval.
+        Call this before .finalize()"""
+        self._interval_end = end
+
+    def finalize(self):
+        """Stop filling the current contiguous interval.
+        All outstanding data will be sent, and the interval end
+        time of the interval will be taken from the 'end' argument
+        used when initializing this class, or the most recent
+        value passed to update_end(), or the last timestamp plus
+        a small epsilon value if no other endpoint was provided.
+
+        If more data is inserted after a finalize(), it will become
+        part of a new interval and there may be a gap left in-between."""
+        # Special marker tells insert_line that this is the end
+        self.insert_line(None, allow_intermediate = False)
+
+        if self._block_len > 0:
+            # We have data pending, so send the final block
+            self._send_block_final()
+        elif None not in (self._interval_start, self._interval_end):
+            # We have no data, but enough information to create an
+            # empty interval.
+            self._block_start = self._interval_start
+            self._interval_start = None
+            self._send_block_final()
+        else:
+            # No data, and no timestamps to use to create an empty
+            # interval.
+            pass
+
+        # Make sure both timestamps are emptied for future intervals.
+        self._interval_start = None
+        self._interval_end = None
+
+    def _send_block_intermediate(self):
+        """Send data, when we still have more data to send.
+        Use the timestamp from the next line, so that the blocks
+        are contiguous."""
+        block_end = extract_timestamp(self._line_new)
+        if self._interval_end is not None and block_end > self._interval_end:
+            # Something's fishy -- the timestamp we found is after
+            # the user's specified end.  Limit it here, and the
+            # server will return an error.
+            block_end = self._interval_end
+        self._send_block(block_end)
+
+    def _send_block_final(self):
+        """Send data, when this is the last block for the interval.
+        There is no next line, so figure out the actual interval end
+        using interval_end or end_epsilon."""
+        if self._interval_end is not None:
+            # Use the user's specified end timestamp
+            block_end = self._interval_end
+            # Clear it in case we send more intervals in the future.
+            self._interval_end = None
+        else:
+            # Add an epsilon to the last timestamp we saw
+            block_end = extract_timestamp(self._line_old) + self._end_epsilon
+        self._send_block(block_end)
+
+    def _send_block(self, block_end):
+        """Send current block to the server"""
+        self.last_response = self._client.stream_insert_block(
+            self._path, "".join(self._block_data),
+            self._block_start, block_end)
+
+        # Clear out the block
+        self._block_data = []
+        self._block_len = 0
+        self._block_start = None
+
+        # Note when we sent it
+        self._last_time = time.time()

nilmdb/client/errors.py

@@ -0,0 +1,33 @@
+"""HTTP client errors"""
+
+from nilmdb.utils.printf import *
+
+class Error(Exception):
+    """Base exception for both ClientError and ServerError responses"""
+    def __init__(self,
+                 status = "Unspecified error",
+                 message = None,
+                 url = None,
+                 traceback = None):
+        Exception.__init__(self, status)
+        self.status = status     # e.g. "400 Bad Request"
+        self.message = message   # textual message from the server
+        self.url = url           # URL we were requesting
+        self.traceback = traceback # server traceback, if available
+    def _format_error(self, show_url):
+        s = sprintf("[%s]", self.status)
+        if self.message:
+            s += sprintf(" %s", self.message)
+        if show_url and self.url: # pragma: no cover
+            s += sprintf(" (%s)", self.url)
+        if self.traceback: # pragma: no cover
+            s += sprintf("\nServer traceback:\n%s", self.traceback)
+        return s
+    def __str__(self):
+        return self._format_error(show_url = False)
+    def __repr__(self): # pragma: no cover
+        return self._format_error(show_url = True)
+class ClientError(Error):
+    pass
+class ServerError(Error):
+    pass

nilmdb/client/httpclient.py

@@ -0,0 +1,208 @@
+"""HTTP client library"""
+
+import nilmdb
+import nilmdb.utils
+from nilmdb.client.errors import ClientError, ServerError, Error
+
+import simplejson as json
+import urlparse
+import pycurl
+import cStringIO
+
+class HTTPClient(object):
+    """Class to manage and perform HTTP requests from the client"""
+    def __init__(self, baseurl = ""):
+        """If baseurl is supplied, all other functions that take
+        a URL can be given a relative URL instead."""
+        # Verify / clean up URL
+        reparsed = urlparse.urlparse(baseurl).geturl()
+        if '://' not in reparsed:
+            reparsed = urlparse.urlparse("http://" + baseurl).geturl()
+        self.baseurl = reparsed
+        self.curl = pycurl.Curl()
+        self.curl.setopt(pycurl.SSL_VERIFYHOST, 2)
+        self.curl.setopt(pycurl.FOLLOWLOCATION, 1)
+        self.curl.setopt(pycurl.MAXREDIRS, 5)
+        self._setup_url()
+
+    def _setup_url(self, url = "", params = ""):
+        url = urlparse.urljoin(self.baseurl, url)
+        if params:
+            url = urlparse.urljoin(
+                url, "?" + nilmdb.utils.urllib.urlencode(params))
+        self.curl.setopt(pycurl.URL, url)
+        self.url = url
+
+    def _check_busy_and_set_upload(self, upload):
+        """Sets the pycurl.UPLOAD option, but also raises a more
+        friendly exception if the client is already serving a request."""
+        try:
+            self.curl.setopt(pycurl.UPLOAD, upload)
+        except pycurl.error as e:
+            if "is currently running" in str(e):
+                raise Exception("Client is already performing a request, and "
+                                "nesting calls is not supported.")
+            else: # pragma: no cover (shouldn't happen)
+                raise
+
+    def _check_error(self, body = None):
+        code = self.curl.getinfo(pycurl.RESPONSE_CODE)
+        if code == 200:
+            return
+        # Default variables for exception.  We use the entire body as
+        # the default message, in case we can't extract it from a JSON
+        # response.
+        args = { "url" : self.url,
+                 "status" : str(code),
+                 "message" : body,
+                 "traceback" : None }
+        try:
+            # Fill with server-provided data if we can
+            jsonerror = json.loads(body)
+            args["status"] = jsonerror["status"]
+            args["message"] = jsonerror["message"]
+            args["traceback"] = jsonerror["traceback"]
+        except Exception: # pragma: no cover
+            pass
+        if code >= 400 and code <= 499:
+            raise ClientError(**args)
+        else: # pragma: no cover
+            if code >= 500 and code <= 599:
+                if args["message"] is None:
+                    args["message"] = ("(no message; try disabling " +
+                                       "response.stream option in " +
+                                       "nilmdb.server for better debugging)")
+                raise ServerError(**args)
+            else:
+                raise Error(**args)
+
+    def _req_generator(self, url, params):
+        """
+        Like self._req(), but runs the perform in a separate thread.
+        It returns a generator that spits out arbitrary-sized chunks
+        of the resulting data, instead of using the WRITEFUNCTION
+        callback.
+        """
+        self._setup_url(url, params)
+        self._status = None
+        error_body = ""
+        self._headers = ""
+        def header_callback(data):
+            if self._status is None:
+                self._status = int(data.split(" ")[1])
+            self._headers += data
+        self.curl.setopt(pycurl.HEADERFUNCTION, header_callback)
+        def perform(callback):
+            self.curl.setopt(pycurl.WRITEFUNCTION, callback)
+            self.curl.perform()
+        try:
+            with nilmdb.utils.Iteratorizer(perform, curl_hack = True) as it:
+                for i in it:
+                    if self._status == 200:
+                        # If we had a 200 response, yield the data to caller.
+                        yield i
+                    else:
+                        # Otherwise, collect it into an error string.
+                        error_body += i
+        except pycurl.error as e:
+            raise ServerError(status = "502 Error",
+                              url = self.url,
+                              message = e[1])
+        # Raise an exception if there was an error
+        self._check_error(error_body)
+
+    def _req(self, url, params):
+        """
+        GET or POST that returns raw data.  Returns the body
+        data as a string, or raises an error if it contained an error.
+        """
+        self._setup_url(url, params)
+        body = cStringIO.StringIO()
+        self.curl.setopt(pycurl.WRITEFUNCTION, body.write)
+        self._headers = ""
+        def header_callback(data):
+            self._headers += data
+        self.curl.setopt(pycurl.HEADERFUNCTION, header_callback)
+        try:
+            self.curl.perform()
+        except pycurl.error as e:
+            raise ServerError(status = "502 Error",
+                              url = self.url,
+                              message = e[1])
+        body_str = body.getvalue()
+        # Raise an exception if there was an error
+        self._check_error(body_str)
+        return body_str
+
+    def close(self):
+        self.curl.close()
+
+    def _iterate_lines(self, it):
+        """
+        Given an iterator that returns arbitrarily-sized chunks
+        of data, return '\n'-delimited lines of text
+        """
+        partial = ""
+        for chunk in it:
+            partial += chunk
+            lines = partial.split("\n")
+            for line in lines[0:-1]:
+                yield line
+            partial = lines[-1]
+        if partial != "":
+            yield partial
+
+    # Non-generator versions
+    def _doreq(self, url, params, retjson):
+        """
+        Perform a request, and return the body.
+
+        url: URL to request (relative to baseurl)
+        params: dictionary of query parameters
+        retjson: expect JSON and return python objects instead of string
+        """
+        out = self._req(url, params)
+        if retjson:
+            return json.loads(out)
+        return out
+
+    def get(self, url, params = None, retjson = True):
+        """Simple GET"""
+        self._check_busy_and_set_upload(0)
+        return self._doreq(url, params, retjson)
+
+    def put(self, url, postdata, params = None, retjson = True):
+        """Simple PUT"""
+        self._check_busy_and_set_upload(1)
+        self._setup_url(url, params)
+        data = cStringIO.StringIO(postdata)
+        self.curl.setopt(pycurl.READFUNCTION, data.read)
+        return self._doreq(url, params, retjson)
+
+    # Generator versions
+    def _doreq_gen(self, url, params, retjson):
+        """
+        Perform a request, and return lines of the body in a generator.
+
+        url: URL to request (relative to baseurl)
+        params: dictionary of query parameters
+        retjson: expect JSON and yield python objects instead of strings
+        """
+        for line in self._iterate_lines(self._req_generator(url, params)):
+            if retjson:
+                yield json.loads(line)
+            else:
+                yield line
+
+    def get_gen(self, url, params = None, retjson = True):
+        """Simple GET, returning a generator"""
+        self._check_busy_and_set_upload(0)
+        return self._doreq_gen(url, params, retjson)
+
+    def put_gen(self, url, postdata, params = None, retjson = True):
+        """Simple PUT, returning a generator"""
+        self._check_busy_and_set_upload(1)
+        self._setup_url(url, params)
+        data = cStringIO.StringIO(postdata)
+        self.curl.setopt(pycurl.READFUNCTION, data.read)
+        return self._doreq_gen(url, params, retjson)

nilmdb/cmdline/__init__.py

@@ -0,0 +1,3 @@
+"""nilmdb.cmdline"""
+
+from nilmdb.cmdline.cmdline import Cmdline

nilmdb/cmdline/cmdline.py

@@ -0,0 +1,151 @@
+"""Command line client functionality"""
+
+import nilmdb
+from nilmdb.utils.printf import *
+from nilmdb.utils import datetime_tz
+
+import sys
+import re
+import argparse
+from argparse import ArgumentDefaultsHelpFormatter as def_form
+
+# Valid subcommands.  Defined in separate files just to break
+# things up -- they're still called with Cmdline as self.
+subcommands = [ "info", "create", "list", "metadata", "insert", "extract",
+                "remove", "destroy" ]
+
+# Import the subcommand modules
+subcmd_mods = {}
+for cmd in subcommands:
+    subcmd_mods[cmd] = __import__("nilmdb.cmdline." + cmd, fromlist = [ cmd ])
+
+class JimArgumentParser(argparse.ArgumentParser):
+    def error(self, message):
+        self.print_usage(sys.stderr)
+        self.exit(2, sprintf("error: %s\n", message))
+
+class Cmdline(object):
+
+    def __init__(self, argv = None):
+        self.argv = argv or sys.argv[1:]
+        self.client = None
+
+    def arg_time(self, toparse):
+        """Parse a time string argument"""
+        try:
+            return self.parse_time(toparse).totimestamp()
+        except ValueError as e:
+            raise argparse.ArgumentTypeError(sprintf("%s \"%s\"",
+                                                     str(e), toparse))
+
+    def parse_time(self, toparse):
+        """
+        Parse a free-form time string and return a datetime_tz object.
+        If the string doesn't contain a timestamp, the current local
+        timezone is assumed (e.g. from the TZ env var).
+        """
+        # If string isn't "now" and doesn't contain at least 4 digits,
+        # consider it invalid.  smartparse might otherwise accept
+        # empty strings and strings with just separators.
+        if toparse != "now" and len(re.findall(r"\d", toparse)) < 4:
+            raise ValueError("not enough digits for a timestamp")
+
+        # Try to just parse the time as given
+        try:
+            return datetime_tz.datetime_tz.smartparse(toparse)
+        except ValueError:
+            pass
+
+        # Try to extract a substring in a condensed format that we expect
+        # to see in a filename or header comment
+        res = re.search(r"(^|[^\d])("            # non-numeric or SOL
+                        r"(199\d|2\d\d\d)"       # year
+                        r"[-/]?"                 # separator
+                        r"(0[1-9]|1[012])"       # month
+                        r"[-/]?"                 # separator
+                        r"([012]\d|3[01])"       # day
+                        r"[-T ]?"                # separator
+                        r"([01]\d|2[0-3])"       # hour
+                        r"[:]?"                  # separator
+                        r"([0-5]\d)"             # minute
+                        r"[:]?"                  # separator
+                        r"([0-5]\d)?"            # second
+                        r"([-+]\d\d\d\d)?"       # timezone
+                        r")", toparse)
+        if res is not None:
+            try:
+                return datetime_tz.datetime_tz.smartparse(res.group(2))
+            except ValueError:
+                pass
+
+        # Could also try to successively parse substrings, but let's
+        # just give up for now.
+        raise ValueError("unable to parse timestamp")
+
+    def time_string(self, timestamp):
+        """
+        Convert a Unix timestamp to a string for printing, using the
+        local timezone for display (e.g. from the TZ env var).
+        """
+        dt = datetime_tz.datetime_tz.fromtimestamp(timestamp)
+        return dt.strftime("%a, %d %b %Y %H:%M:%S.%f %z")
+
+    def parser_setup(self):
+        self.parser = JimArgumentParser(add_help = False,
+                                        formatter_class = def_form)
+
+        group = self.parser.add_argument_group("General options")
+        group.add_argument("-h", "--help", action='help',
+                           help='show this help message and exit')
+        group.add_argument("-V", "--version", action="version",
+                           version = nilmdb.__version__)
+
+        group = self.parser.add_argument_group("Server")
+        group.add_argument("-u", "--url", action="store",
+                           default="http://localhost:12380/",
+                           help="NilmDB server URL (default: %(default)s)")
+
+        sub = self.parser.add_subparsers(title="Commands",
+                                         dest="command",
+                                         description="Specify --help after "
+                                         "the command for command-specific "
+                                         "options.")
+
+        # Set up subcommands (defined in separate files)
+        for cmd in subcommands:
+            subcmd_mods[cmd].setup(self, sub)
+
+    def die(self, formatstr, *args):
+        fprintf(sys.stderr, formatstr + "\n", *args)
+        if self.client:
+            self.client.close()
+        sys.exit(-1)
+
+    def run(self):
+        # Clear cached timezone, so that we can pick up timezone changes
+        # while running this from the test suite.
+        datetime_tz._localtz = None
+
+        # Run parser
+        self.parser_setup()
+        self.args = self.parser.parse_args(self.argv)
+
+        # Run arg verify handler if there is one
+        if "verify" in self.args:
+            self.args.verify(self)
+
+        self.client = nilmdb.Client(self.args.url)
+
+        # Make a test connection to make sure things work
+        try:
+            server_version = self.client.version()
+        except nilmdb.client.Error as e:
+            self.die("error connecting to server: %s", str(e))
+
+        # Now dispatch client request to appropriate function.  Parser
+        # should have ensured that we don't have any unknown commands
+        # here.
+        retval = self.args.handler(self) or 0
+
+        self.client.close()
+        sys.exit(retval)

nilmdb/cmdline/create.py

@@ -0,0 +1,35 @@
+from nilmdb.utils.printf import *
+import nilmdb
+import nilmdb.client
+
+from argparse import RawDescriptionHelpFormatter as raw_form
+
+def setup(self, sub):
+    cmd = sub.add_parser("create", help="Create a new stream",
+                         formatter_class = raw_form,
+                         description="""
+Create a new empty stream at the specified path and with the specified
+layout type.
+
+Layout types are of the format: type_count
+
+  'type' is a data type like 'float32', 'float64', 'uint16', 'int32', etc.
+
+  'count' is the number of columns of this type.
+
+  For example, 'float32_8' means the data for this stream has 8 columns of
+  32-bit floating point values.
+""")
+    cmd.set_defaults(handler = cmd_create)
+    group = cmd.add_argument_group("Required arguments")
+    group.add_argument("path",
+                       help="Path (in database) of new stream, e.g. /foo/bar")
+    group.add_argument("layout",
+                       help="Layout type for new stream, e.g. float32_8")
+
+def cmd_create(self):
+    """Create new stream"""
+    try:
+        self.client.stream_create(self.args.path, self.args.layout)
+    except nilmdb.client.ClientError as e:
+        self.die("error creating stream: %s", str(e))

nilmdb/cmdline/destroy.py

@@ -0,0 +1,25 @@
+from nilmdb.utils.printf import *
+import nilmdb
+import nilmdb.client
+
+from argparse import ArgumentDefaultsHelpFormatter as def_form
+
+def setup(self, sub):
+    cmd = sub.add_parser("destroy", help="Delete a stream and all data",
+                         formatter_class = def_form,
+                         description="""
+                         Destroy the stream at the specified path.  All
+                         data and metadata related to the stream is
+                         permanently deleted.
+                         """)
+    cmd.set_defaults(handler = cmd_destroy)
+    group = cmd.add_argument_group("Required arguments")
+    group.add_argument("path",
+                       help="Path of the stream to delete, e.g. /foo/bar")
+
+def cmd_destroy(self):
+    """Destroy stream"""
+    try:
+        self.client.stream_destroy(self.args.path)
+    except nilmdb.client.ClientError as e:
+        self.die("error destroying stream: %s", str(e))

nilmdb/cmdline/extract.py

@@ -0,0 +1,72 @@
+from __future__ import print_function
+from nilmdb.utils.printf import *
+import nilmdb.client
+
+def setup(self, sub):
+    cmd = sub.add_parser("extract", help="Extract data",
+                         description="""
+                         Extract data from a stream.
+                         """)
+    cmd.set_defaults(verify = cmd_extract_verify,
+                     handler = cmd_extract)
+
+    group = cmd.add_argument_group("Data selection")
+    group.add_argument("path",
+                       help="Path of stream, e.g. /foo/bar")
+    group.add_argument("-s", "--start", required=True,
+                       metavar="TIME", type=self.arg_time,
+                       help="Starting timestamp (free-form, inclusive)")
+    group.add_argument("-e", "--end", required=True,
+                       metavar="TIME", type=self.arg_time,
+                       help="Ending timestamp (free-form, noninclusive)")
+
+    group = cmd.add_argument_group("Output format")
+    group.add_argument("-b", "--bare", action="store_true",
+                       help="Exclude timestamps from output lines")
+    group.add_argument("-a", "--annotate", action="store_true",
+                       help="Include comments with some information "
+                       "about the stream")
+    group.add_argument("-T", "--timestamp-raw", action="store_true",
+                       help="Show raw timestamps in annotated information")
+    group.add_argument("-c", "--count", action="store_true",
+                       help="Just output a count of matched data points")
+
+def cmd_extract_verify(self):
+    if self.args.start is not None and self.args.end is not None:
+        if self.args.start > self.args.end:
+            self.parser.error("start is after end")
+
+def cmd_extract(self):
+    streams = self.client.stream_list(self.args.path)
+    if len(streams) != 1:
+        self.die("error getting stream info for path %s", self.args.path)
+    layout = streams[0][1]
+
+    if self.args.timestamp_raw:
+        time_string = repr
+    else:
+        time_string = self.time_string
+
+    if self.args.annotate:
+        printf("# path: %s\n", self.args.path)
+        printf("# layout: %s\n", layout)
+        printf("# start: %s\n", time_string(self.args.start))
+        printf("# end: %s\n", time_string(self.args.end))
+
+    printed = False
+    for dataline in self.client.stream_extract(self.args.path,
+                                               self.args.start,
+                                               self.args.end,
+                                               self.args.count):
+        if self.args.bare and not self.args.count:
+            # Strip timestamp (first element).  Doesn't make sense
+            # if we are only returning a count.
+            dataline = ' '.join(dataline.split(' ')[1:])
+        print(dataline)
+        printed = True
+    if not printed:
+        if self.args.annotate:
+            printf("# no data\n")
+        return 2
+
+    return 0

nilmdb/cmdline/info.py

@@ -0,0 +1,24 @@
+import nilmdb
+from nilmdb.utils.printf import *
+from nilmdb.utils import human_size
+
+from argparse import ArgumentDefaultsHelpFormatter as def_form
+
+def setup(self, sub):
+    cmd = sub.add_parser("info", help="Server information",
+                         formatter_class = def_form,
+                         description="""
+                         List information about the server, like
+                         version.
+                         """)
+    cmd.set_defaults(handler = cmd_info)
+
+def cmd_info(self):
+    """Print info about the server"""
+    printf("Client version: %s\n", nilmdb.__version__)
+    printf("Server version: %s\n", self.client.version())
+    printf("Server URL: %s\n", self.client.geturl())
+    dbinfo = self.client.dbinfo()
+    printf("Server database path: %s\n", dbinfo["path"])
+    printf("Server database size: %s\n", human_size(dbinfo["size"]))
+    printf("Server database free space: %s\n", human_size(dbinfo["free"]))

nilmdb/cmdline/insert.py

@@ -0,0 +1,103 @@
+from nilmdb.utils.printf import *
+import nilmdb
+import nilmdb.client
+import nilmdb.utils.timestamper as timestamper
+
+import sys
+
+def setup(self, sub):
+    cmd = sub.add_parser("insert", help="Insert data",
+                         description="""
+                         Insert data into a stream.
+                         """)
+    cmd.set_defaults(handler = cmd_insert)
+    cmd.add_argument("-q", "--quiet", action='store_true',
+                     help='suppress unnecessary messages')
+
+    group = cmd.add_argument_group("Timestamping",
+                                   description="""
+                                   If timestamps are already provided in the
+                                   input date, use --none.  Otherwise,
+                                   provide --start, or use --filename to
+                                   try to deduce timestamps from the file.
+
+                                   Set the TZ environment variable to change
+                                   the default timezone.
+                                   """)
+
+    group.add_argument("-r", "--rate", type=float,
+                       help="""
+                       If needed, rate in Hz (required when using --start)
+                       """)
+    exc = group.add_mutually_exclusive_group()
+    exc.add_argument("-s", "--start",
+                     metavar="TIME", type=self.arg_time,
+                     help="Starting timestamp (free-form)")
+    exc.add_argument("-f", "--filename", action="store_true",
+                     help="""
+                     Use filenames to determine start time
+                     (default, if filenames are provided)
+                     """)
+    exc.add_argument("-n", "--none", action="store_true",
+                     help="Timestamp is already present, don't add one")
+
+    group = cmd.add_argument_group("Required parameters")
+    group.add_argument("path",
+                       help="Path of stream, e.g. /foo/bar")
+    group.add_argument("file", nargs="*", default=['-'],
+                       help="File(s) to insert (default: - (stdin))")
+
+def cmd_insert(self):
+    # Find requested stream
+    streams = self.client.stream_list(self.args.path)
+    if len(streams) != 1:
+        self.die("error getting stream info for path %s", self.args.path)
+
+    if self.args.start and len(self.args.file) != 1:
+        self.die("error: --start can only be used with one input file")
+
+    for filename in self.args.file:
+        if filename == '-':
+            infile = sys.stdin
+        else:
+            try:
+                infile = open(filename, "r")
+            except IOError:
+                self.die("error opening input file %s", filename)
+
+        # Build a timestamper for this file
+        if self.args.none:
+            ts = timestamper.TimestamperNull(infile)
+        else:
+            if self.args.start:
+                start = self.args.start
+            else:
+                try:
+                    start = self.parse_time(filename)
+                except ValueError:
+                    self.die("error extracting time from filename '%s'",
+                             filename)
+
+            if not self.args.rate:
+                self.die("error: --rate is needed, but was not specified")
+            rate = self.args.rate
+
+            ts = timestamper.TimestamperRate(infile, start, rate)
+
+        # Print info
+        if not self.args.quiet:
+            printf("Input file: %s\n", filename)
+            printf("Timestamper: %s\n", str(ts))
+
+        # Insert the data
+        try:
+            self.client.stream_insert(self.args.path, ts)
+        except nilmdb.client.Error as e:
+            # TODO: It would be nice to be able to offer better errors
+            # here, particularly in the case of overlap, which just shows
+            # ugly bracketed ranges of 16-digit numbers and a mangled URL.
+            # Need to consider adding something like e.prettyprint()
+            # that is smarter about the contents of the error.
+            self.die("error inserting data: %s", str(e))
+
+    return

nilmdb/cmdline/list.py

@@ -0,0 +1,77 @@
+from nilmdb.utils.printf import *
+
+import fnmatch
+import argparse
+from argparse import ArgumentDefaultsHelpFormatter as def_form
+
+def setup(self, sub):
+    cmd = sub.add_parser("list", help="List streams",
+                         formatter_class = def_form,
+                         description="""
+                         List streams available in the database,
+                         optionally filtering by layout or path.  Wildcards
+                         are accepted.
+                         """)
+    cmd.set_defaults(verify = cmd_list_verify,
+                     handler = cmd_list)
+
+    group = cmd.add_argument_group("Stream filtering")
+    group.add_argument("-p", "--path", metavar="PATH", default="*",
+                       help="Match only this path (-p can be omitted)")
+    group.add_argument("path_positional", default="*",
+                       nargs="?", help=argparse.SUPPRESS)
+    group.add_argument("-l", "--layout", default="*",
+                       help="Match only this stream layout")
+
+    group = cmd.add_argument_group("Interval details")
+    group.add_argument("-d", "--detail", action="store_true",
+                       help="Show available data time intervals")
+    group.add_argument("-T", "--timestamp-raw", action="store_true",
+                       help="Show raw timestamps in time intervals")
+    group.add_argument("-s", "--start",
+                       metavar="TIME", type=self.arg_time,
+                       help="Starting timestamp (free-form, inclusive)")
+    group.add_argument("-e", "--end",
+                       metavar="TIME", type=self.arg_time,
+                       help="Ending timestamp (free-form, noninclusive)")
+
+def cmd_list_verify(self):
+    # A hidden "path_positional" argument lets the user leave off the
+    # "-p" when specifying the path.  Handle it here.
+    got_opt = self.args.path != "*"
+    got_pos = self.args.path_positional != "*"
+    if got_pos:
+        if got_opt:
+            self.parser.error("too many paths specified")
+        else:
+            self.args.path = self.args.path_positional
+
+    if self.args.start is not None and self.args.end is not None:
+        if self.args.start >= self.args.end:
+            self.parser.error("start must precede end")
+
+def cmd_list(self):
+    """List available streams"""
+    streams = self.client.stream_list()
+
+    if self.args.timestamp_raw:
+        time_string = repr
+    else:
+        time_string = self.time_string
+
+    for (path, layout) in streams:
+        if not (fnmatch.fnmatch(path, self.args.path) and
+                fnmatch.fnmatch(layout, self.args.layout)):
+            continue
+
+        printf("%s %s\n", path, layout)
+        if not self.args.detail:
+            continue
+
+        printed = False
+        for (start, end) in self.client.stream_intervals(path, self.args.start,
+                                                         self.args.end):
+            printf("  [ %s -> %s ]\n", time_string(start), time_string(end))
+            printed = True
+        if not printed:
+            printf("  (no intervals)\n")

nilmdb/cmdline/metadata.py

@@ -0,0 +1,65 @@
+from nilmdb.utils.printf import *
+import nilmdb
+import nilmdb.client
+
+def setup(self, sub):
+    cmd = sub.add_parser("metadata", help="Get or set stream metadata",
+                         description="""
+                         Get or set key=value metadata associated with
+                         a stream.
+                         """,
+                         usage="%(prog)s path [-g [key ...] | "
+                         "-s key=value [...] | -u key=value [...]]")
+    cmd.set_defaults(handler = cmd_metadata)
+
+    group = cmd.add_argument_group("Required arguments")
+    group.add_argument("path",
+                       help="Path of stream, e.g. /foo/bar")
+
+    group = cmd.add_argument_group("Actions")
+    exc = group.add_mutually_exclusive_group()
+    exc.add_argument("-g", "--get", nargs="*", metavar="key",
+                     help="Get metadata for specified keys (default all)")
+    exc.add_argument("-s", "--set", nargs="+", metavar="key=value",
+                     help="Replace all metadata with provided "
+                     "key=value pairs")
+    exc.add_argument("-u", "--update", nargs="+", metavar="key=value",
+                     help="Update metadata using provided "
+                     "key=value pairs")
+
+def cmd_metadata(self):
+    """Manipulate metadata"""
+    if self.args.set is not None or self.args.update is not None:
+        # Either set, or update
+        if self.args.set is not None:
+            keyvals = self.args.set
+            handler = self.client.stream_set_metadata
+        else:
+            keyvals = self.args.update
+            handler = self.client.stream_update_metadata
+
+        # Extract key=value pairs
+        data = {}
+        for keyval in keyvals:
+            kv = keyval.split('=')
+            if len(kv) != 2 or kv[0] == "":
+                self.die("error parsing key=value argument '%s'", keyval)
+            data[kv[0]] = kv[1]
+
+        # Make the call
+        try:
+            handler(self.args.path, data)
+        except nilmdb.client.ClientError as e:
+            self.die("error setting/updating metadata: %s", str(e))
+    else:
+        # Get (or unspecified)
+        keys = self.args.get or None
+        try:
+            data = self.client.stream_get_metadata(self.args.path, keys)
+        except nilmdb.client.ClientError as e:
+            self.die("error getting metadata: %s", str(e))
+        for key, value in sorted(data.items()):
+            # Omit nonexistant keys
+            if value is None:
+                value = ""
+            printf("%s=%s\n", key, value)

nilmdb/cmdline/remove.py

@@ -0,0 +1,37 @@
+from nilmdb.utils.printf import *
+import nilmdb
+import nilmdb.client
+
+def setup(self, sub):
+    cmd = sub.add_parser("remove", help="Remove data",
+                         description="""
+                         Remove all data from a specified time range within a
+                         stream.
+                         """)
+    cmd.set_defaults(handler = cmd_remove)
+
+    group = cmd.add_argument_group("Data selection")
+    group.add_argument("path",
+                       help="Path of stream, e.g. /foo/bar")
+    group.add_argument("-s", "--start", required=True,
+                       metavar="TIME", type=self.arg_time,
+                       help="Starting timestamp (free-form, inclusive)")
+    group.add_argument("-e", "--end", required=True,
+                       metavar="TIME", type=self.arg_time,
+                       help="Ending timestamp (free-form, noninclusive)")
+
+    group = cmd.add_argument_group("Output format")
+    group.add_argument("-c", "--count", action="store_true",
+                       help="Output number of data points removed")
+
+def cmd_remove(self):
+    try:
+        count = self.client.stream_remove(self.args.path,
+                                          self.args.start, self.args.end)
+    except nilmdb.client.ClientError as e:
+        self.die("error removing data: %s", str(e))
+
+    if self.args.count:
+        printf("%d\n", count)
+
+    return 0

nilmdb/fileinterval.py

@@ -1,37 +0,0 @@
-"""FileInterval
-
-An Interval that is backed with file data storage"""
-
-from nilmdb.interval import Interval, IntervalSet, IntervalError
-from datetime import datetime
-import bisect
-
-class FileInterval(Interval):
-    """Represents an interval of time and its corresponding data"""
-
-    def __init__(self, start, end, 
-                 filename, 
-                 start_offset = None, end_offset = None):
-        self.start = start
-        self.end = end
-        self.filename = filename
-        if start_offset is None:
-            start_offset = 0
-        self.start_offset = start_offset
-        if end_offset is None:
-            f = open(filename, 'rb')
-            f.seek(0, os.SEEK_END)
-            end_offset = f.tell()
-        self.end_offset = end_offset
-
-    def __setattr__(self, name, value):
-        pass
-
-    def subset(self, start, end):
-        """Return a new Interval that is a subset of this one"""
-        # TODO: Any magic regarding file/offset/length mapping for subsets
-        if (start < self.start or end > self.end):
-            raise IntervalError("not a subset")
-        return FileInterval(start, end)            
-
-    

nilmdb/interval.py

@@ -1,205 +0,0 @@
-"""Interval and IntervalSet
-
-Represents an interval of time, and a sorted set of such intervals"""
-
-from datetime import datetime
-import bisect
-
-class IntervalError(Exception):
-    """Error due to interval overlap, etc"""
-    pass
-
-class Interval(object):
-    """Represents an interval of time"""
-
-    start = None
-    end = None
-
-    def __init__(self, start, end):
-        self.start = start
-        self.end = end
-
-    def __repr__(self):
-        return "Interval(" + repr(self.start) + ", " + repr(self.end) + ")"
-
-    def __str__(self):
-        return "[" + str(self.start) + " -> " + str(self.end) + "]"
-
-    def __setattr__(self, name, value):
-        """Set attribute"""
-        # TODO: If we need to manipulate file names, offsets, lengths, etc,
-        # based on start and end time changing, maybe this is the right spot?
-        # Or we could just disallow changing it here.
-        if not isinstance(value, datetime):
-            raise IntervalError("Must set datetime values")
-        self.__dict__[name] = value
-        if (type(self.start) is type(self.end)):
-            if (self.start > self.end):
-                raise IntervalError("Interval start must precede interval end")
-
-    def __cmp__(self, other):
-        """Compare two intervals.  If non-equal, order by start then end"""
-        if not isinstance(other, Interval):
-            raise TypeError("Can't compare to non-interval")
-        if (self.start == other.start):
-            if (self.end < other.end):
-                return -1
-            if (self.end > other.end):
-                return 1
-            return 0
-        if (self.start < other.start):
-            return -1
-        return 1
-                
-    def intersects(self, other):
-        """Return True if two Interval objects intersect"""
-        if (not isinstance(other, Interval)):
-            raise TypeError("need Interval for intersection test")
-        if (self.end <= other.start or
-            self.start >= other.end):
-            return False
-        else:
-            return True
-
-    def is_adjacent(self, other):
-        """Return True if two Intervals are adjacent (same end or start)"""
-        if (not isinstance(other, Interval)):
-            raise TypeError("need Interval for adjacency test")
-        if (self.end == other.start or
-            self.start == other.end):
-            return True
-        else:
-            return False
-
-    def subset(self, start, end):
-        """Return a new Interval that is a subset of this one"""
-        # TODO: Any magic regarding file/offset/length mapping for subsets
-        if (start < self.start or end > self.end):
-            raise IntervalError("not a subset")
-        return Interval(start, end)            
-
-class IntervalSet(object):
-    """A non-intersecting set of intervals
-
-    Kept sorted internally"""
-
-    def __init__(self, iterable=None):
-        self.data = []
-        if iterable is not None:
-            if isinstance(iterable, Interval):
-                iterable = [iterable]
-            self._add_intervals(iterable)
-
-    def __iter__(self):
-        return self.data.__iter__()
-
-    def __repr__(self):
-        return "IntervalSet(" + repr(list(self.data)) + ")"
-
-    def __cmp__(self, other):
-        # compare isn't supported, they don't really have an ordering
-        raise TypeError("can't compare IntervalSets with cmp()")
-
-    def __eq__(self, other):
-        """Test equality of two IntervalSets.
-
-        Treats adjacent Intervals as equivalent to one long interval,
-        so this function really tests whether the IntervalSets cover
-        the same spans of time."""
-        if not isinstance(other, IntervalSet):
-            return False
-        i = 0
-        j = 0
-        outside = True
-        try:
-            while True:
-                if (outside):
-                    # To match, we need to be finished this set
-                    if (i >= len(self) and j >= len(other)):
-                        return True
-                    # Or the starts need to match
-                    if (self[i].start != other[j].start):
-                        return False
-                    outside = False
-                else:
-                    # We can move on if the two interval ends match
-                    if (self[i].end == other[j].end):
-                        i += 1
-                        j += 1
-                        outside = True
-                    else:
-                        # Whichever ends first needs to be adjacent to the next
-                        if (self[i].end < other[j].end):
-                            if (not self[i].is_adjacent(self[i+1])):
-                                return False
-                            i += 1
-                        else:
-                            if (not other[j].is_adjacent(other[j+1])):
-                                return False
-                            j += 1
-        except IndexError:
-            return False
-
-    def __ne__(self, other):
-        return not self.__eq__(other)
-
-    def __len__(self):
-        return len(self.data)
-
-    def __getitem__(self, key):
-        return self.data.__getitem__(key)
-
-    def __iadd__(self, other):
-        """Inplace add -- modifies self
-
-        This throws an exception if the regions being added intersect."""
-        if isinstance(other, Interval):
-            other = [other]
-        self._add_intervals(other)
-        return self
-        
-    def __add__(self, other):
-        """Add -- returns a new object
-
-        This throws an exception if the regions being added intersect."""
-        new = IntervalSet(self)
-        new += IntervalSet(other)
-        return new
-
-    def __and__(self, other):
-        """Compute a new IntervalSet from the intersection of two others
-
-        Output intervals are built as subsets of the intervals in the
-        first argument (self)."""
-        # If we were given a set, intersect with each interval in that set
-        if isinstance(other, IntervalSet):
-            out = IntervalSet()
-            for interval in other.data:
-                out += self & interval
-            return out
-
-        if not isinstance(other, Interval):
-            raise TypeError("can't intersect with that type")
-
-        out = IntervalSet()
-        for this in self.data:
-            # If there's any overlap, add the overlapping region
-            if (this.end > other.start and this.start < other.end):
-                out += this.subset(max(this.start, other.start),
-                                   min(this.end, other.end))
-        return out
-    
-    def _add_intervals(self, iterable):
-        """Add each Interval from an interable to this set"""
-        for element in iter(iterable):
-            self._add_single_interval(element)
-
-    def _add_single_interval(self, interval):
-        """Add one Interval to this set"""
-        if (not isinstance(interval, Interval)):
-            raise TypeError("can only add Intervals")
-        for existing in self.data:
-            if existing.intersects(interval):
-                raise IntervalError("Tried to add overlapping interval "
-                                    "to this set")
-        bisect.insort(self.data, interval)

nilmdb/scripts/__init__.py

@@ -0,0 +1 @@
+# Command line scripts

nilmdb/scripts/nilmdb_server.py

@@ -0,0 +1,81 @@
+#!/usr/bin/python
+
+import nilmdb.server
+import argparse
+import os
+import socket
+
+def main():
+    """Main entry point for the 'nilmdb-server' command line script"""
+
+    parser = argparse.ArgumentParser(
+        description = 'Run the NilmDB server',
+        formatter_class = argparse.ArgumentDefaultsHelpFormatter)
+
+    parser.add_argument("-V", "--version", action="version",
+                        version = nilmdb.__version__)
+
+    group = parser.add_argument_group("Standard options")
+    group.add_argument('-a', '--address',
+                       help = 'Only listen on the given address',
+                       default = '0.0.0.0')
+    group.add_argument('-p', '--port', help = 'Listen on the given port',
+                       type = int, default = 12380)
+    group.add_argument('-d', '--database', help = 'Database directory',
+                       default = os.path.join(os.getcwd(), "db"))
+    group.add_argument('-q', '--quiet', help = 'Silence output',
+                       action = 'store_true')
+
+    group = parser.add_argument_group("Debug options")
+    group.add_argument('-y', '--yappi', help = 'Run under yappi profiler and '
+                       'invoke interactive shell afterwards',
+                       action = 'store_true')
+
+    args = parser.parse_args()
+
+    # Create database object
+    db = nilmdb.server.NilmDB(args.database)
+
+    # Configure the server
+    if args.quiet:
+        embedded = True
+    else:
+        embedded = False
+    server = nilmdb.server.Server(db,
+                                  host = args.address,
+                                  port = args.port,
+                                  embedded = embedded)
+
+    # Print info
+    if not args.quiet:
+        print "Database: %s" % (os.path.realpath(args.database))
+        if args.address == '0.0.0.0' or args.address == '::':
+            host = socket.getfqdn()
+        else:
+            host = args.address
+        print "Server URL: http://%s:%d/" % ( host, args.port)
+        print "----"
+
+    # Run it
+    if args.yappi:
+        print "Running in yappi"
+        try:
+            import yappi
+            yappi.start()
+            server.start(blocking = True)
+        finally:
+            yappi.stop()
+            yappi.print_stats(sort_type = yappi.SORTTYPE_TTOT, limit = 50)
+            from IPython import embed
+            embed(header = "Use the yappi object to explore further, "
+                  "quit to exit")
+    else:
+        server.start(blocking = True)
+
+    # Clean up
+    if not args.quiet:
+        print "Closing database"
+        db.close()
+
+if __name__ == "__main__":
+    main()

nilmdb/scripts/nilmtool.py

@@ -0,0 +1,10 @@
+#!/usr/bin/python
+
+import nilmdb.cmdline
+
+def main():
+    """Main entry point for the 'nilmtool' command line script"""
+    nilmdb.cmdline.Cmdline().run()
+
+if __name__ == "__main__":
+    main()

nilmdb/server/__init__.py

@@ -0,0 +1,22 @@
+"""nilmdb.server"""
+
+from __future__ import absolute_import
+
+# Try to set up pyximport to automatically rebuild Cython modules.  If
+# this doesn't work, it's OK, as long as the modules were built externally.
+# (e.g. python setup.py build_ext --inplace)
+try:
+    import Cython
+    import distutils.version
+    if (distutils.version.LooseVersion(Cython.__version__) <
+        distutils.version.LooseVersion("0.16")): # pragma: no cover
+        raise ImportError("Cython version too old")
+    import pyximport
+    pyximport.install(inplace = True, build_in_temp = False)
+except ImportError: # pragma: no cover
+    pass
+
+import nilmdb.server.layout
+from nilmdb.server.nilmdb import NilmDB
+from nilmdb.server.server import Server
+from nilmdb.server.errors import NilmDBError, StreamError, OverlapError

nilmdb/server/bulkdata.py

@@ -0,0 +1,488 @@
+# Fixed record size bulk data storage
+
+# Need absolute_import so that "import nilmdb" won't pull in
+# nilmdb.py, but will pull the parent nilmdb module instead.
+from __future__ import absolute_import
+from __future__ import division
+import nilmdb
+from nilmdb.utils.printf import *
+
+import os
+import cPickle as pickle
+import struct
+import mmap
+import re
+
+# If we have the faulthandler module, use it.  All of the mmap stuff
+# might trigger a SIGSEGV or SIGBUS if we're not careful, and
+# faulthandler will give a traceback in that case.  (the Python
+# interpreter will still die either way).
+try: # pragma: no cover
+    import faulthandler
+    faulthandler.enable()
+except: # pragma: no cover
+    pass
+
+# Up to 256 open file descriptors at any given time.
+# These variables are global so they can be used in the decorator arguments.
+table_cache_size = 16
+fd_cache_size = 16
+
+@nilmdb.utils.must_close(wrap_verify = True)
+class BulkData(object):
+    def __init__(self, basepath, **kwargs):
+        self.basepath = basepath
+        self.root = os.path.join(self.basepath, "data")
+
+        # Tuneables
+        if "file_size" in kwargs:
+            self.file_size = kwargs["file_size"]
+        else:
+            # Default to approximately 128 MiB per file
+            self.file_size = 128 * 1024 * 1024
+
+        if "files_per_dir" in kwargs:
+            self.files_per_dir = kwargs["files_per_dir"]
+        else:
+            # 32768 files per dir should work even on FAT32
+            self.files_per_dir = 32768
+
+        # Make root path
+        if not os.path.isdir(self.root):
+            os.mkdir(self.root)
+
+    def close(self):
+        self.getnode.cache_remove_all()
+
+    def _encode_filename(self, path):
+        # Encode all paths to UTF-8, regardless of sys.getfilesystemencoding(),
+        # because we want to be able to represent all code points and the user
+        # will never be directly exposed to filenames.  We can then do path
+        # manipulations on the UTF-8 directly.
+        if isinstance(path, unicode):
+            return path.encode('utf-8')
+        return path
+
+    def create(self, unicodepath, layout_name):
+        """
+        unicodepath: path to the data (e.g. u'/newton/prep').
+        Paths must contain at least two elements, e.g.:
+           /newton/prep
+           /newton/raw
+           /newton/upstairs/prep
+           /newton/upstairs/raw
+
+        layout_name: string for nilmdb.layout.get_named(), e.g. 'float32_8'
+        """
+        path = self._encode_filename(unicodepath)
+
+        if path[0] != '/':
+            raise ValueError("paths must start with /")
+        [ group, node ] = path.rsplit("/", 1)
+        if group == '':
+            raise ValueError("invalid path; path must contain at least one "
+                             "folder")
+
+        # Get layout, and build format string for struct module
+        try:
+            layout = nilmdb.server.layout.get_named(layout_name)
+            struct_fmt = '<d'  # Little endian, double timestamp
+            struct_mapping = {
+                "int8": 'b',
+                "uint8": 'B',
+                "int16": 'h',
+                "uint16": 'H',
+                "int32": 'i',
+                "uint32": 'I',
+                "int64": 'q',
+                "uint64": 'Q',
+                "float32": 'f',
+                "float64": 'd',
+                }
+            struct_fmt += struct_mapping[layout.datatype] * layout.count
+        except KeyError:
+            raise ValueError("no such layout, or bad data types")
+
+        # Create the table.  Note that we make a distinction here
+        # between NilmDB paths (always Unix style, split apart
+        # manually) and OS paths (built up with os.path.join)
+
+        # Make directories leading up to this one
+        elements = path.lstrip('/').split('/')
+        for i in range(len(elements)):
+            ospath = os.path.join(self.root, *elements[0:i])
+            if Table.exists(ospath):
+                raise ValueError("path is subdir of existing node")
+            if not os.path.isdir(ospath):
+                os.mkdir(ospath)
+
+        # Make the final dir
+        ospath = os.path.join(self.root, *elements)
+        if os.path.isdir(ospath):
+            raise ValueError("subdirs of this path already exist")
+        os.mkdir(ospath)
+
+        # Write format string to file
+        Table.create(ospath, struct_fmt, self.file_size, self.files_per_dir)
+
+        # Open and cache it
+        self.getnode(unicodepath)
+
+        # Success
+        return
+
+    def destroy(self, unicodepath):
+        """Fully remove all data at a particular path.  No way to undo
+        it!  The group/path structure is removed, too."""
+        path = self._encode_filename(unicodepath)
+
+        # Get OS path
+        elements = path.lstrip('/').split('/')
+        ospath = os.path.join(self.root, *elements)
+
+        # Remove Table object from cache
+        self.getnode.cache_remove(self, unicodepath)
+
+        # Remove the contents of the target directory
+        if not Table.exists(ospath):
+            raise ValueError("nothing at that path")
+        for (root, dirs, files) in os.walk(ospath, topdown = False):
+            for name in files:
+                os.remove(os.path.join(root, name))
+            for name in dirs:
+                os.rmdir(os.path.join(root, name))
+
+        # Remove empty parent directories
+        for i in reversed(range(len(elements))):
+            ospath = os.path.join(self.root, *elements[0:i+1])
+            try:
+                os.rmdir(ospath)
+            except OSError:
+                break
+
+    # Cache open tables
+    @nilmdb.utils.lru_cache(size = table_cache_size,
+                            onremove = lambda x: x.close())
+    def getnode(self, unicodepath):
+        """Return a Table object corresponding to the given database
+        path, which must exist."""
+        path = self._encode_filename(unicodepath)
+        elements = path.lstrip('/').split('/')
+        ospath = os.path.join(self.root, *elements)
+        return Table(ospath)
+
+@nilmdb.utils.must_close(wrap_verify = True)
+class File(object):
+    """Object representing a single file on disk.  Data can be appended,
+    or the self.mmap handle can be used for random reads."""
+
+    def __init__(self, root, subdir, filename):
+        # Create path if it doesn't exist
+        try:
+            os.mkdir(os.path.join(root, subdir))
+        except OSError:
+            pass
+
+        # Open/create file
+        self._f = open(os.path.join(root, subdir, filename), "a+b", 0)
+
+        # Seek to end, and get size
+        self._f.seek(0, 2)
+        self.size = self._f.tell()
+
+        # Open mmap object
+        self.mmap = None
+        self._mmap_reopen()
+
+    def _mmap_reopen(self):
+        if self.size == 0:
+            # Don't mmap if the file is empty; it would fail
+            pass
+        elif self.mmap is None:
+            # Not opened yet, so open it
+            self.mmap = mmap.mmap(self._f.fileno(), 0)
+        else:
+            # Already opened, so just resize it
+            self.mmap.resize(self.size)
+
+    def close(self):
+        if self.mmap is not None:
+            self.mmap.close()
+        self._f.close()
+
+    def append(self, data):
+        # Write data, flush it, and resize our mmap accordingly
+        self._f.write(data)
+        self._f.flush()
+        self.size += len(data)
+        self._mmap_reopen()
+
+@nilmdb.utils.must_close(wrap_verify = True)
+class Table(object):
+    """Tools to help access a single table (data at a specific OS path)."""
+    # See design.md for design details
+
+    # Class methods, to help keep format details in this class.
+    @classmethod
+    def exists(cls, root):
+        """Return True if a table appears to exist at this OS path"""
+        return os.path.isfile(os.path.join(root, "_format"))
+
+    @classmethod
+    def create(cls, root, struct_fmt, file_size, files_per_dir):
+        """Initialize a table at the given OS path.
+        'struct_fmt' is a Struct module format description"""
+
+        # Calculate rows per file so that each file is approximately
+        # file_size bytes.
+        packer = struct.Struct(struct_fmt)
+        rows_per_file = max(file_size // packer.size, 1)
+
+        fmt = { "rows_per_file": rows_per_file,
+                "files_per_dir": files_per_dir,
+                "struct_fmt": struct_fmt,
+                "version": 1 }
+        with open(os.path.join(root, "_format"), "wb") as f:
+            pickle.dump(fmt, f, 2)
+
+    # Normal methods
+    def __init__(self, root):
+        """'root' is the full OS path to the directory of this table"""
+        self.root = root
+
+        # Load the format and build packer
+        with open(os.path.join(self.root, "_format"), "rb") as f:
+            fmt = pickle.load(f)
+
+        if fmt["version"] != 1: # pragma: no cover (just future proofing)
+            raise NotImplementedError("version " + fmt["version"] +
+                                      " bulk data store not supported")
+
+        self.rows_per_file = fmt["rows_per_file"]
+        self.files_per_dir = fmt["files_per_dir"]
+        self.packer = struct.Struct(fmt["struct_fmt"])
+        self.file_size = self.packer.size * self.rows_per_file
+
+        # Find nrows
+        self.nrows = self._get_nrows()
+
+    def close(self):
+        self.file_open.cache_remove_all()
+
+    # Internal helpers
+    def _get_nrows(self):
+        """Find nrows by locating the lexicographically last filename
+        and using its size"""
+        # Note that this just finds a 'nrows' that is guaranteed to be
+        # greater than the row number of any piece of data that
+        # currently exists, not necessarily all data that _ever_
+        # existed.
+        regex = re.compile("^[0-9a-f]{4,}$")
+
+        # Find the last directory.  We sort and loop through all of them,
+        # starting with the numerically greatest, because the dirs could be
+        # empty if something was deleted.
+        subdirs = sorted(filter(regex.search, os.listdir(self.root)),
+                         key = lambda x: int(x, 16), reverse = True)
+
+        for subdir in subdirs:
+            # Now find the last file in that dir
+            path = os.path.join(self.root, subdir)
+            files = filter(regex.search, os.listdir(path))
+            if not files: # pragma: no cover (shouldn't occur)
+                # Empty dir: try the next one
+                continue
+
+            # Find the numerical max
+            filename = max(files, key = lambda x: int(x, 16))
+            offset = os.path.getsize(os.path.join(self.root, subdir, filename))
+
+            # Convert to row number
+            return self._row_from_offset(subdir, filename, offset)
+
+        # No files, so no data
+        return 0
+
+    def _offset_from_row(self, row):
+        """Return a (subdir, filename, offset, count) tuple:
+
+          subdir: subdirectory for the file
+        filename: the filename that contains the specified row
+          offset: byte offset of the specified row within the file
+           count: number of rows (starting at offset) that fit in the file
+        """
+        filenum = row // self.rows_per_file
+        # It's OK if these format specifiers are too short; the filenames
+        # will just get longer but will still sort correctly.
+        dirname = sprintf("%04x", filenum // self.files_per_dir)
+        filename = sprintf("%04x", filenum % self.files_per_dir)
+        offset = (row % self.rows_per_file) * self.packer.size
+        count = self.rows_per_file - (row % self.rows_per_file)
+        return (dirname, filename, offset, count)
+
+    def _row_from_offset(self, subdir, filename, offset):
+        """Return the row number that corresponds to the given
+        'subdir/filename' and byte-offset within that file."""
+        if (offset % self.packer.size) != 0: # pragma: no cover; shouldn't occur
+            raise ValueError("file offset is not a multiple of data size")
+        filenum = int(subdir, 16) * self.files_per_dir + int(filename, 16)
+        row = (filenum * self.rows_per_file) + (offset // self.packer.size)
+        return row
+
+    # Cache open files
+    @nilmdb.utils.lru_cache(size = fd_cache_size,
+                            onremove = lambda f: f.close())
+    def file_open(self, subdir, filename):
+        """Open and map a given 'subdir/filename' (relative to self.root).
+        Will be automatically closed when evicted from the cache."""
+        return File(self.root, subdir, filename)
+
+    def append(self, data):
+        """Append the data and flush it to disk.
+        data is a nested Python list [[row],[row],[...]]"""
+        remaining = len(data)
+        dataiter = iter(data)
+        while remaining:
+            # See how many rows we can fit into the current file, and open it
+            (subdir, fname, offset, count) = self._offset_from_row(self.nrows)
+            if count > remaining:
+                count = remaining
+
+            f = self.file_open(subdir, fname)
+
+            # Write the data
+            for i in xrange(count):
+                row = dataiter.next()
+                f.append(self.packer.pack(*row))
+            remaining -= count
+            self.nrows += count
+
+    def __getitem__(self, key):
+        """Extract data and return it.  Supports simple indexing
+        (table[n]) and range slices (table[n:m]).  Returns a nested
+        Python list [[row],[row],[...]]"""
+
+        # Handle simple slices
+        if isinstance(key, slice):
+            # Fall back to brute force if the slice isn't simple
+            if ((key.step is not None and key.step != 1) or
+                key.start is None or
+                key.stop is None or
+                key.start >= key.stop or
+                key.start < 0 or
+                key.stop > self.nrows):
+                return [ self[x] for x in xrange(*key.indices(self.nrows)) ]
+
+            ret = []
+            row = key.start
+            remaining = key.stop - key.start
+            while remaining:
+                (subdir, filename, offset, count) = self._offset_from_row(row)
+                if count > remaining:
+                    count = remaining
+                mm = self.file_open(subdir, filename).mmap
+                for i in xrange(count):
+                    ret.append(list(self.packer.unpack_from(mm, offset)))
+                    offset += self.packer.size
+                remaining -= count
+                row += count
+            return ret
+
+        # Handle single points
+        if key < 0 or key >= self.nrows:
+            raise IndexError("Index out of range")
+        (subdir, filename, offset, count) = self._offset_from_row(key)
+        mm = self.file_open(subdir, filename).mmap
+        # unpack_from ignores the mmap object's current seek position
+        return list(self.packer.unpack_from(mm, offset))
+
+    def _remove_rows(self, subdir, filename, start, stop):
+        """Helper to mark specific rows as being removed from a
+        file, and potentially removing or truncating the file itself."""
+        # Import an existing list of deleted rows for this file
+        datafile = os.path.join(self.root, subdir, filename)
+        cachefile = datafile + ".removed"
+        try:
+            with open(cachefile, "rb") as f:
+                ranges = pickle.load(f)
+            cachefile_present = True
+        except:
+            ranges = []
+            cachefile_present = False
+
+        # Append our new range and sort
+        ranges.append((start, stop))
+        ranges.sort()
+
+        # Merge adjacent ranges into "out"
+        merged = []
+        prev = None
+        for new in ranges:
+            if prev is None:
+                # No previous range, so remember this one
+                prev = new
+            elif prev[1] == new[0]:
+                # Previous range connected to this new one; extend prev
+                prev = (prev[0], new[1])
+            else:
+                # Not connected; append previous and start again
+                merged.append(prev)
+                prev = new
+        if prev is not None:
+            merged.append(prev)
+
+        # If the range covered the whole file, we can delete it now.
+        # Note that the last file in a table may be only partially
+        # full (smaller than self.rows_per_file).  We purposely leave
+        # those files around rather than deleting them, because the
+        # remainder will be filled on a subsequent append(), and things
+        # are generally easier if we don't have to special-case that.
+        if (len(merged) == 1 and
+            merged[0][0] == 0 and merged[0][1] == self.rows_per_file):
+            # Close potentially open file in file_open LRU cache
+            self.file_open.cache_remove(self, subdir, filename)
+
+            # Delete files
+            os.remove(datafile)
+            if cachefile_present:
+                os.remove(cachefile)
+
+            # Try deleting subdir, too
+            try:
+                os.rmdir(os.path.join(self.root, subdir))
+            except:
+                pass
+        else:
+            # Update cache.  Try to do it atomically.
+            nilmdb.utils.atomic.replace_file(cachefile,
+                                             pickle.dumps(merged, 2))
+
+    def remove(self, start, stop):
+        """Remove specified rows [start, stop) from this table.
+
+        If a file is left empty, it is fully removed.  Otherwise, a
+        parallel data file is used to remember which rows have been
+        removed, and the file is otherwise untouched."""
+        if start < 0 or start > stop or stop > self.nrows:
+            raise IndexError("Index out of range")
+
+        row = start
+        remaining = stop - start
+        while remaining:
+            # Loop through each file that we need to touch
+            (subdir, filename, offset, count) = self._offset_from_row(row)
+            if count > remaining:
+                count = remaining
+            row_offset = offset // self.packer.size
+            # Mark the rows as being removed
+            self._remove_rows(subdir, filename, row_offset, row_offset + count)
+            remaining -= count
+            row += count
+
+class TimestampOnlyTable(object):
+    """Helper that lets us pass a Tables object into bisect, by
+    returning only the timestamp when a particular row is requested."""
+    def __init__(self, table):
+        self.table = table
+    def __getitem__(self, index):
+        return self.table[index][0]

nilmdb/server/errors.py

@@ -0,0 +1,12 @@
+"""Exceptions"""
+
+class NilmDBError(Exception):
+    """Base exception for NilmDB errors"""
+    def __init__(self, message = "Unspecified error"):
+        Exception.__init__(self, message)
+
+class StreamError(NilmDBError):
+    pass
+
+class OverlapError(NilmDBError):
+    pass

nilmdb/server/interval.pyx

@@ -0,0 +1,329 @@
+"""Interval, IntervalSet
+
+Represents an interval of time, and a set of such intervals.
+
+Intervals are half-open, ie. they include data points with timestamps
+[start, end)
+"""
+
+# First implementation kept a sorted list of intervals and used
+# biesct() to optimize some operations, but this was too slow.
+
+# Second version was based on the quicksect implementation from
+# python-bx, modified slightly to handle floating point intervals.
+# This didn't support deletion.
+
+# Third version is more similar to the first version, using a rb-tree
+# instead of a simple sorted list to maintain O(log n) operations.
+
+# Fourth version is an optimized rb-tree that stores interval starts
+# and ends directly in the tree, like bxinterval did.
+
+cimport rbtree
+cdef extern from "stdint.h":
+    ctypedef unsigned long long uint64_t
+
+class IntervalError(Exception):
+    """Error due to interval overlap, etc"""
+    pass
+
+cdef class Interval:
+    """Represents an interval of time."""
+
+    cdef public double start, end
+
+    def __init__(self, double start, double end):
+        """
+        'start' and 'end' are arbitrary floats that represent time
+        """
+        if start >= end:
+            # Explicitly disallow zero-width intervals (since they're half-open)
+            raise IntervalError("start %s must precede end %s" % (start, end))
+        self.start = float(start)
+        self.end = float(end)
+
+    def __repr__(self):
+        s = repr(self.start) + ", " + repr(self.end)
+        return self.__class__.__name__ + "(" + s + ")"
+
+    def __str__(self):
+        return "[" + repr(self.start) + " -> " + repr(self.end) + ")"
+
+    def __cmp__(self, Interval other):
+        """Compare two intervals.  If non-equal, order by start then end"""
+        if not isinstance(other, Interval):
+            raise TypeError("bad type")
+        if self.start == other.start:
+            if self.end < other.end:
+                return -1
+            if self.end > other.end:
+                return 1
+            return 0
+        if self.start < other.start:
+            return -1
+        return 1
+
+    cpdef intersects(self, Interval other):
+        """Return True if two Interval objects intersect"""
+        if (self.end <= other.start or self.start >= other.end):
+            return False
+        return True
+
+    cpdef subset(self, double start, double end):
+        """Return a new Interval that is a subset of this one"""
+        # A subclass that tracks additional data might override this.
+        if start < self.start or end > self.end:
+            raise IntervalError("not a subset")
+        return Interval(start, end)
+
+cdef class DBInterval(Interval):
+    """
+    Like Interval, but also tracks corresponding start/end times and
+    positions within the database.  These are not currently modified
+    when subsets are taken, but can be used later to help zero in on
+    database positions.
+
+    The actual 'start' and 'end' will always fall within the database
+    start and end, e.g.:
+        db_start = 100, db_startpos = 10000
+        start = 123
+        end = 150
+        db_end = 200, db_endpos = 20000
+    """
+
+    cpdef public double db_start, db_end
+    cpdef public uint64_t db_startpos, db_endpos
+
+    def __init__(self, start, end,
+                 db_start, db_end,
+                 db_startpos, db_endpos):
+        """
+        'db_start' and 'db_end' are arbitrary floats that represent
+        time.  They must be a strict superset of the time interval
+        covered by 'start' and 'end'.  The 'db_startpos' and
+        'db_endpos' are arbitrary database position indicators that
+        correspond to those points.
+        """
+        Interval.__init__(self, start, end)
+        self.db_start = db_start
+        self.db_end = db_end
+        self.db_startpos = db_startpos
+        self.db_endpos = db_endpos
+        if db_start > start or db_end < end:
+            raise IntervalError("database times must span the interval times")
+
+    def __repr__(self):
+        s = repr(self.start) + ", " + repr(self.end)
+        s += ", " + repr(self.db_start) + ", " + repr(self.db_end)
+        s += ", " + repr(self.db_startpos) + ", " + repr(self.db_endpos)
+        return self.__class__.__name__ + "(" + s + ")"
+
+    cpdef subset(self, double start, double end):
+        """
+        Return a new DBInterval that is a subset of this one
+        """
+        if start < self.start or end > self.end:
+            raise IntervalError("not a subset")
+        return DBInterval(start, end,
+                          self.db_start, self.db_end,
+                          self.db_startpos, self.db_endpos)
+
+cdef class IntervalSet:
+    """
+    A non-intersecting set of intervals.
+    """
+
+    cdef public rbtree.RBTree tree
+
+    def __init__(self, source=None):
+        """
+        'source' is an Interval or IntervalSet to add.
+        """
+        self.tree = rbtree.RBTree()
+        if source is not None:
+            self += source
+
+    def __iter__(self):
+        for node in self.tree:
+            if node.obj:
+                yield node.obj
+
+    def __len__(self):
+        return sum(1 for x in self)
+
+    def __repr__(self):
+        descs = [ repr(x) for x in self ]
+        return self.__class__.__name__ + "([" + ", ".join(descs) + "])"
+
+    def __str__(self):
+        descs = [ str(x) for x in self ]
+        return  "[" + ", ".join(descs) + "]"
+
+    def __match__(self, other):
+        # This isn't particularly efficient, but it shouldn't get used in the
+        # general case.
+        """Test equality of two IntervalSets.
+
+        Treats adjacent Intervals as equivalent to one long interval,
+        so this function really tests whether the IntervalSets cover
+        the same spans of time."""
+        i = 0
+        j = 0
+        outside = True
+
+        def is_adjacent(a, b):
+            """Return True if two Intervals are adjacent (same end or start)"""
+            if a.end == b.start or b.end == a.start:
+                return True
+            else:
+                return False
+
+        this = list(self)
+        that = list(other)
+
+        try:
+            while True:
+                if (outside):
+                    # To match, we need to be finished both sets
+                    if (i >= len(this) and j >= len(that)):
+                        return True
+                    # Or the starts need to match
+                    if (this[i].start != that[j].start):
+                        return False
+                    outside = False
+                else:
+                    # We can move on if the two interval ends match
+                    if (this[i].end == that[j].end):
+                        i += 1
+                        j += 1
+                        outside = True
+                    else:
+                        # Whichever ends first needs to be adjacent to the next
+                        if (this[i].end < that[j].end):
+                            if (not is_adjacent(this[i],this[i+1])):
+                                return False
+                            i += 1
+                        else:
+                            if (not is_adjacent(that[j],that[j+1])):
+                                return False
+                            j += 1
+        except IndexError:
+            return False
+
+    # Use __richcmp__ instead of __eq__, __ne__ for Cython.
+    def __richcmp__(self, other, int op):
+        if op == 2: # ==
+            return self.__match__(other)
+        elif op == 3: # !=
+            return not self.__match__(other)
+        return False
+    #def __eq__(self, other):
+    #    return self.__match__(other)
+    #
+    #def __ne__(self, other):
+    #    return not self.__match__(other)
+
+    def __iadd__(self, object other not None):
+        """Inplace add -- modifies self
+
+        This throws an exception if the regions being added intersect."""
+        if isinstance(other, Interval):
+            if self.intersects(other):
+                raise IntervalError("Tried to add overlapping interval "
+                                    "to this set")
+            self.tree.insert(rbtree.RBNode(other.start, other.end, other))
+        else:
+            for x in other:
+                self.__iadd__(x)
+        return self
+
+    def iadd_nocheck(self, Interval other not None):
+        """Inplace add -- modifies self.
+        'Optimized' version that doesn't check for intersection and
+        only inserts the new interval into the tree."""
+        self.tree.insert(rbtree.RBNode(other.start, other.end, other))
+
+    def __isub__(self, Interval other not None):
+        """Inplace subtract -- modifies self
+
+        Removes an interval from the set.  Must exist exactly
+        as provided -- cannot remove a subset of an existing interval."""
+        i = self.tree.find(other.start, other.end)
+        if i is None:
+            raise IntervalError("interval " + str(other) + " not in tree")
+        self.tree.delete(i)
+        return self
+
+    def __add__(self, other not None):
+        """Add -- returns a new object"""
+        new = IntervalSet(self)
+        new += IntervalSet(other)
+        return new
+
+    def __and__(self, other not None):
+        """
+        Compute a new IntervalSet from the intersection of two others
+
+        Output intervals are built as subsets of the intervals in the
+        first argument (self).
+        """
+        out = IntervalSet()
+
+        if not isinstance(other, IntervalSet):
+            for i in self.intersection(other):
+                out.tree.insert(rbtree.RBNode(i.start, i.end, i))
+        else:
+            for x in other:
+                for i in self.intersection(x):
+                    out.tree.insert(rbtree.RBNode(i.start, i.end, i))
+
+        return out
+
+    def intersection(self, Interval interval not None, orig = False):
+        """
+        Compute a sequence of intervals that correspond to the
+        intersection between `self` and the provided interval.
+        Returns a generator that yields each of these intervals
+        in turn.
+
+        Output intervals are built as subsets of the intervals in the
+        first argument (self).
+
+        If orig = True, also return the original interval that was
+        (potentially) subsetted to make the one that is being
+        returned.
+        """
+        if not isinstance(interval, Interval):
+            raise TypeError("bad type")
+        for n in self.tree.intersect(interval.start, interval.end):
+            i = n.obj
+            if i:
+                if i.start >= interval.start and i.end <= interval.end:
+                    if orig:
+                        yield (i, i)
+                    else:
+                        yield i
+                else:
+                    subset = i.subset(max(i.start, interval.start),
+                                      min(i.end, interval.end))
+                    if orig:
+                        yield (subset, i)
+                    else:
+                        yield subset
+
+    cpdef intersects(self, Interval other):
+        """Return True if this IntervalSet intersects another interval"""
+        for n in self.tree.intersect(other.start, other.end):
+            if n.obj.intersects(other):
+                return True
+        return False
+
+    def find_end(self, double t):
+        """
+        Return an Interval from this tree that ends at time t, or
+        None if it doesn't exist.
+        """
+        n = self.tree.find_left_end(t)
+        if n and n.obj.end == t:
+            return n.obj
+        return None

nilmdb/server/interval.pyxdep

@@ -0,0 +1 @@
+rbtree.pxd

nilmdb/server/layout.pyx

@@ -0,0 +1,209 @@
+# cython: profile=False
+
+import time
+import sys
+import inspect
+import cStringIO
+import numpy as np
+
+cdef enum:
+    max_value_count = 64
+
+cimport cython
+cimport libc.stdlib
+cimport libc.stdio
+cimport libc.string
+
+class ParserError(Exception):
+    def __init__(self, line, message):
+        self.message = "line " + str(line) + ": " + message
+        Exception.__init__(self, self.message)
+
+class FormatterError(Exception):
+    pass
+
+class Layout:
+    """Represents a NILM database layout"""
+
+    def __init__(self, typestring):
+        """Initialize this Layout object to handle the specified
+        type string"""
+        try:
+            [ datatype, count ] = typestring.split("_")
+        except:
+            raise KeyError("invalid layout string")
+
+        try:
+            self.count = int(count)
+        except ValueError:
+            raise KeyError("invalid count")
+        if self.count < 1 or self.count > max_value_count:
+            raise KeyError("invalid count")
+
+        if datatype == 'uint16':
+            self.parse = self.parse_uint16
+            self.format = self.format_uint16
+        elif datatype == 'float32' or datatype == 'float64':
+            self.parse = self.parse_float64
+            self.format = self.format_float64
+        else:
+            raise KeyError("invalid type")
+
+        self.datatype = datatype
+
+    # Parsers
+    def parse_float64(self, char *text):
+        cdef int n
+        cdef double ts
+        # Return doubles even in float32 case, since they're going into
+        # a Python array which would upconvert to double anyway.
+        result = []
+        cdef char *end
+        ts = libc.stdlib.strtod(text, &end)
+        if end == text:
+            raise ValueError("bad timestamp")
+        result.append(ts)
+        for n in range(self.count):
+            text = end
+            result.append(libc.stdlib.strtod(text, &end))
+            if end == text:
+                raise ValueError("wrong number of values")
+        n = 0
+        while end[n] == ' ':
+            n += 1
+        if end[n] != '\n' and end[n] != '#' and end[n] != '\0':
+            raise ValueError("extra data on line")
+        return (ts, result)
+
+    def parse_uint16(self, char *text):
+        cdef int n
+        cdef double ts
+        cdef int v
+        result = []
+        cdef char *end
+        ts = libc.stdlib.strtod(text, &end)
+        if end == text:
+            raise ValueError("bad timestamp")
+        result.append(ts)
+        for n in range(self.count):
+            text = end
+            v = libc.stdlib.strtol(text, &end, 10)
+            if v < 0 or v > 65535:
+                raise ValueError("value out of range")
+            result.append(v)
+            if end == text:
+                raise ValueError("wrong number of values")
+        n = 0
+        while end[n] == ' ':
+            n += 1
+        if end[n] != '\n' and end[n] != '#' and end[n] != '\0':
+            raise ValueError("extra data on line")
+        return (ts, result)
+
+    # Formatters
+    def format_float64(self, d):
+        n = len(d) - 1
+        if n != self.count:
+            raise ValueError("wrong number of values for layout type: "
+                             "got %d, wanted %d" % (n, self.count))
+        s = "%.6f" % d[0]
+        for i in range(n):
+            s += " %f" % d[i+1]
+        return s + "\n"
+
+    def format_uint16(self, d):
+        n = len(d) - 1
+        if n != self.count:
+            raise ValueError("wrong number of values for layout type: "
+                             "got %d, wanted %d" % (n, self.count))
+        s = "%.6f" % d[0]
+        for i in range(n):
+            s += " %d" % d[i+1]
+        return s + "\n"
+
+# Get a layout by name
+def get_named(typestring):
+    try:
+        return Layout(typestring)
+    except KeyError:
+        compat = { "PrepData": "float32_8",
+                   "RawData": "uint16_6",
+                   "RawNotchedData": "uint16_9" }
+        return Layout(compat[typestring])
+
+class Parser(object):
+    """Object that parses and stores ASCII data for inclusion into the
+    database"""
+
+    def __init__(self, layout):
+        if issubclass(layout.__class__, Layout):
+            self.layout = layout
+        else:
+            try:
+                self.layout = get_named(layout)
+            except KeyError:
+                raise TypeError("unknown layout")
+
+        self.data = []
+        self.min_timestamp = None
+        self.max_timestamp = None
+
+    def parse(self, textdata):
+        """
+        Parse the data, provided as lines of text, using the current
+        layout, into an internal data structure suitable for a
+        pytables 'table.append(parser.data)'.
+        """
+        cdef double last_ts = 0, ts
+        cdef int n = 0, i
+        cdef char *line
+
+        indata = cStringIO.StringIO(textdata)
+        # Assume any parsing error is a real error.
+        # In the future we might want to skip completely empty lines,
+        # or partial lines right before EOF?
+        try:
+            self.data = []
+            for pyline in indata:
+                line = pyline
+                n += 1
+                if line[0] == '\#':
+                    continue
+                (ts, row) = self.layout.parse(line)
+                if ts <= last_ts:
+                    raise ValueError("timestamp is not "
+                                     "monotonically increasing")
+                last_ts = ts
+                self.data.append(row)
+        except (ValueError, IndexError, TypeError) as e:
+            raise ParserError(n, "error: " + e.message)
+
+        # Mark timestamp ranges
+        if len(self.data):
+            self.min_timestamp = self.data[0][0]
+            self.max_timestamp = self.data[-1][0]
+
+class Formatter(object):
+    """Object that formats database data into ASCII"""
+
+    def __init__(self, layout):
+        if issubclass(layout.__class__, Layout):
+            self.layout = layout
+        else:
+            try:
+                self.layout = get_named(layout)
+            except KeyError:
+                raise TypeError("unknown layout")
+
+    def format(self, data):
+        """
+        Format raw data from the database, using the current layout,
+        as lines of ACSII text.
+        """
+        text = cStringIO.StringIO()
+        try:
+            for row in data:
+                text.write(self.layout.format(row))
+        except (ValueError, IndexError, TypeError) as e:
+            raise FormatterError("formatting error: " + e.message)
+        return text.getvalue()

nilmdb/server/nilmdb.py

@@ -0,0 +1,563 @@
+# -*- coding: utf-8 -*-
+
+"""NilmDB
+
+Object that represents a NILM database file.
+
+Manages both the SQL database and the table storage backend.
+"""
+
+# Need absolute_import so that "import nilmdb" won't pull in
+# nilmdb.py, but will pull the parent nilmdb module instead.
+from __future__ import absolute_import
+import nilmdb
+from nilmdb.utils.printf import *
+from nilmdb.server.interval import (Interval, DBInterval,
+                                    IntervalSet, IntervalError)
+from nilmdb.server import bulkdata
+from nilmdb.server.errors import NilmDBError, StreamError, OverlapError
+
+import sqlite3
+import os
+import errno
+import bisect
+
+# Note about performance and transactions:
+#
+# Committing a transaction in the default sync mode (PRAGMA synchronous=FULL)
+# takes about 125msec.  sqlite3 will commit transactions at 3 times:
+# 1: explicit con.commit()
+# 2: between a series of DML commands and non-DML commands, e.g.
+#    after a series of INSERT, SELECT, but before a CREATE TABLE or PRAGMA.
+# 3: at the end of an explicit transaction, e.g. "with self.con as con:"
+#
+# To speed up testing, or if this transaction speed becomes an issue,
+# the sync=False option to NilmDB.__init__ will set PRAGMA synchronous=OFF.
+
+
+# Don't touch old entries -- just add new ones.
+_sql_schema_updates = {
+    0: """
+    -- All streams
+    CREATE TABLE streams(
+    	id INTEGER PRIMARY KEY,		-- stream ID
+        path TEXT UNIQUE NOT NULL,	-- path, e.g. '/newton/prep'
+        layout TEXT NOT NULL		-- layout name, e.g. float32_8
+    );
+
+    -- Individual timestamped ranges in those streams.
+    -- For a given start_time and end_time, this tells us that the
+    -- data is stored between start_pos and end_pos.
+    -- Times are stored as μs since Unix epoch
+    -- Positions are opaque: PyTables rows, file offsets, etc.
+    --
+    -- Note: end_pos points to the row _after_ end_time, so end_pos-1
+    -- is the last valid row.
+    CREATE TABLE ranges(
+        stream_id INTEGER NOT NULL,
+        start_time INTEGER NOT NULL,
+        end_time INTEGER NOT NULL,
+        start_pos INTEGER NOT NULL,
+        end_pos INTEGER NOT NULL
+    );
+    CREATE INDEX _ranges_index ON ranges (stream_id, start_time, end_time);
+    """,
+
+    1: """
+    -- Generic dictionary-type metadata that can be associated with a stream
+    CREATE TABLE metadata(
+    	stream_id INTEGER NOT NULL,
+        key TEXT NOT NULL,
+        value TEXT
+    );
+    """,
+}
+
+@nilmdb.utils.must_close()
+class NilmDB(object):
+    verbose = 0
+
+    def __init__(self, basepath, sync=True, max_results=None,
+                 bulkdata_args=None):
+        if bulkdata_args is None:
+            bulkdata_args = {}
+
+        # set up path
+        self.basepath = os.path.abspath(basepath)
+
+        # Create the database path if it doesn't exist
+        try:
+            os.makedirs(self.basepath)
+        except OSError as e:
+            if e.errno != errno.EEXIST:
+                raise IOError("can't create tree " + self.basepath)
+
+        # Our data goes inside it
+        self.data = bulkdata.BulkData(self.basepath, **bulkdata_args)
+
+        # SQLite database too
+        sqlfilename = os.path.join(self.basepath, "data.sql")
+        # We use check_same_thread = False, assuming that the rest
+        # of the code (e.g. Server) will be smart and not access this
+        # database from multiple threads simultaneously.  Otherwise
+        # false positives will occur when the database is only opened
+        # in one thread, and only accessed in another.
+        self.con = sqlite3.connect(sqlfilename, check_same_thread = False)
+        self._sql_schema_update()
+
+        # See big comment at top about the performance implications of this
+        if sync:
+            self.con.execute("PRAGMA synchronous=FULL")
+        else:
+            self.con.execute("PRAGMA synchronous=OFF")
+
+        # Approximate largest number of elements that we want to send
+        # in a single reply (for stream_intervals, stream_extract)
+        if max_results:
+            self.max_results = max_results
+        else:
+            self.max_results = 16384
+
+    def get_basepath(self):
+        return self.basepath
+
+    def close(self):
+        if self.con:
+            self.con.commit()
+            self.con.close()
+        self.data.close()
+
+    def _sql_schema_update(self):
+        cur = self.con.cursor()
+        version = cur.execute("PRAGMA user_version").fetchone()[0]
+        oldversion = version
+
+        while version in _sql_schema_updates:
+            cur.executescript(_sql_schema_updates[version])
+            version = version + 1
+            if self.verbose: # pragma: no cover
+                printf("Schema updated to %d\n", version)
+
+        if version != oldversion:
+            with self.con:
+                cur.execute("PRAGMA user_version = {v:d}".format(v=version))
+
+    def _check_user_times(self, start, end):
+        if start is None:
+            start = -1e12
+        if end is None:
+            end = 1e12
+        if start >= end:
+            raise NilmDBError("start must precede end")
+        return (start, end)
+
+    @nilmdb.utils.lru_cache(size = 16)
+    def _get_intervals(self, stream_id):
+        """
+        Return a mutable IntervalSet corresponding to the given stream ID.
+        """
+        iset = IntervalSet()
+        result = self.con.execute("SELECT start_time, end_time, "
+                                  "start_pos, end_pos "
+                                  "FROM ranges "
+                                  "WHERE stream_id=?", (stream_id,))
+        try:
+            for (start_time, end_time, start_pos, end_pos) in result:
+                iset += DBInterval(start_time, end_time,
+                                   start_time, end_time,
+                                   start_pos, end_pos)
+        except IntervalError: # pragma: no cover
+            raise NilmDBError("unexpected overlap in ranges table!")
+
+        return iset
+
+    def _sql_interval_insert(self, id, start, end, start_pos, end_pos):
+        """Helper that adds interval to the SQL database only"""
+        self.con.execute("INSERT INTO ranges "
+                         "(stream_id,start_time,end_time,start_pos,end_pos) "
+                         "VALUES (?,?,?,?,?)",
+                         (id, start, end, start_pos, end_pos))
+
+    def _sql_interval_delete(self, id, start, end, start_pos, end_pos):
+        """Helper that removes interval from the SQL database only"""
+        self.con.execute("DELETE FROM ranges WHERE "
+                         "stream_id=? AND start_time=? AND "
+                         "end_time=? AND start_pos=? AND end_pos=?",
+                         (id, start, end, start_pos, end_pos))
+
+    def _add_interval(self, stream_id, interval, start_pos, end_pos):
+        """
+        Add interval to the internal interval cache, and to the database.
+        Note: arguments must be ints (not numpy.int64, etc)
+        """
+        # Load this stream's intervals
+        iset = self._get_intervals(stream_id)
+
+        # Check for overlap
+        if iset.intersects(interval): # pragma: no cover (gets caught earlier)
+            raise NilmDBError("new interval overlaps existing data")
+
+        # Check for adjacency.  If there's a stream in the database
+        # that ends exactly when this one starts, and the database
+        # rows match up, we can make one interval that covers the
+        # time range [adjacent.start -> interval.end)
+        # and database rows [ adjacent.start_pos -> end_pos ].
+        # Only do this if the resulting interval isn't too large.
+        max_merged_rows = 8000 * 60 * 60 * 1.05 # 1.05 hours at 8 KHz
+        adjacent = iset.find_end(interval.start)
+        if (adjacent is not None and
+            start_pos == adjacent.db_endpos and
+            (end_pos - adjacent.db_startpos) < max_merged_rows):
+            # First delete the old one, both from our iset and the
+            # database
+            iset -= adjacent
+            self._sql_interval_delete(stream_id,
+                                      adjacent.db_start, adjacent.db_end,
+                                      adjacent.db_startpos, adjacent.db_endpos)
+
+            # Now update our interval so the fallthrough add is
+            # correct.
+            interval.start = adjacent.start
+            start_pos = adjacent.db_startpos
+
+        # Add the new interval to the iset
+        iset.iadd_nocheck(DBInterval(interval.start, interval.end,
+                                     interval.start, interval.end,
+                                     start_pos, end_pos))
+
+        # Insert into the database
+        self._sql_interval_insert(stream_id, interval.start, interval.end,
+                                  int(start_pos), int(end_pos))
+
+        self.con.commit()
+
+    def _remove_interval(self, stream_id, original, remove):
+        """
+        Remove an interval from the internal cache and the database.
+
+        stream_id: id of stream
+         original: original DBInterval; must be already present in DB
+        to_remove: DBInterval to remove; must be subset of 'original'
+        """
+        # Just return if we have nothing to remove
+        if remove.start == remove.end: # pragma: no cover
+            return
+
+        # Load this stream's intervals
+        iset = self._get_intervals(stream_id)
+
+        # Remove existing interval from the cached set and the database
+        iset -= original
+        self._sql_interval_delete(stream_id,
+                                  original.db_start, original.db_end,
+                                  original.db_startpos, original.db_endpos)
+
+        # Add back the intervals that would be left over if the
+        # requested interval is removed.  There may be two of them, if
+        # the removed piece was in the middle.
+        def add(iset, start, end, start_pos, end_pos):
+            iset += DBInterval(start, end, start, end, start_pos, end_pos)
+            self._sql_interval_insert(stream_id, start, end, start_pos, end_pos)
+
+        if original.start != remove.start:
+            # Interval before the removed region
+            add(iset, original.start, remove.start,
+                original.db_startpos, remove.db_startpos)
+
+        if original.end != remove.end:
+            # Interval after the removed region
+            add(iset, remove.end, original.end,
+                remove.db_endpos, original.db_endpos)
+
+        # Commit SQL changes
+        self.con.commit()
+
+        return
+
+    def stream_list(self, path = None, layout = None):
+        """Return list of [path, layout] lists of all streams
+        in the database.
+
+        If path is specified, include only streams with a path that
+        matches the given string.
+
+        If layout is specified, include only streams with a layout
+        that matches the given string.
+        """
+        where = "WHERE 1=1"
+        params = ()
+        if layout:
+            where += " AND layout=?"
+            params += (layout,)
+        if path:
+            where += " AND path=?"
+            params += (path,)
+        result = self.con.execute("SELECT path, layout "
+                                  "FROM streams " + where, params).fetchall()
+
+        return sorted(list(x) for x in result)
+
+    def stream_intervals(self, path, start = None, end = None):
+        """
+        Returns (intervals, restart) tuple.
+
+        intervals is a list of [start,end] timestamps of all intervals
+        that exist for path, between start and end.
+
+        restart, if nonzero, means that there were too many results to
+        return in a single request.  The data is complete from the
+        starting timestamp to the point at which it was truncated,
+        and a new request with a start time of 'restart' will fetch
+        the next block of data.
+        """
+        stream_id = self._stream_id(path)
+        intervals = self._get_intervals(stream_id)
+        (start, end) = self._check_user_times(start, end)
+        requested = Interval(start, end)
+        result = []
+        for n, i in enumerate(intervals.intersection(requested)):
+            if n >= self.max_results:
+                restart = i.start
+                break
+            result.append([i.start, i.end])
+        else:
+            restart = 0
+        return (result, restart)
+
+    def stream_create(self, path, layout_name):
+        """Create a new table in the database.
+
+        path: path to the data (e.g. '/newton/prep').
+        Paths must contain at least two elements, e.g.:
+           /newton/prep
+           /newton/raw
+           /newton/upstairs/prep
+           /newton/upstairs/raw
+
+        layout_name: string for nilmdb.layout.get_named(), e.g. 'float32_8'
+        """
+        # Create the bulk storage.  Raises ValueError on error, which we
+        # pass along.
+        self.data.create(path, layout_name)
+
+        # Insert into SQL database once the bulk storage is happy
+        with self.con as con:
+            con.execute("INSERT INTO streams (path, layout) VALUES (?,?)",
+                        (path, layout_name))
+
+    def _stream_id(self, path):
+        """Return unique stream ID"""
+        result = self.con.execute("SELECT id FROM streams WHERE path=?",
+                                  (path,)).fetchone()
+        if result is None:
+            raise StreamError("No stream at path " + path)
+        return result[0]
+
+    def stream_set_metadata(self, path, data):
+        """Set stream metadata from a dictionary, e.g.
+           { description = 'Downstairs lighting',
+             v_scaling = 123.45 }
+           This replaces all existing metadata.
+           """
+        stream_id = self._stream_id(path)
+        with self.con as con:
+            con.execute("DELETE FROM metadata WHERE stream_id=?", (stream_id,))
+            for key in data:
+                if data[key] != '':
+                    con.execute("INSERT INTO metadata VALUES (?, ?, ?)",
+                                (stream_id, key, data[key]))
+
+    def stream_get_metadata(self, path):
+        """Return stream metadata as a dictionary."""
+        stream_id = self._stream_id(path)
+        result = self.con.execute("SELECT metadata.key, metadata.value "
+                                  "FROM metadata "
+                                  "WHERE metadata.stream_id=?", (stream_id,))
+        data = {}
+        for (key, value) in result:
+            data[key] = value
+        return data
+
+    def stream_update_metadata(self, path, newdata):
+        """Update stream metadata from a dictionary"""
+        data = self.stream_get_metadata(path)
+        data.update(newdata)
+        self.stream_set_metadata(path, data)
+
+    def stream_destroy(self, path):
+        """Fully remove a table and all of its data from the database.
+        No way to undo it!  Metadata is removed."""
+        stream_id = self._stream_id(path)
+
+        # Delete the cached interval data (if it was cached)
+        self._get_intervals.cache_remove(self, stream_id)
+
+        # Delete the data
+        self.data.destroy(path)
+
+        # Delete metadata, stream, intervals
+        with self.con as con:
+            con.execute("DELETE FROM metadata WHERE stream_id=?", (stream_id,))
+            con.execute("DELETE FROM ranges WHERE stream_id=?", (stream_id,))
+            con.execute("DELETE FROM streams WHERE id=?", (stream_id,))
+
+    def stream_insert(self, path, start, end, data):
+        """Insert new data into the database.
+           path: Path at which to add the data
+           start: Starting timestamp
+           end: Ending timestamp
+           data: Rows of data, to be passed to bulkdata table.append
+                 method.  E.g. nilmdb.layout.Parser.data
+           """
+        # First check for basic overlap using timestamp info given.
+        stream_id = self._stream_id(path)
+        iset = self._get_intervals(stream_id)
+        interval = Interval(start, end)
+        if iset.intersects(interval):
+            raise OverlapError("new data overlaps existing data at range: "
+                               + str(iset & interval))
+
+        # Insert the data
+        table = self.data.getnode(path)
+        row_start = table.nrows
+        table.append(data)
+        row_end = table.nrows
+
+        # Insert the record into the sql database.
+        self._add_interval(stream_id, interval, row_start, row_end)
+
+        # And that's all
+        return
+
+    def _find_start(self, table, dbinterval):
+        """
+        Given a DBInterval, find the row in the database that
+        corresponds to the start time.  Return the first database
+        position with a timestamp (first element) greater than or
+        equal to 'start'.
+        """
+        # Optimization for the common case where an interval wasn't truncated
+        if dbinterval.start == dbinterval.db_start:
+            return dbinterval.db_startpos
+        return bisect.bisect_left(bulkdata.TimestampOnlyTable(table),
+                                  dbinterval.start,
+                                  dbinterval.db_startpos,
+                                  dbinterval.db_endpos)
+
+    def _find_end(self, table, dbinterval):
+        """
+        Given a DBInterval, find the row in the database that follows
+        the end time.  Return the first database position after the
+        row with timestamp (first element) greater than or equal
+        to 'end'.
+        """
+        # Optimization for the common case where an interval wasn't truncated
+        if dbinterval.end == dbinterval.db_end:
+            return dbinterval.db_endpos
+        # Note that we still use bisect_left here, because we don't
+        # want to include the given timestamp in the results.  This is
+        # so a queries like 1:00 -> 2:00 and 2:00 -> 3:00 return
+        # non-overlapping data.
+        return bisect.bisect_left(bulkdata.TimestampOnlyTable(table),
+                                  dbinterval.end,
+                                  dbinterval.db_startpos,
+                                  dbinterval.db_endpos)
+
+    def stream_extract(self, path, start = None, end = None, count = False):
+        """
+        Returns (data, restart) tuple.
+
+        data is a list of raw data from the database, suitable for
+        passing to e.g. nilmdb.layout.Formatter to translate into
+        textual form.
+
+        restart, if nonzero, means that there were too many results to
+        return in a single request.  The data is complete from the
+        starting timestamp to the point at which it was truncated,
+        and a new request with a start time of 'restart' will fetch
+        the next block of data.
+
+        count, if true, means to not return raw data, but just the count
+        of rows that would have been returned.  This is much faster
+        than actually fetching the data.  It is not limited by
+        max_results.
+        """
+        stream_id = self._stream_id(path)
+        table = self.data.getnode(path)
+        intervals = self._get_intervals(stream_id)
+        (start, end) = self._check_user_times(start, end)
+        requested = Interval(start, end)
+        result = []
+        matched = 0
+        remaining = self.max_results
+        restart = 0
+        for interval in intervals.intersection(requested):
+            # Reading single rows from the table is too slow, so
+            # we use two bisections to find both the starting and
+            # ending row for this particular interval, then
+            # read the entire range as one slice.
+            row_start = self._find_start(table, interval)
+            row_end = self._find_end(table, interval)
+
+            if count:
+                matched += row_end - row_start
+                continue
+
+            # Shorten it if we'll hit the maximum number of results
+            row_max = row_start + remaining
+            if row_max < row_end:
+                row_end = row_max
+                restart = table[row_max][0]
+
+            # Gather these results up
+            result.extend(table[row_start:row_end])
+
+            # Count them
+            remaining -= row_end - row_start
+
+            if restart:
+                break
+
+        if count:
+            return matched
+        return (result, restart)
+
+    def stream_remove(self, path, start = None, end = None):
+        """
+        Remove data from the specified time interval within a stream.
+        Removes all data in the interval [start, end), and intervals
+        are truncated or split appropriately.  Returns the number of
+        data points removed.
+        """
+        stream_id = self._stream_id(path)
+        table = self.data.getnode(path)
+        intervals = self._get_intervals(stream_id)
+        (start, end) = self._check_user_times(start, end)
+        to_remove = Interval(start, end)
+        removed = 0
+
+        # Can't remove intervals from within the iterator, so we need to
+        # remember what's currently in the intersection now.
+        all_candidates = list(intervals.intersection(to_remove, orig = True))
+
+        for (dbint, orig) in all_candidates:
+            # Find row start and end
+            row_start = self._find_start(table, dbint)
+            row_end = self._find_end(table, dbint)
+
+            # Adjust the DBInterval to match the newly found ends
+            dbint.db_start = dbint.start
+            dbint.db_end = dbint.end
+            dbint.db_startpos = row_start
+            dbint.db_endpos = row_end
+
+            # Remove interval from the database
+            self._remove_interval(stream_id, orig, dbint)
+
+            # Remove data from the underlying table storage
+            table.remove(row_start, row_end)
+
+            # Count how many were removed
+            removed += row_end - row_start
+
+        return removed

nilmdb/server/rbtree.pxd

@@ -0,0 +1,23 @@
+cdef class RBNode:
+    cdef public object obj
+    cdef public double start, end
+    cdef public int red
+    cdef public RBNode left, right, parent
+
+cdef class RBTree:
+    cdef public RBNode nil, root
+
+    cpdef getroot(RBTree self)
+    cdef void __rotate_left(RBTree self, RBNode x)
+    cdef void __rotate_right(RBTree self, RBNode y)
+    cdef RBNode __successor(RBTree self, RBNode x)
+    cpdef RBNode successor(RBTree self, RBNode x)
+    cdef RBNode __predecessor(RBTree self, RBNode x)
+    cpdef RBNode predecessor(RBTree self, RBNode x)
+    cpdef insert(RBTree self, RBNode z)
+    cdef void __insert_fixup(RBTree self, RBNode x)
+    cpdef delete(RBTree self, RBNode z)
+    cdef inline void __delete_fixup(RBTree self, RBNode x)
+    cpdef RBNode find(RBTree self, double start, double end)
+    cpdef RBNode find_left_end(RBTree self, double t)
+    cpdef RBNode find_right_start(RBTree self, double t)

nilmdb/server/rbtree.pyx

@@ -0,0 +1,377 @@
+# cython: profile=False
+# cython: cdivision=True
+
+"""
+Jim Paris <jim@jtan.com>
+
+Red-black tree, where keys are stored as start/end timestamps.
+This is a basic interval tree that holds half-open intervals:
+  [start, end)
+Intervals must not overlap.  Fixing that would involve making this
+into an augmented interval tree as described in CLRS 14.3.
+
+Code that assumes non-overlapping intervals is marked with the
+string 'non-overlapping'.
+"""
+
+import sys
+cimport rbtree
+
+cdef class RBNode:
+    """One node of the Red/Black tree, containing a key (start, end)
+    and value (obj)"""
+    def __init__(self, double start, double end, object obj = None):
+        self.obj = obj
+        self.start = start
+        self.end = end
+        self.red = False
+        self.left = None
+        self.right = None
+
+    def __str__(self):
+        if self.red:
+            color = "R"
+        else:
+            color = "B"
+        if self.start == sys.float_info.min:
+            return "[node nil]"
+        return ("[node ("
+                + str(self.obj) + ") "
+                + str(self.start) + " -> " + str(self.end) + " "
+                + color + "]")
+
+cdef class RBTree:
+    """Red/Black tree"""
+
+    # Init
+    def __init__(self):
+        self.nil = RBNode(start = sys.float_info.min,
+                          end = sys.float_info.min)
+        self.nil.left = self.nil
+        self.nil.right = self.nil
+        self.nil.parent = self.nil
+
+        self.root = RBNode(start = sys.float_info.max,
+                           end = sys.float_info.max)
+        self.root.left = self.nil
+        self.root.right = self.nil
+        self.root.parent = self.nil
+
+    # We have a dummy root node to simplify operations, so from an
+    # external point of view, its left child is the real root.
+    cpdef getroot(self):
+        return self.root.left
+
+    # Rotations and basic operations
+    cdef void __rotate_left(self, RBNode x):
+        """Rotate left:
+        #   x           y
+        #  / \   -->   / \
+        # z   y       x   w
+        #    / \     / \
+        #   v   w   z   v
+        """
+        cdef RBNode y = x.right
+        x.right = y.left
+        if y.left is not self.nil:
+            y.left.parent = x
+        y.parent = x.parent
+        if x is x.parent.left:
+            x.parent.left = y
+        else:
+            x.parent.right = y
+        y.left = x
+        x.parent = y
+
+    cdef void __rotate_right(self, RBNode y):
+        """Rotate right:
+        #     y           x
+        #    / \   -->   / \
+        #   x   w       z   y
+        #  / \             / \
+        # z   v           v   w
+        """
+        cdef RBNode x = y.left
+        y.left = x.right
+        if x.right is not self.nil:
+            x.right.parent = y
+        x.parent = y.parent
+        if y is y.parent.left:
+            y.parent.left = x
+        else:
+            y.parent.right = x
+        x.right = y
+        y.parent = x
+
+    cdef RBNode __successor(self, RBNode x):
+        """Returns the successor of RBNode x"""
+        cdef RBNode y = x.right
+        if y is not self.nil:
+            while y.left is not self.nil:
+                y = y.left
+        else:
+            y = x.parent
+            while x is y.right:
+                x = y
+                y = y.parent
+            if y is self.root:
+                return self.nil
+        return y
+    cpdef RBNode successor(self, RBNode x):
+        """Returns the successor of RBNode x, or None"""
+        cdef RBNode y = self.__successor(x)
+        return y if y is not self.nil else None
+
+    cdef RBNode __predecessor(self, RBNode x):
+        """Returns the predecessor of RBNode x"""
+        cdef RBNode y = x.left
+        if y is not self.nil:
+            while y.right is not self.nil:
+                y = y.right
+        else:
+            y = x.parent
+            while x is y.left:
+                if y is self.root:
+                    y = self.nil
+                    break
+                x = y
+                y = y.parent
+        return y
+    cpdef RBNode predecessor(self, RBNode x):
+        """Returns the predecessor of RBNode x, or None"""
+        cdef RBNode y = self.__predecessor(x)
+        return y if y is not self.nil else None
+
+    # Insertion
+    cpdef insert(self, RBNode z):
+        """Insert RBNode z into RBTree and rebalance as necessary"""
+        z.left = self.nil
+        z.right = self.nil
+        cdef RBNode y = self.root
+        cdef RBNode x = self.root.left
+        while x is not self.nil:
+            y = x
+            if (x.start > z.start or (x.start == z.start and x.end > z.end)):
+                x = x.left
+            else:
+                x = x.right
+        z.parent = y
+        if (y is self.root or
+            (y.start > z.start or (y.start == z.start and y.end > z.end))):
+            y.left = z
+        else:
+            y.right = z
+        # relabel/rebalance
+        self.__insert_fixup(z)
+
+    cdef void __insert_fixup(self, RBNode x):
+        """Rebalance/fix RBTree after a simple insertion of RBNode x"""
+        x.red = True
+        while x.parent.red:
+            if x.parent is x.parent.parent.left:
+                y = x.parent.parent.right
+                if y.red:
+                    x.parent.red = False
+                    y.red = False
+                    x.parent.parent.red = True
+                    x = x.parent.parent
+                else:
+                    if x is x.parent.right:
+                        x = x.parent
+                        self.__rotate_left(x)
+                    x.parent.red = False
+                    x.parent.parent.red = True
+                    self.__rotate_right(x.parent.parent)
+            else: # same as above, left/right switched
+                y = x.parent.parent.left
+                if y.red:
+                    x.parent.red = False
+                    y.red = False
+                    x.parent.parent.red = True
+                    x = x.parent.parent
+                else:
+                    if x is x.parent.left:
+                        x = x.parent
+                        self.__rotate_right(x)
+                    x.parent.red = False
+                    x.parent.parent.red = True
+                    self.__rotate_left(x.parent.parent)
+        self.root.left.red = False
+
+    # Deletion
+    cpdef delete(self, RBNode z):
+        if z.left is None or z.right is None:
+            raise AttributeError("you can only delete a node object "
+                                 + "from the tree; use find() to get one")
+        cdef RBNode x, y
+        if z.left is self.nil or z.right is self.nil:
+            y = z
+        else:
+            y = self.__successor(z)
+        if y.left is self.nil:
+            x = y.right
+        else:
+            x = y.left
+        x.parent = y.parent
+        if x.parent is self.root:
+            self.root.left = x
+        else:
+            if y is y.parent.left:
+                y.parent.left = x
+            else:
+                y.parent.right = x
+        if y is not z:
+            # y is the node to splice out, x is its child
+            y.left = z.left
+            y.right = z.right
+            y.parent = z.parent
+            z.left.parent = y
+            z.right.parent = y
+            if z is z.parent.left:
+                z.parent.left = y
+            else:
+                z.parent.right = y
+            if not y.red:
+                y.red = z.red
+                self.__delete_fixup(x)
+            else:
+                y.red = z.red
+        else:
+            if not y.red:
+                self.__delete_fixup(x)
+
+    cdef void __delete_fixup(self, RBNode x):
+        """Rebalance/fix RBTree after a deletion.  RBNode x is the
+        child of the spliced out node."""
+        cdef RBNode rootLeft = self.root.left
+        while not x.red and x is not rootLeft:
+            if x is x.parent.left:
+                w = x.parent.right
+                if w.red:
+                    w.red = False
+                    x.parent.red = True
+                    self.__rotate_left(x.parent)
+                    w = x.parent.right
+                if not w.right.red and not w.left.red:
+                    w.red = True
+                    x = x.parent
+                else:
+                    if not w.right.red:
+                        w.left.red = False
+                        w.red = True
+                        self.__rotate_right(w)
+                        w = x.parent.right
+                    w.red = x.parent.red
+                    x.parent.red = False
+                    w.right.red = False
+                    self.__rotate_left(x.parent)
+                    x = rootLeft # exit loop
+            else: # same as above, left/right switched
+                w = x.parent.left
+                if w.red:
+                    w.red = False
+                    x.parent.red = True
+                    self.__rotate_right(x.parent)
+                    w = x.parent.left
+                if not w.left.red and not w.right.red:
+                    w.red = True
+                    x = x.parent
+                else:
+                    if not w.left.red:
+                        w.right.red = False
+                        w.red = True
+                        self.__rotate_left(w)
+                        w = x.parent.left
+                    w.red = x.parent.red
+                    x.parent.red = False
+                    w.left.red = False
+                    self.__rotate_right(x.parent)
+                    x = rootLeft # exit loop
+        x.red = False
+
+    # Walking, searching
+    def __iter__(self):
+        return self.inorder()
+
+    def inorder(self, RBNode x = None):
+        """Generator that performs an inorder walk for the tree
+        rooted at RBNode x"""
+        if x is None:
+            x = self.getroot()
+        while x.left is not self.nil:
+            x = x.left
+        while x is not self.nil:
+            yield x
+            x = self.__successor(x)
+
+    cpdef RBNode find(self, double start, double end):
+        """Return the node with exactly the given start and end."""
+        cdef RBNode x = self.getroot()
+        while x is not self.nil:
+            if start < x.start:
+                x = x.left
+            elif start == x.start:
+                if end == x.end:
+                    break # found it
+                elif end < x.end:
+                    x = x.left
+                else:
+                    x = x.right
+            else:
+                x = x.right
+        return x if x is not self.nil else None
+
+    cpdef RBNode find_left_end(self, double t):
+        """Find the leftmode node with end >= t.  With non-overlapping
+        intervals, this is the first node that might overlap time t.
+
+        Note that this relies on non-overlapping intervals, since
+        it assumes that we can use the endpoints to traverse the
+        tree even though it was created using the start points."""
+        cdef RBNode x = self.getroot()
+        while x is not self.nil:
+            if t < x.end:
+                if x.left is self.nil:
+                    break
+                x = x.left
+            elif t == x.end:
+                break
+            else:
+                if x.right is self.nil:
+                    x = self.__successor(x)
+                    break
+                x = x.right
+        return x if x is not self.nil else None
+
+    cpdef RBNode find_right_start(self, double t):
+        """Find the rightmode node with start <= t.  With non-overlapping
+        intervals, this is the last node that might overlap time t."""
+        cdef RBNode x = self.getroot()
+        while x is not self.nil:
+            if t < x.start:
+                if x.left is self.nil:
+                    x = self.__predecessor(x)
+                    break
+                x = x.left
+            elif t == x.start:
+                break
+            else:
+                if x.right is self.nil:
+                    break
+                x = x.right
+        return x if x is not self.nil else None
+
+    # Intersections
+    def intersect(self, double start, double end):
+        """Generator that returns nodes that overlap the given
+        (start,end) range.  Assumes non-overlapping intervals."""
+        # Start with the leftmode node that ends after start
+        cdef RBNode n = self.find_left_end(start)
+        while n is not None:
+            if n.start >= end:
+                # this node starts after the requested end; we're done
+                break
+            if start < n.end:
+                # this node overlaps our requested area
+                yield n
+            n = self.successor(n)

nilmdb/server/rbtree.pyxdep

@@ -0,0 +1 @@
+rbtree.pxd

nilmdb/server/server.py

@@ -0,0 +1,502 @@
+"""CherryPy-based server for accessing NILM database via HTTP"""
+
+# Need absolute_import so that "import nilmdb" won't pull in
+# nilmdb.py, but will pull the nilmdb module instead.
+from __future__ import absolute_import
+import nilmdb
+from nilmdb.utils.printf import *
+from nilmdb.server.errors import NilmDBError
+
+import cherrypy
+import sys
+import os
+import simplejson as json
+import decorator
+import traceback
+import psutil
+
+try:
+    cherrypy.tools.json_out
+except: # pragma: no cover
+    sys.stderr.write("Cherrypy 3.2+ required\n")
+    sys.exit(1)
+
+class NilmApp(object):
+    def __init__(self, db):
+        self.db = db
+
+# Decorators
+def chunked_response(func):
+    """Decorator to enable chunked responses."""
+    # Set this to False to get better tracebacks from some requests
+    # (/stream/extract, /stream/intervals).
+    func._cp_config = { 'response.stream': True }
+    return func
+
+def response_type(content_type):
+    """Return a decorator-generating function that sets the
+    response type to the specified string."""
+    def wrapper(func, *args, **kwargs):
+        cherrypy.response.headers['Content-Type'] = content_type
+        return func(*args, **kwargs)
+    return decorator.decorator(wrapper)
+
+@decorator.decorator
+def workaround_cp_bug_1200(func, *args, **kwargs): # pragma: no cover
+    """Decorator to work around CherryPy bug #1200 in a response
+    generator.
+
+    Even if chunked responses are disabled, LookupError or
+    UnicodeError exceptions may still be swallowed by CherryPy due to
+    bug #1200.  This throws them as generic Exceptions instead so that
+    they make it through.
+    """
+    try:
+        for val in func(*args, **kwargs):
+            yield val
+    except (LookupError, UnicodeError):
+        raise Exception("bug workaround; real exception is:\n" +
+                        traceback.format_exc())
+
+def exception_to_httperror(*expected):
+    """Return a decorator-generating function that catches expected
+    errors and throws a HTTPError describing it instead.
+
+        @exception_to_httperror(NilmDBError, ValueError)
+        def foo():
+            pass
+    """
+    def wrapper(func, *args, **kwargs):
+        try:
+            return func(*args, **kwargs)
+        except expected as e:
+            message = sprintf("%s", str(e))
+            raise cherrypy.HTTPError("400 Bad Request", message)
+    # We need to preserve the function's argspecs for CherryPy to
+    # handle argument errors correctly.  Decorator.decorator takes
+    # care of that.
+    return decorator.decorator(wrapper)
+
+# CherryPy apps
+class Root(NilmApp):
+    """Root application for NILM database"""
+
+    def __init__(self, db):
+        super(Root, self).__init__(db)
+
+    # /
+    @cherrypy.expose
+    def index(self):
+        raise cherrypy.NotFound()
+
+    # /favicon.ico
+    @cherrypy.expose
+    def favicon_ico(self):
+        raise cherrypy.NotFound()
+
+    # /version
+    @cherrypy.expose
+    @cherrypy.tools.json_out()
+    def version(self):
+        return nilmdb.__version__
+
+    # /dbinfo
+    @cherrypy.expose
+    @cherrypy.tools.json_out()
+    def dbinfo(self):
+        """Return a dictionary with the database path,
+        size of the database in bytes, and free disk space in bytes"""
+        path = self.db.get_basepath()
+        return { "path": path,
+                 "size": nilmdb.utils.du(path),
+                 "free": psutil.disk_usage(path).free }
+
+class Stream(NilmApp):
+    """Stream-specific operations"""
+
+    # /stream/list
+    # /stream/list?layout=PrepData
+    # /stream/list?path=/newton/prep
+    @cherrypy.expose
+    @cherrypy.tools.json_out()
+    def list(self, path = None, layout = None):
+        """List all streams in the database.  With optional path or
+        layout parameter, just list streams that match the given path
+        or layout"""
+        return self.db.stream_list(path, layout)
+
+    # /stream/create?path=/newton/prep&layout=PrepData
+    @cherrypy.expose
+    @cherrypy.tools.json_out()
+    @exception_to_httperror(NilmDBError, ValueError)
+    def create(self, path, layout):
+        """Create a new stream in the database.  Provide path
+        and one of the nilmdb.layout.layouts keys.
+        """
+        return self.db.stream_create(path, layout)
+
+    # /stream/destroy?path=/newton/prep
+    @cherrypy.expose
+    @cherrypy.tools.json_out()
+    @exception_to_httperror(NilmDBError)
+    def destroy(self, path):
+        """Delete a stream and its associated data."""
+        return self.db.stream_destroy(path)
+
+    # /stream/get_metadata?path=/newton/prep
+    # /stream/get_metadata?path=/newton/prep&key=foo&key=bar
+    @cherrypy.expose
+    @cherrypy.tools.json_out()
+    def get_metadata(self, path, key=None):
+        """Get metadata for the named stream.  If optional
+        key parameters are specified, only return metadata
+        matching the given keys."""
+        try:
+            data = self.db.stream_get_metadata(path)
+        except nilmdb.server.nilmdb.StreamError as e:
+            raise cherrypy.HTTPError("404 Not Found", e.message)
+        if key is None:  # If no keys specified, return them all
+            key = data.keys()
+        elif not isinstance(key, list):
+            key = [ key ]
+        result = {}
+        for k in key:
+            if k in data:
+                result[k] = data[k]
+            else: # Return "None" for keys with no matching value
+                result[k] = None
+        return result
+
+    # /stream/set_metadata?path=/newton/prep&data=<json>
+    @cherrypy.expose
+    @cherrypy.tools.json_out()
+    @exception_to_httperror(NilmDBError, LookupError, TypeError)
+    def set_metadata(self, path, data):
+        """Set metadata for the named stream, replacing any
+        existing metadata.  Data should be a json-encoded
+        dictionary"""
+        data_dict = json.loads(data)
+        self.db.stream_set_metadata(path, data_dict)
+
+    # /stream/update_metadata?path=/newton/prep&data=<json>
+    @cherrypy.expose
+    @cherrypy.tools.json_out()
+    @exception_to_httperror(NilmDBError, LookupError, TypeError)
+    def update_metadata(self, path, data):
+        """Update metadata for the named stream.  Data
+        should be a json-encoded dictionary"""
+        data_dict = json.loads(data)
+        self.db.stream_update_metadata(path, data_dict)
+
+    # /stream/insert?path=/newton/prep
+    @cherrypy.expose
+    @cherrypy.tools.json_out()
+    #@cherrypy.tools.disable_prb()
+    def insert(self, path, start, end):
+        """
+        Insert new data into the database.  Provide textual data
+        (matching the path's layout) as a HTTP PUT.
+        """
+        # Important that we always read the input before throwing any
+        # errors, to keep lengths happy for persistent connections.
+        # However, CherryPy 3.2.2 has a bug where this fails for GET
+        # requests, so catch that. (issue #1134)
+        try:
+            body = cherrypy.request.body.read()
+        except TypeError:
+            raise cherrypy.HTTPError("400 Bad Request", "No request body")
+
+        # Check path and get layout
+        streams = self.db.stream_list(path = path)
+        if len(streams) != 1:
+            raise cherrypy.HTTPError("404 Not Found", "No such stream")
+        layout = streams[0][1]
+
+        # Parse the input data
+        try:
+            parser = nilmdb.server.layout.Parser(layout)
+            parser.parse(body)
+        except nilmdb.server.layout.ParserError as e:
+            raise cherrypy.HTTPError("400 Bad Request",
+                                     "error parsing input data: " +
+                                     e.message)
+
+        # Check limits
+        start = float(start)
+        end = float(end)
+        if start >= end:
+            raise cherrypy.HTTPError("400 Bad Request",
+                                     "start must precede end")
+        if parser.min_timestamp is not None and parser.min_timestamp < start:
+            raise cherrypy.HTTPError("400 Bad Request", "Data timestamp " +
+                                     repr(parser.min_timestamp) +
+                                     " < start time " + repr(start))
+        if parser.max_timestamp is not None and parser.max_timestamp >= end:
+            raise cherrypy.HTTPError("400 Bad Request", "Data timestamp " +
+                                     repr(parser.max_timestamp) +
+                                     " >= end time " + repr(end))
+
+        # Now do the nilmdb insert, passing it the parser full of data.
+        try:
+            self.db.stream_insert(path, start, end, parser.data)
+        except NilmDBError as e:
+            raise cherrypy.HTTPError("400 Bad Request", e.message)
+
+        # Done
+        return
+
+    # /stream/remove?path=/newton/prep
+    # /stream/remove?path=/newton/prep&start=1234567890.0&end=1234567899.0
+    @cherrypy.expose
+    @cherrypy.tools.json_out()
+    @exception_to_httperror(NilmDBError)
+    def remove(self, path, start = None, end = None):
+        """
+        Remove data from the backend database.  Removes all data in
+        the interval [start, end).  Returns the number of data points
+        removed.
+        """
+        if start is not None:
+            start = float(start)
+        if end is not None:
+            end = float(end)
+        if start is not None and end is not None:
+            if start >= end:
+                raise cherrypy.HTTPError("400 Bad Request",
+                                         "start must precede end")
+        return self.db.stream_remove(path, start, end)
+
+    # /stream/intervals?path=/newton/prep
+    # /stream/intervals?path=/newton/prep&start=1234567890.0&end=1234567899.0
+    @cherrypy.expose
+    @chunked_response
+    @response_type("text/plain")
+    def intervals(self, path, start = None, end = None):
+        """
+        Get intervals from backend database.  Streams the resulting
+        intervals as JSON strings separated by newlines.  This may
+        make multiple requests to the nilmdb backend to avoid causing
+        it to block for too long.
+
+        Note that the response type is set to 'text/plain' even
+        though we're sending back JSON; this is because we're not
+        really returning a single JSON object.
+        """
+        if start is not None:
+            start = float(start)
+        if end is not None:
+            end = float(end)
+
+        if start is not None and end is not None:
+            if start >= end:
+                raise cherrypy.HTTPError("400 Bad Request",
+                                         "start must precede end")
+
+        streams = self.db.stream_list(path = path)
+        if len(streams) != 1:
+            raise cherrypy.HTTPError("404 Not Found", "No such stream")
+
+        @workaround_cp_bug_1200
+        def content(start, end):
+            # Note: disable chunked responses to see tracebacks from here.
+            while True:
+                (intervals, restart) = self.db.stream_intervals(path, start, end)
+                response = ''.join([ json.dumps(i) + "\n" for i in intervals ])
+                yield response
+                if restart == 0:
+                    break
+                start = restart
+        return content(start, end)
+
+    # /stream/extract?path=/newton/prep&start=1234567890.0&end=1234567899.0
+    @cherrypy.expose
+    @chunked_response
+    @response_type("text/plain")
+    def extract(self, path, start = None, end = None, count = False):
+        """
+        Extract data from backend database.  Streams the resulting
+        entries as ASCII text lines separated by newlines.  This may
+        make multiple requests to the nilmdb backend to avoid causing
+        it to block for too long.
+
+        Add count=True to return a count rather than actual data.
+        """
+        if start is not None:
+            start = float(start)
+        if end is not None:
+            end = float(end)
+
+        # Check parameters
+        if start is not None and end is not None:
+            if start >= end:
+                raise cherrypy.HTTPError("400 Bad Request",
+                                         "start must precede end")
+
+        # Check path and get layout
+        streams = self.db.stream_list(path = path)
+        if len(streams) != 1:
+            raise cherrypy.HTTPError("404 Not Found", "No such stream")
+        layout = streams[0][1]
+
+        # Get formatter
+        formatter = nilmdb.server.layout.Formatter(layout)
+
+        @workaround_cp_bug_1200
+        def content(start, end, count):
+            # Note: disable chunked responses to see tracebacks from here.
+            if count:
+                matched = self.db.stream_extract(path, start, end, count)
+                yield sprintf("%d\n", matched)
+                return
+
+            while True:
+                (data, restart) = self.db.stream_extract(path, start, end)
+
+                # Format the data and yield it
+                yield formatter.format(data)
+
+                if restart == 0:
+                    return
+                start = restart
+        return content(start, end, count)
+
+class Exiter(object):
+    """App that exits the server, for testing"""
+    @cherrypy.expose
+    def index(self):
+        cherrypy.response.headers['Content-Type'] = 'text/plain'
+        def content():
+            yield 'Exiting by request'
+            raise SystemExit
+        return content()
+    index._cp_config = { 'response.stream': True }
+
+class Server(object):
+    def __init__(self, db, host = '127.0.0.1', port = 8080,
+                 stoppable = False,       # whether /exit URL exists
+                 embedded = True,         # hide diagnostics and output, etc
+                 fast_shutdown = False,   # don't wait for clients to disconn.
+                 force_traceback = False  # include traceback in all errors
+                 ):
+        # Save server version, just for verification during tests
+        self.version = nilmdb.__version__
+
+        # Need to wrap DB object in a serializer because we'll call
+        # into it from separate threads.
+        self.embedded = embedded
+        self.db = nilmdb.utils.Serializer(db)
+
+        # Build up global server configuration
+        cherrypy.config.update({
+            'server.socket_host': host,
+            'server.socket_port': port,
+            'engine.autoreload_on': False,
+            'server.max_request_body_size': 4*1024*1024,
+            })
+        if self.embedded:
+            cherrypy.config.update({ 'environment': 'embedded' })
+
+        # Build up application specific configuration
+        app_config = {}
+        app_config.update({
+            'error_page.default': self.json_error_page,
+            })
+
+        # Send a permissive Access-Control-Allow-Origin (CORS) header
+        # with all responses so that browsers can send cross-domain
+        # requests to this server.
+        app_config.update({ 'response.headers.Access-Control-Allow-Origin':
+                            '*' })
+
+        # Send tracebacks in error responses.  They're hidden by the
+        # error_page function for client errors (code 400-499).
+        app_config.update({ 'request.show_tracebacks' : True })
+        self.force_traceback = force_traceback
+
+        # Patch CherryPy error handler to never pad out error messages.
+        # This isn't necessary, but then again, neither is padding the
+        # error messages.
+        cherrypy._cperror._ie_friendly_error_sizes = {}
+
+        # Build up the application and mount it
+        root = Root(self.db)
+        root.stream = Stream(self.db)
+        if stoppable:
+            root.exit = Exiter()
+        cherrypy.tree.apps = {}
+        cherrypy.tree.mount(root, "/", config = { "/" : app_config })
+
+        # Shutdowns normally wait for clients to disconnect.  To speed
+        # up tests, set fast_shutdown = True
+        if fast_shutdown:
+            # Setting timeout to 0 triggers os._exit(70) at shutdown, grr...
+            cherrypy.server.shutdown_timeout = 0.01
+        else:
+            cherrypy.server.shutdown_timeout = 5
+
+    def json_error_page(self, status, message, traceback, version):
+        """Return a custom error page in JSON so the client can parse it"""
+        errordata = { "status" : status,
+                      "message" : message,
+                      "traceback" : traceback }
+        # Don't send a traceback if the error was 400-499 (client's fault)
+        try:
+            code = int(status.split()[0])
+            if not self.force_traceback:
+                if code >= 400 and code <= 499:
+                    errordata["traceback"] = ""
+        except Exception: # pragma: no cover
+            pass
+        # Override the response type, which was previously set to text/html
+        cherrypy.serving.response.headers['Content-Type'] = (
+            "application/json;charset=utf-8" )
+        # Undo the HTML escaping that cherrypy's get_error_page function applies
+        # (cherrypy issue 1135)
+        for k, v in errordata.iteritems():
+            v = v.replace("&lt;","<")
+            v = v.replace("&gt;",">")
+            v = v.replace("&amp;","&")
+            errordata[k] = v
+        return json.dumps(errordata, separators=(',',':'))
+
+    def start(self, blocking = False, event = None):
+
+        if not self.embedded: # pragma: no cover
+            # Handle signals nicely
+            if hasattr(cherrypy.engine, "signal_handler"):
+                cherrypy.engine.signal_handler.subscribe()
+            if hasattr(cherrypy.engine, "console_control_handler"):
+                cherrypy.engine.console_control_handler.subscribe()
+
+        # Cherrypy stupidly calls os._exit(70) when it can't bind the
+        # port.  At least try to print a reasonable error and continue
+        # in this case, rather than just dying silently (as we would
+        # otherwise do in embedded mode)
+        real_exit = os._exit
+        def fake_exit(code): # pragma: no cover
+            if code == os.EX_SOFTWARE:
+                fprintf(sys.stderr, "error: CherryPy called os._exit!\n")
+            else:
+                real_exit(code)
+        os._exit = fake_exit
+        cherrypy.engine.start()
+        os._exit = real_exit
+
+        # Signal that the engine has started successfully
+        if event is not None:
+            event.set()
+
+        if blocking:
+            try:
+                cherrypy.engine.wait(cherrypy.engine.states.EXITING,
+                                     interval = 0.1, channel = 'main')
+            except (KeyboardInterrupt, IOError): # pragma: no cover
+                cherrypy.engine.log('Keyboard Interrupt: shutting down bus')
+                cherrypy.engine.exit()
+            except SystemExit: # pragma: no cover
+                cherrypy.engine.log('SystemExit raised: shutting down bus')
+                cherrypy.engine.exit()
+                raise
+
+    def stop(self):
+        cherrypy.engine.exit()

nilmdb/test_fileinterval.py

@@ -1,46 +0,0 @@
-from nilmdb import Interval, IntervalSet, IntervalError, FileInterval
-from datetime import datetime
-from nose.tools import assert_raises
-
-from test_interval import iset
-
-def fiset(string):
-    """Like iset, but builds with FileIntervals instead of Intervals"""
-    iset = IntervalSet()
-    for i, c in enumerate(string):
-        day = datetime.strptime("{0:04d}".format(i+2000), "%Y")
-        if (c == "["):
-            start = day
-        elif (c == "|"):
-            iset += FileInterval(start, day, "test.dat")
-            start = day
-        elif (c == "]"):
-            iset += FileInterval(start, day, "test.dat")
-            del start
-    return iset
-
-def test_fileinterval_vs_interval():
-    """Test FileInterval/Interval inheritance"""
-
-    i = iset("[--]")
-    f = fiset("[--]")
-
-    # check types
-    assert(isinstance(i[0], Interval))
-    assert(not isinstance(i[0], FileInterval))
-    assert(isinstance(f[0], Interval))
-    assert(isinstance(f[0], FileInterval))
-
-    # when doing an intersection, result should be a subset of the first arg
-    u = (i & f)
-    assert(isinstance(u[0], Interval))
-    assert(not isinstance(u[0], FileInterval))
-    u = (f & i)
-    assert(isinstance(u[0], Interval))
-    assert(isinstance(u[0], FileInterval))
-
-    # they're still the same though
-    assert(i == f == u)
-
-    # just for coverage
-    assert_raises(IntervalError, fiset("[]")[0].subset, f[0].start, f[0].end)

nilmdb/test_interval.py

@@ -1,188 +0,0 @@
-from nilmdb import Interval, IntervalSet, IntervalError
-from datetime import datetime
-from nose.tools import assert_raises
-import itertools 
-
-def test_interval():
-    """Test the Interval class"""
-    d1 = datetime.strptime("19801205","%Y%m%d")
-    d2 = datetime.strptime("19900216","%Y%m%d")
-    d3 = datetime.strptime("20111205","%Y%m%d")
-
-    # basic construction
-    i = Interval(d1, d1)
-    i = Interval(d1, d3)
-    assert(i.start == d1)
-    assert(i.end == d3)
-
-    # assignment should work
-    i.start = d2
-    try:
-        i.end = d1
-        raise Exception("should have died there")
-    except IntervalError:
-        pass
-    i.start = d1
-    i.end = d2
-
-    # end before start
-    assert_raises(IntervalError, Interval, d3, d1)
-
-    # wrong type
-    assert_raises(IntervalError, Interval, 1, 2)
-
-    # compare
-    assert(Interval(d1, d2) == Interval(d1, d2))
-    assert(Interval(d1, d2) < Interval(d1, d3))
-    assert(Interval(d1, d3) > Interval(d1, d2))
-    assert(Interval(d1, d2) < Interval(d2, d3))
-    assert(Interval(d1, d3) < Interval(d2, d3))
-    assert(Interval(d2, d2) > Interval(d1, d3))
-    assert(Interval(d3, d3) == Interval(d3, d3))
-    assert_raises(TypeError, cmp, i, 123)
-
-    # subset
-    assert(Interval(d1, d3).subset(d1, d2) == Interval(d1, d2))
-    assert_raises(IntervalError, Interval(d2, d3).subset, d1, d2)
-
-    # append
-    assert(Interval(d1, d2).is_adjacent(Interval(d2,d3)))
-    assert(Interval(d2, d3).is_adjacent(Interval(d1,d2)))
-    assert(not Interval(d2, d3).is_adjacent(Interval(d1,d3)))
-    assert_raises(TypeError, Interval(d1, d2).is_adjacent, 1)
-
-    # misc
-    assert(repr(i) == repr(eval(repr(i).replace("datetime.",""))))
-    assert(str(i) == "[1980-12-05 00:00:00 -> 1990-02-16 00:00:00]")
-
-def test_interval_intersect():
-    """Test Interval intersections"""
-    dates = [ datetime.strptime(year, "%y") for year in [ "00", "01", "02", "03" ] ]
-    perm = list(itertools.permutations(dates, 2))
-    prod = list(itertools.product(perm, perm))
-    should_intersect = {
-        False: [4, 5, 8, 20, 48, 56, 60, 96, 97, 100],
-        True: [0, 1, 2, 12, 13, 14, 16, 17, 24, 25, 26, 28, 29,
-               32, 49, 50, 52, 53, 61, 62, 64, 65, 68, 98, 101, 104]}
-    for i,((a,b),(c,d)) in enumerate(prod):
-        try:
-            i1 = Interval(a, b)
-            i2 = Interval(c, d)
-            assert(i1.intersects(i2) == i2.intersects(i1))
-            assert(i in should_intersect[i1.intersects(i2)])
-        except IntervalError:
-            assert(i not in should_intersect[True] and
-                   i not in should_intersect[False])
-    assert_raises(TypeError, i1.intersects, 1234)
-
-def test_intervalset_construct():
-    """Test interval set construction"""
-    dates = [ datetime.strptime(year, "%y") for year in [ "00", "01", "02", "03" ]]
-
-    a = Interval(dates[0], dates[1])
-    b = Interval(dates[1], dates[2])
-    c = Interval(dates[0], dates[2])
-    d = Interval(dates[2], dates[3])
-
-    iseta = IntervalSet(a)
-    isetb = IntervalSet([a, b])
-    isetc = IntervalSet([a])
-    assert(iseta != isetb)
-    assert(iseta == isetc)
-    assert(iseta != 3)
-    assert(IntervalSet(a) != IntervalSet(b))
-    
-    assert_raises(TypeError, cmp, iseta, isetb)
-    assert_raises(IntervalError, IntervalSet, [a, b, c])
-    assert_raises(TypeError, IntervalSet, [1, 2])
-
-    iset = IntervalSet(isetb)   # test iterator
-    assert(iset == isetb)
-    assert(len(iset) == 2)
-    assert(len(IntervalSet()) == 0)
-
-    # Test adding
-    iset = IntervalSet(a)
-    iset += IntervalSet(b)
-    assert(iset == IntervalSet([a, b]))
-    iset = IntervalSet(a)
-    iset += b
-    assert(iset == IntervalSet([a, b]))
-    iset = IntervalSet(a) + IntervalSet(b)
-    assert(iset == IntervalSet([a, b]))
-    iset = IntervalSet(b) + a
-    assert(iset == IntervalSet([a, b]))
-
-    # A set consisting of [0-1],[1-2] should match a set consisting of [0-2]
-    assert(IntervalSet([a,b]) == IntervalSet([c]))
-    # Etc
-    assert(IntervalSet([a,d]) != IntervalSet([c]))
-    assert(IntervalSet([c]) != IntervalSet([a,d]))
-    assert(IntervalSet([c,d]) != IntervalSet([b,d]))
-    
-    # misc
-    assert(repr(iset) == repr(eval(repr(iset).replace("datetime.",""))))
-
-def iset(string):
-    """Build an IntervalSet from a string, for testing purposes
-
-    Each character is a year
-    [ = interval start
-    | = interval end + adjacent start
-    ] = interval end
-    anything else is ignored
-    """
-    iset = IntervalSet()
-    for i, c in enumerate(string):
-        day = datetime.strptime("{0:04d}".format(i+2000), "%Y")
-        if (c == "["):
-            start = day
-        elif (c == "|"):
-            iset += Interval(start, day)
-            start = day
-        elif (c == "]"):
-            iset += Interval(start, day)
-            del start
-    return iset
-
-def test_intervalset_iset():
-    """Test basic iset construction"""
-    assert(iset("  [----]   ") ==
-           iset("  [-|--]   "))
-
-    assert(iset("[]  [--]   ") +
-           iset(" []    [--]") ==
-           iset("[|] [-----]"))
-
-def test_intervalset_intsersect():
-    """Test intersection (&)"""
-    assert_raises(TypeError, iset("[--]").__and__, 1234)
-    
-    assert(iset("[---------]") &
-           iset(" [---]     ") ==
-           iset(" [---]     "))
-
-    assert(iset(" [---]     ") &
-           iset("[---------]") ==
-           iset(" [---]     "))
-
-    assert(iset("    [-----]") &
-           iset(" [-----]   ") ==
-           iset("    [--]   "))
-
-    assert(iset("      [---]") &
-           iset(" [--]      ") ==
-           iset("           "))
-
-    assert(iset("    [-|---]") &
-           iset(" [-----|-] ") ==
-           iset("    [----] "))
-
-    assert(iset("    [-|-]  ") &
-           iset(" [-|--|--] ") ==
-           iset("    [---]  "))
-
-    assert(iset(" [----][--]") &
-           iset("[-] [--] []") ==
-           iset(" [] [-]  []"))
-

nilmdb/utils/__init__.py

@@ -0,0 +1,10 @@
+"""NilmDB utilities"""
+
+from nilmdb.utils.timer import Timer
+from nilmdb.utils.iteratorizer import Iteratorizer
+from nilmdb.utils.serializer import Serializer
+from nilmdb.utils.lrucache import lru_cache
+from nilmdb.utils.diskusage import du, human_size
+from nilmdb.utils.mustclose import must_close
+from nilmdb.utils.urllib import urlencode
+from nilmdb.utils import atomic

nilmdb/utils/atomic.py

@@ -0,0 +1,26 @@
+# Atomic file writing helper.
+
+import os
+
+def replace_file(filename, content):
+    """Attempt to atomically and durably replace the filename with the
+    given contents.  This is intended to be 'pretty good on most
+    OSes', but not necessarily bulletproof."""
+
+    newfilename = filename + ".new"
+
+    # Write to new file, flush it
+    with open(newfilename, "wb") as f:
+        f.write(content)
+        f.flush()
+        os.fsync(f.fileno())
+
+    # Move new file over old one
+    try:
+        os.rename(newfilename, filename)
+    except OSError: # pragma: no cover
+        # Some OSes might not support renaming over an existing file.
+        # This is definitely NOT atomic!
+        os.remove(filename)
+        os.rename(newfilename, filename)
+

nilmdb/utils/datetime_tz/__init__.py

@@ -0,0 +1,710 @@
+#!/usr/bin/python
+#
+# Copyright 2009 Google Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+#
+# Disable the invalid name warning as we are inheriting from a standard library
+# object.
+# pylint: disable-msg=C6409,W0212
+
+"""A version of the datetime module which *cares* about timezones.
+
+This module will never return a naive datetime object. This requires the module
+know your local timezone, which it tries really hard to figure out.
+
+You can override the detection by using the datetime.tzaware.defaulttz_set
+method. It the module is unable to figure out the timezone itself this method
+*must* be called before the normal module is imported. If done before importing
+it can also speed up the time taken to import as the defaulttz will no longer
+try and do the detection.
+"""
+
+__author__ = "tansell@google.com (Tim Ansell)"
+
+import calendar
+import datetime
+import os
+import os.path
+import re
+import time
+import warnings
+import dateutil.parser
+import dateutil.relativedelta
+import dateutil.tz
+import pytz
+import pytz_abbr
+
+
+try:
+  # pylint: disable-msg=C6204
+  import functools
+except ImportError, e:
+
+  class functools(object):
+    """Fake replacement for a full functools."""
+
+    # pylint: disable-msg=W0613
+    @staticmethod
+    def wraps(f, *args, **kw):
+      return f
+
+
+# Need to patch pytz.utc to have a _utcoffset so you can normalize/localize
+# using it.
+pytz.utc._utcoffset = datetime.timedelta()
+
+
+timedelta = datetime.timedelta
+
+
+def _tzinfome(tzinfo):
+  """Gets a tzinfo object from a string.
+
+  Args:
+    tzinfo: A string (or string like) object, or a datetime.tzinfo object.
+
+  Returns:
+    An datetime.tzinfo object.
+
+  Raises:
+    UnknownTimeZoneError: If the timezone given can't be decoded.
+  """
+  if not isinstance(tzinfo, datetime.tzinfo):
+    try:
+      tzinfo = pytz.timezone(tzinfo)
+    except AttributeError:
+      raise pytz.UnknownTimeZoneError("Unknown timezone! %s" % tzinfo)
+  return tzinfo
+
+
+# Our "local" timezone
+_localtz = None
+
+
+def localtz():
+  """Get the local timezone.
+
+  Returns:
+    The localtime timezone as a tzinfo object.
+  """
+  # pylint: disable-msg=W0603
+  global _localtz
+  if _localtz is None:
+    _localtz = detect_timezone()
+  return _localtz
+
+
+def localtz_set(timezone):
+  """Set the local timezone."""
+  # pylint: disable-msg=W0603
+  global _localtz
+  _localtz = _tzinfome(timezone)
+
+
+def detect_timezone():
+  """Try and detect the timezone that Python is currently running in.
+
+  We have a bunch of different methods for trying to figure this out (listed in
+  order they are attempted).
+    * Try TZ environment variable.
+    * Try and find /etc/timezone file (with timezone name).
+    * Try and find /etc/localtime file (with timezone data).
+    * Try and match a TZ to the current dst/offset/shortname.
+
+  Returns:
+    The detected local timezone as a tzinfo object
+
+  Raises:
+    pytz.UnknownTimeZoneError: If it was unable to detect a timezone.
+  """
+  # First we try the TZ variable
+  tz = _detect_timezone_environ()
+  if tz is not None:
+    return tz
+
+  # Second we try /etc/timezone and use the value in that
+  tz = _detect_timezone_etc_timezone()
+  if tz is not None:
+    return tz
+
+  # Next we try and see if something matches the tzinfo in /etc/localtime
+  tz = _detect_timezone_etc_localtime()
+  if tz is not None:
+    return tz
+
+  # Next we try and use a similiar method to what PHP does.
+  # We first try to search on time.tzname, time.timezone, time.daylight to
+  # match a pytz zone.
+  warnings.warn("Had to fall back to worst detection method (the 'PHP' "
+                "method).")
+
+  tz = _detect_timezone_php()
+  if tz is not None:
+    return tz
+
+  raise pytz.UnknownTimeZoneError("Unable to detect your timezone!")
+
+
+def _detect_timezone_environ():
+  if "TZ" in os.environ:
+    try:
+      return pytz.timezone(os.environ["TZ"])
+    except (IOError, pytz.UnknownTimeZoneError):
+      warnings.warn("You provided a TZ environment value (%r) we did not "
+                    "understand!" % os.environ["TZ"])
+
+
+def _detect_timezone_etc_timezone():
+  if os.path.exists("/etc/timezone"):
+    try:
+      tz = file("/etc/timezone").read().strip()
+      try:
+        return pytz.timezone(tz)
+      except (IOError, pytz.UnknownTimeZoneError), ei:
+        warnings.warn("Your /etc/timezone file references a timezone (%r) that"
+                      " is not valid (%r)." % (tz, ei))
+
+    # Problem reading the /etc/timezone file
+    except IOError, eo:
+      warnings.warn("Could not access your /etc/timezone file: %s" % eo)
+
+
+def _detect_timezone_etc_localtime():
+  matches = []
+  if os.path.exists("/etc/localtime"):
+    localtime = pytz.tzfile.build_tzinfo("/etc/localtime",
+                                         file("/etc/localtime"))
+
+    # See if we can find a "Human Name" for this..
+    for tzname in pytz.all_timezones:
+      tz = _tzinfome(tzname)
+
+      if dir(tz) != dir(localtime):
+        continue
+
+      for attrib in dir(tz):
+        # Ignore functions and specials
+        if callable(getattr(tz, attrib)) or attrib.startswith("__"):
+          continue
+
+        # This will always be different
+        if attrib == "zone" or attrib == "_tzinfos":
+          continue
+
+        if getattr(tz, attrib) != getattr(localtime, attrib):
+          break
+
+      # We get here iff break didn't happen, i.e. no meaningful attributes
+      # differ between tz and localtime
+      else:
+        matches.append(tzname)
+
+    if len(matches) == 1:
+      return _tzinfome(matches[0])
+    else:
+      # Warn the person about this!
+      warning = "Could not get a human name for your timezone: "
+      if len(matches) > 1:
+        warning += ("We detected multiple matches for your /etc/localtime. "
+                    "(Matches where %s)" % matches)
+        return _tzinfome(matches[0])
+      else:
+        warning += "We detected no matches for your /etc/localtime."
+      warnings.warn(warning)
+
+      # Register /etc/localtime as the timezone loaded.
+      pytz._tzinfo_cache['/etc/localtime'] = localtime
+      return localtime
+
+
+def _detect_timezone_php():
+  tomatch = (time.tzname[0], time.timezone, time.daylight)
+  now = datetime.datetime.now()
+
+  matches = []
+  for tzname in pytz.all_timezones:
+    try:
+      tz = pytz.timezone(tzname)
+    except IOError:
+      continue
+
+    try:
+      indst = tz.localize(now).timetuple()[-1]
+
+      if tomatch == (tz._tzname, -tz._utcoffset.seconds, indst):
+        matches.append(tzname)
+
+    # pylint: disable-msg=W0704
+    except AttributeError:
+      pass
+
+  if len(matches) > 1:
+    warnings.warn("We detected multiple matches for the timezone, choosing "
+                  "the first %s. (Matches where %s)" % (matches[0], matches))
+    return pytz.timezone(matches[0])
+
+
+class datetime_tz(datetime.datetime):
+  """An extension of the inbuilt datetime adding more functionality.
+
+  The extra functionality includes:
+    * Partial parsing support (IE 2006/02/30 matches %Y/%M/%D %H:%M)
+    * Full integration with pytz (just give it the string of the timezone!)
+    * Proper support for going to/from Unix timestamps (which are in UTC!).
+  """
+  __slots__ = ["is_dst"]
+
+  def __new__(cls, *args, **kw):
+    args = list(args)
+    if not args:
+      raise TypeError("Not enough arguments given.")
+
+    # See if we are given a tzinfo object...
+    tzinfo = None
+    if isinstance(args[-1], (datetime.tzinfo, basestring)):
+      tzinfo = _tzinfome(args.pop(-1))
+    elif kw.get("tzinfo", None) is not None:
+      tzinfo = _tzinfome(kw.pop("tzinfo"))
+
+    # Create a datetime object if we don't have one
+    if isinstance(args[0], datetime.datetime):
+      # Convert the datetime instance to a datetime object.
+      newargs = (list(args[0].timetuple()[0:6]) +
+                 [args[0].microsecond, args[0].tzinfo])
+      dt = datetime.datetime(*newargs)
+
+      if tzinfo is None and dt.tzinfo is None:
+        raise TypeError("Must specify a timezone!")
+
+      if tzinfo is not None and dt.tzinfo is not None:
+        raise TypeError("Can not give a timezone with timezone aware"
+                        " datetime object! (Use localize.)")
+    else:
+      dt = datetime.datetime(*args, **kw)
+
+    if dt.tzinfo is not None:
+      # Re-normalize the dt object
+      dt = dt.tzinfo.normalize(dt)
+
+    else:
+      if tzinfo is None:
+        tzinfo = localtz()
+
+      try:
+        dt = tzinfo.localize(dt, is_dst=None)
+      except pytz.AmbiguousTimeError:
+        is_dst = None
+        if "is_dst" in kw:
+          is_dst = kw.pop("is_dst")
+
+        try:
+          dt = tzinfo.localize(dt, is_dst)
+        except IndexError:
+          raise pytz.AmbiguousTimeError("No such time exists!")
+
+    newargs = list(dt.timetuple()[0:6])+[dt.microsecond, dt.tzinfo]
+    obj = datetime.datetime.__new__(cls, *newargs)
+    obj.is_dst = obj.dst() != datetime.timedelta(0)
+    return obj
+
+  def asdatetime(self, naive=True):
+    """Return this datetime_tz as a datetime object.
+
+    Args:
+      naive: Return *without* any tz info.
+
+    Returns:
+      This datetime_tz as a datetime object.
+    """
+    args = list(self.timetuple()[0:6])+[self.microsecond]
+    if not naive:
+      args.append(self.tzinfo)
+    return datetime.datetime(*args)
+
+  def asdate(self):
+    """Return this datetime_tz as a date object.
+
+    Returns:
+      This datetime_tz as a date object.
+    """
+    return datetime.date(self.year, self.month, self.day)
+
+  def totimestamp(self):
+    """Convert this datetime object back to a unix timestamp.
+
+    The Unix epoch is the time 00:00:00 UTC on January 1, 1970.
+
+    Returns:
+      Unix timestamp.
+    """
+    return calendar.timegm(self.utctimetuple())+1e-6*self.microsecond
+
+  def astimezone(self, tzinfo):
+    """Returns a version of this timestamp converted to the given timezone.
+
+    Args:
+      tzinfo: Either a datetime.tzinfo object or a string (which will be looked
+              up in pytz.
+
+    Returns:
+      A datetime_tz object in the given timezone.
+    """
+    # Assert we are not a naive datetime object
+    assert self.tzinfo is not None
+
+    tzinfo = _tzinfome(tzinfo)
+
+    d = self.asdatetime(naive=False).astimezone(tzinfo)
+    return datetime_tz(d)
+
+  # pylint: disable-msg=C6113
+  def replace(self, **kw):
+    """Return datetime with new specified fields given as arguments.
+
+    For example, dt.replace(days=4) would return a new datetime_tz object with
+    exactly the same as dt but with the days attribute equal to 4.
+
+    Any attribute can be replaced, but tzinfo can not be set to None.
+
+    Args:
+      Any datetime_tz attribute.
+
+    Returns:
+      A datetime_tz object with the attributes replaced.
+
+    Raises:
+      TypeError: If the given replacement is invalid.
+    """
+    if "tzinfo" in kw:
+      if kw["tzinfo"] is None:
+        raise TypeError("Can not remove the timezone use asdatetime()")
+
+    is_dst = None
+    if "is_dst" in kw:
+      is_dst = kw["is_dst"]
+      del kw["is_dst"]
+    else:
+      # Use our own DST setting..
+      is_dst = self.is_dst
+
+    replaced = self.asdatetime().replace(**kw)
+
+    return datetime_tz(replaced, tzinfo=self.tzinfo.zone, is_dst=is_dst)
+
+  # pylint: disable-msg=C6310
+  @classmethod
+  def smartparse(cls, toparse, tzinfo=None):
+    """Method which uses dateutil.parse and extras to try and parse the string.
+
+    Valid dates are found at:
+     http://labix.org/python-dateutil#head-1443e0f14ad5dff07efd465e080d1110920673d8-2
+
+    Other valid formats include:
+      "now" or "today"
+      "yesterday"
+      "tommorrow"
+      "5 minutes ago"
+      "10 hours ago"
+      "10h5m ago"
+      "start of yesterday"
+      "end of tommorrow"
+      "end of 3rd of March"
+
+    Args:
+      toparse: The string to parse.
+      tzinfo: Timezone for the resultant datetime_tz object should be in.
+              (Defaults to your local timezone.)
+
+    Returns:
+      New datetime_tz object.
+
+    Raises:
+      ValueError: If unable to make sense of the input.
+    """
+    # Default for empty fields are:
+    #  year/month/day == now
+    #  hour/minute/second/microsecond == 0
+    toparse = toparse.strip()
+
+    if tzinfo is None:
+      dt = cls.now()
+    else:
+      dt = cls.now(tzinfo)
+
+    default = dt.replace(hour=0, minute=0, second=0, microsecond=0)
+
+    # Remove "start of " and "end of " prefix in the string
+    if toparse.lower().startswith("end of "):
+      toparse = toparse[7:].strip()
+
+      dt += datetime.timedelta(days=1)
+      dt = dt.replace(hour=0, minute=0, second=0, microsecond=0)
+      dt -= datetime.timedelta(microseconds=1)
+
+      default = dt
+
+    elif toparse.lower().startswith("start of "):
+      toparse = toparse[9:].strip()
+
+      dt = dt.replace(hour=0, minute=0, second=0, microsecond=0)
+      default = dt
+
+    # Handle strings with "now", "today", "yesterday", "tomorrow" and "ago".
+    # Need to use lowercase
+    toparselower = toparse.lower()
+
+    if toparselower in ["now", "today"]:
+      pass
+
+    elif toparselower == "yesterday":
+      dt -= datetime.timedelta(days=1)
+
+    elif toparselower == "tommorrow":
+      dt += datetime.timedelta(days=1)
+
+    elif "ago" in toparselower:
+      # Remove the "ago" bit
+      toparselower = toparselower[:-3]
+      # Replace all "a day and an hour" with "1 day 1 hour"
+      toparselower = toparselower.replace("a ", "1 ")
+      toparselower = toparselower.replace("an ", "1 ")
+      toparselower = toparselower.replace(" and ", " ")
+
+      # Match the following
+      # 1 hour ago
+      # 1h ago
+      # 1 h ago
+      # 1 hour ago
+      # 2 hours ago
+      # Same with minutes, seconds, etc.
+
+      tocheck = ("seconds", "minutes", "hours", "days", "weeks", "months",
+                 "years")
+      result = {}
+      for match in re.finditer("([0-9]+)([^0-9]*)", toparselower):
+        amount = int(match.group(1))
+        unit = match.group(2).strip()
+
+        for bit in tocheck:
+          regex = "^([%s]|((%s)s?))$" % (
+              bit[0], bit[:-1])
+
+          bitmatch = re.search(regex, unit)
+          if bitmatch:
+            result[bit] = amount
+            break
+        else:
+          raise ValueError("Was not able to parse date unit %r!" % unit)
+
+      delta = dateutil.relativedelta.relativedelta(**result)
+      dt -= delta
+
+    else:
+      # Handle strings with normal datetime format, use original case.
+      dt = dateutil.parser.parse(toparse, default=default.asdatetime(),
+                                 tzinfos=pytz_abbr.tzinfos)
+      if dt is None:
+        raise ValueError("Was not able to parse date!")
+
+      if dt.tzinfo is pytz_abbr.unknown:
+        dt = dt.replace(tzinfo=None)
+
+      if dt.tzinfo is None:
+        if tzinfo is None:
+          tzinfo = localtz()
+        dt = cls(dt, tzinfo)
+      else:
+        if isinstance(dt.tzinfo, pytz_abbr.tzabbr):
+          abbr = dt.tzinfo
+          dt = dt.replace(tzinfo=None)
+          dt = cls(dt, abbr.zone, is_dst=abbr.dst)
+
+        dt = cls(dt)
+
+    return dt
+
+  @classmethod
+  def utcfromtimestamp(cls, timestamp):
+    """Returns a datetime object of a given timestamp (in UTC)."""
+    obj = datetime.datetime.utcfromtimestamp(timestamp)
+    obj = pytz.utc.localize(obj)
+    return cls(obj)
+
+  @classmethod
+  def fromtimestamp(cls, timestamp):
+    """Returns a datetime object of a given timestamp (in local tz)."""
+    d = cls.utcfromtimestamp(timestamp)
+    return d.astimezone(localtz())
+
+  @classmethod
+  def utcnow(cls):
+    """Return a new datetime representing UTC day and time."""
+    obj = datetime.datetime.utcnow()
+    obj = cls(obj, tzinfo=pytz.utc)
+    return obj
+
+  @classmethod
+  def now(cls, tzinfo=None):
+    """[tz] -> new datetime with tz's local day and time."""
+    obj = cls.utcnow()
+    if tzinfo is None:
+      tzinfo = localtz()
+    return obj.astimezone(tzinfo)
+
+  today = now
+
+  @staticmethod
+  def fromordinal(ordinal):
+    raise SyntaxError("Not enough information to create a datetime_tz object "
+                      "from an ordinal. Please use datetime.date.fromordinal")
+
+
+class iterate(object):
+  """Helpful iterators for working with datetime_tz objects."""
+
+  @staticmethod
+  def between(start, delta, end=None):
+    """Return an iterator between this date till given end point.
+
+    Example usage:
+      >>> d = datetime_tz.smartparse("5 days ago")
+      2008/05/12 11:45
+      >>> for i in d.between(timedelta(days=1), datetime_tz.now()):
+      >>>    print i
+      2008/05/12 11:45
+      2008/05/13 11:45
+      2008/05/14 11:45
+      2008/05/15 11:45
+      2008/05/16 11:45
+
+    Args:
+      start: The date to start at.
+      delta: The interval to iterate with.
+      end: (Optional) Date to end at. If not given the iterator will never
+           terminate.
+
+    Yields:
+      datetime_tz objects.
+    """
+    toyield = start
+    while end is None or toyield < end:
+      yield toyield
+      toyield += delta
+
+  @staticmethod
+  def weeks(start, end=None):
+    """Iterate over the weeks between the given datetime_tzs.
+
+    Args:
+      start: datetime_tz to start from.
+      end: (Optional) Date to end at, if not given the iterator will never
+           terminate.
+
+    Returns:
+      An iterator which generates datetime_tz objects a week apart.
+    """
+    return iterate.between(start, datetime.timedelta(days=7), end)
+
+  @staticmethod
+  def days(start, end=None):
+    """Iterate over the days between the given datetime_tzs.
+
+    Args:
+      start: datetime_tz to start from.
+      end: (Optional) Date to end at, if not given the iterator will never
+           terminate.
+
+    Returns:
+      An iterator which generates datetime_tz objects a day apart.
+    """
+    return iterate.between(start, datetime.timedelta(days=1), end)
+
+  @staticmethod
+  def hours(start, end=None):
+    """Iterate over the hours between the given datetime_tzs.
+
+    Args:
+      start: datetime_tz to start from.
+      end: (Optional) Date to end at, if not given the iterator will never
+           terminate.
+
+    Returns:
+      An iterator which generates datetime_tz objects a hour apart.
+    """
+    return iterate.between(start, datetime.timedelta(hours=1), end)
+
+  @staticmethod
+  def minutes(start, end=None):
+    """Iterate over the minutes between the given datetime_tzs.
+
+    Args:
+      start: datetime_tz to start from.
+      end: (Optional) Date to end at, if not given the iterator will never
+           terminate.
+
+    Returns:
+      An iterator which generates datetime_tz objects a minute apart.
+    """
+    return iterate.between(start, datetime.timedelta(minutes=1), end)
+
+  @staticmethod
+  def seconds(start, end=None):
+    """Iterate over the seconds between the given datetime_tzs.
+
+    Args:
+      start: datetime_tz to start from.
+      end: (Optional) Date to end at, if not given the iterator will never
+           terminate.
+
+    Returns:
+      An iterator which generates datetime_tz objects a second apart.
+    """
+    return iterate.between(start, datetime.timedelta(minutes=1), end)
+
+
+def _wrap_method(name):
+  """Wrap a method.
+
+  Patch a method which might return a datetime.datetime to return a
+  datetime_tz.datetime_tz instead.
+
+  Args:
+    name: The name of the method to patch
+  """
+  method = getattr(datetime.datetime, name)
+
+  # Have to give the second argument as method has no __module__ option.
+  @functools.wraps(method, ("__name__", "__doc__"), ())
+  def wrapper(*args, **kw):
+    r = method(*args, **kw)
+
+    if isinstance(r, datetime.datetime) and not isinstance(r, datetime_tz):
+      r = datetime_tz(r)
+    return r
+
+  setattr(datetime_tz, name, wrapper)
+
+for methodname in ["__add__", "__radd__", "__rsub__", "__sub__", "combine"]:
+
+  # Make sure we have not already got an override for this method
+  assert methodname not in datetime_tz.__dict__
+
+  _wrap_method(methodname)
+
+
+__all__ = ['datetime_tz', 'detect_timezone', 'iterate', 'localtz',
+    'localtz_set', 'timedelta', '_detect_timezone_environ',
+    '_detect_timezone_etc_localtime', '_detect_timezone_etc_timezone',
+    '_detect_timezone_php']

nilmdb/utils/datetime_tz/pytz_abbr.py

@@ -0,0 +1,230 @@
+#!/usr/bin/python2.4
+# -*- coding: utf-8 -*-
+#
+# Copyright 2010 Google Inc. All Rights Reserved.
+#
+
+"""
+Common time zone acronyms/abbreviations for use with the datetime_tz module.
+
+*WARNING*: There are lots of caveats when using this module which are listed
+below.
+
+CAVEAT 1: The acronyms/abbreviations are not globally unique, they are not even
+unique within a region. For example, EST can mean any of,
+  Eastern Standard Time in Australia (which is 10 hour ahead of UTC)
+  Eastern Standard Time in North America (which is 5 hours behind UTC)
+
+Where there are two abbreviations the more popular one will appear in the all
+dictionary, while the less common one will only appear in that countries region
+dictionary. IE If using all, EST will be mapped to Eastern Standard Time in
+North America.
+
+CAVEAT 2: Many of the acronyms don't map to a neat Oslon timezones. For example,
+Eastern European Summer Time (EEDT) is used by many different countries in
+Europe *at different times*! If the acronym does not map neatly to one zone it
+is mapped to the Etc/GMT+-XX Oslon zone. This means that any date manipulations
+can end up with idiot things like summer time in the middle of winter.
+
+CAVEAT 3: The Summer/Standard time difference is really important! For an hour
+each year it is needed to determine which time you are actually talking about.
+    2002-10-27 01:20:00 EST != 2002-10-27 01:20:00 EDT
+"""
+
+import datetime
+import pytz
+import pytz.tzfile
+
+
+class tzabbr(datetime.tzinfo):
+  """A timezone abbreviation.
+
+  *WARNING*: This is not a tzinfo implementation! Trying to use this as tzinfo
+  object will result in failure.  We inherit from datetime.tzinfo so we can get
+  through the dateutil checks.
+  """
+  pass
+
+
+# A "marker" tzinfo object which is used to signify an unknown timezone.
+unknown = datetime.tzinfo(0)
+
+
+regions = {'all': {}, 'military': {}}
+# Create a special alias for the all and military regions
+all = regions['all']
+military = regions['military']
+
+
+def tzabbr_register(abbr, name, region, zone, dst):
+  """Register a new timezone abbreviation in the global registry.
+
+  If another abbreviation with the same name has already been registered it new
+  abbreviation will only be registered in region specific dictionary.
+  """
+  newabbr = tzabbr()
+  newabbr.abbr = abbr
+  newabbr.name = name
+  newabbr.region = region
+  newabbr.zone = zone
+  newabbr.dst = dst
+
+  if abbr not in all:
+    all[abbr] = newabbr
+
+  if not region in regions:
+    regions[region] = {}
+
+  assert abbr not in regions[region]
+  regions[region][abbr] = newabbr
+
+
+def tzinfos_create(use_region):
+  abbrs = regions[use_region]
+
+  def tzinfos(abbr, offset):
+    if abbr:
+      if abbr in abbrs:
+        result = abbrs[abbr]
+        if offset:
+          # FIXME: Check the offset matches the abbreviation we just selected.
+          pass
+        return result
+      else:
+        raise ValueError, "Unknown timezone found %s" % abbr
+    if offset == 0:
+      return pytz.utc
+    if offset:
+      return pytz.FixedOffset(offset/60)
+    return unknown
+
+  return tzinfos
+
+
+# Create a special alias for the all tzinfos
+tzinfos = tzinfos_create('all')
+
+
+# Create the abbreviations.
+# *WARNING*: Order matters!
+tzabbr_register("A", u"Alpha Time Zone", u"Military", "Etc/GMT-1", False)
+tzabbr_register("ACDT", u"Australian Central Daylight Time", u"Australia",
+                "Australia/Adelaide", True)
+tzabbr_register("ACST", u"Australian Central Standard Time", u"Australia",
+                "Australia/Adelaide", False)
+tzabbr_register("ADT", u"Atlantic Daylight Time", u"North America",
+                "America/Halifax", True)
+tzabbr_register("AEDT", u"Australian Eastern Daylight Time", u"Australia",
+                "Australia/Sydney", True)
+tzabbr_register("AEST", u"Australian Eastern Standard Time", u"Australia",
+                "Australia/Sydney", False)
+tzabbr_register("AKDT", u"Alaska Daylight Time", u"North America",
+                "US/Alaska", True)
+tzabbr_register("AKST", u"Alaska Standard Time", u"North America",
+                "US/Alaska", False)
+tzabbr_register("AST", u"Atlantic Standard Time", u"North America",
+                "America/Halifax", False)
+tzabbr_register("AWDT", u"Australian Western Daylight Time", u"Australia",
+                "Australia/West", True)
+tzabbr_register("AWST", u"Australian Western Standard Time", u"Australia",
+                "Australia/West", False)
+tzabbr_register("B", u"Bravo Time Zone", u"Military", "Etc/GMT-2", False)
+tzabbr_register("BST", u"British Summer Time", u"Europe", "Europe/London", True)
+tzabbr_register("C", u"Charlie Time Zone", u"Military", "Etc/GMT-2", False)
+tzabbr_register("CDT", u"Central Daylight Time", u"North America",
+                "US/Central", True)
+tzabbr_register("CEDT", u"Central European Daylight Time", u"Europe",
+                "Etc/GMT+2", True)
+tzabbr_register("CEST", u"Central European Summer Time", u"Europe",
+                "Etc/GMT+2", True)
+tzabbr_register("CET", u"Central European Time", u"Europe", "Etc/GMT+1", False)
+tzabbr_register("CST", u"Central Standard Time", u"North America",
+                "US/Central", False)
+tzabbr_register("CXT", u"Christmas Island Time", u"Australia",
+                "Indian/Christmas", False)
+tzabbr_register("D", u"Delta Time Zone", u"Military", "Etc/GMT-2", False)
+tzabbr_register("E", u"Echo Time Zone", u"Military", "Etc/GMT-2", False)
+tzabbr_register("EDT", u"Eastern Daylight Time", u"North America",
+                "US/Eastern", True)
+tzabbr_register("EEDT", u"Eastern European Daylight Time", u"Europe",
+                "Etc/GMT+3", True)
+tzabbr_register("EEST", u"Eastern European Summer Time", u"Europe",
+                "Etc/GMT+3", True)
+tzabbr_register("EET", u"Eastern European Time", u"Europe", "Etc/GMT+2", False)
+tzabbr_register("EST", u"Eastern Standard Time", u"North America",
+                "US/Eastern", False)
+tzabbr_register("F", u"Foxtrot Time Zone", u"Military", "Etc/GMT-6", False)
+tzabbr_register("G", u"Golf Time Zone", u"Military", "Etc/GMT-7", False)
+tzabbr_register("GMT", u"Greenwich Mean Time", u"Europe", pytz.utc, False)
+tzabbr_register("H", u"Hotel Time Zone", u"Military", "Etc/GMT-8", False)
+#tzabbr_register("HAA", u"Heure Avancée de l'Atlantique", u"North America", u"UTC - 3 hours")
+#tzabbr_register("HAC", u"Heure Avancée du Centre", u"North America", u"UTC - 5 hours")
+tzabbr_register("HADT", u"Hawaii-Aleutian Daylight Time", u"North America",
+                "Pacific/Honolulu", True)
+#tzabbr_register("HAE", u"Heure Avancée de l'Est", u"North America", u"UTC - 4 hours")
+#tzabbr_register("HAP", u"Heure Avancée du Pacifique", u"North America", u"UTC - 7 hours")
+#tzabbr_register("HAR", u"Heure Avancée des Rocheuses", u"North America", u"UTC - 6 hours")
+tzabbr_register("HAST", u"Hawaii-Aleutian Standard Time", u"North America",
+                "Pacific/Honolulu", False)
+#tzabbr_register("HAT", u"Heure Avancée de Terre-Neuve", u"North America", u"UTC - 2:30 hours")
+#tzabbr_register("HAY", u"Heure Avancée du Yukon", u"North America", u"UTC - 8 hours")
+tzabbr_register("HDT", u"Hawaii Daylight Time", u"North America",
+                "Pacific/Honolulu", True)
+#tzabbr_register("HNA", u"Heure Normale de l'Atlantique", u"North America", u"UTC - 4 hours")
+#tzabbr_register("HNC", u"Heure Normale du Centre", u"North America", u"UTC - 6 hours")
+#tzabbr_register("HNE", u"Heure Normale de l'Est", u"North America", u"UTC - 5 hours")
+#tzabbr_register("HNP", u"Heure Normale du Pacifique", u"North America", u"UTC - 8 hours")
+#tzabbr_register("HNR", u"Heure Normale des Rocheuses", u"North America", u"UTC - 7 hours")
+#tzabbr_register("HNT", u"Heure Normale de Terre-Neuve", u"North America", u"UTC - 3:30 hours")
+#tzabbr_register("HNY", u"Heure Normale du Yukon", u"North America", u"UTC - 9 hours")
+tzabbr_register("HST", u"Hawaii Standard Time", u"North America",
+                "Pacific/Honolulu", False)
+tzabbr_register("I", u"India Time Zone", u"Military", "Etc/GMT-9", False)
+tzabbr_register("IST", u"Irish Summer Time", u"Europe", "Europe/Dublin", True)
+tzabbr_register("K", u"Kilo Time Zone", u"Military", "Etc/GMT-10", False)
+tzabbr_register("L", u"Lima Time Zone", u"Military", "Etc/GMT-11", False)
+tzabbr_register("M", u"Mike Time Zone", u"Military", "Etc/GMT-12", False)
+tzabbr_register("MDT", u"Mountain Daylight Time", u"North America",
+                "US/Mountain", True)
+#tzabbr_register("MESZ", u"Mitteleuroäische Sommerzeit", u"Europe", u"UTC + 2 hours")
+#tzabbr_register("MEZ", u"Mitteleuropäische Zeit", u"Europe", u"UTC + 1 hour")
+tzabbr_register("MSD", u"Moscow Daylight Time", u"Europe",
+                "Europe/Moscow", True)
+tzabbr_register("MSK", u"Moscow Standard Time", u"Europe",
+                "Europe/Moscow", False)
+tzabbr_register("MST", u"Mountain Standard Time", u"North America",
+                "US/Mountain", False)
+tzabbr_register("N", u"November Time Zone", u"Military", "Etc/GMT+1", False)
+tzabbr_register("NDT", u"Newfoundland Daylight Time", u"North America",
+                "America/St_Johns", True)
+tzabbr_register("NFT", u"Norfolk (Island) Time", u"Australia",
+                "Pacific/Norfolk", False)
+tzabbr_register("NST", u"Newfoundland Standard Time", u"North America",
+                "America/St_Johns", False)
+tzabbr_register("O", u"Oscar Time Zone", u"Military", "Etc/GMT+2", False)
+tzabbr_register("P", u"Papa Time Zone", u"Military", "Etc/GMT+3", False)
+tzabbr_register("PDT", u"Pacific Daylight Time", u"North America",
+                "US/Pacific", True)
+tzabbr_register("PST", u"Pacific Standard Time", u"North America",
+                "US/Pacific", False)
+tzabbr_register("Q", u"Quebec Time Zone", u"Military", "Etc/GMT+4", False)
+tzabbr_register("R", u"Romeo Time Zone", u"Military", "Etc/GMT+5", False)
+tzabbr_register("S", u"Sierra Time Zone", u"Military", "Etc/GMT+6", False)
+tzabbr_register("T", u"Tango Time Zone", u"Military", "Etc/GMT+7", False)
+tzabbr_register("U", u"Uniform Time Zone", u"Military", "Etc/GMT+8", False)
+tzabbr_register("UTC", u"Coordinated Universal Time", u"Europe",
+                pytz.utc, False)
+tzabbr_register("V", u"Victor Time Zone", u"Military", "Etc/GMT+9", False)
+tzabbr_register("W", u"Whiskey Time Zone", u"Military", "Etc/GMT+10", False)
+tzabbr_register("WDT", u"Western Daylight Time", u"Australia",
+                "Australia/West", True)
+tzabbr_register("WEDT", u"Western European Daylight Time", u"Europe",
+                "Etc/GMT+1", True)
+tzabbr_register("WEST", u"Western European Summer Time", u"Europe",
+                "Etc/GMT+1", True)
+tzabbr_register("WET", u"Western European Time", u"Europe", pytz.utc, False)
+tzabbr_register("WST", u"Western Standard Time", u"Australia",
+                "Australia/West", False)
+tzabbr_register("X", u"X-ray Time Zone", u"Military", "Etc/GMT+11", False)
+tzabbr_register("Y", u"Yankee Time Zone", u"Military", "Etc/GMT+12", False)
+tzabbr_register("Z", u"Zulu Time Zone", u"Military", pytz.utc, False)

nilmdb/utils/diskusage.py

@@ -0,0 +1,25 @@
+import os
+from math import log
+
+def human_size(num):
+    """Human friendly file size"""
+    unit_list = zip(['bytes', 'kiB', 'MiB', 'GiB', 'TiB'], [0, 0, 1, 2, 2])
+    if num > 1:
+        exponent = min(int(log(num, 1024)), len(unit_list) - 1)
+        quotient = float(num) / 1024**exponent
+        unit, num_decimals = unit_list[exponent]
+        format_string = '{:.%sf} {}' % (num_decimals)
+        return format_string.format(quotient, unit)
+    if num == 0: # pragma: no cover
+        return '0 bytes'
+    if num == 1: # pragma: no cover
+        return '1 byte'
+
+def du(path):
+    """Like du -sb, returns total size of path in bytes."""
+    size = os.path.getsize(path)
+    if os.path.isdir(path):
+        for thisfile in os.listdir(path):
+            filepath = os.path.join(path, thisfile)
+            size += du(filepath)
+    return size

nilmdb/utils/iteratorizer.py

@@ -0,0 +1,99 @@
+import Queue
+import threading
+import sys
+import contextlib
+
+# This file provides a context manager that converts a function
+# that takes a callback into a generator that returns an iterable.
+# This is done by running the function in a new thread.
+
+# Based partially on http://stackoverflow.com/questions/9968592/
+
+class IteratorizerThread(threading.Thread):
+    def __init__(self, queue, function, curl_hack):
+        """
+        function: function to execute, which takes the
+        callback (provided by this class) as an argument
+        """
+        threading.Thread.__init__(self)
+        self.function = function
+        self.queue = queue
+        self.die = False
+        self.curl_hack = curl_hack
+
+    def callback(self, data):
+        try:
+            if self.die:
+                raise Exception() # trigger termination
+            self.queue.put((1, data))
+        except:
+            if self.curl_hack:
+                # We can't raise exceptions, because the pycurl
+                # extension module will unconditionally print the
+                # exception itself, and not pass it up to the caller.
+                # Instead, just return a value that tells curl to
+                # abort.  (-1 would be best, in case we were given 0
+                # bytes, but the extension doesn't support that).
+                self.queue.put((2, sys.exc_info()))
+                return 0
+            raise
+
+    def run(self):
+        try:
+            result = self.function(self.callback)
+        except:
+            self.queue.put((2, sys.exc_info()))
+        else:
+            self.queue.put((0, result))
+
+@contextlib.contextmanager
+def Iteratorizer(function, curl_hack = False):
+    """
+    Context manager that takes a function expecting a callback,
+    and provides an iterable that yields the values passed to that
+    callback instead.
+
+    function: function to execute, which takes a callback
+    (provided by this context manager) as an argument
+
+        with iteratorizer(func) as it:
+            for i in it:
+                print 'callback was passed:', i
+        print 'function returned:', it.retval
+    """
+    queue = Queue.Queue(maxsize = 1)
+    thread = IteratorizerThread(queue, function, curl_hack)
+    thread.daemon = True
+    thread.start()
+
+    class iteratorizer_gen(object):
+        def __init__(self, queue):
+            self.queue = queue
+            self.retval = None
+
+        def __iter__(self):
+            return self
+
+        def next(self):
+            (typ, data) = self.queue.get()
+            if typ == 0:
+                # function has returned
+                self.retval = data
+                raise StopIteration
+            elif typ == 1:
+                # data is available
+                return data
+            else:
+                # callback raised an exception
+                raise data[0], data[1], data[2]
+
+    try:
+        yield iteratorizer_gen(queue)
+    finally:
+        # Ask the thread to die, if it's still running.
+        thread.die = True
+        while thread.isAlive():
+            try:
+                queue.get(True, 0.01)
+            except: # pragma: no cover
+                pass

nilmdb/utils/lrucache.py

@@ -0,0 +1,76 @@
+# Memoize a function's return value with a least-recently-used cache
+# Based on:
+#   http://code.activestate.com/recipes/498245-lru-and-lfu-cache-decorators/
+# with added 'destructor' functionality.
+
+import collections
+import decorator
+
+def lru_cache(size = 10, onremove = None, keys = slice(None)):
+    """Least-recently-used cache decorator.
+
+    @lru_cache(size = 10, onevict = None)
+    def f(...):
+        pass
+
+    Given a function and arguments, memoize its return value.  Up to
+    'size' elements are cached.  'keys' is a slice object that
+    represents which arguments are used as the cache key.
+
+    When evicting a value from the cache, call the function
+    'onremove' with the value that's being evicted.
+
+    Call f.cache_remove(...) to evict the cache entry with the given
+    arguments.  Call f.cache_remove_all() to evict all entries.
+    f.cache_hits and f.cache_misses give statistics.
+    """
+
+    def decorate(func):
+        cache = collections.OrderedDict()	# order: least- to most-recent
+
+        def evict(value):
+            if onremove:
+                onremove(value)
+
+        def wrapper(orig, *args, **kwargs):
+            if kwargs:
+                raise NotImplementedError("kwargs not supported")
+            key = args[keys]
+            try:
+                value = cache.pop(key)
+                orig.cache_hits += 1
+            except KeyError:
+                value = orig(*args)
+                orig.cache_misses += 1
+                if len(cache) >= size:
+                    evict(cache.popitem(0)[1])	# evict LRU cache entry
+            cache[key] = value              	# (re-)insert this key at end
+            return value
+
+        def cache_remove(*args):
+            """Remove the described key from this cache, if present."""
+            key = args
+            if key in cache:
+                evict(cache.pop(key))
+            else:
+                if len(cache) > 0 and len(args) != len(cache.iterkeys().next()):
+                    raise KeyError("trying to remove from LRU cache, but "
+                                   "number of arguments doesn't match the "
+                                   "cache key length")
+
+        def cache_remove_all():
+            for key in cache:
+                evict(cache.pop(key))
+
+        def cache_info():
+            return (func.cache_hits, func.cache_misses)
+
+        new = decorator.decorator(wrapper, func)
+        func.cache_hits = 0
+        func.cache_misses = 0
+        new.cache_info = cache_info
+        new.cache_remove = cache_remove
+        new.cache_remove_all = cache_remove_all
+        return new
+
+    return decorate

nilmdb/utils/mustclose.py

@@ -0,0 +1,64 @@
+from nilmdb.utils.printf import *
+import sys
+import inspect
+import decorator
+
+def must_close(errorfile = sys.stderr, wrap_verify = False):
+    """Class decorator that warns on 'errorfile' at deletion time if
+    the class's close() member wasn't called.
+
+    If 'wrap_verify' is True, every class method is wrapped with a
+    verifier that will raise AssertionError if the .close() method has
+    already been called."""
+    def class_decorator(cls):
+
+        # Helper to replace a class method with a wrapper function,
+        # while maintaining argument specs etc.
+        def wrap_class_method(wrapper_func):
+            method = wrapper_func.__name__
+            if method in cls.__dict__:
+                orig = getattr(cls, method).im_func
+            else:
+                orig = lambda self: None
+            setattr(cls, method, decorator.decorator(wrapper_func, orig))
+
+        @wrap_class_method
+        def __init__(orig, self, *args, **kwargs):
+            ret = orig(self, *args, **kwargs)
+            self.__dict__["_must_close"] = True
+            self.__dict__["_must_close_initialized"] = True
+            return ret
+
+        @wrap_class_method
+        def __del__(orig, self, *args, **kwargs):
+            if "_must_close" in self.__dict__:
+                fprintf(errorfile, "error: %s.close() wasn't called!\n",
+                        self.__class__.__name__)
+            return orig(self, *args, **kwargs)
+
+        @wrap_class_method
+        def close(orig, self, *args, **kwargs):
+            if "_must_close" in self.__dict__:
+                del self._must_close
+            return orig(self, *args, **kwargs)
+
+        # Optionally wrap all other functions
+        def verifier(orig, self, *args, **kwargs):
+            if ("_must_close" not in self.__dict__ and
+                "_must_close_initialized" in self.__dict__):
+                raise AssertionError("called " + str(orig) + " after close")
+            return orig(self, *args, **kwargs)
+        if wrap_verify:
+            for (name, method) in inspect.getmembers(cls, inspect.ismethod):
+                # Skip class methods
+                if method.__self__ is not None:
+                    continue
+                # Skip some methods
+                if name in [ "__del__", "__init__" ]:
+                    continue
+                # Set up wrapper
+                setattr(cls, name, decorator.decorator(verifier,
+                                                       method.im_func))
+
+        return cls
+    return class_decorator

nilmdb/utils/printf.py

@@ -0,0 +1,9 @@
+"""printf, fprintf, sprintf"""
+
+from __future__ import print_function
+def printf(_str, *args):
+    print(_str % args, end='')
+def fprintf(_file, _str, *args):
+    print(_str % args, end='', file=_file)
+def sprintf(_str, *args):
+    return (_str % args)

nilmdb/utils/serializer.py

@@ -0,0 +1,72 @@
+import Queue
+import threading
+import sys
+
+# This file provides a class that will wrap an object and serialize
+# all calls to its methods.  All calls to that object will be queued
+# and executed from a single thread, regardless of which thread makes
+# the call.
+
+# Based partially on http://stackoverflow.com/questions/2642515/
+
+class SerializerThread(threading.Thread):
+    """Thread that retrieves call information from the queue, makes the
+    call, and returns the results."""
+    def __init__(self, call_queue):
+        threading.Thread.__init__(self)
+        self.call_queue = call_queue
+
+    def run(self):
+        while True:
+            result_queue, func, args, kwargs = self.call_queue.get()
+            # Terminate if result_queue is None
+            if result_queue is None:
+                return
+            try:
+                result = func(*args, **kwargs) # wrapped
+            except:
+                result_queue.put((sys.exc_info(), None))
+            else:
+                result_queue.put((None, result))
+
+class WrapCall(object):
+    """Wrap a callable using the given queues"""
+
+    def __init__(self, call_queue, result_queue, func):
+        self.call_queue = call_queue
+        self.result_queue = result_queue
+        self.func = func
+
+    def __call__(self, *args, **kwargs):
+        self.call_queue.put((self.result_queue, self.func, args, kwargs))
+        ( exc_info, result ) = self.result_queue.get()
+        if exc_info is None:
+            return result
+        else:
+            raise exc_info[0], exc_info[1], exc_info[2]
+
+class WrapObject(object):
+    """Wrap all calls to methods in a target object with WrapCall"""
+
+    def __init__(self, target):
+        self.__wrap_target = target
+        self.__wrap_call_queue = Queue.Queue()
+        self.__wrap_serializer = SerializerThread(self.__wrap_call_queue)
+        self.__wrap_serializer.daemon = True
+        self.__wrap_serializer.start()
+
+    def __getattr__(self, key):
+        """Wrap methods of self.__wrap_target in a WrapCall instance"""
+        func = getattr(self.__wrap_target, key)
+        if not callable(func):
+            raise TypeError("Can't serialize attribute %r (type: %s)"
+                            % (key, type(func)))
+        result_queue = Queue.Queue()
+        return WrapCall(self.__wrap_call_queue, result_queue, func)
+
+    def __del__(self):
+        self.__wrap_call_queue.put((None, None, None, None))
+        self.__wrap_serializer.join()
+
+# Just an alias
+Serializer = WrapObject

nilmdb/utils/timer.py

@@ -0,0 +1,22 @@
+# -*- coding: utf-8 -*-
+
+# Simple timer to time a block of code, for optimization debugging
+# use like:
+#   with nilmdb.utils.Timer("flush"):
+#       foo.flush()
+
+from __future__ import print_function
+import contextlib
+import time
+
+@contextlib.contextmanager
+def Timer(name = None, tosyslog = False):
+    start = time.time()
+    yield
+    elapsed = int((time.time() - start) * 1000)
+    msg = (name or 'elapsed') + ": " + str(elapsed) + " ms"
+    if tosyslog: # pragma: no cover
+        import syslog
+        syslog.syslog(msg)
+    else:
+        print(msg)

nilmdb/utils/timestamper.py

@@ -0,0 +1,104 @@
+"""File-like objects that add timestamps to the input lines"""
+
+from nilmdb.utils.printf import *
+from nilmdb.utils import datetime_tz
+
+class Timestamper(object):
+    """A file-like object that adds timestamps to lines of an input file."""
+    def __init__(self, infile, ts_iter):
+        """file: filename, or another file-like object
+           ts_iter: iterator that returns a timestamp string for
+           each line of the file"""
+        if isinstance(infile, basestring):
+            self.file = open(infile, "r")
+        else:
+            self.file = infile
+        self.ts_iter = ts_iter
+
+    def close(self):
+        self.file.close()
+
+    def readline(self, *args):
+        while True:
+            line = self.file.readline(*args)
+            if not line:
+                return ""
+            if line[0] == '#':
+                continue
+            break
+        try:
+            return self.ts_iter.next() + line
+        except StopIteration:
+            return ""
+
+    def readlines(self, size = None):
+        out = ""
+        while True:
+            line = self.readline()
+            out += line
+            if not line or (size and len(out) >= size):
+                break
+        return out
+
+    def __iter__(self):
+        return self
+
+    def next(self):
+        result = self.readline()
+        if not result:
+            raise StopIteration
+        return result
+
+class TimestamperRate(Timestamper):
+    """Timestamper that uses a start time and a fixed rate"""
+    def __init__(self, infile, start, rate, end = None):
+        """
+        file: file name or object
+
+        start: Unix timestamp for the first value
+
+        rate: 1/rate is added to the timestamp for each line
+
+        end: If specified, raise StopIteration before outputting a value
+             greater than this."""
+        def iterator(start, rate, end):
+            n = 0
+            rate = float(rate)
+            while True:
+                now = start + n / rate
+                if end and now >= end:
+                    raise StopIteration
+                yield sprintf("%.6f ", start + n / rate)
+                n += 1
+        # Handle case where we're passed a datetime or datetime_tz object
+        if "totimestamp" in dir(start):
+            start = start.totimestamp()
+        Timestamper.__init__(self, infile, iterator(start, rate, end))
+        self.start = start
+        self.rate = rate
+    def __str__(self):
+        start = datetime_tz.datetime_tz.fromtimestamp(self.start)
+        start = start.strftime("%a, %d %b %Y %H:%M:%S %Z")
+        return sprintf("TimestamperRate(..., start=\"%s\", rate=%g)",
+                       str(start), self.rate)
+
+class TimestamperNow(Timestamper):
+    """Timestamper that uses current time"""
+    def __init__(self, infile):
+        def iterator():
+            while True:
+                now = datetime_tz.datetime_tz.utcnow().totimestamp()
+                yield sprintf("%.6f ", now)
+        Timestamper.__init__(self, infile, iterator())
+    def __str__(self):
+        return "TimestamperNow(...)"
+
+class TimestamperNull(Timestamper):
+    """Timestamper that adds nothing to each line"""
+    def __init__(self, infile):
+        def iterator():
+            while True:
+                yield ""
+        Timestamper.__init__(self, infile, iterator())
+    def __str__(self):
+        return "TimestamperNull(...)"

nilmdb/utils/urllib.py

@@ -0,0 +1,37 @@
+from __future__ import absolute_import
+from urllib import quote_plus, _is_unicode
+
+# urllib.urlencode insists on encoding Unicode as ASCII.  This is based
+# on that function, except we always encode it as UTF-8 instead.
+
+def urlencode(query):
+    """Encode a dictionary into a URL query string.
+
+    If any values in the query arg are sequences, each sequence
+    element is converted to a separate parameter.
+    """
+
+    query = query.items()
+
+    l = []
+    for k, v in query:
+        k = quote_plus(str(k))
+        if isinstance(v, str):
+            v = quote_plus(v)
+            l.append(k + '=' + v)
+        elif _is_unicode(v):
+            v = quote_plus(v.encode("utf-8","strict"))
+            l.append(k + '=' + v)
+        else:
+            try:
+                # is this a sufficient test for sequence-ness?
+                len(v)
+            except TypeError:
+                # not a sequence
+                v = quote_plus(str(v))
+                l.append(k + '=' + v)
+            else:
+                # loop over the sequence
+                for elt in v:
+                    l.append(k + '=' + quote_plus(str(elt)))
+    return '&'.join(l)

pytables-test/Makefile

@@ -1,5 +0,0 @@
-all:
-	time python test-indexed-read.py
-
-clean:
-	rm -f *pyc

pytables-test/README.jim

@@ -1,2 +0,0 @@
-New version from:
-  http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=641485#15

pytables-test/TODO.txt

@@ -1,12 +0,0 @@
-- Make CherryPy server that can handle simple GET/POST,
-  and a httplib client that can talk to that server.
-  Steps:
-  - Make server handle GET
-  - Make client send request, get response
-  - Add request streaming to server
-  - Add request streaming to client
-  - Make server handle POST
-  - Make client send request, get response
-  - Add request streaming to server
-  - Add request streaming to client
-  - Integrate into a server process that also keeps database open.

pytables-test/indexing-notes

@@ -1,3 +0,0 @@
-Indexing time64 doesn't seem to work -- needed to do "time >= 1243052015" even though the actual database times
-should be something like 1243052015.847000.  Let's switch to just using a 64-bit integer counting e.g.
-microseconds since 1970-01-01 

pytables-test/sample-query

@@ -1,3 +0,0 @@
-timestamp > 1243052015
-took 394.5 minutes in vitables
-(2340 rows matched)

pytables-test/server.py

@@ -1,53 +0,0 @@
-import sys
-import tables
-import nilmdb
-
-try:
-    import cherrypy
-    cherrypy.tools.json_out
-except:
-    sys.stderr.write("Cherrypy 3.2+ required\n")
-    sys.exit(1)
-
-class NilmApp:
-    def __init__(self, db):
-        self.db = db
-
-class Root(NilmApp):
-    """NILM Database"""
-
-    server_version = "1.0"
-
-    @cherrypy.expose
-    def index(self):
-        raise cherrypy.NotFound()
-
-    @cherrypy.expose
-    def favicon_ico(self):
-        raise cherrypy.NotFound()
-
-    @cherrypy.expose
-    @cherrypy.tools.json_out()
-    def version(self):
-        return self.server_version
-
-class Stream(NilmApp):
-    """Stream operations"""
-
-    @cherrypy.expose
-    @cherrypy.tools.json_out()
-    def list(self):
-        return 
-    
-cherrypy.config.update({
-    'server.socket_host': '127.0.0.1',
-    'server.socket_port': 12380
-    })
-
-db = nilmdb.nilmdb()
-cherrypy.tree.mount(Root(db), "/")
-cherrypy.tree.mount(Stream(db), "/stream")
-
-if __name__ == "__main__":
-    cherrypy.engine.start()
-    cherrypy.engine.block()

pytables-test/speed-pytables.py

@@ -1,16 +0,0 @@
-import tables
-import numpy
-
-class RawSample(tables.IsDescription):
-    timestamp = tables.UInt64Col()
-    voltage   = tables.UInt16Col(shape = 3)
-    current   = tables.UInt16Col(shape = 3)
-
-h5file = tables.openFile("test.h5", mode = "w", title = "Test")
-group = h5file.createGroup("/", "raw", "Raw Data")
-table = h5file.createTable(group, "nilm1", RawSample, "NILM 1")
-
-print repr(h5file)
-
-# write rows
-

pytables-test/test-indexing.py

@@ -1,54 +0,0 @@
-#!/usr/bin/python
-
-from tables import *
-import re
-import time
-
-# A class to describe our data
-class PrepData(IsDescription):
-    timestamp = Int64Col()
-    p1 = Float32Col()
-    q1 = Float32Col()
-    p3 = Float32Col()
-    q3 = Float32Col()
-    p5 = Float32Col()
-    q5 = Float32Col()
-    p7 = Float32Col()
-    q7 = Float32Col()
-
-filename = "test.h5"
-h5file = openFile(filename, mode = "w", title = "NILM Test")
-
-group = h5file.createGroup("/", "newton", "Newton school")
-table = h5file.createTable(group, "prep", PrepData, "Prep Data", expectedrows = 120 * 86400 * 90)
-
-table.cols.timestamp.createIndex()
-
-for i in range(0, 80):
-    # Open file
-    data = open("data/alldata")
-    count = 0
-    oldtime = time.time()
-    prep = table.row
-    for line in data:
-        count = count + 1
-        if count % 1000000 == 0:
-            print str(i) + ": " + str((time.time() - oldtime)) + ", total " + str(count/1000000) + "m lines"
-            oldtime = time.time()
-        v = re.split('\s+', line)
-        prep['timestamp'] = int(v[0]) + 500000000 * i
-        prep['p1'] = v[1]
-        prep['q1'] = v[2]
-        prep['p3'] = v[3]
-        prep['q3'] = v[4]
-        prep['p5'] = v[5]
-        prep['q5'] = v[6]
-        prep['p7'] = v[7]
-        prep['q7'] = v[8]
-        prep.append()
-    data.close()
-
-h5file.close()
-
-
-

pytables-test/test-write.py

@@ -1,54 +0,0 @@
-#!/usr/bin/python
-
-from tables import *
-import re
-import time
-
-# A class to describe our data
-class PrepData(IsDescription):
-    timestamp = Time64Col()
-    p1 = Float32Col()
-    q1 = Float32Col()
-    p3 = Float32Col()
-    q3 = Float32Col()
-    p5 = Float32Col()
-    q5 = Float32Col()
-    p7 = Float32Col()
-    q7 = Float32Col()
-
-filename = "test.h5"
-h5file = openFile(filename, mode = "w", title = "NILM Test")
-
-group = h5file.createGroup("/", "newton", "Newton school")
-table = h5file.createTable(group, "prep", PrepData, "Prep Data")
-
-table.cols.timestamp.createIndex()
-
-for i in range(0, 80):
-    # Open file
-    data = open("data/alldata")
-    count = 0
-    oldtime = time.time()
-    prep = table.row
-    for line in data:
-        count = count + 1
-        if count % 1000000 == 0:
-            print str(i) + ": " + str((time.time() - oldtime)) + ", total " + str(count/1000000) + "m lines"
-            oldtime = time.time()
-        v = re.split('\s+', line)
-        prep['timestamp'] = float(v[0]) / 1000.0 + 500000 * i
-        prep['p1'] = v[1]
-        prep['q1'] = v[2]
-        prep['p3'] = v[3]
-        prep['q3'] = v[4]
-        prep['p5'] = v[5]
-        prep['q5'] = v[6]
-        prep['p7'] = v[7]
-        prep['q7'] = v[8]
-        prep.append()
-    data.close()
-
-h5file.close()
-
-
-

setup.cfg

@@ -1,9 +1,40 @@
+[aliases]
+test = nosetests
+
 [nosetests]
+# Note: values must be set to 1, and have no comments on the same line,
+# for "python setup.py nosetests" to work correctly.
 nocapture=1
+# Comment this out to see CherryPy logs on failure:
+nologcapture=1
 with-coverage=1
 cover-inclusive=1
 cover-package=nilmdb
 cover-erase=1
+# this works, puts html output in cover/ dir:
+# cover-html=1
+# need nose 1.1.3 for this:
+# cover-branches=1
+#debug=nose
+#debug-log=nose.log
 stop=1
 verbosity=2
-
+tests=tests
+#tests=tests/test_bulkdata.py
+#tests=tests/test_mustclose.py
+#tests=tests/test_lrucache.py
+#tests=tests/test_cmdline.py
+#tests=tests/test_layout.py
+#tests=tests/test_rbtree.py
+#tests=tests/test_interval.py
+#tests=tests/test_rbtree.py,tests/test_interval.py
+#tests=tests/test_interval.py
+#tests=tests/test_client.py
+#tests=tests/test_timestamper.py
+#tests=tests/test_serializer.py
+#tests=tests/test_iteratorizer.py
+#tests=tests/test_client.py:TestClient.test_client_nilmdb
+#tests=tests/test_nilmdb.py
+#with-profile=1
+#profile-sort=time
+##profile-restrict=10  # doesn't work right, treated as string or something

setup.py

@@ -1,9 +1,135 @@
 #!/usr/bin/python
 
-from distutils.core import setup
+# To release a new version, tag it:
+#   git tag -a nilmdb-1.1 -m "Version 1.1"
+#   git push --tags
+# Then just package it up:
+#   python setup.py sdist
 
-setup(name = 'nilmdb',
-      version = '1.0',
-      scripts = [ 'bin/nilm-test.py' ],
-      packages = [ 'nilmdb' ],
+# This is supposed to be using Distribute:
+#
+#   distutils provides a "setup" method.
+#   setuptools is a set of monkeypatches on top of that.
+#   distribute is a particular version/implementation of setuptools.
+#
+# So we don't really know if this is using the old setuptools or the
+# Distribute-provided version of setuptools.
+
+import traceback
+import sys
+import os
+
+try:
+    from setuptools import setup, find_packages
+    from distutils.extension import Extension
+    import distutils.version
+except ImportError:
+    traceback.print_exc()
+    print "Please install the prerequisites listed in README.txt"
+    sys.exit(1)
+
+# Versioneer manages version numbers from git tags.
+# https://github.com/warner/python-versioneer
+import versioneer
+versioneer.versionfile_source = 'nilmdb/_version.py'
+versioneer.versionfile_build = 'nilmdb/_version.py'
+versioneer.tag_prefix = 'nilmdb-'
+versioneer.parentdir_prefix = 'nilmdb-'
+
+# Hack to workaround logging/multiprocessing issue:
+# https://groups.google.com/d/msg/nose-users/fnJ-kAUbYHQ/_UsLN786ygcJ
+try: import multiprocessing
+except: pass
+
+# Use Cython if it's new enough, otherwise use preexisting C files.
+cython_modules = [ 'nilmdb.server.interval',
+                   'nilmdb.server.layout',
+                   'nilmdb.server.rbtree' ]
+try:
+    import Cython
+    from Cython.Build import cythonize
+    if (distutils.version.LooseVersion(Cython.__version__) <
+        distutils.version.LooseVersion("0.16")):
+        print "Cython version", Cython.__version__, "is too old; not using it."
+        raise ImportError()
+    use_cython = True
+except ImportError:
+    use_cython = False
+
+ext_modules = []
+for modulename in cython_modules:
+    filename = modulename.replace('.','/')
+    if use_cython:
+        ext_modules.extend(cythonize(filename + ".pyx"))
+    else:
+        cfile = filename + ".c"
+        if not os.path.exists(cfile):
+            raise Exception("Missing source file " + cfile + ".  "
+                            "Try installing cython >= 0.16.")
+        ext_modules.append(Extension(modulename, [ cfile ]))
+
+# We need a MANIFEST.in.  Generate it here rather than polluting the
+# repository with yet another setup-related file.
+with open("MANIFEST.in", "w") as m:
+    m.write("""
+# Root
+include README.txt
+include setup.cfg
+include setup.py
+include versioneer.py
+include Makefile
+include .coveragerc
+include .pylintrc
+
+# Cython files -- include source.
+recursive-include nilmdb/server *.pyx *.pyxdep *.pxd
+
+# Tests
+recursive-include tests *.py
+recursive-include tests/data *
+include tests/test.order
+
+# Docs
+recursive-include docs Makefile *.md
+""")
+
+# Run setup
+setup(name='nilmdb',
+      version = versioneer.get_version(),
+      cmdclass = versioneer.get_cmdclass(),
+      url = 'https://git.jim.sh/jim/lees/nilmdb.git',
+      author = 'Jim Paris',
+      description = "NILM Database",
+      long_description = "NILM Database",
+      license = "Proprietary",
+      author_email = 'jim@jtan.com',
+      tests_require = [ 'nose',
+                        'coverage',
+                        ],
+      setup_requires = [ 'distribute',
+                         ],
+      install_requires = [ 'decorator',
+                           'cherrypy >= 3.2',
+                           'simplejson',
+                           'pycurl',
+                           'python-dateutil',
+                           'pytz',
+                           'psutil >= 0.3.0',
+                           ],
+      packages = [ 'nilmdb',
+                   'nilmdb.utils',
+                   'nilmdb.utils.datetime_tz',
+                   'nilmdb.server',
+                   'nilmdb.client',
+                   'nilmdb.cmdline',
+                   'nilmdb.scripts',
+                   ],
+      entry_points = {
+          'console_scripts': [
+              'nilmtool = nilmdb.scripts.nilmtool:main',
+              'nilmdb-server = nilmdb.scripts.nilmdb_server:main',
+              ],
+          },
+      ext_modules = ext_modules,
+      zip_safe = False,
       )

test/Makefile

@@ -1,5 +0,0 @@
-all:
-	python speed-readbinary.py
-
-clean:
-	rm -f *pyc

test/printf.py

@@ -1,4 +0,0 @@
-from __future__ import print_function
-def printf(str, *args):
-    print(str % args, end='')
-    

test/speed-readascii.py

@@ -1,60 +0,0 @@
-#!/usr/bin/python
-
-from printf import printf
-import time
-import re
-import numpy as np
-import itertools
-
-class Timer():
-    def __init__(self, arg):
-        self.arg = arg
-    def __enter__(self): self.start = time.time()
-    def __exit__(self, *args): printf("%s: %f lines/sec\n", self.arg, 1e6 / (time.time() - self.start))
-
-def test_split():
-    for n, line in enumerate(open('1m.raw', 'r')):
-        out = [0]*6
-        tmp = [ int(i) for i in line.partition('#')[0].split() ]
-        out[0:len(tmp)] = tmp
-        if (n % 100000 == 0):
-            printf("line %d = %s\n", n, str(out))
-
-def test_split2():
-    for n, line in enumerate(open('1m.raw', 'r')):
-        out = [0]*6
-        tmp = [ int(i,10) for i in line.partition('#')[0].split() ]
-        out[0:len(tmp)] = tmp
-        if (n % 100000 == 0):
-            printf("line %d = %s\n", n, str(out))
-
-def test_regex():
-    for n, line in enumerate(open('1m.raw', 'r')):
-        out = [0]*6
-        tmp = [ int(x) for x in re.findall('(\d+)\s+',line.partition('#')[0]) ]
-        out[0:len(tmp)] = tmp
-        if (n % 100000 == 0):
-            printf("line %d = %s\n", n, str(out))
-
-def test_bigregex():
-    regex = re.compile('^(?:\s*)' + '(?:(\d+)\s+)?' * 6)
-    for n, line in enumerate(open('1m.raw', 'r')):
-        out = [ int(x or 0) for x in re.match(regex, line).groups() ]
-        if (n % 100000 == 0):
-            printf("line %d = %s\n", n, str(out))
-
-with Timer("regex"):
-    test_regex() # 102k/sec
-
-with Timer("split"):
-    test_split() # 175k/sec
-
-with Timer("split2"):
-    test_split2() # 275k/sec
-
-with Timer("bigregex"):
-    test_bigregex() # 110k/sec
-
-# The "int" operation takes quite a while -- int(x,10) is twice as fast
-# Perl does about 500k/sec
-

test/speed-readbinary.py

@@ -1,74 +0,0 @@
-#!/usr/bin/python
-
-from printf import printf
-import time
-import re
-import numpy as np
-import itertools
-import struct
-import array
-import os
-import mmap
-
-class Timer():
-    def __init__(self, arg):
-        self.arg = arg
-    def __enter__(self): self.start = time.time()
-    def __exit__(self, *args): printf("%s: %f klines/sec\n", self.arg, 1e3 / (time.time() - self.start))
-
-def test_struct1():
-    """read with struct.unpack"""
-    f = open('1m.bin', 'rb')
-    f.seek(0,os.SEEK_END)
-    filesize = f.tell()
-    f.seek(0,os.SEEK_SET)
-    packer = struct.Struct('!dHHHHHH')
-    items = filesize / packer.size
-    for n in xrange(items):
-        s = f.read(packer.size)
-        out = packer.unpack(s)
-        if (n % 100000 == 0):
-            printf("line %d = %s\n", n, str(out))
-
-def test_struct2():
-    """read with struct.unpack, convert to string"""
-    f = open('1m.bin', 'rb')
-    f.seek(0,os.SEEK_END)
-    filesize = f.tell()
-    f.seek(0,os.SEEK_SET)
-    packer = struct.Struct('!dHHHHHH')
-    items = filesize / packer.size
-    for n in xrange(items):
-        s = f.read(packer.size)
-        out = packer.unpack(s)
-        x = str(out)
-        if (n % 100000 == 0):
-            printf("line %d = %s\n", n, str(out))
-
-def test_mmap():
-    """struct.unpack with mmap"""
-    with open('1m.bin', 'rb') as f:
-        f.seek(0,os.SEEK_END)
-        filesize = f.tell()
-        f.seek(0,os.SEEK_SET)
-        m = mmap.mmap(f.fileno(), filesize, access=mmap.ACCESS_READ)
-        packer = struct.Struct('!dHHHHHH')
-        items = filesize / packer.size
-        for n in xrange(items):
-            out = packer.unpack(m[packer.size*n : packer.size*(n+1)])
-            if (n % 100000 == 0):
-                printf("line %d = %s\n", n, str(out))
-
-with Timer("mmap"):
-    test_mmap()  # 1600k
-
-with Timer("struct1"):
-    test_struct1()  # 1460k
-
-with Timer("struct2"):
-    test_struct2()  # 210k
-
-# Reading from the file is again much quicker than converting to string
-# Use mmap, it's good
-
-

test/speed-writebinary.py

@@ -1,76 +0,0 @@
-#!/usr/bin/python
-
-from printf import printf
-import time
-import re
-import numpy as np
-import itertools
-import struct
-import array
-
-class Timer():
-    def __init__(self, arg):
-        self.arg = arg
-    def __enter__(self): self.start = time.time()
-    def __exit__(self, *args): printf("%s: %f klines/sec\n", self.arg, 1e3 / (time.time() - self.start))
-
-def read_ascii():
-    for n in xrange(1000000):
-        yield (1234, 2345, 3456, 4576, 5678, 6789)
-#    for n, line in enumerate(open('1m.raw', 'r')):
-#        out = [0]*6
-#        tmp = [ int(i,10) for i in line.partition('#')[0].split() ]
-#        out[0:len(tmp)] = tmp
-#        if (n % 100000 == 0):
-#            printf("line %d = %s\n", n, str(out))
-#        yield out
-
-def test_struct1():
-    """write with struct.pack"""
-    f = open('1m.bin', 'wb')
-    for out in read_ascii():
-        s = struct.pack('!HHHHHH', *out)
-        f.write(s)
-
-def test_struct2():
-    """use constant format string"""
-    f = open('1m.bin', 'wb')
-    packer = struct.Struct('!HHHHHH')
-    for out in read_ascii():
-        f.write(packer.pack(*out))
-    f.close()
-    printf("size was %d\n", packer.size)
-
-def test_struct3():
-    """like struct1, with timestamp"""
-    f = open('1m.bin', 'wb')
-    for out in read_ascii():
-        s = struct.pack('!dHHHHHH', time.time(), *out)
-        f.write(s)
-
-def test_struct4():
-    """like struct2, with timestamp"""
-    f = open('1m.bin', 'wb')
-    packer = struct.Struct('!dHHHHHH')
-    for out in read_ascii():
-        f.write(packer.pack(time.time(), *out))
-    f.close()
-    printf("size was %d\n", packer.size)
-
-#raise Exception('done')
-
-with Timer("struct1"):
-    test_struct1() # 1089k
-
-with Timer("struct2"):
-    test_struct2() # 1249k
-
-with Timer("struct3"):
-    test_struct3() # 845k
-
-with Timer("struct4"):
-    test_struct4() # 922k
-
-# This seems fast enough for writing new data, since it's faster than
-# we read ascii data anyway.  Use e.g. struct4
-

test/test-struct-pack.py

@@ -1,11 +0,0 @@
-#!/usr/bin/python
-
-import struct
-import mmap
-
-f = open("test.dat", "rb+")
-mm = mmap.mmap(f.fileno(),3)
-
-print len(mm)
-print "first 3 bytes: " + mm[0:3];
-

test/test.dat

@@ -1 +0,0 @@
-

















test/todo.md

@@ -1,7 +0,0 @@
-- Have a class representing the file contents
-- Looks like an array
-  - len(), get(), index
-  - some form of bisect search
-  - get_extents = return [0].timestamp, [-1].timestamp
-  - 
-- Can append?  Sure, why not.  Just write to the file, extend mmap accordingly.

tests/data/extract-1

@@ -0,0 +1,124 @@
+# path: /newton/prep
+# layout: PrepData
+# start: Fri, 23 Mar 2012 10:00:30.000000 +0000
+# end: Fri, 23 Mar 2012 10:00:31.000000 +0000
+1332496830.000000 251774.000000 224241.000000 5688.100098 1915.530029 9329.219727 4183.709961 1212.349976 2641.790039
+1332496830.008333 259567.000000 222698.000000 6207.600098 678.671997 9380.230469 4575.580078 2830.610107 2688.629883
+1332496830.016667 263073.000000 223304.000000 4961.640137 2197.120117 7687.310059 4861.859863 2732.780029 3008.540039
+1332496830.025000 257614.000000 223323.000000 5003.660156 3525.139893 7165.310059 4685.620117 1715.380005 3440.479980
+1332496830.033333 255780.000000 221915.000000 6357.310059 2145.290039 8426.969727 3775.350098 1475.390015 3797.239990
+1332496830.041667 260166.000000 223008.000000 6702.589844 1484.959961 9288.099609 3330.830078 1228.500000 3214.320068
+1332496830.050000 261231.000000 226426.000000 4980.060059 2982.379883 8499.629883 4267.669922 994.088989 2292.889893
+1332496830.058333 255117.000000 226642.000000 4584.410156 4656.439941 7860.149902 5317.310059 1473.599976 2111.689941
+1332496830.066667 253300.000000 223554.000000 6455.089844 3036.649902 8869.750000 4986.310059 2607.360107 2839.590088
+1332496830.075000 261061.000000 221263.000000 6951.979980 1500.239990 9386.099609 3791.679932 2677.010010 3980.629883
+1332496830.083333 266503.000000 223198.000000 5189.609863 2594.560059 8571.530273 3175.000000 919.840027 3792.010010
+1332496830.091667 260692.000000 225184.000000 3782.479980 4642.879883 7662.959961 3917.790039 -251.097000 2907.060059
+1332496830.100000 253963.000000 225081.000000 5123.529785 3839.550049 8669.030273 4877.819824 943.723999 2527.449951
+1332496830.108333 256555.000000 224169.000000 5930.600098 2298.540039 8906.709961 5331.680176 2549.909912 3053.560059
+1332496830.116667 260889.000000 225010.000000 4681.129883 2971.870117 7900.040039 4874.080078 2322.429932 3649.120117
+1332496830.125000 257944.000000 224923.000000 3291.139893 4357.089844 7131.589844 4385.560059 1077.050049 3664.040039
+1332496830.133333 255009.000000 223018.000000 4584.819824 2864.000000 8469.490234 3625.580078 985.557007 3504.229980
+1332496830.141667 260114.000000 221947.000000 5676.189941 1210.339966 9393.780273 3390.239990 1654.020020 3018.699951
+1332496830.150000 264277.000000 224438.000000 4446.620117 2176.719971 8142.089844 4584.879883 2327.830078 2615.800049
+1332496830.158333 259221.000000 226471.000000 2734.439941 4182.759766 6389.549805 5540.520020 1958.880005 2720.120117
+1332496830.166667 252650.000000 224831.000000 4163.640137 2989.989990 7179.200195 5213.060059 1929.550049 3457.659912
+1332496830.175000 257083.000000 222048.000000 5759.040039 702.440979 8566.549805 3552.020020 1832.939941 3956.189941
+1332496830.183333 263130.000000 222967.000000 5141.140137 1166.119995 8666.959961 2720.370117 971.374023 3479.729980
+1332496830.191667 260236.000000 225265.000000 3425.139893 3339.080078 7853.609863 3674.949951 525.908020 2443.310059
+1332496830.200000 253503.000000 224527.000000 4398.129883 2927.429932 8110.279785 4842.470215 1513.869995 2467.100098
+1332496830.208333 256126.000000 222693.000000 6043.529785 656.223999 8797.559570 4832.410156 2832.370117 3426.139893
+1332496830.216667 261677.000000 223608.000000 5830.459961 1033.910034 8123.939941 3980.689941 1927.959961 4092.719971
+1332496830.225000 259457.000000 225536.000000 4015.570068 2995.989990 7135.439941 3713.550049 307.220001 3849.429932
+1332496830.233333 253352.000000 224216.000000 4650.560059 3196.620117 8131.279785 3586.159912 70.832298 3074.179932
+1332496830.241667 256124.000000 221513.000000 6100.479980 821.979980 9757.540039 3474.510010 1647.520020 2559.860107
+1332496830.250000 263024.000000 221559.000000 5789.959961 699.416992 9129.740234 4153.080078 2829.250000 2677.270020
+1332496830.258333 261720.000000 224015.000000 4358.500000 2645.360107 7414.109863 4810.669922 2225.989990 3185.989990
+1332496830.266667 254756.000000 224240.000000 4857.379883 3229.679932 7539.310059 4769.140137 1507.130005 3668.260010
+1332496830.275000 256889.000000 222658.000000 6473.419922 1214.109985 9010.759766 3848.729980 1303.839966 3778.500000
+1332496830.283333 264208.000000 223316.000000 5700.450195 1116.560059 9087.610352 3846.679932 1293.589966 2891.560059
+1332496830.291667 263310.000000 225719.000000 3936.120117 3252.360107 7552.850098 4897.859863 1156.630005 2037.160034
+1332496830.300000 255079.000000 225086.000000 4536.450195 3960.110107 7454.589844 5479.069824 1596.359985 2190.800049
+1332496830.308333 254487.000000 222508.000000 6635.859863 1758.849976 8732.969727 4466.970215 2650.360107 3139.310059
+1332496830.316667 261241.000000 222432.000000 6702.270020 1085.130005 8989.230469 3112.989990 1933.560059 3828.409912
+1332496830.325000 262119.000000 225587.000000 4714.950195 2892.360107 8107.819824 2961.310059 239.977997 3273.719971
+1332496830.333333 254999.000000 226514.000000 4532.089844 4126.899902 8200.129883 3872.590088 56.089001 2370.580078
+1332496830.341667 254289.000000 224033.000000 6538.810059 2251.439941 9419.429688 4564.450195 2077.810059 2508.169922
+1332496830.350000 261890.000000 221960.000000 6846.089844 1475.270020 9125.589844 4598.290039 3299.219971 3475.419922
+1332496830.358333 264502.000000 223085.000000 5066.379883 3270.560059 7933.169922 4173.709961 1908.910034 3867.459961
+1332496830.366667 257889.000000 223656.000000 4201.660156 4473.640137 7688.339844 4161.580078 687.578979 3653.689941
+1332496830.375000 254270.000000 223151.000000 5715.140137 2752.139893 9273.320312 3772.949951 896.403992 3256.060059
+1332496830.383333 258257.000000 224217.000000 6114.310059 1856.859985 9604.320312 4200.490234 1764.380005 2939.219971
+1332496830.391667 260020.000000 226868.000000 4237.529785 3605.879883 8066.220215 5430.250000 2138.580078 2696.709961
+1332496830.400000 255083.000000 225924.000000 3350.310059 4853.069824 7045.819824 5925.200195 1893.609985 2897.340088
+1332496830.408333 254453.000000 222127.000000 5271.330078 2491.500000 8436.679688 5032.080078 2436.050049 3724.590088
+1332496830.416667 262588.000000 219950.000000 5994.620117 789.273987 9029.650391 3515.739990 1953.569946 4014.520020
+1332496830.425000 265610.000000 223333.000000 4391.410156 2400.959961 8146.459961 3536.959961 530.231995 3133.919922
+1332496830.433333 257470.000000 226977.000000 2975.320068 4633.529785 7278.560059 4640.100098 -50.150200 2024.959961
+1332496830.441667 250687.000000 226331.000000 4517.859863 3183.800049 8072.600098 5281.660156 1605.140015 2335.139893
+1332496830.450000 255563.000000 224495.000000 5551.000000 1101.300049 8461.490234 4725.700195 2726.669922 3480.540039
+1332496830.458333 261335.000000 224645.000000 4764.680176 1557.020020 7833.350098 3524.810059 1577.410034 4038.620117
+1332496830.466667 260269.000000 224008.000000 3558.030029 2987.610107 7362.439941 3279.229980 562.442017 3786.550049
+1332496830.475000 257435.000000 221777.000000 4972.600098 2166.879883 8481.440430 3328.719971 1037.130005 3271.370117
+1332496830.483333 261046.000000 221550.000000 5816.180176 590.216980 9120.929688 3895.399902 2382.669922 2824.169922
+1332496830.491667 262766.000000 224473.000000 4835.049805 1785.770020 7880.759766 4745.620117 2443.659912 3229.550049
+1332496830.500000 256509.000000 226413.000000 3758.870117 3461.199951 6743.770020 4928.959961 1536.619995 3546.689941
+1332496830.508333 250793.000000 224372.000000 5218.490234 2865.260010 7803.959961 4351.089844 1333.819946 3680.489990
+1332496830.516667 256319.000000 222066.000000 6403.970215 732.344971 9627.759766 3089.300049 1516.780029 3653.689941
+1332496830.525000 263343.000000 223235.000000 5200.430176 1388.579956 9372.849609 3371.229980 1450.390015 2678.909912
+1332496830.533333 260903.000000 225110.000000 3722.580078 3246.659912 7876.540039 4716.810059 1498.439941 2116.520020
+1332496830.541667 254416.000000 223769.000000 4841.649902 2956.399902 8115.919922 5392.359863 2142.810059 2652.320068
+1332496830.550000 256698.000000 222172.000000 6471.229980 970.395996 8834.980469 4816.839844 2376.629883 3605.860107
+1332496830.558333 261841.000000 223537.000000 5500.740234 1189.660034 8365.730469 4016.469971 1042.270020 3821.199951
+1332496830.566667 259503.000000 225840.000000 3827.929932 3088.840088 7676.140137 3978.310059 -357.006989 3016.419922
+1332496830.575000 253457.000000 224636.000000 4914.609863 3097.449951 8224.900391 4321.439941 171.373993 2412.360107
+1332496830.583333 256029.000000 222221.000000 6841.799805 1028.500000 9252.299805 4387.569824 2418.139893 2510.100098
+1332496830.591667 262840.000000 222550.000000 6210.250000 1410.729980 8538.900391 4152.580078 3009.300049 3219.760010
+1332496830.600000 261633.000000 225065.000000 4284.529785 3357.209961 7282.169922 3823.590088 1402.839966 3644.669922
+1332496830.608333 254591.000000 225109.000000 4693.160156 3647.739990 7745.160156 3686.379883 490.161011 3448.860107
+1332496830.616667 254780.000000 223599.000000 6527.379883 1569.869995 9438.429688 3456.580078 1162.520020 3252.010010
+1332496830.625000 260639.000000 224107.000000 6531.049805 1633.050049 9283.719727 4174.020020 2089.550049 2775.750000
+1332496830.633333 261108.000000 225472.000000 4968.259766 3527.850098 7692.870117 5137.100098 2207.389893 2436.659912
+1332496830.641667 255775.000000 223708.000000 4963.450195 4017.370117 7701.419922 5269.649902 2284.399902 2842.080078
+1332496830.650000 257398.000000 220947.000000 6767.500000 1645.709961 9107.070312 4000.179932 2548.860107 3624.770020
+1332496830.658333 264924.000000 221559.000000 6471.459961 1110.329956 9459.650391 3108.169922 1696.969971 3893.439941
+1332496830.666667 265339.000000 225733.000000 4348.799805 3459.510010 8475.299805 4031.239990 573.346985 2910.270020
+1332496830.675000 256814.000000 226995.000000 3479.540039 4949.790039 7499.910156 5624.709961 751.656006 2347.709961
+1332496830.683333 253316.000000 225161.000000 5147.060059 3218.429932 8460.160156 5869.299805 2336.320068 2987.959961
+1332496830.691667 259360.000000 223101.000000 5549.120117 1869.949951 8740.759766 4668.939941 2457.909912 3758.820068
+1332496830.700000 262012.000000 224016.000000 4173.609863 3004.129883 8157.040039 3704.729980 987.963989 3652.750000
+1332496830.708333 257176.000000 224420.000000 3517.300049 4118.750000 7822.240234 3718.229980 37.264900 2953.679932
+1332496830.716667 255146.000000 223322.000000 4923.979980 2330.679932 9095.910156 3792.399902 1013.070007 2711.239990
+1332496830.725000 260524.000000 223651.000000 5413.629883 1146.209961 8817.169922 4419.649902 2446.649902 2832.050049
+1332496830.733333 262098.000000 225752.000000 4262.979980 2270.969971 7135.479980 5067.120117 2294.679932 3376.620117
+1332496830.741667 256889.000000 225379.000000 3606.459961 3568.189941 6552.649902 4970.270020 1516.380005 3662.570068
+1332496830.750000 253948.000000 222631.000000 5511.700195 2066.300049 7952.660156 4019.909912 1513.140015 3752.629883
+1332496830.758333 259799.000000 222067.000000 5873.500000 608.583984 9253.780273 2870.739990 1348.239990 3344.199951
+1332496830.766667 262547.000000 224901.000000 4346.080078 1928.099976 8590.969727 3455.459961 904.390991 2379.270020
+1332496830.775000 256137.000000 226761.000000 3423.560059 3379.080078 7471.149902 4894.169922 1153.540039 2031.410034
+1332496830.783333 250326.000000 225013.000000 5519.979980 2423.969971 7991.759766 5117.950195 2098.790039 3099.239990
+1332496830.791667 255454.000000 222992.000000 6547.950195 496.496002 8751.339844 3900.560059 2132.290039 4076.810059
+1332496830.800000 261286.000000 223489.000000 5152.850098 1501.510010 8425.610352 2888.030029 776.114014 3786.360107
+1332496830.808333 258969.000000 224069.000000 3832.610107 3001.979980 7979.259766 3182.310059 52.716000 2874.800049
+1332496830.816667 254946.000000 222035.000000 5317.879883 2139.800049 9103.139648 3955.610107 1235.170044 2394.149902
+1332496830.825000 258676.000000 221205.000000 6594.910156 505.343994 9423.360352 4562.470215 2913.739990 2892.350098
+1332496830.833333 262125.000000 223566.000000 5116.750000 1773.599976 8082.200195 4776.370117 2386.389893 3659.729980
+1332496830.841667 257835.000000 225918.000000 3714.300049 3477.080078 7205.370117 4554.609863 711.539001 3878.419922
+1332496830.850000 253660.000000 224371.000000 5022.450195 2592.429932 8277.200195 4119.370117 486.507996 3666.739990
+1332496830.858333 259503.000000 222061.000000 6589.950195 659.935974 9596.919922 3598.100098 1702.489990 3036.600098
+1332496830.866667 265495.000000 222843.000000 5541.850098 1728.430054 8459.959961 4492.000000 2231.969971 2430.620117
+1332496830.875000 260929.000000 224996.000000 4000.949951 3745.989990 6983.790039 5430.859863 1855.260010 2533.379883
+1332496830.883333 252716.000000 224335.000000 5086.560059 3401.149902 7597.970215 5196.120117 1755.719971 3079.760010
+1332496830.891667 254110.000000 223111.000000 6822.189941 1229.079956 9164.339844 3761.229980 1679.390015 3584.879883
+1332496830.900000 259969.000000 224693.000000 6183.950195 1538.500000 9222.080078 3139.169922 949.901978 3180.800049
+1332496830.908333 259078.000000 226913.000000 4388.890137 3694.820068 8195.019531 3933.000000 426.079987 2388.449951
+1332496830.916667 254563.000000 224760.000000 5168.439941 4020.939941 8450.269531 4758.910156 1458.900024 2286.429932
+1332496830.925000 258059.000000 221217.000000 6883.459961 1649.530029 9232.780273 4457.649902 3057.820068 3031.949951
+1332496830.933333 264667.000000 221177.000000 6218.509766 1645.729980 8657.179688 3663.500000 2528.280029 3978.340088
+1332496830.941667 262925.000000 224382.000000 4627.500000 3635.929932 7892.799805 3431.320068 604.508972 3901.370117
+1332496830.950000 254708.000000 225448.000000 4408.250000 4461.040039 8197.169922 3953.750000 -44.534599 3154.870117
+1332496830.958333 253702.000000 224635.000000 5825.770020 2577.050049 9590.049805 4569.250000 1460.270020 2785.169922
+1332496830.966667 260206.000000 224140.000000 5387.979980 1951.160034 8789.509766 5131.660156 2706.379883 2972.479980
+1332496830.975000 261240.000000 224737.000000 3860.810059 3418.310059 7414.529785 5284.520020 2271.379883 3183.149902
+1332496830.983333 256140.000000 223252.000000 3850.010010 3957.139893 7262.649902 4964.640137 1499.510010 3453.129883
+1332496830.991667 256116.000000 221349.000000 5594.479980 2054.399902 8835.129883 3662.010010 1485.510010 3613.010010

tests/data/extract-2

@@ -0,0 +1,119 @@
+1332496830.008333 259567.000000 222698.000000 6207.600098 678.671997 9380.230469 4575.580078 2830.610107 2688.629883
+1332496830.016667 263073.000000 223304.000000 4961.640137 2197.120117 7687.310059 4861.859863 2732.780029 3008.540039
+1332496830.025000 257614.000000 223323.000000 5003.660156 3525.139893 7165.310059 4685.620117 1715.380005 3440.479980
+1332496830.033333 255780.000000 221915.000000 6357.310059 2145.290039 8426.969727 3775.350098 1475.390015 3797.239990
+1332496830.041667 260166.000000 223008.000000 6702.589844 1484.959961 9288.099609 3330.830078 1228.500000 3214.320068
+1332496830.050000 261231.000000 226426.000000 4980.060059 2982.379883 8499.629883 4267.669922 994.088989 2292.889893
+1332496830.058333 255117.000000 226642.000000 4584.410156 4656.439941 7860.149902 5317.310059 1473.599976 2111.689941
+1332496830.066667 253300.000000 223554.000000 6455.089844 3036.649902 8869.750000 4986.310059 2607.360107 2839.590088
+1332496830.075000 261061.000000 221263.000000 6951.979980 1500.239990 9386.099609 3791.679932 2677.010010 3980.629883
+1332496830.083333 266503.000000 223198.000000 5189.609863 2594.560059 8571.530273 3175.000000 919.840027 3792.010010
+1332496830.091667 260692.000000 225184.000000 3782.479980 4642.879883 7662.959961 3917.790039 -251.097000 2907.060059
+1332496830.100000 253963.000000 225081.000000 5123.529785 3839.550049 8669.030273 4877.819824 943.723999 2527.449951
+1332496830.108333 256555.000000 224169.000000 5930.600098 2298.540039 8906.709961 5331.680176 2549.909912 3053.560059
+1332496830.116667 260889.000000 225010.000000 4681.129883 2971.870117 7900.040039 4874.080078 2322.429932 3649.120117
+1332496830.125000 257944.000000 224923.000000 3291.139893 4357.089844 7131.589844 4385.560059 1077.050049 3664.040039
+1332496830.133333 255009.000000 223018.000000 4584.819824 2864.000000 8469.490234 3625.580078 985.557007 3504.229980
+1332496830.141667 260114.000000 221947.000000 5676.189941 1210.339966 9393.780273 3390.239990 1654.020020 3018.699951
+1332496830.150000 264277.000000 224438.000000 4446.620117 2176.719971 8142.089844 4584.879883 2327.830078 2615.800049
+1332496830.158333 259221.000000 226471.000000 2734.439941 4182.759766 6389.549805 5540.520020 1958.880005 2720.120117
+1332496830.166667 252650.000000 224831.000000 4163.640137 2989.989990 7179.200195 5213.060059 1929.550049 3457.659912
+1332496830.175000 257083.000000 222048.000000 5759.040039 702.440979 8566.549805 3552.020020 1832.939941 3956.189941
+1332496830.183333 263130.000000 222967.000000 5141.140137 1166.119995 8666.959961 2720.370117 971.374023 3479.729980
+1332496830.191667 260236.000000 225265.000000 3425.139893 3339.080078 7853.609863 3674.949951 525.908020 2443.310059
+1332496830.200000 253503.000000 224527.000000 4398.129883 2927.429932 8110.279785 4842.470215 1513.869995 2467.100098
+1332496830.208333 256126.000000 222693.000000 6043.529785 656.223999 8797.559570 4832.410156 2832.370117 3426.139893
+1332496830.216667 261677.000000 223608.000000 5830.459961 1033.910034 8123.939941 3980.689941 1927.959961 4092.719971
+1332496830.225000 259457.000000 225536.000000 4015.570068 2995.989990 7135.439941 3713.550049 307.220001 3849.429932
+1332496830.233333 253352.000000 224216.000000 4650.560059 3196.620117 8131.279785 3586.159912 70.832298 3074.179932
+1332496830.241667 256124.000000 221513.000000 6100.479980 821.979980 9757.540039 3474.510010 1647.520020 2559.860107
+1332496830.250000 263024.000000 221559.000000 5789.959961 699.416992 9129.740234 4153.080078 2829.250000 2677.270020
+1332496830.258333 261720.000000 224015.000000 4358.500000 2645.360107 7414.109863 4810.669922 2225.989990 3185.989990
+1332496830.266667 254756.000000 224240.000000 4857.379883 3229.679932 7539.310059 4769.140137 1507.130005 3668.260010
+1332496830.275000 256889.000000 222658.000000 6473.419922 1214.109985 9010.759766 3848.729980 1303.839966 3778.500000
+1332496830.283333 264208.000000 223316.000000 5700.450195 1116.560059 9087.610352 3846.679932 1293.589966 2891.560059
+1332496830.291667 263310.000000 225719.000000 3936.120117 3252.360107 7552.850098 4897.859863 1156.630005 2037.160034
+1332496830.300000 255079.000000 225086.000000 4536.450195 3960.110107 7454.589844 5479.069824 1596.359985 2190.800049
+1332496830.308333 254487.000000 222508.000000 6635.859863 1758.849976 8732.969727 4466.970215 2650.360107 3139.310059
+1332496830.316667 261241.000000 222432.000000 6702.270020 1085.130005 8989.230469 3112.989990 1933.560059 3828.409912
+1332496830.325000 262119.000000 225587.000000 4714.950195 2892.360107 8107.819824 2961.310059 239.977997 3273.719971
+1332496830.333333 254999.000000 226514.000000 4532.089844 4126.899902 8200.129883 3872.590088 56.089001 2370.580078
+1332496830.341667 254289.000000 224033.000000 6538.810059 2251.439941 9419.429688 4564.450195 2077.810059 2508.169922
+1332496830.350000 261890.000000 221960.000000 6846.089844 1475.270020 9125.589844 4598.290039 3299.219971 3475.419922
+1332496830.358333 264502.000000 223085.000000 5066.379883 3270.560059 7933.169922 4173.709961 1908.910034 3867.459961
+1332496830.366667 257889.000000 223656.000000 4201.660156 4473.640137 7688.339844 4161.580078 687.578979 3653.689941
+1332496830.375000 254270.000000 223151.000000 5715.140137 2752.139893 9273.320312 3772.949951 896.403992 3256.060059
+1332496830.383333 258257.000000 224217.000000 6114.310059 1856.859985 9604.320312 4200.490234 1764.380005 2939.219971
+1332496830.391667 260020.000000 226868.000000 4237.529785 3605.879883 8066.220215 5430.250000 2138.580078 2696.709961
+1332496830.400000 255083.000000 225924.000000 3350.310059 4853.069824 7045.819824 5925.200195 1893.609985 2897.340088
+1332496830.408333 254453.000000 222127.000000 5271.330078 2491.500000 8436.679688 5032.080078 2436.050049 3724.590088
+1332496830.416667 262588.000000 219950.000000 5994.620117 789.273987 9029.650391 3515.739990 1953.569946 4014.520020
+1332496830.425000 265610.000000 223333.000000 4391.410156 2400.959961 8146.459961 3536.959961 530.231995 3133.919922
+1332496830.433333 257470.000000 226977.000000 2975.320068 4633.529785 7278.560059 4640.100098 -50.150200 2024.959961
+1332496830.441667 250687.000000 226331.000000 4517.859863 3183.800049 8072.600098 5281.660156 1605.140015 2335.139893
+1332496830.450000 255563.000000 224495.000000 5551.000000 1101.300049 8461.490234 4725.700195 2726.669922 3480.540039
+1332496830.458333 261335.000000 224645.000000 4764.680176 1557.020020 7833.350098 3524.810059 1577.410034 4038.620117
+1332496830.466667 260269.000000 224008.000000 3558.030029 2987.610107 7362.439941 3279.229980 562.442017 3786.550049
+1332496830.475000 257435.000000 221777.000000 4972.600098 2166.879883 8481.440430 3328.719971 1037.130005 3271.370117
+1332496830.483333 261046.000000 221550.000000 5816.180176 590.216980 9120.929688 3895.399902 2382.669922 2824.169922
+1332496830.491667 262766.000000 224473.000000 4835.049805 1785.770020 7880.759766 4745.620117 2443.659912 3229.550049
+1332496830.500000 256509.000000 226413.000000 3758.870117 3461.199951 6743.770020 4928.959961 1536.619995 3546.689941
+1332496830.508333 250793.000000 224372.000000 5218.490234 2865.260010 7803.959961 4351.089844 1333.819946 3680.489990
+1332496830.516667 256319.000000 222066.000000 6403.970215 732.344971 9627.759766 3089.300049 1516.780029 3653.689941
+1332496830.525000 263343.000000 223235.000000 5200.430176 1388.579956 9372.849609 3371.229980 1450.390015 2678.909912
+1332496830.533333 260903.000000 225110.000000 3722.580078 3246.659912 7876.540039 4716.810059 1498.439941 2116.520020
+1332496830.541667 254416.000000 223769.000000 4841.649902 2956.399902 8115.919922 5392.359863 2142.810059 2652.320068
+1332496830.550000 256698.000000 222172.000000 6471.229980 970.395996 8834.980469 4816.839844 2376.629883 3605.860107
+1332496830.558333 261841.000000 223537.000000 5500.740234 1189.660034 8365.730469 4016.469971 1042.270020 3821.199951
+1332496830.566667 259503.000000 225840.000000 3827.929932 3088.840088 7676.140137 3978.310059 -357.006989 3016.419922
+1332496830.575000 253457.000000 224636.000000 4914.609863 3097.449951 8224.900391 4321.439941 171.373993 2412.360107
+1332496830.583333 256029.000000 222221.000000 6841.799805 1028.500000 9252.299805 4387.569824 2418.139893 2510.100098
+1332496830.591667 262840.000000 222550.000000 6210.250000 1410.729980 8538.900391 4152.580078 3009.300049 3219.760010
+1332496830.600000 261633.000000 225065.000000 4284.529785 3357.209961 7282.169922 3823.590088 1402.839966 3644.669922
+1332496830.608333 254591.000000 225109.000000 4693.160156 3647.739990 7745.160156 3686.379883 490.161011 3448.860107
+1332496830.616667 254780.000000 223599.000000 6527.379883 1569.869995 9438.429688 3456.580078 1162.520020 3252.010010
+1332496830.625000 260639.000000 224107.000000 6531.049805 1633.050049 9283.719727 4174.020020 2089.550049 2775.750000
+1332496830.633333 261108.000000 225472.000000 4968.259766 3527.850098 7692.870117 5137.100098 2207.389893 2436.659912
+1332496830.641667 255775.000000 223708.000000 4963.450195 4017.370117 7701.419922 5269.649902 2284.399902 2842.080078
+1332496830.650000 257398.000000 220947.000000 6767.500000 1645.709961 9107.070312 4000.179932 2548.860107 3624.770020
+1332496830.658333 264924.000000 221559.000000 6471.459961 1110.329956 9459.650391 3108.169922 1696.969971 3893.439941
+1332496830.666667 265339.000000 225733.000000 4348.799805 3459.510010 8475.299805 4031.239990 573.346985 2910.270020
+1332496830.675000 256814.000000 226995.000000 3479.540039 4949.790039 7499.910156 5624.709961 751.656006 2347.709961
+1332496830.683333 253316.000000 225161.000000 5147.060059 3218.429932 8460.160156 5869.299805 2336.320068 2987.959961
+1332496830.691667 259360.000000 223101.000000 5549.120117 1869.949951 8740.759766 4668.939941 2457.909912 3758.820068
+1332496830.700000 262012.000000 224016.000000 4173.609863 3004.129883 8157.040039 3704.729980 987.963989 3652.750000
+1332496830.708333 257176.000000 224420.000000 3517.300049 4118.750000 7822.240234 3718.229980 37.264900 2953.679932
+1332496830.716667 255146.000000 223322.000000 4923.979980 2330.679932 9095.910156 3792.399902 1013.070007 2711.239990
+1332496830.725000 260524.000000 223651.000000 5413.629883 1146.209961 8817.169922 4419.649902 2446.649902 2832.050049
+1332496830.733333 262098.000000 225752.000000 4262.979980 2270.969971 7135.479980 5067.120117 2294.679932 3376.620117
+1332496830.741667 256889.000000 225379.000000 3606.459961 3568.189941 6552.649902 4970.270020 1516.380005 3662.570068
+1332496830.750000 253948.000000 222631.000000 5511.700195 2066.300049 7952.660156 4019.909912 1513.140015 3752.629883
+1332496830.758333 259799.000000 222067.000000 5873.500000 608.583984 9253.780273 2870.739990 1348.239990 3344.199951
+1332496830.766667 262547.000000 224901.000000 4346.080078 1928.099976 8590.969727 3455.459961 904.390991 2379.270020
+1332496830.775000 256137.000000 226761.000000 3423.560059 3379.080078 7471.149902 4894.169922 1153.540039 2031.410034
+1332496830.783333 250326.000000 225013.000000 5519.979980 2423.969971 7991.759766 5117.950195 2098.790039 3099.239990
+1332496830.791667 255454.000000 222992.000000 6547.950195 496.496002 8751.339844 3900.560059 2132.290039 4076.810059
+1332496830.800000 261286.000000 223489.000000 5152.850098 1501.510010 8425.610352 2888.030029 776.114014 3786.360107
+1332496830.808333 258969.000000 224069.000000 3832.610107 3001.979980 7979.259766 3182.310059 52.716000 2874.800049
+1332496830.816667 254946.000000 222035.000000 5317.879883 2139.800049 9103.139648 3955.610107 1235.170044 2394.149902
+1332496830.825000 258676.000000 221205.000000 6594.910156 505.343994 9423.360352 4562.470215 2913.739990 2892.350098
+1332496830.833333 262125.000000 223566.000000 5116.750000 1773.599976 8082.200195 4776.370117 2386.389893 3659.729980
+1332496830.841667 257835.000000 225918.000000 3714.300049 3477.080078 7205.370117 4554.609863 711.539001 3878.419922
+1332496830.850000 253660.000000 224371.000000 5022.450195 2592.429932 8277.200195 4119.370117 486.507996 3666.739990
+1332496830.858333 259503.000000 222061.000000 6589.950195 659.935974 9596.919922 3598.100098 1702.489990 3036.600098
+1332496830.866667 265495.000000 222843.000000 5541.850098 1728.430054 8459.959961 4492.000000 2231.969971 2430.620117
+1332496830.875000 260929.000000 224996.000000 4000.949951 3745.989990 6983.790039 5430.859863 1855.260010 2533.379883
+1332496830.883333 252716.000000 224335.000000 5086.560059 3401.149902 7597.970215 5196.120117 1755.719971 3079.760010
+1332496830.891667 254110.000000 223111.000000 6822.189941 1229.079956 9164.339844 3761.229980 1679.390015 3584.879883
+1332496830.900000 259969.000000 224693.000000 6183.950195 1538.500000 9222.080078 3139.169922 949.901978 3180.800049
+1332496830.908333 259078.000000 226913.000000 4388.890137 3694.820068 8195.019531 3933.000000 426.079987 2388.449951
+1332496830.916667 254563.000000 224760.000000 5168.439941 4020.939941 8450.269531 4758.910156 1458.900024 2286.429932
+1332496830.925000 258059.000000 221217.000000 6883.459961 1649.530029 9232.780273 4457.649902 3057.820068 3031.949951
+1332496830.933333 264667.000000 221177.000000 6218.509766 1645.729980 8657.179688 3663.500000 2528.280029 3978.340088
+1332496830.941667 262925.000000 224382.000000 4627.500000 3635.929932 7892.799805 3431.320068 604.508972 3901.370117
+1332496830.950000 254708.000000 225448.000000 4408.250000 4461.040039 8197.169922 3953.750000 -44.534599 3154.870117
+1332496830.958333 253702.000000 224635.000000 5825.770020 2577.050049 9590.049805 4569.250000 1460.270020 2785.169922
+1332496830.966667 260206.000000 224140.000000 5387.979980 1951.160034 8789.509766 5131.660156 2706.379883 2972.479980
+1332496830.975000 261240.000000 224737.000000 3860.810059 3418.310059 7414.529785 5284.520020 2271.379883 3183.149902
+1332496830.983333 256140.000000 223252.000000 3850.010010 3957.139893 7262.649902 4964.640137 1499.510010 3453.129883
+1332496830.991667 256116.000000 221349.000000 5594.479980 2054.399902 8835.129883 3662.010010 1485.510010 3613.010010

tests/data/extract-3

@@ -0,0 +1 @@
+1332496830.008333 259567.000000 222698.000000 6207.600098 678.671997 9380.230469 4575.580078 2830.610107 2688.629883

tests/data/extract-4

@@ -0,0 +1,2 @@
+1332496830.008333 259567.000000 222698.000000 6207.600098 678.671997 9380.230469 4575.580078 2830.610107 2688.629883
+1332496830.016667 263073.000000 223304.000000 4961.640137 2197.120117 7687.310059 4861.859863 2732.780029 3008.540039

tests/data/extract-5

@@ -0,0 +1,124 @@
+# path: /newton/prep
+# layout: PrepData
+# start: Fri, 23 Mar 2012 10:00:30.000000 +0000
+# end: Fri, 23 Mar 2012 10:00:31.000000 +0000
+251774.000000 224241.000000 5688.100098 1915.530029 9329.219727 4183.709961 1212.349976 2641.790039
+259567.000000 222698.000000 6207.600098 678.671997 9380.230469 4575.580078 2830.610107 2688.629883
+263073.000000 223304.000000 4961.640137 2197.120117 7687.310059 4861.859863 2732.780029 3008.540039
+257614.000000 223323.000000 5003.660156 3525.139893 7165.310059 4685.620117 1715.380005 3440.479980
+255780.000000 221915.000000 6357.310059 2145.290039 8426.969727 3775.350098 1475.390015 3797.239990
+260166.000000 223008.000000 6702.589844 1484.959961 9288.099609 3330.830078 1228.500000 3214.320068
+261231.000000 226426.000000 4980.060059 2982.379883 8499.629883 4267.669922 994.088989 2292.889893
+255117.000000 226642.000000 4584.410156 4656.439941 7860.149902 5317.310059 1473.599976 2111.689941
+253300.000000 223554.000000 6455.089844 3036.649902 8869.750000 4986.310059 2607.360107 2839.590088
+261061.000000 221263.000000 6951.979980 1500.239990 9386.099609 3791.679932 2677.010010 3980.629883
+266503.000000 223198.000000 5189.609863 2594.560059 8571.530273 3175.000000 919.840027 3792.010010
+260692.000000 225184.000000 3782.479980 4642.879883 7662.959961 3917.790039 -251.097000 2907.060059
+253963.000000 225081.000000 5123.529785 3839.550049 8669.030273 4877.819824 943.723999 2527.449951
+256555.000000 224169.000000 5930.600098 2298.540039 8906.709961 5331.680176 2549.909912 3053.560059
+260889.000000 225010.000000 4681.129883 2971.870117 7900.040039 4874.080078 2322.429932 3649.120117
+257944.000000 224923.000000 3291.139893 4357.089844 7131.589844 4385.560059 1077.050049 3664.040039
+255009.000000 223018.000000 4584.819824 2864.000000 8469.490234 3625.580078 985.557007 3504.229980
+260114.000000 221947.000000 5676.189941 1210.339966 9393.780273 3390.239990 1654.020020 3018.699951
+264277.000000 224438.000000 4446.620117 2176.719971 8142.089844 4584.879883 2327.830078 2615.800049
+259221.000000 226471.000000 2734.439941 4182.759766 6389.549805 5540.520020 1958.880005 2720.120117
+252650.000000 224831.000000 4163.640137 2989.989990 7179.200195 5213.060059 1929.550049 3457.659912
+257083.000000 222048.000000 5759.040039 702.440979 8566.549805 3552.020020 1832.939941 3956.189941
+263130.000000 222967.000000 5141.140137 1166.119995 8666.959961 2720.370117 971.374023 3479.729980
+260236.000000 225265.000000 3425.139893 3339.080078 7853.609863 3674.949951 525.908020 2443.310059
+253503.000000 224527.000000 4398.129883 2927.429932 8110.279785 4842.470215 1513.869995 2467.100098
+256126.000000 222693.000000 6043.529785 656.223999 8797.559570 4832.410156 2832.370117 3426.139893
+261677.000000 223608.000000 5830.459961 1033.910034 8123.939941 3980.689941 1927.959961 4092.719971
+259457.000000 225536.000000 4015.570068 2995.989990 7135.439941 3713.550049 307.220001 3849.429932
+253352.000000 224216.000000 4650.560059 3196.620117 8131.279785 3586.159912 70.832298 3074.179932
+256124.000000 221513.000000 6100.479980 821.979980 9757.540039 3474.510010 1647.520020 2559.860107
+263024.000000 221559.000000 5789.959961 699.416992 9129.740234 4153.080078 2829.250000 2677.270020
+261720.000000 224015.000000 4358.500000 2645.360107 7414.109863 4810.669922 2225.989990 3185.989990
+254756.000000 224240.000000 4857.379883 3229.679932 7539.310059 4769.140137 1507.130005 3668.260010
+256889.000000 222658.000000 6473.419922 1214.109985 9010.759766 3848.729980 1303.839966 3778.500000
+264208.000000 223316.000000 5700.450195 1116.560059 9087.610352 3846.679932 1293.589966 2891.560059
+263310.000000 225719.000000 3936.120117 3252.360107 7552.850098 4897.859863 1156.630005 2037.160034
+255079.000000 225086.000000 4536.450195 3960.110107 7454.589844 5479.069824 1596.359985 2190.800049
+254487.000000 222508.000000 6635.859863 1758.849976 8732.969727 4466.970215 2650.360107 3139.310059
+261241.000000 222432.000000 6702.270020 1085.130005 8989.230469 3112.989990 1933.560059 3828.409912
+262119.000000 225587.000000 4714.950195 2892.360107 8107.819824 2961.310059 239.977997 3273.719971
+254999.000000 226514.000000 4532.089844 4126.899902 8200.129883 3872.590088 56.089001 2370.580078
+254289.000000 224033.000000 6538.810059 2251.439941 9419.429688 4564.450195 2077.810059 2508.169922
+261890.000000 221960.000000 6846.089844 1475.270020 9125.589844 4598.290039 3299.219971 3475.419922
+264502.000000 223085.000000 5066.379883 3270.560059 7933.169922 4173.709961 1908.910034 3867.459961
+257889.000000 223656.000000 4201.660156 4473.640137 7688.339844 4161.580078 687.578979 3653.689941
+254270.000000 223151.000000 5715.140137 2752.139893 9273.320312 3772.949951 896.403992 3256.060059
+258257.000000 224217.000000 6114.310059 1856.859985 9604.320312 4200.490234 1764.380005 2939.219971
+260020.000000 226868.000000 4237.529785 3605.879883 8066.220215 5430.250000 2138.580078 2696.709961
+255083.000000 225924.000000 3350.310059 4853.069824 7045.819824 5925.200195 1893.609985 2897.340088
+254453.000000 222127.000000 5271.330078 2491.500000 8436.679688 5032.080078 2436.050049 3724.590088
+262588.000000 219950.000000 5994.620117 789.273987 9029.650391 3515.739990 1953.569946 4014.520020
+265610.000000 223333.000000 4391.410156 2400.959961 8146.459961 3536.959961 530.231995 3133.919922
+257470.000000 226977.000000 2975.320068 4633.529785 7278.560059 4640.100098 -50.150200 2024.959961
+250687.000000 226331.000000 4517.859863 3183.800049 8072.600098 5281.660156 1605.140015 2335.139893
+255563.000000 224495.000000 5551.000000 1101.300049 8461.490234 4725.700195 2726.669922 3480.540039
+261335.000000 224645.000000 4764.680176 1557.020020 7833.350098 3524.810059 1577.410034 4038.620117
+260269.000000 224008.000000 3558.030029 2987.610107 7362.439941 3279.229980 562.442017 3786.550049
+257435.000000 221777.000000 4972.600098 2166.879883 8481.440430 3328.719971 1037.130005 3271.370117
+261046.000000 221550.000000 5816.180176 590.216980 9120.929688 3895.399902 2382.669922 2824.169922
+262766.000000 224473.000000 4835.049805 1785.770020 7880.759766 4745.620117 2443.659912 3229.550049
+256509.000000 226413.000000 3758.870117 3461.199951 6743.770020 4928.959961 1536.619995 3546.689941
+250793.000000 224372.000000 5218.490234 2865.260010 7803.959961 4351.089844 1333.819946 3680.489990
+256319.000000 222066.000000 6403.970215 732.344971 9627.759766 3089.300049 1516.780029 3653.689941
+263343.000000 223235.000000 5200.430176 1388.579956 9372.849609 3371.229980 1450.390015 2678.909912
+260903.000000 225110.000000 3722.580078 3246.659912 7876.540039 4716.810059 1498.439941 2116.520020
+254416.000000 223769.000000 4841.649902 2956.399902 8115.919922 5392.359863 2142.810059 2652.320068
+256698.000000 222172.000000 6471.229980 970.395996 8834.980469 4816.839844 2376.629883 3605.860107
+261841.000000 223537.000000 5500.740234 1189.660034 8365.730469 4016.469971 1042.270020 3821.199951
+259503.000000 225840.000000 3827.929932 3088.840088 7676.140137 3978.310059 -357.006989 3016.419922
+253457.000000 224636.000000 4914.609863 3097.449951 8224.900391 4321.439941 171.373993 2412.360107
+256029.000000 222221.000000 6841.799805 1028.500000 9252.299805 4387.569824 2418.139893 2510.100098
+262840.000000 222550.000000 6210.250000 1410.729980 8538.900391 4152.580078 3009.300049 3219.760010
+261633.000000 225065.000000 4284.529785 3357.209961 7282.169922 3823.590088 1402.839966 3644.669922
+254591.000000 225109.000000 4693.160156 3647.739990 7745.160156 3686.379883 490.161011 3448.860107
+254780.000000 223599.000000 6527.379883 1569.869995 9438.429688 3456.580078 1162.520020 3252.010010
+260639.000000 224107.000000 6531.049805 1633.050049 9283.719727 4174.020020 2089.550049 2775.750000
+261108.000000 225472.000000 4968.259766 3527.850098 7692.870117 5137.100098 2207.389893 2436.659912
+255775.000000 223708.000000 4963.450195 4017.370117 7701.419922 5269.649902 2284.399902 2842.080078
+257398.000000 220947.000000 6767.500000 1645.709961 9107.070312 4000.179932 2548.860107 3624.770020
+264924.000000 221559.000000 6471.459961 1110.329956 9459.650391 3108.169922 1696.969971 3893.439941
+265339.000000 225733.000000 4348.799805 3459.510010 8475.299805 4031.239990 573.346985 2910.270020
+256814.000000 226995.000000 3479.540039 4949.790039 7499.910156 5624.709961 751.656006 2347.709961
+253316.000000 225161.000000 5147.060059 3218.429932 8460.160156 5869.299805 2336.320068 2987.959961
+259360.000000 223101.000000 5549.120117 1869.949951 8740.759766 4668.939941 2457.909912 3758.820068
+262012.000000 224016.000000 4173.609863 3004.129883 8157.040039 3704.729980 987.963989 3652.750000
+257176.000000 224420.000000 3517.300049 4118.750000 7822.240234 3718.229980 37.264900 2953.679932
+255146.000000 223322.000000 4923.979980 2330.679932 9095.910156 3792.399902 1013.070007 2711.239990
+260524.000000 223651.000000 5413.629883 1146.209961 8817.169922 4419.649902 2446.649902 2832.050049
+262098.000000 225752.000000 4262.979980 2270.969971 7135.479980 5067.120117 2294.679932 3376.620117
+256889.000000 225379.000000 3606.459961 3568.189941 6552.649902 4970.270020 1516.380005 3662.570068
+253948.000000 222631.000000 5511.700195 2066.300049 7952.660156 4019.909912 1513.140015 3752.629883
+259799.000000 222067.000000 5873.500000 608.583984 9253.780273 2870.739990 1348.239990 3344.199951
+262547.000000 224901.000000 4346.080078 1928.099976 8590.969727 3455.459961 904.390991 2379.270020
+256137.000000 226761.000000 3423.560059 3379.080078 7471.149902 4894.169922 1153.540039 2031.410034
+250326.000000 225013.000000 5519.979980 2423.969971 7991.759766 5117.950195 2098.790039 3099.239990
+255454.000000 222992.000000 6547.950195 496.496002 8751.339844 3900.560059 2132.290039 4076.810059
+261286.000000 223489.000000 5152.850098 1501.510010 8425.610352 2888.030029 776.114014 3786.360107
+258969.000000 224069.000000 3832.610107 3001.979980 7979.259766 3182.310059 52.716000 2874.800049
+254946.000000 222035.000000 5317.879883 2139.800049 9103.139648 3955.610107 1235.170044 2394.149902
+258676.000000 221205.000000 6594.910156 505.343994 9423.360352 4562.470215 2913.739990 2892.350098
+262125.000000 223566.000000 5116.750000 1773.599976 8082.200195 4776.370117 2386.389893 3659.729980
+257835.000000 225918.000000 3714.300049 3477.080078 7205.370117 4554.609863 711.539001 3878.419922
+253660.000000 224371.000000 5022.450195 2592.429932 8277.200195 4119.370117 486.507996 3666.739990
+259503.000000 222061.000000 6589.950195 659.935974 9596.919922 3598.100098 1702.489990 3036.600098
+265495.000000 222843.000000 5541.850098 1728.430054 8459.959961 4492.000000 2231.969971 2430.620117
+260929.000000 224996.000000 4000.949951 3745.989990 6983.790039 5430.859863 1855.260010 2533.379883
+252716.000000 224335.000000 5086.560059 3401.149902 7597.970215 5196.120117 1755.719971 3079.760010
+254110.000000 223111.000000 6822.189941 1229.079956 9164.339844 3761.229980 1679.390015 3584.879883
+259969.000000 224693.000000 6183.950195 1538.500000 9222.080078 3139.169922 949.901978 3180.800049
+259078.000000 226913.000000 4388.890137 3694.820068 8195.019531 3933.000000 426.079987 2388.449951
+254563.000000 224760.000000 5168.439941 4020.939941 8450.269531 4758.910156 1458.900024 2286.429932
+258059.000000 221217.000000 6883.459961 1649.530029 9232.780273 4457.649902 3057.820068 3031.949951
+264667.000000 221177.000000 6218.509766 1645.729980 8657.179688 3663.500000 2528.280029 3978.340088
+262925.000000 224382.000000 4627.500000 3635.929932 7892.799805 3431.320068 604.508972 3901.370117
+254708.000000 225448.000000 4408.250000 4461.040039 8197.169922 3953.750000 -44.534599 3154.870117
+253702.000000 224635.000000 5825.770020 2577.050049 9590.049805 4569.250000 1460.270020 2785.169922
+260206.000000 224140.000000 5387.979980 1951.160034 8789.509766 5131.660156 2706.379883 2972.479980
+261240.000000 224737.000000 3860.810059 3418.310059 7414.529785 5284.520020 2271.379883 3183.149902
+256140.000000 223252.000000 3850.010010 3957.139893 7262.649902 4964.640137 1499.510010 3453.129883
+256116.000000 221349.000000 5594.479980 2054.399902 8835.129883 3662.010010 1485.510010 3613.010010

tests/data/extract-6

@@ -0,0 +1,120 @@
+251774.000000 224241.000000 5688.100098 1915.530029 9329.219727 4183.709961 1212.349976 2641.790039
+259567.000000 222698.000000 6207.600098 678.671997 9380.230469 4575.580078 2830.610107 2688.629883
+263073.000000 223304.000000 4961.640137 2197.120117 7687.310059 4861.859863 2732.780029 3008.540039
+257614.000000 223323.000000 5003.660156 3525.139893 7165.310059 4685.620117 1715.380005 3440.479980
+255780.000000 221915.000000 6357.310059 2145.290039 8426.969727 3775.350098 1475.390015 3797.239990
+260166.000000 223008.000000 6702.589844 1484.959961 9288.099609 3330.830078 1228.500000 3214.320068
+261231.000000 226426.000000 4980.060059 2982.379883 8499.629883 4267.669922 994.088989 2292.889893
+255117.000000 226642.000000 4584.410156 4656.439941 7860.149902 5317.310059 1473.599976 2111.689941
+253300.000000 223554.000000 6455.089844 3036.649902 8869.750000 4986.310059 2607.360107 2839.590088
+261061.000000 221263.000000 6951.979980 1500.239990 9386.099609 3791.679932 2677.010010 3980.629883
+266503.000000 223198.000000 5189.609863 2594.560059 8571.530273 3175.000000 919.840027 3792.010010
+260692.000000 225184.000000 3782.479980 4642.879883 7662.959961 3917.790039 -251.097000 2907.060059
+253963.000000 225081.000000 5123.529785 3839.550049 8669.030273 4877.819824 943.723999 2527.449951
+256555.000000 224169.000000 5930.600098 2298.540039 8906.709961 5331.680176 2549.909912 3053.560059
+260889.000000 225010.000000 4681.129883 2971.870117 7900.040039 4874.080078 2322.429932 3649.120117
+257944.000000 224923.000000 3291.139893 4357.089844 7131.589844 4385.560059 1077.050049 3664.040039
+255009.000000 223018.000000 4584.819824 2864.000000 8469.490234 3625.580078 985.557007 3504.229980
+260114.000000 221947.000000 5676.189941 1210.339966 9393.780273 3390.239990 1654.020020 3018.699951
+264277.000000 224438.000000 4446.620117 2176.719971 8142.089844 4584.879883 2327.830078 2615.800049
+259221.000000 226471.000000 2734.439941 4182.759766 6389.549805 5540.520020 1958.880005 2720.120117
+252650.000000 224831.000000 4163.640137 2989.989990 7179.200195 5213.060059 1929.550049 3457.659912
+257083.000000 222048.000000 5759.040039 702.440979 8566.549805 3552.020020 1832.939941 3956.189941
+263130.000000 222967.000000 5141.140137 1166.119995 8666.959961 2720.370117 971.374023 3479.729980
+260236.000000 225265.000000 3425.139893 3339.080078 7853.609863 3674.949951 525.908020 2443.310059
+253503.000000 224527.000000 4398.129883 2927.429932 8110.279785 4842.470215 1513.869995 2467.100098
+256126.000000 222693.000000 6043.529785 656.223999 8797.559570 4832.410156 2832.370117 3426.139893
+261677.000000 223608.000000 5830.459961 1033.910034 8123.939941 3980.689941 1927.959961 4092.719971
+259457.000000 225536.000000 4015.570068 2995.989990 7135.439941 3713.550049 307.220001 3849.429932
+253352.000000 224216.000000 4650.560059 3196.620117 8131.279785 3586.159912 70.832298 3074.179932
+256124.000000 221513.000000 6100.479980 821.979980 9757.540039 3474.510010 1647.520020 2559.860107
+263024.000000 221559.000000 5789.959961 699.416992 9129.740234 4153.080078 2829.250000 2677.270020
+261720.000000 224015.000000 4358.500000 2645.360107 7414.109863 4810.669922 2225.989990 3185.989990
+254756.000000 224240.000000 4857.379883 3229.679932 7539.310059 4769.140137 1507.130005 3668.260010
+256889.000000 222658.000000 6473.419922 1214.109985 9010.759766 3848.729980 1303.839966 3778.500000
+264208.000000 223316.000000 5700.450195 1116.560059 9087.610352 3846.679932 1293.589966 2891.560059
+263310.000000 225719.000000 3936.120117 3252.360107 7552.850098 4897.859863 1156.630005 2037.160034
+255079.000000 225086.000000 4536.450195 3960.110107 7454.589844 5479.069824 1596.359985 2190.800049
+254487.000000 222508.000000 6635.859863 1758.849976 8732.969727 4466.970215 2650.360107 3139.310059
+261241.000000 222432.000000 6702.270020 1085.130005 8989.230469 3112.989990 1933.560059 3828.409912
+262119.000000 225587.000000 4714.950195 2892.360107 8107.819824 2961.310059 239.977997 3273.719971
+254999.000000 226514.000000 4532.089844 4126.899902 8200.129883 3872.590088 56.089001 2370.580078
+254289.000000 224033.000000 6538.810059 2251.439941 9419.429688 4564.450195 2077.810059 2508.169922
+261890.000000 221960.000000 6846.089844 1475.270020 9125.589844 4598.290039 3299.219971 3475.419922
+264502.000000 223085.000000 5066.379883 3270.560059 7933.169922 4173.709961 1908.910034 3867.459961
+257889.000000 223656.000000 4201.660156 4473.640137 7688.339844 4161.580078 687.578979 3653.689941
+254270.000000 223151.000000 5715.140137 2752.139893 9273.320312 3772.949951 896.403992 3256.060059
+258257.000000 224217.000000 6114.310059 1856.859985 9604.320312 4200.490234 1764.380005 2939.219971
+260020.000000 226868.000000 4237.529785 3605.879883 8066.220215 5430.250000 2138.580078 2696.709961
+255083.000000 225924.000000 3350.310059 4853.069824 7045.819824 5925.200195 1893.609985 2897.340088
+254453.000000 222127.000000 5271.330078 2491.500000 8436.679688 5032.080078 2436.050049 3724.590088
+262588.000000 219950.000000 5994.620117 789.273987 9029.650391 3515.739990 1953.569946 4014.520020
+265610.000000 223333.000000 4391.410156 2400.959961 8146.459961 3536.959961 530.231995 3133.919922
+257470.000000 226977.000000 2975.320068 4633.529785 7278.560059 4640.100098 -50.150200 2024.959961
+250687.000000 226331.000000 4517.859863 3183.800049 8072.600098 5281.660156 1605.140015 2335.139893
+255563.000000 224495.000000 5551.000000 1101.300049 8461.490234 4725.700195 2726.669922 3480.540039
+261335.000000 224645.000000 4764.680176 1557.020020 7833.350098 3524.810059 1577.410034 4038.620117
+260269.000000 224008.000000 3558.030029 2987.610107 7362.439941 3279.229980 562.442017 3786.550049
+257435.000000 221777.000000 4972.600098 2166.879883 8481.440430 3328.719971 1037.130005 3271.370117
+261046.000000 221550.000000 5816.180176 590.216980 9120.929688 3895.399902 2382.669922 2824.169922
+262766.000000 224473.000000 4835.049805 1785.770020 7880.759766 4745.620117 2443.659912 3229.550049
+256509.000000 226413.000000 3758.870117 3461.199951 6743.770020 4928.959961 1536.619995 3546.689941
+250793.000000 224372.000000 5218.490234 2865.260010 7803.959961 4351.089844 1333.819946 3680.489990
+256319.000000 222066.000000 6403.970215 732.344971 9627.759766 3089.300049 1516.780029 3653.689941
+263343.000000 223235.000000 5200.430176 1388.579956 9372.849609 3371.229980 1450.390015 2678.909912
+260903.000000 225110.000000 3722.580078 3246.659912 7876.540039 4716.810059 1498.439941 2116.520020
+254416.000000 223769.000000 4841.649902 2956.399902 8115.919922 5392.359863 2142.810059 2652.320068
+256698.000000 222172.000000 6471.229980 970.395996 8834.980469 4816.839844 2376.629883 3605.860107
+261841.000000 223537.000000 5500.740234 1189.660034 8365.730469 4016.469971 1042.270020 3821.199951
+259503.000000 225840.000000 3827.929932 3088.840088 7676.140137 3978.310059 -357.006989 3016.419922
+253457.000000 224636.000000 4914.609863 3097.449951 8224.900391 4321.439941 171.373993 2412.360107
+256029.000000 222221.000000 6841.799805 1028.500000 9252.299805 4387.569824 2418.139893 2510.100098
+262840.000000 222550.000000 6210.250000 1410.729980 8538.900391 4152.580078 3009.300049 3219.760010
+261633.000000 225065.000000 4284.529785 3357.209961 7282.169922 3823.590088 1402.839966 3644.669922
+254591.000000 225109.000000 4693.160156 3647.739990 7745.160156 3686.379883 490.161011 3448.860107
+254780.000000 223599.000000 6527.379883 1569.869995 9438.429688 3456.580078 1162.520020 3252.010010
+260639.000000 224107.000000 6531.049805 1633.050049 9283.719727 4174.020020 2089.550049 2775.750000
+261108.000000 225472.000000 4968.259766 3527.850098 7692.870117 5137.100098 2207.389893 2436.659912
+255775.000000 223708.000000 4963.450195 4017.370117 7701.419922 5269.649902 2284.399902 2842.080078
+257398.000000 220947.000000 6767.500000 1645.709961 9107.070312 4000.179932 2548.860107 3624.770020
+264924.000000 221559.000000 6471.459961 1110.329956 9459.650391 3108.169922 1696.969971 3893.439941
+265339.000000 225733.000000 4348.799805 3459.510010 8475.299805 4031.239990 573.346985 2910.270020
+256814.000000 226995.000000 3479.540039 4949.790039 7499.910156 5624.709961 751.656006 2347.709961
+253316.000000 225161.000000 5147.060059 3218.429932 8460.160156 5869.299805 2336.320068 2987.959961
+259360.000000 223101.000000 5549.120117 1869.949951 8740.759766 4668.939941 2457.909912 3758.820068
+262012.000000 224016.000000 4173.609863 3004.129883 8157.040039 3704.729980 987.963989 3652.750000
+257176.000000 224420.000000 3517.300049 4118.750000 7822.240234 3718.229980 37.264900 2953.679932
+255146.000000 223322.000000 4923.979980 2330.679932 9095.910156 3792.399902 1013.070007 2711.239990
+260524.000000 223651.000000 5413.629883 1146.209961 8817.169922 4419.649902 2446.649902 2832.050049
+262098.000000 225752.000000 4262.979980 2270.969971 7135.479980 5067.120117 2294.679932 3376.620117
+256889.000000 225379.000000 3606.459961 3568.189941 6552.649902 4970.270020 1516.380005 3662.570068
+253948.000000 222631.000000 5511.700195 2066.300049 7952.660156 4019.909912 1513.140015 3752.629883
+259799.000000 222067.000000 5873.500000 608.583984 9253.780273 2870.739990 1348.239990 3344.199951
+262547.000000 224901.000000 4346.080078 1928.099976 8590.969727 3455.459961 904.390991 2379.270020
+256137.000000 226761.000000 3423.560059 3379.080078 7471.149902 4894.169922 1153.540039 2031.410034
+250326.000000 225013.000000 5519.979980 2423.969971 7991.759766 5117.950195 2098.790039 3099.239990
+255454.000000 222992.000000 6547.950195 496.496002 8751.339844 3900.560059 2132.290039 4076.810059
+261286.000000 223489.000000 5152.850098 1501.510010 8425.610352 2888.030029 776.114014 3786.360107
+258969.000000 224069.000000 3832.610107 3001.979980 7979.259766 3182.310059 52.716000 2874.800049
+254946.000000 222035.000000 5317.879883 2139.800049 9103.139648 3955.610107 1235.170044 2394.149902
+258676.000000 221205.000000 6594.910156 505.343994 9423.360352 4562.470215 2913.739990 2892.350098
+262125.000000 223566.000000 5116.750000 1773.599976 8082.200195 4776.370117 2386.389893 3659.729980
+257835.000000 225918.000000 3714.300049 3477.080078 7205.370117 4554.609863 711.539001 3878.419922
+253660.000000 224371.000000 5022.450195 2592.429932 8277.200195 4119.370117 486.507996 3666.739990
+259503.000000 222061.000000 6589.950195 659.935974 9596.919922 3598.100098 1702.489990 3036.600098
+265495.000000 222843.000000 5541.850098 1728.430054 8459.959961 4492.000000 2231.969971 2430.620117
+260929.000000 224996.000000 4000.949951 3745.989990 6983.790039 5430.859863 1855.260010 2533.379883
+252716.000000 224335.000000 5086.560059 3401.149902 7597.970215 5196.120117 1755.719971 3079.760010
+254110.000000 223111.000000 6822.189941 1229.079956 9164.339844 3761.229980 1679.390015 3584.879883
+259969.000000 224693.000000 6183.950195 1538.500000 9222.080078 3139.169922 949.901978 3180.800049
+259078.000000 226913.000000 4388.890137 3694.820068 8195.019531 3933.000000 426.079987 2388.449951
+254563.000000 224760.000000 5168.439941 4020.939941 8450.269531 4758.910156 1458.900024 2286.429932
+258059.000000 221217.000000 6883.459961 1649.530029 9232.780273 4457.649902 3057.820068 3031.949951
+264667.000000 221177.000000 6218.509766 1645.729980 8657.179688 3663.500000 2528.280029 3978.340088
+262925.000000 224382.000000 4627.500000 3635.929932 7892.799805 3431.320068 604.508972 3901.370117
+254708.000000 225448.000000 4408.250000 4461.040039 8197.169922 3953.750000 -44.534599 3154.870117
+253702.000000 224635.000000 5825.770020 2577.050049 9590.049805 4569.250000 1460.270020 2785.169922
+260206.000000 224140.000000 5387.979980 1951.160034 8789.509766 5131.660156 2706.379883 2972.479980
+261240.000000 224737.000000 3860.810059 3418.310059 7414.529785 5284.520020 2271.379883 3183.149902
+256140.000000 223252.000000 3850.010010 3957.139893 7262.649902 4964.640137 1499.510010 3453.129883
+256116.000000 221349.000000 5594.479980 2054.399902 8835.129883 3662.010010 1485.510010 3613.010010

tests/data/extract-7

@@ -0,0 +1,124 @@
+# path: /newton/prep
+# layout: PrepData
+# start: 1332496830.0
+# end: 1332496830.999
+1332496830.000000 251774.000000 224241.000000 5688.100098 1915.530029 9329.219727 4183.709961 1212.349976 2641.790039
+1332496830.008333 259567.000000 222698.000000 6207.600098 678.671997 9380.230469 4575.580078 2830.610107 2688.629883
+1332496830.016667 263073.000000 223304.000000 4961.640137 2197.120117 7687.310059 4861.859863 2732.780029 3008.540039
+1332496830.025000 257614.000000 223323.000000 5003.660156 3525.139893 7165.310059 4685.620117 1715.380005 3440.479980
+1332496830.033333 255780.000000 221915.000000 6357.310059 2145.290039 8426.969727 3775.350098 1475.390015 3797.239990
+1332496830.041667 260166.000000 223008.000000 6702.589844 1484.959961 9288.099609 3330.830078 1228.500000 3214.320068
+1332496830.050000 261231.000000 226426.000000 4980.060059 2982.379883 8499.629883 4267.669922 994.088989 2292.889893
+1332496830.058333 255117.000000 226642.000000 4584.410156 4656.439941 7860.149902 5317.310059 1473.599976 2111.689941
+1332496830.066667 253300.000000 223554.000000 6455.089844 3036.649902 8869.750000 4986.310059 2607.360107 2839.590088
+1332496830.075000 261061.000000 221263.000000 6951.979980 1500.239990 9386.099609 3791.679932 2677.010010 3980.629883
+1332496830.083333 266503.000000 223198.000000 5189.609863 2594.560059 8571.530273 3175.000000 919.840027 3792.010010
+1332496830.091667 260692.000000 225184.000000 3782.479980 4642.879883 7662.959961 3917.790039 -251.097000 2907.060059
+1332496830.100000 253963.000000 225081.000000 5123.529785 3839.550049 8669.030273 4877.819824 943.723999 2527.449951
+1332496830.108333 256555.000000 224169.000000 5930.600098 2298.540039 8906.709961 5331.680176 2549.909912 3053.560059
+1332496830.116667 260889.000000 225010.000000 4681.129883 2971.870117 7900.040039 4874.080078 2322.429932 3649.120117
+1332496830.125000 257944.000000 224923.000000 3291.139893 4357.089844 7131.589844 4385.560059 1077.050049 3664.040039
+1332496830.133333 255009.000000 223018.000000 4584.819824 2864.000000 8469.490234 3625.580078 985.557007 3504.229980
+1332496830.141667 260114.000000 221947.000000 5676.189941 1210.339966 9393.780273 3390.239990 1654.020020 3018.699951
+1332496830.150000 264277.000000 224438.000000 4446.620117 2176.719971 8142.089844 4584.879883 2327.830078 2615.800049
+1332496830.158333 259221.000000 226471.000000 2734.439941 4182.759766 6389.549805 5540.520020 1958.880005 2720.120117
+1332496830.166667 252650.000000 224831.000000 4163.640137 2989.989990 7179.200195 5213.060059 1929.550049 3457.659912
+1332496830.175000 257083.000000 222048.000000 5759.040039 702.440979 8566.549805 3552.020020 1832.939941 3956.189941
+1332496830.183333 263130.000000 222967.000000 5141.140137 1166.119995 8666.959961 2720.370117 971.374023 3479.729980
+1332496830.191667 260236.000000 225265.000000 3425.139893 3339.080078 7853.609863 3674.949951 525.908020 2443.310059
+1332496830.200000 253503.000000 224527.000000 4398.129883 2927.429932 8110.279785 4842.470215 1513.869995 2467.100098
+1332496830.208333 256126.000000 222693.000000 6043.529785 656.223999 8797.559570 4832.410156 2832.370117 3426.139893
+1332496830.216667 261677.000000 223608.000000 5830.459961 1033.910034 8123.939941 3980.689941 1927.959961 4092.719971
+1332496830.225000 259457.000000 225536.000000 4015.570068 2995.989990 7135.439941 3713.550049 307.220001 3849.429932
+1332496830.233333 253352.000000 224216.000000 4650.560059 3196.620117 8131.279785 3586.159912 70.832298 3074.179932
+1332496830.241667 256124.000000 221513.000000 6100.479980 821.979980 9757.540039 3474.510010 1647.520020 2559.860107
+1332496830.250000 263024.000000 221559.000000 5789.959961 699.416992 9129.740234 4153.080078 2829.250000 2677.270020
+1332496830.258333 261720.000000 224015.000000 4358.500000 2645.360107 7414.109863 4810.669922 2225.989990 3185.989990
+1332496830.266667 254756.000000 224240.000000 4857.379883 3229.679932 7539.310059 4769.140137 1507.130005 3668.260010
+1332496830.275000 256889.000000 222658.000000 6473.419922 1214.109985 9010.759766 3848.729980 1303.839966 3778.500000
+1332496830.283333 264208.000000 223316.000000 5700.450195 1116.560059 9087.610352 3846.679932 1293.589966 2891.560059
+1332496830.291667 263310.000000 225719.000000 3936.120117 3252.360107 7552.850098 4897.859863 1156.630005 2037.160034
+1332496830.300000 255079.000000 225086.000000 4536.450195 3960.110107 7454.589844 5479.069824 1596.359985 2190.800049
+1332496830.308333 254487.000000 222508.000000 6635.859863 1758.849976 8732.969727 4466.970215 2650.360107 3139.310059
+1332496830.316667 261241.000000 222432.000000 6702.270020 1085.130005 8989.230469 3112.989990 1933.560059 3828.409912
+1332496830.325000 262119.000000 225587.000000 4714.950195 2892.360107 8107.819824 2961.310059 239.977997 3273.719971
+1332496830.333333 254999.000000 226514.000000 4532.089844 4126.899902 8200.129883 3872.590088 56.089001 2370.580078
+1332496830.341667 254289.000000 224033.000000 6538.810059 2251.439941 9419.429688 4564.450195 2077.810059 2508.169922
+1332496830.350000 261890.000000 221960.000000 6846.089844 1475.270020 9125.589844 4598.290039 3299.219971 3475.419922
+1332496830.358333 264502.000000 223085.000000 5066.379883 3270.560059 7933.169922 4173.709961 1908.910034 3867.459961
+1332496830.366667 257889.000000 223656.000000 4201.660156 4473.640137 7688.339844 4161.580078 687.578979 3653.689941
+1332496830.375000 254270.000000 223151.000000 5715.140137 2752.139893 9273.320312 3772.949951 896.403992 3256.060059
+1332496830.383333 258257.000000 224217.000000 6114.310059 1856.859985 9604.320312 4200.490234 1764.380005 2939.219971
+1332496830.391667 260020.000000 226868.000000 4237.529785 3605.879883 8066.220215 5430.250000 2138.580078 2696.709961
+1332496830.400000 255083.000000 225924.000000 3350.310059 4853.069824 7045.819824 5925.200195 1893.609985 2897.340088
+1332496830.408333 254453.000000 222127.000000 5271.330078 2491.500000 8436.679688 5032.080078 2436.050049 3724.590088
+1332496830.416667 262588.000000 219950.000000 5994.620117 789.273987 9029.650391 3515.739990 1953.569946 4014.520020
+1332496830.425000 265610.000000 223333.000000 4391.410156 2400.959961 8146.459961 3536.959961 530.231995 3133.919922
+1332496830.433333 257470.000000 226977.000000 2975.320068 4633.529785 7278.560059 4640.100098 -50.150200 2024.959961
+1332496830.441667 250687.000000 226331.000000 4517.859863 3183.800049 8072.600098 5281.660156 1605.140015 2335.139893
+1332496830.450000 255563.000000 224495.000000 5551.000000 1101.300049 8461.490234 4725.700195 2726.669922 3480.540039
+1332496830.458333 261335.000000 224645.000000 4764.680176 1557.020020 7833.350098 3524.810059 1577.410034 4038.620117
+1332496830.466667 260269.000000 224008.000000 3558.030029 2987.610107 7362.439941 3279.229980 562.442017 3786.550049
+1332496830.475000 257435.000000 221777.000000 4972.600098 2166.879883 8481.440430 3328.719971 1037.130005 3271.370117
+1332496830.483333 261046.000000 221550.000000 5816.180176 590.216980 9120.929688 3895.399902 2382.669922 2824.169922
+1332496830.491667 262766.000000 224473.000000 4835.049805 1785.770020 7880.759766 4745.620117 2443.659912 3229.550049
+1332496830.500000 256509.000000 226413.000000 3758.870117 3461.199951 6743.770020 4928.959961 1536.619995 3546.689941
+1332496830.508333 250793.000000 224372.000000 5218.490234 2865.260010 7803.959961 4351.089844 1333.819946 3680.489990
+1332496830.516667 256319.000000 222066.000000 6403.970215 732.344971 9627.759766 3089.300049 1516.780029 3653.689941
+1332496830.525000 263343.000000 223235.000000 5200.430176 1388.579956 9372.849609 3371.229980 1450.390015 2678.909912
+1332496830.533333 260903.000000 225110.000000 3722.580078 3246.659912 7876.540039 4716.810059 1498.439941 2116.520020
+1332496830.541667 254416.000000 223769.000000 4841.649902 2956.399902 8115.919922 5392.359863 2142.810059 2652.320068
+1332496830.550000 256698.000000 222172.000000 6471.229980 970.395996 8834.980469 4816.839844 2376.629883 3605.860107
+1332496830.558333 261841.000000 223537.000000 5500.740234 1189.660034 8365.730469 4016.469971 1042.270020 3821.199951
+1332496830.566667 259503.000000 225840.000000 3827.929932 3088.840088 7676.140137 3978.310059 -357.006989 3016.419922
+1332496830.575000 253457.000000 224636.000000 4914.609863 3097.449951 8224.900391 4321.439941 171.373993 2412.360107
+1332496830.583333 256029.000000 222221.000000 6841.799805 1028.500000 9252.299805 4387.569824 2418.139893 2510.100098
+1332496830.591667 262840.000000 222550.000000 6210.250000 1410.729980 8538.900391 4152.580078 3009.300049 3219.760010
+1332496830.600000 261633.000000 225065.000000 4284.529785 3357.209961 7282.169922 3823.590088 1402.839966 3644.669922
+1332496830.608333 254591.000000 225109.000000 4693.160156 3647.739990 7745.160156 3686.379883 490.161011 3448.860107
+1332496830.616667 254780.000000 223599.000000 6527.379883 1569.869995 9438.429688 3456.580078 1162.520020 3252.010010
+1332496830.625000 260639.000000 224107.000000 6531.049805 1633.050049 9283.719727 4174.020020 2089.550049 2775.750000
+1332496830.633333 261108.000000 225472.000000 4968.259766 3527.850098 7692.870117 5137.100098 2207.389893 2436.659912
+1332496830.641667 255775.000000 223708.000000 4963.450195 4017.370117 7701.419922 5269.649902 2284.399902 2842.080078
+1332496830.650000 257398.000000 220947.000000 6767.500000 1645.709961 9107.070312 4000.179932 2548.860107 3624.770020
+1332496830.658333 264924.000000 221559.000000 6471.459961 1110.329956 9459.650391 3108.169922 1696.969971 3893.439941
+1332496830.666667 265339.000000 225733.000000 4348.799805 3459.510010 8475.299805 4031.239990 573.346985 2910.270020
+1332496830.675000 256814.000000 226995.000000 3479.540039 4949.790039 7499.910156 5624.709961 751.656006 2347.709961
+1332496830.683333 253316.000000 225161.000000 5147.060059 3218.429932 8460.160156 5869.299805 2336.320068 2987.959961
+1332496830.691667 259360.000000 223101.000000 5549.120117 1869.949951 8740.759766 4668.939941 2457.909912 3758.820068
+1332496830.700000 262012.000000 224016.000000 4173.609863 3004.129883 8157.040039 3704.729980 987.963989 3652.750000
+1332496830.708333 257176.000000 224420.000000 3517.300049 4118.750000 7822.240234 3718.229980 37.264900 2953.679932
+1332496830.716667 255146.000000 223322.000000 4923.979980 2330.679932 9095.910156 3792.399902 1013.070007 2711.239990
+1332496830.725000 260524.000000 223651.000000 5413.629883 1146.209961 8817.169922 4419.649902 2446.649902 2832.050049
+1332496830.733333 262098.000000 225752.000000 4262.979980 2270.969971 7135.479980 5067.120117 2294.679932 3376.620117
+1332496830.741667 256889.000000 225379.000000 3606.459961 3568.189941 6552.649902 4970.270020 1516.380005 3662.570068
+1332496830.750000 253948.000000 222631.000000 5511.700195 2066.300049 7952.660156 4019.909912 1513.140015 3752.629883
+1332496830.758333 259799.000000 222067.000000 5873.500000 608.583984 9253.780273 2870.739990 1348.239990 3344.199951
+1332496830.766667 262547.000000 224901.000000 4346.080078 1928.099976 8590.969727 3455.459961 904.390991 2379.270020
+1332496830.775000 256137.000000 226761.000000 3423.560059 3379.080078 7471.149902 4894.169922 1153.540039 2031.410034
+1332496830.783333 250326.000000 225013.000000 5519.979980 2423.969971 7991.759766 5117.950195 2098.790039 3099.239990
+1332496830.791667 255454.000000 222992.000000 6547.950195 496.496002 8751.339844 3900.560059 2132.290039 4076.810059
+1332496830.800000 261286.000000 223489.000000 5152.850098 1501.510010 8425.610352 2888.030029 776.114014 3786.360107
+1332496830.808333 258969.000000 224069.000000 3832.610107 3001.979980 7979.259766 3182.310059 52.716000 2874.800049
+1332496830.816667 254946.000000 222035.000000 5317.879883 2139.800049 9103.139648 3955.610107 1235.170044 2394.149902
+1332496830.825000 258676.000000 221205.000000 6594.910156 505.343994 9423.360352 4562.470215 2913.739990 2892.350098
+1332496830.833333 262125.000000 223566.000000 5116.750000 1773.599976 8082.200195 4776.370117 2386.389893 3659.729980
+1332496830.841667 257835.000000 225918.000000 3714.300049 3477.080078 7205.370117 4554.609863 711.539001 3878.419922
+1332496830.850000 253660.000000 224371.000000 5022.450195 2592.429932 8277.200195 4119.370117 486.507996 3666.739990
+1332496830.858333 259503.000000 222061.000000 6589.950195 659.935974 9596.919922 3598.100098 1702.489990 3036.600098
+1332496830.866667 265495.000000 222843.000000 5541.850098 1728.430054 8459.959961 4492.000000 2231.969971 2430.620117
+1332496830.875000 260929.000000 224996.000000 4000.949951 3745.989990 6983.790039 5430.859863 1855.260010 2533.379883
+1332496830.883333 252716.000000 224335.000000 5086.560059 3401.149902 7597.970215 5196.120117 1755.719971 3079.760010
+1332496830.891667 254110.000000 223111.000000 6822.189941 1229.079956 9164.339844 3761.229980 1679.390015 3584.879883
+1332496830.900000 259969.000000 224693.000000 6183.950195 1538.500000 9222.080078 3139.169922 949.901978 3180.800049
+1332496830.908333 259078.000000 226913.000000 4388.890137 3694.820068 8195.019531 3933.000000 426.079987 2388.449951
+1332496830.916667 254563.000000 224760.000000 5168.439941 4020.939941 8450.269531 4758.910156 1458.900024 2286.429932
+1332496830.925000 258059.000000 221217.000000 6883.459961 1649.530029 9232.780273 4457.649902 3057.820068 3031.949951
+1332496830.933333 264667.000000 221177.000000 6218.509766 1645.729980 8657.179688 3663.500000 2528.280029 3978.340088
+1332496830.941667 262925.000000 224382.000000 4627.500000 3635.929932 7892.799805 3431.320068 604.508972 3901.370117
+1332496830.950000 254708.000000 225448.000000 4408.250000 4461.040039 8197.169922 3953.750000 -44.534599 3154.870117
+1332496830.958333 253702.000000 224635.000000 5825.770020 2577.050049 9590.049805 4569.250000 1460.270020 2785.169922
+1332496830.966667 260206.000000 224140.000000 5387.979980 1951.160034 8789.509766 5131.660156 2706.379883 2972.479980
+1332496830.975000 261240.000000 224737.000000 3860.810059 3418.310059 7414.529785 5284.520020 2271.379883 3183.149902
+1332496830.983333 256140.000000 223252.000000 3850.010010 3957.139893 7262.649902 4964.640137 1499.510010 3453.129883
+1332496830.991667 256116.000000 221349.000000 5594.479980 2054.399902 8835.129883 3662.010010 1485.510010 3613.010010

tests/data/prep-20120323T1002-first19lines

@@ -0,0 +1,19 @@
+2.56437e+05  2.24430e+05  4.01161e+03  3.47534e+03  7.49589e+03  3.38894e+03  2.61397e+02  3.73126e+03  
+2.53963e+05  2.24167e+05  5.62107e+03  1.54801e+03  9.16517e+03  3.52293e+03  1.05893e+03  2.99696e+03  
+2.58508e+05  2.24930e+05  6.01140e+03  8.18866e+02  9.03995e+03  4.48244e+03  2.49039e+03  2.67934e+03  
+2.59627e+05  2.26022e+05  4.47450e+03  2.42302e+03  7.41419e+03  5.07197e+03  2.43938e+03  2.96296e+03  
+2.55187e+05  2.24632e+05  4.73857e+03  3.39804e+03  7.39512e+03  4.72645e+03  1.83903e+03  3.39353e+03  
+2.57102e+05  2.21623e+05  6.14413e+03  1.44109e+03  8.75648e+03  3.49532e+03  1.86994e+03  3.75253e+03  
+2.63653e+05  2.21770e+05  6.22177e+03  7.38962e+02  9.54760e+03  2.66682e+03  1.46266e+03  3.33257e+03  
+2.63613e+05  2.25256e+05  4.47712e+03  2.43745e+03  8.51021e+03  3.85563e+03  9.59442e+02  2.38718e+03  
+2.55350e+05  2.26264e+05  4.28372e+03  3.92394e+03  7.91247e+03  5.46652e+03  1.28499e+03  2.09372e+03  
+2.52727e+05  2.24609e+05  5.85193e+03  2.49198e+03  8.54063e+03  5.62305e+03  2.33978e+03  3.00714e+03  
+2.58475e+05  2.23578e+05  5.92487e+03  1.39448e+03  8.77962e+03  4.54418e+03  2.13203e+03  3.84976e+03  
+2.61563e+05  2.24609e+05  4.33614e+03  2.45575e+03  8.05538e+03  3.46911e+03  6.27873e+02  3.66420e+03  
+2.56401e+05  2.24441e+05  4.18715e+03  3.45717e+03  7.90669e+03  3.53355e+03  -5.84482e+00  2.96687e+03  
+2.54745e+05  2.22644e+05  6.02005e+03  1.94721e+03  9.28939e+03  3.80020e+03  1.34820e+03  2.37785e+03  
+2.60723e+05  2.22660e+05  6.69719e+03  1.03048e+03  9.26124e+03  4.34917e+03  2.84530e+03  2.73619e+03  
+2.63089e+05  2.25711e+05  4.77887e+03  2.60417e+03  7.39660e+03  4.59811e+03  2.17472e+03  3.40729e+03  
+2.55843e+05  2.27128e+05  4.02413e+03  4.39323e+03  6.79336e+03  4.62535e+03  7.52009e+02  3.44647e+03  
+2.51904e+05  2.24868e+05  5.82289e+03  3.02127e+03  8.46160e+03  3.80298e+03  8.07212e+02  3.53468e+03  
+2.57670e+05  2.22974e+05  6.73436e+03  1.60956e+03  9.92960e+03  2.98028e+03  1.44168e+03  3.05351e+03  

tests/data/prep-20120323T1004-badtimes

@@ -0,0 +1,11 @@
+1332497040.000000 2.56439e+05  2.24775e+05  2.92897e+03  4.66646e+03  7.58491e+03  3.57351e+03  -4.34171e+02  2.98819e+03  
+1332497040.010000 2.51903e+05  2.23202e+05  4.23696e+03  3.49363e+03  8.53493e+03  4.29416e+03  8.49573e+02  2.38189e+03  
+1332497040.020000 2.57625e+05  2.20247e+05  5.47017e+03  1.35872e+03  9.18903e+03  4.56136e+03  2.65599e+03  2.60912e+03  
+1332497040.030000 2.63375e+05  2.20706e+05  4.51842e+03  1.80758e+03  8.17208e+03  4.17463e+03  2.57884e+03  3.32848e+03  
+1332497040.040000 2.59221e+05  2.22346e+05  2.98879e+03  3.66264e+03  6.87274e+03  3.94223e+03  1.25928e+03  3.51786e+03  
+1332497040.050000 2.51918e+05  2.22281e+05  4.22677e+03  2.84764e+03  7.78323e+03  3.81659e+03  8.04944e+02  3.46314e+03  
+1332497040.050000 2.54478e+05  2.21701e+05  5.61366e+03  1.02262e+03  9.26581e+03  3.50152e+03  1.29331e+03  3.07271e+03  
+1332497040.060000 2.59568e+05  2.22945e+05  4.97190e+03  1.28250e+03  8.62081e+03  4.06316e+03  1.85717e+03  2.61990e+03  
+1332497040.070000 2.57269e+05  2.23697e+05  3.60527e+03  3.05749e+03  7.22363e+03  4.90330e+03  1.93736e+03  2.35357e+03  
+1332497040.080000 2.52274e+05  2.21438e+05  5.01228e+03  2.86309e+03  7.87115e+03  4.80448e+03  2.18291e+03  2.93397e+03  
+1332497040.090000 2.56468e+05  2.19205e+05  6.29804e+03  8.09467e+02  9.12895e+03  3.52055e+03  2.16980e+03  3.88739e+03  

tests/runtests.py

@@ -0,0 +1,49 @@
+#!/usr/bin/python
+
+import nose
+import os
+import sys
+import glob
+from collections import OrderedDict
+
+# Change into parent dir
+os.chdir(os.path.dirname(os.path.realpath(__file__)) + "/..")
+
+class JimOrderPlugin(nose.plugins.Plugin):
+    """When searching for tests and encountering a directory that
+    contains a 'test.order' file, run tests listed in that file, in the
+    order that they're listed.  Globs are OK in that file and duplicates
+    are removed."""
+    name = 'jimorder'
+    score = 10000
+
+    def prepareTestLoader(self, loader):
+        def wrap(func):
+            def wrapper(name, *args, **kwargs):
+                addr = nose.selector.TestAddress(
+                    name, workingDir=loader.workingDir)
+                try:
+                    order = os.path.join(addr.filename, "test.order")
+                except:
+                    order = None
+                if order and os.path.exists(order):
+                    files = []
+                    for line in open(order):
+                        line = line.split('#')[0].strip()
+                        if not line:
+                            continue
+                        fn = os.path.join(addr.filename, line.strip())
+                        files.extend(sorted(glob.glob(fn)) or [fn])
+                    files = list(OrderedDict.fromkeys(files))
+                    tests = [ wrapper(fn, *args, **kwargs) for fn in files ]
+                    return loader.suiteClass(tests)
+                return func(name, *args, **kwargs)
+            return wrapper
+        loader.loadTestsFromName = wrap(loader.loadTestsFromName)
+        return loader
+
+# Use setup.cfg for most of the test configuration.  Adding
+# --with-jimorder here means that a normal "nosetests" run will
+# still work, it just won't support test.order.
+nose.main(addplugins = [ JimOrderPlugin() ],
+          argv = sys.argv + ["--with-jimorder"])

tests/test.order

@@ -0,0 +1,18 @@
+test_printf.py
+test_lrucache.py
+test_mustclose.py
+
+test_serializer.py
+test_iteratorizer.py
+
+test_timestamper.py
+test_layout.py
+test_rbtree.py
+test_interval.py
+
+test_bulkdata.py
+test_nilmdb.py
+test_client.py
+test_cmdline.py
+
+test_*.py

tests/test_bulkdata.py

@@ -0,0 +1,102 @@
+# -*- coding: utf-8 -*-
+
+import nilmdb
+from nilmdb.utils.printf import *
+from nose.tools import *
+from nose.tools import assert_raises
+import itertools
+
+from testutil.helpers import *
+
+testdb = "tests/bulkdata-testdb"
+
+import nilmdb.server.bulkdata
+from nilmdb.server.bulkdata import BulkData
+
+class TestBulkData(object):
+
+    def test_bulkdata(self):
+        for (size, files, db) in [ ( 0, 0, testdb ),
+                                       ( 25, 1000, testdb ),
+                                       ( 1000, 3, testdb.decode("utf-8") ) ]:
+            recursive_unlink(db)
+            os.mkdir(db)
+            self.do_basic(db, size, files)
+
+    def do_basic(self, db, size, files):
+        """Do the basic test with variable file_size and files_per_dir"""
+        if not size or not files:
+            data = BulkData(db)
+        else:
+            data = BulkData(db, file_size = size, files_per_dir = files)
+
+        # create empty
+        with assert_raises(ValueError):
+            data.create("/foo", "uint16_8")
+        with assert_raises(ValueError):
+            data.create("foo/bar", "uint16_8")
+        with assert_raises(ValueError):
+            data.create("/foo/bar", "uint8_8")
+        data.create("/foo/bar", "uint16_8")
+        data.create(u"/foo/baz/quux", "float64_16")
+        with assert_raises(ValueError):
+            data.create("/foo/bar/baz", "uint16_8")
+        with assert_raises(ValueError):
+            data.create("/foo/baz", "float64_16")
+
+        # get node -- see if caching works
+        nodes = []
+        for i in range(5000):
+            nodes.append(data.getnode("/foo/bar"))
+            nodes.append(data.getnode("/foo/baz/quux"))
+        del nodes
+
+        # Test node
+        node = data.getnode("/foo/bar")
+        with assert_raises(IndexError):
+            x = node[0]
+        raw = []
+        for i in range(1000):
+            raw.append([10000+i, 1, 2, 3, 4, 5, 6, 7, 8 ])
+        node.append(raw[0:1])
+        node.append(raw[1:100])
+        node.append(raw[100:])
+
+        misc_slices = [ 0, 100, slice(None), slice(0), slice(10),
+                        slice(5,10), slice(3,None), slice(3,-3),
+                        slice(20,10), slice(200,100,-1), slice(None,0,-1),
+                        slice(100,500,5) ]
+        # Extract slices
+        for s in misc_slices:
+            eq_(node[s], raw[s])
+
+        # Get some coverage of remove; remove is more fully tested
+        # in cmdline
+        with assert_raises(IndexError):
+            node.remove(9999,9998)
+
+        # close, reopen
+        # reopen
+        data.close()
+        if not size or not files:
+            data = BulkData(db)
+        else:
+            data = BulkData(db, file_size = size, files_per_dir = files)
+        node = data.getnode("/foo/bar")
+
+        # Extract slices
+        for s in misc_slices:
+            eq_(node[s], raw[s])
+
+        # destroy
+        with assert_raises(ValueError):
+            data.destroy("/foo")
+        with assert_raises(ValueError):
+            data.destroy("/foo/baz")
+        with assert_raises(ValueError):
+            data.destroy("/foo/qwerty")
+        data.destroy("/foo/baz/quux")
+        data.destroy("/foo/bar")
+
+        # close
+        data.close()

tests/test_client.py

@@ -0,0 +1,578 @@
+# -*- coding: utf-8 -*-
+
+import nilmdb
+from nilmdb.utils.printf import *
+from nilmdb.utils import timestamper
+from nilmdb.client import ClientError, ServerError
+from nilmdb.utils import datetime_tz
+
+from nose.tools import *
+from nose.tools import assert_raises
+import itertools
+import distutils.version
+import os
+import sys
+import threading
+import cStringIO
+import simplejson as json
+import unittest
+import warnings
+import resource
+import time
+
+from testutil.helpers import *
+
+testdb = "tests/client-testdb"
+testurl = "http://localhost:12380/"
+
+def setup_module():
+    global test_server, test_db
+    # Clear out DB
+    recursive_unlink(testdb)
+
+    # Start web app on a custom port
+    test_db = nilmdb.NilmDB(testdb, sync = False)
+    test_server = nilmdb.Server(test_db, host = "127.0.0.1",
+                                port = 12380, stoppable = False,
+                                fast_shutdown = True,
+                                force_traceback = False)
+    test_server.start(blocking = False)
+
+def teardown_module():
+    global test_server, test_db
+    # Close web app
+    test_server.stop()
+    test_db.close()
+
+class TestClient(object):
+
+    def test_client_01_basic(self):
+        # Test a fake host
+        client = nilmdb.Client(url = "http://localhost:1/")
+        with assert_raises(nilmdb.client.ServerError):
+            client.version()
+        client.close()
+
+        # Trigger same error with a PUT request
+        client = nilmdb.Client(url = "http://localhost:1/")
+        with assert_raises(nilmdb.client.ServerError):
+            client.version()
+        client.close()
+
+        # Then a fake URL on a real host
+        client = nilmdb.Client(url = "http://localhost:12380/fake/")
+        with assert_raises(nilmdb.client.ClientError):
+            client.version()
+        client.close()
+
+        # Now a real URL with no http:// prefix
+        client = nilmdb.Client(url = "localhost:12380")
+        version = client.version()
+        client.close()
+
+        # Now use the real URL
+        client = nilmdb.Client(url = testurl)
+        version = client.version()
+        eq_(distutils.version.LooseVersion(version),
+            distutils.version.LooseVersion(test_server.version))
+
+        # Bad URLs should give 404, not 500
+        with assert_raises(ClientError):
+            client.http.get("/stream/create")
+        client.close()
+
+    def test_client_02_createlist(self):
+        # Basic stream tests, like those in test_nilmdb:test_stream
+        client = nilmdb.Client(url = testurl)
+
+        # Database starts empty
+        eq_(client.stream_list(), [])
+
+        # Bad path
+        with assert_raises(ClientError):
+            client.stream_create("foo/bar/baz", "PrepData")
+        with assert_raises(ClientError):
+            client.stream_create("/foo", "PrepData")
+        # Bad layout type
+        with assert_raises(ClientError):
+            client.stream_create("/newton/prep", "NoSuchLayout")
+
+        # Create three streams
+        client.stream_create("/newton/prep", "PrepData")
+        client.stream_create("/newton/raw", "RawData")
+        client.stream_create("/newton/zzz/rawnotch", "RawNotchedData")
+
+        # Verify we got 3 streams
+        eq_(client.stream_list(), [ ["/newton/prep", "PrepData"],
+                                    ["/newton/raw", "RawData"],
+                                    ["/newton/zzz/rawnotch", "RawNotchedData"]
+                                    ])
+        # Match just one type or one path
+        eq_(client.stream_list(layout="RawData"),
+            [ ["/newton/raw", "RawData"] ])
+        eq_(client.stream_list(path="/newton/raw"),
+            [ ["/newton/raw", "RawData"] ])
+
+        # Try messing with resource limits to trigger errors and get
+        # more coverage.  Here, make it so we can only create files 1
+        # byte in size, which will trigger an IOError in the server when
+        # we create a table.
+        limit = resource.getrlimit(resource.RLIMIT_FSIZE)
+        resource.setrlimit(resource.RLIMIT_FSIZE, (1, limit[1]))
+        with assert_raises(ServerError) as e:
+            client.stream_create("/newton/hello", "RawData")
+        resource.setrlimit(resource.RLIMIT_FSIZE, limit)
+
+        client.close()
+
+    def test_client_03_metadata(self):
+        client = nilmdb.Client(url = testurl)
+
+        # Set / get metadata
+        eq_(client.stream_get_metadata("/newton/prep"), {})
+        eq_(client.stream_get_metadata("/newton/raw"), {})
+        meta1 = { "description": "The Data",
+                  "v_scale": "1.234" }
+        meta2 = { "description": "The Data" }
+        meta3 = { "v_scale": "1.234" }
+        client.stream_set_metadata("/newton/prep", meta1)
+        client.stream_update_metadata("/newton/prep", {})
+        client.stream_update_metadata("/newton/raw", meta2)
+        client.stream_update_metadata("/newton/raw", meta3)
+        eq_(client.stream_get_metadata("/newton/prep"), meta1)
+        eq_(client.stream_get_metadata("/newton/raw"), meta1)
+        eq_(client.stream_get_metadata("/newton/raw",
+                                       [ "description" ] ), meta2)
+        eq_(client.stream_get_metadata("/newton/raw",
+                                       [ "description", "v_scale" ] ), meta1)
+
+        # missing key
+        eq_(client.stream_get_metadata("/newton/raw", "descr"),
+            { "descr": None })
+        eq_(client.stream_get_metadata("/newton/raw", [ "descr" ]),
+            { "descr": None })
+
+        # test wrong types (list instead of dict)
+        with assert_raises(ClientError):
+            client.stream_set_metadata("/newton/prep", [1,2,3])
+        with assert_raises(ClientError):
+            client.stream_update_metadata("/newton/prep", [1,2,3])
+        client.close()
+
+    def test_client_04_insert(self):
+        client = nilmdb.Client(url = testurl)
+
+        datetime_tz.localtz_set("America/New_York")
+
+        testfile = "tests/data/prep-20120323T1000"
+        start = datetime_tz.datetime_tz.smartparse("20120323T1000")
+        start = start.totimestamp()
+        rate = 120
+
+        # First try a nonexistent path
+        data = timestamper.TimestamperRate(testfile, start, 120)
+        with assert_raises(ClientError) as e:
+            result = client.stream_insert("/newton/no-such-path", data)
+        in_("404 Not Found", str(e.exception))
+
+        # Now try reversed timestamps
+        data = timestamper.TimestamperRate(testfile, start, 120)
+        data = reversed(list(data))
+        with assert_raises(ClientError) as e:
+            result = client.stream_insert("/newton/prep", data)
+        in_("400 Bad Request", str(e.exception))
+        in_("timestamp is not monotonically increasing", str(e.exception))
+
+        # Now try empty data (no server request made)
+        empty = cStringIO.StringIO("")
+        data = timestamper.TimestamperRate(empty, start, 120)
+        result = client.stream_insert("/newton/prep", data)
+        eq_(result, None)
+
+        # It's OK to insert an empty interval
+        client.http.put("stream/insert", "", { "path": "/newton/prep",
+                                               "start": 1, "end": 2 })
+        eq_(list(client.stream_intervals("/newton/prep")), [[1, 2]])
+        client.stream_remove("/newton/prep")
+        eq_(list(client.stream_intervals("/newton/prep")), [])
+
+        # Timestamps can be negative too
+        client.http.put("stream/insert", "", { "path": "/newton/prep",
+                                               "start": -2, "end": -1 })
+        eq_(list(client.stream_intervals("/newton/prep")), [[-2, -1]])
+        client.stream_remove("/newton/prep")
+        eq_(list(client.stream_intervals("/newton/prep")), [])
+
+        # Intervals that end at zero shouldn't be any different
+        client.http.put("stream/insert", "", { "path": "/newton/prep",
+                                               "start": -1, "end": 0 })
+        eq_(list(client.stream_intervals("/newton/prep")), [[-1, 0]])
+        client.stream_remove("/newton/prep")
+        eq_(list(client.stream_intervals("/newton/prep")), [])
+
+        # Try forcing a server request with equal start and end
+        with assert_raises(ClientError) as e:
+            client.http.put("stream/insert", "", { "path": "/newton/prep",
+                                                   "start": 0, "end": 0 })
+        in_("400 Bad Request", str(e.exception))
+        in_("start must precede end", str(e.exception))
+
+        # Specify start/end (starts too late)
+        data = timestamper.TimestamperRate(testfile, start, 120)
+        with assert_raises(ClientError) as e:
+            result = client.stream_insert("/newton/prep", data,
+                                          start + 5, start + 120)
+        in_("400 Bad Request", str(e.exception))
+        in_("Data timestamp 1332511200.0 < start time 1332511205.0",
+            str(e.exception))
+
+        # Specify start/end (ends too early)
+        data = timestamper.TimestamperRate(testfile, start, 120)
+        with assert_raises(ClientError) as e:
+            result = client.stream_insert("/newton/prep", data,
+                                          start, start + 1)
+        in_("400 Bad Request", str(e.exception))
+        # Client chunks the input, so the exact timestamp here might change
+        # if the chunk positions change.
+        in_("Data timestamp 1332511271.016667 >= end time 1332511201.0",
+            str(e.exception))
+
+        # Now do the real load
+        data = timestamper.TimestamperRate(testfile, start, 120)
+        result = client.stream_insert("/newton/prep", data,
+                                      start, start + 119.999777)
+
+        # Verify the intervals.  Should be just one, even if the data
+        # was inserted in chunks, due to nilmdb interval concatenation.
+        intervals = list(client.stream_intervals("/newton/prep"))
+        eq_(intervals, [[start, start + 119.999777]])
+
+        # Try some overlapping data -- just insert it again
+        data = timestamper.TimestamperRate(testfile, start, 120)
+        with assert_raises(ClientError) as e:
+            result = client.stream_insert("/newton/prep", data)
+        in_("400 Bad Request", str(e.exception))
+        in_("verlap", str(e.exception))
+
+        client.close()
+
+    def test_client_05_extractremove(self):
+        # Misc tests for extract and remove.  Most of them are in test_cmdline.
+        client = nilmdb.Client(url = testurl)
+
+        for x in client.stream_extract("/newton/prep", 999123, 999124):
+            raise AssertionError("shouldn't be any data for this request")
+
+        with assert_raises(ClientError) as e:
+            client.stream_remove("/newton/prep", 123, 120)
+
+        # Test the exception we get if we nest requests
+        with assert_raises(Exception) as e:
+            for data in client.stream_extract("/newton/prep"):
+                x = client.stream_intervals("/newton/prep")
+        in_("nesting calls is not supported", str(e.exception))
+
+        # Test count
+        eq_(client.stream_count("/newton/prep"), 14400)
+
+        client.close()
+
+    def test_client_06_generators(self):
+        # A lot of the client functionality is already tested by test_cmdline,
+        # but this gets a bit more coverage that cmdline misses.
+        client = nilmdb.Client(url = testurl)
+
+        # Trigger a client error in generator
+        start = datetime_tz.datetime_tz.smartparse("20120323T2000")
+        end = datetime_tz.datetime_tz.smartparse("20120323T1000")
+        for function in [ client.stream_intervals, client.stream_extract ]:
+            with assert_raises(ClientError) as e:
+                function("/newton/prep",
+                         start.totimestamp(),
+                         end.totimestamp()).next()
+            in_("400 Bad Request", str(e.exception))
+            in_("start must precede end", str(e.exception))
+
+        # Trigger a curl error in generator
+        with assert_raises(ServerError) as e:
+            client.http.get_gen("http://nosuchurl/").next()
+
+        # Trigger a curl error in generator
+        with assert_raises(ServerError) as e:
+            client.http.get_gen("http://nosuchurl/").next()
+
+        # Check non-json version of string output
+        eq_(json.loads(client.http.get("/stream/list",retjson=False)),
+            client.http.get("/stream/list",retjson=True))
+
+        # Check non-json version of generator output
+        for (a, b) in itertools.izip(
+            client.http.get_gen("/stream/list",retjson=False),
+            client.http.get_gen("/stream/list",retjson=True)):
+            eq_(json.loads(a), b)
+
+        # Check PUT with generator out
+        with assert_raises(ClientError) as e:
+            client.http.put_gen("stream/insert", "",
+                                { "path": "/newton/prep",
+                                  "start": 0, "end": 0 }).next()
+        in_("400 Bad Request", str(e.exception))
+        in_("start must precede end", str(e.exception))
+
+        # Check 404 for missing streams
+        for function in [ client.stream_intervals, client.stream_extract ]:
+            with assert_raises(ClientError) as e:
+                function("/no/such/stream").next()
+            in_("404 Not Found", str(e.exception))
+            in_("No such stream", str(e.exception))
+
+        client.close()
+
+    def test_client_07_headers(self):
+        # Make sure that /stream/intervals and /stream/extract
+        # properly return streaming, chunked, text/plain response.
+        # Pokes around in client.http internals a bit to look at the
+        # response headers.
+
+        client = nilmdb.Client(url = testurl)
+        http = client.http
+
+        # Use a warning rather than returning a test failure, so that we can
+        # still disable chunked responses for debugging.
+
+        # Intervals
+        x = http.get("stream/intervals", { "path": "/newton/prep" },
+                            retjson=False)
+        lines_(x, 1)
+        if "Transfer-Encoding: chunked" not in http._headers:
+            warnings.warn("Non-chunked HTTP response for /stream/intervals")
+        if "Content-Type: text/plain;charset=utf-8" not in http._headers:
+            raise AssertionError("/stream/intervals is not text/plain:\n" +
+                                 http._headers)
+
+        # Extract
+        x = http.get("stream/extract",
+                            { "path": "/newton/prep",
+                              "start": "123",
+                              "end": "124" }, retjson=False)
+        if "Transfer-Encoding: chunked" not in http._headers:
+            warnings.warn("Non-chunked HTTP response for /stream/extract")
+        if "Content-Type: text/plain;charset=utf-8" not in http._headers:
+            raise AssertionError("/stream/extract is not text/plain:\n" +
+                                 http._headers)
+
+        # Make sure Access-Control-Allow-Origin gets set
+        if "Access-Control-Allow-Origin: " not in http._headers:
+            raise AssertionError("No Access-Control-Allow-Origin (CORS) "
+                                 "header in /stream/extract response:\n" +
+                                 http._headers)
+
+        client.close()
+
+    def test_client_08_unicode(self):
+        # Basic Unicode tests
+        client = nilmdb.Client(url = testurl)
+
+        # Delete streams that exist
+        for stream in client.stream_list():
+            client.stream_destroy(stream[0])
+
+        # Database is empty
+        eq_(client.stream_list(), [])
+
+        # Create Unicode stream, match it
+        raw = [ u"/düsseldorf/raw", u"uint16_6" ]
+        prep = [ u"/düsseldorf/prep", u"uint16_6" ]
+        client.stream_create(*raw)
+        eq_(client.stream_list(), [raw])
+        eq_(client.stream_list(layout=raw[1]), [raw])
+        eq_(client.stream_list(path=raw[0]), [raw])
+        client.stream_create(*prep)
+        eq_(client.stream_list(), [prep, raw])
+
+        # Set / get metadata with Unicode keys and values
+        eq_(client.stream_get_metadata(raw[0]), {})
+        eq_(client.stream_get_metadata(prep[0]), {})
+        meta1 = { u"alpha": u"α",
+                  u"β": u"beta" }
+        meta2 = { u"alpha": u"α" }
+        meta3 = { u"β": u"beta" }
+        client.stream_set_metadata(prep[0], meta1)
+        client.stream_update_metadata(prep[0], {})
+        client.stream_update_metadata(raw[0], meta2)
+        client.stream_update_metadata(raw[0], meta3)
+        eq_(client.stream_get_metadata(prep[0]), meta1)
+        eq_(client.stream_get_metadata(raw[0]), meta1)
+        eq_(client.stream_get_metadata(raw[0], [ "alpha" ]), meta2)
+        eq_(client.stream_get_metadata(raw[0], [ "alpha", "β" ]), meta1)
+
+        client.close()
+
+    def test_client_09_closing(self):
+        # Make sure we actually close sockets correctly.  New
+        # connections will block for a while if they're not, since the
+        # server will stop accepting new connections.
+        for test in [1, 2]:
+            start = time.time()
+            for i in range(50):
+                if time.time() - start > 15:
+                    raise AssertionError("Connections seem to be blocking... "
+                                         "probably not closing properly.")
+                if test == 1:
+                    # explicit close
+                    client = nilmdb.Client(url = testurl)
+                    with assert_raises(ClientError) as e:
+                        client.stream_remove("/newton/prep", 123, 120)
+                    client.close() # remove this to see the failure
+                elif test == 2:
+                    # use the context manager
+                    with nilmdb.Client(url = testurl) as c:
+                        with assert_raises(ClientError) as e:
+                            c.stream_remove("/newton/prep", 123, 120)
+
+    def test_client_10_context(self):
+        # Test using the client's stream insertion context manager to
+        # insert data.
+        client = nilmdb.Client(testurl)
+
+        client.stream_create("/context/test", "uint16_1")
+        with client.stream_insert_context("/context/test") as ctx:
+            # override _max_data to trigger frequent server updates
+            ctx._max_data = 15
+
+            with assert_raises(ValueError):
+                ctx.insert_line("100 1")
+
+            ctx.insert_line("100 1\n")
+            ctx.insert_iter([ "101 1\n",
+                              "102 1\n",
+                              "103 1\n" ])
+            ctx.insert_line("104 1\n")
+            ctx.insert_line("105 1\n")
+            ctx.finalize()
+
+            ctx.insert_line("106 1\n")
+            ctx.update_end(106.5)
+            ctx.finalize()
+            ctx.update_start(106.8)
+            ctx.insert_line("107 1\n")
+            ctx.insert_line("108 1\n")
+            ctx.insert_line("109 1\n")
+            ctx.insert_line("110 1\n")
+            ctx.insert_line("111 1\n")
+            ctx.update_end(113)
+            ctx.insert_line("112 1\n")
+            ctx.update_end(114)
+            ctx.insert_line("113 1\n")
+            ctx.update_end(115)
+            ctx.insert_line("114 1\n")
+            ctx.finalize()
+
+        with assert_raises(ClientError):
+            with client.stream_insert_context("/context/test", 100, 200) as ctx:
+                ctx.insert_line("115 1\n")
+
+        with assert_raises(ClientError):
+            with client.stream_insert_context("/context/test", 200, 300) as ctx:
+                ctx.insert_line("115 1\n")
+
+        with client.stream_insert_context("/context/test", 200, 300) as ctx:
+            # make sure our override wasn't permanent
+            ne_(ctx._max_data, 15)
+            ctx.insert_line("225 1\n")
+            ctx.finalize()
+
+        eq_(list(client.stream_intervals("/context/test")),
+            [ [ 100, 105.000001 ],
+              [ 106, 106.5 ],
+              [ 106.8, 115 ],
+              [ 200, 300 ] ])
+
+        client.stream_destroy("/context/test")
+        client.close()
+
+    def test_client_11_emptyintervals(self):
+        # Empty intervals are ok!  If recording detection events
+        # by inserting rows into the database, we want to be able to
+        # have an interval where no events occurred.  Test them here.
+        client = nilmdb.Client(testurl)
+        client.stream_create("/empty/test", "uint16_1")
+
+        def info():
+            result = []
+            for interval in list(client.stream_intervals("/empty/test")):
+                result.append((client.stream_count("/empty/test", *interval),
+                               interval))
+            return result
+
+        eq_(info(), [])
+
+        # Insert a region with just a few points
+        with client.stream_insert_context("/empty/test") as ctx:
+            ctx.update_start(100)
+            ctx.insert_line("140 1\n")
+            ctx.insert_line("150 1\n")
+            ctx.insert_line("160 1\n")
+            ctx.update_end(200)
+            ctx.finalize()
+
+        eq_(info(), [(3, [100, 200])])
+
+        # Delete chunk, which will leave one data point and two intervals
+        client.stream_remove("/empty/test", 145, 175)
+        eq_(info(), [(1, [100, 145]),
+                     (0, [175, 200])])
+
+        # Try also creating a completely empty interval from scratch,
+        # in a few different ways.
+        client.stream_insert_block("/empty/test", "", 300, 350)
+        client.stream_insert("/empty/test", [], 400, 450)
+        with client.stream_insert_context("/empty/test", 500, 550):
+            pass
+
+        # If enough timestamps aren't provided, empty streams won't be created.
+        client.stream_insert("/empty/test", [])
+        with client.stream_insert_context("/empty/test"):
+            pass
+        client.stream_insert("/empty/test", [], start = 600)
+        with client.stream_insert_context("/empty/test", start = 700):
+            pass
+        client.stream_insert("/empty/test", [], end = 850)
+        with client.stream_insert_context("/empty/test", end = 950):
+            pass
+
+        # Try various things that might cause problems
+        with client.stream_insert_context("/empty/test", 1000, 1050):
+            ctx.finalize() # inserts [1000, 1050]
+            ctx.finalize() # nothing
+            ctx.finalize() # nothing
+            ctx.insert_line("1100 1\n")
+            ctx.finalize() # inserts [1100, 1100.000001]
+            ctx.update_start(1199)
+            ctx.insert_line("1200 1\n")
+            ctx.update_end(1250)
+            ctx.finalize() # inserts [1199, 1250]
+            ctx.update_start(1299)
+            ctx.finalize() # nothing
+            ctx.update_end(1350)
+            ctx.finalize() # nothing
+            ctx.update_start(1400)
+            ctx.update_end(1450)
+            ctx.finalize()
+            # implicit last finalize inserts [1400, 1450]
+
+        # Check everything
+        eq_(info(), [(1, [100, 145]),
+                     (0, [175, 200]),
+                     (0, [300, 350]),
+                     (0, [400, 450]),
+                     (0, [500, 550]),
+                     (0, [1000, 1050]),
+                     (1, [1100, 1100.000001]),
+                     (1, [1199, 1250]),
+                     (0, [1400, 1450]),
+                     ])
+
+        # Clean up
+        client.stream_destroy("/empty/test")
+        client.close()

tests/test_cmdline.py

@@ -0,0 +1,846 @@
+# -*- coding: utf-8 -*-
+
+import nilmdb
+from nilmdb.utils.printf import *
+import nilmdb.cmdline
+from nilmdb.utils import datetime_tz
+
+import unittest
+from nose.tools import *
+from nose.tools import assert_raises
+import itertools
+import os
+import re
+import shutil
+import sys
+import threading
+import urllib2
+from urllib2 import urlopen, HTTPError
+import Queue
+import StringIO
+import shlex
+
+from testutil.helpers import *
+
+testdb = "tests/cmdline-testdb"
+
+def server_start(max_results = None, bulkdata_args = {}):
+    global test_server, test_db
+    # Start web app on a custom port
+    test_db = nilmdb.NilmDB(testdb, sync = False,
+                            max_results = max_results,
+                            bulkdata_args = bulkdata_args)
+    test_server = nilmdb.Server(test_db, host = "127.0.0.1",
+                                port = 12380, stoppable = False,
+                                fast_shutdown = True,
+                                force_traceback = False)
+    test_server.start(blocking = False)
+
+def server_stop():
+    global test_server, test_db
+    # Close web app
+    test_server.stop()
+    test_db.close()
+
+def setup_module():
+    global test_server, test_db
+    # Clear out DB
+    recursive_unlink(testdb)
+    server_start()
+
+def teardown_module():
+    server_stop()
+
+# Add an encoding property to StringIO so Python will convert Unicode
+# properly when writing or reading.
+class UTF8StringIO(StringIO.StringIO):
+    encoding = 'utf-8'
+
+class TestCmdline(object):
+
+    def run(self, arg_string, infile=None, outfile=None):
+        """Run a cmdline client with the specified argument string,
+        passing the given input.  Returns a tuple with the output and
+        exit code"""
+        # printf("TZ=UTC ./nilmtool.py %s\n", arg_string)
+        class stdio_wrapper:
+            def __init__(self, stdin, stdout, stderr):
+                self.io = (stdin, stdout, stderr)
+            def __enter__(self):
+                self.saved = ( sys.stdin, sys.stdout, sys.stderr )
+                ( sys.stdin, sys.stdout, sys.stderr ) = self.io
+            def __exit__(self, type, value, traceback):
+                ( sys.stdin, sys.stdout, sys.stderr ) = self.saved
+        # Empty input if none provided
+        if infile is None:
+            infile = UTF8StringIO("")
+        # Capture stderr
+        errfile = UTF8StringIO()
+        if outfile is None:
+            # If no output file, capture stdout with stderr
+            outfile = errfile
+        with stdio_wrapper(infile, outfile, errfile) as s:
+            try:
+                # shlex doesn't support Unicode very well.  Encode the
+                # string as UTF-8 explicitly before splitting.
+                args = shlex.split(arg_string.encode('utf-8'))
+                nilmdb.cmdline.Cmdline(args).run()
+                sys.exit(0)
+            except SystemExit as e:
+                exitcode = e.code
+        captured = outfile.getvalue()
+        self.captured = captured
+        self.exitcode = exitcode
+
+    def ok(self, arg_string, infile = None):
+        self.run(arg_string, infile)
+        if self.exitcode != 0:
+            self.dump()
+            eq_(self.exitcode, 0)
+
+    def fail(self, arg_string, infile = None,
+             exitcode = None, require_error = True):
+        self.run(arg_string, infile)
+        if exitcode is not None and self.exitcode != exitcode:
+            # Wrong exit code
+            self.dump()
+            eq_(self.exitcode, exitcode)
+        if self.exitcode == 0:
+            # Success, when we wanted failure
+            self.dump()
+            ne_(self.exitcode, 0)
+        # Make sure the output contains the word "error" at the
+        # beginning of a line, but only if an exitcode wasn't
+        # specified.
+        if require_error and not re.search("^error",
+                                           self.captured, re.MULTILINE):
+            raise AssertionError("command failed, but output doesn't "
+                                 "contain the string 'error'")
+
+    def contain(self, checkstring):
+        in_(checkstring, self.captured)
+
+    def match(self, checkstring):
+        eq_(checkstring, self.captured)
+
+    def matchfile(self, file):
+        # Captured data should match file contents exactly
+        with open(file) as f:
+            contents = f.read()
+            if contents != self.captured:
+                print contents[1:1000] + "\n"
+                print self.captured[1:1000] + "\n"
+                raise AssertionError("captured data doesn't match " + file)
+
+    def matchfilecount(self, file):
+        # Last line of captured data should match the number of
+        # non-commented lines in file
+        count = 0
+        with open(file) as f:
+            for line in f:
+                if line[0] != '#':
+                    count += 1
+        eq_(self.captured.splitlines()[-1], sprintf("%d", count))
+
+    def dump(self):
+        printf("-----dump start-----\n%s-----dump end-----\n", self.captured)
+
+    def test_01_basic(self):
+
+        # help
+        self.ok("--help")
+        self.contain("usage:")
+
+        # fail for no args
+        self.fail("")
+
+        # fail for no such option
+        self.fail("--nosuchoption")
+
+        # fail for bad command
+        self.fail("badcommand")
+
+        # try some URL constructions
+        self.fail("--url http://nosuchurl/ info")
+        self.contain("Couldn't resolve host 'nosuchurl'")
+
+        self.fail("--url nosuchurl info")
+        self.contain("Couldn't resolve host 'nosuchurl'")
+
+        self.fail("-u nosuchurl/foo info")
+        self.contain("Couldn't resolve host 'nosuchurl'")
+
+        self.fail("-u localhost:0 info")
+        self.contain("couldn't connect to host")
+
+        self.ok("-u localhost:12380 info")
+        self.ok("info")
+
+        # Duplicated arguments should fail, but this isn't implemented
+        # due to it being kind of a pain with argparse.
+        if 0:
+            self.fail("-u url1 -u url2 info")
+            self.contain("duplicated argument")
+
+            self.fail("list --detail --detail")
+            self.contain("duplicated argument")
+
+            self.fail("list --detail --path path1 --path path2")
+            self.contain("duplicated argument")
+
+            self.fail("extract --start 2000-01-01 --start 2001-01-02")
+            self.contain("duplicated argument")
+
+    def test_02_info(self):
+        self.ok("info")
+        self.contain("Server URL: http://localhost:12380/")
+        self.contain("Client version: " + nilmdb.__version__)
+        self.contain("Server version: " + test_server.version)
+        self.contain("Server database path")
+        self.contain("Server database size")
+        self.contain("Server database free space")
+
+    def test_03_createlist(self):
+        # Basic stream tests, like those in test_client.
+
+        # No streams
+        self.ok("list")
+        self.match("")
+
+        # Bad paths
+        self.fail("create foo/bar/baz PrepData")
+        self.contain("paths must start with /")
+
+        self.fail("create /foo PrepData")
+        self.contain("invalid path")
+
+        # Bad layout type
+        self.fail("create /newton/prep NoSuchLayout")
+        self.contain("no such layout")
+        self.fail("create /newton/prep float32_0")
+        self.contain("no such layout")
+        self.fail("create /newton/prep float33_1")
+        self.contain("no such layout")
+
+        # Create a few streams
+        self.ok("create /newton/zzz/rawnotch RawNotchedData")
+        self.ok("create /newton/prep PrepData")
+        self.ok("create /newton/raw RawData")
+
+        # Should not be able to create a stream with another stream as
+        # its parent
+        self.fail("create /newton/prep/blah PrepData")
+        self.contain("path is subdir of existing node")
+
+        # Should not be able to create a stream at a location that
+        # has other nodes as children
+        self.fail("create /newton/zzz PrepData")
+        self.contain("subdirs of this path already exist")
+
+        # Verify we got those 3 streams and they're returned in
+        # alphabetical order.
+        self.ok("list")
+        self.match("/newton/prep PrepData\n"
+                   "/newton/raw RawData\n"
+                   "/newton/zzz/rawnotch RawNotchedData\n")
+
+        # Match just one type or one path.  Also check
+        # that --path is optional
+        self.ok("list --path /newton/raw")
+        self.match("/newton/raw RawData\n")
+
+        self.ok("list /newton/raw")
+        self.match("/newton/raw RawData\n")
+
+        self.fail("list -p /newton/raw /newton/raw")
+        self.contain("too many paths")
+
+        self.ok("list --layout RawData")
+        self.match("/newton/raw RawData\n")
+
+        # Wildcard matches
+        self.ok("list --layout Raw*")
+        self.match("/newton/raw RawData\n"
+                   "/newton/zzz/rawnotch RawNotchedData\n")
+
+        self.ok("list --path *zzz* --layout Raw*")
+        self.match("/newton/zzz/rawnotch RawNotchedData\n")
+
+        self.ok("list *zzz* --layout Raw*")
+        self.match("/newton/zzz/rawnotch RawNotchedData\n")
+
+        self.ok("list --path *zzz* --layout Prep*")
+        self.match("")
+
+        # reversed range
+        self.fail("list /newton/prep --start 2020-01-01 --end 2000-01-01")
+        self.contain("start must precede end")
+
+    def test_04_metadata(self):
+        # Set / get metadata
+        self.fail("metadata")
+        self.fail("metadata --get")
+
+        self.ok("metadata /newton/prep")
+        self.match("")
+
+        self.ok("metadata /newton/raw --get")
+        self.match("")
+
+        self.ok("metadata /newton/prep --set "
+                "'description=The Data' "
+                "v_scale=1.234")
+        self.ok("metadata /newton/raw --update "
+                "'description=The Data'")
+        self.ok("metadata /newton/raw --update "
+                "v_scale=1.234")
+
+        # various parsing tests
+        self.ok("metadata /newton/raw --update foo=")
+        self.fail("metadata /newton/raw --update =bar")
+        self.fail("metadata /newton/raw --update foo==bar")
+        self.fail("metadata /newton/raw --update foo;bar")
+
+        # errors
+        self.fail("metadata /newton/nosuchstream foo=bar")
+        self.contain("unrecognized arguments")
+        self.fail("metadata /newton/nosuchstream")
+        self.contain("No stream at path")
+        self.fail("metadata /newton/nosuchstream --set foo=bar")
+        self.contain("No stream at path")
+
+        self.ok("metadata /newton/prep")
+        self.match("description=The Data\nv_scale=1.234\n")
+
+        self.ok("metadata /newton/prep --get")
+        self.match("description=The Data\nv_scale=1.234\n")
+
+        self.ok("metadata /newton/prep --get descr")
+        self.match("descr=\n")
+
+        self.ok("metadata /newton/prep --get description")
+        self.match("description=The Data\n")
+
+        self.ok("metadata /newton/prep --get description v_scale")
+        self.match("description=The Data\nv_scale=1.234\n")
+
+        self.ok("metadata /newton/prep --set "
+                "'description=The Data'")
+
+        self.ok("metadata /newton/prep --get")
+        self.match("description=The Data\n")
+
+        self.fail("metadata /newton/nosuchpath")
+        self.contain("No stream at path /newton/nosuchpath")
+
+    def test_05_parsetime(self):
+        os.environ['TZ'] = "America/New_York"
+        cmd = nilmdb.cmdline.Cmdline(None)
+        test = datetime_tz.datetime_tz.now()
+        eq_(cmd.parse_time(str(test)), test)
+        test = datetime_tz.datetime_tz.smartparse("20120405 1400-0400")
+        eq_(cmd.parse_time("hi there 20120405 1400-0400 testing! 123"), test)
+        eq_(cmd.parse_time("20120405 1800 UTC"), test)
+        eq_(cmd.parse_time("20120405 1400-0400 UTC"), test)
+        for badtime in [ "20120405 1400-9999", "hello", "-", "", "4:00" ]:
+            with assert_raises(ValueError):
+                x = cmd.parse_time(badtime)
+        x = cmd.parse_time("now")
+        eq_(cmd.parse_time("snapshot-20120405-140000.raw.gz"), test)
+        eq_(cmd.parse_time("prep-20120405T1400"), test)
+
+    def test_06_insert(self):
+        self.ok("insert --help")
+
+        self.fail("insert /foo/bar baz qwer")
+        self.contain("error getting stream info")
+
+        self.fail("insert /newton/prep baz qwer")
+        self.match("error opening input file baz\n")
+
+        self.fail("insert /newton/prep")
+        self.contain("error extracting time")
+
+        self.fail("insert --start 19801205 /newton/prep 1 2 3 4")
+        self.contain("--start can only be used with one input file")
+
+        self.fail("insert /newton/prep "
+                  "tests/data/prep-20120323T1000")
+
+        # insert pre-timestamped data, from stdin
+        os.environ['TZ'] = "UTC"
+        with open("tests/data/prep-20120323T1004-timestamped") as input:
+            self.ok("insert --none /newton/prep", input)
+
+        # insert pre-timestamped data, with bad times (non-monotonic)
+        os.environ['TZ'] = "UTC"
+        with open("tests/data/prep-20120323T1004-badtimes") as input:
+            self.fail("insert --none /newton/prep", input)
+            self.contain("error parsing input data")
+            self.contain("line 7:")
+            self.contain("timestamp is not monotonically increasing")
+
+        # insert data with normal timestamper from filename
+        os.environ['TZ'] = "UTC"
+        self.ok("insert --rate 120 /newton/prep "
+                "tests/data/prep-20120323T1000 "
+                "tests/data/prep-20120323T1002")
+
+        # overlap
+        os.environ['TZ'] = "UTC"
+        self.fail("insert --rate 120 /newton/prep "
+                  "tests/data/prep-20120323T1004")
+        self.contain("overlap")
+
+        # Just to help test more situations -- stop and restart
+        # the server now.  This tests nilmdb's interval caching,
+        # at the very least.
+        server_stop()
+        server_start()
+
+        # still an overlap if we specify a different start
+        os.environ['TZ'] = "America/New_York"
+        self.fail("insert --rate 120 --start '03/23/2012 06:05:00' /newton/prep"
+                  " tests/data/prep-20120323T1004")
+        self.contain("overlap")
+
+        # wrong format
+        os.environ['TZ'] = "UTC"
+        self.fail("insert --rate 120 /newton/raw "
+                  "tests/data/prep-20120323T1004")
+        self.contain("error parsing input data")
+
+        # empty data does nothing
+        self.ok("insert --rate 120 --start '03/23/2012 06:05:00' /newton/prep "
+                "/dev/null")
+
+        # bad start time
+        self.fail("insert --rate 120 --start 'whatever' /newton/prep /dev/null")
+
+    def test_07_detail(self):
+        # Just count the number of lines, it's probably fine
+        self.ok("list --detail")
+        lines_(self.captured, 8)
+
+        self.ok("list --detail --path *prep")
+        lines_(self.captured, 4)
+
+        self.ok("list --detail --path *prep --start='23 Mar 2012 10:02'")
+        lines_(self.captured, 3)
+
+        self.ok("list --detail --path *prep --start='23 Mar 2012 10:05'")
+        lines_(self.captured, 2)
+
+        self.ok("list --detail --path *prep --start='23 Mar 2012 10:05:15'")
+        lines_(self.captured, 2)
+        self.contain("10:05:15.000")
+
+        self.ok("list --detail --path *prep --start='23 Mar 2012 10:05:15.50'")
+        lines_(self.captured, 2)
+        self.contain("10:05:15.500")
+
+        self.ok("list --detail --path *prep --start='23 Mar 2012 19:05:15.50'")
+        lines_(self.captured, 2)
+        self.contain("no intervals")
+
+        self.ok("list --detail --path *prep --start='23 Mar 2012 10:05:15.50'"
+                + " --end='23 Mar 2012 10:05:15.51'")
+        lines_(self.captured, 2)
+        self.contain("10:05:15.500")
+
+        self.ok("list --detail")
+        lines_(self.captured, 8)
+
+        # Verify the "raw timestamp" output
+        self.ok("list --detail --path *prep --timestamp-raw "
+                "--start='23 Mar 2012 10:05:15.50'")
+        lines_(self.captured, 2)
+        self.contain("[ 1332497115.5 -> 1332497159.991668 ]")
+
+        self.ok("list --detail --path *prep -T "
+                "--start='23 Mar 2012 10:05:15.612'")
+        lines_(self.captured, 2)
+        self.contain("[ 1332497115.612 -> 1332497159.991668 ]")
+
+    def test_08_extract(self):
+        # nonexistent stream
+        self.fail("extract /no/such/foo --start 2000-01-01 --end 2020-01-01")
+        self.contain("error getting stream info")
+
+        # reversed range
+        self.fail("extract -a /newton/prep --start 2020-01-01 --end 2000-01-01")
+        self.contain("start is after end")
+
+        # empty ranges return error 2
+        self.fail("extract -a /newton/prep " +
+                  "--start '23 Mar 2012 20:00:30' " +
+                  "--end '23 Mar 2012 20:00:31'",
+                  exitcode = 2, require_error = False)
+        self.contain("no data")
+        self.fail("extract -a /newton/prep " +
+                  "--start '23 Mar 2012 20:00:30.000001' " +
+                  "--end '23 Mar 2012 20:00:30.000002'",
+                  exitcode = 2, require_error = False)
+        self.contain("no data")
+        self.fail("extract -a /newton/prep " +
+                  "--start '23 Mar 2022 10:00:30' " +
+                  "--end '23 Mar 2022 10:00:31'",
+                  exitcode = 2, require_error = False)
+        self.contain("no data")
+
+        # but are ok if we're just counting results
+        self.ok("extract --count /newton/prep " +
+                "--start '23 Mar 2012 20:00:30' " +
+                "--end '23 Mar 2012 20:00:31'")
+        self.match("0\n")
+        self.ok("extract -c /newton/prep " +
+                "--start '23 Mar 2012 20:00:30.000001' " +
+                "--end '23 Mar 2012 20:00:30.000002'")
+        self.match("0\n")
+
+        # Check various dumps against stored copies of how they should appear
+        def test(file, start, end, extra=""):
+            self.ok("extract " + extra + " /newton/prep " +
+                    "--start '23 Mar 2012 " + start + "' " +
+                    "--end '23 Mar 2012 " + end + "'")
+            self.matchfile("tests/data/extract-" + str(file))
+            self.ok("extract --count " + extra + " /newton/prep " +
+                    "--start '23 Mar 2012 " + start + "' " +
+                    "--end '23 Mar 2012 " + end + "'")
+            self.matchfilecount("tests/data/extract-" + str(file))
+        test(1, "10:00:30", "10:00:31", extra="-a")
+        test(1, "10:00:30.000000", "10:00:31", extra="-a")
+        test(2, "10:00:30.000001", "10:00:31")
+        test(2, "10:00:30.008333", "10:00:31")
+        test(3, "10:00:30.008333", "10:00:30.008334")
+        test(3, "10:00:30.008333", "10:00:30.016667")
+        test(4, "10:00:30.008333", "10:00:30.025")
+        test(5, "10:00:30", "10:00:31", extra="--annotate --bare")
+        test(6, "10:00:30", "10:00:31", extra="-b")
+        test(7, "10:00:30", "10:00:30.999", extra="-a -T")
+        test(7, "10:00:30", "10:00:30.999", extra="-a --timestamp-raw")
+
+        # all data put in by tests
+        self.ok("extract -a /newton/prep --start 2000-01-01 --end 2020-01-01")
+        lines_(self.captured, 43204)
+        self.ok("extract -c /newton/prep --start 2000-01-01 --end 2020-01-01")
+        self.match("43200\n")
+
+    def test_09_truncated(self):
+        # Test truncated responses by overriding the nilmdb max_results
+        server_stop()
+        server_start(max_results = 2)
+        self.ok("list --detail")
+        lines_(self.captured, 8)
+        server_stop()
+        server_start()
+
+    def test_10_remove(self):
+        # Removing data
+
+        # Try nonexistent stream
+        self.fail("remove /no/such/foo --start 2000-01-01 --end 2020-01-01")
+        self.contain("No stream at path")
+
+        # empty or backward ranges return errors
+        self.fail("remove /newton/prep --start 2020-01-01 --end 2000-01-01")
+        self.contain("start must precede end")
+
+        self.fail("remove /newton/prep " +
+                  "--start '23 Mar 2012 10:00:30' " +
+                  "--end '23 Mar 2012 10:00:30'")
+        self.contain("start must precede end")
+        self.fail("remove /newton/prep " +
+                  "--start '23 Mar 2012 10:00:30.000001' " +
+                  "--end '23 Mar 2012 10:00:30.000001'")
+        self.contain("start must precede end")
+        self.fail("remove /newton/prep " +
+                  "--start '23 Mar 2022 10:00:30' " +
+                  "--end '23 Mar 2022 10:00:30'")
+        self.contain("start must precede end")
+
+        # Verbose
+        self.ok("remove -c /newton/prep " +
+                "--start '23 Mar 2022 20:00:30' " +
+                "--end '23 Mar 2022 20:00:31'")
+        self.match("0\n")
+        self.ok("remove --count /newton/prep " +
+                "--start '23 Mar 2022 20:00:30' " +
+                "--end '23 Mar 2022 20:00:31'")
+        self.match("0\n")
+
+        # Make sure we have the data we expect
+        self.ok("list --detail /newton/prep")
+        self.match("/newton/prep PrepData\n" +
+                   "  [ Fri, 23 Mar 2012 10:00:00.000000 +0000"
+                   " -> Fri, 23 Mar 2012 10:01:59.991668 +0000 ]\n"
+                   "  [ Fri, 23 Mar 2012 10:02:00.000000 +0000"
+                   " -> Fri, 23 Mar 2012 10:03:59.991668 +0000 ]\n"
+                   "  [ Fri, 23 Mar 2012 10:04:00.000000 +0000"
+                   " -> Fri, 23 Mar 2012 10:05:59.991668 +0000 ]\n")
+
+        # Remove various chunks of prep data and make sure
+        # they're gone.
+        self.ok("remove -c /newton/prep " +
+                "--start '23 Mar 2012 10:00:30' " +
+                "--end '23 Mar 2012 10:00:40'")
+        self.match("1200\n")
+
+        self.ok("remove -c /newton/prep " +
+                "--start '23 Mar 2012 10:00:10' " +
+                "--end '23 Mar 2012 10:00:20'")
+        self.match("1200\n")
+
+        self.ok("remove -c /newton/prep " +
+                "--start '23 Mar 2012 10:00:05' " +
+                "--end '23 Mar 2012 10:00:25'")
+        self.match("1200\n")
+
+        self.ok("remove -c /newton/prep " +
+                "--start '23 Mar 2012 10:03:50' " +
+                "--end '23 Mar 2012 10:06:50'")
+        self.match("15600\n")
+
+        self.ok("extract -c /newton/prep --start 2000-01-01 --end 2020-01-01")
+        self.match("24000\n")
+
+        # See the missing chunks in list output
+        self.ok("list --detail /newton/prep")
+        self.match("/newton/prep PrepData\n" +
+                   "  [ Fri, 23 Mar 2012 10:00:00.000000 +0000"
+                   " -> Fri, 23 Mar 2012 10:00:05.000000 +0000 ]\n"
+                   "  [ Fri, 23 Mar 2012 10:00:25.000000 +0000"
+                   " -> Fri, 23 Mar 2012 10:00:30.000000 +0000 ]\n"
+                   "  [ Fri, 23 Mar 2012 10:00:40.000000 +0000"
+                   " -> Fri, 23 Mar 2012 10:01:59.991668 +0000 ]\n"
+                   "  [ Fri, 23 Mar 2012 10:02:00.000000 +0000"
+                   " -> Fri, 23 Mar 2012 10:03:50.000000 +0000 ]\n")
+
+        # Remove all data, verify it's missing
+        self.ok("remove /newton/prep --start 2000-01-01 --end 2020-01-01")
+        self.match("")  # no count requested this time
+        self.ok("list --detail /newton/prep")
+        self.match("/newton/prep PrepData\n" +
+                   "  (no intervals)\n")
+
+        # Reinsert some data, to verify that no overlaps with deleted
+        # data are reported
+        os.environ['TZ'] = "UTC"
+        self.ok("insert --rate 120 /newton/prep "
+                "tests/data/prep-20120323T1000 "
+                "tests/data/prep-20120323T1002")
+
+    def test_11_destroy(self):
+        # Delete records
+        self.ok("destroy --help")
+
+        self.fail("destroy")
+        self.contain("too few arguments")
+
+        self.fail("destroy /no/such/stream")
+        self.contain("No stream at path")
+
+        self.fail("destroy asdfasdf")
+        self.contain("No stream at path")
+
+        # From previous tests, we have:
+        self.ok("list")
+        self.match("/newton/prep PrepData\n"
+                   "/newton/raw RawData\n"
+                   "/newton/zzz/rawnotch RawNotchedData\n")
+
+        # Notice how they're not empty
+        self.ok("list --detail")
+        lines_(self.captured, 7)
+
+        # Delete some
+        self.ok("destroy /newton/prep")
+        self.ok("list")
+        self.match("/newton/raw RawData\n"
+                   "/newton/zzz/rawnotch RawNotchedData\n")
+
+        self.ok("destroy /newton/zzz/rawnotch")
+        self.ok("list")
+        self.match("/newton/raw RawData\n")
+
+        self.ok("destroy /newton/raw")
+        self.ok("create /newton/raw RawData")
+        self.ok("destroy /newton/raw")
+        self.ok("list")
+        self.match("")
+
+        # Re-create a previously deleted location, and some new ones
+        rebuild = [ "/newton/prep", "/newton/zzz",
+                    "/newton/raw", "/newton/asdf/qwer" ]
+        for path in rebuild:
+            # Create the path
+            self.ok("create " + path + " PrepData")
+            self.ok("list")
+            self.contain(path)
+            # Make sure it was created empty
+            self.ok("list --detail --path " + path)
+            self.contain("(no intervals)")
+
+    def test_12_unicode(self):
+        # Unicode paths.
+        self.ok("destroy /newton/asdf/qwer")
+        self.ok("destroy /newton/prep")
+        self.ok("destroy /newton/raw")
+        self.ok("destroy /newton/zzz")
+
+        self.ok(u"create /düsseldorf/raw uint16_6")
+        self.ok("list --detail")
+        self.contain(u"/düsseldorf/raw uint16_6")
+        self.contain("(no intervals)")
+
+        # Unicode metadata
+        self.ok(u"metadata /düsseldorf/raw --set α=beta 'γ=δ'")
+        self.ok(u"metadata /düsseldorf/raw --update 'α=β ε τ α'")
+        self.ok(u"metadata /düsseldorf/raw")
+        self.match(u"α=β ε τ α\nγ=δ\n")
+
+        self.ok(u"destroy /düsseldorf/raw")
+
+    def test_13_files(self):
+        # Test BulkData's ability to split into multiple files,
+        # by forcing the file size to be really small.
+        server_stop()
+        server_start(bulkdata_args = { "file_size" : 920, # 23 rows per file
+                                       "files_per_dir" : 3 })
+
+        # Fill data
+        self.ok("create /newton/prep float32_8")
+        os.environ['TZ'] = "UTC"
+        with open("tests/data/prep-20120323T1004-timestamped") as input:
+            self.ok("insert --none /newton/prep", input)
+
+        # Extract it
+        self.ok("extract /newton/prep --start '2000-01-01' " +
+                "--end '2012-03-23 10:04:01'")
+        lines_(self.captured, 120)
+        self.ok("extract /newton/prep --start '2000-01-01' " +
+                "--end '2022-03-23 10:04:01'")
+        lines_(self.captured, 14400)
+
+        # Make sure there were lots of files generated in the database
+        # dir
+        nfiles = 0
+        for (dirpath, dirnames, filenames) in os.walk(testdb):
+            nfiles += len(filenames)
+        assert(nfiles > 500)
+
+        # Make sure we can restart the server with a different file
+        # size and have it still work
+        server_stop()
+        server_start()
+        self.ok("extract /newton/prep --start '2000-01-01' " +
+                "--end '2022-03-23 10:04:01'")
+        lines_(self.captured, 14400)
+
+        # Now recreate the data one more time and make sure there are
+        # fewer files.
+        self.ok("destroy /newton/prep")
+        self.fail("destroy /newton/prep") # already destroyed
+        self.ok("create /newton/prep float32_8")
+        os.environ['TZ'] = "UTC"
+        with open("tests/data/prep-20120323T1004-timestamped") as input:
+            self.ok("insert --none /newton/prep", input)
+        nfiles = 0
+        for (dirpath, dirnames, filenames) in os.walk(testdb):
+            nfiles += len(filenames)
+        lt_(nfiles, 50)
+        self.ok("destroy /newton/prep") # destroy again
+
+    def test_14_remove_files(self):
+        # Test BulkData's ability to remove when data is split into
+        # multiple files.  Should be a fairly comprehensive test of
+        # remove functionality.
+        server_stop()
+        server_start(bulkdata_args = { "file_size" : 920, # 23 rows per file
+                                       "files_per_dir" : 3 })
+
+        # Insert data.  Just for fun, insert out of order
+        self.ok("create /newton/prep PrepData")
+        os.environ['TZ'] = "UTC"
+        self.ok("insert --rate 120 /newton/prep "
+                "tests/data/prep-20120323T1002 "
+                "tests/data/prep-20120323T1000")
+
+        # Should take up about 2.8 MB here (including directory entries)
+        du_before = nilmdb.utils.diskusage.du(testdb)
+
+        # Make sure we have the data we expect
+        self.ok("list --detail")
+        self.match("/newton/prep PrepData\n" +
+                   "  [ Fri, 23 Mar 2012 10:00:00.000000 +0000"
+                   " -> Fri, 23 Mar 2012 10:01:59.991668 +0000 ]\n"
+                   "  [ Fri, 23 Mar 2012 10:02:00.000000 +0000"
+                   " -> Fri, 23 Mar 2012 10:03:59.991668 +0000 ]\n")
+
+        # Remove various chunks of prep data and make sure
+        # they're gone.
+        self.ok("extract -c /newton/prep --start 2000-01-01 --end 2020-01-01")
+        self.match("28800\n")
+
+        self.ok("remove -c /newton/prep " +
+                "--start '23 Mar 2012 10:00:30' " +
+                "--end '23 Mar 2012 10:03:30'")
+        self.match("21600\n")
+
+        self.ok("remove -c /newton/prep " +
+                "--start '23 Mar 2012 10:00:10' " +
+                "--end '23 Mar 2012 10:00:20'")
+        self.match("1200\n")
+
+        self.ok("remove -c /newton/prep " +
+                "--start '23 Mar 2012 10:00:05' " +
+                "--end '23 Mar 2012 10:00:25'")
+        self.match("1200\n")
+
+        self.ok("remove -c /newton/prep " +
+                "--start '23 Mar 2012 10:03:50' " +
+                "--end '23 Mar 2012 10:06:50'")
+        self.match("1200\n")
+
+        self.ok("extract -c /newton/prep --start 2000-01-01 --end 2020-01-01")
+        self.match("3600\n")
+
+        # See the missing chunks in list output
+        self.ok("list --detail")
+        self.match("/newton/prep PrepData\n" +
+                   "  [ Fri, 23 Mar 2012 10:00:00.000000 +0000"
+                   " -> Fri, 23 Mar 2012 10:00:05.000000 +0000 ]\n"
+                   "  [ Fri, 23 Mar 2012 10:00:25.000000 +0000"
+                   " -> Fri, 23 Mar 2012 10:00:30.000000 +0000 ]\n"
+                   "  [ Fri, 23 Mar 2012 10:03:30.000000 +0000"
+                   " -> Fri, 23 Mar 2012 10:03:50.000000 +0000 ]\n")
+
+        # We have 1/8 of the data that we had before, so the file size
+        # should have dropped below 1/4 of what it used to be
+        du_after = nilmdb.utils.diskusage.du(testdb)
+        lt_(du_after, (du_before / 4))
+
+        # Remove anything that came from the 10:02 data file
+        self.ok("remove /newton/prep " +
+                "--start '23 Mar 2012 10:02:00' --end '2020-01-01'")
+
+        # Re-insert 19 lines from that file, then remove them again.
+        # With the specific file_size above, this will cause the last
+        # file in the bulk data storage to be exactly file_size large,
+        # so removing the data should also remove that last file.
+        self.ok("insert --rate 120 /newton/prep " +
+                "tests/data/prep-20120323T1002-first19lines")
+        self.ok("remove /newton/prep " +
+                "--start '23 Mar 2012 10:02:00' --end '2020-01-01'")
+
+        # Shut down and restart server, to force nrows to get refreshed.
+        server_stop()
+        server_start()
+
+        # Re-add the full 10:02 data file.  This tests adding new data once
+        # we removed data near the end.
+        self.ok("insert --rate 120 /newton/prep tests/data/prep-20120323T1002")
+
+        # See if we can extract it all
+        self.ok("extract /newton/prep --start 2000-01-01 --end 2020-01-01")
+        lines_(self.captured, 15600)

tests/test_interval.py

@@ -0,0 +1,373 @@
+# -*- coding: utf-8 -*-
+
+import nilmdb
+from nilmdb.utils.printf import *
+from nilmdb.utils import datetime_tz
+
+from nose.tools import *
+from nose.tools import assert_raises
+import itertools
+
+from nilmdb.server.interval import (Interval, DBInterval,
+                                    IntervalSet, IntervalError)
+
+from testutil.helpers import *
+import unittest
+
+# set to False to skip live renders
+do_live_renders = False
+def render(iset, description = "", live = True):
+    import testutil.renderdot as renderdot
+    r = renderdot.RBTreeRenderer(iset.tree)
+    return r.render(description, live and do_live_renders)
+
+def makeset(string):
+    """Build an IntervalSet from a string, for testing purposes
+
+    Each character is 1 second
+    [ = interval start
+    | = interval end + next start
+    ] = interval end
+    . = zero-width interval (identical start and end)
+    anything else is ignored
+    """
+    iset = IntervalSet()
+    for i, c in enumerate(string):
+        day = i + 10000
+        if (c == "["):
+            start = day
+        elif (c == "|"):
+            iset += Interval(start, day)
+            start = day
+        elif (c == ")"):
+            iset += Interval(start, day)
+            del start
+        elif (c == "."):
+            iset += Interval(day, day)
+    return iset
+
+class TestInterval:
+    def test_interval(self):
+        # Test Interval class
+        os.environ['TZ'] = "America/New_York"
+        datetime_tz._localtz = None
+        (d1, d2, d3) = [ datetime_tz.datetime_tz.smartparse(x).totimestamp()
+                         for x in [ "03/24/2012", "03/25/2012", "03/26/2012" ] ]
+
+        # basic construction
+        i = Interval(d1, d2)
+        i = Interval(d1, d3)
+        eq_(i.start, d1)
+        eq_(i.end, d3)
+
+        # assignment is allowed, but not verified
+        i.start = d2
+        #with assert_raises(IntervalError):
+        #    i.end = d1
+        i.start = d1
+        i.end = d2
+
+        # end before start
+        with assert_raises(IntervalError):
+            i = Interval(d3, d1)
+
+        # compare
+        assert(Interval(d1, d2) == Interval(d1, d2))
+        assert(Interval(d1, d2) < Interval(d1, d3))
+        assert(Interval(d1, d3) > Interval(d1, d2))
+        assert(Interval(d1, d2) < Interval(d2, d3))
+        assert(Interval(d1, d3) < Interval(d2, d3))
+        assert(Interval(d2, d2+0.01) > Interval(d1, d3))
+        assert(Interval(d3, d3+0.01) == Interval(d3, d3+0.01))
+        #with assert_raises(TypeError): # was AttributeError, that's wrong
+        #    x = (i == 123)
+
+        # subset
+        eq_(Interval(d1, d3).subset(d1, d2), Interval(d1, d2))
+        with assert_raises(IntervalError):
+            x = Interval(d2, d3).subset(d1, d2)
+
+        # big integers and floats
+        x = Interval(5000111222, 6000111222)
+        eq_(str(x), "[5000111222.0 -> 6000111222.0)")
+        x = Interval(123.45, 234.56)
+        eq_(str(x), "[123.45 -> 234.56)")
+
+        # misc
+        i = Interval(d1, d2)
+        eq_(repr(i), repr(eval(repr(i))))
+        eq_(str(i), "[1332561600.0 -> 1332648000.0)")
+
+    def test_interval_intersect(self):
+        # Test Interval intersections
+        dates = [ 100, 200, 300, 400 ]
+        perm = list(itertools.permutations(dates, 2))
+        prod = list(itertools.product(perm, perm))
+        should_intersect = {
+            False: [4, 5, 8, 20, 48, 56, 60, 96, 97, 100],
+            True: [0, 1, 2, 12, 13, 14, 16, 17, 24, 25, 26, 28, 29,
+                   32, 49, 50, 52, 53, 61, 62, 64, 65, 68, 98, 101, 104]
+            }
+        for i,((a,b),(c,d)) in enumerate(prod):
+            try:
+                i1 = Interval(a, b)
+                i2 = Interval(c, d)
+                eq_(i1.intersects(i2), i2.intersects(i1))
+                in_(i, should_intersect[i1.intersects(i2)])
+            except IntervalError:
+                assert(i not in should_intersect[True] and
+                       i not in should_intersect[False])
+        with assert_raises(TypeError):
+            x = i1.intersects(1234)
+
+    def test_intervalset_construct(self):
+        # Test IntervalSet construction
+        dates = [ 100, 200, 300, 400 ]
+
+        a = Interval(dates[0], dates[1])
+        b = Interval(dates[1], dates[2])
+        c = Interval(dates[0], dates[2])
+        d = Interval(dates[2], dates[3])
+
+        iseta = IntervalSet(a)
+        isetb = IntervalSet([a, b])
+        isetc = IntervalSet([a])
+        ne_(iseta, isetb)
+        eq_(iseta, isetc)
+        with assert_raises(TypeError):
+            x = iseta != 3
+        ne_(IntervalSet(a), IntervalSet(b))
+
+        # Note that assignment makes a new reference (not a copy)
+        isetd = IntervalSet(isetb)
+        isete = isetd
+        eq_(isetd, isetb)
+        eq_(isetd, isete)
+        isetd -= a
+        ne_(isetd, isetb)
+        eq_(isetd, isete)
+
+        # test iterator
+        for interval in iseta:
+            pass
+
+        # overlap
+        with assert_raises(IntervalError):
+            x = IntervalSet([a, b, c])
+
+        # bad types
+        with assert_raises(Exception):
+            x = IntervalSet([1, 2])
+
+        iset = IntervalSet(isetb)   # test iterator
+        eq_(iset, isetb)
+        eq_(len(iset), 2)
+        eq_(len(IntervalSet()), 0)
+
+        # Test adding
+        iset = IntervalSet(a)
+        iset += IntervalSet(b)
+        eq_(iset, IntervalSet([a, b]))
+
+        iset = IntervalSet(a)
+        iset += b
+        eq_(iset, IntervalSet([a, b]))
+
+        iset = IntervalSet(a)
+        iset.iadd_nocheck(b)
+        eq_(iset, IntervalSet([a, b]))
+
+        iset = IntervalSet(a) + IntervalSet(b)
+        eq_(iset, IntervalSet([a, b]))
+
+        iset = IntervalSet(b) + a
+        eq_(iset, IntervalSet([a, b]))
+
+        # A set consisting of [0-1],[1-2] should match a set consisting of [0-2]
+        eq_(IntervalSet([a,b]), IntervalSet([c]))
+        # Etc
+        ne_(IntervalSet([a,d]), IntervalSet([c]))
+        ne_(IntervalSet([c]), IntervalSet([a,d]))
+        ne_(IntervalSet([c,d]), IntervalSet([b,d]))
+
+        # misc
+        eq_(repr(iset), repr(eval(repr(iset))))
+        eq_(str(iset), "[[100.0 -> 200.0), [200.0 -> 300.0)]")
+
+    def test_intervalset_geniset(self):
+        # Test basic iset construction
+        eq_(makeset("  [----)   "),
+            makeset("  [-|--)   "))
+
+        eq_(makeset("[)  [--)   ") +
+            makeset(" [)    [--)"),
+            makeset("[|) [-----)"))
+
+        eq_(makeset("  [-------)"),
+            makeset("  [-|-----|"))
+
+
+    def test_intervalset_intersect(self):
+        # Test intersection (&)
+        with assert_raises(TypeError): # was AttributeError
+            x = makeset("[--)") & 1234
+
+        # Intersection with interval
+        eq_(makeset("[---|---)[)") &
+            list(makeset("  [------) "))[0],
+            makeset("  [-----)  "))
+
+        # Intersection with sets
+        eq_(makeset("[---------)") &
+            makeset(" [---)     "),
+            makeset(" [---)     "))
+
+        eq_(makeset(" [---)     ") &
+            makeset("[---------)"),
+            makeset(" [---)     "))
+
+        eq_(makeset("    [-----)") &
+            makeset(" [-----)   "),
+            makeset("    [--)   "))
+
+        eq_(makeset(" [--)  [--)") &
+            makeset("  [------) "),
+            makeset("  [-)  [-) "))
+
+        eq_(makeset("      [---)") &
+            makeset(" [--)      "),
+            makeset("           "))
+
+        eq_(makeset("    [-|---)") &
+            makeset(" [-----|-) "),
+            makeset("    [----) "))
+
+        eq_(makeset("    [-|-)  ") &
+            makeset(" [-|--|--) "),
+            makeset("    [---)  "))
+
+        # Border cases -- will give different results if intervals are
+        # half open or fully closed.  Right now, they are half open,
+        # although that's a little messy since the database intervals
+        # often contain a data point at the endpoint.
+        half_open = True
+        if half_open:
+            eq_(makeset("      [---)") &
+                makeset(" [----)    "),
+                makeset("           "))
+            eq_(makeset(" [----)[--)") &
+                makeset("[-) [--) [)"),
+                makeset(" [) [-)  [)"))
+        else:
+            eq_(makeset("      [---)") &
+                makeset(" [----)    "),
+                makeset("      .    "))
+            eq_(makeset(" [----)[--)") &
+                makeset("[-) [--) [)"),
+                makeset(" [) [-). [)"))
+
+class TestIntervalDB:
+    def test_dbinterval(self):
+        # Test DBInterval class
+        i = DBInterval(100, 200, 100, 200, 10000, 20000)
+        eq_(i.start, 100)
+        eq_(i.end, 200)
+        eq_(i.db_start, 100)
+        eq_(i.db_end, 200)
+        eq_(i.db_startpos, 10000)
+        eq_(i.db_endpos, 20000)
+        eq_(repr(i), repr(eval(repr(i))))
+
+        # end before start
+        with assert_raises(IntervalError):
+            i = DBInterval(200, 100, 100, 200, 10000, 20000)
+
+        # db_start too late
+        with assert_raises(IntervalError):
+            i = DBInterval(100, 200, 150, 200, 10000, 20000)
+
+        # db_end too soon
+        with assert_raises(IntervalError):
+            i = DBInterval(100, 200, 100, 150, 10000, 20000)
+
+        # actual start, end can be a subset
+        a = DBInterval(150, 200, 100, 200, 10000, 20000)
+        b = DBInterval(100, 150, 100, 200, 10000, 20000)
+        c = DBInterval(150, 160, 100, 200, 10000, 20000)
+
+        # Make a set of DBIntervals
+        iseta = IntervalSet([a, b])
+        isetc = IntervalSet(c)
+        assert(iseta.intersects(a))
+        assert(iseta.intersects(b))
+
+        # Test subset
+        with assert_raises(IntervalError):
+            x = a.subset(150, 250)
+
+        # Subset of those IntervalSets should still contain DBIntervals
+        for i in IntervalSet(iseta.intersection(Interval(125,250))):
+            assert(isinstance(i, DBInterval))
+
+class TestIntervalTree:
+
+    def test_interval_tree(self):
+        import random
+        random.seed(1234)
+
+        # make a set of 100 intervals
+        iset = IntervalSet()
+        j = 100
+        for i in random.sample(xrange(j),j):
+            interval = Interval(i, i+1)
+            iset += interval
+        render(iset, "Random Insertion")
+
+        # remove about half of them
+        for i in random.sample(xrange(j),j):
+            if random.randint(0,1):
+                iset -= Interval(i, i+1)
+
+        # try removing an interval that doesn't exist
+        with assert_raises(IntervalError):
+            iset -= Interval(1234,5678)
+        render(iset, "Random Insertion, deletion")
+
+        # make a set of 100 intervals, inserted in order
+        iset = IntervalSet()
+        j = 100
+        for i in xrange(j):
+            interval = Interval(i, i+1)
+            iset += interval
+        render(iset, "In-order insertion")
+
+class TestIntervalSpeed:
+    @unittest.skip("this is slow")
+    def test_interval_speed(self):
+        import yappi
+        import time
+        import testutil.aplotter as aplotter
+        import random
+        import math
+
+        print
+        yappi.start()
+        speeds = {}
+        limit = 10 # was 20
+        for j in [ 2**x for x in range(5,limit) ]:
+            start = time.time()
+            iset = IntervalSet()
+            for i in random.sample(xrange(j),j):
+                interval = Interval(i, i+1)
+                iset += interval
+            speed = (time.time() - start) * 1000000.0
+            printf("%d: %g μs (%g μs each, O(n log n) ratio %g)\n",
+                   j,
+                   speed,
+                   speed/j,
+                   speed / (j*math.log(j))) # should be constant
+            speeds[j] = speed
+        aplotter.plot(speeds.keys(), speeds.values(), plot_slope=True)
+        yappi.stop()
+        yappi.print_stats(sort_type=yappi.SORTTYPE_TTOT, limit=10)
+

tests/test_iteratorizer.py

@@ -0,0 +1,61 @@
+import nilmdb
+from nilmdb.utils.printf import *
+
+import nose
+from nose.tools import *
+from nose.tools import assert_raises
+import threading
+import time
+
+from testutil.helpers import *
+
+def func_with_callback(a, b, callback):
+    callback(a)
+    callback(b)
+    callback(a+b)
+    return "return value"
+
+class TestIteratorizer(object):
+    def test(self):
+
+        # First try it with a normal callback
+        self.result = ""
+        def cb(x):
+            self.result += str(x)
+        func_with_callback(1, 2, cb)
+        eq_(self.result, "123")
+
+        # Now make it an iterator
+        result = ""
+        f = lambda x: func_with_callback(1, 2, x)
+        with nilmdb.utils.Iteratorizer(f) as it:
+            for i in it:
+                result += str(i)
+        eq_(result, "123")
+        eq_(it.retval, "return value")
+
+        # Make sure things work when an exception occurs
+        result = ""
+        with nilmdb.utils.Iteratorizer(
+            lambda x: func_with_callback(1, "a", x)) as it:
+            with assert_raises(TypeError) as e:
+                for i in it:
+                    result += str(i)
+        eq_(result, "1a")
+
+        # Now try to trigger the case where we stop iterating
+        # mid-generator, and expect the iteratorizer to clean up after
+        # itself.  This doesn't have a particular result in the test,
+        # but gains coverage.
+        def foo():
+            with nilmdb.utils.Iteratorizer(f) as it:
+                it.next()
+        foo()
+        eq_(it.retval, None)
+
+        # Do the same thing when the curl hack is applied
+        def foo():
+            with nilmdb.utils.Iteratorizer(f, curl_hack = True) as it:
+                it.next()
+        foo()
+        eq_(it.retval, None)

tests/test_layout.py

@@ -0,0 +1,266 @@
+# -*- coding: utf-8 -*-
+
+import nilmdb
+
+from nilmdb.utils.printf import *
+
+from nose.tools import *
+from nose.tools import assert_raises
+import distutils.version
+import itertools
+import os
+import shutil
+import sys
+import cherrypy
+import threading
+import urllib2
+from urllib2 import urlopen, HTTPError
+import Queue
+import cStringIO
+import random
+import unittest
+
+from testutil.helpers import *
+
+from nilmdb.server.layout import *
+
+class TestLayouts(object):
+    # Some nilmdb.layout tests.  Not complete, just fills in missing
+    # coverage.
+    def test_layouts(self):
+        x = nilmdb.server.layout.get_named("PrepData")
+        y = nilmdb.server.layout.get_named("float32_8")
+        eq_(x.count, y.count)
+        eq_(x.datatype, y.datatype)
+        y = nilmdb.server.layout.get_named("float32_7")
+        ne_(x.count, y.count)
+        eq_(x.datatype, y.datatype)
+
+    def test_parsing(self):
+        self.real_t_parsing("PrepData", "RawData", "RawNotchedData")
+        self.real_t_parsing("float32_8", "uint16_6", "uint16_9")
+    def real_t_parsing(self, name_prep, name_raw, name_rawnotch):
+        # invalid layouts
+        with assert_raises(TypeError) as e:
+            parser = Parser("NoSuchLayout")
+        with assert_raises(TypeError) as e:
+            parser = Parser("float32")
+
+        # too little data
+        parser = Parser(name_prep)
+        data = ( "1234567890.000000 1.1 2.2 3.3 4.4 5.5\n" +
+                 "1234567890.100000 1.1 2.2 3.3 4.4 5.5\n")
+        with assert_raises(ParserError) as e:
+            parser.parse(data)
+        in_("error", str(e.exception))
+
+        # too much data
+        parser = Parser(name_prep)
+        data = ( "1234567890.000000 1.1 2.2 3.3 4.4 5.5 6.6 7.7 8.8 9.9\n" +
+                 "1234567890.100000 1.1 2.2 3.3 4.4 5.5 6.6 7.7 8.8 9.9\n")
+        with assert_raises(ParserError) as e:
+            parser.parse(data)
+        in_("error", str(e.exception))
+
+        # just right
+        parser = Parser(name_prep)
+        data = ( "1234567890.000000 1.1 2.2 3.3 4.4 5.5 6.6 7.7 8.8\n" +
+                 "1234567890.100000 1.1 2.2 3.3 4.4 5.5 6.6 7.7 8.8\n")
+        parser.parse(data)
+        eq_(parser.min_timestamp, 1234567890.0)
+        eq_(parser.max_timestamp, 1234567890.1)
+        eq_(parser.data, [[1234567890.0,1.1,2.2,3.3,4.4,5.5,6.6,7.7,8.8],
+                          [1234567890.1,1.1,2.2,3.3,4.4,5.5,6.6,7.7,8.8]])
+
+        # try RawData too, with clamping
+        parser = Parser(name_raw)
+        data = ( "1234567890.000000 1 2 3 4 5 6\n" +
+                 "1234567890.100000 1 2 3 4 5 6\n" )
+        parser.parse(data)
+        eq_(parser.data, [[1234567890.0,1,2,3,4,5,6],
+                          [1234567890.1,1,2,3,4,5,6]])
+
+        # pass an instantiated class
+        parser = Parser(get_named(name_rawnotch))
+        data = ( "1234567890.000000 1 2 3 4 5 6 7 8 9\n" +
+                 "1234567890.100000 1 2 3 4 5 6 7 8 9\n" )
+        parser.parse(data)
+
+        # non-monotonic
+        parser = Parser(name_raw)
+        data = ( "1234567890.100000 1 2 3 4 5 6\n" +
+                 "1234567890.099999 1 2 3 4 5 6\n" )
+        with assert_raises(ParserError) as e:
+            parser.parse(data)
+        in_("not monotonically increasing", str(e.exception))
+
+        parser = Parser(name_raw)
+        data = ( "1234567890.100000 1 2 3 4 5 6\n" +
+                 "1234567890.100000 1 2 3 4 5 6\n" )
+        with assert_raises(ParserError) as e:
+            parser.parse(data)
+        in_("not monotonically increasing", str(e.exception))
+
+        parser = Parser(name_raw)
+        data = ( "1234567890.100000 1 2 3 4 5 6\n" +
+                 "1234567890.100001 1 2 3 4 5 6\n" )
+        parser.parse(data)
+
+        # RawData with values out of bounds
+        parser = Parser(name_raw)
+        data = ( "1234567890.000000 1 2 3 4 500000 6\n" +
+                 "1234567890.100000 1 2 3 4 5 6\n" )
+        with assert_raises(ParserError) as e:
+            parser.parse(data)
+        in_("value out of range", str(e.exception))
+
+        # Empty data should work but is useless
+        parser = Parser(name_raw)
+        data = ""
+        parser.parse(data)
+        assert(parser.min_timestamp is None)
+        assert(parser.max_timestamp is None)
+
+    def test_formatting(self):
+        self.real_t_formatting("PrepData", "RawData", "RawNotchedData")
+        self.real_t_formatting("float32_8", "uint16_6", "uint16_9")
+    def real_t_formatting(self, name_prep, name_raw, name_rawnotch):
+        # invalid layout
+        with assert_raises(TypeError) as e:
+            formatter = Formatter("NoSuchLayout")
+
+        # too little data
+        formatter = Formatter(name_prep)
+        data = [ [ 1234567890.000000, 1.1, 2.2, 3.3, 4.4, 5.5 ],
+                 [ 1234567890.100000, 1.1, 2.2, 3.3, 4.4, 5.5 ] ]
+        with assert_raises(FormatterError) as e:
+            formatter.format(data)
+        in_("error", str(e.exception))
+
+        # too much data
+        formatter = Formatter(name_prep)
+        data = [ [ 1234567890.000000, 1, 2, 3, 4, 5, 6, 7, 8, 9 ],
+                 [ 1234567890.100000, 1, 2, 3, 4, 5, 6, 7, 8, 9 ] ]
+        with assert_raises(FormatterError) as e:
+            formatter.format(data)
+        in_("error", str(e.exception))
+
+        # just right
+        formatter = Formatter(name_prep)
+        data = [ [ 1234567890.000000, 1.1, 2.2, 3.3, 4.4, 5.5, 6.6, 7.7, 8.8 ],
+                 [ 1234567890.100000, 1.1, 2.2, 3.3, 4.4, 5.5, 6.6, 7.7, 8.8 ] ]
+        text = formatter.format(data)
+        eq_(text,
+            "1234567890.000000 1.100000 2.200000 3.300000 4.400000 " +
+            "5.500000 6.600000 7.700000 8.800000\n" +
+            "1234567890.100000 1.100000 2.200000 3.300000 4.400000 " +
+            "5.500000 6.600000 7.700000 8.800000\n")
+
+        # try RawData too
+        formatter = Formatter(name_raw)
+        data = [ [ 1234567890.000000, 1, 2, 3, 4, 5, 6 ],
+                 [ 1234567890.100000, 1, 2, 3, 4, 5, 6 ] ]
+        text = formatter.format(data)
+        eq_(text,
+            "1234567890.000000 1 2 3 4 5 6\n" +
+            "1234567890.100000 1 2 3 4 5 6\n")
+
+        # pass an instantiated class
+        formatter = Formatter(get_named(name_rawnotch))
+        data = [ [ 1234567890.000000, 1, 2, 3, 4, 5, 6, 7, 8, 9 ],
+                 [ 1234567890.100000, 1, 2, 3, 4, 5, 6, 7, 8, 9 ] ]
+        text = formatter.format(data)
+        eq_(text,
+            "1234567890.000000 1 2 3 4 5 6 7 8 9\n" +
+            "1234567890.100000 1 2 3 4 5 6 7 8 9\n")
+
+        # Empty data should work but is useless
+        formatter = Formatter(name_raw)
+        data = []
+        text = formatter.format(data)
+        eq_(text, "")
+
+    def test_roundtrip(self):
+        self.real_t_roundtrip("PrepData", "RawData", "RawNotchedData")
+        self.real_t_roundtrip("float32_8", "uint16_6", "uint16_9")
+    def real_t_roundtrip(self, name_prep, name_raw, name_rawnotch):
+        # Verify that textual data passed into the Parser, and then
+        # back through the Formatter, then back into the Parser,
+        # gives identical parsed representations
+        random.seed(12345)
+
+        def do_roundtrip(layout, datagen):
+            for i in range(100):
+                rows = random.randint(1,100)
+                data = ""
+                ts = 1234567890
+                for r in range(rows):
+                    ts += random.uniform(0,1)
+                    row = sprintf("%f", ts) + " "
+                    row += " ".join(datagen())
+                    row += "\n"
+                    data += row
+                parser1 = Parser(layout)
+                formatter = Formatter(layout)
+                parser2 = Parser(layout)
+                parser1.parse(data)
+                parser2.parse(formatter.format(parser1.data))
+                eq_(parser1.data, parser2.data)
+
+        def datagen():
+            return [ sprintf("%f", random.uniform(-1000,1000))
+                     for x in range(8) ]
+        do_roundtrip(name_prep, datagen)
+
+        def datagen():
+            return [ sprintf("%d", random.randint(0,65535))
+                     for x in range(6) ]
+        do_roundtrip(name_raw, datagen)
+
+        def datagen():
+            return [ sprintf("%d", random.randint(0,65535))
+                     for x in range(9) ]
+        do_roundtrip(name_rawnotch, datagen)
+
+class TestLayoutSpeed:
+    @unittest.skip("this is slow")
+    def test_layout_speed(self):
+        import time
+
+        random.seed(54321)
+
+        def do_speedtest(layout, datagen, rows = 5000, times = 100):
+            # Build data once
+            data = ""
+            ts = 1234567890
+            for r in range(rows):
+                ts += random.uniform(0,1)
+                row = sprintf("%f", ts) + " "
+                row += " ".join(datagen())
+                row += "\n"
+                data += row
+
+            # Do lots of roundtrips
+            start = time.time()
+            for i in range(times):
+                parser = Parser(layout)
+                formatter = Formatter(layout)
+                parser.parse(data)
+                data = formatter.format(parser.data)
+            elapsed = time.time() - start
+            printf("roundtrip %s: %d ms, %.1f μs/row, %d rows/sec\n",
+                   layout,
+                   elapsed * 1e3,
+                   (elapsed * 1e6) / (rows * times),
+                   (rows * times) / elapsed)
+
+        print ""
+        def datagen():
+            return [ sprintf("%f", random.uniform(-1000,1000))
+                     for x in range(10) ]
+        do_speedtest("float32_10", datagen)
+
+        def datagen():
+            return [ sprintf("%d", random.randint(0,65535))
+                     for x in range(10) ]
+        do_speedtest("uint16_10", datagen)

tests/test_lrucache.py

@@ -0,0 +1,83 @@
+import nilmdb
+from nilmdb.utils.printf import *
+
+import nose
+from nose.tools import *
+from nose.tools import assert_raises
+import threading
+import time
+import inspect
+
+from testutil.helpers import *
+
+@nilmdb.utils.lru_cache(size = 3)
+def foo1(n):
+    return n
+
+@nilmdb.utils.lru_cache(size = 5)
+def foo2(n):
+    return n
+
+def foo3d(n):
+    foo3d.destructed.append(n)
+foo3d.destructed = []
+@nilmdb.utils.lru_cache(size = 3, onremove = foo3d)
+def foo3(n):
+    return n
+
+class Foo:
+    def __init__(self):
+        self.calls = 0
+    @nilmdb.utils.lru_cache(size = 3, keys = slice(1, 2))
+    def foo(self, n, **kwargs):
+        self.calls += 1
+
+class TestLRUCache(object):
+    def test(self):
+
+        [ foo1(n) for n in [ 1, 2, 3, 1, 2, 3, 1, 2, 3 ] ]
+        eq_(foo1.cache_info(), (6, 3))
+        [ foo1(n) for n in [ 1, 2, 3, 1, 2, 3, 1, 2, 3 ] ]
+        eq_(foo1.cache_info(), (15, 3))
+        [ foo1(n) for n in [ 4, 2, 1, 1, 4 ] ]
+        eq_(foo1.cache_info(), (18, 5))
+
+        [ foo2(n) for n in [ 1, 2, 3, 1, 2, 3, 1, 2, 3 ] ]
+        eq_(foo2.cache_info(), (6, 3))
+        [ foo2(n) for n in [ 1, 2, 3, 1, 2, 3, 1, 2, 3 ] ]
+        eq_(foo2.cache_info(), (15, 3))
+        [ foo2(n) for n in [ 4, 2, 1, 1, 4 ] ]
+        eq_(foo2.cache_info(), (19, 4))
+
+        [ foo3(n) for n in [ 1, 2, 3, 1, 2, 3, 1, 2, 3 ] ]
+        eq_(foo3.cache_info(), (6, 3))
+        [ foo3(n) for n in [ 1, 2, 3, 1, 2, 3, 1, 2, 3 ] ]
+        eq_(foo3.cache_info(), (15, 3))
+        [ foo3(n) for n in [ 4, 2, 1, 1, 4 ] ]
+        eq_(foo3.cache_info(), (18, 5))
+        eq_(foo3d.destructed, [1, 3])
+        with assert_raises(KeyError):
+            foo3.cache_remove(1,2,3)
+        foo3.cache_remove(1)
+        eq_(foo3d.destructed, [1, 3, 1])
+        foo3.cache_remove_all()
+        eq_(foo3d.destructed, [1, 3, 1, 2, 4 ])
+
+        foo = Foo()
+        foo.foo(5)
+        foo.foo(6)
+        foo.foo(7)
+        foo.foo(5)
+        eq_(foo.calls, 3)
+
+        # Can't handle keyword arguments right now
+        with assert_raises(NotImplementedError):
+            foo.foo(3, asdf = 7)
+
+        # Verify that argspecs were maintained
+        eq_(inspect.getargspec(foo1),
+            inspect.ArgSpec(args=['n'],
+                            varargs=None, keywords=None, defaults=None))
+        eq_(inspect.getargspec(foo.foo),
+            inspect.ArgSpec(args=['self', 'n'],
+                            varargs=None, keywords="kwargs", defaults=None))

tests/test_mustclose.py

@@ -0,0 +1,110 @@
+import nilmdb
+from nilmdb.utils.printf import *
+
+import nose
+from nose.tools import *
+from nose.tools import assert_raises
+
+from testutil.helpers import *
+
+import sys
+import cStringIO
+import gc
+
+import inspect
+
+err = cStringIO.StringIO()
+
+@nilmdb.utils.must_close(errorfile = err)
+class Foo:
+    def __init__(self, arg):
+        fprintf(err, "Init %s\n", arg)
+
+    def __del__(self):
+        fprintf(err, "Deleting\n")
+
+    def close(self):
+        fprintf(err, "Closing\n")
+
+@nilmdb.utils.must_close(errorfile = err, wrap_verify = True)
+class Bar:
+    def __init__(self):
+        fprintf(err, "Init\n")
+
+    def __del__(self):
+        fprintf(err, "Deleting\n")
+
+    def close(self):
+        fprintf(err, "Closing\n")
+
+    def blah(self, arg):
+        fprintf(err, "Blah %s\n", arg)
+
+@nilmdb.utils.must_close(errorfile = err)
+class Baz:
+    pass
+
+class TestMustClose(object):
+    def test(self):
+
+        # Note: this test might fail if the Python interpreter doesn't
+        # garbage collect the object (and call its __del__ function)
+        # right after a "del x".
+
+        # Trigger error
+        err.truncate()
+        x = Foo("hi")
+        # Verify that the arg spec was maintained
+        eq_(inspect.getargspec(x.__init__),
+            inspect.ArgSpec(args = ['self', 'arg'],
+                            varargs = None, keywords = None, defaults = None))
+        del x
+        gc.collect()
+        eq_(err.getvalue(),
+            "Init hi\n"
+            "error: Foo.close() wasn't called!\n"
+            "Deleting\n")
+
+        # No error
+        err.truncate(0)
+        y = Foo("bye")
+        y.close()
+        del y
+        gc.collect()
+        eq_(err.getvalue(),
+            "Init bye\n"
+            "Closing\n"
+            "Deleting\n")
+
+        # Verify function calls when wrap_verify is True
+        err.truncate(0)
+        z = Bar()
+        eq_(inspect.getargspec(z.blah),
+            inspect.ArgSpec(args = ['self', 'arg'],
+                            varargs = None, keywords = None, defaults = None))
+        z.blah("boo")
+        z.close()
+        with assert_raises(AssertionError) as e:
+            z.blah("hello")
+        in_("called <function blah at 0x", str(e.exception))
+        in_("> after close", str(e.exception))
+        # Since the most recent assertion references 'z',
+        # we need to raise another assertion here so that
+        # 'z' will get properly deleted.
+        with assert_raises(AssertionError):
+            raise AssertionError()
+        del z
+        gc.collect()
+        eq_(err.getvalue(),
+            "Init\n"
+            "Blah boo\n"
+            "Closing\n"
+            "Deleting\n")
+
+        # Class with missing methods
+        err.truncate(0)
+        w = Baz()
+        w.close()
+        del w
+        eq_(err.getvalue(), "")
+

tests/test_nilmdb.py

@@ -0,0 +1,212 @@
+import nilmdb
+
+from nose.tools import *
+from nose.tools import assert_raises
+import distutils.version
+import simplejson as json
+import itertools
+import os
+import shutil
+import sys
+import cherrypy
+import threading
+import urllib2
+from urllib2 import urlopen, HTTPError
+import Queue
+import cStringIO
+import time
+
+testdb = "tests/testdb"
+
+#@atexit.register
+#def cleanup():
+#    os.unlink(testdb)
+
+from testutil.helpers import *
+
+class Test00Nilmdb(object):  # named 00 so it runs first
+    def test_NilmDB(self):
+        recursive_unlink(testdb)
+
+        with assert_raises(IOError):
+            nilmdb.NilmDB("/nonexistant-db/foo")
+
+        db = nilmdb.NilmDB(testdb)
+        db.close()
+        db = nilmdb.NilmDB(testdb, sync=False)
+        db.close()
+
+        # test timer, just to get coverage
+        capture = cStringIO.StringIO()
+        old = sys.stdout
+        sys.stdout = capture
+        with nilmdb.utils.Timer("test"):
+            time.sleep(0.01)
+        sys.stdout = old
+        in_("test: ", capture.getvalue())
+
+    def test_stream(self):
+        db = nilmdb.NilmDB(testdb, sync=False)
+        eq_(db.stream_list(), [])
+
+        # Bad path
+        with assert_raises(ValueError):
+            db.stream_create("foo/bar/baz", "PrepData")
+        with assert_raises(ValueError):
+            db.stream_create("/foo", "PrepData")
+        # Bad layout type
+        with assert_raises(ValueError):
+            db.stream_create("/newton/prep", "NoSuchLayout")
+        db.stream_create("/newton/prep", "PrepData")
+        db.stream_create("/newton/raw", "RawData")
+        db.stream_create("/newton/zzz/rawnotch", "RawNotchedData")
+
+        # Verify we got 3 streams
+        eq_(db.stream_list(), [ ["/newton/prep", "PrepData"],
+                                ["/newton/raw", "RawData"],
+                                ["/newton/zzz/rawnotch", "RawNotchedData"]
+                                ])
+        # Match just one type or one path
+        eq_(db.stream_list(layout="RawData"), [ ["/newton/raw", "RawData"] ])
+        eq_(db.stream_list(path="/newton/raw"), [ ["/newton/raw", "RawData"] ])
+
+        # Verify that columns were made right (pytables specific)
+        if "h5file" in db.data.__dict__:
+            h5file = db.data.h5file
+            eq_(len(h5file.getNode("/newton/prep").cols), 9)
+            eq_(len(h5file.getNode("/newton/raw").cols), 7)
+            eq_(len(h5file.getNode("/newton/zzz/rawnotch").cols), 10)
+            assert(not h5file.getNode("/newton/prep").colindexed["timestamp"])
+            assert(not h5file.getNode("/newton/prep").colindexed["c1"])
+
+        # Set / get metadata
+        eq_(db.stream_get_metadata("/newton/prep"), {})
+        eq_(db.stream_get_metadata("/newton/raw"), {})
+        meta1 = { "description": "The Data",
+                  "v_scale": "1.234" }
+        meta2 = { "description": "The Data" }
+        meta3 = { "v_scale": "1.234" }
+        db.stream_set_metadata("/newton/prep", meta1)
+        db.stream_update_metadata("/newton/prep", {})
+        db.stream_update_metadata("/newton/raw", meta2)
+        db.stream_update_metadata("/newton/raw", meta3)
+        eq_(db.stream_get_metadata("/newton/prep"), meta1)
+        eq_(db.stream_get_metadata("/newton/raw"), meta1)
+
+        # fill in some test coverage for start >= end
+        with assert_raises(nilmdb.server.NilmDBError):
+            db.stream_remove("/newton/prep", 0, 0)
+        with assert_raises(nilmdb.server.NilmDBError):
+            db.stream_remove("/newton/prep", 1, 0)
+        db.stream_remove("/newton/prep", 0, 1)
+
+        db.close()
+
+class TestBlockingServer(object):
+    def setUp(self):
+        self.db = nilmdb.NilmDB(testdb, sync=False)
+
+    def tearDown(self):
+        self.db.close()
+
+    def test_blocking_server(self):
+        # Start web app on a custom port
+        self.server = nilmdb.Server(self.db, host = "127.0.0.1",
+                                    port = 12380, stoppable = True)
+
+        # Run it
+        event = threading.Event()
+        def run_server():
+            self.server.start(blocking = True, event = event)
+        thread = threading.Thread(target = run_server)
+        thread.start()
+        if not event.wait(timeout = 10):
+            raise AssertionError("server didn't start in 10 seconds")
+
+        # Send request to exit.
+        req = urlopen("http://127.0.0.1:12380/exit/", timeout = 1)
+
+        # Wait for it
+        thread.join()
+
+def geturl(path):
+    req = urlopen("http://127.0.0.1:12380" + path, timeout = 10)
+    return req.read()
+
+def getjson(path):
+    return json.loads(geturl(path))
+
+class TestServer(object):
+
+    def setUp(self):
+        # Start web app on a custom port
+        self.db = nilmdb.NilmDB(testdb, sync=False)
+        self.server = nilmdb.Server(self.db, host = "127.0.0.1",
+                                    port = 12380, stoppable = False)
+        self.server.start(blocking = False)
+
+    def tearDown(self):
+        # Close web app
+        self.server.stop()
+        self.db.close()
+
+    def test_server(self):
+        # Make sure we can't force an exit, and test other 404 errors
+        for url in [ "/exit", "/", "/favicon.ico" ]:
+            with assert_raises(HTTPError) as e:
+                geturl(url)
+            eq_(e.exception.code, 404)
+
+        # Check version
+        eq_(distutils.version.LooseVersion(getjson("/version")),
+            distutils.version.LooseVersion(nilmdb.__version__))
+
+    def test_stream_list(self):
+        # Known streams that got populated by an earlier test (test_nilmdb)
+        streams = getjson("/stream/list")
+
+        eq_(streams, [
+            ['/newton/prep', 'PrepData'],
+            ['/newton/raw', 'RawData'],
+            ['/newton/zzz/rawnotch', 'RawNotchedData'],
+            ])
+
+        streams = getjson("/stream/list?layout=RawData")
+        eq_(streams, [['/newton/raw', 'RawData']])
+
+        streams = getjson("/stream/list?layout=NoSuchLayout")
+        eq_(streams, [])
+
+
+    def test_stream_metadata(self):
+        with assert_raises(HTTPError) as e:
+            getjson("/stream/get_metadata?path=foo")
+        eq_(e.exception.code, 404)
+
+        data = getjson("/stream/get_metadata?path=/newton/prep")
+        eq_(data, {'description': 'The Data', 'v_scale': '1.234'})
+
+        data = getjson("/stream/get_metadata?path=/newton/prep"
+                       "&key=v_scale")
+        eq_(data, {'v_scale': '1.234'})
+
+        data = getjson("/stream/get_metadata?path=/newton/prep"
+                       "&key=v_scale&key=description")
+        eq_(data, {'description': 'The Data', 'v_scale': '1.234'})
+
+        data = getjson("/stream/get_metadata?path=/newton/prep"
+                       "&key=v_scale&key=foo")
+        eq_(data, {'foo': None, 'v_scale': '1.234'})
+
+        data = getjson("/stream/get_metadata?path=/newton/prep"
+                       "&key=foo")
+        eq_(data, {'foo': None})
+
+
+    def test_insert(self):
+        # GET instead of POST (no body)
+        # (actual POST test is done by client code)
+        with assert_raises(HTTPError) as e:
+            getjson("/stream/insert?path=/newton/prep&start=0&end=0")
+        eq_(e.exception.code, 400)
+