Tests for Unicode compliance

We replace cStringIO with StringIO subclass that forces UTF-8
encoding, and explicitly convert commandlines to UTF-8 before
shlex.  These changes will only affect tests, not normal commandline
operation.

.gitignore

@@ -0,0 +1,4 @@
+db/
+tests/*testdb/
+.coverage
+*.pyc

README.txt

@@ -1,2 +1,4 @@
 sudo apt-get install python-nose python-coverage
-sudo apt-get install python-tables cython python-cherrypy3
+sudo apt-get install python-tables python-cherrypy3
+sudo apt-get install cython # 0.17.1-1 or newer
+

TODO

@@ -1,5 +1 @@
 - Merge adjacent intervals on insert (maybe with client help?)
-
-- Better testing:
-  - see about getting coverage on layout.pyx
-  - layout.pyx performance tests, before and after generalization

design.md

@@ -143,6 +143,13 @@ Speed
 	 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
@@ -161,6 +168,18 @@ IntervalSet speed
 - 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
 -------

nilmdb/RedBlackTree.cc

@@ -1,605 +0,0 @@
-
-
-
-// The RedBlackEntry class is an Abstract Base Class.  This means that no
-// instance of the RedBlackEntry class can exist.  Only classes which
-// inherit from the RedBlackEntry class can exist.  Furthermore any class
-// which inherits from the RedBlackEntry class must define the member
-// function GetKey().  The Print() member function does not have to
-// be defined because a default definition exists.
-//
-// The GetKey() function should return an integer key for that entry.
-// The key for an entry should never change otherwise bad things might occur.
-
-class RedBlackEntry {
-public:
-  RedBlackEntry();
-  virtual ~RedBlackEntry();
-  virtual int GetKey() const = 0;
-  virtual void Print() const;
-};
-
-class RedBlackTreeNode {
-  friend class RedBlackTree;
-public:
-  void Print(RedBlackTreeNode*,
-	     RedBlackTreeNode*) const;
-  RedBlackTreeNode();
-  RedBlackTreeNode(RedBlackEntry *);
-  RedBlackEntry * GetEntry() const;
-  ~RedBlackTreeNode();
-protected:
-  RedBlackEntry * storedEntry;
-  int key;
-  int red; /* if red=0 then the node is black */
-  RedBlackTreeNode * left;
-  RedBlackTreeNode * right;
-  RedBlackTreeNode * parent;
-};
-
-
-
-class RedBlackTree {
-public:
-  RedBlackTree();
-  ~RedBlackTree();
-  void Print() const;
-  RedBlackEntry * DeleteNode(RedBlackTreeNode *);
-  RedBlackTreeNode * Insert(RedBlackEntry *);
-  RedBlackTreeNode * GetPredecessorOf(RedBlackTreeNode *) const;
-  RedBlackTreeNode * GetSuccessorOf(RedBlackTreeNode *) const;
-  RedBlackTreeNode * Search(int key);
-  TemplateStack<RedBlackTreeNode *> * Enumerate(int low, int high) ;
-  void CheckAssumptions() const;
-protected:
-  /*  A sentinel is used for root and for nil.  These sentinels are */
-  /*  created when RedBlackTreeCreate is caled.  root->left should always */
-  /*  point to the node which is the root of the tree.  nil points to a */
-  /*  node which should always be black but has aribtrary children and */
-  /*  parent and no key or info.  The point of using these sentinels is so */
-  /*  that the root and nil nodes do not require special cases in the code */
-  RedBlackTreeNode * root;
-  RedBlackTreeNode * nil;
-  void LeftRotate(RedBlackTreeNode *);
-  void RightRotate(RedBlackTreeNode *);
-  void TreeInsertHelp(RedBlackTreeNode *);
-  void TreePrintHelper(RedBlackTreeNode *) const;
-  void FixUpMaxHigh(RedBlackTreeNode *);
-  void DeleteFixUp(RedBlackTreeNode *);
-};
-
-const int MIN_INT=-MAX_INT;
-
-RedBlackTreeNode::RedBlackTreeNode(){
-};
-
-RedBlackTreeNode::RedBlackTreeNode(RedBlackEntry * newEntry)
-  : storedEntry (newEntry) , key(newEntry->GetKey()) {
-};
-
-RedBlackTreeNode::~RedBlackTreeNode(){
-};
-
-RedBlackEntry * RedBlackTreeNode::GetEntry() const {return storedEntry;}
-
-RedBlackEntry::RedBlackEntry(){
-};
-RedBlackEntry::~RedBlackEntry(){
-};
-void RedBlackEntry::Print() const {
-  cout << "No Print Method defined. Using Default: " << GetKey() << endl;
-}
-
-RedBlackTree::RedBlackTree()
-{
-  nil = new RedBlackTreeNode;
-  nil->left = nil->right = nil->parent = nil;
-  nil->red = 0;
-  nil->key = MIN_INT;
-  nil->storedEntry = NULL;
-
-  root = new RedBlackTreeNode;
-  root->parent = root->left = root->right = nil;
-  root->key = MAX_INT;
-  root->red=0;
-  root->storedEntry = NULL;
-}
-
-/***********************************************************************/
-/*  FUNCTION:  LeftRotate */
-/**/
-/*  INPUTS:  the node to rotate on */
-/**/
-/*  OUTPUT:  None */
-/**/
-/*  Modifies Input: this, x */
-/**/
-/*  EFFECTS:  Rotates as described in _Introduction_To_Algorithms by */
-/*            Cormen, Leiserson, Rivest (Chapter 14).  Basically this */
-/*            makes the parent of x be to the left of x, x the parent of */
-/*            its parent before the rotation and fixes other pointers */
-/*            accordingly.  */
-/***********************************************************************/
-
-void RedBlackTree::LeftRotate(RedBlackTreeNode* x) {
-  RedBlackTreeNode* y;
-
-  /*  I originally wrote this function to use the sentinel for */
-  /*  nil to avoid checking for nil.  However this introduces a */
-  /*  very subtle bug because sometimes this function modifies */
-  /*  the parent pointer of nil.  This can be a problem if a */
-  /*  function which calls LeftRotate also uses the nil sentinel */
-  /*  and expects the nil sentinel's parent pointer to be unchanged */
-  /*  after calling this function.  For example, when DeleteFixUP */
-  /*  calls LeftRotate it expects the parent pointer of nil to be */
-  /*  unchanged. */
-
-  y=x->right;
-  x->right=y->left;
-
-  if (y->left != nil) y->left->parent=x; /* used to use sentinel here */
-  /* and do an unconditional assignment instead of testing for nil */
-
-  y->parent=x->parent;
-
-  /* instead of checking if x->parent is the root as in the book, we */
-  /* count on the root sentinel to implicitly take care of this case */
-  if( x == x->parent->left) {
-    x->parent->left=y;
-  } else {
-    x->parent->right=y;
-  }
-  y->left=x;
-  x->parent=y;
-}
-
-/***********************************************************************/
-/*  FUNCTION:  RighttRotate */
-/**/
-/*  INPUTS:  node to rotate on */
-/**/
-/*  OUTPUT:  None */
-/**/
-/*  Modifies Input?: this, y */
-/**/
-/*  EFFECTS:  Rotates as described in _Introduction_To_Algorithms by */
-/*            Cormen, Leiserson, Rivest (Chapter 14).  Basically this */
-/*            makes the parent of x be to the left of x, x the parent of */
-/*            its parent before the rotation and fixes other pointers */
-/*            accordingly.  */
-/***********************************************************************/
-
-void RedBlackTree::RightRotate(RedBlackTreeNode* y) {
-  RedBlackTreeNode* x;
-
-  /*  I originally wrote this function to use the sentinel for */
-  /*  nil to avoid checking for nil.  However this introduces a */
-  /*  very subtle bug because sometimes this function modifies */
-  /*  the parent pointer of nil.  This can be a problem if a */
-  /*  function which calls LeftRotate also uses the nil sentinel */
-  /*  and expects the nil sentinel's parent pointer to be unchanged */
-  /*  after calling this function.  For example, when DeleteFixUP */
-  /*  calls LeftRotate it expects the parent pointer of nil to be */
-  /*  unchanged. */
-
-  x=y->left;
-  y->left=x->right;
-
-  if (nil != x->right)  x->right->parent=y; /*used to use sentinel here */
-  /* and do an unconditional assignment instead of testing for nil */
-
-  /* instead of checking if x->parent is the root as in the book, we */
-  /* count on the root sentinel to implicitly take care of this case */
-  x->parent=y->parent;
-  if( y == y->parent->left) {
-    y->parent->left=x;
-  } else {
-    y->parent->right=x;
-  }
-  x->right=y;
-  y->parent=x;
-}
-
-/***********************************************************************/
-/*  FUNCTION:  TreeInsertHelp  */
-/**/
-/*  INPUTS:  z is the node to insert */
-/**/
-/*  OUTPUT:  none */
-/**/
-/*  Modifies Input:  this, z */
-/**/
-/*  EFFECTS:  Inserts z into the tree as if it were a regular binary tree */
-/*            using the algorithm described in _Introduction_To_Algorithms_ */
-/*            by Cormen et al.  This funciton is only intended to be called */
-/*            by the Insert function and not by the user */
-/***********************************************************************/
-
-void RedBlackTree::TreeInsertHelp(RedBlackTreeNode* z) {
-  /*  This function should only be called by RedBlackTree::Insert */
-  RedBlackTreeNode* x;
-  RedBlackTreeNode* y;
-
-  z->left=z->right=nil;
-  y=root;
-  x=root->left;
-  while( x != nil) {
-    y=x;
-    if ( x->key > z->key) {
-      x=x->left;
-    } else { /* x->key <= z->key */
-      x=x->right;
-    }
-  }
-  z->parent=y;
-  if ( (y == root) ||
-       (y->key > z->key) ) {
-    y->left=z;
-  } else {
-    y->right=z;
-  }
-}
-
-/*  Before calling InsertNode  the node x should have its key set */
-
-/***********************************************************************/
-/*  FUNCTION:  InsertNode */
-/**/
-/*  INPUTS:  newEntry is the entry to insert*/
-/**/
-/*  OUTPUT:  This function returns a pointer to the newly inserted node */
-/*           which is guarunteed to be valid until this node is deleted. */
-/*           What this means is if another data structure stores this */
-/*           pointer then the tree does not need to be searched when this */
-/*           is to be deleted. */
-/**/
-/*  Modifies Input: tree */
-/**/
-/*  EFFECTS:  Creates a node node which contains the appropriate key and */
-/*            info pointers and inserts it into the tree. */
-/***********************************************************************/
-/* jim */
-RedBlackTreeNode * RedBlackTree::Insert(RedBlackEntry * newEntry)
-{
-  RedBlackTreeNode * y;
-  RedBlackTreeNode * x;
-  RedBlackTreeNode * newNode;
-
-  x = new RedBlackTreeNode(newEntry);
-  TreeInsertHelp(x);
-  newNode = x;
-  x->red=1;
-  while(x->parent->red) { /* use sentinel instead of checking for root */
-    if (x->parent == x->parent->parent->left) {
-      y=x->parent->parent->right;
-      if (y->red) {
-	x->parent->red=0;
-	y->red=0;
-	x->parent->parent->red=1;
-	x=x->parent->parent;
-      } else {
-	if (x == x->parent->right) {
-	  x=x->parent;
-	  LeftRotate(x);
-	}
-	x->parent->red=0;
-	x->parent->parent->red=1;
-	RightRotate(x->parent->parent);
-      }
-    } else { /* case for x->parent == x->parent->parent->right */
-             /* this part is just like the section above with */
-             /* left and right interchanged */
-      y=x->parent->parent->left;
-      if (y->red) {
-	x->parent->red=0;
-	y->red=0;
-	x->parent->parent->red=1;
-	x=x->parent->parent;
-      } else {
-	if (x == x->parent->left) {
-	  x=x->parent;
-	  RightRotate(x);
-	}
-	x->parent->red=0;
-	x->parent->parent->red=1;
-	LeftRotate(x->parent->parent);
-      }
-    }
-  }
-  root->left->red=0;
-  return(newNode);
-}
-
-/***********************************************************************/
-/*  FUNCTION:  GetSuccessorOf  */
-/**/
-/*    INPUTS:  x is the node we want the succesor of */
-/**/
-/*    OUTPUT:  This function returns the successor of x or NULL if no */
-/*             successor exists. */
-/**/
-/*    Modifies Input: none */
-/**/
-/*    Note:  uses the algorithm in _Introduction_To_Algorithms_ */
-/***********************************************************************/
-
-RedBlackTreeNode * RedBlackTree::GetSuccessorOf(RedBlackTreeNode * x) const
-{
-  RedBlackTreeNode* y;
-
-  if (nil != (y = x->right)) { /* assignment to y is intentional */
-    while(y->left != nil) { /* returns the minium of the right subtree of x */
-      y=y->left;
-    }
-    return(y);
-  } else {
-    y=x->parent;
-    while(x == y->right) { /* sentinel used instead of checking for nil */
-      x=y;
-      y=y->parent;
-    }
-    if (y == root) return(nil);
-    return(y);
-  }
-}
-
-/***********************************************************************/
-/*  FUNCTION:  GetPredecessorOf  */
-/**/
-/*    INPUTS:  x is the node to get predecessor of */
-/**/
-/*    OUTPUT:  This function returns the predecessor of x or NULL if no */
-/*             predecessor exists. */
-/**/
-/*    Modifies Input: none */
-/**/
-/*    Note:  uses the algorithm in _Introduction_To_Algorithms_ */
-/***********************************************************************/
-
-RedBlackTreeNode * RedBlackTree::GetPredecessorOf(RedBlackTreeNode * x) const {
-  RedBlackTreeNode* y;
-
-  if (nil != (y = x->left)) { /* assignment to y is intentional */
-    while(y->right != nil) { /* returns the maximum of the left subtree of x */
-      y=y->right;
-    }
-    return(y);
-  } else {
-    y=x->parent;
-    while(x == y->left) {
-      if (y == root) return(nil);
-      x=y;
-      y=y->parent;
-    }
-    return(y);
-  }
-}
-
-/***********************************************************************/
-/*  FUNCTION:  Print */
-/**/
-/*    INPUTS:  none */
-/**/
-/*    OUTPUT:  none  */
-/**/
-/*    EFFECTS:  This function recursively prints the nodes of the tree */
-/*              inorder. */
-/**/
-/*    Modifies Input: none */
-/**/
-/*    Note:    This function should only be called from ITTreePrint */
-/***********************************************************************/
-
-void RedBlackTreeNode::Print(RedBlackTreeNode * nil,
-			     RedBlackTreeNode * root) const {
-  storedEntry->Print();
-  printf(", key=%i ",key);
-  printf("  l->key=");
-  if( left == nil) printf("NULL"); else printf("%i",left->key);
-  printf("  r->key=");
-  if( right == nil) printf("NULL"); else printf("%i",right->key);
-  printf("  p->key=");
-  if( parent == root) printf("NULL"); else printf("%i",parent->key);
-  printf("  red=%i\n",red);
-}
-
-void RedBlackTree::TreePrintHelper( RedBlackTreeNode* x) const {
-
-  if (x != nil) {
-    TreePrintHelper(x->left);
-    x->Print(nil,root);
-    TreePrintHelper(x->right);
-  }
-}
-
-/***********************************************************************/
-/*  FUNCTION:  Print */
-/**/
-/*    INPUTS:  none */
-/**/
-/*    OUTPUT:  none */
-/**/
-/*    EFFECT:  This function recursively prints the nodes of the tree */
-/*             inorder. */
-/**/
-/*    Modifies Input: none */
-/**/
-/***********************************************************************/
-
-void RedBlackTree::Print() const {
-  TreePrintHelper(root->left);
-}
-
-/***********************************************************************/
-/*  FUNCTION:  DeleteFixUp */
-/**/
-/*    INPUTS:  x is the child of the spliced */
-/*             out node in DeleteNode. */
-/**/
-/*    OUTPUT:  none */
-/**/
-/*    EFFECT:  Performs rotations and changes colors to restore red-black */
-/*             properties after a node is deleted */
-/**/
-/*    Modifies Input: this, x */
-/**/
-/*    The algorithm from this function is from _Introduction_To_Algorithms_ */
-/***********************************************************************/
-
-void RedBlackTree::DeleteFixUp(RedBlackTreeNode* x) {
-  RedBlackTreeNode * w;
-  RedBlackTreeNode * rootLeft = root->left;
-
-  while( (!x->red) && (rootLeft != x)) {
-    if (x == x->parent->left) {
-
-//
-      w=x->parent->right;
-      if (w->red) {
-	w->red=0;
-	x->parent->red=1;
-	LeftRotate(x->parent);
-	w=x->parent->right;
-      }
-      if ( (!w->right->red) && (!w->left->red) ) {
-	w->red=1;
-	x=x->parent;
-      } else {
-	if (!w->right->red) {
-	  w->left->red=0;
-	  w->red=1;
-	  RightRotate(w);
-	  w=x->parent->right;
-	}
-	w->red=x->parent->red;
-	x->parent->red=0;
-	w->right->red=0;
-	LeftRotate(x->parent);
-	x=rootLeft; /* this is to exit while loop */
-      }
-//
-
-    } else { /* the code below is has left and right switched from above */
-      w=x->parent->left;
-      if (w->red) {
-	w->red=0;
-	x->parent->red=1;
-	RightRotate(x->parent);
-	w=x->parent->left;
-      }
-      if ( (!w->right->red) && (!w->left->red) ) {
-	w->red=1;
-	x=x->parent;
-      } else {
-	if (!w->left->red) {
-	  w->right->red=0;
-	  w->red=1;
-	  LeftRotate(w);
-	  w=x->parent->left;
-	}
-	w->red=x->parent->red;
-	x->parent->red=0;
-	w->left->red=0;
-	RightRotate(x->parent);
-	x=rootLeft; /* this is to exit while loop */
-      }
-    }
-  }
-  x->red=0;
-
-}
-
-
-/***********************************************************************/
-/*  FUNCTION:  DeleteNode */
-/**/
-/*    INPUTS:  tree is the tree to delete node z from */
-/**/
-/*    OUTPUT:  returns the RedBlackEntry stored at deleted node */
-/**/
-/*    EFFECT:  Deletes z from tree and but don't call destructor */
-/**/
-/*    Modifies Input:  z */
-/**/
-/*    The algorithm from this function is from _Introduction_To_Algorithms_ */
-/***********************************************************************/
-
-RedBlackEntry * RedBlackTree::DeleteNode(RedBlackTreeNode * z){
-  RedBlackTreeNode* y;
-  RedBlackTreeNode* x;
-  RedBlackEntry * returnValue = z->storedEntry;
-
-  y= ((z->left == nil) || (z->right == nil)) ? z : GetSuccessorOf(z);
-  x= (y->left == nil) ? y->right : y->left;
-  if (root == (x->parent = y->parent)) { /* assignment of y->p to x->p is intentional */
-    root->left=x;
-  } else {
-    if (y == y->parent->left) {
-      y->parent->left=x;
-    } else {
-      y->parent->right=x;
-    }
-  }
-  if (y != z) { /* y should not be nil in this case */
-
-    /* y is the node to splice out and x is its child */
-
-    y->left=z->left;
-    y->right=z->right;
-    y->parent=z->parent;
-    z->left->parent=z->right->parent=y;
-    if (z == z->parent->left) {
-      z->parent->left=y;
-    } else {
-      z->parent->right=y;
-    }
-    if (!(y->red)) {
-      y->red = z->red;
-      DeleteFixUp(x);
-    } else
-      y->red = z->red;
-    delete z;
-  } else {
-    if (!(y->red)) DeleteFixUp(x);
-    delete y;
-  }
-  return returnValue;
-}
-
-
-/***********************************************************************/
-/*  FUNCTION:  Enumerate */
-/**/
-/*    INPUTS:  tree is the tree to look for keys between [low,high] */
-/**/
-/*    OUTPUT:  stack containing pointers to the nodes between [low,high] */
-/**/
-/*    Modifies Input: none */
-/**/
-/*    EFFECT:  Returns a stack containing pointers to nodes containing */
-/*             keys which in [low,high]/ */
-/**/
-/***********************************************************************/
-
-TemplateStack<RedBlackTreeNode *> * RedBlackTree::Enumerate(int low,
-							    int high)  {
-  TemplateStack<RedBlackTreeNode *> * enumResultStack =
-    new TemplateStack<RedBlackTreeNode *>(4);
-
-  RedBlackTreeNode* x=root->left;
-  RedBlackTreeNode* lastBest=NULL;
-
-  while(nil != x) {
-    if ( x->key > high ) {
-      x=x->left;
-    } else {
-      lastBest=x;
-      x=x->right;
-    }
-  }
-  while ( (lastBest) && (low <= lastBest->key) ) {
-    enumResultStack->Push(lastBest);
-    lastBest=GetPredecessorOf(lastBest);
-  }
-  return(enumResultStack);
-}

nilmdb/__init__.py

@@ -3,14 +3,10 @@
 from .nilmdb import NilmDB
 from .server import Server
 from .client import Client
-from .timer import Timer
-
-import cmdline
 
 import pyximport; pyximport.install()
 import layout
-
-import serializer
-import timestamper
 import interval
-import du
+
+import cmdline
+

nilmdb/bulkdata.py

@@ -0,0 +1,310 @@
+# Fixed record size bulk data storage
+
+from __future__ import absolute_import
+from __future__ import division
+import nilmdb
+from nilmdb.utils.printf import *
+
+import os
+import sys
+import cPickle as pickle
+import struct
+import fnmatch
+import mmap
+
+# Up to 256 open file descriptors at any given time
+table_cache_size = 16
+fd_cache_size = 16
+
+@nilmdb.utils.must_close()
+class BulkData(object):
+    def __init__(self, basepath):
+        self.basepath = basepath
+        self.root = os.path.join(self.basepath, "data")
+
+        # 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")
+
+        # Get layout, and build format string for struct module
+        try:
+            layout = nilmdb.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',
+                }
+            for n in range(layout.count):
+                struct_fmt += struct_mapping[layout.datatype]
+        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)
+        try:
+            # 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)
+        except OSError as e:
+            raise ValueError("error creating table at that path: " + e.strerror)
+
+        # 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, ospath)
+
+        # Remove the contents of the target directory
+        if not os.path.isfile(os.path.join(ospath, "format")):
+            raise ValueError("nothing at that path")
+        for file in os.listdir(ospath):
+            os.remove(os.path.join(ospath, file))
+
+        # 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()
+class Table(object):
+    """Tools to help access a single table (data at a specific OS path)"""
+
+    # 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):
+        """Initialize a table at the given OS path.
+        'struct_fmt' is a Struct module format description"""
+        format = { "rows_per_file": 4 * 1024 * 1024,
+                   "struct_fmt": struct_fmt }
+        with open(os.path.join(root, "format"), "wb") as f:
+            pickle.dump(format, 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(self._fullpath("format"), "rb") as f:
+            format = pickle.load(f)
+        self.rows_per_file = format["rows_per_file"]
+        self.packer = struct.Struct(format["struct_fmt"])
+        self.file_size = self.packer.size * self.rows_per_file
+
+        # Find nrows by locating the lexicographically last filename
+        # and using its size.
+        pattern = '[0-9a-f]' * 8
+        allfiles = fnmatch.filter(os.listdir(self.root), pattern)
+        if allfiles:
+            filename = max(allfiles)
+            offset = os.path.getsize(self._fullpath(filename))
+            self.nrows = self._row_from_fnoffset(filename, offset)
+        else:
+            self.nrows = 0
+
+    def close(self):
+        self.mmap_open.cache_remove_all()
+
+    # Internal helpers
+    def _fullpath(self, filename):
+        return os.path.join(self.root, filename)
+
+    def _fnoffset_from_row(self, row):
+        """Return a (filename, offset, count) tuple:
+
+        filename: the filename that contains the specified row
+          offset: byte offset of the specified row within the file
+           count: number of rows (starting at offste) that fit in the file
+        """
+        filenum = row // self.rows_per_file
+        filename = sprintf("%08x", filenum)
+        offset = (row % self.rows_per_file) * self.packer.size
+        count = self.rows_per_file - (row % self.rows_per_file)
+        return (filename, offset, count)
+
+    def _row_from_fnoffset(self, filename, offset):
+        """Return the row number that corresponds to the given
+        filename and byte-offset within that file."""
+        filenum = int(filename, 16)
+        if (offset % self.packer.size) != 0:
+            raise ValueError("file offset is not a multiple of data size")
+        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 x: x.close())
+    def mmap_open(self, file, newsize = None):
+        """Open and map a given filename (relative to self.root).
+        Will be automatically closed when evicted from the cache.
+
+        If 'newsize' is provided, the file is truncated to the given
+        size before the mapping is returned.  (Note that the LRU cache
+        on this function means the truncate will only happen if the
+        object isn't already cached; mmap.resize should be used too)"""
+        f = open(os.path.join(self.root, file), "a+", 0)
+        if newsize is not None:
+            # mmap can't map a zero-length file, so this allows the
+            # caller to set the filesize between file creation and
+            # mmap.
+            f.truncate(newsize)
+        mm = mmap.mmap(f.fileno(), 0)
+        return mm
+
+    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
+            (filename, offset, count) = self._fnoffset_from_row(self.nrows)
+            if count > remaining:
+                count = remaining
+            newsize = offset + count * self.packer.size
+            mm = self.mmap_open(filename, newsize)
+            mm.seek(offset)
+
+            # Extend the file to the target length.  We specified
+            # newsize when opening, but that may have been ignored if
+            # the mmap_open returned a cached object.
+            mm.resize(newsize)
+
+            # Write the data
+            for i in xrange(count):
+                row = dataiter.next()
+                mm.write(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:
+                (filename, offset, count) = self._fnoffset_from_row(row)
+                if count > remaining:
+                    count = remaining
+                mm = self.mmap_open(filename)
+                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")
+        (filename, offset, count) = self._fnoffset_from_row(key)
+        mm = self.mmap_open(filename)
+        # unpack_from ignores the mmap object's current seek position
+        return self.packer.unpack_from(mm, offset)
+
+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/bxintersect.pyx

@@ -1,495 +0,0 @@
-# cython: profile=False
-# This is from bx-python 554:07aca5a9f6fc (BSD licensed), modified to
-# store interval ranges as doubles rather than 32-bit integers.
-
-"""
-Data structure for performing intersect queries on a set of intervals which
-preserves all information about the intervals (unlike bitset projection methods).
-
-:Authors: James Taylor (james@jamestaylor.org),
-          Ian Schenk (ian.schenck@gmail.com),
-          Brent Pedersen (bpederse@gmail.com)
-"""
-
-# Historical note:
-#    This module original contained an implementation based on sorted endpoints
-#    and a binary search, using an idea from Scott Schwartz and Piotr Berman.
-#    Later an interval tree implementation was implemented by Ian for Galaxy's
-#    join tool (see `bx.intervals.operations.quicksect.py`). This was then
-#    converted to Cython by Brent, who also added support for
-#    upstream/downstream/neighbor queries. This was modified by James to
-#    handle half-open intervals strictly, to maintain sort order, and to
-#    implement the same interface as the original Intersecter.
-
-#cython: cdivision=True
-
-import operator
-
-cdef extern from "stdlib.h":
-    int ceil(float f)
-    float log(float f)
-    int RAND_MAX
-    int rand()
-    int strlen(char *)
-    int iabs(int)
-
-cdef inline double dmax2(double a, double b):
-    if b > a: return b
-    return a
-
-cdef inline double dmax3(double a, double b, double c):
-    if b > a:
-        if c > b:
-            return c
-        return b
-    if a > c:
-        return a
-    return c
-
-cdef inline double dmin3(double a, double b, double c):
-    if b < a:
-        if c < b:
-            return c
-        return b
-    if a < c:
-        return a
-    return c
-
-cdef inline double dmin2(double a, double b):
-    if b < a: return b
-    return a
-
-cdef float nlog = -1.0 / log(0.5)
-
-cdef class IntervalNode:
-    """
-    A single node of an `IntervalTree`.
-
-    NOTE: Unless you really know what you are doing, you probably should us
-          `IntervalTree` rather than using this directly.
-    """
-    cdef float priority
-    cdef public object interval
-    cdef public double start, end
-    cdef double minend, maxend, minstart
-    cdef IntervalNode cleft, cright, croot
-
-    property left_node:
-        def __get__(self):
-            return self.cleft if self.cleft is not EmptyNode else None
-    property right_node:
-        def __get__(self):
-            return self.cright if self.cright is not EmptyNode else None
-    property root_node:
-        def __get__(self):
-            return self.croot if self.croot is not EmptyNode else None
-
-    def __repr__(self):
-        return "IntervalNode(%g, %g)" % (self.start, self.end)
-
-    def __cinit__(IntervalNode self, double start, double end, object interval):
-        # Python lacks the binomial distribution, so we convert a
-        # uniform into a binomial because it naturally scales with
-        # tree size.  Also, python's uniform is perfect since the
-        # upper limit is not inclusive, which gives us undefined here.
-        self.priority = ceil(nlog * log(-1.0/(1.0 * rand()/RAND_MAX - 1)))
-        self.start    = start
-        self.end      = end
-        self.interval = interval
-        self.maxend   = end
-        self.minstart = start
-        self.minend   = end
-        self.cleft    = EmptyNode
-        self.cright   = EmptyNode
-        self.croot    = EmptyNode
-
-    cpdef IntervalNode insert(IntervalNode self, double start, double end, object interval):
-        """
-        Insert a new IntervalNode into the tree of which this node is
-        currently the root. The return value is the new root of the tree (which
-        may or may not be this node!)
-        """
-        cdef IntervalNode croot = self
-        # If starts are the same, decide which to add interval to based on
-        # end, thus maintaining sortedness relative to start/end
-        cdef double decision_endpoint = start
-        if start == self.start:
-            decision_endpoint = end
-
-        if decision_endpoint > self.start:
-            # insert to cright tree
-            if self.cright is not EmptyNode:
-                self.cright = self.cright.insert( start, end, interval )
-            else:
-                self.cright = IntervalNode( start, end, interval )
-            # rebalance tree
-            if self.priority < self.cright.priority:
-                croot = self.rotate_left()
-        else:
-            # insert to cleft tree
-            if self.cleft is not EmptyNode:
-                self.cleft = self.cleft.insert( start, end, interval)
-            else:
-                self.cleft = IntervalNode( start, end, interval)
-            # rebalance tree
-            if self.priority < self.cleft.priority:
-                croot = self.rotate_right()
-
-        croot.set_ends()
-        self.cleft.croot  = croot
-        self.cright.croot = croot
-        return croot
-
-    cdef IntervalNode rotate_right(IntervalNode self):
-        cdef IntervalNode croot = self.cleft
-        self.cleft  = self.cleft.cright
-        croot.cright = self
-        self.set_ends()
-        return croot
-
-    cdef IntervalNode rotate_left(IntervalNode self):
-        cdef IntervalNode croot = self.cright
-        self.cright = self.cright.cleft
-        croot.cleft  = self
-        self.set_ends()
-        return croot
-
-    cdef inline void set_ends(IntervalNode self):
-        if self.cright is not EmptyNode and self.cleft is not EmptyNode:
-            self.maxend = dmax3(self.end, self.cright.maxend, self.cleft.maxend)
-            self.minend = dmin3(self.end, self.cright.minend, self.cleft.minend)
-            self.minstart = dmin3(self.start, self.cright.minstart, self.cleft.minstart)
-        elif self.cright is not EmptyNode:
-            self.maxend = dmax2(self.end, self.cright.maxend)
-            self.minend = dmin2(self.end, self.cright.minend)
-            self.minstart = dmin2(self.start, self.cright.minstart)
-        elif self.cleft is not EmptyNode:
-            self.maxend = dmax2(self.end, self.cleft.maxend)
-            self.minend = dmin2(self.end, self.cleft.minend)
-            self.minstart = dmin2(self.start, self.cleft.minstart)
-
-
-    def intersect( self, double start, double end, sort=True ):
-        """
-        given a start and a end, return a list of features
-        falling within that range
-        """
-        cdef list results = []
-        self._intersect( start, end, results )
-        if sort:
-            results = sorted(results)
-        return results
-
-    find = intersect
-
-    cdef void _intersect( IntervalNode self, double start, double end, list results):
-        # Left subtree
-        if self.cleft is not EmptyNode and self.cleft.maxend > start:
-            self.cleft._intersect( start, end, results )
-        # This interval
-        if ( self.end > start ) and ( self.start < end ):
-            results.append( self.interval )
-        # Right subtree
-        if self.cright is not EmptyNode and self.start < end:
-            self.cright._intersect( start, end, results )
-
-
-    cdef void _seek_left(IntervalNode self, double position, list results, int n, double max_dist):
-        # we know we can bail in these 2 cases.
-        if self.maxend + max_dist < position:
-            return
-        if self.minstart > position:
-            return
-
-        # the ordering of these 3 blocks makes it so the results are
-        # ordered nearest to farest from the query position
-        if self.cright is not EmptyNode:
-            self.cright._seek_left(position, results, n, max_dist)
-
-        if -1 < position - self.end < max_dist:
-            results.append(self.interval)
-
-        # TODO: can these conditionals be more stringent?
-        if self.cleft is not EmptyNode:
-                self.cleft._seek_left(position, results, n, max_dist)
-
-
-
-    cdef void _seek_right(IntervalNode self, double position, list results, int n, double max_dist):
-        # we know we can bail in these 2 cases.
-        if self.maxend < position: return
-        if self.minstart - max_dist > position: return
-
-        #print "SEEK_RIGHT:",self, self.cleft, self.maxend, self.minstart, position
-
-        # the ordering of these 3 blocks makes it so the results are
-        # ordered nearest to farest from the query position
-        if self.cleft is not EmptyNode:
-                self.cleft._seek_right(position, results, n, max_dist)
-
-        if -1 < self.start - position < max_dist:
-            results.append(self.interval)
-
-        if self.cright is not EmptyNode:
-                self.cright._seek_right(position, results, n, max_dist)
-
-
-    cpdef left(self, position, int n=1, double max_dist=2500):
-        """
-        find n features with a start > than `position`
-        f: a Interval object (or anything with an `end` attribute)
-        n: the number of features to return
-        max_dist: the maximum distance to look before giving up.
-        """
-        cdef list results = []
-        # use start - 1 becuase .left() assumes strictly left-of
-        self._seek_left( position - 1, results, n, max_dist )
-        if len(results) == n: return results
-        r = results
-        r.sort(key=operator.attrgetter('end'), reverse=True)
-        return r[:n]
-
-    cpdef right(self, position, int n=1, double max_dist=2500):
-        """
-        find n features with a end < than position
-        f: a Interval object (or anything with a `start` attribute)
-        n: the number of features to return
-        max_dist: the maximum distance to look before giving up.
-        """
-        cdef list results = []
-        # use end + 1 becuase .right() assumes strictly right-of
-        self._seek_right(position + 1, results, n, max_dist)
-        if len(results) == n: return results
-        r = results
-        r.sort(key=operator.attrgetter('start'))
-        return r[:n]
-
-    def traverse(self):
-        if self.cleft is not EmptyNode:
-            for node in self.cleft.traverse():
-                yield node
-        yield self.interval
-        if self.cright is not EmptyNode:
-            for node in self.cright.traverse():
-                yield node
-
-cdef IntervalNode EmptyNode = IntervalNode( 0, 0, Interval(0, 0))
-
-## ---- Wrappers that retain the old interface -------------------------------
-
-cdef class Interval:
-    """
-    Basic feature, with required integer start and end properties.
-    Also accepts optional strand as +1 or -1 (used for up/downstream queries),
-    a name, and any arbitrary data is sent in on the info keyword argument
-
-    >>> from bx.intervals.intersection import Interval
-
-    >>> f1 = Interval(23, 36)
-    >>> f2 = Interval(34, 48, value={'chr':12, 'anno':'transposon'})
-    >>> f2
-    Interval(34, 48, value={'anno': 'transposon', 'chr': 12})
-
-    """
-    cdef public double start, end
-    cdef public object value, chrom, strand
-
-    def __init__(self, double start, double end, object value=None, object chrom=None, object strand=None ):
-        assert start <= end, "start must be less than end"
-        self.start  = start
-        self.end   = end
-        self.value = value
-        self.chrom = chrom
-        self.strand = strand
-
-    def __repr__(self):
-        fstr = "Interval(%g, %g" % (self.start, self.end)
-        if not self.value is None:
-            fstr += ", value=" + str(self.value)
-        fstr += ")"
-        return fstr
-
-    def __richcmp__(self, other, op):
-        if op == 0:
-            # <
-            return self.start < other.start or self.end < other.end
-        elif op == 1:
-            # <=
-            return self == other or self < other
-        elif op == 2:
-            # ==
-            return self.start == other.start and self.end == other.end
-        elif op == 3:
-            # !=
-            return self.start != other.start or self.end != other.end
-        elif op == 4:
-            # >
-            return self.start > other.start or self.end > other.end
-        elif op == 5:
-            # >=
-            return self == other or self > other
-
-cdef class IntervalTree:
-    """
-    Data structure for performing window intersect queries on a set of
-    of possibly overlapping 1d intervals.
-
-    Usage
-    =====
-
-    Create an empty IntervalTree
-
-    >>> from bx.intervals.intersection import Interval, IntervalTree
-    >>> intersecter = IntervalTree()
-
-    An interval is a start and end position and a value (possibly None).
-    You can add any object as an interval:
-
-    >>> intersecter.insert( 0, 10, "food" )
-    >>> intersecter.insert( 3, 7, dict(foo='bar') )
-
-    >>> intersecter.find( 2, 5 )
-    ['food', {'foo': 'bar'}]
-
-    If the object has start and end attributes (like the Interval class) there
-    is are some shortcuts:
-
-    >>> intersecter = IntervalTree()
-    >>> intersecter.insert_interval( Interval( 0, 10 ) )
-    >>> intersecter.insert_interval( Interval( 3, 7 ) )
-    >>> intersecter.insert_interval( Interval( 3, 40 ) )
-    >>> intersecter.insert_interval( Interval( 13, 50 ) )
-
-    >>> intersecter.find( 30, 50 )
-    [Interval(3, 40), Interval(13, 50)]
-    >>> intersecter.find( 100, 200 )
-    []
-
-    Before/after for intervals
-
-    >>> intersecter.before_interval( Interval( 10, 20 ) )
-    [Interval(3, 7)]
-    >>> intersecter.before_interval( Interval( 5, 20 ) )
-    []
-
-    Upstream/downstream
-
-    >>> intersecter.upstream_of_interval(Interval(11, 12))
-    [Interval(0, 10)]
-    >>> intersecter.upstream_of_interval(Interval(11, 12, strand="-"))
-    [Interval(13, 50)]
-
-    >>> intersecter.upstream_of_interval(Interval(1, 2, strand="-"), num_intervals=3)
-    [Interval(3, 7), Interval(3, 40), Interval(13, 50)]
-
-
-    """
-
-    cdef IntervalNode root
-
-    def __cinit__( self ):
-        root = None
-
-    # ---- Position based interfaces -----------------------------------------
-
-    def insert( self, double start, double end, object value=None ):
-        """
-        Insert the interval [start,end) associated with value `value`.
-        """
-        if self.root is None:
-            self.root = IntervalNode( start, end, value )
-        else:
-            self.root = self.root.insert( start, end, value )
-
-    add = insert
-
-
-    def find( self, start, end ):
-        """
-        Return a sorted list of all intervals overlapping [start,end).
-        """
-        if self.root is None:
-            return []
-        return self.root.find( start, end )
-
-    def before( self, position, num_intervals=1, max_dist=2500 ):
-        """
-        Find `num_intervals` intervals that lie before `position` and are no
-        further than `max_dist` positions away
-        """
-        if self.root is None:
-            return []
-        return self.root.left( position, num_intervals, max_dist )
-
-    def after( self, position, num_intervals=1, max_dist=2500 ):
-        """
-        Find `num_intervals` intervals that lie after `position` and are no
-        further than `max_dist` positions away
-        """
-        if self.root is None:
-            return []
-        return self.root.right( position, num_intervals, max_dist )
-
-    # ---- Interval-like object based interfaces -----------------------------
-
-    def insert_interval( self, interval ):
-        """
-        Insert an "interval" like object (one with at least start and end
-        attributes)
-        """
-        self.insert( interval.start, interval.end, interval )
-
-    add_interval = insert_interval
-
-    def before_interval( self, interval, num_intervals=1, max_dist=2500 ):
-        """
-        Find `num_intervals` intervals that lie completely before `interval`
-        and are no further than `max_dist` positions away
-        """
-        if self.root is None:
-            return []
-        return self.root.left( interval.start, num_intervals, max_dist )
-
-    def after_interval( self, interval, num_intervals=1, max_dist=2500 ):
-        """
-        Find `num_intervals` intervals that lie completely after `interval` and
-        are no further than `max_dist` positions away
-        """
-        if self.root is None:
-            return []
-        return self.root.right( interval.end, num_intervals, max_dist )
-
-    def upstream_of_interval( self, interval, num_intervals=1, max_dist=2500 ):
-        """
-        Find `num_intervals` intervals that lie completely upstream of
-        `interval` and are no further than `max_dist` positions away
-        """
-        if self.root is None:
-            return []
-        if interval.strand == -1 or interval.strand == "-":
-            return self.root.right( interval.end, num_intervals, max_dist )
-        else:
-            return self.root.left( interval.start, num_intervals, max_dist )
-
-    def downstream_of_interval( self, interval, num_intervals=1, max_dist=2500 ):
-        """
-        Find `num_intervals` intervals that lie completely downstream of
-        `interval` and are no further than `max_dist` positions away
-        """
-        if self.root is None:
-            return []
-        if interval.strand == -1 or interval.strand == "-":
-            return self.root.left( interval.start, num_intervals, max_dist )
-        else:
-            return self.root.right( interval.end, num_intervals, max_dist )
-
-    def traverse(self):
-        """
-        iterator that traverses the tree
-        """
-        if self.root is None:
-            return iter([])
-        return self.root.traverse()
-
-# For backward compatibility
-Intersecter = IntervalTree

nilmdb/client.py

@@ -1,13 +1,16 @@
+# -*- coding: utf-8 -*-
+
 """Class for performing HTTP client requests via libcurl"""
 
 from __future__ import absolute_import
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 
 import time
 import sys
 import re
 import os
 import simplejson as json
+import itertools
 
 import nilmdb.httpclient
 
@@ -16,6 +19,10 @@ from nilmdb.httpclient import ClientError, ServerError, Error
 
 version = "1.0"
 
+def float_to_string(f):
+    # Use repr to maintain full precision in the string output.
+    return repr(float(f))
+
 class Client(object):
     """Main client interface to the Nilm database."""
 
@@ -84,33 +91,82 @@ class Client(object):
                    "layout" : layout }
         return self.http.get("stream/create", params)
 
-    def stream_insert(self, path, data):
+    def stream_destroy(self, path):
+        """Delete stream and its contents"""
+        params = { "path": path }
+        return self.http.get("stream/destroy", params)
+
+    def stream_insert(self, path, data, start = None, end = None):
         """Insert data into a stream.  data should be a file-like object
-        that provides ASCII data that matches the database layout for path."""
+        that provides ASCII data that matches the database layout for path.
+
+        start and end are the starting and ending timestamp of this
+        stream; all timestamps t in the data must satisfy 'start <= t
+        < end'.  If left unspecified, 'start' is the timestamp of the
+        first line of data, and 'end' is the timestamp on the last line
+        of data, plus a small delta of 1μs.
+        """
         params = { "path": path }
 
         # See design.md for a discussion of how much data to send.
         # These are soft limits -- actual data might be rounded up.
         max_data = 1048576
         max_time = 30
+        end_epsilon = 1e-6
+
+        def pairwise(iterable):
+            "s -> (s0,s1), (s1,s2), ..., (sn,None)"
+            a, b = itertools.tee(iterable)
+            next(b, None)
+            return itertools.izip_longest(a, b)
+
+        def extract_timestamp(line):
+            return float(line.split()[0])
 
         def sendit():
-            result = self.http.put("stream/insert", send_data, params)
-            params["old_timestamp"] = result[1]
-            return result
+            # If we have more data after this, use the timestamp of
+            # the next line as the end.  Otherwise, use the given
+            # overall end time, or add end_epsilon to the last data
+            # point.
+            if nextline:
+                block_end = extract_timestamp(nextline)
+                if end and block_end > end:
+                    # This is unexpected, but we'll defer to the server
+                    # to return an error in this case.
+                    block_end = end
+            elif end:
+                block_end = end
+            else:
+                block_end = extract_timestamp(line) + end_epsilon
 
+            # Send it
+            params["start"] = float_to_string(block_start)
+            params["end"] = float_to_string(block_end)
+            return self.http.put("stream/insert", block_data, params)
+
+        clock_start = time.time()
+        block_data = ""
+        block_start = start
         result = None
-        start = time.time()
-        send_data = ""
-        for line in data:
-            elapsed = time.time() - start
-            send_data += line
+        for (line, nextline) in pairwise(data):
+            # If we don't have a starting time, extract it from the first line
+            if block_start is None:
+                block_start = extract_timestamp(line)
 
-            if (len(send_data) > max_data) or (elapsed > max_time):
+            clock_elapsed = time.time() - clock_start
+            block_data += line
+
+            # If we have enough data, or enough time has elapsed,
+            # send this block to the server, and empty things out
+            # for the next block.
+            if (len(block_data) > max_data) or (clock_elapsed > max_time):
                 result = sendit()
-                send_data = ""
-                start = time.time()
-        if len(send_data):
+                block_start = None
+                block_data = ""
+                clock_start = time.time()
+
+        # One last block?
+        if len(block_data):
             result = sendit()
 
         # Return the most recent JSON result we got back, or None if
@@ -125,9 +181,9 @@ class Client(object):
             "path": path
         }
         if start is not None:
-            params["start"] = repr(start)  # use repr to keep precision
+            params["start"] = float_to_string(start)
         if end is not None:
-            params["end"] = repr(end)
+            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):
@@ -143,9 +199,9 @@ class Client(object):
             "path": path,
         }
         if start is not None:
-            params["start"] = repr(start)  # use repr to keep precision
+            params["start"] = float_to_string(start)
         if end is not None:
-            params["end"] = repr(end)
+            params["end"] = float_to_string(end)
         if count:
             params["count"] = 1
 

nilmdb/cmdline/cmdline.py

@@ -1,7 +1,7 @@
 """Command line client functionality"""
 
 from __future__ import absolute_import
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 import nilmdb.client
 
 import datetime_tz
@@ -15,7 +15,8 @@ version = "0.1"
 
 # 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" ]
+subcommands = [ "info", "create", "list", "metadata", "insert", "extract",
+                "destroy" ]
 
 # Import the subcommand modules.  Equivalent way of doing this would be
 # from . import info as cmd_info

nilmdb/cmdline/create.py

@@ -1,5 +1,5 @@
 from __future__ import absolute_import
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 import nilmdb.client
 
 from argparse import ArgumentDefaultsHelpFormatter as def_form

nilmdb/cmdline/destroy.py

@@ -0,0 +1,25 @@
+from __future__ import absolute_import
+from nilmdb.utils.printf import *
+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 deleting stream: %s", str(e))

nilmdb/cmdline/extract.py

@@ -1,7 +1,7 @@
 from __future__ import absolute_import
-from nilmdb.printf import *
+from __future__ import print_function
+from nilmdb.utils.printf import *
 import nilmdb.client
-import nilmdb.layout
 import sys
 
 def setup(self, sub):
@@ -51,7 +51,7 @@ def cmd_extract(self):
             # Strip timestamp (first element).  Doesn't make sense
             # if we are only returning a count.
             dataline = ' '.join(dataline.split(' ')[1:])
-        print dataline
+        print(dataline)
         printed = True
     if not printed:
         if self.args.annotate:

nilmdb/cmdline/info.py

@@ -1,5 +1,5 @@
 from __future__ import absolute_import
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 
 from argparse import ArgumentDefaultsHelpFormatter as def_form
 

nilmdb/cmdline/insert.py

@@ -1,7 +1,6 @@
 from __future__ import absolute_import
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 import nilmdb.client
-import nilmdb.layout
 import nilmdb.timestamper
 
 import sys

nilmdb/cmdline/list.py

@@ -1,5 +1,5 @@
 from __future__ import absolute_import
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 import nilmdb.client
 
 import fnmatch

nilmdb/cmdline/metadata.py

@@ -1,5 +1,5 @@
 from __future__ import absolute_import
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 import nilmdb.client
 
 def setup(self, sub):

nilmdb/httpclient.py

@@ -1,7 +1,8 @@
 """HTTP client library"""
 
 from __future__ import absolute_import
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
+import nilmdb.utils
 
 import time
 import sys
@@ -9,12 +10,9 @@ import re
 import os
 import simplejson as json
 import urlparse
-import urllib
 import pycurl
 import cStringIO
 
-import nilmdb.iteratorizer
-
 class Error(Exception):
     """Base exception for both ClientError and ServerError responses"""
     def __init__(self,
@@ -60,7 +58,8 @@ class HTTPClient(object):
     def _setup_url(self, url = "", params = ""):
         url = urlparse.urljoin(self.baseurl, url)
         if params:
-            url = urlparse.urljoin(url, "?" + urllib.urlencode(params, True))
+            url = urlparse.urljoin(
+                url, "?" + nilmdb.utils.urllib.urlencode(params, True))
         self.curl.setopt(pycurl.URL, url)
         self.url = url
 
@@ -85,6 +84,10 @@ class HTTPClient(object):
             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)
@@ -109,7 +112,7 @@ class HTTPClient(object):
             self.curl.setopt(pycurl.WRITEFUNCTION, callback)
             self.curl.perform()
         try:
-            for i in nilmdb.iteratorizer.Iteratorizer(func):
+            for i in nilmdb.utils.Iteratorizer(func):
                 if self._status == 200:
                     # If we had a 200 response, yield the data to the caller.
                     yield i

nilmdb/interval.pyx

@@ -1,8 +1,9 @@
-"""Interval and IntervalSet
+"""Interval, IntervalSet
 
 Represents an interval of time, and a set of such intervals.
 
-Intervals are closed, ie. they include timestamps [start, end]
+Intervals are half-open, ie. they include data points with timestamps
+[start, end)
 """
 
 # First implementation kept a sorted list of intervals and used
@@ -18,16 +19,20 @@ Intervals are closed, ie. they include timestamps [start, end]
 # Fourth version is an optimized rb-tree that stores interval starts
 # and ends directly in the tree, like bxinterval did.
 
-import rbtree
+cimport rbtree
+cdef extern from "stdint.h":
+    ctypedef unsigned long long uint64_t
 
 class IntervalError(Exception):
     """Error due to interval overlap, etc"""
     pass
 
-class Interval(object):
+cdef class Interval:
     """Represents an interval of time."""
 
-    def __init__(self, start, end):
+    cdef public double start, end
+
+    def __init__(self, double start, double end):
         """
         'start' and 'end' are arbitrary floats that represent time
         """
@@ -41,9 +46,9 @@ class Interval(object):
         return self.__class__.__name__ + "(" + s + ")"
 
     def __str__(self):
-        return "[" + str(self.start) + " -> " + str(self.end) + "]"
+        return "[" + repr(self.start) + " -> " + repr(self.end) + ")"
 
-    def __cmp__(self, other):
+    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")
@@ -57,20 +62,20 @@ class Interval(object):
             return -1
         return 1
 
-    def intersects(self, other):
+    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
 
-    def subset(self, start, end):
+    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)
 
-class DBInterval(Interval):
+cdef class DBInterval(Interval):
     """
     Like Interval, but also tracks corresponding start/end times and
     positions within the database.  These are not currently modified
@@ -85,6 +90,9 @@ class DBInterval(Interval):
         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):
@@ -109,7 +117,7 @@ class DBInterval(Interval):
         s += ", " + repr(self.db_startpos) + ", " + repr(self.db_endpos)
         return self.__class__.__name__ + "(" + s + ")"
 
-    def subset(self, start, end):
+    cpdef subset(self, double start, double end):
         """
         Return a new DBInterval that is a subset of this one
         """
@@ -119,11 +127,13 @@ class DBInterval(Interval):
                           self.db_start, self.db_end,
                           self.db_startpos, self.db_endpos)
 
-class IntervalSet(object):
+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.
@@ -148,7 +158,7 @@ class IntervalSet(object):
         descs = [ str(x) for x in self ]
         return  "[" + ", ".join(descs) + "]"
 
-    def __eq__(self, other):
+    def __match__(self, other):
         # This isn't particularly efficient, but it shouldn't get used in the
         # general case.
         """Test equality of two IntervalSets.
@@ -167,8 +177,8 @@ class IntervalSet(object):
             else:
                 return False
 
-        this = [ x for x in self ]
-        that = [ x for x in other ]
+        this = list(self)
+        that = list(other)
 
         try:
             while True:
@@ -199,10 +209,20 @@ class IntervalSet(object):
         except IndexError:
             return False
 
-    def __ne__(self, other):
-        return not self.__eq__(other)
+    # 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, other):
+    def __iadd__(self, object other not None):
         """Inplace add -- modifies self
 
         This throws an exception if the regions being added intersect."""
@@ -210,13 +230,19 @@ class IntervalSet(object):
             if self.intersects(other):
                 raise IntervalError("Tried to add overlapping interval "
                                     "to this set")
-            self.tree.insert(rbtree.RBNode(other))
+            self.tree.insert(rbtree.RBNode(other.start, other.end, other))
         else:
             for x in other:
                 self.__iadd__(x)
         return self
 
-    def __isub__(self, other):
+    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
@@ -227,13 +253,13 @@ class IntervalSet(object):
         self.tree.delete(i)
         return self
 
-    def __add__(self, other):
+    def __add__(self, other not None):
         """Add -- returns a new object"""
         new = IntervalSet(self)
         new += IntervalSet(other)
         return new
 
-    def __and__(self, other):
+    def __and__(self, other not None):
         """
         Compute a new IntervalSet from the intersection of two others
 
@@ -244,15 +270,15 @@ class IntervalSet(object):
 
         if not isinstance(other, IntervalSet):
             for i in self.intersection(other):
-                out.tree.insert(rbtree.RBNode(i))
+                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))
+                    out.tree.insert(rbtree.RBNode(i.start, i.end, i))
 
         return out
 
-    def intersection(self, interval):
+    def intersection(self, Interval interval not None):
         """
         Compute a sequence of intervals that correspond to the
         intersection between `self` and the provided interval.
@@ -269,23 +295,24 @@ class IntervalSet(object):
             if i:
                 if i.start >= interval.start and i.end <= interval.end:
                     yield i
-                elif i.start > interval.end:
-                    break
                 else:
                     subset = i.subset(max(i.start, interval.start),
                                       min(i.end, interval.end))
                     yield subset
 
-    def intersects(self, other):
-        ### PROBABLY WRONG
+    cpdef intersects(self, Interval other):
         """Return True if this IntervalSet intersects another interval"""
-        node = self.tree.find_left(other.start, other.end)
-        if node is None:
-            return False
-        for n in self.tree.inorder(node):
-            if n.obj:
-                if n.obj.intersects(other):
-                    return True
-                if n.obj > other:
-                    break
+        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/interval.pyxdep

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

nilmdb/layout.pyx

@@ -1,6 +1,5 @@
 # cython: profile=False
 
-import tables
 import time
 import sys
 import inspect
@@ -122,15 +121,6 @@ class Layout:
             s += " %d" % d[i+1]
         return s + "\n"
 
-    # PyTables description
-    def description(self):
-        """Return the PyTables description of this layout"""
-        desc = {}
-        desc['timestamp'] = tables.Col.from_type('float64', pos=0)
-        for n in range(self.count):
-            desc['c' + str(n+1)] = tables.Col.from_type(self.datatype, pos=n+1)
-        return tables.Description(desc)
-
 # Get a layout by name
 def get_named(typestring):
     try:

nilmdb/nilmdb.py

@@ -4,17 +4,16 @@
 
 Object that represents a NILM database file.
 
-Manages both the SQL database and the PyTables storage backend.
+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 nilmdb module instead.
 from __future__ import absolute_import
 import nilmdb
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 
 import sqlite3
-import tables
 import time
 import sys
 import os
@@ -25,6 +24,8 @@ import pyximport
 pyximport.install()
 from nilmdb.interval import Interval, DBInterval, IntervalSet, IntervalError
 
+from . import bulkdata
+
 # Note about performance and transactions:
 #
 # Committing a transaction in the default sync mode (PRAGMA synchronous=FULL)
@@ -87,19 +88,13 @@ class StreamError(NilmDBError):
 class OverlapError(NilmDBError):
     pass
 
-# Helper that lets us pass a Pytables table into bisect
-class BisectableTable(object):
-    def __init__(self, table):
-        self.table = table
-    def __getitem__(self, index):
-        return self.table[index][0]
-
+@nilmdb.utils.must_close()
 class NilmDB(object):
     verbose = 0
 
     def __init__(self, basepath, sync=True, max_results=None):
         # set up path
-        self.basepath = os.path.abspath(basepath.rstrip('/'))
+        self.basepath = os.path.abspath(basepath)
 
         # Create the database path if it doesn't exist
         try:
@@ -108,16 +103,16 @@ class NilmDB(object):
             if e.errno != errno.EEXIST:
                 raise IOError("can't create tree " + self.basepath)
 
-        # Our HD5 file goes inside it
-        h5filename = os.path.abspath(self.basepath + "/data.h5")
-        self.h5file = tables.openFile(h5filename, "a", "NILM Database")
+        # Our data goes inside it
+        self.data = bulkdata.BulkData(self.basepath)
 
         # SQLite database too
-        sqlfilename = os.path.abspath(self.basepath + "/data.sql")
+        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.  That requirement
-        # may be relaxed later.
+        # 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()
 
@@ -134,17 +129,6 @@ class NilmDB(object):
         else:
             self.max_results = 16384
 
-        self.opened = True
-
-        # Cached intervals
-        self._cached_iset = {}
-
-    def __del__(self):
-        if "opened" in self.__dict__: # pragma: no cover
-            fprintf(sys.stderr,
-                    "error: NilmDB.close() wasn't called, path %s",
-                    self.basepath)
-
     def get_basepath(self):
         return self.basepath
 
@@ -152,8 +136,7 @@ class NilmDB(object):
         if self.con:
             self.con.commit()
             self.con.close()
-        self.h5file.close()
-        del self.opened
+        self.data.close()
 
     def _sql_schema_update(self):
         cur = self.con.cursor()
@@ -170,58 +153,78 @@ class NilmDB(object):
             with self.con:
                 cur.execute("PRAGMA user_version = {v:d}".format(v=version))
 
+    @nilmdb.utils.lru_cache(size = 16)
     def _get_intervals(self, stream_id):
         """
         Return a mutable IntervalSet corresponding to the given stream ID.
         """
-        # Load from database if not cached
-        if stream_id not in self._cached_iset:
-            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 as e: # pragma: no cover
-                raise NilmDBError("unexpected overlap in ranges table!")
-            self._cached_iset[stream_id] = iset
-        # Return cached value
-        return self._cached_iset[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 as e: # pragma: no cover
+            raise NilmDBError("unexpected overlap in ranges table!")
 
-    # TODO: Split add_interval into two pieces, one to add
-    # and one to flush to disk?
-    # Need to think about this.  Basic problem is that we can't
-    # mess with intervals once they're in the IntervalSet,
-    # without mucking with bxinterval internals.
-
-    # Maybe add a separate optimization step?
-    # Join intervals that have a fairly small gap between them
+        return iset
 
     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)
         """
-        # Ensure this stream's intervals are cached, and add the new
-        # interval to that cache.
+        # Load this stream's intervals
         iset = self._get_intervals(stream_id)
-        try:
-            iset += DBInterval(interval.start, interval.end,
-                               interval.start, interval.end,
-                               start_pos, end_pos)
-        except IntervalError as e: # pragma: no cover
+
+        # 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 = 30000000 # a bit more than 1 hour 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.con.execute("DELETE FROM ranges WHERE "
+                             "stream_id=? AND start_time=? AND "
+                             "end_time=? AND start_pos=? AND "
+                             "end_pos=?", (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.con.execute("INSERT INTO ranges "
                          "(stream_id,start_time,end_time,start_pos,end_pos) "
                          "VALUES (?,?,?,?,?)",
                          (stream_id, interval.start, interval.end,
                           int(start_pos), int(end_pos)))
+
         self.con.commit()
 
     def stream_list(self, path = None, layout = None):
@@ -285,38 +288,11 @@ class NilmDB(object):
 
         layout_name: string for nilmdb.layout.get_named(), e.g. 'float32_8'
         """
-        if path[0] != '/':
-            raise ValueError("paths must start with /")
-        [ group, node ] = path.rsplit("/", 1)
-        if group == '':
-            raise ValueError("invalid path")
+        # Create the bulk storage.  Raises ValueError on error, which we
+        # pass along.
+        self.data.create(path, layout_name)
 
-        # Make the group structure, one element at a time
-        group_path = group.lstrip('/').split("/")
-        for i in range(len(group_path)):
-            parent = "/" + "/".join(group_path[0:i])
-            child = group_path[i]
-            try:
-                self.h5file.createGroup(parent, child)
-            except tables.NodeError:
-                pass
-
-        # Get description
-        try:
-            desc = nilmdb.layout.get_named(layout_name).description()
-        except KeyError:
-            raise ValueError("no such layout")
-
-        # Estimated table size (for PyTables optimization purposes): assume
-        # 3 months worth of data at 8 KHz.  It's OK if this is wrong.
-        exp_rows = 8000 * 60*60*24*30*3
-
-        # Create the table
-        table = self.h5file.createTable(group, node,
-                                        description = desc,
-                                        expectedrows = exp_rows)
-
-        # Insert into SQL database once the PyTables is happy
+        # 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))
@@ -337,8 +313,7 @@ class NilmDB(object):
            """
         stream_id = self._stream_id(path)
         with self.con as con:
-            con.execute("DELETE FROM metadata "
-                        "WHERE stream_id=?", (stream_id,))
+            con.execute("DELETE FROM metadata WHERE stream_id=?", (stream_id,))
             for key in data:
                 if data[key] != '':
                     con.execute("INSERT INTO metadata VALUES (?, ?, ?)",
@@ -361,44 +336,47 @@ class NilmDB(object):
         data.update(newdata)
         self.stream_set_metadata(path, data)
 
-    def stream_insert(self, path, parser, old_timestamp = None):
+    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
+        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
-           parser: nilmdb.layout.Parser instance full of data to insert
+           start: Starting timestamp
+           end: Ending timestamp
+           data: Rows of data, to be passed to PyTable's table.append
+                 method.  E.g. nilmdb.layout.Parser.data
            """
-        if (not parser.min_timestamp or not parser.max_timestamp or
-            not len(parser.data)):
-            raise StreamError("no data provided")
-
-        # If we were provided with an old timestamp, the expectation
-        # is that the client has a contiguous block of time it is sending,
-        # but it's doing it over multiple calls to stream_insert.
-        # old_timestamp is the max_timestamp of the previous insert.
-        # To make things continuous, use that as our starting timestamp
-        # instead of what the parser found.
-        if old_timestamp:
-            min_timestamp = old_timestamp
-        else:
-            min_timestamp = parser.min_timestamp
-
         # First check for basic overlap using timestamp info given.
         stream_id = self._stream_id(path)
         iset = self._get_intervals(stream_id)
-        interval = Interval(min_timestamp, parser.max_timestamp)
+        interval = Interval(start, end)
         if iset.intersects(interval):
-            raise OverlapError("new data overlaps existing data: "
+            raise OverlapError("new data overlaps existing data at range: "
                                + str(iset & interval))
 
-        # Insert the data into pytables
-        table = self.h5file.getNode(path)
+        # Insert the data
+        table = self.data.getnode(path)
         row_start = table.nrows
-        table.append(parser.data)
+        table.append(data)
         row_end = table.nrows
-        table.flush()
 
         # Insert the record into the sql database.
-        # Casts are to convert from numpy.int64.
-        self._add_interval(stream_id, interval, int(row_start), int(row_end))
+        self._add_interval(stream_id, interval, row_start, row_end)
 
         # And that's all
         return "ok"
@@ -413,7 +391,7 @@ class NilmDB(object):
         # Optimization for the common case where an interval wasn't truncated
         if interval.start == interval.db_start:
             return interval.db_startpos
-        return bisect.bisect_left(BisectableTable(table),
+        return bisect.bisect_left(bulkdata.TimestampOnlyTable(table),
                                   interval.start,
                                   interval.db_startpos,
                                   interval.db_endpos)
@@ -432,7 +410,7 @@ class NilmDB(object):
         # 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(BisectableTable(table),
+        return bisect.bisect_left(bulkdata.TimestampOnlyTable(table),
                                   interval.end,
                                   interval.db_startpos,
                                   interval.db_endpos)
@@ -456,7 +434,7 @@ class NilmDB(object):
         than actually fetching the data.  It is not limited by
         max_results.
         """
-        table = self.h5file.getNode(path)
+        table = self.data.getnode(path)
         stream_id = self._stream_id(path)
         intervals = self._get_intervals(stream_id)
         requested = Interval(start or 0, end or 1e12)

nilmdb/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/rbtree.pyx

@@ -1,20 +1,27 @@
-"""Red-black tree, where keys are stored as start/end timestamps."""
+# 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
 
-class RBNode(object):
-    """One node of the Red/Black tree.  obj points to any object,
-    'start' and 'end' are timestamps that represent the key."""
-    def __init__(self, obj = None, start = None, end = None):
-        """If given an object but no start/end times, get the
-        start/end times from the object.
-
-        If given start/end times, obj can be anything, including None."""
+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
-        if start is None:
-            start = obj.start
-        if end is None:
-            end = obj.end
         self.start = start
         self.end = end
         self.red = False
@@ -26,21 +33,23 @@ class RBNode(object):
             color = "R"
         else:
             color = "B"
-        return ("[node "
+        if self.start == sys.float_info.min:
+            return "[node nil]"
+        return ("[node ("
+                + str(self.obj) + ") "
                 + str(self.start) + " -> " + str(self.end) + " "
                 + color + "]")
 
-class RBTree(object):
+cdef class RBTree:
     """Red/Black tree"""
 
     # Init
     def __init__(self):
         self.nil = RBNode(start = sys.float_info.min,
-                           end = 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.nil.nil = True
 
         self.root = RBNode(start = sys.float_info.max,
                            end = sys.float_info.max)
@@ -48,9 +57,21 @@ class RBTree(object):
         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
-    def __rotate_left(self, x):
-        y = x.right
+    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
@@ -62,8 +83,15 @@ class RBTree(object):
         y.left = x
         x.parent = y
 
-    def __rotate_right(self, y):
-        x = y.left
+    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
@@ -75,9 +103,9 @@ class RBTree(object):
         x.right = y
         y.parent = x
 
-    def __successor(self, x):
+    cdef RBNode __successor(self, RBNode x):
         """Returns the successor of RBNode x"""
-        y = x.right
+        cdef RBNode y = x.right
         if y is not self.nil:
             while y.left is not self.nil:
                 y = y.left
@@ -89,10 +117,14 @@ class RBTree(object):
             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
 
-    def _predecessor(self, x):
+    cdef RBNode __predecessor(self, RBNode x):
         """Returns the predecessor of RBNode x"""
-        y = x.left
+        cdef RBNode y = x.left
         if y is not self.nil:
             while y.right is not self.nil:
                 y = y.right
@@ -105,14 +137,18 @@ class RBTree(object):
                 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
-    def insert(self, z):
+    cpdef insert(self, RBNode z):
         """Insert RBNode z into RBTree and rebalance as necessary"""
         z.left = self.nil
         z.right = self.nil
-        y = self.root
-        x = self.root.left
+        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)):
@@ -128,7 +164,7 @@ class RBTree(object):
         # relabel/rebalance
         self.__insert_fixup(z)
 
-    def __insert_fixup(self, x):
+    cdef void __insert_fixup(self, RBNode x):
         """Rebalance/fix RBTree after a simple insertion of RBNode x"""
         x.red = True
         while x.parent.red:
@@ -163,10 +199,11 @@ class RBTree(object):
         self.root.left.red = False
 
     # Deletion
-    def delete(self, z):
+    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:
@@ -203,10 +240,10 @@ class RBTree(object):
             if not y.red:
                 self.__delete_fixup(x)
 
-    def __delete_fixup(self, x):
+    cdef void __delete_fixup(self, RBNode x):
         """Rebalance/fix RBTree after a deletion.  RBNode x is the
         child of the spliced out node."""
-        rootLeft = self.root.left
+        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
@@ -252,141 +289,89 @@ class RBTree(object):
                     x = rootLeft # exit loop
         x.red = False
 
-    # Rendering
-    def __render_dot_node(self, node, max_depth = 20):
-        from printf import sprintf
-        """Render a single node and its children into a dot graph fragment"""
-        if max_depth == 0:
-            return ""
-        if node is self.nil:
-            return ""
-        def c(red):
-            if red:
-                return 'color="#ff0000", style=filled, fillcolor="#ffc0c0"'
-            else:
-                return 'color="#000000", style=filled, fillcolor="#c0c0c0"'
-        s = sprintf("%d [label=\"%g\\n%g\", %s];\n",
-                    id(node),
-                    node.start, node.end,
-                    c(node.red))
-
-        if node.left is self.nil:
-            s += sprintf("L%d [label=\"-\", %s];\n", id(node), c(False))
-            s += sprintf("%d -> L%d [label=L];\n", id(node), id(node))
-        else:
-            s += sprintf("%d -> %d [label=L];\n", id(node), id(node.left))
-        if node.right is self.nil:
-            s += sprintf("R%d [label=\"-\", %s];\n", id(node), c(False))
-            s += sprintf("%d -> R%d [label=R];\n", id(node), id(node))
-        else:
-            s += sprintf("%d -> %d [label=R];\n", id(node), id(node.right))
-        s += self.__render_dot_node(node.left, max_depth-1)
-        s += self.__render_dot_node(node.right, max_depth-1)
-        return s
-
-    def render_dot(self, title = "RBTree"):
-        """Render the entire RBTree as a dot graph"""
-        return ("digraph rbtree {\n"
-                + self.__render_dot_node(self.root.left)
-                + "}\n");
-
-    def render_dot_live(self, title = "RBTree"):
-        """Render the entire RBTree as a dot graph, live GTK view"""
-        import gtk
-        import gtk.gdk
-        sys.path.append("/usr/share/xdot")
-        import xdot
-        xdot.Pen.highlighted = lambda pen: pen
-        s = ("digraph rbtree {\n"
-             + self.__render_dot_node(self.root)
-             + "}\n");
-        window = xdot.DotWindow()
-        window.set_dotcode(s)
-        window.set_title(title + " - any key to close")
-        window.connect('destroy', gtk.main_quit)
-        def quit(widget, event):
-            if not event.is_modifier:
-                window.destroy()
-                gtk.main_quit()
-        window.widget.connect('key-press-event', quit)
-        gtk.main()
-
     # Walking, searching
     def __iter__(self):
-        return self.inorder(self.root.left)
+        return self.inorder()
 
-    def inorder(self, x = None):
+    def inorder(self, RBNode x = None):
         """Generator that performs an inorder walk for the tree
-        starting at RBNode x"""
+        rooted at RBNode x"""
         if x is None:
-            x = self.root.left
+            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)
 
-    def __find_all(self, start, end, x):
-        """Find node with the specified (start,end) key.
-        Also returns the largest node less than or equal to key,
-        and the smallest node greater or equal to than key."""
-        if x is None:
-            x = self.root.left
-        largest = self.nil
-        smallest = self.nil
+    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:
-                smallest = x
-                x = x.left # start <
+                x = x.left
             elif start == x.start:
-                if end < x.end:
-                    smallest = x
-                    x = x.left # start =, end <
-                elif end == x.end: # found it
-                    smallest = x
-                    largest = x
-                    break
+                if end == x.end:
+                    break # found it
+                elif end < x.end:
+                    x = x.left
                 else:
-                    largest = x
-                    x = x.right # start =, end >
+                    x = x.right
             else:
-                largest = x
-                x = x.right # start >
-        return (x, smallest, largest)
+                x = x.right
+        return x if x is not self.nil else None
 
-    def find(self, start, end, x = None):
-        """Find node with the key == (start,end), or None"""
-        y = self.__find_all(start, end, x)[1]
-        return y if y 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.
 
-    def find_right(self, start, end, x = None):
-        """Find node with the smallest key >= (start,end), or None"""
-        y = self.__find_all(start, end, x)[1]
-        return y if y is not self.nil else None
+        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
 
-    def find_left(self, start, end, x = None):
-        """Find node with the largest key <= (start,end), or None"""
-        y = self.__find_all(start, end, x)[2]
-        return y if y 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, start, end):
+    def intersect(self, double start, double end):
         """Generator that returns nodes that overlap the given
-        (start,end) range, for the tree rooted at RBNode x.
-
-        NOTE: this assumes non-overlapping intervals."""
-        # Start with the leftmost node before the starting point
-        n = self.find_left(start, start)
-        # If we didn't find one, look for the leftmode node before the
-        # ending point instead.
-        if n is None:
-            n = self.find_left(end, end)
-        # If we still didn't find it, there are no intervals that intersect.
-        if n is None:
-            return none
-
-        # Now yield this node and all successors until their endpoints
-
-        if False:
-            yield
-        return
+        (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/rbtree.pyxdep

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

nilmdb/server.py

@@ -3,15 +3,15 @@
 # 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
+from nilmdb.utils.printf import *
 import nilmdb
 
-from nilmdb.printf import *
-
 import cherrypy
 import sys
 import time
 import os
 import simplejson as json
+import functools
 
 try:
     import cherrypy
@@ -26,6 +26,46 @@ class NilmApp(object):
 
 version = "1.1"
 
+# 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 workaround_cp_bug_1200(func): # pragma: no cover (just a workaround)
+    """Decorator to work around CherryPy bug #1200 in a response
+    generator"""
+    # Even if chunked responses are disabled, you may still miss miss
+    # LookupError, or UnicodeError exceptions due to CherryPy bug
+    # #1200.  This throws them as generic Exceptions insteads.
+    import traceback
+    @functools.wraps(func)
+    def wrapper(*args, **kwargs):
+        try:
+            for val in func(*args, **kwargs):
+                yield val
+        except (LookupError, UnicodeError) as e:
+            raise Exception("bug workaround; real exception is:\n" +
+                            traceback.format_exc())
+    return wrapper
+
+def exception_to_httperror(response = "400 Bad Request"):
+    """Return a decorator that catches Exception and throws
+    a HTTPError describing it instead"""
+    def decorator(func):
+        @functools.wraps(func)
+        def wrapper(*args, **kwargs):
+            try:
+                return func(*args, **kwargs)
+            except Exception as e:
+                message = sprintf("%s: %s", type(e).__name__, str(e))
+                raise cherrypy.HTTPError(response, message)
+        return wrapper
+    return decorator
+
+# CherryPy apps
 class Root(NilmApp):
     """Root application for NILM database"""
 
@@ -59,7 +99,7 @@ class Root(NilmApp):
     @cherrypy.expose
     @cherrypy.tools.json_out()
     def dbsize(self):
-        return nilmdb.du.du(self.db.get_basepath())
+        return nilmdb.utils.du(self.db.get_basepath())
 
 class Stream(NilmApp):
     """Stream-specific operations"""
@@ -78,15 +118,20 @@ class Stream(NilmApp):
     # /stream/create?path=/newton/prep&layout=PrepData
     @cherrypy.expose
     @cherrypy.tools.json_out()
+    @exception_to_httperror()
     def create(self, path, layout):
         """Create a new stream in the database.  Provide path
         and one of the nilmdb.layout.layouts keys.
         """
-        try:
-            return self.db.stream_create(path, layout)
-        except Exception as e:
-            message = sprintf("%s: %s", type(e).__name__, e.message)
-            raise cherrypy.HTTPError("400 Bad Request", message)
+        return self.db.stream_create(path, layout)
+
+    # /stream/destroy?path=/newton/prep
+    @cherrypy.expose
+    @cherrypy.tools.json_out()
+    @exception_to_httperror()
+    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
@@ -115,49 +160,35 @@ class Stream(NilmApp):
     # /stream/set_metadata?path=/newton/prep&data=<json>
     @cherrypy.expose
     @cherrypy.tools.json_out()
+    @exception_to_httperror()
     def set_metadata(self, path, data):
         """Set metadata for the named stream, replacing any
         existing metadata.  Data should be a json-encoded
         dictionary"""
-        try:
-            data_dict = json.loads(data)
-            self.db.stream_set_metadata(path, data_dict)
-        except Exception as e:
-            message = sprintf("%s: %s", type(e).__name__, e.message)
-            raise cherrypy.HTTPError("400 Bad Request", message)
+        data_dict = json.loads(data)
+        self.db.stream_set_metadata(path, data_dict)
         return "ok"
 
     # /stream/update_metadata?path=/newton/prep&data=<json>
     @cherrypy.expose
     @cherrypy.tools.json_out()
+    @exception_to_httperror()
     def update_metadata(self, path, data):
         """Update metadata for the named stream.  Data
         should be a json-encoded dictionary"""
-        try:
-            data_dict = json.loads(data)
-            self.db.stream_update_metadata(path, data_dict)
-        except Exception as e:
-            message = sprintf("%s: %s", type(e).__name__, e.message)
-            raise cherrypy.HTTPError("400 Bad Request", message)
+        data_dict = json.loads(data)
+        self.db.stream_update_metadata(path, data_dict)
         return "ok"
 
     # /stream/insert?path=/newton/prep
     @cherrypy.expose
     @cherrypy.tools.json_out()
     #@cherrypy.tools.disable_prb()
-    def insert(self, path, old_timestamp = None):
+    def insert(self, path, start, end):
         """
         Insert new data into the database.  Provide textual data
         (matching the path's layout) as a HTTP PUT.
-
-        old_timestamp is used when making multiple, split-up insertions
-        for a larger contiguous block of data.  The first insert
-        will return the maximum timestamp that it saw, and the second
-        insert should provide this timestamp as an argument.  This is
-        used to extend the previous database interval rather than
-        start a new one.
         """
-
         # 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
@@ -182,22 +213,36 @@ class Stream(NilmApp):
                                      "Error parsing input data: " +
                                      e.message)
 
+        if (not parser.min_timestamp or not parser.max_timestamp or
+            not len(parser.data)):
+            raise cherrypy.HTTPError("400 Bad Request",
+                                     "no data provided")
+
+        # Check limits
+        start = float(start)
+        end = float(end)
+        if parser.min_timestamp < start:
+            raise cherrypy.HTTPError("400 Bad Request", "Data timestamp " +
+                                     repr(parser.min_timestamp) +
+                                     " < start time " + repr(start))
+        if 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:
-            if old_timestamp:
-                old_timestamp = float(old_timestamp)
-            result = self.db.stream_insert(path, parser, old_timestamp)
+            result = self.db.stream_insert(path, start, end, parser.data)
         except nilmdb.nilmdb.NilmDBError as e:
             raise cherrypy.HTTPError("400 Bad Request", e.message)
 
-        # Return the maximum timestamp that we saw.  The client will
-        # return this back to us as the old_timestamp parameter, if
-        # it has more data to send.
-        return ("ok", parser.max_timestamp)
+        # Done
+        return "ok"
 
     # /stream/intervals?path=/newton/prep
     # /stream/intervals?path=/newton/prep&start=1234567890.0&end=1234567899.0
     @cherrypy.expose
+    @chunked_response
     def intervals(self, path, start = None, end = None):
         """
         Get intervals from backend database.  Streams the resulting
@@ -219,9 +264,9 @@ class Stream(NilmApp):
         if len(streams) != 1:
             raise cherrypy.HTTPError("404 Not Found", "No such stream")
 
+        @workaround_cp_bug_1200
         def content(start, end):
-            # Note: disable response.stream below to get better debug info
-            # from tracebacks in this subfunction.
+            # 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 ])
@@ -230,10 +275,10 @@ class Stream(NilmApp):
                     break
                 start = restart
         return content(start, end)
-    intervals._cp_config = { 'response.stream': True } # chunked HTTP response
 
     # /stream/extract?path=/newton/prep&start=1234567890.0&end=1234567899.0
     @cherrypy.expose
+    @chunked_response
     def extract(self, path, start = None, end = None, count = False):
         """
         Extract data from backend database.  Streams the resulting
@@ -263,9 +308,9 @@ class Stream(NilmApp):
         # Get formatter
         formatter = nilmdb.layout.Formatter(layout)
 
+        @workaround_cp_bug_1200
         def content(start, end, count):
-            # Note: disable response.stream below to get better debug info
-            # from tracebacks in this subfunction.
+            # 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)
@@ -281,8 +326,6 @@ class Stream(NilmApp):
                     return
                 start = restart
         return content(start, end, count)
-    extract._cp_config = { 'response.stream': True } # chunked HTTP response
-
 
 class Exiter(object):
     """App that exits the server, for testing"""
@@ -307,7 +350,7 @@ class Server(object):
         # Need to wrap DB object in a serializer because we'll call
         # into it from separate threads.
         self.embedded = embedded
-        self.db = nilmdb.serializer.WrapObject(db)
+        self.db = nilmdb.utils.Serializer(db)
         cherrypy.config.update({
             'server.socket_host': host,
             'server.socket_port': port,

nilmdb/timestamper.py

@@ -1,7 +1,7 @@
 """File-like objects that add timestamps to the input lines"""
 
 from __future__ import absolute_import
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 
 import time
 import os

nilmdb/utils/__init__.py

@@ -0,0 +1,9 @@
+"""NilmDB utilities"""
+
+from .timer import Timer
+from .iteratorizer import Iteratorizer
+from .serializer import Serializer
+from .lrucache import lru_cache
+from .diskusage import du
+from .mustclose import must_close
+from .urllib import urlencode

nilmdb/utils/lrucache.py

@@ -0,0 +1,66 @@
+# 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 functools
+
+def lru_cache(size = 10, onremove = 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.
+
+    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 decorator(func):
+        cache = collections.OrderedDict()	# order: least- to most-recent
+
+        def evict(value):
+            if onremove:
+                onremove(value)
+
+        @functools.wraps(func)
+        def wrapper(*args, **kwargs):
+            key = args + tuple(sorted(kwargs.items()))
+            try:
+                value = cache.pop(key)
+                wrapper.cache_hits += 1
+            except KeyError:
+                value = func(*args, **kwargs)
+                wrapper.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, **kwargs):
+            """Remove the described key from this cache, if present.
+            Note that if the original wrapped function was implicitly
+            passed 'self', you need to pass it as an argument here too."""
+            key = args + tuple(sorted(kwargs.items()))
+            if key in cache:
+                evict(cache.pop(key))
+
+        def cache_remove_all():
+            for key in cache:
+                evict(cache.pop(key))
+
+        wrapper.cache_hits = 0
+        wrapper.cache_misses = 0
+        wrapper.cache_remove = cache_remove
+        wrapper.cache_remove_all = cache_remove_all
+
+        return wrapper
+    return decorator

nilmdb/utils/mustclose.py

@@ -0,0 +1,42 @@
+# Class decorator that warns on stderr at deletion time if the class's
+# close() member wasn't called.
+
+from nilmdb.utils.printf import *
+import sys
+
+def must_close(errorfile = sys.stderr):
+    def decorator(cls):
+        def dummy(*args, **kwargs):
+            pass
+        if "__init__" not in cls.__dict__:
+            cls.__init__ = dummy
+        if "__del__" not in cls.__dict__:
+            cls.__del__ = dummy
+        if "close" not in cls.__dict__:
+            cls.close = dummy
+
+        orig_init = cls.__init__
+        orig_del = cls.__del__
+        orig_close = cls.close
+
+        def __init__(self, *args, **kwargs):
+            ret = orig_init(self, *args, **kwargs)
+            self.__dict__["_must_close"] = True
+            return ret
+
+        def __del__(self):
+            if "_must_close" in self.__dict__:
+                fprintf(errorfile, "error: %s.close() wasn't called!\n",
+                        self.__class__.__name__)
+            return orig_del(self)
+
+        def close(self, *args, **kwargs):
+            del self._must_close
+            return orig_close(self)
+
+        cls.__init__ = __init__
+        cls.__del__ = __del__
+        cls.close = close
+
+        return cls
+    return decorator

nilmdb/utils/serializer.py

@@ -67,3 +67,6 @@ class WrapObject(object):
     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

@@ -5,6 +5,7 @@
 #   with nilmdb.Timer("flush"):
 #       foo.flush()
 
+from __future__ import print_function
 import contextlib
 import time
 
@@ -18,4 +19,4 @@ def Timer(name = None, tosyslog = False):
         import syslog
         syslog.syslog(msg)
     else:
-        print msg
+        print(msg)

nilmdb/utils/urllib.py

@@ -0,0 +1,68 @@
+from __future__ import absolute_import
+from urllib import quote_plus, _is_unicode
+
+# urllib.urlencode insists on encoding Unicode as ASCII.  This is an
+# exact copy of that function, except we encode it as UTF-8 instead.
+
+def urlencode(query, doseq=0):
+    """Encode a sequence of two-element tuples or dictionary into a URL query string.
+
+    If any values in the query arg are sequences and doseq is true, each
+    sequence element is converted to a separate parameter.
+
+    If the query arg is a sequence of two-element tuples, the order of the
+    parameters in the output will match the order of parameters in the
+    input.
+    """
+
+    if hasattr(query,"items"):
+        # mapping objects
+        query = query.items()
+    else:
+        # it's a bother at times that strings and string-like objects are
+        # sequences...
+        try:
+            # non-sequence items should not work with len()
+            # non-empty strings will fail this
+            if len(query) and not isinstance(query[0], tuple):
+                raise TypeError
+            # zero-length sequences of all types will get here and succeed,
+            # but that's a minor nit - since the original implementation
+            # allowed empty dicts that type of behavior probably should be
+            # preserved for consistency
+        except TypeError:
+            ty,va,tb = sys.exc_info()
+            raise TypeError, "not a valid non-string sequence or mapping object", tb
+
+    l = []
+    if not doseq:
+        # preserve old behavior
+        for k, v in query:
+            k = quote_plus(str(k))
+            v = quote_plus(str(v))
+            l.append(k + '=' + v)
+    else:
+        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):
+                # is there a reasonable way to convert to ASCII?
+                # encode generates a string, but "replace" or "ignore"
+                # lose information and "strict" can raise UnicodeError
+                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)

runserver.py

@@ -3,14 +3,17 @@
 import nilmdb
 import argparse
 
-parser = argparse.ArgumentParser(description='Run the NILM server')
+formatter = argparse.ArgumentDefaultsHelpFormatter
+parser = argparse.ArgumentParser(description='Run the NILM server',
+                                 formatter_class = formatter)
 parser.add_argument('-p', '--port', help='Port number', type=int, default=12380)
+parser.add_argument('-d', '--database', help='Database directory', default="db")
 parser.add_argument('-y', '--yappi', help='Run with yappi profiler',
                     action='store_true')
 args = parser.parse_args()
 
 # Start web app on a custom port
-db = nilmdb.NilmDB("db")
+db = nilmdb.NilmDB(args.database)
 server = nilmdb.Server(db, host = "127.0.0.1",
                        port = args.port,
                        embedded = False)

setup.cfg

@@ -10,10 +10,14 @@ cover-erase=
 ##cover-branches=     # need nose 1.1.3 for this
 stop=
 verbosity=2
+#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_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/renderdot.py

@@ -0,0 +1,90 @@
+import sys
+
+class Renderer(object):
+
+    def __init__(self, getleft, getright,
+                 getred, getstart, getend, nil):
+        self.getleft = getleft
+        self.getright = getright
+        self.getred = getred
+        self.getstart = getstart
+        self.getend = getend
+        self.nil = nil
+
+    # Rendering
+    def __render_dot_node(self, node, max_depth = 20):
+        from nilmdb.utils.printf import sprintf
+        """Render a single node and its children into a dot graph fragment"""
+        if max_depth == 0:
+            return ""
+        if node is self.nil:
+            return ""
+        def c(red):
+            if red:
+                return 'color="#ff0000", style=filled, fillcolor="#ffc0c0"'
+            else:
+                return 'color="#000000", style=filled, fillcolor="#c0c0c0"'
+        s = sprintf("%d [label=\"%g\\n%g\", %s];\n",
+                    id(node),
+                    self.getstart(node), self.getend(node),
+                    c(self.getred(node)))
+
+        if self.getleft(node) is self.nil:
+            s += sprintf("L%d [label=\"-\", %s];\n", id(node), c(False))
+            s += sprintf("%d -> L%d [label=L];\n", id(node), id(node))
+        else:
+            s += sprintf("%d -> %d [label=L];\n",
+                         id(node),id(self.getleft(node)))
+        if self.getright(node) is self.nil:
+            s += sprintf("R%d [label=\"-\", %s];\n", id(node), c(False))
+            s += sprintf("%d -> R%d [label=R];\n", id(node), id(node))
+        else:
+            s += sprintf("%d -> %d [label=R];\n",
+                         id(node), id(self.getright(node)))
+        s += self.__render_dot_node(self.getleft(node), max_depth-1)
+        s += self.__render_dot_node(self.getright(node), max_depth-1)
+        return s
+
+    def render_dot(self, rootnode, title = "Tree"):
+        """Render the entire tree as a dot graph"""
+        return ("digraph rbtree {\n"
+                + self.__render_dot_node(rootnode)
+                + "}\n");
+
+    def render_dot_live(self, rootnode, title = "Tree"):
+        """Render the entiretree as a dot graph, live GTK view"""
+        import gtk
+        import gtk.gdk
+        sys.path.append("/usr/share/xdot")
+        import xdot
+        xdot.Pen.highlighted = lambda pen: pen
+        s = ("digraph rbtree {\n"
+             + self.__render_dot_node(rootnode)
+             + "}\n");
+        window = xdot.DotWindow()
+        window.set_dotcode(s)
+        window.set_title(title + " - any key to close")
+        window.connect('destroy', gtk.main_quit)
+        def quit(widget, event):
+            if not event.is_modifier:
+                window.destroy()
+                gtk.main_quit()
+        window.widget.connect('key-press-event', quit)
+        gtk.main()
+
+class RBTreeRenderer(Renderer):
+    def __init__(self, tree):
+        Renderer.__init__(self,
+                          lambda node: node.left,
+                          lambda node: node.right,
+                          lambda node: node.red,
+                          lambda node: node.start,
+                          lambda node: node.end,
+                          tree.nil)
+        self.tree = tree
+
+    def render(self, title = "RBTree", live = True):
+        if live:
+            return Renderer.render_dot_live(self, self.tree.getroot(), title)
+        else:
+            return Renderer.render_dot(self, self.tree.getroot(), title)

tests/test_client.py

@@ -1,5 +1,7 @@
+# -*- coding: utf-8 -*-
+
 import nilmdb
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 from nilmdb.client import ClientError, ServerError
 
 import datetime_tz
@@ -82,6 +84,8 @@ class TestClient(object):
         # 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")
@@ -131,6 +135,7 @@ class TestClient(object):
 
         testfile = "tests/data/prep-20120323T1000"
         start = datetime_tz.datetime_tz.smartparse("20120323T1000")
+        start = start.totimestamp()
         rate = 120
 
         # First try a nonexistent path
@@ -155,14 +160,41 @@ class TestClient(object):
 
         # Try forcing a server request with empty data
         with assert_raises(ClientError) as e:
-            client.http.put("stream/insert", "", { "path": "/newton/prep" })
+            client.http.put("stream/insert", "", { "path": "/newton/prep",
+                                                   "start": 0, "end": 0 })
         in_("400 Bad Request", str(e.exception))
         in_("no data provided", str(e.exception))
 
+        # Specify start/end (starts too late)
+        data = nilmdb.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 = nilmdb.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 = nilmdb.timestamper.TimestamperRate(testfile, start, 120)
-        result = client.stream_insert("/newton/prep", data)
-        eq_(result[0], "ok")
+        result = client.stream_insert("/newton/prep", data,
+                                      start, start + 119.999777)
+        eq_(result, "ok")
+
+        # 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 = nilmdb.timestamper.TimestamperRate(testfile, start, 120)
@@ -215,7 +247,8 @@ class TestClient(object):
         # Check PUT with generator out
         with assert_raises(ClientError) as e:
             client.http.put_gen("stream/insert", "",
-                                { "path": "/newton/prep" }).next()
+                                { "path": "/newton/prep",
+                                  "start": 0, "end": 0 }).next()
         in_("400 Bad Request", str(e.exception))
         in_("no data provided", str(e.exception))
 
@@ -238,7 +271,7 @@ class TestClient(object):
         # still disable chunked responses for debugging.
         x = client.http.get("stream/intervals", { "path": "/newton/prep" },
                             retjson=False)
-        eq_(x.count('\n'), 2)
+        lines_(x, 1)
         if "transfer-encoding: chunked" not in client.http._headers.lower():
             warnings.warn("Non-chunked HTTP response for /stream/intervals")
 
@@ -248,3 +281,40 @@ class TestClient(object):
                               "end": "123" }, retjson=False)
         if "transfer-encoding: chunked" not in client.http._headers.lower():
             warnings.warn("Non-chunked HTTP response for /stream/extract")
+
+    def test_client_7_unicode(self):
+        # Basic Unicode tests
+        client = nilmdb.Client(url = "http://localhost:12380/")
+
+        # 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)

tests/test_cmdline.py

@@ -1,5 +1,7 @@
+# -*- coding: utf-8 -*-
+
 import nilmdb
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 import nilmdb.cmdline
 
 from nose.tools import *
@@ -13,7 +15,7 @@ import threading
 import urllib2
 from urllib2 import urlopen, HTTPError
 import Queue
-import cStringIO
+import StringIO
 import shlex
 
 from test_helpers import *
@@ -45,12 +47,18 @@ def setup_module():
 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)
@@ -61,15 +69,18 @@ class TestCmdline(object):
                 ( sys.stdin, sys.stdout, sys.stderr ) = self.saved
         # Empty input if none provided
         if infile is None:
-            infile = cStringIO.StringIO("")
+            infile = UTF8StringIO("")
         # Capture stderr
-        errfile = cStringIO.StringIO()
+        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:
-                nilmdb.cmdline.Cmdline(shlex.split(arg_string)).run()
+                # 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
@@ -192,11 +203,22 @@ class TestCmdline(object):
         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")
-        self.ok("create /newton/zzz/rawnotch RawNotchedData")
 
-        # Verify we got those 3 streams
+        # 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"
@@ -286,16 +308,9 @@ class TestCmdline(object):
         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)
-        with assert_raises(ValueError):
-            print cmd.parse_time("20120405 1400-9999")
-        with assert_raises(ValueError):
-            print cmd.parse_time("hello")
-        with assert_raises(ValueError):
-            print cmd.parse_time("-")
-        with assert_raises(ValueError):
-            print cmd.parse_time("")
-        with assert_raises(ValueError):
-            print cmd.parse_time("14:00")
+        for badtime in [ "20120405 1400-9999", "hello", "-", "", "14:00" ]:
+            with assert_raises(ValueError):
+                x = cmd.parse_time(badtime)
         eq_(cmd.parse_time("snapshot-20120405-140000.raw.gz"), test)
         eq_(cmd.parse_time("prep-20120405T1400"), test)
 
@@ -362,36 +377,36 @@ class TestCmdline(object):
     def test_cmdline_07_detail(self):
         # Just count the number of lines, it's probably fine
         self.ok("list --detail")
-        eq_(self.captured.count('\n'), 11)
+        lines_(self.captured, 8)
 
         self.ok("list --detail --path *prep")
-        eq_(self.captured.count('\n'), 7)
+        lines_(self.captured, 4)
 
         self.ok("list --detail --path *prep --start='23 Mar 2012 10:02'")
-        eq_(self.captured.count('\n'), 5)
+        lines_(self.captured, 3)
 
         self.ok("list --detail --path *prep --start='23 Mar 2012 10:05'")
-        eq_(self.captured.count('\n'), 3)
+        lines_(self.captured, 2)
 
         self.ok("list --detail --path *prep --start='23 Mar 2012 10:05:15'")
-        eq_(self.captured.count('\n'), 2)
+        lines_(self.captured, 2)
         self.contain("10:05:15.000")
 
         self.ok("list --detail --path *prep --start='23 Mar 2012 10:05:15.50'")
-        eq_(self.captured.count('\n'), 2)
+        lines_(self.captured, 2)
         self.contain("10:05:15.500")
 
         self.ok("list --detail --path *prep --start='23 Mar 2012 19:05:15.50'")
-        eq_(self.captured.count('\n'), 2)
+        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 10:05:15.50'")
-        eq_(self.captured.count('\n'), 2)
+        lines_(self.captured, 2)
         self.contain("10:05:15.500")
 
         self.ok("list --detail")
-        eq_(self.captured.count('\n'), 11)
+        lines_(self.captured, 8)
 
     def test_cmdline_08_extract(self):
         # nonexistent stream
@@ -444,7 +459,7 @@ class TestCmdline(object):
 
         # all data put in by tests
         self.ok("extract -a /newton/prep --start 2000-01-01 --end 2020-01-01")
-        eq_(self.captured.count('\n'), 43204)
+        lines_(self.captured, 43204)
         self.ok("extract -c /newton/prep --start 2000-01-01 --end 2020-01-01")
         self.match("43200\n")
 
@@ -453,6 +468,75 @@ class TestCmdline(object):
         server_stop()
         server_start(max_results = 2)
         self.ok("list --detail")
-        eq_(self.captured.count('\n'), 11)
+        lines_(self.captured, 8)
         server_stop()
         server_start()
+
+    def test_cmdline_10_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, 8)
+
+        # 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_cmdline_11_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")

tests/test_helpers.py

@@ -20,6 +20,12 @@ def ne_(a, b):
     if not a != b:
         raise AssertionError("unexpected %s == %s" % (myrepr(a), myrepr(b)))
 
+def lines_(a, n):
+    l = a.count('\n')
+    if not l == n:
+        raise AssertionError("wanted %d lines, got %d in output: '%s'"
+                             % (n, l, a))
+
 def recursive_unlink(path):
     try:
         shutil.rmtree(path)

tests/test_interval.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 
 import nilmdb
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 import datetime_tz
 
 from nose.tools import *
@@ -13,12 +13,19 @@ from nilmdb.interval import Interval, DBInterval, IntervalSet, IntervalError
 from test_helpers import *
 import unittest
 
+# set to False to skip live renders
+do_live_renders = False
+def render(iset, description = "", live = True):
+    import 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 + adjacent start
+    | = interval end + next start
     ] = interval end
     . = zero-width interval (identical start and end)
     anything else is ignored
@@ -31,7 +38,7 @@ def makeset(string):
         elif (c == "|"):
             iset += Interval(start, day)
             start = day
-        elif (c == "]"):
+        elif (c == ")"):
             iset += Interval(start, day)
             del start
         elif (c == "."):
@@ -71,24 +78,24 @@ class TestInterval:
         assert(Interval(d1, d3) < Interval(d2, d3))
         assert(Interval(d2, d2) > Interval(d1, d3))
         assert(Interval(d3, d3) == Interval(d3, d3))
-        with assert_raises(TypeError): # was AttributeError, that's wrong
-            x = (i == 123)
+        #with assert_raises(TypeError): # was AttributeError, that's wrong
+        #    x = (i == 123)
 
         # subset
-        assert(Interval(d1, d3).subset(d1, d2) == Interval(d1, d2))
+        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]")
+        eq_(str(x), "[5000111222.0 -> 6000111222.0)")
         x = Interval(123.45, 234.56)
-        eq_(str(x), "[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]")
+        eq_(str(i), "[1332561600.0 -> 1332648000.0)")
 
     def test_interval_intersect(self):
         # Test Interval intersections
@@ -109,7 +116,7 @@ class TestInterval:
             except IntervalError:
                 assert(i not in should_intersect[True] and
                        i not in should_intersect[False])
-        with assert_raises(AttributeError):
+        with assert_raises(TypeError):
             x = i1.intersects(1234)
 
     def test_intervalset_construct(self):
@@ -130,6 +137,15 @@ class TestInterval:
             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
@@ -151,11 +167,18 @@ class TestInterval:
         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]))
 
@@ -168,61 +191,79 @@ class TestInterval:
 
         # misc
         eq_(repr(iset), repr(eval(repr(iset))))
-        eq_(str(iset), "[[100.0 -> 200.0], [200.0 -> 300.0]]")
+        eq_(str(iset), "[[100.0 -> 200.0), [200.0 -> 300.0)]")
 
     def test_intervalset_geniset(self):
         # Test basic iset construction
-        assert(makeset("  [----]   ") ==
-               makeset("  [-|--]   "))
+        eq_(makeset("  [----)   "),
+            makeset("  [-|--)   "))
 
-        assert(makeset("[]  [--]   ") +
-               makeset(" []    [--]") ==
-               makeset("[|] [-----]"))
+        eq_(makeset("[)  [--)   ") +
+            makeset(" [)    [--)"),
+            makeset("[|) [-----)"))
 
-        assert(makeset("  [-------]") ==
-               makeset("  [-|-----|"))
+        eq_(makeset("  [-------)"),
+            makeset("  [-|-----|"))
 
 
     def test_intervalset_intersect(self):
         # Test intersection (&)
         with assert_raises(TypeError): # was AttributeError
-            x = makeset("[--]") & 1234
+            x = makeset("[--)") & 1234
 
-        assert(makeset("[---------]") &
-               makeset(" [---]     ") ==
-               makeset(" [---]     "))
+        # Intersection with interval
+        eq_(makeset("[---|---)[)") &
+            list(makeset("  [------) "))[0],
+            makeset("  [-----)  "))
 
-        assert(makeset(" [---]     ") &
-               makeset("[---------]") ==
-               makeset(" [---]     "))
+        # Intersection with sets
+        eq_(makeset("[---------)") &
+            makeset(" [---)     "),
+            makeset(" [---)     "))
 
-        assert(makeset("    [-----]") &
-               makeset(" [-----]   ") ==
-               makeset("    [--]   "))
+        eq_(makeset(" [---)     ") &
+            makeset("[---------)"),
+            makeset(" [---)     "))
 
-        assert(makeset(" [--]  [--]") &
-               makeset("  [------] ") ==
-               makeset("  [-]  [-] "))
+        eq_(makeset("    [-----)") &
+            makeset(" [-----)   "),
+            makeset("    [--)   "))
 
-        assert(makeset("      [---]") &
-               makeset(" [--]      ") ==
-               makeset("           "))
+        eq_(makeset(" [--)  [--)") &
+            makeset("  [------) "),
+            makeset("  [-)  [-) "))
 
-        assert(makeset("      [---]") &
-               makeset(" [----]    ") ==
-               makeset("      .    "))
+        eq_(makeset("      [---)") &
+            makeset(" [--)      "),
+            makeset("           "))
 
-        assert(makeset("    [-|---]") &
-               makeset(" [-----|-] ") ==
-               makeset("    [----] "))
+        eq_(makeset("    [-|---)") &
+            makeset(" [-----|-) "),
+            makeset("    [----) "))
 
-        assert(makeset("    [-|-]  ") &
-               makeset(" [-|--|--] ") ==
-               makeset("    [---]  "))
+        eq_(makeset("    [-|-)  ") &
+            makeset(" [-|--|--) "),
+            makeset("    [---)  "))
 
-        assert(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):
@@ -273,12 +314,13 @@ class TestIntervalTree:
         import random
         random.seed(1234)
 
-        # make a set of 500 intervals
+        # make a set of 100 intervals
         iset = IntervalSet()
-        j = 500
+        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):
@@ -288,10 +330,15 @@ class TestIntervalTree:
         # try removing an interval that doesn't exist
         with assert_raises(IntervalError):
             iset -= Interval(1234,5678)
+        render(iset, "Random Insertion, deletion")
 
-        # show the graph
-        if False:
-            iset.tree.render_dot_live()
+        # 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")
@@ -300,18 +347,23 @@ class TestIntervalSpeed:
         import time
         import aplotter
         import random
+        import math
 
         print
         yappi.start()
         speeds = {}
-        for j in [ 2**x for x in range(5,18) ]:
+        for j in [ 2**x for x in range(5,20) ]:
             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)\n", j, speed, speed/j)
+            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()

tests/test_iteratorizer.py

@@ -1,5 +1,5 @@
 import nilmdb
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 
 import nose
 from nose.tools import *
@@ -9,8 +9,6 @@ import time
 
 from test_helpers import *
 
-import nilmdb.iteratorizer
-
 def func_with_callback(a, b, callback):
     callback(a)
     callback(b)
@@ -27,16 +25,18 @@ class TestIteratorizer(object):
         eq_(self.result, "123")
 
         # Now make it an iterator
-        it = nilmdb.iteratorizer.Iteratorizer(lambda x:
-                                              func_with_callback(1, 2, x))
+        it = nilmdb.utils.Iteratorizer(
+            lambda x:
+            func_with_callback(1, 2, x))
         result = ""
         for i in it:
             result += str(i)
         eq_(result, "123")
 
         # Make sure things work when an exception occurs
-        it = nilmdb.iteratorizer.Iteratorizer(lambda x:
-                                              func_with_callback(1, "a", x))
+        it = nilmdb.utils.Iteratorizer(
+            lambda x:
+            func_with_callback(1, "a", x))
         result = ""
         with assert_raises(TypeError) as e:
             for i in it:
@@ -48,7 +48,8 @@ class TestIteratorizer(object):
         # itself.  This doesn't have a particular result in the test,
         # but gains coverage.
         def foo():
-            it = nilmdb.iteratorizer.Iteratorizer(lambda x:
-                                                  func_with_callback(1, 2, x))
+            it = nilmdb.utils.Iteratorizer(
+                lambda x:
+                func_with_callback(1, 2, x))
             it.next()
         foo()

tests/test_layout.py

@@ -2,7 +2,7 @@
 
 import nilmdb
 
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 
 from nose.tools import *
 from nose.tools import assert_raises
@@ -28,9 +28,13 @@ class TestLayouts(object):
     # Some nilmdb.layout tests.  Not complete, just fills in missing
     # coverage.
     def test_layouts(self):
-        x = nilmdb.layout.get_named("PrepData").description()
-        y = nilmdb.layout.get_named("float32_8").description()
-        eq_(repr(x), repr(y))
+        x = nilmdb.layout.get_named("PrepData")
+        y = nilmdb.layout.get_named("float32_8")
+        eq_(x.count, y.count)
+        eq_(x.datatype, y.datatype)
+        y = nilmdb.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")

tests/test_lrucache.py

@@ -0,0 +1,53 @@
+import nilmdb
+from nilmdb.utils.printf import *
+
+import nose
+from nose.tools import *
+from nose.tools import assert_raises
+import threading
+import time
+
+from test_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 TestLRUCache(object):
+    def test(self):
+        [ foo1(n) for n in [ 1, 2, 3, 1, 2, 3, 1, 2, 3 ] ]
+        eq_((foo1.cache_hits, foo1.cache_misses), (6, 3))
+        [ foo1(n) for n in [ 1, 2, 3, 1, 2, 3, 1, 2, 3 ] ]
+        eq_((foo1.cache_hits, foo1.cache_misses), (15, 3))
+        [ foo1(n) for n in [ 4, 2, 1, 1, 4 ] ]
+        eq_((foo1.cache_hits, foo1.cache_misses), (18, 5))
+
+        [ foo2(n) for n in [ 1, 2, 3, 1, 2, 3, 1, 2, 3 ] ]
+        eq_((foo2.cache_hits, foo2.cache_misses), (6, 3))
+        [ foo2(n) for n in [ 1, 2, 3, 1, 2, 3, 1, 2, 3 ] ]
+        eq_((foo2.cache_hits, foo2.cache_misses), (15, 3))
+        [ foo2(n) for n in [ 4, 2, 1, 1, 4 ] ]
+        eq_((foo2.cache_hits, foo2.cache_misses), (19, 4))
+
+        [ foo3(n) for n in [ 1, 2, 3, 1, 2, 3, 1, 2, 3 ] ]
+        eq_((foo3.cache_hits, foo3.cache_misses), (6, 3))
+        [ foo3(n) for n in [ 1, 2, 3, 1, 2, 3, 1, 2, 3 ] ]
+        eq_((foo3.cache_hits, foo3.cache_misses), (15, 3))
+        [ foo3(n) for n in [ 4, 2, 1, 1, 4 ] ]
+        eq_((foo3.cache_hits, foo3.cache_misses), (18, 5))
+        eq_(foo3d.destructed, [1, 3])
+        foo3.cache_remove(1)
+        eq_(foo3d.destructed, [1, 3, 1])
+        foo3.cache_remove_all()
+        eq_(foo3d.destructed, [1, 3, 1, 2, 4 ])

tests/test_mustclose.py

@@ -0,0 +1,59 @@
+import nilmdb
+from nilmdb.utils.printf import *
+
+import nose
+from nose.tools import *
+from nose.tools import assert_raises
+
+from test_helpers import *
+
+import sys
+import cStringIO
+
+err = cStringIO.StringIO()
+
+@nilmdb.utils.must_close(errorfile = err)
+class Foo:
+    def __init__(self):
+        fprintf(err, "Init\n")
+
+    def __del__(self):
+        fprintf(err, "Deleting\n")
+
+    def close(self):
+        fprintf(err, "Closing\n")
+
+@nilmdb.utils.must_close(errorfile = err)
+class Bar:
+    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".
+
+        x = Foo()
+        del x
+        eq_(err.getvalue(),
+            "Init\n"
+            "error: Foo.close() wasn't called!\n"
+            "Deleting\n")
+
+        err.truncate(0)
+
+        y = Foo()
+        y.close()
+        del y
+        eq_(err.getvalue(),
+            "Init\n"
+            "Closing\n"
+            "Deleting\n")
+
+        err.truncate(0)
+
+        z = Bar()
+        z.close()
+        del z
+        eq_(err.getvalue(), "")

tests/test_nilmdb.py

@@ -14,6 +14,7 @@ import urllib2
 from urllib2 import urlopen, HTTPError
 import Queue
 import cStringIO
+import time
 
 testdb = "tests/testdb"
 
@@ -39,8 +40,8 @@ class Test00Nilmdb(object):  # named 00 so it runs first
         capture = cStringIO.StringIO()
         old = sys.stdout
         sys.stdout = capture
-        with nilmdb.Timer("test"):
-            nilmdb.timer.time.sleep(0.01)
+        with nilmdb.utils.Timer("test"):
+            time.sleep(0.01)
         sys.stdout = old
         in_("test: ", capture.getvalue())
 
@@ -69,12 +70,14 @@ class Test00Nilmdb(object):  # named 00 so it runs first
         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
-        eq_(len(db.h5file.getNode("/newton/prep").cols), 9)
-        eq_(len(db.h5file.getNode("/newton/raw").cols), 7)
-        eq_(len(db.h5file.getNode("/newton/zzz/rawnotch").cols), 10)
-        assert(not db.h5file.getNode("/newton/prep").colindexed["timestamp"])
-        assert(not db.h5file.getNode("/newton/prep").colindexed["c1"])
+        # 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"), {})
@@ -196,6 +199,6 @@ class TestServer(object):
         # 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")
+            getjson("/stream/insert?path=/newton/prep&start=0&end=0")
         eq_(e.exception.code, 400)
 

tests/test_printf.py

@@ -1,5 +1,5 @@
 import nilmdb
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 
 from nose.tools import *
 from nose.tools import assert_raises

tests/test_rbtree.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 
 import nilmdb
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 
 from nose.tools import *
 from nose.tools import assert_raises
@@ -11,65 +11,149 @@ from nilmdb.rbtree import RBTree, RBNode
 from test_helpers import *
 import unittest
 
-render = False
+# set to False to skip live renders
+do_live_renders = False
+def render(tree, description = "", live = True):
+    import renderdot
+    r = renderdot.RBTreeRenderer(tree)
+    return r.render(description, live and do_live_renders)
 
 class TestRBTree:
     def test_rbtree(self):
         rb = RBTree()
-        rb.insert(RBNode(None, 10000, 10001))
-        rb.insert(RBNode(None, 10004, 10007))
-        rb.insert(RBNode(None, 10001, 10002))
-        s = rb.render_dot()
+        rb.insert(RBNode(10000, 10001))
+        rb.insert(RBNode(10004, 10007))
+        rb.insert(RBNode(10001, 10002))
         # There was a typo that gave the RBTree a loop in this case.
         # Verify that the dot isn't too big.
+        s = render(rb, live = False)
         assert(len(s.splitlines()) < 30)
 
     def test_rbtree_big(self):
         import random
         random.seed(1234)
 
-        # make a set of 500 intervals, inserted in order
+        # make a set of 100 intervals, inserted in order
         rb = RBTree()
-        j = 500
+        j = 100
         for i in xrange(j):
-            rb.insert(RBNode(None, i, i+1))
-
-        # show the graph
-        if render:
-            rb.render_dot_live("in-order insert")
+            rb.insert(RBNode(i, i+1))
+        render(rb, "in-order insert")
 
         # remove about half of them
         for i in random.sample(xrange(j),j):
             if random.randint(0,1):
                 rb.delete(rb.find(i, i+1))
+        render(rb, "in-order insert, random delete")
 
-        # show the graph
-        if render:
-            rb.render_dot_live("in-order insert, random delete")
-
-        # make a set of 500 intervals, inserted at random
+        # make a set of 100 intervals, inserted at random
         rb = RBTree()
-        j = 500
+        j = 100
         for i in random.sample(xrange(j),j):
-            rb.insert(RBNode(None, i, i+1))
-
-        # show the graph
-        if render:
-            rb.render_dot_live("random insert")
+            rb.insert(RBNode(i, i+1))
+        render(rb, "random insert")
 
         # remove about half of them
         for i in random.sample(xrange(j),j):
             if random.randint(0,1):
                 rb.delete(rb.find(i, i+1))
+        render(rb, "random insert, random delete")
 
-        # show the graph
-        if render:
-            rb.render_dot_live("random insert, random delete")
+        # in-order insert of 50 more
+        for i in xrange(50):
+            rb.insert(RBNode(i+500, i+501))
+        render(rb, "random insert, random delete, in-order insert")
 
-        # in-order insert of 250 more
-        for i in xrange(250):
-            rb.insert(RBNode(None, i+500, i+501))
+    def test_rbtree_basics(self):
+        rb = RBTree()
+        vals = [ 7, 14, 1, 2, 8, 11, 5, 15, 4]
+        for n in vals:
+            rb.insert(RBNode(n, n))
 
-        # show the graph
-        if render:
-            rb.render_dot_live("random insert, random delete, in-order insert")
+        # stringify
+        s = ""
+        for node in rb:
+            s += str(node)
+        in_("[node (None) 1", s)
+        eq_(str(rb.nil), "[node nil]")
+
+        # inorder traversal, successor and predecessor
+        last = 0
+        for node in rb:
+            assert(node.start > last)
+            last = node.start
+            successor = rb.successor(node)
+            if successor:
+                assert(rb.predecessor(successor) is node)
+            predecessor = rb.predecessor(node)
+            if predecessor:
+                assert(rb.successor(predecessor) is node)
+
+        # Delete node not in the tree
+        with assert_raises(AttributeError):
+            rb.delete(RBNode(1,2))
+
+        # Delete all nodes!
+        for node in rb:
+            rb.delete(node)
+
+        # Build it up again, make sure it matches
+        for n in vals:
+            rb.insert(RBNode(n, n))
+        s2 = ""
+        for node in rb:
+            s2 += str(node)
+        assert(s == s2)
+
+    def test_rbtree_find(self):
+        # Get a little bit of coverage for some overlapping cases,
+        # even though the class doesn't fully support it.
+        rb = RBTree()
+        nodes = [ RBNode(1, 5), RBNode(1, 10), RBNode(1, 15) ]
+        for n in nodes:
+            rb.insert(n)
+        assert(rb.find(1, 5) is nodes[0])
+        assert(rb.find(1, 10) is nodes[1])
+        assert(rb.find(1, 15) is nodes[2])
+
+    def test_rbtree_find_leftright(self):
+        # Now let's get some ranges in there
+        rb = RBTree()
+        vals = [ 7, 14, 1, 2, 8, 11, 5, 15, 4]
+        for n in vals:
+            rb.insert(RBNode(n*10, n*10+5))
+
+        # Check find_end_left, find_right_start
+        for i in range(160):
+            left = rb.find_left_end(i)
+            right = rb.find_right_start(i)
+            if left:
+                # endpoint should be more than i
+                assert(left.end >= i)
+                # all earlier nodes should have a lower endpoint
+                for node in rb:
+                    if node is left:
+                        break
+                    assert(node.end < i)
+            if right:
+                # startpoint should be less than i
+                assert(right.start <= i)
+                # all later nodes should have a higher startpoint
+                for node in reversed(list(rb)):
+                    if node is right:
+                        break
+                    assert(node.start > i)
+
+    def test_rbtree_intersect(self):
+        # Fill with some ranges
+        rb = RBTree()
+        rb.insert(RBNode(10,20))
+        rb.insert(RBNode(20,25))
+        rb.insert(RBNode(30,40))
+        # Just a quick test; test_interval will do better.
+        eq_(len(list(rb.intersect(1,100))), 3)
+        eq_(len(list(rb.intersect(10,20))), 1)
+        eq_(len(list(rb.intersect(5,15))), 1)
+        eq_(len(list(rb.intersect(15,15))), 1)
+        eq_(len(list(rb.intersect(20,21))), 1)
+        eq_(len(list(rb.intersect(19,21))), 2)

tests/test_serializer.py

@@ -1,5 +1,5 @@
 import nilmdb
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 
 import nose
 from nose.tools import *
@@ -57,7 +57,7 @@ class TestUnserialized(Base):
 class TestSerialized(Base):
     def setUp(self):
         self.realfoo = Foo()
-        self.foo = nilmdb.serializer.WrapObject(self.realfoo)
+        self.foo = nilmdb.utils.Serializer(self.realfoo)
 
     def tearDown(self):
         del self.foo

tests/test_timestamper.py

@@ -1,5 +1,5 @@
 import nilmdb
-from nilmdb.printf import *
+from nilmdb.utils.printf import *
 
 import datetime_tz
 

timeit.sh

@@ -1,20 +1,22 @@
+./nilmtool.py destroy /bpnilm/2/raw
 ./nilmtool.py create /bpnilm/2/raw RawData
 
-if true; then
-    time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s 20110513-110000 /bpnilm/2/raw
-    time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s 20110513-120001 /bpnilm/2/raw
+if false; then
+    time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s 20110513-110000 -r 8000 /bpnilm/2/raw
+    time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s 20110513-120001 -r 8000 /bpnilm/2/raw
 else
-    for i in $(seq 2000 2050); do
-	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-010001 /bpnilm/2/raw
-	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-020002 /bpnilm/2/raw
-	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-030003 /bpnilm/2/raw
-	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-040004 /bpnilm/2/raw
-	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-050005 /bpnilm/2/raw
-	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-060006 /bpnilm/2/raw
-	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-070007 /bpnilm/2/raw
-	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-080008 /bpnilm/2/raw
-	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-090009 /bpnilm/2/raw
-	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-100010 /bpnilm/2/raw
+    # 170 hours, about 98 gigs uncompressed:
+    for i in $(seq 2000 2016); do
+	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-010001 -r 8000 /bpnilm/2/raw
+	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-020002 -r 8000 /bpnilm/2/raw
+	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-030003 -r 8000 /bpnilm/2/raw
+	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-040004 -r 8000 /bpnilm/2/raw
+	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-050005 -r 8000 /bpnilm/2/raw
+	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-060006 -r 8000 /bpnilm/2/raw
+	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-070007 -r 8000 /bpnilm/2/raw
+	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-080008 -r 8000 /bpnilm/2/raw
+	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-090009 -r 8000 /bpnilm/2/raw
+	time zcat /home/jim/bpnilm-data/snapshot-1-20110513-110002.raw.gz | ./nilmtool.py insert -s ${i}0101-100010 -r 8000 /bpnilm/2/raw
     done
 fi