Use absolute_import from the __future__ everywhere

[bup.git] / lib / bup / bloom.py

diff --git a/lib/bup/bloom.py b/lib/bup/bloom.py
index 5444fd5d0a67717e561bb23d92800a36dcfa1ade..54da4b8cc8fed08971f17a56a08da5352354ca77 100644 (file)
--- a/lib/bup/bloom.py
+++ b/lib/bup/bloom.py
@@ -4,7 +4,7 @@ There are four basic things to consider when building a bloom filter:
 The size, in bits, of the filter
 The capacity, in entries, of the filter
 The probability of a false positive that is tolerable
-The number of bits readily available to use for addresing filter bits
+The number of bits readily available to use for addressing filter bits
 
 There is one major tunable that is not directly related to the above:
 k: the number of bits set in the filter per entry
@@ -72,16 +72,21 @@ reasonable size.
 Based on these parameters, a combination of k=4 and k=5 provides the behavior
 that bup needs.  As such, I've implemented bloom addressing, adding and
 checking functions in C for these two values.  Because k=5 requires less space
-and gives better overall pfalse_positive perofrmance, it is preferred if a
+and gives better overall pfalse_positive performance, it is preferred if a
 table with k=5 can represent the repository.
 
 None of this tells us what max_pfalse_positive to choose.
 
 Brandon Low <lostlogic@lostlogicx.com> 2011-02-04
 """
-import sys, os, math, mmap
+
+from __future__ import absolute_import
+import sys, os, math, mmap, struct
+
 from bup import _helpers
-from bup.helpers import *
+from bup.helpers import (debug1, debug2, log, mmap_read, mmap_readwrite,
+                         mmap_readwrite_private, unlink)
+
 
 BLOOM_VERSION = 2
 MAX_BITS_EACH = 32 # Kinda arbitrary, but 4 bytes per entry is pretty big
@@ -94,6 +99,9 @@ _total_steps = 0
 bloom_contains = _helpers.bloom_contains
 bloom_add = _helpers.bloom_add
 
+# FIXME: check bloom create() and ShaBloom handling/ownership of "f".
+# The ownership semantics should be clarified since the caller needs
+# to know who is responsible for closing it.
 
 class ShaBloom:
     """Wrapper which contains data from multiple index files. """
@@ -190,11 +198,15 @@ class ShaBloom:
         k = self.k
         return 100*(1-math.exp(-k*float(n)/m))**k
 
-    def add_idx(self, ix):
-        """Add the object to the filter, return current pfalse_positive."""
+    def add(self, ids):
+        """Add the hashes in ids (packed binary 20-bytes) to the filter."""
         if not self.map:
             raise Exception("Cannot add to closed bloom")
-        self.entries += bloom_add(self.map, ix.shatable, self.bits, self.k)
+        self.entries += bloom_add(self.map, ids, self.bits, self.k)
+
+    def add_idx(self, ix):
+        """Add the object to the filter."""
+        self.add(ix.shatable)
         self.idxnames.append(os.path.basename(ix.name))
 
     def exists(self, sha):
@@ -237,3 +249,6 @@ def create(name, expected, delaywrite=None, f=None, k=None):
         expected = 1
     return ShaBloom(name, f=f, readwrite=True, expected=expected)
 
+
+def clear_bloom(dir):
+    unlink(os.path.join(dir, 'bup.bloom'))