Rev 2507: Using text.split() is down to 174ms in http://bzr.arbash-meinel.com/branches/bzr/0.17-dev/dirstate_pyrex

[John Arbash Meinel]

At http://bzr.arbash-meinel.com/branches/bzr/0.17-dev/dirstate_pyrex

------------------------------------------------------------
revno: 2507
revision-id: john at arbash-meinel.com-20070504221204-d9mjz2nl8fd5maxp
parent: john at arbash-meinel.com-20070504220621-iwla6gmrtx7iy37s
committer: John Arbash Meinel <john at arbash-meinel.com>
branch nick: dirstate_pyrex
timestamp: Fri 2007-05-04 17:12:04 -0500
message:
  Using text.split() is down to 174ms
  We'll need some work to get the Reader version faster.
modified:
  bzrlib/compiled/dirstate_helpers.pyx dirstate_helpers.pyx-20070503201057-u425eni465q4idwn-3
-------------- next part --------------
=== modified file 'bzrlib/compiled/dirstate_helpers.pyx'
--- a/bzrlib/compiled/dirstate_helpers.pyx	2007-05-04 22:06:21 +0000
+++ b/bzrlib/compiled/dirstate_helpers.pyx	2007-05-04 22:12:04 +0000
@@ -260,7 +260,7 @@
     if not PyList_CheckExact(fields):
         raise TypeError('fields must be a list')
 
-    pos = 0
+    pos = 1
     field_count = len(fields)
 
     state._dirblocks = [('', []), ('', [])]
@@ -352,15 +352,17 @@
     text = state._state_file.read()
     # TODO: check the crc checksums. crc_measured = zlib.crc32(text)
 
-    reader = Reader(text)
+    # reader = Reader(text)
 
     num_present_parents = state._num_present_parents()
     entry_size = state._fields_per_entry()
 
-    fields = reader.get_all_fields()
+    # fields = reader.get_all_fields()
+    fields = text.split('\0')
+    fields.pop()
 
     # skip the first field which is the trailing null from the header.
-    cur = 0
+    cur = 1
 
     # Each line now has an extra '\n' field which is not used
     # so we just skip over it
@@ -371,12 +373,12 @@
     num_entries = state._num_entries
     expected_field_count = entry_size * num_entries
     field_count = len(fields)
-    if field_count - cur != expected_field_count:
+    if (field_count - cur) != expected_field_count:
         # this checks our adjustment, and also catches file too short.
         raise AssertionError(
             'field count incorrect %s != %s, entry_size=%s, '
             'num_entries=%s fields=%r' % (
-                field_count - cur, expected_field_count, entry_size,
+                (field_count - cur), expected_field_count, entry_size,
                 state._num_entries, fields))
 
     if num_present_parents == 0: