Hook-up hashing infrastructure

Signed-off-by: Jeremy Kerr <jk@ozlabs.org>

3 files changed, 93 insertions, 5 deletions

diff --git a/apps/patchwork/bin/rehash.py b/apps/patchwork/bin/rehash.py
new file mode 100755
index 0000000..1b3e3e9
--- /dev/null
+++ b/apps/patchwork/bin/rehash.py
@@ -0,0 +1,28 @@
+#!/usr/bin/python
+#
+# Patchwork - automated patch tracking system
+# Copyright (C) 2008 Jeremy Kerr <jk@ozlabs.org>
+#
+# This file is part of the Patchwork package.
+#
+# Patchwork is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# Patchwork is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with Patchwork; if not, write to the Free Software
+# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+from patchwork.models import Patch
+
+if __name__ == '__main__':
+    for patch in Patch.objects.all():
+        print patch.id, patch.name
+        patch.hash = None
+        patch.save()
diff --git a/apps/patchwork/models.py b/apps/patchwork/models.py
index fb2ccc7..f354acb 100644
--- a/apps/patchwork/models.py
+++ b/apps/patchwork/models.py
@@ -22,6 +22,7 @@ from django.contrib.auth.models import User
 from django.core.urlresolvers import reverse
 from django.contrib.sites.models import Site
 from django.conf import settings
+from patchwork.parser import hash_patch
 import django.oldforms as oldforms
 
 import re
@@ -223,7 +224,7 @@ class Patch(models.Model):
     headers = models.TextField(blank = True)
     content = models.TextField()
     commit_ref = models.CharField(max_length=255, null = True, blank = True)
-    hash = HashField()
+    hash = HashField(null = True)
 
     def __str__(self):
         return self.name
@@ -236,8 +237,10 @@ class Patch(models.Model):
             s = self.state
         except:
             self.state = State.objects.get(ordering =  0)
-        if hash is None:
-            print "no hash"
+
+        if self.hash is None:
+            self.hash = hash_patch(self.content).digest()
+
         super(Patch, self).save()
 
     def is_editable(self, user):
diff --git a/apps/patchwork/parser.py b/apps/patchwork/parser.py
index 16d1de4..8ed36cc 100644
--- a/apps/patchwork/parser.py
+++ b/apps/patchwork/parser.py
@@ -22,6 +22,16 @@
 
 import re
 
+try:
+    import hashlib
+    sha1_hash = hashlib.sha1
+except ImportError:
+    import sha
+    sha1_hash = sha.sha
+
+_hunk_re = re.compile('^\@\@ -\d+(?:,(\d+))? \+\d+(?:,(\d+))? \@\@')
+_filename_re = re.compile('^(---|\+\+\+) (\S+)')
+
 def parse_patch(text):
     patchbuf = ''
     commentbuf = ''
@@ -53,7 +63,6 @@ def parse_patch(text):
     lc = (0, 0)
     hunk = 0
 
-    hunk_re = re.compile('^\@\@ -\d+(?:,(\d+))? \+\d+(?:,(\d+))? \@\@')
 
     for line in text.split('\n'):
         line += '\n'
@@ -91,7 +100,7 @@ def parse_patch(text):
                 buf = ''
 
         elif state == 3:
-            match = hunk_re.match(line)
+            match = _hunk_re.match(line)
             if match:
 
                 def fn(x):
@@ -149,10 +158,58 @@ def parse_patch(text):
 
     return (patchbuf, commentbuf)
 
+def hash_patch(str):
+    # normalise spaces
+    str = str.replace('\r', '')
+    str = str.strip() + '\n'
+
+    prefixes = ['-', '+', ' ']
+    hash = sha1_hash()
+
+    for line in str.split('\n'):
+
+        if len(line) <= 0:
+            continue
+
+        hunk_match = _hunk_re.match(line)
+        filename_match = _filename_re.match(line)
+
+        if filename_match:
+            # normalise -p1 top-directories
+            if filename_match.group(1) == '---':
+                filename = 'a/'
+            else:
+                filename = 'b/'
+            filename += '/'.join(filename_match.group(2).split('/')[1:])
+
+            line = filename_match.group(1) + ' ' + filename
+
+        elif hunk_match:
+            # remove line numbers, but leave line counts
+            def fn(x):
+                if not x:
+                    return 1
+                return int(x)
+            line_nos = map(fn, hunk_match.groups())
+            line = '@@ -%d +%d @@' % tuple(line_nos)
+
+        elif line[0] in prefixes:
+            # if we have a +, - or context line, leave as-is
+            pass
+
+        else:
+            # other lines are ignored
+            continue
+
+        hash.update(line.encode('utf-8') + '\n')
+
+    return hash
+
 if __name__ == '__main__':
     import sys
     (patch, comment) = parse_patch(sys.stdin.read())
     if patch:
         print "Patch: ------\n" + patch
+        print "hash: %s" % hash_patch(patch).hexdigest()
     if comment:
         print "Comment: ----\n" + comment