summaryrefslogtreecommitdiff
path: root/eggs/mercurial-1.7.3-py2.6-linux-x86_64.egg/mercurial/similar.py
diff options
context:
space:
mode:
authorNishanth Amuluru2011-01-08 11:20:57 +0530
committerNishanth Amuluru2011-01-08 11:20:57 +0530
commit65411d01d448ff0cd4abd14eee14cf60b5f8fc20 (patch)
treeb4c404363c4c63a61d6e2f8bd26c5b057c1fb09d /eggs/mercurial-1.7.3-py2.6-linux-x86_64.egg/mercurial/similar.py
parent2e35094d43b4cc6974172e1febf76abb50f086ec (diff)
downloadpytask-65411d01d448ff0cd4abd14eee14cf60b5f8fc20.tar.gz
pytask-65411d01d448ff0cd4abd14eee14cf60b5f8fc20.tar.bz2
pytask-65411d01d448ff0cd4abd14eee14cf60b5f8fc20.zip
Added buildout stuff and made changes accordingly
--HG-- rename : profile/management/__init__.py => eggs/djangorecipe-0.20-py2.6.egg/EGG-INFO/dependency_links.txt rename : profile/management/__init__.py => eggs/djangorecipe-0.20-py2.6.egg/EGG-INFO/not-zip-safe rename : profile/management/__init__.py => eggs/infrae.subversion-1.4.5-py2.6.egg/EGG-INFO/dependency_links.txt rename : profile/management/__init__.py => eggs/infrae.subversion-1.4.5-py2.6.egg/EGG-INFO/not-zip-safe rename : profile/management/__init__.py => eggs/mercurial-1.7.3-py2.6-linux-x86_64.egg/EGG-INFO/dependency_links.txt rename : profile/management/__init__.py => eggs/mercurial-1.7.3-py2.6-linux-x86_64.egg/EGG-INFO/not-zip-safe rename : profile/management/__init__.py => eggs/py-1.4.0-py2.6.egg/EGG-INFO/dependency_links.txt rename : profile/management/__init__.py => eggs/py-1.4.0-py2.6.egg/EGG-INFO/not-zip-safe rename : profile/management/__init__.py => eggs/zc.buildout-1.5.2-py2.6.egg/EGG-INFO/dependency_links.txt rename : profile/management/__init__.py => eggs/zc.buildout-1.5.2-py2.6.egg/EGG-INFO/not-zip-safe rename : profile/management/__init__.py => eggs/zc.recipe.egg-1.3.2-py2.6.egg/EGG-INFO/dependency_links.txt rename : profile/management/__init__.py => eggs/zc.recipe.egg-1.3.2-py2.6.egg/EGG-INFO/not-zip-safe rename : profile/management/__init__.py => parts/django/Django.egg-info/dependency_links.txt rename : taskapp/models.py => parts/django/django/conf/app_template/models.py rename : taskapp/tests.py => parts/django/django/conf/app_template/tests.py rename : taskapp/views.py => parts/django/django/conf/app_template/views.py rename : taskapp/views.py => parts/django/django/contrib/gis/tests/geo3d/views.py rename : profile/management/__init__.py => parts/django/tests/modeltests/delete/__init__.py rename : profile/management/__init__.py => parts/django/tests/modeltests/files/__init__.py rename : profile/management/__init__.py => parts/django/tests/modeltests/invalid_models/__init__.py rename : profile/management/__init__.py => parts/django/tests/modeltests/m2m_signals/__init__.py rename : profile/management/__init__.py => parts/django/tests/modeltests/model_package/__init__.py rename : profile/management/__init__.py => parts/django/tests/regressiontests/bash_completion/__init__.py rename : profile/management/__init__.py => parts/django/tests/regressiontests/bash_completion/management/__init__.py rename : profile/management/__init__.py => parts/django/tests/regressiontests/bash_completion/management/commands/__init__.py rename : profile/management/__init__.py => parts/django/tests/regressiontests/bash_completion/models.py rename : profile/management/__init__.py => parts/django/tests/regressiontests/delete_regress/__init__.py rename : profile/management/__init__.py => parts/django/tests/regressiontests/file_storage/__init__.py rename : profile/management/__init__.py => parts/django/tests/regressiontests/max_lengths/__init__.py rename : profile/forms.py => pytask/profile/forms.py rename : profile/management/__init__.py => pytask/profile/management/__init__.py rename : profile/management/commands/seed_db.py => pytask/profile/management/commands/seed_db.py rename : profile/models.py => pytask/profile/models.py rename : profile/templatetags/user_tags.py => pytask/profile/templatetags/user_tags.py rename : taskapp/tests.py => pytask/profile/tests.py rename : profile/urls.py => pytask/profile/urls.py rename : profile/utils.py => pytask/profile/utils.py rename : profile/views.py => pytask/profile/views.py rename : static/css/base.css => pytask/static/css/base.css rename : taskapp/tests.py => pytask/taskapp/tests.py rename : taskapp/views.py => pytask/taskapp/views.py rename : templates/base.html => pytask/templates/base.html rename : templates/profile/browse_notifications.html => pytask/templates/profile/browse_notifications.html rename : templates/profile/edit.html => pytask/templates/profile/edit.html rename : templates/profile/view.html => pytask/templates/profile/view.html rename : templates/profile/view_notification.html => pytask/templates/profile/view_notification.html rename : templates/registration/activate.html => pytask/templates/registration/activate.html rename : templates/registration/activation_email.txt => pytask/templates/registration/activation_email.txt rename : templates/registration/activation_email_subject.txt => pytask/templates/registration/activation_email_subject.txt rename : templates/registration/logged_out.html => pytask/templates/registration/logged_out.html rename : templates/registration/login.html => pytask/templates/registration/login.html rename : templates/registration/logout.html => pytask/templates/registration/logout.html rename : templates/registration/password_change_done.html => pytask/templates/registration/password_change_done.html rename : templates/registration/password_change_form.html => pytask/templates/registration/password_change_form.html rename : templates/registration/password_reset_complete.html => pytask/templates/registration/password_reset_complete.html rename : templates/registration/password_reset_confirm.html => pytask/templates/registration/password_reset_confirm.html rename : templates/registration/password_reset_done.html => pytask/templates/registration/password_reset_done.html rename : templates/registration/password_reset_email.html => pytask/templates/registration/password_reset_email.html rename : templates/registration/password_reset_form.html => pytask/templates/registration/password_reset_form.html rename : templates/registration/registration_complete.html => pytask/templates/registration/registration_complete.html rename : templates/registration/registration_form.html => pytask/templates/registration/registration_form.html rename : utils.py => pytask/utils.py
Diffstat (limited to 'eggs/mercurial-1.7.3-py2.6-linux-x86_64.egg/mercurial/similar.py')
-rw-r--r--eggs/mercurial-1.7.3-py2.6-linux-x86_64.egg/mercurial/similar.py103
1 files changed, 103 insertions, 0 deletions
diff --git a/eggs/mercurial-1.7.3-py2.6-linux-x86_64.egg/mercurial/similar.py b/eggs/mercurial-1.7.3-py2.6-linux-x86_64.egg/mercurial/similar.py
new file mode 100644
index 0000000..b18795b
--- /dev/null
+++ b/eggs/mercurial-1.7.3-py2.6-linux-x86_64.egg/mercurial/similar.py
@@ -0,0 +1,103 @@
+# similar.py - mechanisms for finding similar files
+#
+# Copyright 2005-2007 Matt Mackall <mpm@selenic.com>
+#
+# This software may be used and distributed according to the terms of the
+# GNU General Public License version 2 or any later version.
+
+from i18n import _
+import util
+import mdiff
+import bdiff
+
+def _findexactmatches(repo, added, removed):
+ '''find renamed files that have no changes
+
+ Takes a list of new filectxs and a list of removed filectxs, and yields
+ (before, after) tuples of exact matches.
+ '''
+ numfiles = len(added) + len(removed)
+
+ # Get hashes of removed files.
+ hashes = {}
+ for i, fctx in enumerate(removed):
+ repo.ui.progress(_('searching for exact renames'), i, total=numfiles)
+ h = util.sha1(fctx.data()).digest()
+ hashes[h] = fctx
+
+ # For each added file, see if it corresponds to a removed file.
+ for i, fctx in enumerate(added):
+ repo.ui.progress(_('searching for exact renames'), i + len(removed),
+ total=numfiles)
+ h = util.sha1(fctx.data()).digest()
+ if h in hashes:
+ yield (hashes[h], fctx)
+
+ # Done
+ repo.ui.progress(_('searching for exact renames'), None)
+
+def _findsimilarmatches(repo, added, removed, threshold):
+ '''find potentially renamed files based on similar file content
+
+ Takes a list of new filectxs and a list of removed filectxs, and yields
+ (before, after, score) tuples of partial matches.
+ '''
+ copies = {}
+ for i, r in enumerate(removed):
+ repo.ui.progress(_('searching for similar files'), i, total=len(removed))
+
+ # lazily load text
+ @util.cachefunc
+ def data():
+ orig = r.data()
+ return orig, mdiff.splitnewlines(orig)
+
+ def score(text):
+ orig, lines = data()
+ # bdiff.blocks() returns blocks of matching lines
+ # count the number of bytes in each
+ equal = 0
+ matches = bdiff.blocks(text, orig)
+ for x1, x2, y1, y2 in matches:
+ for line in lines[y1:y2]:
+ equal += len(line)
+
+ lengths = len(text) + len(orig)
+ return equal * 2.0 / lengths
+
+ for a in added:
+ bestscore = copies.get(a, (None, threshold))[1]
+ myscore = score(a.data())
+ if myscore >= bestscore:
+ copies[a] = (r, myscore)
+ repo.ui.progress(_('searching'), None)
+
+ for dest, v in copies.iteritems():
+ source, score = v
+ yield source, dest, score
+
+def findrenames(repo, added, removed, threshold):
+ '''find renamed files -- yields (before, after, score) tuples'''
+ parentctx = repo['.']
+ workingctx = repo[None]
+
+ # Zero length files will be frequently unrelated to each other, and
+ # tracking the deletion/addition of such a file will probably cause more
+ # harm than good. We strip them out here to avoid matching them later on.
+ addedfiles = set([workingctx[fp] for fp in added
+ if workingctx[fp].size() > 0])
+ removedfiles = set([parentctx[fp] for fp in removed
+ if fp in parentctx and parentctx[fp].size() > 0])
+
+ # Find exact matches.
+ for (a, b) in _findexactmatches(repo,
+ sorted(addedfiles), sorted(removedfiles)):
+ addedfiles.remove(b)
+ yield (a.path(), b.path(), 1.0)
+
+ # If the user requested similar files to be matched, search for them also.
+ if threshold < 1.0:
+ for (a, b, score) in _findsimilarmatches(repo,
+ sorted(addedfiles), sorted(removedfiles), threshold):
+ yield (a.path(), b.path(), score)
+