arsenetar/dupeguru
1
0
Fork 0
mirror of https://github.com/arsenetar/dupeguru.git synced 2026-01-22 06:37:17 +00:00
Code Releases Wiki Activity

Converted to py3k. There's probably some bugs still. So far, I managed to run dupeGuru SE under pyobjc and qt.

Browse Source
This commit is contained in:
Virgil Dupras
2010-08-11 16:39:06 +02:00
parent fb79daad6a
commit 854d194f88
57 changed files with 394 additions and 338 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
core/tests/app_test.py
View File

@@ -109,7 +109,7 @@ class TCDupeGuru(TestCase):
def test_Scan_with_objects_evaluating_to_false(self):
class FakeFile(fs.File):
def __nonzero__(self):
def __bool__(self):
return False
@@ -200,11 +200,11 @@ class TCDupeGuruWithResults(TestCase):
if expected is not None:
expected = set(expected)
not_called = expected - calls
assert not not_called, u"These calls haven't been made: {0}".format(not_called)
assert not not_called, "These calls haven't been made: {0}".format(not_called)
if not_expected is not None:
not_expected = set(not_expected)
called = not_expected & calls
assert not called, u"These calls shouldn't have been made: {0}".format(called)
assert not called, "These calls shouldn't have been made: {0}".format(called)
gui.clear_calls()
def clear_gui_calls(self):
@@ -409,9 +409,9 @@ class TCDupeGuruWithResults(TestCase):
def test_only_unicode_is_added_to_ignore_list(self):
def FakeIgnore(first,second):
if not isinstance(first,unicode):
if not isinstance(first,str):
self.fail()
if not isinstance(second,unicode):
if not isinstance(second,str):
self.fail()
app = self.app
@@ -423,11 +423,11 @@ class TCDupeGuruWithResults(TestCase):
class TCDupeGuru_renameSelected(TestCase):
def setUp(self):
p = self.tmppath()
fp = open(unicode(p + 'foo bar 1'),mode='w')
fp = open(str(p + 'foo bar 1'),mode='w')
fp.close()
fp = open(unicode(p + 'foo bar 2'),mode='w')
fp = open(str(p + 'foo bar 2'),mode='w')
fp.close()
fp = open(unicode(p + 'foo bar 3'),mode='w')
fp = open(str(p + 'foo bar 3'),mode='w')
fp.close()
files = fs.get_files(p)
matches = engine.getmatches(files)

12
core/tests/directories_test.py
View File

@@ -82,8 +82,8 @@ class TCDirectories(TestCase):
def test_AddPath_non_latin(self):
p = Path(self.tmpdir())
to_add = p + u'unicode\u201a'
os.mkdir(unicode(to_add))
to_add = p + 'unicode\u201a'
os.mkdir(str(to_add))
d = Directories()
try:
d.add_path(to_add)
@@ -111,7 +111,7 @@ class TCDirectories(TestCase):
self.assertEqual(STATE_REFERENCE,d.get_state(p))
self.assertEqual(STATE_REFERENCE,d.get_state(p + 'dir1'))
self.assertEqual(1,len(d.states))
self.assertEqual(p,d.states.keys()[0])
self.assertEqual(p,list(d.states.keys())[0])
self.assertEqual(STATE_REFERENCE,d.states[p])
def test_get_state_with_path_not_there(self):
@@ -213,11 +213,11 @@ class TCDirectories(TestCase):
def test_unicode_save(self):
d = Directories()
p1 = self.tmppath() + u'hello\xe9'
p1 = self.tmppath() + 'hello\xe9'
io.mkdir(p1)
io.mkdir(p1 + u'foo\xe9')
io.mkdir(p1 + 'foo\xe9')
d.add_path(p1)
d.set_state(p1 + u'foo\xe9', STATE_EXCLUDED)
d.set_state(p1 + 'foo\xe9', STATE_EXCLUDED)
tmpxml = op.join(self.tmpdir(), 'directories_testunit.xml')
try:
d.save_to_file(tmpxml)

8
core/tests/engine_test.py
View File

@@ -62,12 +62,12 @@ class TCgetwords(TestCase):
def test_splitter_chars(self):
self.assertEqual(
[chr(i) for i in xrange(ord('a'),ord('z')+1)],
[chr(i) for i in range(ord('a'),ord('z')+1)],
getwords("a-b_c&d+e(f)g;h\\i[j]k{l}m:n.o,p<q>r/s?t~u!v@w#x$y*z")
)
def test_joiner_chars(self):
self.assertEqual(["aec"], getwords(u"a'e\u0301c"))
self.assertEqual(["aec"], getwords("a'e\u0301c"))
def test_empty(self):
self.assertEqual([], getwords(''))
@@ -76,7 +76,7 @@ class TCgetwords(TestCase):
self.assertEqual(['foo', 'bar'], getwords('FOO BAR'))
def test_decompose_unicode(self):
self.assertEqual(getwords(u'foo\xe9bar'), ['fooebar'])
self.assertEqual(getwords('foo\xe9bar'), ['fooebar'])
class TCgetfields(TestCase):
@@ -768,7 +768,7 @@ class TCget_groups(TestCase):
self.assert_(o3 in g)
def test_four_sized_group(self):
l = [NamedObject("foobar") for i in xrange(4)]
l = [NamedObject("foobar") for i in range(4)]
m = getmatches(l)
r = get_groups(m)
self.assertEqual(1,len(r))

20
core/tests/ignore_test.py
View File

@@ -6,7 +6,7 @@
# which should be included with this package. The terms are also available at
# http://www.hardcoded.net/licenses/hs_license
import cStringIO
import io
from lxml import etree
from hsutil.testutil import eq_
@@ -59,7 +59,7 @@ def test_save_to_xml():
il.Ignore('foo','bar')
il.Ignore('foo','bleh')
il.Ignore('bleh','bar')
f = cStringIO.StringIO()
f = io.BytesIO()
il.save_to_xml(f)
f.seek(0)
doc = etree.parse(f)
@@ -76,19 +76,19 @@ def test_SaveThenLoad():
il.Ignore('foo', 'bar')
il.Ignore('foo', 'bleh')
il.Ignore('bleh', 'bar')
il.Ignore(u'\u00e9', 'bar')
f = cStringIO.StringIO()
il.Ignore('\u00e9', 'bar')
f = io.BytesIO()
il.save_to_xml(f)
f.seek(0)
f.seek(0)
il = IgnoreList()
il.load_from_xml(f)
eq_(4,len(il))
assert il.AreIgnored(u'\u00e9','bar')
assert il.AreIgnored('\u00e9','bar')
def test_LoadXML_with_empty_file_tags():
f = cStringIO.StringIO()
f.write('<?xml version="1.0" encoding="utf-8"?><ignore_list><file><file/></file></ignore_list>')
f = io.BytesIO()
f.write(b'<?xml version="1.0" encoding="utf-8"?><ignore_list><file><file/></file></ignore_list>')
f.seek(0)
il = IgnoreList()
il.load_from_xml(f)
@@ -130,12 +130,12 @@ def test_filter():
def test_save_with_non_ascii_items():
il = IgnoreList()
il.Ignore(u'\xac', u'\xbf')
f = cStringIO.StringIO()
il.Ignore('\xac', '\xbf')
f = io.BytesIO()
try:
il.save_to_xml(f)
except Exception as e:
raise AssertionError(unicode(e))
raise AssertionError(str(e))
def test_len():
il = IgnoreList()

42
core/tests/results_test.py
View File

@@ -7,7 +7,7 @@
# which should be included with this package. The terms are also available at
# http://www.hardcoded.net/licenses/hs_license
import StringIO
import io
import os.path as op
from lxml import etree
@@ -25,7 +25,7 @@ class NamedObject(engine_test.NamedObject):
path = property(lambda x:Path('basepath') + x.name)
is_ref = False
def __nonzero__(self):
def __bool__(self):
return False #Make sure that operations are made correctly when the bool value of files is false.
# Returns a group set that looks like that:
@@ -63,7 +63,7 @@ class TCResultsEmpty(TestCase):
self.assert_(self.results.get_group_of_duplicate('foo') is None)
def test_save_to_xml(self):
f = StringIO.StringIO()
f = io.BytesIO()
self.results.save_to_xml(f)
f.seek(0)
doc = etree.parse(f)
@@ -324,7 +324,7 @@ class TCResultsMarkings(TestCase):
def test_SaveXML(self):
self.results.mark(self.objects[1])
self.results.mark_invert()
f = StringIO.StringIO()
f = io.BytesIO()
self.results.save_to_xml(f)
f.seek(0)
doc = etree.parse(f)
@@ -345,7 +345,7 @@ class TCResultsMarkings(TestCase):
self.objects[4].name = 'ibabtu 2' #we can't have 2 files with the same path
self.results.mark(self.objects[1])
self.results.mark_invert()
f = StringIO.StringIO()
f = io.BytesIO()
self.results.save_to_xml(f)
f.seek(0)
r = Results(data)
@@ -369,7 +369,7 @@ class TCResultsXML(TestCase):
def test_save_to_xml(self):
self.objects[0].is_ref = True
self.objects[0].words = [['foo','bar']]
f = StringIO.StringIO()
f = io.BytesIO()
self.results.save_to_xml(f)
f.seek(0)
doc = etree.parse(f)
@@ -408,7 +408,7 @@ class TCResultsXML(TestCase):
self.objects[0].is_ref = True
self.objects[4].name = 'ibabtu 2' #we can't have 2 files with the same path
f = StringIO.StringIO()
f = io.BytesIO()
self.results.save_to_xml(f)
f.seek(0)
r = Results(data)
@@ -451,7 +451,7 @@ class TCResultsXML(TestCase):
return [f for f in self.objects if str(f.path) == path][0]
self.objects[4].name = 'ibabtu 2' #we can't have 2 files with the same path
f = StringIO.StringIO()
f = io.BytesIO()
self.results.save_to_xml(f)
f.seek(0)
r = Results(data)
@@ -490,7 +490,7 @@ class TCResultsXML(TestCase):
match_node.set('percentage', 'baz')
group_node = etree.SubElement(root, 'foobar') #invalid group
group_node = etree.SubElement(root, 'group') #empty group
f = StringIO.StringIO()
f = io.BytesIO()
tree = etree.ElementTree(root)
tree.write(f, encoding='utf-8')
f.seek(0)
@@ -501,30 +501,30 @@ class TCResultsXML(TestCase):
def test_xml_non_ascii(self):
def get_file(path):
if path == op.join('basepath',u'\xe9foo bar'):
if path == op.join('basepath','\xe9foo bar'):
return objects[0]
if path == op.join('basepath',u'bar bleh'):
if path == op.join('basepath','bar bleh'):
return objects[1]
objects = [NamedObject(u"\xe9foo bar",True),NamedObject("bar bleh",True)]
objects = [NamedObject("\xe9foo bar",True),NamedObject("bar bleh",True)]
matches = engine.getmatches(objects) #we should have 5 matches
groups = engine.get_groups(matches) #We should have 2 groups
for g in groups:
g.prioritize(lambda x:objects.index(x)) #We want the dupes to be in the same order as the list is
results = Results(data)
results.groups = groups
f = StringIO.StringIO()
f = io.BytesIO()
results.save_to_xml(f)
f.seek(0)
r = Results(data)
r.load_from_xml(f,get_file)
g = r.groups[0]
self.assertEqual(u"\xe9foo bar",g[0].name)
self.assertEqual("\xe9foo bar",g[0].name)
self.assertEqual(['efoo','bar'],g[0].words)
def test_load_invalid_xml(self):
f = StringIO.StringIO()
f.write('<this is invalid')
f = io.BytesIO()
f.write(b'<this is invalid')
f.seek(0)
r = Results(data)
r.load_from_xml(f,None)
@@ -546,7 +546,7 @@ class TCResultsXML(TestCase):
fake_matches.add(engine.Match(d1, d3, 43))
fake_matches.add(engine.Match(d2, d3, 46))
group.matches = fake_matches
f = StringIO.StringIO()
f = io.BytesIO()
results = self.results
results.save_to_xml(f)
f.seek(0)
@@ -564,7 +564,7 @@ class TCResultsXML(TestCase):
def test_save_and_load(self):
# previously, when reloading matches, they wouldn't be reloaded as namedtuples
f = StringIO.StringIO()
f = io.BytesIO()
self.results.save_to_xml(f)
f.seek(0)
self.results.load_from_xml(f, self.get_file)
@@ -572,13 +572,13 @@ class TCResultsXML(TestCase):
def test_apply_filter_works_on_paths(self):
# apply_filter() searches on the whole path, not just on the filename.
self.results.apply_filter(u'basepath')
self.results.apply_filter('basepath')
eq_(len(self.results.groups), 2)
def test_save_xml_with_invalid_characters(self):
# Don't crash when saving files that have invalid xml characters in their path
self.objects[0].name = u'foo\x19'
self.results.save_to_xml(StringIO.StringIO()) # don't crash
self.objects[0].name = 'foo\x19'
self.results.save_to_xml(io.BytesIO()) # don't crash
class TCResultsFilter(TestCase):

19
core/tests/scanner_test.py
View File

@@ -25,6 +25,9 @@ class NamedObject(object):
self.path = Path('')
self.words = getwords(name)
def __repr__(self):
return '<NamedObject %r>' % self.name
no = NamedObject
@@ -297,8 +300,8 @@ class ScannerTestFakeFiles(TestCase):
s.scanned_tags = set(['title'])
o1 = no('foo')
o2 = no('bar')
o1.title = u'foobar\u00e9'
o2.title = u'foobar\u00e9'
o1.title = 'foobar\u00e9'
o2.title = 'foobar\u00e9'
try:
r = s.GetDupeGroups([o1, o2])
except UnicodeEncodeError:
@@ -362,11 +365,11 @@ class ScannerTestFakeFiles(TestCase):
f1 = no('foobar')
f2 = no('foobar')
f3 = no('foobar')
f1.path = Path(u'foo1\u00e9')
f2.path = Path(u'foo2\u00e9')
f3.path = Path(u'foo3\u00e9')
s.ignore_list.Ignore(unicode(f1.path),unicode(f2.path))
s.ignore_list.Ignore(unicode(f1.path),unicode(f3.path))
f1.path = Path('foo1\u00e9')
f2.path = Path('foo2\u00e9')
f3.path = Path('foo3\u00e9')
s.ignore_list.Ignore(str(f1.path),str(f2.path))
s.ignore_list.Ignore(str(f1.path),str(f3.path))
r = s.GetDupeGroups([f1,f2,f3])
eq_(len(r), 1)
g = r[0]
@@ -379,7 +382,7 @@ class ScannerTestFakeFiles(TestCase):
# A very wrong way to use any() was added at some point, causing resulting group list
# to be empty.
class FalseNamedObject(NamedObject):
def __nonzero__(self):
def __bool__(self):
return False