1
0
mirror of https://github.com/arsenetar/dupeguru.git synced 2025-05-07 09:19:50 +00:00

Compare commits

...

5 Commits

Author SHA1 Message Date
0b46ca2222
Merge pull request #879 from glubsy/fix_unicode
Fix stripping (japanese) unicode characters
2021-05-25 19:11:19 -05:00
72e0f76242
Merge pull request #898 from AlttiRi/master
Change reference background color #894
2021-05-25 19:10:31 -05:00
[Alt'tiRi]
65c1d463f8
Change reference background color #894 2021-05-22 02:52:41 +03:00
glubsy
f1ae478433 Fix including character at the border 2021-04-29 05:29:35 +02:00
glubsy
c4dcfd3d4b Fix stripping (japanese) unicode characters
* Accents are getting removed from Unicode characters to generate similar "words".
* Non-latin characters which cannot be processed that way (eg. japanese, greek, russian, etc.) should not be filtered out at all otherwise files are erroneously skipped or detected as dupes if only some characters make it passed the filter.
* Starting from an arbitrary unicode codepoint (converted to decimal), above which we know it is pointless to try any sort of processing, we leave the characters as is.
* Fix #878.
2021-04-29 05:15:34 +02:00
3 changed files with 18 additions and 3 deletions

View File

@ -26,8 +26,19 @@ def getwords(s):
# We decompose the string so that ascii letters with accents can be part of the word.
s = normalize("NFD", s)
s = multi_replace(s, "-_&+():;\\[]{}.,<>/?~!@#$*", " ").lower()
# logging.debug(f"DEBUG chars for: {s}\n"
# f"{[c for c in s if ord(c) != 32]}\n"
# f"{[ord(c) for c in s if ord(c) != 32]}")
# HACK We shouldn't ignore non-ascii characters altogether. Any Unicode char
# above common european characters that cannot be "sanitized" (ie. stripped
# of their accents, etc.) are preserved as is. The arbitrary limit is
# obtained from this one: ord("\u037e") GREEK QUESTION MARK
s = "".join(
c for c in s if c in string.ascii_letters + string.digits + string.whitespace
c for c in s
if (ord(c) <= 894
and c in string.ascii_letters + string.digits + string.whitespace
)
or ord(c) > 894
)
return [_f for _f in s.split(" ") if _f] # remove empty elements

View File

@ -69,6 +69,10 @@ class TestCasegetwords:
eq_(["a", "b", "c", "d"], getwords("a b c d"))
eq_(["a", "b", "c", "d"], getwords(" a b c d "))
def test_unicode(self):
eq_(["e", "c", "0", "a", "o", "u", "e", "u"], getwords("é ç 0 à ö û è ¤ ù"))
eq_(["02", "君のこころは輝いてるかい?", "国木田花丸", "solo", "ver"], getwords("02 君のこころは輝いてるかい? 国木田花丸 Solo Ver"))
def test_splitter_chars(self):
eq_(
[chr(i) for i in range(ord("a"), ord("z") + 1)],
@ -85,7 +89,7 @@ class TestCasegetwords:
eq_(["foo", "bar"], getwords("FOO BAR"))
def test_decompose_unicode(self):
eq_(getwords("foo\xe9bar"), ["fooebar"])
eq_(["fooebar"], getwords("foo\xe9bar"))
class TestCasegetfields:

View File

@ -102,7 +102,7 @@ class Preferences(PreferencesBase):
self.details_dialog_override_theme_icons = False if not ISLINUX else True
self.details_dialog_viewers_show_scrollbars = True
self.result_table_ref_foreground_color = QColor(Qt.blue)
self.result_table_ref_background_color = QColor(Qt.darkGray)
self.result_table_ref_background_color = QColor(Qt.lightGray)
self.result_table_delta_foreground_color = QColor(255, 142, 40) # orange
self.resultWindowIsMaximized = False
self.resultWindowRect = None