Skip to content

fix: resolve Python 3.12 SyntaxWarning for invalid escape sequences #85

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Yusuf-Gadelrab wants to merge 2 commits into
base: master
Choose a base branch
from
Open

fix: resolve Python 3.12 SyntaxWarning for invalid escape sequences #85

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6b6c71d
fix: resolve Python 3.12 SyntaxWarning for invalid escape sequences i…
Yusuf-Gadelrab Aug 10, 2026
e9d16ba
fix: complete Python 3.12+ SyntaxWarning cleanup in trans.py and arab…
Yusuf-Gadelrab Aug 13, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions pyarabic/araby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -271,14 +271,14 @@
# ~ """ all alef like letters """
LIGUATURES_PATTERN = re.compile(u"[" + u"".join(LIGUATURES) + u"]", re.UNICODE)
# ~ """ all liguatures pattern """
TOKEN_PATTERN = re.compile(u"([^\w\u0670\u064b-\u0652']+)", re.UNICODE)
TOKEN_PATTERN = re.compile(r"([^\w\u0670\u064b-\u0652']+)", re.UNICODE)
# ~ """ pattern to tokenize a text"""
TOKEN_PATTERN_SPLIT = re.compile(u"([\w\u0670\u064b-\u0652']+)", re.UNICODE)
TOKEN_PATTERN_SPLIT = re.compile(r"([\w\u0670\u064b-\u0652']+)", re.UNICODE)
# ~ """ pattern to tokenize a text with positions"""
TOKEN_REPLACE = re.compile(u'\t|\r|\f|\v| ')

# Arabic string
ARABIC_STRING = re.compile(u"([^\u0600-\u0652%s%s%s\s\d])" \
ARABIC_STRING = re.compile(r"([^\u0600-\u0652%s%s%s\s\d])" \
% (LAM_ALEF, LAM_ALEF_HAMZA_ABOVE, LAM_ALEF_MADDA_ABOVE), re.UNICODE)
# Arabic range
ARABIC_RANGE = re.compile(
Expand Down Expand Up @@ -1234,7 +1234,7 @@ def reduce_tashkeel(text):
u"%s(?=%s)" % (FATHA, ALEF), \
# delete fatha from yeh and waw if they are in the word begining.

u"(?<=\s(%s|%s))%s" % (WAW, YEH, FATHA), \
r"(?<=\s(%s|%s))%s" % (WAW, YEH, FATHA), \
# delete kasra if preceded by Hamza below alef.

u"(?<=%s)%s" % (ALEF_HAMZA_BELOW, KASRA), \
Expand Down Expand Up @@ -1447,7 +1447,7 @@ def autocorrect(text):
@rtype: unicode
"""
## HARAKAT
text = re.sub(u"(?<=[\s\d])([%s])+"%(TASHKEEL_STRING),"",text, re.UNICODE)
text = re.sub(r"(?<=[\s\d])([%s])+"%(TASHKEEL_STRING),"",text, re.UNICODE)
text = re.sub(u"^([%s])+"%(TASHKEEL_STRING),"",text , re.UNICODE)
# tanwin on alef
text = re.sub(ALEF+FATHATAN, FATHATAN + ALEF,text , re.UNICODE)
Expand Down
2 changes: 1 addition & 1 deletion pyarabic/araby_const.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -268,4 +268,4 @@
#~ """ all alef like letters """
LIGUATURES_PATTERN = re.compile(u"["+u"".join(LIGUATURES)+u"]", re.UNICODE)
#~ """ all liguatures pattern """
TOKEN_PATTERN = re.compile(u"[^\w\u064b-\u0652']+", re.UNICODE)
TOKEN_PATTERN = re.compile(r"[^\w\u064b-\u0652']+", re.UNICODE)
4 changes: 2 additions & 2 deletions pyarabic/trans.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -316,7 +316,7 @@ def segment_language(text):
resultlist.append(('latin', actual_text))
arabic = True
actual_text = k
elif re.search(u"[\s\d\?, :\!\(\)]", k):
elif re.search(r"[\s\d\?, :\!\(\)]", k):
actual_text += k
else:
if arabic:
Expand Down Expand Up @@ -515,7 +515,7 @@ def decode_tashkeel(word, marks, method = "ascii"):
# test detect language
text =u"""السلام عليكم how are you, لم اسمع أخبارك منذ مدة, where are you going"""
print(arepr(segment_language(text)))
text_out= delimite_language(text, start='\RL{', end="}")
text_out= delimite_language(text, start=r'\RL{', end="}")
print(text_out.encode('utf8'))
text_out= delimite_language(text, start="<arabic>", end="</arabic>")
print(text_out.encode('utf8'))