From 6b6c71d5dab0884bbcc6703b949ccaedf0d0cffd Mon Sep 17 00:00:00 2001
From: Yusuf Gadelrab <yusuf.gadelrab06@gmail.com>
Date: Mon, 10 Aug 2026 23:42:00 +0000
Subject: [PATCH 1/2] fix: resolve Python 3.12 SyntaxWarning for invalid escape
 sequences in regex literals

---
 pyarabic/araby.py | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/pyarabic/araby.py b/pyarabic/araby.py
index 0476a67..e79de32 100644
--- a/pyarabic/araby.py
+++ b/pyarabic/araby.py
@@ -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(
@@ -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), \
@@ -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)        

From e9d16bace58779d48eb320d1cf74d5d51f0295b3 Mon Sep 17 00:00:00 2001
From: Yusuf Gadelrab <yusuf.gadelrab06@gmail.com>
Date: Thu, 13 Aug 2026 19:55:09 +0000
Subject: [PATCH 2/2] fix: complete Python 3.12+ SyntaxWarning cleanup in
 trans.py and araby_const.py

The initial commit in this PR fixed araby.py, but three invalid escape
sequences remained elsewhere in the package, so importing pyarabic still
emitted SyntaxWarnings:

- araby_const.py:271 - \w in TOKEN_PATTERN
- trans.py:319       - \s \d \? \! \( \) in a character class
- trans.py:518       - '\RL{' LaTeX delimiter in the __main__ demo

All three are converted to raw strings, which is byte-identical for the
trans.py cases. For araby_const.py the \uXXXX escapes move from Python
to the re module, which supports them identically; equivalence was
verified by differential testing (see PR description).

trans.py CRLF line endings and UTF-8 BOM are preserved.
---
 pyarabic/araby_const.py | 2 +-
 pyarabic/trans.py       | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/pyarabic/araby_const.py b/pyarabic/araby_const.py
index 5abb204..5b61261 100644
--- a/pyarabic/araby_const.py
+++ b/pyarabic/araby_const.py
@@ -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)
diff --git a/pyarabic/trans.py b/pyarabic/trans.py
index 965234a..0f8fae7 100644
--- a/pyarabic/trans.py
+++ b/pyarabic/trans.py
@@ -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:
@@ -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'))