refactor: unify PUNCTUATION constants in domain/split_pattern.py

abogen/domain/split_pattern.py

@@ -5,8 +5,12 @@ import re
 
 from abogen.domain.enums import Language, SubtitleMode
 
-PUNCTUATION_SENTENCE = r".!?。！？"
+# Canonical punctuation sets covering all supported scripts:
-PUNCTUATION_SENTENCE_COMMA = r".!?,。！？、，"
+# ASCII (. ! ?), Arabic ؟, CJK (。！？), Devanagari ।
+PUNCTUATION_SENTENCE = r".!?؟。！？।"
+# Commas: ASCII , CJK fullwidth ，CJK ideographic 、
+PUNCTUATION_SENTENCE_COMMA = r".!?,？。！？،，、।"
+PUNCTUATION_COMMAS = ",，、"
 
 
 def get_split_pattern(language: str, subtitle_mode: str) -> str:

abogen/domain/subtitle_generation.py

@@ -11,11 +11,7 @@ import re
 from typing import List, Optional, Tuple
 
 from abogen.domain.enums import Language, SubtitleMode
-
+from abogen.domain.split_pattern import PUNCTUATION_SENTENCE, PUNCTUATION_SENTENCE_COMMA
-
-# Punctuation constants for sentence splitting
-PUNCTUATION_SENTENCE = ".!?\u061f\u3002\uff01\uff1f"  # .!? .?. ??
-PUNCTUATION_SENTENCE_COMMA = ".!?,\u3001\u061f\u3002\uff01\uff0c\uff1f"  # .!?, ,. ??
 
 
 def process_subtitle_tokens(
@@ -87,7 +83,7 @@ def _process_karaoke_highlighting(
     fallback_end_time: Optional[float],
 ) -> None:
     """Process tokens for Sentence + Highlighting mode (karaoke effect)."""
-    separator = rf"[{re.escape(PUNCTUATION_SENTENCE)}]"
+    separator = rf"[{PUNCTUATION_SENTENCE}]"
     current_sentence = []
     word_count = 0
 
@@ -247,11 +243,9 @@ def _process_regex_sentences(
     if subtitle_mode == SubtitleMode.LINE:
         separator = r"\n"
     elif subtitle_mode == SubtitleMode.SENTENCE:
-        # Use punctuation without comma
+        separator = rf"[{PUNCTUATION_SENTENCE}]"
-        separator = rf"[{re.escape(PUNCTUATION_SENTENCE)}]"
     else:  # Sentence + Comma
-        # Use punctuation with comma
+        separator = rf"[{PUNCTUATION_SENTENCE_COMMA}]"
-        separator = rf"[{re.escape(PUNCTUATION_SENTENCE_COMMA)}]"
 
     current_sentence = []
     word_count = 0

abogen/pyqt/conversion.py

@@ -78,6 +78,7 @@ from abogen.subtitle_utils import (
     sanitize_name_for_os,
     split_text_by_voice_markers
 )
+from abogen.domain.split_pattern import PUNCTUATION_SENTENCE, PUNCTUATION_SENTENCE_COMMA, PUNCTUATION_COMMAS
 
 class CountdownDialog(QDialog):
     """Base dialog with auto-accept countdown functionality"""
@@ -241,11 +242,6 @@ class ConversionThread(QThread):
     log_updated = pyqtSignal(object)  # Updated signal for log updates
     chapters_detected = pyqtSignal(int)  # Signal for chapter detection
 
-    # Punctuation constants for unified handling across languages
-    PUNCTUATION_SENTENCE = ".!?।。！？"
-    PUNCTUATION_SENTENCE_COMMA = ".!?,।。！？、，"
-    PUNCTUATION_COMMAS = ",，、"
-
     def __init__(
         self,
         file_name,
@@ -932,7 +928,7 @@ class ConversionThread(QThread):
                             # For Sentence + Comma mode, still split on commas within spaCy sentences
                             if self.subtitle_mode == "Sentence + Comma":
                                 active_split_pattern = r"(?<=[{}]){}|\n+".format(
-                                    self.PUNCTUATION_COMMAS, spacing_pattern
+                                    PUNCTUATION_COMMAS, spacing_pattern
                                 )
                             else:
                                 active_split_pattern = (