[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
gagan3012 · Jan 20, 2025 · c3763ca · c3763ca
1 parent f51b50a
commit c3763ca
Show file tree

Hide file tree

Showing 2 changed files with 2,907 additions and 2,905 deletions.
diff --git a/PolyDeDupe/non_alpha.py b/PolyDeDupe/non_alpha.py
@@ -2,33 +2,33 @@
 
 NON_ALPHA = re.compile(
     "[^"
-    "\u0080-\u00FF"  # Latin-1 Supplement (covers many Western European languages)
-    "\u0100-\u017F"  # Latin Extended-A (Central European, Baltic, etc.)
-    "\u0180-\u024F"  # Latin Extended-B (additional European languages)
-    "\u1E00-\u1EFF"  # Latin Extended Additional (covers Vietnamese, some African languages)
-    "\u0400-\u04FF"  # Cyrillic (covers Russian, Bulgarian, Serbian, etc.)
-    "\u0370-\u03FF"  # Greek and Coptic
-    "\u1F00-\u1FFF"  # Greek Extended
+    "\u0080-\u00ff"  # Latin-1 Supplement (covers many Western European languages)
+    "\u0100-\u017f"  # Latin Extended-A (Central European, Baltic, etc.)
+    "\u0180-\u024f"  # Latin Extended-B (additional European languages)
+    "\u1e00-\u1eff"  # Latin Extended Additional (covers Vietnamese, some African languages)
+    "\u0400-\u04ff"  # Cyrillic (covers Russian, Bulgarian, Serbian, etc.)
+    "\u0370-\u03ff"  # Greek and Coptic
+    "\u1f00-\u1fff"  # Greek Extended
     # Including your original ranges
-    "\u0600-\u06FF"  # Arabic
-    "\u07C0-\u07FF"  # N'Ko
-    "\u0900-\u097F"  # Devanagari (Hindi, Marathi, Sanskrit)
-    "\u1200-\u137F"  # Ethiopic (Amharic, Tigrinya)
-    "\u2D30-\u2D7F"  # Tifinagh (Berber languages)
-    "\uA500-\uA63F"  # Vai (West African)
+    "\u0600-\u06ff"  # Arabic
+    "\u07c0-\u07ff"  # N'Ko
+    "\u0900-\u097f"  # Devanagari (Hindi, Marathi, Sanskrit)
+    "\u1200-\u137f"  # Ethiopic (Amharic, Tigrinya)
+    "\u2d30-\u2d7f"  # Tifinagh (Berber languages)
+    "\ua500-\ua63f"  # Vai (West African)
     # Additional language ranges
-    "\u4E00-\u9FFF"  # CJK Unified Ideographs (Chinese)
-    "\uAC00-\uD7AF"  # Hangul Syllables (Korean)
-    "\u3040-\u309F\u30A0-\u30FF"  # Hiragana and Katakana (Japanese)
-    "\u0B80-\u0BFF"  # Tamil
-    "\u0C00-\u0C7F"  # Telugu
-    "\u0C80-\u0CFF"  # Kannada
-    "\u0D00-\u0D7F"  # Malayalam
-    "\u0980-\u09FF"  # Bengali
-    "\u0A00-\u0A7F"  # Gurmukhi (Punjabi)
-    "\u0A80-\u0AFF"  # Gujarati
-    "\u0B00-\u0B7F"  # Oriya
-    "\u0750-\u077F"  # Arabic Supplement
+    "\u4e00-\u9fff"  # CJK Unified Ideographs (Chinese)
+    "\uac00-\ud7af"  # Hangul Syllables (Korean)
+    "\u3040-\u309f\u30a0-\u30ff"  # Hiragana and Katakana (Japanese)
+    "\u0b80-\u0bff"  # Tamil
+    "\u0c00-\u0c7f"  # Telugu
+    "\u0c80-\u0cff"  # Kannada
+    "\u0d00-\u0d7f"  # Malayalam
+    "\u0980-\u09ff"  # Bengali
+    "\u0a00-\u0a7f"  # Gurmukhi (Punjabi)
+    "\u0a80-\u0aff"  # Gujarati
+    "\u0b00-\u0b7f"  # Oriya
+    "\u0750-\u077f"  # Arabic Supplement
     "A-Za-z_0-9"  # General Latin, numerals, and underscore
     "]"
 )