is_cjk

1 files changed, 46 insertions, 0 deletions

diff --git a/python/cjk.py b/python/cjk.py
new file mode 100644
index 0000000..9a417d1
--- /dev/null
+++ b/python/cjk.py
@@ -0,0 +1,46 @@
+#!/usr/bin/env python
+
+# Chinese
+ranges = [{"from":"\u4E00",  "to":"\u9FFF"},   # CJK Unified Ideographs
+          {"from":"\u3400",  "to":"\u4DBF"},   # CJK Unified Ideographs Extension A
+          #{"from":"\u20000", "to":"\u2A6DF"}, # CJK Unified Ideographs Extension B
+          #{"from":"\u2A700", "to":"\u2B73F"}, # CJK Unified Ideographs Extension C
+          #{"from":"\u2B740", "to":"\u2B81F"}, # CJK Unified Ideographs Extension D
+          #{"from":"\u2B820", "to":"\u2CEAF"}, # CJK Unified Ideographs Extension E
+          #{"from":"\u2B820", "to":"\u2CEAF"}, # CJK Unified Ideographs Extension F
+          {"from":"\u2E80",  "to":"\u2EFF"},   # CJK Radicals Supplement
+          {"from":"\u2F00",  "to":"\u2FDF"},   # Kangxi Radicals
+          {"from":"\u2FF0",  "to":"\u2FFF"},   # Ideographic Description Characters
+          {"from":"\u31C0",  "to":"\u31EF"},   # CJK Strokes
+          {"from":"\u3200",  "to":"\u32FF"},   # Enclosed CJK Letters and Months
+          {"from":"\u3300",  "to":"\u33FF"},   # CJK Compatibility
+          {"from":"\uF900",  "to":"\uFAFF"},   # CJK Compatibility Ideographs
+          #{"from":"\u1F200", "to":"\u1F2FF"}, # Enclosed Ideographic Supplement
+          #{"from":"\u2F800", "to":"\u2FA1F"}  # CJK Compatibility Ideographs Supplement
+          ]
+
+# Japanese
+ranges.extend([{"from":"\u3040", "to":"\u309F"},   # Hiragana
+              #{"from":"\u1B100", "to":"\u1B12F"}, # Kana Extended-A
+              #{"from":"\u1B000", "to":"\u1B0FF"}, # Kana Supplement
+              {"from":"\u30A0",  "to":"\u30FF"},   # Katakana
+              {"from":"\u31F0",  "to":"\u31FF"}])  # Katakana Phonetic Extensions
+
+# Korean
+ranges.extend([{"from":"\u1100", "to":"\u11FF"},  # Hangul Jamo
+               {"from":"\uA960", "to":"\uA97F"},  # Hangul Jamo Extended-A
+               {"from":"\uD7B0", "to":"\uD7FF"},  # Hangul Jamo Extended-B
+               {"from":"\u3130", "to":"\u318F"},  # Hangul Compatibility Jamo
+               {"from":"\uAC00", "to":"\uD7AF"}]) # Hangul Syllables
+
+# Punctuation, etc.
+ranges.extend([{"from":"\u3000",  "to":"\u303F"},   # CJK Symbols and Punctuation
+               #{"from":"\u16FE0", "to":"\u16FFF"}, # Ideographic Symbols and Punctuation
+               {"from":"\uFE30",  "to":"\uFE4F"},   # CJK Compatibility Forms 
+               {"from":"\uFE50",  "to":"\uFE6F"},   # Small Form Variants
+               {"from":"\uFE10",  "to":"\uFE1F"},   # Vertical Forms
+               {"from":"\uFF00",  "to":"\uFFEF"}])  # Halfwidth and Fullwidth Forms
+
+def is_cjk(char):
+  return any([ord(range["from"]) <= ord(char) <= ord(range["to"]) for range in ranges])
+