Alert if the commit message is written in Chinese

The hook checks for the presence of characters in the typical Chinese
Unicode range (e.g., CJK Unified Ideographs).

Change-Id: I186bfd3ffd79868ddb1f51b4052fa4397fe19be5

Author: jserv

scripts/aspell-pws

@@ -300,3 +300,4 @@ sed
 changeid
 en
 msg
+cjk

scripts/commit-msg.hook

@@ -277,7 +277,7 @@ validate_commit_message() {
     add_warning 1 "Avoid mentioning C source filenames in the commit subject"
   fi
 
-  # 11a. Disallow parentheses in the commit subject.
+  # 7b. Disallow parentheses in the commit subject.
   if [[ ${COMMIT_SUBJECT_TO_PROCESS} =~ [\(\)] ]]; then
     add_warning 1 "Avoid using parentheses '()' in commit subjects"
   fi
@@ -334,6 +334,13 @@ validate_commit_message() {
   # 13. Always use American English.
   # ------------------------------------------------------------------------------
 
+  # Alert if the commit message appears to be written in Chinese.
+  # This pattern matches any Chinese character (common CJK Unified Ideographs).
+  MISSPELLED_WORDS=$(echo "$FULL_COMMIT_MSG" | grep "[一-龥]")
+  if [ -n "$MISSPELLED_WORDS" ]; then
+    add_warning 1 "Commit message appears to be written in Chinese: $MISSPELLED_WORDS"
+  fi
+
   # Use aspell to list misspelled words according to American English.
   MISSPELLED_WORDS=$(echo "$FULL_COMMIT_MSG" | $ASPELL --lang=en --list --home-dir=scripts --personal=aspell-pws)
   if [ -n "$MISSPELLED_WORDS" ]; then