From 208ea8ea4c7b680380a65d5a3795eedbcd10be9e Mon Sep 17 00:00:00 2001
From: Jim Huang <jserv@ccns.ncku.edu.tw>
Date: Sat, 22 Feb 2025 00:30:59 +0800
Subject: [PATCH 1/2] 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
---
 scripts/aspell-pws      | 1 +
 scripts/commit-msg.hook | 9 ++++++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/scripts/aspell-pws b/scripts/aspell-pws
index 00d2a452b..6deba882c 100644
--- a/scripts/aspell-pws
+++ b/scripts/aspell-pws
@@ -300,3 +300,4 @@ sed
 changeid
 en
 msg
+cjk
diff --git a/scripts/commit-msg.hook b/scripts/commit-msg.hook
index d542d0bea..c9b6979f3 100755
--- a/scripts/commit-msg.hook
+++ b/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

From a1da15f9c8027fe4039acc79489ab0178b4b72b5 Mon Sep 17 00:00:00 2001
From: Jim Huang <jserv@ccns.ncku.edu.tw>
Date: Sat, 22 Feb 2025 00:46:38 +0800
Subject: [PATCH 2/2] Remove quoted text for spell checking

This removes any text enclosed in single or double quotes.

Change-Id: Id65506bb0f4470ecf4ece58cb88f4c9f22d9afd7
---
 scripts/aspell-pws      | 31 +++++++++++++++++++++++++++++++
 scripts/commit-msg.hook |  7 +++++--
 2 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/scripts/aspell-pws b/scripts/aspell-pws
index 6deba882c..6acafb22b 100644
--- a/scripts/aspell-pws
+++ b/scripts/aspell-pws
@@ -301,3 +301,34 @@ changeid
 en
 msg
 cjk
+massif
+csapp
+cmu
+ele
+lima
+github
+ih
+it
+AddressSanitizer
+asan
+dbg
+dev
+dpkg
+apt
+siglongjmp
+sigsetjmp
+SIGABRT
+SIGALRM
+SIGBUS
+SIGFPE
+SIGHUP
+SIGILL
+SIGINT
+SIGKILL
+SIGPIPE
+SIGQUIT
+SIGSEGV
+SIGTERM
+SIGTRAP
+SIGUSR
+SIGWINCH
diff --git a/scripts/commit-msg.hook b/scripts/commit-msg.hook
index c9b6979f3..747d66fb4 100755
--- a/scripts/commit-msg.hook
+++ b/scripts/commit-msg.hook
@@ -341,8 +341,11 @@ validate_commit_message() {
     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" | $ASPELL --lang=en --list --home-dir=scripts --personal=aspell-pws)
+  # Remove quoted text from FULL_COMMIT_MSG for spell checking.
+  MSG_FOR_SPELLCHECK=$(echo "$FULL_COMMIT_MSG" | sed -E "s/(['\"][^'\"]*['\"])//g")
+
+  # Use aspell to list misspelled words according to American English, ignoring quoted text.
+  MISSPELLED_WORDS=$(echo "$MSG_FOR_SPELLCHECK" | $ASPELL --lang=en --list --home-dir=scripts --personal=aspell-pws)
   if [ -n "$MISSPELLED_WORDS" ]; then
     add_warning 1 "Avoid using non-American English words"
   fi