view hgeditor @ 27699:c8d3392f76e1

encoding: handle UTF-16 internal limit with fromutf8b (issue5031)

Default builds of Python have a Unicode type that isn't actually full
Unicode but UTF-16, which encodes non-BMP codepoints to a pair of BMP
codepoints with surrogate escaping. Since our UTF-8b hack escaping
uses a plane that overlaps with the UTF-16 escaping system, this gets
extra complicated. In addition, unichr() for codepoints greater than
U+FFFF may not work either.

This changes the code to reuse getutf8char to walk the byte string, so we
only rely on Python for unpacking our U+DCxx characters.

#!/bin/sh
#
# This is an example of using HGEDITOR to create of diff to review the
# changes while committing.

# If you want to pass your favourite editor some other parameters
# only for Mercurial, modify this:
case "${EDITOR}" in
    "")
        EDITOR="vi"
        ;;
    emacs)
        EDITOR="$EDITOR -nw"
        ;;
    gvim|vim)
        EDITOR="$EDITOR -f -o"
        ;;
esac


HGTMP=""
cleanup_exit() {
    rm -rf "$HGTMP"
}

# Remove temporary files even if we get interrupted
trap "cleanup_exit" 0 # normal exit
trap "exit 255" HUP INT QUIT ABRT TERM

HGTMP=$(mktemp -d ${TMPDIR-/tmp}/hgeditor.XXXXXX)
[ x$HGTMP != x -a -d $HGTMP ] || {
  echo "Could not create temporary directory! Exiting." 1>&2
  exit 1
}

(
    grep '^HG: changed' "$1" | cut -b 13- | while read changed; do
        "$HG" diff "$changed" >> "$HGTMP/diff"
    done
)

cat "$1" > "$HGTMP/msg"

MD5=$(which md5sum 2>/dev/null) || \
    MD5=$(which md5 2>/dev/null)
[ -x "${MD5}" ] && CHECKSUM=`${MD5} "$HGTMP/msg"`
if [ -s "$HGTMP/diff" ]; then
    $EDITOR "$HGTMP/msg" "$HGTMP/diff" || exit $?
else
    $EDITOR "$HGTMP/msg" || exit $?
fi
[ -x "${MD5}" ] && (echo "$CHECKSUM" | ${MD5} -c >/dev/null 2>&1 && exit 13)

mv "$HGTMP/msg" "$1"

exit $?