view tests/test-encoding @ 12408:78a97859b90d

revset: support raw string literals

This adds support for r'...' and r"..." as string literals. Strings
with the "r" prefix will not have their escape characters interpreted.

This is especially useful for grep(), where, with regular string
literals, \number is interpreted as an octal escape code, and \b is
interpreted as the backspace character (\x08).

#!/bin/sh

hg init t
cd t

# we need a repo with some legacy latin-1 changesets
hg unbundle $TESTDIR/legacy-encoding.hg
hg co

python << EOF
f = file('latin-1', 'w'); f.write("latin-1 e' encoded: \xe9"); f.close()
f = file('utf-8', 'w'); f.write("utf-8 e' encoded: \xc3\xa9"); f.close()
f = file('latin-1-tag', 'w'); f.write("\xe9"); f.close()
EOF

echo % should fail with encoding error
echo "plain old ascii" > a
hg st
HGENCODING=ascii hg ci -l latin-1

echo % these should work
echo "latin-1" > a
HGENCODING=latin-1 hg ci -l latin-1
echo "utf-8" > a
HGENCODING=utf-8 hg ci -l utf-8

HGENCODING=latin-1 hg tag `cat latin-1-tag`
HGENCODING=latin-1 hg branch `cat latin-1-tag`
HGENCODING=latin-1 hg ci -m 'latin1 branch'
rm .hg/branch

echo "% hg log (ascii)"
hg --encoding ascii log
echo "% hg log (latin-1)"
hg --encoding latin-1 log
echo "% hg log (utf-8)"
hg --encoding utf-8 log
echo "% hg tags (ascii)"
HGENCODING=ascii hg tags
echo "% hg tags (latin-1)"
HGENCODING=latin-1 hg tags
echo "% hg tags (utf-8)"
HGENCODING=utf-8 hg tags
echo "% hg branches (ascii)"
HGENCODING=ascii hg branches
echo "% hg branches (latin-1)"
HGENCODING=latin-1 hg branches
echo "% hg branches (utf-8)"
HGENCODING=utf-8 hg branches

echo '[ui]' >> .hg/hgrc
echo 'fallbackencoding = koi8-r' >> .hg/hgrc
echo "% hg log (utf-8)"
HGENCODING=utf-8 hg log

echo "% hg log (dolphin)"
HGENCODING=dolphin hg log

HGENCODING=ascii hg branch `cat latin-1-tag`
cp latin-1-tag .hg/branch
HGENCODING=latin-1 hg ci -m 'should fail'
exit 0