tests/test-eol-update

convert/darcs: handle non-ASCII metadata in darcs changelog (issue2354)

Given a commit author or message with non-ASCII characters in a darcs
repo, convert would raise a UnicodeEncodeError when adding changesets
to the hg changelog.

This happened because etree returns back unicode objects for any text
it can't encode into ASCII. convert was passing these objects to
changelog.add(), which would then attempt encoding.fromlocal() on
them.

This patch ensures converter_source.recode() is called on each piece
of commit data returned by etree.

(Also note that darcs is currently encoding agnostic and will print
out whatever is in a patch's metadata byte-for-byte, even in the XML
changelog.)

#!/bin/sh

cat > $HGRCPATH <<EOF
[diff]
git = 1
EOF

seteol () {
    if [ $1 = "LF" ]; then
        EOL='\n'
    else
        EOL='\r\n'
    fi
}

makerepo () {
    echo
    echo "# ==== setup repository ===="
    echo '% hg init'
    hg init repo
    cd repo

    cat > .hgeol <<EOF
[patterns]
**.txt = LF
EOF

    printf "first\nsecond\nthird\n" > a.txt
    hg commit --addremove -m 'LF commit'

    cat > .hgeol <<EOF
[patterns]
**.txt = CRLF
EOF

    printf "first\r\nsecond\r\nthird\r\n" > a.txt
    hg commit -m 'CRLF commit'

    cd ..
}

dotest () {
    seteol $1

    echo
    echo "% hg clone repo repo-$1"
    hg clone --noupdate repo repo-$1
    cd repo-$1

    cat > .hg/hgrc <<EOF
[extensions]
eol =
EOF

    hg update

    echo '% printrepr.py a.txt (before)'
    python $TESTDIR/printrepr.py < a.txt

    printf "first${EOL}third${EOL}" > a.txt

    echo '% printrepr.py a.txt (after)'
    python $TESTDIR/printrepr.py < a.txt
    echo '% hg diff'
    hg diff | python $TESTDIR/printrepr.py

    echo '% hg update 0'
    hg update 0

    echo '% printrepr.py a.txt'
    python $TESTDIR/printrepr.py < a.txt
    echo '% hg diff'
    hg diff | python $TESTDIR/printrepr.py


    cd ..
    rm -r repo-$1
}

makerepo
dotest LF
dotest CRLF
rm -r repo