view tests/test-highlight @ 12252:4481f8a93c7a stable

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

"$TESTDIR/hghave" pygments || exit 80

cat <<EOF >> $HGRCPATH
[extensions]
highlight =
[web]
pygments_style = friendly
EOF

hg init test
cd test
# create random Python file to exercise Pygments
cat <<EOF > primes.py
#!/usr/bin/env python

"""Fun with generators. Corresponding Haskell implementation:

primes = 2 : sieve [3, 5..]
    where sieve (p:ns) = p : sieve [n | n <- ns, mod n p /= 0]
"""

from itertools import dropwhile, ifilter, islice, count, chain

def primes():
    """Generate all primes."""
    def sieve(ns):
        p = ns.next()
        # It is important to yield *here* in order to stop the
        # infinite recursion.
        yield p
        ns = ifilter(lambda n: n % p != 0, ns)
        for n in sieve(ns):
            yield n

    odds = ifilter(lambda i: i % 2 == 1, count())
    return chain([2], sieve(dropwhile(lambda n: n < 3, odds)))

if __name__ == "__main__":
    import sys
    try:
        n = int(sys.argv[1])
    except (ValueError, IndexError):
        n = 10
    p = primes()
    print "The first %d primes: %s" % (n, list(islice(p, n)))
EOF

hg ci -Ama

echo % hg serve
hg serve -p $HGPORT -d -n test --pid-file=hg.pid -A access.log -E errors.log
cat hg.pid >> $DAEMON_PIDS

echo % hgweb filerevision, html
("$TESTDIR/get-with-headers.py" localhost:$HGPORT '/file/tip/primes.py') \
    | sed "s/class=\"k\"/class=\"kn\"/g" | sed "s/class=\"mf\"/class=\"mi\"/g"

echo % hgweb fileannotate, html
("$TESTDIR/get-with-headers.py" localhost:$HGPORT '/annotate/tip/primes.py') \
    | sed "s/class=\"k\"/class=\"kn\"/g" | sed "s/class=\"mi\"/class=\"mf\"/g"

echo % hgweb fileannotate, raw
("$TESTDIR/get-with-headers.py" localhost:$HGPORT '/annotate/tip/primes.py?style=raw') \
    | sed "s/test@//" > a

echo "200 Script output follows" > b
echo "" >> b
echo "" >> b
hg annotate "primes.py" >> b
echo "" >> b
echo "" >> b
echo "" >> b
echo "" >> b

diff -u b a

echo
echo % hgweb filerevision, raw
("$TESTDIR/get-with-headers.py" localhost:$HGPORT '/file/tip/primes.py?style=raw') \
    > a

echo "200 Script output follows" > b
echo "" >> b
hg cat primes.py >> b

diff -u b a

echo
echo % hgweb highlightcss friendly
"$TESTDIR/get-with-headers.py" localhost:$HGPORT '/highlightcss' > out
head -n 4 out
rm out

echo % errors encountered
cat errors.log
"$TESTDIR/killdaemons.py"

# Change the pygments style
cat > .hg/hgrc <<EOF
[web]
pygments_style = fruity
EOF

echo % hg serve again
hg serve -p $HGPORT -d -n test --pid-file=hg.pid -A access.log -E errors.log
cat hg.pid >> $DAEMON_PIDS

echo % hgweb highlightcss fruity
"$TESTDIR/get-with-headers.py" localhost:$HGPORT '/highlightcss' > out
head -n 4 out
rm out

echo % errors encountered
cat errors.log

cd ..
hg init eucjp
cd eucjp

python -c 'print("\265\376")' >> eucjp.txt  # Japanese kanji "Kyo"

hg ci -Ama

hgserveget () {
    "$TESTDIR/killdaemons.py"
    echo % HGENCODING="$1" hg serve
    HGENCODING="$1" hg serve -p $HGPORT -d -n test --pid-file=hg.pid -E errors.log
    cat hg.pid >> $DAEMON_PIDS

    echo % hgweb filerevision, html
    "$TESTDIR/get-with-headers.py" localhost:$HGPORT "/file/tip/$2" \
        | grep '<div class="parity0 source">' | $TESTDIR/printrepr.py
    echo % errors encountered
    cat errors.log
}

hgserveget euc-jp eucjp.txt
hgserveget utf-8 eucjp.txt
hgserveget us-ascii eucjp.txt