view tests/test-update-branches @ 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

# Construct the following history tree:
#
# @  5:e1bb631146ca  b1
# |
# o  4:a4fdb3b883c4 0:b608b9236435  b1
# |
# | o  3:4b57d2520816 1:44592833ba9f
# | |
# | | o  2:063f31070f65
# | |/
# | o  1:44592833ba9f
# |/
# o  0:b608b9236435

hg init
echo foo > foo
echo zero > a
hg ci -qAm0
echo one > a ; hg ci -m1
echo two > a ; hg ci -m2
hg up -q 1
echo three > a ; hg ci -qm3
hg up -q 0
hg branch -q b1
echo four > a ; hg ci -qm4
echo five > a ; hg ci -qm5

echo % initial repo state
echo
hg --config 'extensions.graphlog=' \
    glog --template '{rev}:{node|short} {parents} {branches}\n'

# Test helper functions.

revtest () {
    msg=$1
    dirtyflag=$2   # 'clean' or 'dirty'
    startrev=$3
    targetrev=$4
    opt=$5
    echo % revtest $msg $startrev $targetrev
    hg up -qC $startrev
    test $dirtyflag = dirty && echo dirty > foo
    hg up $opt $targetrev
    hg parent --template 'parent={rev}\n'
    hg stat
}    

norevtest () {
    msg=$1
    dirtyflag=$2   # 'clean' or 'dirty'
    startrev=$3
    opt=$4
    echo % norevtest $msg $startrev
    hg up -qC $startrev
    test $dirtyflag = dirty && echo dirty > foo
    hg up $opt
    hg parent --template 'parent={rev}\n'
    hg stat
}    

# Test cases are documented in a table in the update function of merge.py.
# Cases are run as shown in that table, row by row.

norevtest 'none clean linear' clean 4
norevtest 'none clean same'   clean 2

revtest 'none clean linear' clean 1 2
revtest 'none clean same'   clean 2 3
revtest 'none clean cross'  clean 3 4

revtest 'none dirty linear' dirty 1 2
revtest 'none dirty same'   dirty 2 3
revtest 'none dirty cross'  dirty 3 4

revtest '-C dirty linear'   dirty 1 2 -C
revtest '-c dirty linear'   dirty 1 2 -c
norevtest '-c clean same'   clean 2 -c
revtest '-cC dirty linear'  dirty 1 2 -cC