view tests/test-revset @ 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

HGENCODING=utf-8
export HGENCODING

try() {
	echo '% hg debugrevspec' $@
	hg debugrevspec --debug $@
}

log() {
    echo "% log '$1'"
    hg log --template '{rev}\n' -r "$1"
}

hg init repo
cd repo

echo a > a
hg branch a
hg ci -Aqm0

echo b > b
hg branch b
hg ci -Aqm1

rm a
hg branch a-b-c-
hg ci -Aqm2 -u Bob

hg co 1
hg branch +a+b+c+
hg ci -Aqm3

hg co 2  # interleave
echo bb > b
hg branch -- -a-b-c-
hg ci -Aqm4 -d "May 12 2005"

hg co 3
hg branch /a/b/c/
hg ci -Aqm"5 bug"

hg merge 4
hg branch _a_b_c_
hg ci -Aqm"6 issue619"

hg branch .a.b.c.
hg ci -Aqm7

hg branch all
hg ci --close-branch -Aqm8

hg co 4
hg branch é
hg ci -Aqm9

hg tag -r6 1.0

hg clone --quiet -U -r 7 . ../remote1
hg clone --quiet -U -r 8 . ../remote2
echo "[paths]" >> .hg/hgrc
echo "default = ../remote1" >> .hg/hgrc

# names that should work without quoting
try a
try b-a
try _a_b_c_
try _a_b_c_-a
try .a.b.c.
try .a.b.c.-a
try -- '-a-b-c-' # complains
log -a-b-c- # succeeds with fallback
try -- -a-b-c--a # complains
try é

# quoting needed
try '"-a-b-c-"-a'

log '1 or 2'
log '1|2'
log '1 and 2'
log '1&2'
try '1&2|3' # precedence - and is higher
try '1|2&3' 
try '1&2&3' # associativity
try '1|(2|3)'
log '1.0' # tag
log 'a' # branch
log '2785f51ee' 
log 'date(2005)'
log 'date(this is a test)'
log 'date()'
log 'date'
log 'date(' 
log 'date(tip)'
log '"date"'
log 'date(2005) and 1::'

log 'ancestor(1)'
log 'ancestor(4,5)'
log 'ancestor(4,5) and 4'
log 'ancestors(5)'
log 'author(bob)'
log 'branch(é)'
log 'children(ancestor(4,5))'
log 'closed()'
log 'contains(a)'
log 'descendants(2 or 3)'
log 'file(b)'
log 'follow()'
log 'grep("issue\d+")'
log 'head()'
log 'heads(6::)'
log 'keyword(issue)'
log 'limit(head(), 1)'
log 'max(contains(a))'
log 'merge()'
log 'modifies(b)'
log 'outgoing()'
log 'outgoing("../remote1")'
log 'outgoing("../remote2")'
log 'p1(merge())'
log 'p2(merge())'
log 'parents(merge())'
log 'removes(a)'
log 'roots(all())'
log 'reverse(2 or 3 or 4 or 5)'
log 'sort(limit(reverse(all()), 3))'
log 'sort(2 or 3 or 4 or 5, date)'
log 'tagged()'
log 'user(bob)'

log '4::8'
log '4:8'

log 'sort(!merge() & (modifies(b) | user(bob) | keyword(bug) | keyword(issue) & 1::9), "-date")'

log 'not 0 and 0:2'
log 'not 1 and 0:2'
log 'not 2 and 0:2'
log '(1 and 2)::'
log '(1 and 2):'
log '(1 and 2):3'
log 'sort(head(), -rev)'