view tests/test-import-eol @ 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

cat > makepatch.py <<EOF
f = file('eol.diff', 'wb')
w = f.write
w('test message\n')
w('diff --git a/a b/a\n')
w('--- a/a\n')
w('+++ b/a\n')
w('@@ -1,5 +1,5 @@\n')
w(' a\n')
w('-bbb\r\n')
w('+yyyy\r\n')
w(' cc\r\n')
w(' \n')
w(' d\n')
w('-e\n')
w('\ No newline at end of file\n')
w('+z\r\n')
w('\ No newline at end of file\r\n')
EOF

hg init repo
cd repo
echo '\.diff' > .hgignore

# Test different --eol values
python -c 'file("a", "wb").write("a\nbbb\ncc\n\nd\ne")'
hg ci -Am adda
python ../makepatch.py

echo % invalid eol
hg --config patch.eol='LFCR' import eol.diff
hg revert -a

echo % force LF
hg --traceback --config patch.eol='LF' import eol.diff
python -c 'print repr(file("a","rb").read())'
hg st

echo % force CRLF
hg up -C 0
hg --traceback --config patch.eol='CRLF' import eol.diff
python -c 'print repr(file("a","rb").read())'
hg st

echo % auto EOL on LF file
hg up -C 0
hg --traceback --config patch.eol='auto' import eol.diff
python -c 'print repr(file("a","rb").read())'
hg st

echo % auto EOL on CRLF file
python -c 'file("a", "wb").write("a\r\nbbb\r\ncc\r\n\r\nd\r\ne")'
hg commit -m 'switch EOLs in a'
hg --traceback --config patch.eol='auto' import eol.diff
python -c 'print repr(file("a","rb").read())'
hg st

echo % auto EOL on new file or source without any EOL
python -c 'file("noeol", "wb").write("noeol")'
hg add noeol
hg commit -m 'add noeol'
python -c 'file("noeol", "wb").write("noeol\r\nnoeol\n")'
python -c 'file("neweol", "wb").write("neweol\nneweol\r\n")'
hg add neweol
hg diff --git > noeol.diff
hg revert --no-backup noeol neweol
rm neweol
hg --traceback --config patch.eol='auto' import -m noeol noeol.diff
python -c 'print repr(file("noeol","rb").read())'
python -c 'print repr(file("neweol","rb").read())'
hg st

# Test --eol and binary patches
python -c 'file("b", "wb").write("a\x00\nb\r\nd")'
hg ci -Am addb
python -c 'file("b", "wb").write("a\x00\nc\r\nd")'
hg diff --git > bin.diff
hg revert --no-backup b
echo % binary patch with --eol
hg import --config patch.eol='CRLF' -m changeb bin.diff
python -c 'print repr(file("b","rb").read())'
hg st
cd ..