view tests/test-convert-cvs @ 5451:0a43875677b1

revlog: break up compression of large deltas

Python's zlib apparently makes an internal copy of strings passed to
compress(). To avoid this, compress strings 1M at a time, then join
them at the end if the result would be smaller than the original.

For initial commits of large but compressible files, this cuts peak
memory usage nearly in half.

#!/bin/sh

"$TESTDIR/hghave" cvs cvsps || exit 80

echo "[extensions]" >> $HGRCPATH
echo "convert = " >> $HGRCPATH

echo % create cvs repository
mkdir cvsrepo
cd cvsrepo
export CVSROOT=`pwd`
cd ..

cvs -q -d "$CVSROOT" init

echo % create source directory
mkdir src-temp
cd src-temp
echo a > a
mkdir b
cd b
echo c > c
cd ..

echo % import source directory
cvs -q import -m import src INITIAL start
cd ..

echo % checkout source directory
cvs -q checkout src

echo % commit a new revision changing b/c
cd src
echo c >> b/c
cvs -q commit -mci0 . | grep '<--' |\
    sed -e 's:.*src/\(.*\),v.*:checking in src/\1,v:g'
cd ..

echo % convert fresh repo
hg convert src src-hg | sed -e 's/connecting to.*cvsrepo/connecting to cvsrepo/g'
cat src-hg/a
cat src-hg/b/c

echo % convert fresh repo with --filemap
echo include b/c > filemap
hg convert --filemap filemap src src-filemap | sed -e 's/connecting to.*cvsrepo/connecting to cvsrepo/g'
cat src-hg/b/c
hg -R src-filemap log --template '#rev# #desc# files: #files#\n'

echo % commit new file revisions
cd src
echo a >> a
echo c >> b/c
cvs -q commit -mci1 . | grep '<--' |\
    sed -e 's:.*src/\(.*\),v.*:checking in src/\1,v:g'
cd ..

echo % convert again
hg convert src src-hg | sed -e 's/connecting to.*cvsrepo/connecting to cvsrepo/g'
cat src-hg/a
cat src-hg/b/c

echo % convert again with --filemap
hg convert --filemap filemap src src-filemap | sed -e 's/connecting to.*cvsrepo/connecting to cvsrepo/g'
cat src-hg/b/c
hg -R src-filemap log --template '#rev# #desc# files: #files#\n'