tests/test-convert-p4-filetypes

findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.

We speed up 'findrenames' for the usecase when a user specifies they
want a similarity of 100% by matching files by their exact SHA1 hash
value. This reduces the number of comparisons required to find exact
matches from O(n^2) to O(n).

While it would be nice if we could just use mercurial's pre-calculated
SHA1 hash for existing files, this hash includes the file's ancestor
information making it unsuitable for our purposes. Instead, we calculate
the hash of old content from scratch.

The following benchmarks were taken on the current head of crew:

addremove 100% similarity:
  rm -rf *; hg up -C; mv tests tests.new
  hg --time addremove -s100 --dry-run

  before:  real 176.350 secs (user 128.890+0.000 sys 47.430+0.000)
  after:   real   2.130 secs (user   1.890+0.000 sys  0.240+0.000)

addremove 75% similarity:
  rm -rf *; hg up -C; mv tests tests.new; \
      for i in tests.new/*; do echo x >> $i; done
  hg --time addremove -s75  --dry-run

  before: real 264.560 secs (user 215.130+0.000 sys 49.410+0.000)
  after:  real 218.710 secs (user 172.790+0.000 sys 45.870+0.000)

#!/bin/sh

"$TESTDIR/hghave" p4 execbit symlink || exit 80

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

echo % create p4 depot
P4ROOT=`pwd`/depot; export P4ROOT
P4AUDIT=$P4ROOT/audit; export P4AUDIT
P4JOURNAL=$P4ROOT/journal; export P4JOURNAL
P4LOG=$P4ROOT/log; export P4LOG
P4PORT=localhost:16661; export P4PORT
P4DEBUG=1; export P4DEBUG
P4CHARSET=utf8; export P4CHARSET

echo % start the p4 server
[ ! -d $P4ROOT ] && mkdir $P4ROOT
p4d -f -J off -xi >$P4ROOT/stdout 2>$P4ROOT/stderr
p4d -f -J off >$P4ROOT/stdout 2>$P4ROOT/stderr &
trap "echo % stop the p4 server ; p4 admin stop" EXIT

# wait for the server to initialize
while ! p4 ; do
   sleep 1
done >/dev/null 2>/dev/null

echo % create a client spec
P4CLIENT=hg-p4-import; export P4CLIENT
DEPOTPATH=//depot/test-mercurial-import/...
p4 client -o | sed '/^View:/,$ d' >p4client
echo View: >>p4client
echo " $DEPOTPATH //$P4CLIENT/..." >>p4client
p4 client -i <p4client

echo % populate the depot
TYPES="text binary symlink"
TYPES="$TYPES text+m text+w text+x text+k text+kx text+ko text+l text+C text+D text+F text+S text+S2"
TYPES="$TYPES binary+k binary+x binary+kx symlink+k"
TYPES="$TYPES ctext cxtext ktext kxtext ltext tempobj ubinary uxbinary xbinary xltext xtempobj xtext"
# not testing these
#TYPES="$TYPES apple resource unicode utf16 uresource xunicode xutf16"
for T in $TYPES ; do
   T2=`echo $T | tr [:upper:] [:lower:]`
   case $T in
      apple)
	 ;;
      symlink*)
         echo "this is target $T" >target_$T2
         ln -s target_$T file_$T2
         p4 add target_$T2
         p4 add -t $T file_$T2
         ;;
      binary*)
	 python -c "file('file_$T2', 'wb').write('this is $T')"
         p4 add -t $T file_$T2
         ;;
      *)
         echo "this is $T" >file_$T2
         p4 add -t $T file_$T2
         ;;
   esac
done
p4 submit -d initial

echo % test keyword expansion
p4 edit file_* target_*
for T in $TYPES ; do
   T2=`echo $T | tr [:upper:] [:lower:]`
   echo '$Id$'       >>file_$T2
   echo '$Header$'   >>file_$T2
   echo '$Date$'     >>file_$T2
   echo '$DateTime$' >>file_$T2
   echo '$Change$'   >>file_$T2
   echo '$File$'     >>file_$T2
   echo '$Revision$' >>file_$T2
   echo '$Header$$Header$Header$' >>file_$T2
done

ln -s 'target_$Header$' crazy_symlink+k
p4 add -t symlink+k crazy_symlink+k

p4 submit -d keywords

echo % check keywords in p4
grep -H Header file_*

echo % convert
hg convert -s p4 $DEPOTPATH dst
hg -R dst log --template 'rev={rev} desc="{desc}" tags="{tags}" files="{files}"\n'g

echo % revision 0
hg -R dst update 0
head dst/file_* | cat -v

echo
echo % revision 1
hg -R dst update 1
head dst/file_* | cat -v
echo
echo % crazy_symlink
readlink crazy_symlink+k
readlink dst/crazy_symlink+k