Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
"grep -P" learned to use Unicode Character Property to grok character classes when processing \b and \w etc. * cb/grep-pcre-ucp: grep: correctly identify utf-8 characters with \{b,w} in -P
- Loading branch information
Showing
2 changed files
with
43 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,42 @@ | ||
#!/bin/sh | ||
|
||
test_description="git-grep's perl regex | ||
If GIT_PERF_GREP_THREADS is set to a list of threads (e.g. '1 4 8' | ||
etc.) we will test the patterns under those numbers of threads. | ||
" | ||
|
||
. ./perf-lib.sh | ||
|
||
test_perf_large_repo | ||
test_checkout_worktree | ||
|
||
if test -n "$GIT_PERF_GREP_THREADS" | ||
then | ||
test_set_prereq PERF_GREP_ENGINES_THREADS | ||
fi | ||
|
||
for pattern in \ | ||
'\\bhow' \ | ||
'\\bÆvar' \ | ||
'\\d+ \\bÆvar' \ | ||
'\\bBelón\\b' \ | ||
'\\w{12}\\b' | ||
do | ||
echo '$pattern' >pat | ||
if ! test_have_prereq PERF_GREP_ENGINES_THREADS | ||
then | ||
test_perf "grep -P '$pattern'" --prereq PCRE " | ||
git -P grep -f pat || : | ||
" | ||
else | ||
for threads in $GIT_PERF_GREP_THREADS | ||
do | ||
test_perf "grep -P '$pattern' with $threads threads" --prereq PTHREADS,PCRE " | ||
git -c grep.threads=$threads -P grep -f pat || : | ||
" | ||
done | ||
fi | ||
done | ||
|
||
test_done |