git-commit-vandalism/diffcore-pickaxe.c

291 lines
7.1 KiB
C
Raw Normal View History

/*
* Copyright (C) 2005 Junio C Hamano
* Copyright (C) 2010 Google Inc.
*/
#include "git-compat-util.h"
#include "diff.h"
#include "diffcore.h"
#include "xdiff-interface.h"
Use kwset in pickaxe Benchmarks in the hot cache case: before: $ perf stat --repeat=5 git log -Sqwerty Performance counter stats for 'git log -Sqwerty' (5 runs): 47,092,744 cache-misses # 2.825 M/sec ( +- 1.607% ) 123,368,389 cache-references # 7.400 M/sec ( +- 0.812% ) 330,040,998 branch-misses # 3.134 % ( +- 0.257% ) 10,530,896,750 branches # 631.663 M/sec ( +- 0.121% ) 62,037,201,030 instructions # 1.399 IPC ( +- 0.142% ) 44,331,294,321 cycles # 2659.073 M/sec ( +- 0.326% ) 96,794 page-faults # 0.006 M/sec ( +- 11.952% ) 25 CPU-migrations # 0.000 M/sec ( +- 25.266% ) 1,424 context-switches # 0.000 M/sec ( +- 0.540% ) 16671.708650 task-clock-msecs # 0.997 CPUs ( +- 0.343% ) 16.728692052 seconds time elapsed ( +- 0.344% ) after: $ perf stat --repeat=5 git log -Sqwerty Performance counter stats for 'git log -Sqwerty' (5 runs): 51,385,522 cache-misses # 4.619 M/sec ( +- 0.565% ) 129,177,880 cache-references # 11.611 M/sec ( +- 0.219% ) 319,222,775 branch-misses # 6.946 % ( +- 0.134% ) 4,595,913,233 branches # 413.086 M/sec ( +- 0.112% ) 31,395,042,533 instructions # 1.062 IPC ( +- 0.129% ) 29,558,348,598 cycles # 2656.740 M/sec ( +- 0.204% ) 93,224 page-faults # 0.008 M/sec ( +- 4.487% ) 19 CPU-migrations # 0.000 M/sec ( +- 10.425% ) 950 context-switches # 0.000 M/sec ( +- 0.360% ) 11125.796039 task-clock-msecs # 0.997 CPUs ( +- 0.239% ) 11.164216599 seconds time elapsed ( +- 0.240% ) So the kwset code is about 33% faster. Signed-off-by: Fredrik Kuivinen <frekui@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-08-21 00:41:57 +02:00
#include "kwset.h"
#include "pretty.h"
#include "quote.h"
typedef int (*pickaxe_fn)(mmfile_t *one, mmfile_t *two,
struct diff_options *o,
regex_t *regexp, kwset_t kws);
struct diffgrep_cb {
regex_t *regexp;
int hit;
};
static int diffgrep_consume(void *priv, char *line, unsigned long len)
{
struct diffgrep_cb *data = priv;
regmatch_t regmatch;
if (line[0] != '+' && line[0] != '-')
return 0;
if (data->hit)
BUG("Already matched in diffgrep_consume! Broken xdiff_emit_line_fn?");
if (!regexec_buf(data->regexp, line + 1, len - 1, 1,
&regmatch, 0)) {
data->hit = 1;
return 1;
}
return 0;
}
static int diff_grep(mmfile_t *one, mmfile_t *two,
struct diff_options *o,
regex_t *regexp, kwset_t kws UNUSED)
{
struct diffgrep_cb ecbdata;
xpparam_t xpp;
xdemitconf_t xecfg;
int ret;
/*
* We have both sides; need to run textual diff and see if
* the pattern appears on added/deleted lines.
*/
memset(&xpp, 0, sizeof(xpp));
memset(&xecfg, 0, sizeof(xecfg));
ecbdata.regexp = regexp;
ecbdata.hit = 0;
xecfg.flags = XDL_EMIT_NO_HUNK_HDR;
xecfg.ctxlen = o->context;
xecfg.interhunkctxlen = o->interhunkcontext;
/*
* An xdiff error might be our "data->hit" from above. See the
* comment for xdiff_emit_line_fn in xdiff-interface.h
*/
ret = xdi_diff_outf(one, two, NULL, diffgrep_consume,
&ecbdata, &xpp, &xecfg);
if (ecbdata.hit)
return 1;
if (ret)
return ret;
return 0;
}
static unsigned int contains(mmfile_t *mf, regex_t *regexp, kwset_t kws,
unsigned int limit)
{
unsigned int cnt = 0;
unsigned long sz = mf->size;
const char *data = mf->ptr;
if (regexp) {
regmatch_t regmatch;
int flags = 0;
while (sz &&
!regexec_buf(regexp, data, sz, 1, &regmatch, flags)) {
flags |= REG_NOTBOL;
data += regmatch.rm_eo;
pickaxe: fix segfault with '-S<...> --pickaxe-regex' 'git {log,diff,...} -S<...> --pickaxe-regex' can segfault as a result of out-of-bounds memory reads. diffcore-pickaxe.c:contains() looks for all matches of the given regex in a buffer in a loop, advancing the buffer pointer to the end of the last match in each iteration. When we switched to REG_STARTEND in b7d36ffca (regex: use regexec_buf(), 2016-09-21), we started passing the size of that buffer to the regexp engine, too. Unfortunately, this buffer size is never updated on subsequent iterations, and as the buffer pointer advances on each iteration, this "bufptr+bufsize" points past the end of the buffer. This results in segmentation fault, if that memory can't be accessed. In case of 'git log' it can also result in erroneously listed commits, if the memory past the end of buffer is accessible and happens to contain data matching the regex. Reduce the buffer size on each iteration as the buffer pointer is advanced, thus maintaining the correct end of buffer location. Furthermore, make sure that the buffer pointer is not dereferenced in the control flow statements when we already reached the end of the buffer. The new test is flaky, I've never seen it fail on my Linux box even without the fix, but this is expected according to db5dfa3 (regex: -G<pattern> feeds a non NUL-terminated string to regexec() and fails, 2016-09-21). However, it did fail on Travis CI with the first (and incomplete) version of the fix, and based on that commit message I would expect the new test without the fix to fail most of the time on Windows. Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-18 19:24:08 +01:00
sz -= regmatch.rm_eo;
if (sz && regmatch.rm_so == regmatch.rm_eo) {
data++;
pickaxe: fix segfault with '-S<...> --pickaxe-regex' 'git {log,diff,...} -S<...> --pickaxe-regex' can segfault as a result of out-of-bounds memory reads. diffcore-pickaxe.c:contains() looks for all matches of the given regex in a buffer in a loop, advancing the buffer pointer to the end of the last match in each iteration. When we switched to REG_STARTEND in b7d36ffca (regex: use regexec_buf(), 2016-09-21), we started passing the size of that buffer to the regexp engine, too. Unfortunately, this buffer size is never updated on subsequent iterations, and as the buffer pointer advances on each iteration, this "bufptr+bufsize" points past the end of the buffer. This results in segmentation fault, if that memory can't be accessed. In case of 'git log' it can also result in erroneously listed commits, if the memory past the end of buffer is accessible and happens to contain data matching the regex. Reduce the buffer size on each iteration as the buffer pointer is advanced, thus maintaining the correct end of buffer location. Furthermore, make sure that the buffer pointer is not dereferenced in the control flow statements when we already reached the end of the buffer. The new test is flaky, I've never seen it fail on my Linux box even without the fix, but this is expected according to db5dfa3 (regex: -G<pattern> feeds a non NUL-terminated string to regexec() and fails, 2016-09-21). However, it did fail on Travis CI with the first (and incomplete) version of the fix, and based on that commit message I would expect the new test without the fix to fail most of the time on Windows. Signed-off-by: SZEDER Gábor <szeder.dev@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-03-18 19:24:08 +01:00
sz--;
}
cnt++;
if (limit && cnt == limit)
return cnt;
}
} else { /* Classic exact string match */
while (sz) {
struct kwsmatch kwsm;
size_t offset = kwsexec(kws, data, sz, &kwsm);
Use kwset in pickaxe Benchmarks in the hot cache case: before: $ perf stat --repeat=5 git log -Sqwerty Performance counter stats for 'git log -Sqwerty' (5 runs): 47,092,744 cache-misses # 2.825 M/sec ( +- 1.607% ) 123,368,389 cache-references # 7.400 M/sec ( +- 0.812% ) 330,040,998 branch-misses # 3.134 % ( +- 0.257% ) 10,530,896,750 branches # 631.663 M/sec ( +- 0.121% ) 62,037,201,030 instructions # 1.399 IPC ( +- 0.142% ) 44,331,294,321 cycles # 2659.073 M/sec ( +- 0.326% ) 96,794 page-faults # 0.006 M/sec ( +- 11.952% ) 25 CPU-migrations # 0.000 M/sec ( +- 25.266% ) 1,424 context-switches # 0.000 M/sec ( +- 0.540% ) 16671.708650 task-clock-msecs # 0.997 CPUs ( +- 0.343% ) 16.728692052 seconds time elapsed ( +- 0.344% ) after: $ perf stat --repeat=5 git log -Sqwerty Performance counter stats for 'git log -Sqwerty' (5 runs): 51,385,522 cache-misses # 4.619 M/sec ( +- 0.565% ) 129,177,880 cache-references # 11.611 M/sec ( +- 0.219% ) 319,222,775 branch-misses # 6.946 % ( +- 0.134% ) 4,595,913,233 branches # 413.086 M/sec ( +- 0.112% ) 31,395,042,533 instructions # 1.062 IPC ( +- 0.129% ) 29,558,348,598 cycles # 2656.740 M/sec ( +- 0.204% ) 93,224 page-faults # 0.008 M/sec ( +- 4.487% ) 19 CPU-migrations # 0.000 M/sec ( +- 10.425% ) 950 context-switches # 0.000 M/sec ( +- 0.360% ) 11125.796039 task-clock-msecs # 0.997 CPUs ( +- 0.239% ) 11.164216599 seconds time elapsed ( +- 0.240% ) So the kwset code is about 33% faster. Signed-off-by: Fredrik Kuivinen <frekui@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-08-21 00:41:57 +02:00
if (offset == -1)
break;
sz -= offset + kwsm.size[0];
data += offset + kwsm.size[0];
cnt++;
if (limit && cnt == limit)
return cnt;
}
}
return cnt;
}
static int has_changes(mmfile_t *one, mmfile_t *two,
struct diff_options *o UNUSED,
regex_t *regexp, kwset_t kws)
{
unsigned int c1 = one ? contains(one, regexp, kws, 0) : 0;
unsigned int c2 = two ? contains(two, regexp, kws, c1 + 1) : 0;
return c1 != c2;
}
static int pickaxe_match(struct diff_filepair *p, struct diff_options *o,
regex_t *regexp, kwset_t kws, pickaxe_fn fn)
{
struct userdiff_driver *textconv_one = NULL;
struct userdiff_driver *textconv_two = NULL;
mmfile_t mf1, mf2;
int ret;
/* ignore unmerged */
if (!DIFF_FILE_VALID(p->one) && !DIFF_FILE_VALID(p->two))
return 0;
diffcore: add a pickaxe option to find a specific blob Sometimes users are given a hash of an object and they want to identify it further (ex.: Use verify-pack to find the largest blobs, but what are these? or [1]) One might be tempted to extend git-describe to also work with blobs, such that `git describe <blob-id>` gives a description as '<commit-ish>:<path>'. This was implemented at [2]; as seen by the sheer number of responses (>110), it turns out this is tricky to get right. The hard part to get right is picking the correct 'commit-ish' as that could be the commit that (re-)introduced the blob or the blob that removed the blob; the blob could exist in different branches. Junio hinted at a different approach of solving this problem, which this patch implements. Teach the diff machinery another flag for restricting the information to what is shown. For example: $ ./git log --oneline --find-object=v2.0.0:Makefile b2feb64309 Revert the whole "ask curl-config" topic for now 47fbfded53 i18n: only extract comments marked with "TRANSLATORS:" we observe that the Makefile as shipped with 2.0 was appeared in v1.9.2-471-g47fbfded53 and in v2.0.0-rc1-5-gb2feb6430b. The reason why these commits both occur prior to v2.0.0 are evil merges that are not found using this new mechanism. [1] https://stackoverflow.com/questions/223678/which-commit-has-this-blob [2] https://public-inbox.org/git/20171028004419.10139-1-sbeller@google.com/ Signed-off-by: Stefan Beller <sbeller@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-01-04 23:50:42 +01:00
if (o->objfind) {
return (DIFF_FILE_VALID(p->one) &&
oidset_contains(o->objfind, &p->one->oid)) ||
(DIFF_FILE_VALID(p->two) &&
oidset_contains(o->objfind, &p->two->oid));
}
diff: make struct diff_flags members lowercase Now that the flags stored in struct diff_flags are being accessed directly and not through macros, change all struct members from being uppercase to lowercase. This conversion is done using the following semantic patch: @@ expression E; @@ - E.RECURSIVE + E.recursive @@ expression E; @@ - E.TREE_IN_RECURSIVE + E.tree_in_recursive @@ expression E; @@ - E.BINARY + E.binary @@ expression E; @@ - E.TEXT + E.text @@ expression E; @@ - E.FULL_INDEX + E.full_index @@ expression E; @@ - E.SILENT_ON_REMOVE + E.silent_on_remove @@ expression E; @@ - E.FIND_COPIES_HARDER + E.find_copies_harder @@ expression E; @@ - E.FOLLOW_RENAMES + E.follow_renames @@ expression E; @@ - E.RENAME_EMPTY + E.rename_empty @@ expression E; @@ - E.HAS_CHANGES + E.has_changes @@ expression E; @@ - E.QUICK + E.quick @@ expression E; @@ - E.NO_INDEX + E.no_index @@ expression E; @@ - E.ALLOW_EXTERNAL + E.allow_external @@ expression E; @@ - E.EXIT_WITH_STATUS + E.exit_with_status @@ expression E; @@ - E.REVERSE_DIFF + E.reverse_diff @@ expression E; @@ - E.CHECK_FAILED + E.check_failed @@ expression E; @@ - E.RELATIVE_NAME + E.relative_name @@ expression E; @@ - E.IGNORE_SUBMODULES + E.ignore_submodules @@ expression E; @@ - E.DIRSTAT_CUMULATIVE + E.dirstat_cumulative @@ expression E; @@ - E.DIRSTAT_BY_FILE + E.dirstat_by_file @@ expression E; @@ - E.ALLOW_TEXTCONV + E.allow_textconv @@ expression E; @@ - E.TEXTCONV_SET_VIA_CMDLINE + E.textconv_set_via_cmdline @@ expression E; @@ - E.DIFF_FROM_CONTENTS + E.diff_from_contents @@ expression E; @@ - E.DIRTY_SUBMODULES + E.dirty_submodules @@ expression E; @@ - E.IGNORE_UNTRACKED_IN_SUBMODULES + E.ignore_untracked_in_submodules @@ expression E; @@ - E.IGNORE_DIRTY_SUBMODULES + E.ignore_dirty_submodules @@ expression E; @@ - E.OVERRIDE_SUBMODULE_CONFIG + E.override_submodule_config @@ expression E; @@ - E.DIRSTAT_BY_LINE + E.dirstat_by_line @@ expression E; @@ - E.FUNCCONTEXT + E.funccontext @@ expression E; @@ - E.PICKAXE_IGNORE_CASE + E.pickaxe_ignore_case @@ expression E; @@ - E.DEFAULT_FOLLOW_RENAMES + E.default_follow_renames Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-31 19:19:11 +01:00
if (o->flags.allow_textconv) {
textconv_one = get_textconv(o->repo, p->one);
textconv_two = get_textconv(o->repo, p->two);
}
/*
* If we have an unmodified pair, we know that the count will be the
* same and don't even have to load the blobs. Unless textconv is in
* play, _and_ we are using two different textconv filters (e.g.,
* because a pair is an exact rename with different textconv attributes
* for each side, which might generate different content).
*/
if (textconv_one == textconv_two && diff_unmodified_pair(p))
return 0;
log -G: ignore binary files The -G<regex> option of log looks for the differences whose patch text contains added/removed lines that match regex. Currently -G looks also into patches of binary files (which according to [1]) is binary as well. This has a couple of issues: - It makes the pickaxe search slow. In a proprietary repository of the author with only ~5500 commits and a total .git size of ~300MB searching takes ~13 seconds $time git log -Gwave > /dev/null real 0m13,241s user 0m12,596s sys 0m0,644s whereas when we ignore binary files with this patch it takes ~4s $time ~/devel/git/git log -Gwave > /dev/null real 0m3,713s user 0m3,608s sys 0m0,105s which is a speedup of more than fourfold. - The internally used algorithm for generating patch text is based on xdiff and its states in [1] > The output format of the binary patch file is proprietary > (and binary) and it is basically a collection of copy and insert > commands [..] which means that the current format could change once the internal algorithm is changed as the format is not standardized. In addition the git binary patch format used for preparing patches for git apply is *different* from the xdiff format as can be seen by comparing git log -p -a commit 6e95bf4bafccf14650d02ab57f3affe669be10cf Author: A U Thor <author@example.com> Date: Thu Apr 7 15:14:13 2005 -0700 modify binary file diff --git a/data.bin b/data.bin index f414c84..edfeb6f 100644 --- a/data.bin +++ b/data.bin @@ -1,2 +1,4 @@ a a^@a +a +a^@a with git log --binary commit 6e95bf4bafccf14650d02ab57f3affe669be10cf Author: A U Thor <author@example.com> Date: Thu Apr 7 15:14:13 2005 -0700 modify binary file diff --git a/data.bin b/data.bin index f414c84bd3aa25fa07836bb1fb73db784635e24b..edfeb6f501[..] GIT binary patch literal 12 QcmYe~N@Pgn0zx1O01)N^ZvX%Q literal 6 NcmYe~N@Pgn0ssWg0XP5v which seems unexpected. To resolve these issues this patch makes -G<regex> ignore binary files by default. Textconv filters are supported and also -a/--text for getting the old and broken behaviour back. The -S<block of text> option of log looks for differences that changes the number of occurrences of the specified block of text (i.e. addition/deletion) in a file. As we want to keep the current behaviour, add a test to ensure it stays that way. [1]: http://www.xmailserver.org/xdiff.html Signed-off-by: Thomas Braun <thomas.braun@virtuell-zuhause.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-12-14 19:49:12 +01:00
if ((o->pickaxe_opts & DIFF_PICKAXE_KIND_G) &&
!o->flags.text &&
((!textconv_one && diff_filespec_is_binary(o->repo, p->one)) ||
(!textconv_two && diff_filespec_is_binary(o->repo, p->two))))
return 0;
mf1.size = fill_textconv(o->repo, textconv_one, p->one, &mf1.ptr);
mf2.size = fill_textconv(o->repo, textconv_two, p->two, &mf2.ptr);
pickaxe -G: don't special-case create/delete Instead of special-casing creations and deletions let's just generate a diff for them. This logic of not running a diff under -G if we don't have both sides dates back to the original implementation of -S in 52e9578985f ([PATCH] Introducing software archaeologist's tool "pickaxe"., 2005-05-21). In the case of -S we were not working with the xdiff interface and needed to do this, but when -G was implemented in f506b8e8b5f (git log/diff: add -G<regexp> that greps in the patch text, 2010-08-23) this logic was diligently copied over. But as the performance test added earlier in this series shows, this does not make much of a difference. With: time GIT_TEST_LONG= GIT_PERF_REPEAT_COUNT=10 GIT_PERF_MAKE_OPTS='-j8 CFLAGS=-O3' ./run origin/next HEAD~ HEAD -- p4209-pickaxe.sh With the HEAD~ commit being the preceding "pickaxe -G: terminate early on matching lines" we get these results. Note that it's only the -G codepaths that are relevant to this change: Test origin/next HEAD~ HEAD ----------------------------------------------------------------------------------------------------------------------------------------- 4209.1: git log -S'int main' <limit-rev>.. 0.35(0.32+0.03) 0.35(0.33+0.02) +0.0% 0.35(0.30+0.05) +0.0% 4209.2: git log -S'æ' <limit-rev>.. 0.46(0.42+0.04) 0.46(0.41+0.05) +0.0% 0.46(0.42+0.04) +0.0% 4209.3: git log --pickaxe-regex -S'(int|void|null)' <limit-rev>.. 0.65(0.62+0.02) 0.64(0.61+0.02) -1.5% 0.64(0.60+0.04) -1.5% 4209.4: git log --pickaxe-regex -S'if *\([^ ]+ & ' <limit-rev>.. 0.52(0.45+0.06) 0.52(0.50+0.01) +0.0% 0.54(0.47+0.04) +3.8% 4209.5: git log --pickaxe-regex -S'[àáâãäåæñøùúûüýþ]' <limit-rev>.. 0.39(0.34+0.05) 0.39(0.34+0.04) +0.0% 0.39(0.36+0.03) +0.0% 4209.6: git log -G'(int|void|null)' <limit-rev>.. 0.60(0.55+0.04) 0.58(0.54+0.03) -3.3% 0.58(0.49+0.08) -3.3% 4209.7: git log -G'if *\([^ ]+ & ' <limit-rev>.. 0.61(0.52+0.06) 0.59(0.53+0.05) -3.3% 0.59(0.54+0.05) -3.3% 4209.8: git log -G'[àáâãäåæñøùúûüýþ]' <limit-rev>.. 0.61(0.51+0.07) 0.58(0.54+0.04) -4.9% 0.57(0.51+0.06) -6.6% 4209.9: git log -i -S'int main' <limit-rev>.. 0.36(0.31+0.04) 0.36(0.34+0.02) +0.0% 0.35(0.32+0.03) -2.8% 4209.10: git log -i -S'æ' <limit-rev>.. 0.36(0.33+0.03) 0.39(0.34+0.01) +8.3% 0.36(0.32+0.03) +0.0% 4209.11: git log -i --pickaxe-regex -S'(int|void|null)' <limit-rev>.. 0.83(0.77+0.05) 0.82(0.77+0.05) -1.2% 0.80(0.75+0.04) -3.6% 4209.12: git log -i --pickaxe-regex -S'if *\([^ ]+ & ' <limit-rev>.. 0.67(0.61+0.03) 0.64(0.61+0.03) -4.5% 0.63(0.61+0.02) -6.0% 4209.13: git log -i --pickaxe-regex -S'[àáâãäåæñøùúûüýþ]' <limit-rev>.. 0.40(0.37+0.02) 0.40(0.37+0.03) +0.0% 0.40(0.36+0.04) +0.0% 4209.14: git log -i -G'(int|void|null)' <limit-rev>.. 0.58(0.51+0.07) 0.59(0.52+0.06) +1.7% 0.58(0.52+0.05) +0.0% 4209.15: git log -i -G'if *\([^ ]+ & ' <limit-rev>.. 0.60(0.54+0.05) 0.60(0.54+0.06) +0.0% 0.60(0.56+0.03) +0.0% 4209.16: git log -i -G'[àáâãäåæñøùúûüýþ]' <limit-rev>.. 0.58(0.51+0.06) 0.57(0.52+0.05) -1.7% 0.60(0.48+0.09) +3.4% This small simplification really doesn't buy us much now, but I've got plans to both convert the pickaxe code to using a PCREv2 backend[1] and to implement additional pickaxe modes to do custom searches through the diff[2]. Always having the diff available under -G is going to help to simplify both of those changes. 1. https://lore.kernel.org/git/20210203032811.14979-22-avarab@gmail.com/ 2. https://lore.kernel.org/git/20190424152215.16251-3-avarab@gmail.com/ Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-04-12 19:15:27 +02:00
ret = fn(&mf1, &mf2, o, regexp, kws);
if (textconv_one)
free(mf1.ptr);
if (textconv_two)
free(mf2.ptr);
diff_free_filespec_data(p->one);
diff_free_filespec_data(p->two);
return ret;
}
static void pickaxe(struct diff_queue_struct *q, struct diff_options *o,
regex_t *regexp, kwset_t kws, pickaxe_fn fn)
{
int i;
struct diff_queue_struct outq;
DIFF_QUEUE_CLEAR(&outq);
if (o->pickaxe_opts & DIFF_PICKAXE_ALL) {
/* Showing the whole changeset if needle exists */
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
if (pickaxe_match(p, o, regexp, kws, fn))
return; /* do not munge the queue */
}
/*
* Otherwise we will clear the whole queue by copying
* the empty outq at the end of this function, but
* first clear the current entries in the queue.
*/
for (i = 0; i < q->nr; i++)
diff_free_filepair(q->queue[i]);
} else {
/* Showing only the filepairs that has the needle */
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
if (pickaxe_match(p, o, regexp, kws, fn))
diff_q(&outq, p);
else
diff_free_filepair(p);
}
}
free(q->queue);
*q = outq;
}
static void regcomp_or_die(regex_t *regex, const char *needle, int cflags)
{
int err = regcomp(regex, needle, cflags);
if (err) {
/* The POSIX.2 people are surely sick */
char errbuf[1024];
regerror(err, regex, errbuf, 1024);
die("invalid regex: %s", errbuf);
}
}
void diffcore_pickaxe(struct diff_options *o)
{
const char *needle = o->pickaxe;
int opts = o->pickaxe_opts;
regex_t regex, *regexp = NULL;
Use kwset in pickaxe Benchmarks in the hot cache case: before: $ perf stat --repeat=5 git log -Sqwerty Performance counter stats for 'git log -Sqwerty' (5 runs): 47,092,744 cache-misses # 2.825 M/sec ( +- 1.607% ) 123,368,389 cache-references # 7.400 M/sec ( +- 0.812% ) 330,040,998 branch-misses # 3.134 % ( +- 0.257% ) 10,530,896,750 branches # 631.663 M/sec ( +- 0.121% ) 62,037,201,030 instructions # 1.399 IPC ( +- 0.142% ) 44,331,294,321 cycles # 2659.073 M/sec ( +- 0.326% ) 96,794 page-faults # 0.006 M/sec ( +- 11.952% ) 25 CPU-migrations # 0.000 M/sec ( +- 25.266% ) 1,424 context-switches # 0.000 M/sec ( +- 0.540% ) 16671.708650 task-clock-msecs # 0.997 CPUs ( +- 0.343% ) 16.728692052 seconds time elapsed ( +- 0.344% ) after: $ perf stat --repeat=5 git log -Sqwerty Performance counter stats for 'git log -Sqwerty' (5 runs): 51,385,522 cache-misses # 4.619 M/sec ( +- 0.565% ) 129,177,880 cache-references # 11.611 M/sec ( +- 0.219% ) 319,222,775 branch-misses # 6.946 % ( +- 0.134% ) 4,595,913,233 branches # 413.086 M/sec ( +- 0.112% ) 31,395,042,533 instructions # 1.062 IPC ( +- 0.129% ) 29,558,348,598 cycles # 2656.740 M/sec ( +- 0.204% ) 93,224 page-faults # 0.008 M/sec ( +- 4.487% ) 19 CPU-migrations # 0.000 M/sec ( +- 10.425% ) 950 context-switches # 0.000 M/sec ( +- 0.360% ) 11125.796039 task-clock-msecs # 0.997 CPUs ( +- 0.239% ) 11.164216599 seconds time elapsed ( +- 0.240% ) So the kwset code is about 33% faster. Signed-off-by: Fredrik Kuivinen <frekui@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-08-21 00:41:57 +02:00
kwset_t kws = NULL;
pickaxe_fn fn;
if (opts & ~DIFF_PICKAXE_KIND_OBJFIND &&
(!needle || !*needle))
BUG("should have needle under -G or -S");
if (opts & (DIFF_PICKAXE_REGEX | DIFF_PICKAXE_KIND_G)) {
int cflags = REG_EXTENDED | REG_NEWLINE;
if (o->pickaxe_opts & DIFF_PICKAXE_IGNORE_CASE)
cflags |= REG_ICASE;
regcomp_or_die(&regex, needle, cflags);
regexp = &regex;
if (opts & DIFF_PICKAXE_KIND_G)
fn = diff_grep;
else if (opts & DIFF_PICKAXE_REGEX)
fn = has_changes;
else
/*
* We don't need to check the combination of
* -G and --pickaxe-regex, by the time we get
* here diff.c has already died if they're
* combined. See the usage tests in
* t4209-log-pickaxe.sh.
*/
BUG("unreachable");
diffcore: add a pickaxe option to find a specific blob Sometimes users are given a hash of an object and they want to identify it further (ex.: Use verify-pack to find the largest blobs, but what are these? or [1]) One might be tempted to extend git-describe to also work with blobs, such that `git describe <blob-id>` gives a description as '<commit-ish>:<path>'. This was implemented at [2]; as seen by the sheer number of responses (>110), it turns out this is tricky to get right. The hard part to get right is picking the correct 'commit-ish' as that could be the commit that (re-)introduced the blob or the blob that removed the blob; the blob could exist in different branches. Junio hinted at a different approach of solving this problem, which this patch implements. Teach the diff machinery another flag for restricting the information to what is shown. For example: $ ./git log --oneline --find-object=v2.0.0:Makefile b2feb64309 Revert the whole "ask curl-config" topic for now 47fbfded53 i18n: only extract comments marked with "TRANSLATORS:" we observe that the Makefile as shipped with 2.0 was appeared in v1.9.2-471-g47fbfded53 and in v2.0.0-rc1-5-gb2feb6430b. The reason why these commits both occur prior to v2.0.0 are evil merges that are not found using this new mechanism. [1] https://stackoverflow.com/questions/223678/which-commit-has-this-blob [2] https://public-inbox.org/git/20171028004419.10139-1-sbeller@google.com/ Signed-off-by: Stefan Beller <sbeller@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-01-04 23:50:42 +01:00
} else if (opts & DIFF_PICKAXE_KIND_S) {
if (o->pickaxe_opts & DIFF_PICKAXE_IGNORE_CASE &&
has_non_ascii(needle)) {
struct strbuf sb = STRBUF_INIT;
int cflags = REG_NEWLINE | REG_ICASE;
basic_regex_quote_buf(&sb, needle);
regcomp_or_die(&regex, sb.buf, cflags);
strbuf_release(&sb);
regexp = &regex;
} else {
kws = kwsalloc(o->pickaxe_opts & DIFF_PICKAXE_IGNORE_CASE
? tolower_trans_tbl : NULL);
kwsincr(kws, needle, strlen(needle));
kwsprep(kws);
}
fn = has_changes;
} else if (opts & DIFF_PICKAXE_KIND_OBJFIND) {
fn = NULL;
} else {
BUG("unknown pickaxe_opts flag");
}
pickaxe(&diff_queued_diff, o, regexp, kws, fn);
if (regexp)
regfree(regexp);
diffcore: add a pickaxe option to find a specific blob Sometimes users are given a hash of an object and they want to identify it further (ex.: Use verify-pack to find the largest blobs, but what are these? or [1]) One might be tempted to extend git-describe to also work with blobs, such that `git describe <blob-id>` gives a description as '<commit-ish>:<path>'. This was implemented at [2]; as seen by the sheer number of responses (>110), it turns out this is tricky to get right. The hard part to get right is picking the correct 'commit-ish' as that could be the commit that (re-)introduced the blob or the blob that removed the blob; the blob could exist in different branches. Junio hinted at a different approach of solving this problem, which this patch implements. Teach the diff machinery another flag for restricting the information to what is shown. For example: $ ./git log --oneline --find-object=v2.0.0:Makefile b2feb64309 Revert the whole "ask curl-config" topic for now 47fbfded53 i18n: only extract comments marked with "TRANSLATORS:" we observe that the Makefile as shipped with 2.0 was appeared in v1.9.2-471-g47fbfded53 and in v2.0.0-rc1-5-gb2feb6430b. The reason why these commits both occur prior to v2.0.0 are evil merges that are not found using this new mechanism. [1] https://stackoverflow.com/questions/223678/which-commit-has-this-blob [2] https://public-inbox.org/git/20171028004419.10139-1-sbeller@google.com/ Signed-off-by: Stefan Beller <sbeller@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2018-01-04 23:50:42 +01:00
if (kws)
Use kwset in pickaxe Benchmarks in the hot cache case: before: $ perf stat --repeat=5 git log -Sqwerty Performance counter stats for 'git log -Sqwerty' (5 runs): 47,092,744 cache-misses # 2.825 M/sec ( +- 1.607% ) 123,368,389 cache-references # 7.400 M/sec ( +- 0.812% ) 330,040,998 branch-misses # 3.134 % ( +- 0.257% ) 10,530,896,750 branches # 631.663 M/sec ( +- 0.121% ) 62,037,201,030 instructions # 1.399 IPC ( +- 0.142% ) 44,331,294,321 cycles # 2659.073 M/sec ( +- 0.326% ) 96,794 page-faults # 0.006 M/sec ( +- 11.952% ) 25 CPU-migrations # 0.000 M/sec ( +- 25.266% ) 1,424 context-switches # 0.000 M/sec ( +- 0.540% ) 16671.708650 task-clock-msecs # 0.997 CPUs ( +- 0.343% ) 16.728692052 seconds time elapsed ( +- 0.344% ) after: $ perf stat --repeat=5 git log -Sqwerty Performance counter stats for 'git log -Sqwerty' (5 runs): 51,385,522 cache-misses # 4.619 M/sec ( +- 0.565% ) 129,177,880 cache-references # 11.611 M/sec ( +- 0.219% ) 319,222,775 branch-misses # 6.946 % ( +- 0.134% ) 4,595,913,233 branches # 413.086 M/sec ( +- 0.112% ) 31,395,042,533 instructions # 1.062 IPC ( +- 0.129% ) 29,558,348,598 cycles # 2656.740 M/sec ( +- 0.204% ) 93,224 page-faults # 0.008 M/sec ( +- 4.487% ) 19 CPU-migrations # 0.000 M/sec ( +- 10.425% ) 950 context-switches # 0.000 M/sec ( +- 0.360% ) 11125.796039 task-clock-msecs # 0.997 CPUs ( +- 0.239% ) 11.164216599 seconds time elapsed ( +- 0.240% ) So the kwset code is about 33% faster. Signed-off-by: Fredrik Kuivinen <frekui@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-08-21 00:41:57 +02:00
kwsfree(kws);
return;
}