Staging
v0.7.0
Revision cb99a34e23e32ca8e94bafaa9699cfd133a17fd3 authored by Derrick Stolee on 24 October 2019, 13:40:42 UTC, committed by Junio C Hamano on 25 October 2019, 02:19:16 UTC
The previous commit includes a failing test for an issue around
fetch.writeCommitGraph and fetching in a repo with a submodule. Here, we
fix that bug and set the test to "test_expect_success".

The problem arises with this set of commands when the remote repo at
<url> has a submodule. Note that --recurse-submodules is not needed to
demonstrate the bug.

	$ git clone <url> test
	$ cd test
	$ git -c fetch.writeCommitGraph=true fetch origin
	Computing commit graph generation numbers: 100% (12/12), done.
	BUG: commit-graph.c:886: missing parent <hash1> for commit <hash2>
	Aborted (core dumped)

As an initial fix, I converted the code in builtin/fetch.c that calls
write_commit_graph_reachable() to instead launch a "git commit-graph
write --reachable --split" process. That code worked, but is not how we
want the feature to work long-term.

That test did demonstrate that the issue must be something to do with
internal state of the 'git fetch' process.

The write_commit_graph() method in commit-graph.c ensures the commits we
plan to write are "closed under reachability" using close_reachable().
This method walks from the input commits, and uses the UNINTERESTING
flag to mark which commits have already been visited. This allows the
walk to take O(N) time, where N is the number of commits, instead of
O(P) time, where P is the number of paths. (The number of paths can be
exponential in the number of commits.)

However, the UNINTERESTING flag is used in lots of places in the
codebase. This flag usually means some barrier to stop a commit walk,
such as in revision-walking to compare histories. It is not often
cleared after the walk completes because the starting points of those
walks do not have the UNINTERESTING flag, and clear_commit_marks() would
stop immediately.

This is happening during a 'git fetch' call with a remote. The fetch
negotiation is comparing the remote refs with the local refs and marking
some commits as UNINTERESTING.

I tested running clear_commit_marks_many() to clear the UNINTERESTING
flag inside close_reachable(), but the tips did not have the flag, so
that did nothing.

It turns out that the calculate_changed_submodule_paths() method is at
fault. Thanks, Peff, for pointing out this detail! More specifically,
for each submodule, the collect_changed_submodules() runs a revision
walk to essentially do file-history on the list of submodules. That
revision walk marks commits UNININTERESTING if they are simplified away
by not changing the submodule.

Instead, I finally arrived on the conclusion that I should use a flag
that is not used in any other part of the code. In commit-reach.c, a
number of flags were defined for commit walk algorithms. The REACHABLE
flag seemed like it made the most sense, and it seems it was not
actually used in the file. The REACHABLE flag was used in early versions
of commit-reach.c, but was removed by 4fbcca4 (commit-reach: make
can_all_from_reach... linear, 2018-07-20).

Add the REACHABLE flag to commit-graph.c and use it instead of
UNINTERESTING in close_reachable(). This fixes the bug in manual
testing.

Reported-by: Johannes Schindelin <johannes.schindelin@gmx.de>
Helped-by: Jeff King <peff@peff.net>
Helped-by: Szeder Gábor <szeder.dev@gmail.com>
Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
1 parent e88aab9
Raw File
diffcore-pickaxe.c
/*
 * Copyright (C) 2005 Junio C Hamano
 * Copyright (C) 2010 Google Inc.
 */
#include "cache.h"
#include "diff.h"
#include "diffcore.h"
#include "xdiff-interface.h"
#include "kwset.h"
#include "commit.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 void diffgrep_consume(void *priv, char *line, unsigned long len)
{
	struct diffgrep_cb *data = priv;
	regmatch_t regmatch;

	if (line[0] != '+' && line[0] != '-')
		return;
	if (data->hit)
		/*
		 * NEEDSWORK: we should have a way to terminate the
		 * caller early.
		 */
		return;
	data->hit = !regexec_buf(data->regexp, line + 1, len - 1, 1,
				 &regmatch, 0);
}

static int diff_grep(mmfile_t *one, mmfile_t *two,
		     struct diff_options *o,
		     regex_t *regexp, kwset_t kws)
{
	regmatch_t regmatch;
	struct diffgrep_cb ecbdata;
	xpparam_t xpp;
	xdemitconf_t xecfg;

	if (!one)
		return !regexec_buf(regexp, two->ptr, two->size,
				    1, &regmatch, 0);
	if (!two)
		return !regexec_buf(regexp, one->ptr, one->size,
				    1, &regmatch, 0);

	/*
	 * 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.ctxlen = o->context;
	xecfg.interhunkctxlen = o->interhunkcontext;
	if (xdi_diff_outf(one, two, discard_hunk_line, diffgrep_consume,
			  &ecbdata, &xpp, &xecfg))
		return 0;
	return ecbdata.hit;
}

static unsigned int contains(mmfile_t *mf, regex_t *regexp, kwset_t kws)
{
	unsigned int cnt;
	unsigned long sz;
	const char *data;

	sz = mf->size;
	data = mf->ptr;
	cnt = 0;

	if (regexp) {
		regmatch_t regmatch;
		int flags = 0;

		while (sz && *data &&
		       !regexec_buf(regexp, data, sz, 1, &regmatch, flags)) {
			flags |= REG_NOTBOL;
			data += regmatch.rm_eo;
			sz -= regmatch.rm_eo;
			if (sz && *data && regmatch.rm_so == regmatch.rm_eo) {
				data++;
				sz--;
			}
			cnt++;
		}

	} else { /* Classic exact string match */
		while (sz) {
			struct kwsmatch kwsm;
			size_t offset = kwsexec(kws, data, sz, &kwsm);
			if (offset == -1)
				break;
			sz -= offset + kwsm.size[0];
			data += offset + kwsm.size[0];
			cnt++;
		}
	}
	return cnt;
}

static int has_changes(mmfile_t *one, mmfile_t *two,
		       struct diff_options *o,
		       regex_t *regexp, kwset_t kws)
{
	unsigned int one_contains = one ? contains(one, regexp, kws) : 0;
	unsigned int two_contains = two ? contains(two, regexp, kws) : 0;
	return one_contains != two_contains;
}

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;

	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));
	}

	if (!o->pickaxe[0])
		return 0;

	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;

	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);

	ret = fn(DIFF_FILE_VALID(p->one) ? &mf1 : NULL,
		 DIFF_FILE_VALID(p->two) ? &mf2 : NULL,
		 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;
	kwset_t kws = NULL;

	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;
	} 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);
		}
	}

	pickaxe(&diff_queued_diff, o, regexp, kws,
		(opts & DIFF_PICKAXE_KIND_G) ? diff_grep : has_changes);

	if (regexp)
		regfree(regexp);
	if (kws)
		kwsfree(kws);
	return;
}
back to top