git log/diff: add -G<regexp> that greps in the patch text

Teach "-G<regexp>" that is similar to "-S<regexp> --pickaxe-regexp" to the
"git diff" family of commands.  This limits the diff queue to filepairs
whose patch text actually has an added or a deleted line that matches the
given regexp.  Unlike "-S<regexp>", changing other parts of the line that
has a substring that matches the given regexp IS counted as a change, as
such a change would appear as one deletion followed by one addition in a
patch text.

Unlike -S (pickaxe) that is intended to be used to quickly detect a commit
that changes the number of occurrences of hits between the preimage and
the postimage to serve as a part of larger toolchain, this is meant to be
used as the top-level Porcelain feature.

The implementation unfortunately has to run "diff" twice if you are
running "log" family of commands to produce patches in the final output
(e.g. "git log -p" or "git format-patch").  I think we _could_ cache the
result in-core if we wanted to, but that would require larger surgery to
the diffcore machinery (i.e. adding an extra pointer in the filepair
structure to keep a pointer to a strbuf around, stuff the textual diff to
the strbuf inside diffgrep_consume(), and make use of it in later stages
when it is available) and it may not be worth it.

Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 149 insertions, 1 deletions

diff --git a/diffcore-pickaxe.c b/diffcore-pickaxe.c
index 13f61fbb08..84195e47aa 100644
--- a/diffcore-pickaxe.c
+++ b/diffcore-pickaxe.c
@@ -1,9 +1,148 @@
 /*
  * Copyright (C) 2005 Junio C Hamano
+ * Copyright (C) 2010 Google Inc.
  */
 #include "cache.h"
 #include "diff.h"
 #include "diffcore.h"
+#include "xdiff-interface.h"
+
+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;
+	int hold;
+
+	if (line[0] != '+' && line[0] != '-')
+		return;
+	if (data->hit)
+		/*
+		 * NEEDSWORK: we should have a way to terminate the
+		 * caller early.
+		 */
+		return;
+	/* Yuck -- line ought to be "const char *"! */
+	hold = line[len];
+	line[len] = '\0';
+	data->hit = !regexec(data->regexp, line + 1, 1, &regmatch, 0);
+	line[len] = hold;
+}
+
+static void fill_one(struct diff_filespec *one,
+		     mmfile_t *mf, struct userdiff_driver **textconv)
+{
+	if (DIFF_FILE_VALID(one)) {
+		*textconv = get_textconv(one);
+		mf->size = fill_textconv(*textconv, one, &mf->ptr);
+	} else {
+		memset(mf, 0, sizeof(*mf));
+	}
+}
+
+static int diff_grep(struct diff_filepair *p, regex_t *regexp, struct diff_options *o)
+{
+	regmatch_t regmatch;
+	struct userdiff_driver *textconv_one = NULL;
+	struct userdiff_driver *textconv_two = NULL;
+	mmfile_t mf1, mf2;
+	int hit;
+
+	if (diff_unmodified_pair(p))
+		return 0;
+
+	fill_one(p->one, &mf1, &textconv_one);
+	fill_one(p->two, &mf2, &textconv_two);
+
+	if (!mf1.ptr) {
+		if (!mf2.ptr)
+			return 0; /* ignore unmerged */
+		/* created "two" -- does it have what we are looking for? */
+		hit = !regexec(regexp, p->two->data, 1, &regmatch, 0);
+	} else if (!mf2.ptr) {
+		/* removed "one" -- did it have what we are looking for? */
+		hit = !regexec(regexp, p->one->data, 1, &regmatch, 0);
+	} else {
+		/*
+		 * We have both sides; need to run textual diff and see if
+		 * the pattern appears on added/deleted lines.
+		 */
+		struct diffgrep_cb ecbdata;
+		xpparam_t xpp;
+		xdemitconf_t xecfg;
+
+		memset(&xpp, 0, sizeof(xpp));
+		memset(&xecfg, 0, sizeof(xecfg));
+		ecbdata.regexp = regexp;
+		ecbdata.hit = 0;
+		xecfg.ctxlen = o->context;
+		xecfg.interhunkctxlen = o->interhunkcontext;
+		xdi_diff_outf(&mf1, &mf2, diffgrep_consume, &ecbdata,
+			      &xpp, &xecfg);
+		hit = ecbdata.hit;
+	}
+	if (textconv_one)
+		free(mf1.ptr);
+	if (textconv_two)
+		free(mf2.ptr);
+	return hit;
+}
+
+static void diffcore_pickaxe_grep(struct diff_options *o)
+{
+	struct diff_queue_struct *q = &diff_queued_diff;
+	int i, has_changes, err;
+	regex_t regex;
+	struct diff_queue_struct outq;
+	outq.queue = NULL;
+	outq.nr = outq.alloc = 0;
+
+	err = regcomp(&regex, o->pickaxe, REG_EXTENDED | REG_NEWLINE);
+	if (err) {
+		char errbuf[1024];
+		regerror(err, &regex, errbuf, 1024);
+		regfree(&regex);
+		die("invalid log-grep regex: %s", errbuf);
+	}
+
+	if (o->pickaxe_opts & DIFF_PICKAXE_ALL) {
+		/* Showing the whole changeset if needle exists */
+		for (i = has_changes = 0; !has_changes && i < q->nr; i++) {
+			struct diff_filepair *p = q->queue[i];
+			if (diff_grep(p, &regex, o))
+				has_changes++;
+		}
+		if (has_changes)
+			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 (diff_grep(p, &regex, o))
+				diff_q(&outq, p);
+			else
+				diff_free_filepair(p);
+		}
+	}
+
+	regfree(&regex);
+
+	free(q->queue);
+	*q = outq;
+	return;
+}
 
 static unsigned int contains(struct diff_filespec *one,
 			     const char *needle, unsigned long len,
@@ -48,7 +187,7 @@ static unsigned int contains(struct diff_filespec *one,
 	return cnt;
 }
 
-void diffcore_pickaxe(struct diff_options *o)
+static void diffcore_pickaxe_count(struct diff_options *o)
 {
 	const char *needle = o->pickaxe;
 	int opts = o->pickaxe_opts;
@@ -138,3 +277,12 @@ void diffcore_pickaxe(struct diff_options *o)
 	*q = outq;
 	return;
 }
+
+void diffcore_pickaxe(struct diff_options *o)
+{
+	/* Might want to warn when both S and G are on; I don't care... */
+	if (o->pickaxe_opts & DIFF_PICKAXE_KIND_G)
+		return diffcore_pickaxe_grep(o);
+	else
+		return diffcore_pickaxe_count(o);
+}