Merge branch 'jc/pickaxe-grep'

* jc/pickaxe-grep:
  diff/log -G<pattern>: tests
  git log/diff: add -G<regexp> that greps in the patch text
  diff: pass the entire diff-options to diffcore_pickaxe()
  gitdiffcore doc: update pickaxe description

10 files changed, 226 insertions, 9 deletions

diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt
index 4656a97e60..f77a0f8749 100644
--- a/Documentation/diff-options.txt
+++ b/Documentation/diff-options.txt
@@ -284,8 +284,12 @@ ifndef::git-format-patch[]
 	appearing in diff output; see the 'pickaxe' entry in
 	linkgit:gitdiffcore[7] for more details.
 
+-G<regex>::
+	Look for differences whose added or removed line matches
+	the given <regex>.
+
 --pickaxe-all::
-	When `-S` finds a change, show all the changes in that
+	When `-S` or `-G` finds a change, show all the changes in that
 	changeset, not just the files that contain the change
 	in <string>.
 
diff --git a/Documentation/gitdiffcore.txt b/Documentation/gitdiffcore.txt
index 5d91a7e5b3..6af29a4603 100644
--- a/Documentation/gitdiffcore.txt
+++ b/Documentation/gitdiffcore.txt
@@ -227,9 +227,9 @@ changes that touch a specified string, and is controlled by the
 commands.
 
 When diffcore-pickaxe is in use, it checks if there are
-filepairs whose "result" side has the specified string and
-whose "origin" side does not.  Such a filepair represents "the
-string appeared in this changeset".  It also checks for the
+filepairs whose "result" side and whose "origin" side have
+different number of specified string.  Such a filepair represents
+"the string appeared in this changeset".  It also checks for the
 opposite case that loses the specified string.
 
 When `\--pickaxe-all` is not in effect, diffcore-pickaxe leaves
diff --git a/diff.c b/diff.c
index 0e2e872e0b..71efa8edd4 100644
--- a/diff.c
+++ b/diff.c
@@ -3271,12 +3271,17 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 	}
 	else if ((argcount = short_opt('S', av, &optarg))) {
 		options->pickaxe = optarg;
+		options->pickaxe_opts |= DIFF_PICKAXE_KIND_S;
+		return argcount;
+	} else if ((argcount = short_opt('G', av, &optarg))) {
+		options->pickaxe = optarg;
+		options->pickaxe_opts |= DIFF_PICKAXE_KIND_G;
 		return argcount;
 	}
 	else if (!strcmp(arg, "--pickaxe-all"))
-		options->pickaxe_opts = DIFF_PICKAXE_ALL;
+		options->pickaxe_opts |= DIFF_PICKAXE_ALL;
 	else if (!strcmp(arg, "--pickaxe-regex"))
-		options->pickaxe_opts = DIFF_PICKAXE_REGEX;
+		options->pickaxe_opts |= DIFF_PICKAXE_REGEX;
 	else if ((argcount = short_opt('O', av, &optarg))) {
 		options->orderfile = optarg;
 		return argcount;
@@ -4176,7 +4181,7 @@ void diffcore_std(struct diff_options *options)
 			diffcore_merge_broken();
 	}
 	if (options->pickaxe)
-		diffcore_pickaxe(options->pickaxe, options->pickaxe_opts);
+		diffcore_pickaxe(options);
 	if (options->orderfile)
 		diffcore_order(options->orderfile);
 	if (!options->found_follow)
diff --git a/diff.h b/diff.h
index bf2f44d840..1fd44f5e47 100644
--- a/diff.h
+++ b/diff.h
@@ -238,6 +238,9 @@ extern int diff_setup_done(struct diff_options *);
 #define DIFF_PICKAXE_ALL	1
 #define DIFF_PICKAXE_REGEX	2
 
+#define DIFF_PICKAXE_KIND_S	4 /* traditional plumbing counter */
+#define DIFF_PICKAXE_KIND_G	8 /* grep in the patch */
+
 extern void diffcore_std(struct diff_options *);
 extern void diffcore_fix_diff_index(struct diff_options *);
 
diff --git a/diffcore-pickaxe.c b/diffcore-pickaxe.c
index 929de15aa9..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,
@@ -48,8 +187,10 @@ static unsigned int contains(struct diff_filespec *one,
 	return cnt;
 }
 
-void diffcore_pickaxe(const char *needle, int opts)
+static void diffcore_pickaxe_count(struct diff_options *o)
 {
+	const char *needle = o->pickaxe;
+	int opts = o->pickaxe_opts;
 	struct diff_queue_struct *q = &diff_queued_diff;
 	unsigned long len = strlen(needle);
 	int i, has_changes;
@@ -136,3 +277,12 @@ void diffcore_pickaxe(const char *needle, int opts)
 	*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);
+}
diff --git a/diffcore.h b/diffcore.h
index 8b3241ad13..b8f1fdecf4 100644
--- a/diffcore.h
+++ b/diffcore.h
@@ -107,7 +107,7 @@ extern void diff_q(struct diff_queue_struct *, struct diff_filepair *);
 extern void diffcore_break(int);
 extern void diffcore_rename(struct diff_options *);
 extern void diffcore_merge_broken(void);
-extern void diffcore_pickaxe(const char *needle, int opts);
+extern void diffcore_pickaxe(struct diff_options *);
 extern void diffcore_order(const char *orderfile);
 
 #define DIFF_DEBUG 0
diff --git a/t/t4013-diff-various.sh b/t/t4013-diff-various.sh
index 19857f4326..9a66520588 100755
--- a/t/t4013-diff-various.sh
+++ b/t/t4013-diff-various.sh
@@ -210,6 +210,9 @@ log -m -p master
 log -SF master
 log -S F master
 log -SF -p master
+log -GF master
+log -GF -p master
+log -GF -p --pickaxe-all master
 log --decorate --all
 log --decorate=full --all
 
diff --git a/t/t4013/diff.log_-GF_-p_--pickaxe-all_master b/t/t4013/diff.log_-GF_-p_--pickaxe-all_master
new file mode 100644
index 0000000000..d36f88098b
--- /dev/null
+++ b/t/t4013/diff.log_-GF_-p_--pickaxe-all_master
@@ -0,0 +1,27 @@
+$ git log -GF -p --pickaxe-all master
+commit 9a6d4949b6b76956d9d5e26f2791ec2ceff5fdc0
+Author: A U Thor <author@example.com>
+Date:   Mon Jun 26 00:02:00 2006 +0000
+
+    Third
+
+diff --git a/dir/sub b/dir/sub
+index 8422d40..cead32e 100644
+--- a/dir/sub
++++ b/dir/sub
+@@ -2,3 +2,5 @@ A
+ B
+ C
+ D
++E
++F
+diff --git a/file1 b/file1
+new file mode 100644
+index 0000000..b1e6722
+--- /dev/null
++++ b/file1
+@@ -0,0 +1,3 @@
++A
++B
++C
+$
diff --git a/t/t4013/diff.log_-GF_-p_master b/t/t4013/diff.log_-GF_-p_master
new file mode 100644
index 0000000000..9d93f2c23a
--- /dev/null
+++ b/t/t4013/diff.log_-GF_-p_master
@@ -0,0 +1,18 @@
+$ git log -GF -p master
+commit 9a6d4949b6b76956d9d5e26f2791ec2ceff5fdc0
+Author: A U Thor <author@example.com>
+Date:   Mon Jun 26 00:02:00 2006 +0000
+
+    Third
+
+diff --git a/dir/sub b/dir/sub
+index 8422d40..cead32e 100644
+--- a/dir/sub
++++ b/dir/sub
+@@ -2,3 +2,5 @@ A
+ B
+ C
+ D
++E
++F
+$
diff --git a/t/t4013/diff.log_-GF_master b/t/t4013/diff.log_-GF_master
new file mode 100644
index 0000000000..4c6708d2d0
--- /dev/null
+++ b/t/t4013/diff.log_-GF_master
@@ -0,0 +1,7 @@
+$ git log -GF master
+commit 9a6d4949b6b76956d9d5e26f2791ec2ceff5fdc0
+Author: A U Thor <author@example.com>
+Date:   Mon Jun 26 00:02:00 2006 +0000
+
+    Third
+$