Merge branch 'jc/maint-log-grep-all-match'

Fix a long-standing bug in "git log --grep" when multiple "--grep"
are used together with "--all-match" and "--author" or "--committer".

* jc/maint-log-grep-all-match:
  t7810-grep: test --all-match with multiple --grep and --author options
  t7810-grep: test interaction of multiple --grep and --author options
  t7810-grep: test multiple --author with --all-match
  t7810-grep: test multiple --grep with and without --all-match
  t7810-grep: bring log --grep tests in common form
  grep.c: mark private file-scope symbols as static
  log: document use of multiple commit limiting options
  log --grep/--author: honor --all-match honored for multiple --grep patterns
  grep: show --debug output only once
  grep: teach --debug option to dump the parse tree

Author: gitster

Documentation/rev-list-options.txt

@@ -3,8 +3,15 @@ Commit Limiting
 
 Besides specifying a range of commits that should be listed using the
 special notations explained in the description, additional commit
-limiting may be applied. Note that they are applied before commit
-ordering and formatting options, such as '--reverse'.
+limiting may be applied.
+
+Using more options generally further limits the output (e.g.
+`--since=<date1>` limits to commits newer than `<date1>`, and using it
+with `--grep=<pattern>` further limits to commits whose log message
+has a line that matches `<pattern>`), unless otherwise noted.
+
+Note that these are applied before commit
+ordering and formatting options, such as `--reverse`.
 
 --
 
@@ -39,16 +46,22 @@ endif::git-rev-list[]
 --committer=<pattern>::
 
 	Limit the commits output to ones with author/committer
-	header lines that match the specified pattern (regular expression).
+	header lines that match the specified pattern (regular
+	expression).  With more than one `--author=<pattern>`,
+	commits whose author matches any of the given patterns are
+	chosen (similarly for multiple `--committer=<pattern>`).
 
 --grep=<pattern>::
 
 	Limit the commits output to ones with log message that
-	matches the specified pattern (regular expression).
+	matches the specified pattern (regular expression).  With
+	more than one `--grep=<pattern>`, commits whose message
+	matches any of the given patterns are chosen (but see
+	`--all-match`).
 
 --all-match::
 	Limit the commits output to ones that match all given --grep,
-	--author and --committer instead of ones that match at least one.
+	instead of ones that match at least one.
 
 -i::
 --regexp-ignore-case::

builtin/grep.c

@@ -209,6 +209,7 @@ static void start_threads(struct grep_opt *opt)
 		int err;
 		struct grep_opt *o = grep_opt_dup(opt);
 		o->output = strbuf_out;
+		o->debug = 0;
 		compile_grep_patterns(o);
 		err = pthread_create(&threads[i], NULL, run, o);
 
@@ -817,6 +818,9 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 			   N_("indicate hit with exit status without output")),
 		OPT_BOOLEAN(0, "all-match", &opt.all_match,
 			N_("show only matches from files that match all patterns")),
+		{ OPTION_SET_INT, 0, "debug", &opt.debug, NULL,
+		  N_("show parse tree for grep expression"),
+		  PARSE_OPT_NOARG | PARSE_OPT_HIDDEN, NULL, 1 },
 		OPT_GROUP(""),
 		{ OPTION_STRING, 'O', "open-files-in-pager", &show_in_pager,
 			N_("pager"), N_("show matching files in the pager"),

grep.c

@@ -3,6 +3,10 @@
 #include "userdiff.h"
 #include "xdiff-interface.h"
 
+static int grep_source_load(struct grep_source *gs);
+static int grep_source_is_binary(struct grep_source *gs);
+
+
 static struct grep_pat *create_grep_pat(const char *pat, size_t patlen,
 					const char *origin, int no,
 					enum grep_pat_token t,
@@ -332,6 +336,87 @@ static struct grep_expr *compile_pattern_expr(struct grep_pat **list)
 	return compile_pattern_or(list);
 }
 
+static void indent(int in)
+{
+	while (in-- > 0)
+		fputc(' ', stderr);
+}
+
+static void dump_grep_pat(struct grep_pat *p)
+{
+	switch (p->token) {
+	case GREP_AND: fprintf(stderr, "*and*"); break;
+	case GREP_OPEN_PAREN: fprintf(stderr, "*(*"); break;
+	case GREP_CLOSE_PAREN: fprintf(stderr, "*)*"); break;
+	case GREP_NOT: fprintf(stderr, "*not*"); break;
+	case GREP_OR: fprintf(stderr, "*or*"); break;
+
+	case GREP_PATTERN: fprintf(stderr, "pattern"); break;
+	case GREP_PATTERN_HEAD: fprintf(stderr, "pattern_head"); break;
+	case GREP_PATTERN_BODY: fprintf(stderr, "pattern_body"); break;
+	}
+
+	switch (p->token) {
+	default: break;
+	case GREP_PATTERN_HEAD:
+		fprintf(stderr, "<head %d>", p->field); break;
+	case GREP_PATTERN_BODY:
+		fprintf(stderr, "<body>"); break;
+	}
+	switch (p->token) {
+	default: break;
+	case GREP_PATTERN_HEAD:
+	case GREP_PATTERN_BODY:
+	case GREP_PATTERN:
+		fprintf(stderr, "%.*s", (int)p->patternlen, p->pattern);
+		break;
+	}
+	fputc('\n', stderr);
+}
+
+static void dump_grep_expression_1(struct grep_expr *x, int in)
+{
+	indent(in);
+	switch (x->node) {
+	case GREP_NODE_TRUE:
+		fprintf(stderr, "true\n");
+		break;
+	case GREP_NODE_ATOM:
+		dump_grep_pat(x->u.atom);
+		break;
+	case GREP_NODE_NOT:
+		fprintf(stderr, "(not\n");
+		dump_grep_expression_1(x->u.unary, in+1);
+		indent(in);
+		fprintf(stderr, ")\n");
+		break;
+	case GREP_NODE_AND:
+		fprintf(stderr, "(and\n");
+		dump_grep_expression_1(x->u.binary.left, in+1);
+		dump_grep_expression_1(x->u.binary.right, in+1);
+		indent(in);
+		fprintf(stderr, ")\n");
+		break;
+	case GREP_NODE_OR:
+		fprintf(stderr, "(or\n");
+		dump_grep_expression_1(x->u.binary.left, in+1);
+		dump_grep_expression_1(x->u.binary.right, in+1);
+		indent(in);
+		fprintf(stderr, ")\n");
+		break;
+	}
+}
+
+static void dump_grep_expression(struct grep_opt *opt)
+{
+	struct grep_expr *x = opt->pattern_expression;
+
+	if (opt->all_match)
+		fprintf(stderr, "[all-match]\n");
+	dump_grep_expression_1(x, 0);
+	fflush(NULL);
+}
+
 static struct grep_expr *grep_true_expr(void)
 {
 	struct grep_expr *z = xcalloc(1, sizeof(*z));
@@ -395,7 +480,23 @@ static struct grep_expr *prep_header_patterns(struct grep_opt *opt)
 	return header_expr;
 }
 
-void compile_grep_patterns(struct grep_opt *opt)
+static struct grep_expr *grep_splice_or(struct grep_expr *x, struct grep_expr *y)
+{
+	struct grep_expr *z = x;
+
+	while (x) {
+		assert(x->node == GREP_NODE_OR);
+		if (x->u.binary.right &&
+		    x->u.binary.right->node == GREP_NODE_TRUE) {
+			x->u.binary.right = y;
+			break;
+		}
+		x = x->u.binary.right;
+	}
+	return z;
+}
+
+static void compile_grep_patterns_real(struct grep_opt *opt)
 {
 	struct grep_pat *p;
 	struct grep_expr *header_expr = prep_header_patterns(opt);
@@ -415,7 +516,7 @@ void compile_grep_patterns(struct grep_opt *opt)
 
 	if (opt->all_match || header_expr)
 		opt->extended = 1;
-	else if (!opt->extended)
+	else if (!opt->extended && !opt->debug)
 		return;
 
 	p = opt->pattern_list;
@@ -429,12 +530,22 @@ void compile_grep_patterns(struct grep_opt *opt)
 
 	if (!opt->pattern_expression)
 		opt->pattern_expression = header_expr;
+	else if (opt->all_match)
+		opt->pattern_expression = grep_splice_or(header_expr,
+							 opt->pattern_expression);
 	else
 		opt->pattern_expression = grep_or_expr(opt->pattern_expression,
 						       header_expr);
 	opt->all_match = 1;
 }
 
+void compile_grep_patterns(struct grep_opt *opt)
+{
+	compile_grep_patterns_real(opt);
+	if (opt->debug)
+		dump_grep_expression(opt);
+}
+
 static void free_pattern_expr(struct grep_expr *x)
 {
 	switch (x->node) {

grep.h

@@ -98,6 +98,7 @@ struct grep_opt {
 	int word_regexp;
 	int fixed;
 	int all_match;
+	int debug;
 #define GREP_BINARY_DEFAULT	0
 #define GREP_BINARY_NOMATCH	1
 #define GREP_BINARY_TEXT	2
@@ -158,11 +159,10 @@ struct grep_source {
 
 void grep_source_init(struct grep_source *gs, enum grep_source_type type,
 		      const char *name, const void *identifier);
-int grep_source_load(struct grep_source *gs);
 void grep_source_clear_data(struct grep_source *gs);
 void grep_source_clear(struct grep_source *gs);
 void grep_source_load_driver(struct grep_source *gs);
-int grep_source_is_binary(struct grep_source *gs);
+
 
 int grep_source(struct grep_opt *opt, struct grep_source *gs);
 

revision.c

@@ -1598,6 +1598,8 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg
 	} else if ((argcount = parse_long_opt("grep", argv, &optarg))) {
 		add_message_grep(revs, optarg);
 		return argcount;
+	} else if (!strcmp(arg, "--grep-debug")) {
+		revs->grep_filter.debug = 1;
 	} else if (!strcmp(arg, "--extended-regexp") || !strcmp(arg, "-E")) {
 		revs->grep_filter.regflags |= REG_EXTENDED;
 	} else if (!strcmp(arg, "--regexp-ignore-case") || !strcmp(arg, "-i")) {

t/t7810-grep.sh

@@ -502,31 +502,41 @@ test_expect_success 'log grep setup' '
 
 test_expect_success 'log grep (1)' '
 	git log --author=author --pretty=tformat:%s >actual &&
-	( echo third ; echo initial ) >expect &&
+	{
+		echo third && echo initial
+	} >expect &&
 	test_cmp expect actual
 '
 
 test_expect_success 'log grep (2)' '
 	git log --author=" * " -F --pretty=tformat:%s >actual &&
-	( echo second ) >expect &&
+	{
+		echo second
+	} >expect &&
 	test_cmp expect actual
 '
 
 test_expect_success 'log grep (3)' '
 	git log --author="^A U" --pretty=tformat:%s >actual &&
-	( echo third ; echo initial ) >expect &&
+	{
+		echo third && echo initial
+	} >expect &&
 	test_cmp expect actual
 '
 
 test_expect_success 'log grep (4)' '
 	git log --author="frotz\.com>$" --pretty=tformat:%s >actual &&
-	( echo second ) >expect &&
+	{
+		echo second
+	} >expect &&
 	test_cmp expect actual
 '
 
 test_expect_success 'log grep (5)' '
 	git log --author=Thor -F --pretty=tformat:%s >actual &&
-	( echo third ; echo initial ) >expect &&
+	{
+		echo third && echo initial
+	} >expect &&
 	test_cmp expect actual
 '
 
@@ -536,11 +546,19 @@ test_expect_success 'log grep (6)' '
 	test_cmp expect actual
 '
 
-test_expect_success 'log --grep --author implicitly uses all-match' '
-	# grep matches initial and second but not third
-	# author matches only initial and third
-	git log --author="A U Thor" --grep=s --grep=l --format=%s >actual &&
-	echo initial >expect &&
+test_expect_success 'log with multiple --grep uses union' '
+	git log --grep=i --grep=r --format=%s >actual &&
+	{
+		echo fourth && echo third && echo initial
+	} >expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'log --all-match with multiple --grep uses intersection' '
+	git log --all-match --grep=i --grep=r --format=%s >actual &&
+	{
+		echo third
+	} >expect &&
 	test_cmp expect actual
 '
 
@@ -552,17 +570,61 @@ test_expect_success 'log with multiple --author uses union' '
 	test_cmp expect actual
 '
 
-test_expect_success 'log with --grep and multiple --author uses all-match' '
+test_expect_success 'log --all-match with multiple --author still uses union' '
+	git log --all-match --author="Thor" --author="Aster" --format=%s >actual &&
+	{
+	    echo third && echo second && echo initial
+	} >expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'log --grep --author uses intersection' '
+	# grep matches only third and fourth
+	# author matches only initial and third
+	git log --author="A U Thor" --grep=r --format=%s >actual &&
+	{
+		echo third
+	} >expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'log --grep --grep --author takes union of greps and intersects with author' '
+	# grep matches initial and second but not third
+	# author matches only initial and third
+	git log --author="A U Thor" --grep=s --grep=l --format=%s >actual &&
+	{
+		echo initial
+	} >expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'log ---all-match -grep --author --author still takes union of authors and intersects with grep' '
+	# grep matches only initial and third
+	# author matches all but second
+	git log --all-match --author="Thor" --author="Night" --grep=i --format=%s >actual &&
+	{
+	    echo third && echo initial
+	} >expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'log --grep --author --author takes union of authors and intersects with grep' '
+	# grep matches only initial and third
+	# author matches all but second
 	git log --author="Thor" --author="Night" --grep=i --format=%s >actual &&
 	{
 	    echo third && echo initial
 	} >expect &&
 	test_cmp expect actual
 '
 
-test_expect_success 'log with --grep and multiple --author uses all-match' '
-	git log --author="Thor" --author="Night" --grep=q --format=%s >actual &&
-	>expect &&
+test_expect_success 'log --all-match --grep --grep --author takes intersection' '
+	# grep matches only third
+	# author matches only initial and third
+	git log --all-match --author="A U Thor" --grep=i --grep=r --format=%s >actual &&
+	{
+		echo third
+	} >expect &&
 	test_cmp expect actual
 '