[PATCH v7 1/2] grep: refactor next_match() and match_one_pattern() for external use

[Hamza Mahfooz <someguy@effective-light.com>]

These changes are made in preparation of, the colorization support for the
"git log" subcommands that, rely on regex functionality (i.e. "--author",
"--committer" and "--grep"). These changes are necessary primarily because
match_one_pattern() expects header lines to be prefixed, however, in
pretty, the prefixes are stripped from the lines because the name-email
pairs needs to go through additional parsing, before they can be printed
and because next_match() doesn't handle the case of
"ctx == GREP_CONTEXT_HEAD" at all. So, teach next_match() how to handle the
new case, move header_field[] so it can be used by pretty to reappend
relevant prefixes and teach match_one_pattern() how to handle subsequent
header line match attempts.

Signed-off-by: Hamza Mahfooz <someguy@effective-light.com>
---
v5: separate grep changes from pretty changes.

v6: rescope some variables.

v7: export header_field[] and allow for subsequent matches on header lines
    in match_one_pattern().
---
 grep.c | 53 ++++++++++++++++++++++++++++-------------------------
 grep.h | 13 +++++++++++++
 2 files changed, 41 insertions(+), 25 deletions(-)

diff --git a/grep.c b/grep.c
index 14fe8a0fd2..f4126011c5 100644
--- a/grep.c
+++ b/grep.c
@@ -935,15 +935,6 @@ static void strip_timestamp(const char *bol, const char **eol_p)
 	}
 }
 
-static struct {
-	const char *field;
-	size_t len;
-} header_field[] = {
-	{ "author ", 7 },
-	{ "committer ", 10 },
-	{ "reflog ", 7 },
-};
-
 static int match_one_pattern(struct grep_pat *p,
 			     const char *bol, const char *eol,
 			     enum grep_context ctx,
@@ -953,18 +944,23 @@ static int match_one_pattern(struct grep_pat *p,
 	const char *start = bol;
 
 	if ((p->token != GREP_PATTERN) &&
-	    ((p->token == GREP_PATTERN_HEAD) != (ctx == GREP_CONTEXT_HEAD)))
+	    ((p->token == GREP_PATTERN_HEAD) != (ctx == GREP_CONTEXT_HEAD)) &&
+	    ((p->token == GREP_PATTERN_BODY) != (ctx == GREP_CONTEXT_BODY)))
 		return 0;
 
 	if (p->token == GREP_PATTERN_HEAD) {
-		const char *field;
-		size_t len;
-		assert(p->field < ARRAY_SIZE(header_field));
-		field = header_field[p->field].field;
-		len = header_field[p->field].len;
-		if (strncmp(bol, field, len))
-			return 0;
-		bol += len;
+		if (!(eflags & REG_NOTBOL)) {
+			const char *field;
+			size_t len;
+
+			assert(p->field < ARRAY_SIZE(grep_header_fields));
+			field = grep_header_fields[p->field].field;
+			len = grep_header_fields[p->field].len;
+			if (strncmp(bol, field, len))
+				return 0;
+			bol += len;
+		}
+
 		switch (p->field) {
 		case GREP_HEADER_AUTHOR:
 		case GREP_HEADER_COMMITTER:
@@ -1158,22 +1154,28 @@ static int match_next_pattern(struct grep_pat *p,
 	return 1;
 }
 
-static int next_match(struct grep_opt *opt,
-		      const char *bol, const char *eol,
-		      enum grep_context ctx, regmatch_t *pmatch, int eflags)
+int grep_next_match(struct grep_opt *opt,
+		    const char *bol, const char *eol,
+		    enum grep_context ctx, regmatch_t *pmatch,
+		    enum grep_header_field field, int eflags)
 {
 	struct grep_pat *p;
 	int hit = 0;
 
 	pmatch->rm_so = pmatch->rm_eo = -1;
 	if (bol < eol) {
-		for (p = opt->pattern_list; p; p = p->next) {
+		for (p = ((ctx == GREP_CONTEXT_HEAD)
+			   ? opt->header_list : opt->pattern_list);
+			  p; p = p->next) {
 			switch (p->token) {
 			case GREP_PATTERN: /* atom */
 			case GREP_PATTERN_HEAD:
 			case GREP_PATTERN_BODY:
-				hit |= match_next_pattern(p, bol, eol, ctx,
-							  pmatch, eflags);
+				if ((field == GREP_HEADER_FIELD_MAX) ||
+				    (p->field == field))
+					hit |= match_next_pattern(p, bol, eol,
+								  ctx, pmatch,
+								  eflags);
 				break;
 			default:
 				break;
@@ -1261,7 +1263,8 @@ static void show_line(struct grep_opt *opt,
 			else if (sign == '=')
 				line_color = opt->colors[GREP_COLOR_FUNCTION];
 		}
-		while (next_match(opt, bol, eol, ctx, &match, eflags)) {
+		while (grep_next_match(opt, bol, eol, ctx, &match,
+				       GREP_HEADER_FIELD_MAX, eflags)) {
 			if (match.rm_so == match.rm_eo)
 				break;
 
diff --git a/grep.h b/grep.h
index 3cb8a83ae8..4847c37280 100644
--- a/grep.h
+++ b/grep.h
@@ -23,6 +23,15 @@ typedef int pcre2_general_context;
 #include "thread-utils.h"
 #include "userdiff.h"
 
+static const struct {
+	const char *field;
+	size_t len;
+} grep_header_fields[] = {
+	{ "author ", 7 },
+	{ "committer ", 10 },
+	{ "reflog ", 7 },
+};
+
 struct repository;
 
 enum grep_pat_token {
@@ -190,6 +199,10 @@ void append_header_grep_pattern(struct grep_opt *, enum grep_header_field, const
 void compile_grep_patterns(struct grep_opt *opt);
 void free_grep_patterns(struct grep_opt *opt);
 int grep_buffer(struct grep_opt *opt, const char *buf, unsigned long size);
+int grep_next_match(struct grep_opt *opt,
+		    const char *bol, const char *eol,
+		    enum grep_context ctx, regmatch_t *pmatch,
+		    enum grep_header_field field, int eflags);
 
 struct grep_source {
 	char *name;
-- 
2.33.0