git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH v13 1/3] grep: refactor next_match() and match_one_pattern() for external use

From
Hamza Mahfooz <someguy@effective-light.com>
Date
Oct 15, 2021, 16:13 UTC
Message-ID
<20211015161356.3372-1-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 need 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 and move match_one_pattern()'s core logic to headerless_match_one_pattern() while preserving match_one_pattern()'s uses that depend on the additional processing.

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().
v8: add headerless_match_one_pattern() and move header_field[] back.
v9: get rid of the new check in headerless_match_one_pattern(), move the
    header pattern filtering logic in grep_next_match() and document
    grep_next_match() in grep.h.
v10: add a "magic" comment in grep_next_match() to signify a fall through
     in the switch statement.
---
 grep.c | 79 ++++++++++++++++++++++++++++++++++++----------------------
 grep.h |  9 +++++++
 2 files changed, 58 insertions(+), 30 deletions(-)
diff --git a/grep.c b/grep.c
index 14fe8a0fd2..fe847a0111 100644
--- a/grep.c
+++ b/grep.c
@@ -944,10 +944,10 @@ static struct {
 	{ "reflog ", 7 },
 };
 
-static int match_one_pattern(struct grep_pat *p,
-			     const char *bol, const char *eol,
-			     enum grep_context ctx,
-			     regmatch_t *pmatch, int eflags)
+static int headerless_match_one_pattern(struct grep_pat *p,
+					const char *bol, const char *eol,
+					enum grep_context ctx,
+					regmatch_t *pmatch, int eflags)
 {
 	int hit = 0;
 	const char *start = bol;
@@ -956,25 +956,6 @@ static int match_one_pattern(struct grep_pat *p,
 	    ((p->token == GREP_PATTERN_HEAD) != (ctx == GREP_CONTEXT_HEAD)))
 		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;
-		switch (p->field) {
-		case GREP_HEADER_AUTHOR:
-		case GREP_HEADER_COMMITTER:
-			strip_timestamp(bol, &eol);
-			break;
-		default:
-			break;
-		}
-	}
-
  again:
 	hit = patmatch(p, bol, eol, pmatch, eflags);
 
@@ -1025,6 +1006,36 @@ static int match_one_pattern(struct grep_pat *p,
 	return hit;
 }
 
+static int match_one_pattern(struct grep_pat *p,
+			     const char *bol, const char *eol,
+			     enum grep_context ctx, regmatch_t *pmatch,
+			     int eflags)
+{
+	const char *field;
+	size_t len;
+
+	if (p->token == GREP_PATTERN_HEAD) {
+		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;
+
+		switch (p->field) {
+		case GREP_HEADER_AUTHOR:
+		case GREP_HEADER_COMMITTER:
+			strip_timestamp(bol, &eol);
+			break;
+		default:
+			break;
+		}
+	}
+
+	return headerless_match_one_pattern(p, bol, eol, ctx, pmatch, eflags);
+}
+
+
 static int match_expr_eval(struct grep_opt *opt, struct grep_expr *x,
 			   const char *bol, const char *eol,
 			   enum grep_context ctx, ssize_t *col,
@@ -1143,7 +1154,7 @@ static int match_next_pattern(struct grep_pat *p,
 {
 	regmatch_t match;
 
-	if (!match_one_pattern(p, bol, eol, ctx, &match, eflags))
+	if (!headerless_match_one_pattern(p, bol, eol, ctx, &match, eflags))
 		return 0;
 	if (match.rm_so < 0 || match.rm_eo < 0)
 		return 0;
@@ -1158,19 +1169,26 @@ 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:
+				if ((field != GREP_HEADER_FIELD_MAX) &&
+				    (p->field != field))
+					continue;
+				/* fall thru */
+			case GREP_PATTERN: /* atom */
 			case GREP_PATTERN_BODY:
 				hit |= match_next_pattern(p, bol, eol, ctx,
 							  pmatch, eflags);
@@ -1261,7 +1279,8 @@ 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..808ad76f0c 100644
--- a/grep.h
+++ b/grep.h
@@ -191,6 +191,15 @@ 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);
 
+/* The field parameter is only used to filter header patterns
+ * (where appropriate). If filtering isn't desirable
+ * GREP_HEADER_FIELD_MAX should be supplied.
+ */
+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
Next: Hamza Mahfooz
Message 1 of 47 in “grep: refactor next_match() and match_one_pattern() for external use”
  1. 1/3 grep: refactor next_match() and match_one_pattern() for external useHamza Mahfooz, Oct 15, 2021
  2. 3/3 grep/pcre2: fix an edge case concerning ascii patterns and UTF-8 dataHamza Mahfooz, Oct 15, 2021
  3. Junio C HamanoOct 15, 2021
  4. René ScharfeOct 16, 2021
  5. Ævar Arnfjörð BjarmasonOct 16, 2021
  6. René ScharfeOct 16, 2021
  7. Junio C HamanoOct 17, 2021
  8. René ScharfeOct 17, 2021
  9. Ævar Arnfjörð BjarmasonOct 17, 2021
  10. Andreas SchwabNov 15, 2021
  11. Ævar Arnfjörð BjarmasonNov 15, 2021
  12. Carlo ArenasNov 16, 2021
  13. Andreas SchwabNov 16, 2021
  14. Carlo ArenasNov 16, 2021
  15. Andreas SchwabNov 16, 2021
  16. Andreas SchwabNov 16, 2021
  17. Carlo ArenasNov 16, 2021
  18. Andreas SchwabNov 16, 2021
  19. grep: avoid setting UTF mode when not neededCarlo Marcelo Arenas Belón, Nov 16, 2021
  20. Ævar Arnfjörð BjarmasonNov 16, 2021
  21. Hamza MahfoozNov 16, 2021
  22. Ævar Arnfjörð BjarmasonNov 17, 2021
  23. Carlo ArenasNov 16, 2021
  24. Junio C HamanoNov 16, 2021
  25. grep: avoid setting UTF mode when dangerous with PCRECarlo Marcelo Arenas Belón, Nov 17, 2021
  26. Junio C HamanoNov 18, 2021
  27. Carlo ArenasNov 18, 2021
  28. Hamza MahfoozNov 18, 2021
  29. Ævar Arnfjörð BjarmasonNov 19, 2021
  30. Hamza MahfoozNov 18, 2021
  31. René ScharfeNov 17, 2021
  32. Carlo ArenasNov 17, 2021
  33. Ævar Arnfjörð BjarmasonNov 17, 2021
  34. Carlo ArenasNov 17, 2021
  35. Ævar Arnfjörð BjarmasonNov 18, 2021
  36. Junio C HamanoNov 18, 2021
  37. René ScharfeNov 18, 2021
  38. Ævar Arnfjörð BjarmasonNov 19, 2021
  39. René ScharfeNov 19, 2021
  40. Carlo ArenasNov 19, 2021
  41. Junio C HamanoNov 19, 2021
  42. 2/3 pretty: colorize pattern matches in commit messagesHamza Mahfooz, Oct 15, 2021
  43. Junio C HamanoOct 15, 2021
  44. Hamza MahfoozOct 15, 2021
  45. Junio C HamanoOct 15, 2021
  46. Hamza MahfoozOct 15, 2021
  47. Junio C HamanoOct 15, 2021

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.