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

[PATCH v3 09/14] range-diff: split lines manually

From
Thomas Gummerer <t.gummerer@gmail.com>
Date
Jul 8, 2019, 16:33 UTC
Message-ID
<20190708163315.29912-10-t.gummerer@gmail.com>
In-Reply-To
<20190708163315.29912-1-t.gummerer@gmail.com>

Currently range-diff uses the 'strbuf_getline()' function for doing its line by line processing. In a future patch we want to do parts of that parsing using the 'parse_git_diff_header()' function. That function does its own line by line reading of the input, and doesn't use strbufs. This doesn't match with how we do the line-by-line processing in range-diff currently.

Switch range-diff to do our own line by line parsing, so we can re-use the 'parse_git_diff_header()' function later.

Signed-off-by: Thomas Gummerer <t.gummerer@gmail.com>
---
 range-diff.c | 68 ++++++++++++++++++++++++++++++++--------------------
 1 file changed, 42 insertions(+), 26 deletions(-)
diff --git a/range-diff.c b/range-diff.c
index 9242b8975f..784fac301b 100644
--- a/range-diff.c
+++ b/range-diff.c
@@ -24,6 +24,17 @@ struct patch_util {
 	struct object_id oid;
 };
 
+static size_t find_end_of_line(char *buffer, unsigned long size)
+{
+	char *eol = memchr(buffer, '\n', size);
+
+	if (!eol)
+		return size;
+
+	*eol = '\0';
+	return eol + 1 - buffer;
+}
+
 /*
  * Reads the patches into a string list, with the `util` field being populated
  * as struct object_id (will need to be free()d).
@@ -31,10 +42,12 @@ struct patch_util {
 static int read_patches(const char *range, struct string_list *list)
 {
 	struct child_process cp = CHILD_PROCESS_INIT;
-	FILE *in;
-	struct strbuf buf = STRBUF_INIT, line = STRBUF_INIT;
+	struct strbuf buf = STRBUF_INIT, contents = STRBUF_INIT;
 	struct patch_util *util = NULL;
 	int in_header = 1;
+	char *line;
+	int offset, len;
+	size_t size;
 
 	argv_array_pushl(&cp.args, "log", "--no-color", "-p", "--no-merges",
 			"--reverse", "--date-order", "--decorate=no",
@@ -54,17 +67,20 @@ static int read_patches(const char *range, struct string_list *list)
 
 	if (start_command(&cp))
 		return error_errno(_("could not start `log`"));
-	in = fdopen(cp.out, "r");
-	if (!in) {
+	if (strbuf_read(&contents, cp.out, 0) < 0) {
 		error_errno(_("could not read `log` output"));
 		finish_command(&cp);
 		return -1;
 	}
 
-	while (strbuf_getline(&line, in) != EOF) {
+	line = contents.buf;
+	size = contents.len;
+	for (offset = 0; size > 0; offset += len, size -= len, line += len) {
 		const char *p;
 
-		if (skip_prefix(line.buf, "commit ", &p)) {
+		len = find_end_of_line(line, size);
+		line[len - 1] = '\0';
+		if (skip_prefix(line, "commit ", &p)) {
 			if (util) {
 				string_list_append(list, buf.buf)->util = util;
 				strbuf_reset(&buf);
@@ -75,8 +91,7 @@ static int read_patches(const char *range, struct string_list *list)
 				free(util);
 				string_list_clear(list, 1);
 				strbuf_release(&buf);
-				strbuf_release(&line);
-				fclose(in);
+				strbuf_release(&contents);
 				finish_command(&cp);
 				return -1;
 			}
@@ -85,26 +100,28 @@ static int read_patches(const char *range, struct string_list *list)
 			continue;
 		}
 
-		if (starts_with(line.buf, "diff --git")) {
+		if (starts_with(line, "diff --git")) {
 			in_header = 0;
 			strbuf_addch(&buf, '\n');
 			if (!util->diff_offset)
 				util->diff_offset = buf.len;
 			strbuf_addch(&buf, ' ');
-			strbuf_addbuf(&buf, &line);
+			strbuf_addstr(&buf, line);
 		} else if (in_header) {
-			if (starts_with(line.buf, "Author: ")) {
-				strbuf_addbuf(&buf, &line);
+			if (starts_with(line, "Author: ")) {
+				strbuf_addstr(&buf, line);
 				strbuf_addstr(&buf, "\n\n");
-			} else if (starts_with(line.buf, "    ")) {
-				strbuf_rtrim(&line);
-				strbuf_addbuf(&buf, &line);
+			} else if (starts_with(line, "    ")) {
+				p = line + len - 2;
+				while (isspace(*p) && p >= line)
+					p--;
+				strbuf_add(&buf, line, p - line + 1);
 				strbuf_addch(&buf, '\n');
 			}
 			continue;
-		} else if (starts_with(line.buf, "@@ "))
+		} else if (starts_with(line, "@@ "))
 			strbuf_addstr(&buf, "@@");
-		else if (!line.buf[0] || starts_with(line.buf, "index "))
+		else if (!line[0] || starts_with(line, "index "))
 			/*
 			 * A completely blank (not ' \n', which is context)
 			 * line is not valid in a diff.  We skip it
@@ -117,25 +134,24 @@ static int read_patches(const char *range, struct string_list *list)
 			 * we are not interested.
 			 */
 			continue;
-		else if (line.buf[0] == '>') {
+		else if (line[0] == '>') {
 			strbuf_addch(&buf, '+');
-			strbuf_add(&buf, line.buf + 1, line.len - 1);
-		} else if (line.buf[0] == '<') {
+			strbuf_addstr(&buf, line + 1);
+		} else if (line[0] == '<') {
 			strbuf_addch(&buf, '-');
-			strbuf_add(&buf, line.buf + 1, line.len - 1);
-		} else if (line.buf[0] == '#') {
+			strbuf_addstr(&buf, line + 1);
+		} else if (line[0] == '#') {
 			strbuf_addch(&buf, ' ');
-			strbuf_add(&buf, line.buf + 1, line.len - 1);
+			strbuf_addstr(&buf, line + 1);
 		} else {
 			strbuf_addch(&buf, ' ');
-			strbuf_addbuf(&buf, &line);
+			strbuf_addstr(&buf, line);
 		}
 
 		strbuf_addch(&buf, '\n');
 		util->diffsize++;
 	}
-	fclose(in);
-	strbuf_release(&line);
+	strbuf_release(&contents);
 
 	if (util)
 		string_list_append(list, buf.buf)->util = util;
-- 
2.22.0.510.g264f2c817a
Previous: Thomas GummererNext: Thomas Gummerer
Message 38 of 61 in “output improvements for git range-diff”
  1. 00/14 output improvements for git range-diffThomas Gummerer, Jul 5, 2019
  2. 01/14 apply: replace marc.info link with public-inboxThomas Gummerer, Jul 5, 2019
  3. 03/14 apply: only pass required data to git_header_nameThomas Gummerer, Jul 5, 2019
  4. 02/14 apply: only pass required data to skip_tree_prefixThomas Gummerer, Jul 5, 2019
  5. 04/14 apply: only pass required data to check_header_lineThomas Gummerer, Jul 5, 2019
  6. 05/14 apply: only pass required data to find_name_*Thomas Gummerer, Jul 5, 2019
  7. 07/14 apply: make parse_git_header publicThomas Gummerer, Jul 5, 2019
  8. Johannes SchindelinJul 5, 2019
  9. 06/14 apply: only pass required data to gitdiff_* functionsThomas Gummerer, Jul 5, 2019
  10. Johannes SchindelinJul 5, 2019
  11. 08/14 range-diff: fix function parameter indentationThomas Gummerer, Jul 5, 2019
  12. 09/14 range-diff: split lines manuallyThomas Gummerer, Jul 5, 2019
  13. Johannes SchindelinJul 5, 2019
  14. Thomas GummererJul 8, 2019
  15. 10/14 range-diff: don't remove funcname from inner diffThomas Gummerer, Jul 5, 2019
  16. Johannes SchindelinJul 5, 2019
  17. 11/14 range-diff: suppress line count in outer diffThomas Gummerer, Jul 5, 2019
  18. 12/14 range-diff: add section header instead of diff headerThomas Gummerer, Jul 5, 2019
  19. Johannes SchindelinJul 5, 2019
  20. Thomas GummererJul 8, 2019
  21. Johannes SchindelinJul 8, 2019
  22. 13/14 range-diff: add filename to inner diffThomas Gummerer, Jul 5, 2019
  23. 14/14 range-diff: add headers to the outer hunk headerThomas Gummerer, Jul 5, 2019
  24. Johannes SchindelinJul 5, 2019
  25. Thomas GummererJul 8, 2019
  26. 00/14 output improvements for git range-diffThomas Gummerer, Jul 8, 2019
  27. 01/14 apply: replace marc.info link with public-inboxThomas Gummerer, Jul 8, 2019
  28. 02/14 apply: only pass required data to skip_tree_prefixThomas Gummerer, Jul 8, 2019
  29. 03/14 apply: only pass required data to git_header_nameThomas Gummerer, Jul 8, 2019
  30. 04/14 apply: only pass required data to check_header_lineThomas Gummerer, Jul 8, 2019
  31. 05/14 apply: only pass required data to find_name_*Thomas Gummerer, Jul 8, 2019
  32. 06/14 apply: only pass required data to gitdiff_* functionsThomas Gummerer, Jul 8, 2019
  33. 07/14 apply: make parse_git_header publicThomas Gummerer, Jul 8, 2019
  34. Junio C HamanoJul 9, 2019
  35. Thomas GummererJul 9, 2019
  36. Junio C HamanoJul 9, 2019
  37. Thomas GummererJul 10, 2019
  38. 09/14 range-diff: split lines manuallyThomas Gummerer, Jul 8, 2019
  39. 08/14 range-diff: fix function parameter indentationThomas Gummerer, Jul 8, 2019
  40. 10/14 range-diff: don't remove funcname from inner diffThomas Gummerer, Jul 8, 2019
  41. 11/14 range-diff: suppress line count in outer diffThomas Gummerer, Jul 8, 2019
  42. 12/14 range-diff: add section header instead of diff headerThomas Gummerer, Jul 8, 2019
  43. 14/14 range-diff: add headers to the outer hunk headerThomas Gummerer, Jul 8, 2019
  44. 13/14 range-diff: add filename to inner diffThomas Gummerer, Jul 8, 2019
  45. 00/14 output improvements for git range-diffThomas Gummerer, Jul 11, 2019
  46. 01/14 apply: replace marc.info link with public-inboxThomas Gummerer, Jul 11, 2019
  47. 02/14 apply: only pass required data to skip_tree_prefixThomas Gummerer, Jul 11, 2019
  48. 04/14 apply: only pass required data to check_header_lineThomas Gummerer, Jul 11, 2019
  49. 03/14 apply: only pass required data to git_header_nameThomas Gummerer, Jul 11, 2019
  50. 05/14 apply: only pass required data to find_name_*Thomas Gummerer, Jul 11, 2019
  51. 06/14 apply: only pass required data to gitdiff_* functionsThomas Gummerer, Jul 11, 2019
  52. 08/14 range-diff: fix function parameter indentationThomas Gummerer, Jul 11, 2019
  53. 07/14 apply: make parse_git_diff_header publicThomas Gummerer, Jul 11, 2019
  54. 09/14 range-diff: split lines manuallyThomas Gummerer, Jul 11, 2019
  55. 10/14 range-diff: don't remove funcname from inner diffThomas Gummerer, Jul 11, 2019
  56. 12/14 range-diff: add section header instead of diff headerThomas Gummerer, Jul 11, 2019
  57. 11/14 range-diff: suppress line count in outer diffThomas Gummerer, Jul 11, 2019
  58. 13/14 range-diff: add filename to inner diffThomas Gummerer, Jul 11, 2019
  59. 14/14 range-diff: add headers to the outer hunk headerThomas Gummerer, Jul 11, 2019
  60. Ramsay JonesJul 11, 2019
  61. Johannes SchindelinJul 12, 2019

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.