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

[PATCH v4 6/6] convert.c: simplify text_stat

From
tboegi@web.de <tboegi@web.de>
Date
Feb 10, 2016, 16:24 UTC
Message-ID
<1455121483-16470-1-git-send-email-tboegi@web.de>
In-Reply-To
<Message-Id=1453558101-6858-1-git-send-email-tboegi@web.de>
From: Torsten Bögershausen <tboegi@web.de>

Simplify the statistics: lonecr counts the CR which is not followed by a LF, lonelf counts the LF which is not preceded by a CR, crlf counts CRLF combinations. This simplifies the evaluation of the statistics.

Signed-off-by: Torsten Bögershausen <tboegi@web.de>
---
 convert.c | 47 ++++++++++++++++++++++-------------------------
 1 file changed, 22 insertions(+), 25 deletions(-)
diff --git a/convert.c b/convert.c
index e4e2877..18af685 100644
--- a/convert.c
+++ b/convert.c
@@ -31,7 +31,7 @@ enum crlf_action {
 
 struct text_stat {
 	/* NUL, CR, LF and CRLF counts */
-	unsigned nul, cr, lf, crlf;
+	unsigned nul, lonecr, lonelf, crlf;
 
 	/* These are just approximations! */
 	unsigned printable, nonprintable;
@@ -46,13 +46,15 @@ static void gather_stats(const char *buf, unsigned long size, struct text_stat *
 	for (i = 0; i < size; i++) {
 		unsigned char c = buf[i];
 		if (c == '\r') {
-			stats->cr++;
-			if (i+1 < size && buf[i+1] == '\n')
+			if (i+1 < size && buf[i+1] == '\n') {
 				stats->crlf++;
+				i++;
+			} else
+				stats->lonecr++;
 			continue;
 		}
 		if (c == '\n') {
-			stats->lf++;
+			stats->lonelf++;
 			continue;
 		}
 		if (c == 127)
@@ -86,7 +88,7 @@ static void gather_stats(const char *buf, unsigned long size, struct text_stat *
  */
 static int convert_is_binary(unsigned long size, const struct text_stat *stats)
 {
-	if (stats->cr != stats->crlf)
+	if (stats->lonecr)
 		return 1;
 	if (stats->nul)
 		return 1;
@@ -98,19 +100,18 @@ static int convert_is_binary(unsigned long size, const struct text_stat *stats)
 static unsigned int gather_convert_stats(const char *data, unsigned long size)
 {
 	struct text_stat stats;
+	int ret = 0;
 	if (!data || !size)
 		return 0;
 	gather_stats(data, size, &stats);
 	if (convert_is_binary(size, &stats))
-		return CONVERT_STAT_BITS_BIN;
-	else if (stats.crlf && stats.crlf == stats.lf)
-		return CONVERT_STAT_BITS_TXT_CRLF;
-	else if (stats.crlf && stats.lf)
-		return CONVERT_STAT_BITS_TXT_CRLF | CONVERT_STAT_BITS_TXT_LF;
-	else if (stats.lf)
-		return CONVERT_STAT_BITS_TXT_LF;
-	else
-		return 0;
+		ret |= CONVERT_STAT_BITS_BIN;
+	if (stats.crlf)
+		ret |= CONVERT_STAT_BITS_TXT_CRLF;
+	if (stats.lonelf)
+		ret |=  CONVERT_STAT_BITS_TXT_LF;
+
+	return ret;
 }
 
 static const char *gather_convert_stats_ascii(const char *data, unsigned long size)
@@ -207,7 +208,7 @@ static void check_safe_crlf(const char *path, enum crlf_action crlf_action,
 		 * CRLFs would be added by checkout:
 		 * check if we have "naked" LFs
 		 */
-		if (stats->lf != stats->crlf) {
+		if (stats->lonelf) {
 			if (checksafe == SAFE_CRLF_WARN)
 				warning("LF will be replaced by CRLF in %s.\nThe file will have its original line endings in your working directory.", path);
 			else /* i.e. SAFE_CRLF_FAIL */
@@ -266,8 +267,8 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
 
 	check_safe_crlf(path, crlf_action, &stats, checksafe);
 
-	/* Optimization: No CR? Nothing to convert, regardless. */
-	if (!stats.cr)
+	/* Optimization: No CRLF? Nothing to convert, regardless. */
+	if (!stats.crlf)
 		return 0;
 
 	/*
@@ -314,19 +315,15 @@ static int crlf_to_worktree(const char *path, const char *src, size_t len,
 
 	gather_stats(src, len, &stats);
 
-	/* No LF? Nothing to convert, regardless. */
-	if (!stats.lf)
-		return 0;
-
-	/* Was it already in CRLF format? */
-	if (stats.lf == stats.crlf)
+	/* No "naked" LF? Nothing to convert, regardless. */
+	if (!stats.lonelf)
 		return 0;
 
 	if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
 		if (crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
 			/* If we have any CR or CRLF line endings, we do not touch it */
 			/* This is the new safer autocrlf-handling */
-			if (stats.cr > 0 || stats.crlf > 0)
+			if (stats.lonecr || stats.crlf )
 				return 0;
 		}
 
@@ -338,7 +335,7 @@ static int crlf_to_worktree(const char *path, const char *src, size_t len,
 	if (src == buf->buf)
 		to_free = strbuf_detach(buf, NULL);
 
-	strbuf_grow(buf, len + stats.lf - stats.crlf);
+	strbuf_grow(buf, len + stats.lonelf);
 	for (;;) {
 		const char *nl = memchr(src, '\n', len);
 		if (!nl)
-- 
2.7.0.303.g2c4f448.dirty
Previous: tboegi@web.deNext: tboegi@web.de
Message 40 of 47 in “t0027: Add tests for get_stream_filter()”
  1. t0027: Add tests for get_stream_filter()tboegi@web.de, Jan 24, 2016
  2. Junio C HamanoJan 27, 2016
  3. Torsten BögershausenJan 27, 2016
  4. 1/6 t0027: Add tests for get_stream_filter()tboegi@web.de, Jan 27, 2016
  5. 1/6 t0027: Add tests for get_stream_filter()tboegi@web.de, Feb 2, 2016
  6. Junio C HamanoFeb 2, 2016
  7. 2/6 convert.c: Remove path when not neededtboegi@web.de, Feb 2, 2016
  8. Junio C HamanoFeb 2, 2016
  9. 3/6 convert.c: Remove input_crlf_action()tboegi@web.de, Feb 2, 2016
  10. Junio C HamanoFeb 2, 2016
  11. 4/6 convert.c: Use text_eol_is_crlf()tboegi@web.de, Feb 2, 2016
  12. 5/6 convert: auto_crlf=false and no attributes set: same as binarytboegi@web.de, Feb 2, 2016
  13. 6/6 convert.c: Refactor crlf_actiontboegi@web.de, Feb 2, 2016
  14. 1/7 t0027: Add tests for get_stream_filter()tboegi@web.de, Feb 4, 2016
  15. Junio C HamanoFeb 4, 2016
  16. 2/7 convert.c: remove unused parameter 'path'tboegi@web.de, Feb 4, 2016
  17. 3/7 convert.c: Remove input_crlf_action()tboegi@web.de, Feb 4, 2016
  18. 4/7 convert.c: Use text_eol_is_crlf()tboegi@web.de, Feb 4, 2016
  19. Junio C HamanoFeb 4, 2016
  20. 5/7 convert: auto_crlf=false and no attributes set: same as binarytboegi@web.de, Feb 4, 2016
  21. 6/7 convert.c: Refactor crlf_actiontboegi@web.de, Feb 4, 2016
  22. 7/7 convert.c: simplify text_stattboegi@web.de, Feb 4, 2016
  23. Junio C HamanoFeb 4, 2016
  24. 1/7 t0027: Add tests for get_stream_filter()tboegi@web.de, Feb 5, 2016
  25. Junio C HamanoFeb 8, 2016
  26. 2/7 convert.c: remove unused parameter 'path'tboegi@web.de, Feb 5, 2016
  27. 3/7 convert.c: Remove input_crlf_action()tboegi@web.de, Feb 5, 2016
  28. 4/7 convert.c: use text_eol_is_crlf()tboegi@web.de, Feb 5, 2016
  29. 5/7 convert: auto_crlf=false and no attributes set: same as binarytboegi@web.de, Feb 5, 2016
  30. Junio C HamanoFeb 8, 2016
  31. Torsten BögershausenFeb 9, 2016
  32. Junio C HamanoFeb 9, 2016
  33. 6/7 convert.c: refactor crlf_actiontboegi@web.de, Feb 5, 2016
  34. 7/7 convert.c: simplify text_stattboegi@web.de, Feb 5, 2016
  35. 1/6 t0027: add tests for get_stream_filter()tboegi@web.de, Feb 10, 2016
  36. 2/6 convert.c: remove unused parameter 'path'tboegi@web.de, Feb 10, 2016
  37. 3/6 convert.c: remove input_crlf_action()tboegi@web.de, Feb 10, 2016
  38. 4/6 convert.c: use text_eol_is_crlf()tboegi@web.de, Feb 10, 2016
  39. 5/6 convert.c: refactor crlf_actiontboegi@web.de, Feb 10, 2016
  40. 6/6 convert.c: simplify text_stattboegi@web.de, Feb 10, 2016
  41. 1/1 convert.c: correct attr_actiontboegi@web.de, Feb 22, 2016
  42. Eric SunshineFeb 22, 2016
  43. Junio C HamanoFeb 22, 2016
  44. Junio C HamanoFeb 22, 2016
  45. Torsten BögershausenFeb 23, 2016
  46. 1/1 convert.c: correct attr_actiontboegi@web.de, Feb 23, 2016
  47. Junio C HamanoFeb 23, 2016

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.