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

[PATCH v3 6/7] convert.c: refactor crlf_action

From
tboegi@web.de <tboegi@web.de>
Date
Feb 5, 2016, 16:13 UTC
Message-ID
<1454688808-20910-1-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>

Refactor the determination and usage of crlf_action. Today, when no attributes are set on a file, crlf_action is set to CRLF_GUESS, and later, CRLF_GUESS is used as an indication that core.autocrlf is not false and that some automatic eol conversion is needed. Make more clear, what is what, by defining:

- CRLF_UNDEFINED : No attributes set. Temparally used, until core.autocrlf
                   and core.eol is evaluated and one of CRLF_BINARY,
                   CRLF_AUTO_INPUT or CRLF_AUTO_CRLF is selected
- CRLF_BINARY    : No processing of line endings.
- CRLF_TEXT      : attribute "text" is set, line endings are processed.
- CRLF_TEXT_INPUT: attribute "input" or "eol=lf" is set. This implies text.
- CRLF_TEXT_CRLF : attribute "eol=crlf" is set. This implies text.
- CRLF_AUTO      : attribute "auto" is set.
- CRLF_AUTO_INPUT: No attributes, core.autocrlf=input
- CRLF_AUTO_CRLF : No attributes, core.autocrlf=true
Signed-off-by: Torsten Bögershausen <tboegi@web.de>
---
 convert.c | 75 ++++++++++++++++++++++++++++++++++++++-------------------------
 1 file changed, 45 insertions(+), 30 deletions(-)
diff --git a/convert.c b/convert.c
index e9c9448..e4e2877 100644
--- a/convert.c
+++ b/convert.c
@@ -19,12 +19,14 @@
 #define CONVERT_STAT_BITS_BIN       0x4
 
 enum crlf_action {
-	CRLF_GUESS = -1,
-	CRLF_BINARY = 0,
+	CRLF_UNDEFINED,
+	CRLF_BINARY,
 	CRLF_TEXT,
-	CRLF_INPUT,
-	CRLF_CRLF,
-	CRLF_AUTO
+	CRLF_TEXT_INPUT,
+	CRLF_TEXT_CRLF,
+	CRLF_AUTO,
+	CRLF_AUTO_INPUT,
+	CRLF_AUTO_CRLF
 };
 
 struct text_stat {
@@ -167,18 +169,19 @@ static enum eol output_eol(enum crlf_action crlf_action)
 	switch (crlf_action) {
 	case CRLF_BINARY:
 		return EOL_UNSET;
-	case CRLF_CRLF:
+	case CRLF_TEXT_CRLF:
 		return EOL_CRLF;
-	case CRLF_INPUT:
+	case CRLF_TEXT_INPUT:
 		return EOL_LF;
-	case CRLF_GUESS:
-		if (!auto_crlf)
-			return EOL_UNSET;
-		/* fall through */
+	case CRLF_UNDEFINED:
+	case CRLF_AUTO_CRLF:
+	case CRLF_AUTO_INPUT:
 	case CRLF_TEXT:
 	case CRLF_AUTO:
+		/* fall through */
 		return text_eol_is_crlf() ? EOL_CRLF : EOL_LF;
 	}
+	warning("Illegal crlf_action %d\n", (int)crlf_action);
 	return core_eol;
 }
 
@@ -247,11 +250,11 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
 
 	gather_stats(src, len, &stats);
 
-	if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) {
+	if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
 		if (convert_is_binary(len, &stats))
 			return 0;
 
-		if (crlf_action == CRLF_GUESS) {
+		if (crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
 			/*
 			 * If the file in the index has any CR in it, do not convert.
 			 * This is the new safer autocrlf handling.
@@ -278,7 +281,7 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
 	if (strbuf_avail(buf) + buf->len < len)
 		strbuf_grow(buf, len - buf->len);
 	dst = buf->buf;
-	if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) {
+	if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
 		/*
 		 * If we guessed, we already know we rejected a file with
 		 * lone CR, and we can strip a CR without looking at what
@@ -319,8 +322,8 @@ static int crlf_to_worktree(const char *path, const char *src, size_t len,
 	if (stats.lf == stats.crlf)
 		return 0;
 
-	if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) {
-		if (crlf_action == CRLF_GUESS) {
+	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)
@@ -708,16 +711,16 @@ static enum crlf_action git_path_check_crlf(struct git_attr_check *check)
 	const char *value = check->value;
 
 	if (ATTR_TRUE(value))
-		return CRLF_TEXT;
+		return text_eol_is_crlf() ? CRLF_TEXT_CRLF : CRLF_TEXT_INPUT;
 	else if (ATTR_FALSE(value))
 		return CRLF_BINARY;
 	else if (ATTR_UNSET(value))
 		;
 	else if (!strcmp(value, "input"))
-		return CRLF_INPUT;
+		return CRLF_TEXT_INPUT;
 	else if (!strcmp(value, "auto"))
 		return CRLF_AUTO;
-	return CRLF_GUESS;
+	return CRLF_UNDEFINED;
 }
 
 static enum eol git_path_check_eol(struct git_attr_check *check)
@@ -780,7 +783,7 @@ static void convert_attrs(struct conv_attrs *ca, const char *path)
 	if (!git_check_attr(path, NUM_CONV_ATTRS, ccheck)) {
 		enum eol eol_attr;
 		ca->crlf_action = git_path_check_crlf(ccheck + 4);
-		if (ca->crlf_action == CRLF_GUESS)
+		if (ca->crlf_action == CRLF_UNDEFINED)
 			ca->crlf_action = git_path_check_crlf(ccheck + 0);
 		ca->attr_action = ca->crlf_action;
 		ca->ident = git_path_check_ident(ccheck + 1);
@@ -789,16 +792,22 @@ static void convert_attrs(struct conv_attrs *ca, const char *path)
 			return;
 		eol_attr = git_path_check_eol(ccheck + 3);
 		if (eol_attr == EOL_LF)
-			ca->crlf_action = CRLF_INPUT;
+			ca->crlf_action = CRLF_TEXT_INPUT;
 		else if (eol_attr == EOL_CRLF)
-			ca->crlf_action = CRLF_CRLF;
+			ca->crlf_action = CRLF_TEXT_CRLF;
 	} else {
 		ca->drv = NULL;
-		ca->crlf_action = CRLF_GUESS;
+		ca->crlf_action = CRLF_UNDEFINED;
 		ca->ident = 0;
 	}
-	if (ca->crlf_action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE)
+	if (ca->crlf_action == CRLF_TEXT)
+		ca->crlf_action = text_eol_is_crlf() ? CRLF_TEXT_CRLF : CRLF_TEXT_INPUT;
+	if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_FALSE)
 		ca->crlf_action = CRLF_BINARY;
+	if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_TRUE)
+		ca->crlf_action = CRLF_AUTO_CRLF;
+	if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_INPUT)
+		ca->crlf_action = CRLF_AUTO_INPUT;
 }
 
 int would_convert_to_git_filter_fd(const char *path)
@@ -826,18 +835,22 @@ const char *get_convert_attr_ascii(const char *path)
 
 	convert_attrs(&ca, path);
 	switch (ca.attr_action) {
-	case CRLF_GUESS:
+	case CRLF_UNDEFINED:
 		return "";
 	case CRLF_BINARY:
 		return "-text";
 	case CRLF_TEXT:
 		return "text";
-	case CRLF_INPUT:
+	case CRLF_TEXT_INPUT:
 		return "text eol=lf";
-	case CRLF_CRLF:
-		return "text=auto eol=crlf";
+	case CRLF_TEXT_CRLF:
+		return "text eol=crlf";
 	case CRLF_AUTO:
 		return "text=auto";
+	case CRLF_AUTO_CRLF:
+		return "text=auto eol=crlf"; /* This is not supported yet */
+	case CRLF_AUTO_INPUT:
+		return "text=auto eol=lf"; /* This is not supported yet */
 	}
 	return "";
 }
@@ -1383,11 +1396,13 @@ struct stream_filter *get_stream_filter(const char *path, const unsigned char *s
 
 	crlf_action = ca.crlf_action;
 
-	if ((crlf_action == CRLF_BINARY) || (crlf_action == CRLF_INPUT))
+	if ((crlf_action == CRLF_BINARY) ||
+			crlf_action == CRLF_AUTO_INPUT ||
+			(crlf_action == CRLF_TEXT_INPUT))
 		filter = cascade_filter(filter, &null_filter_singleton);
 
 	else if (output_eol(crlf_action) == EOL_CRLF &&
-		 !(crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS))
+		 !(crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_CRLF))
 		filter = cascade_filter(filter, lf_to_crlf_filter());
 
 	return filter;

-- 
2.7.0.303.g2c4f448.dirty
Previous: Junio C HamanoNext: tboegi@web.de
Message 33 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.