ls-files: add eol diagnostics

When working in a cross-platform environment, a user may want to
check if text files are stored normalized in the repository and
if .gitattributes are set appropriately.

Make it possible to let Git show the line endings in the index and
in the working tree and the effective text/eol attributes.

The end of line ("eolinfo") are shown like this:

    "-text"        binary (or with bare CR) file
    "none"         text file without any EOL
    "lf"           text file with LF
    "crlf"         text file with CRLF
    "mixed"        text file with mixed line endings.

The effective text/eol attribute is one of these:

    "", "-text", "text", "text=auto", "text eol=lf", "text eol=crlf"

git ls-files --eol gives an output like this:

    i/none   w/none   attr/text=auto      t/t5100/empty
    i/-text  w/-text  attr/-text          t/test-binary-2.png
    i/lf     w/lf     attr/text eol=lf    t/t5100/rfc2047-info-0007
    i/lf     w/crlf   attr/text eol=crlf  doit.bat
    i/mixed  w/mixed  attr/               locale/XX.po

to show what eol convention is used in the data in the index ('i'),
and in the working tree ('w'), and what attribute is in effect,
for each path that is shown.

Add test cases in t0027.

Helped-By: Eric Sunshine <sunshine@sunshineco.com>
Signed-off-by: Torsten Bögershausen <tboegi@web.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Documentation/git-ls-files.txt

@@ -12,6 +12,7 @@ SYNOPSIS
 'git ls-files' [-z] [-t] [-v]
 		(--[cached|deleted|others|ignored|stage|unmerged|killed|modified])*
 		(-[c|d|o|i|s|u|k|m])*
+		[--eol]
 		[-x <pattern>|--exclude=<pattern>]
 		[-X <file>|--exclude-from=<file>]
 		[--exclude-per-directory=<file>]
@@ -147,6 +148,24 @@ a space) at the start of each line:
 	possible for manual inspection; the exact format may change at
 	any time.
 
+--eol::
+	Show <eolinfo> and <eolattr> of files.
+	<eolinfo> is the file content identification used by Git when
+	the "text" attribute is "auto" (or not set and core.autocrlf is not false).
+	<eolinfo> is either "-text", "none", "lf", "crlf", "mixed" or "".
++
+"" means the file is not a regular file, it is not in the index or
+not accessable in the working tree.
++
+<eolattr> is the attribute that is used when checking out or committing,
+it is either "", "-text", "text", "text=auto", "text eol=lf", "text eol=crlf".
+Note: Currently Git does not support "text=auto eol=lf" or "text=auto eol=crlf",
+that may change in the future.
++
+Both the <eolinfo> in the index ("i/<eolinfo>")
+and in the working tree ("w/<eolinfo>") are shown for regular files,
+followed by the  ("attr/<eolattr>").
+
 \--::
 	Do not interpret any more arguments as options.
 
@@ -161,6 +180,9 @@ which case it outputs:
 
         [<tag> ]<mode> <object> <stage> <file>
 
+'git ls-files --eol' will show
+	i/<eolinfo><SPACES>w/<eolinfo><SPACES>attr/<eolattr><SPACE*><TAB><file>
+
 'git ls-files --unmerged' and 'git ls-files --stage' can be used to examine
 detailed information on unmerged paths.
 

builtin/ls-files.c

@@ -27,6 +27,7 @@ static int show_killed;
 static int show_valid_bit;
 static int line_terminator = '\n';
 static int debug_mode;
+static int show_eol;
 
 static const char *prefix;
 static int max_prefix_len;
@@ -47,6 +48,23 @@ static const char *tag_modified = "";
 static const char *tag_skip_worktree = "";
 static const char *tag_resolve_undo = "";
 
+static void write_eolinfo(const struct cache_entry *ce, const char *path)
+{
+	if (!show_eol)
+		return;
+	else {
+		struct stat st;
+		const char *i_txt = "";
+		const char *w_txt = "";
+		const char *a_txt = get_convert_attr_ascii(path);
+		if (ce && S_ISREG(ce->ce_mode))
+			i_txt = get_cached_convert_stats_ascii(ce->name);
+		if (!lstat(path, &st) && S_ISREG(st.st_mode))
+			w_txt = get_wt_convert_stats_ascii(path);
+		printf("i/%-5s w/%-5s attr/%-17s\t", i_txt, w_txt, a_txt);
+	}
+}
+
 static void write_name(const char *name)
 {
 	/*
@@ -68,6 +86,7 @@ static void show_dir_entry(const char *tag, struct dir_entry *ent)
 		return;
 
 	fputs(tag, stdout);
+	write_eolinfo(NULL, ent->name);
 	write_name(ent->name);
 }
 
@@ -170,6 +189,7 @@ static void show_ce_entry(const char *tag, const struct cache_entry *ce)
 		       find_unique_abbrev(ce->sha1,abbrev),
 		       ce_stage(ce));
 	}
+	write_eolinfo(ce, ce->name);
 	write_name(ce->name);
 	if (debug_mode) {
 		const struct stat_data *sd = &ce->ce_stat_data;
@@ -433,6 +453,7 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix)
 		OPT_BIT(0, "directory", &dir.flags,
 			N_("show 'other' directories' names only"),
 			DIR_SHOW_OTHER_DIRECTORIES),
+		OPT_BOOL(0, "eol", &show_eol, N_("show line endings of files")),
 		OPT_NEGBIT(0, "empty-directory", &dir.flags,
 			N_("don't show empty directories"),
 			DIR_HIDE_EMPTY_DIRECTORIES),

convert.c

@@ -13,6 +13,11 @@
  * translation when the "text" attribute or "auto_crlf" option is set.
  */
 
+/* Stat bits: When BIN is set, the txt bits are unset */
+#define CONVERT_STAT_BITS_TXT_LF    0x1
+#define CONVERT_STAT_BITS_TXT_CRLF  0x2
+#define CONVERT_STAT_BITS_BIN       0x4
+
 enum crlf_action {
 	CRLF_GUESS = -1,
 	CRLF_BINARY = 0,
@@ -75,26 +80,75 @@ static void gather_stats(const char *buf, unsigned long size, struct text_stat *
 
 /*
  * The same heuristics as diff.c::mmfile_is_binary()
+ * We treat files with bare CR as binary
  */
-static int is_binary(unsigned long size, struct text_stat *stats)
+static int convert_is_binary(unsigned long size, const struct text_stat *stats)
 {
-
+	if (stats->cr != stats->crlf)
+		return 1;
 	if (stats->nul)
 		return 1;
 	if ((stats->printable >> 7) < stats->nonprintable)
 		return 1;
-	/*
-	 * Other heuristics? Average line length might be relevant,
-	 * as might LF vs CR vs CRLF counts..
-	 *
-	 * NOTE! It might be normal to have a low ratio of CRLF to LF
-	 * (somebody starts with a LF-only file and edits it with an editor
-	 * that adds CRLF only to lines that are added..). But do  we
-	 * want to support CR-only? Probably not.
-	 */
 	return 0;
 }
 
+static unsigned int gather_convert_stats(const char *data, unsigned long size)
+{
+	struct text_stat stats;
+	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;
+}
+
+static const char *gather_convert_stats_ascii(const char *data, unsigned long size)
+{
+	unsigned int convert_stats = gather_convert_stats(data, size);
+
+	if (convert_stats & CONVERT_STAT_BITS_BIN)
+		return "-text";
+	switch (convert_stats) {
+	case CONVERT_STAT_BITS_TXT_LF:
+		return "lf";
+	case CONVERT_STAT_BITS_TXT_CRLF:
+		return "crlf";
+	case CONVERT_STAT_BITS_TXT_LF | CONVERT_STAT_BITS_TXT_CRLF:
+		return "mixed";
+	default:
+		return "none";
+	}
+}
+
+const char *get_cached_convert_stats_ascii(const char *path)
+{
+	const char *ret;
+	unsigned long sz;
+	void *data = read_blob_data_from_cache(path, &sz);
+	ret = gather_convert_stats_ascii(data, sz);
+	free(data);
+	return ret;
+}
+
+const char *get_wt_convert_stats_ascii(const char *path)
+{
+	const char *ret = "";
+	struct strbuf sb = STRBUF_INIT;
+	if (strbuf_read_file(&sb, path, 0) >= 0)
+		ret = gather_convert_stats_ascii(sb.buf, sb.len);
+	strbuf_release(&sb);
+	return ret;
+}
+
 static enum eol output_eol(enum crlf_action crlf_action)
 {
 	switch (crlf_action) {
@@ -187,18 +241,7 @@ 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) {
-		/*
-		 * We're currently not going to even try to convert stuff
-		 * that has bare CR characters. Does anybody do that crazy
-		 * stuff?
-		 */
-		if (stats.cr != stats.crlf)
-			return 0;
-
-		/*
-		 * And add some heuristics for binary vs text, of course...
-		 */
-		if (is_binary(len, &stats))
+		if (convert_is_binary(len, &stats))
 			return 0;
 
 		if (crlf_action == CRLF_GUESS) {
@@ -277,11 +320,7 @@ static int crlf_to_worktree(const char *path, const char *src, size_t len,
 				return 0;
 		}
 
-		/* If we have any bare CR characters, we're not going to touch it */
-		if (stats.cr != stats.crlf)
-			return 0;
-
-		if (is_binary(len, &stats))
+		if (convert_is_binary(len, &stats))
 			return 0;
 	}
 
@@ -777,6 +816,30 @@ int would_convert_to_git_filter_fd(const char *path)
 	return apply_filter(path, NULL, 0, -1, NULL, ca.drv->clean);
 }
 
+const char *get_convert_attr_ascii(const char *path)
+{
+	struct conv_attrs ca;
+	enum crlf_action crlf_action;
+
+	convert_attrs(&ca, path);
+	crlf_action = input_crlf_action(ca.crlf_action, ca.eol_attr);
+	switch (crlf_action) {
+	case CRLF_GUESS:
+		return "";
+	case CRLF_BINARY:
+		return "-text";
+	case CRLF_TEXT:
+		return "text";
+	case CRLF_INPUT:
+		return "text eol=lf";
+	case CRLF_CRLF:
+		return "text=auto eol=crlf";
+	case CRLF_AUTO:
+		return "text=auto";
+	}
+	return "";
+}
+
 int convert_to_git(const char *path, const char *src, size_t len,
                    struct strbuf *dst, enum safe_crlf checksafe)
 {

convert.h

@@ -32,6 +32,9 @@ enum eol {
 };
 
 extern enum eol core_eol;
+extern const char *get_cached_convert_stats_ascii(const char *path);
+extern const char *get_wt_convert_stats_ascii(const char *path);
+extern const char *get_convert_attr_ascii(const char *path);
 
 /* returns 1 if *dst was used */
 extern int convert_to_git(const char *path, const char *src, size_t len,