Merge branch 'js/commit-format'

* js/commit-format:
  show_date(): rename the "relative" parameter to "mode"
  Actually make print_wrapped_text() useful
  pretty-formats: add 'format:<string>'

8 files changed, 268 insertions, 16 deletions

diff --git a/Documentation/pretty-formats.txt b/Documentation/pretty-formats.txt
index fb0b0b9582..2fe6c31967 100644
--- a/Documentation/pretty-formats.txt
+++ b/Documentation/pretty-formats.txt
@@ -77,9 +77,53 @@ displayed in full, regardless of whether --abbrev or
 true parent commits, without taking grafts nor history
 simplification into account.
 
+	* 'format:'
++
+The 'format:' format allows you to specify which information
+you want to show. It works a little bit like printf format,
+with the notable exception that you get a newline with '%n'
+instead of '\n'.
+
+E.g, 'format:"The author of %h was %an, %ar%nThe title was >>%s<<"'
+would show something like this:
+
+The author of fe6e0ee was Junio C Hamano, 23 hours ago
+The title was >>t4119: test autocomputing -p<n> for traditional diff input.<<
+
+The placeholders are:
+
+- '%H': commit hash
+- '%h': abbreviated commit hash
+- '%T': tree hash
+- '%t': abbreviated tree hash
+- '%P': parent hashes
+- '%p': abbreviated parent hashes
+- '%an': author name
+- '%ae': author email
+- '%ad': author date
+- '%aD': author date, RFC2822 style
+- '%ar': author date, relative
+- '%at': author date, UNIX timestamp
+- '%cn': committer name
+- '%ce': committer email
+- '%cd': committer date
+- '%cD': committer date, RFC2822 style
+- '%cr': committer date, relative
+- '%ct': committer date, UNIX timestamp
+- '%e': encoding
+- '%s': subject
+- '%b': body
+- '%Cred': switch color to red
+- '%Cgreen': switch color to green
+- '%Cblue': switch color to blue
+- '%Creset': reset color
+- '%n': newline
+
+
 --encoding[=<encoding>]::
 	The commit objects record the encoding used for the log message
 	in their encoding header; this option can be used to tell the
 	command to re-code the commit log message in the encoding
 	preferred by the user.  For non plumbing commands this
 	defaults to UTF-8.
+
diff --git a/cache.h b/cache.h
index b84e3decfc..8018b2cd3b 100644
--- a/cache.h
+++ b/cache.h
@@ -327,7 +327,8 @@ extern void *read_object_with_reference(const unsigned char *sha1,
 					unsigned long *size,
 					unsigned char *sha1_ret);
 
-const char *show_date(unsigned long time, int timezone, int relative);
+enum date_mode { DATE_NORMAL = 0, DATE_RELATIVE, DATE_SHORT };
+const char *show_date(unsigned long time, int timezone, enum date_mode mode);
 const char *show_rfc2822_date(unsigned long time, int timezone);
 int parse_date(const char *date, char *buf, int bufsize);
 void datestamp(char *buf, int bufsize);
diff --git a/commit.c b/commit.c
index da515a4973..5552527342 100644
--- a/commit.c
+++ b/commit.c
@@ -3,6 +3,7 @@
 #include "commit.h"
 #include "pkt-line.h"
 #include "utf8.h"
+#include "interpolate.h"
 
 int save_commit_buffer = 1;
 
@@ -36,8 +37,11 @@ struct cmt_fmt_map {
 	{ "full",	5,	CMIT_FMT_FULL },
 	{ "fuller",	5,	CMIT_FMT_FULLER },
 	{ "oneline",	1,	CMIT_FMT_ONELINE },
+	{ "format:",	7,	CMIT_FMT_USERFORMAT},
 };
 
+static char *user_format;
+
 enum cmit_fmt get_commit_format(const char *arg)
 {
 	int i;
@@ -46,6 +50,12 @@ enum cmit_fmt get_commit_format(const char *arg)
 		return CMIT_FMT_DEFAULT;
 	if (*arg == '=')
 		arg++;
+	if (!prefixcmp(arg, "format:")) {
+		if (user_format)
+			free(user_format);
+		user_format = xstrdup(arg + 7);
+		return CMIT_FMT_USERFORMAT;
+	}
 	for (i = 0; i < ARRAY_SIZE(cmt_fmts); i++) {
 		if (!strncmp(arg, cmt_fmts[i].n, cmt_fmts[i].cmp_len) &&
 		    !strncmp(arg, cmt_fmts[i].n, strlen(arg)))
@@ -710,6 +720,188 @@ static char *logmsg_reencode(const struct commit *commit,
 	return out;
 }
 
+static char *xstrndup(const char *text, int len)
+{
+	char *result = xmalloc(len + 1);
+	memcpy(result, text, len);
+	result[len] = '\0';
+	return result;
+}
+
+static void fill_person(struct interp *table, const char *msg, int len)
+{
+	int start, end, tz = 0;
+	unsigned long date;
+	char *ep;
+
+	/* parse name */
+	for (end = 0; end < len && msg[end] != '<'; end++)
+		; /* do nothing */
+	start = end + 1;
+	while (end > 0 && isspace(msg[end - 1]))
+		end--;
+	table[0].value = xstrndup(msg, end);
+
+	if (start >= len)
+		return;
+
+	/* parse email */
+	for (end = start + 1; end < len && msg[end] != '>'; end++)
+		; /* do nothing */
+
+	if (end >= len)
+		return;
+
+	table[1].value = xstrndup(msg + start, end - start);
+
+	/* parse date */
+	for (start = end + 1; start < len && isspace(msg[start]); start++)
+		; /* do nothing */
+	if (start >= len)
+		return;
+	date = strtoul(msg + start, &ep, 10);
+	if (msg + start == ep)
+		return;
+
+	table[5].value = xstrndup(msg + start, ep - msg + start);
+
+	/* parse tz */
+	for (start = ep - msg + 1; start < len && isspace(msg[start]); start++)
+		; /* do nothing */
+	if (start + 1 < len) {
+		tz = strtoul(msg + start + 1, NULL, 10);
+		if (msg[start] == '-')
+			tz = -tz;
+	}
+
+	interp_set_entry(table, 2, show_date(date, tz, 0));
+	interp_set_entry(table, 3, show_rfc2822_date(date, tz));
+	interp_set_entry(table, 4, show_date(date, tz, 1));
+}
+
+static long format_commit_message(const struct commit *commit,
+		const char *msg, char *buf, unsigned long space)
+{
+	struct interp table[] = {
+		{ "%H" },	/* commit hash */
+		{ "%h" },	/* abbreviated commit hash */
+		{ "%T" },	/* tree hash */
+		{ "%t" },	/* abbreviated tree hash */
+		{ "%P" },	/* parent hashes */
+		{ "%p" },	/* abbreviated parent hashes */
+		{ "%an" },	/* author name */
+		{ "%ae" },	/* author email */
+		{ "%ad" },	/* author date */
+		{ "%aD" },	/* author date, RFC2822 style */
+		{ "%ar" },	/* author date, relative */
+		{ "%at" },	/* author date, UNIX timestamp */
+		{ "%cn" },	/* committer name */
+		{ "%ce" },	/* committer email */
+		{ "%cd" },	/* committer date */
+		{ "%cD" },	/* committer date, RFC2822 style */
+		{ "%cr" },	/* committer date, relative */
+		{ "%ct" },	/* committer date, UNIX timestamp */
+		{ "%e" },	/* encoding */
+		{ "%s" },	/* subject */
+		{ "%b" },	/* body */
+		{ "%Cred" },	/* red */
+		{ "%Cgreen" },	/* green */
+		{ "%Cblue" },	/* blue */
+		{ "%Creset" },	/* reset color */
+		{ "%n" }	/* newline */
+	};
+	enum interp_index {
+		IHASH = 0, IHASH_ABBREV,
+		ITREE, ITREE_ABBREV,
+		IPARENTS, IPARENTS_ABBREV,
+		IAUTHOR_NAME, IAUTHOR_EMAIL,
+		IAUTHOR_DATE, IAUTHOR_DATE_RFC2822, IAUTHOR_DATE_RELATIVE,
+		IAUTHOR_TIMESTAMP,
+		ICOMMITTER_NAME, ICOMMITTER_EMAIL,
+		ICOMMITTER_DATE, ICOMMITTER_DATE_RFC2822,
+		ICOMMITTER_DATE_RELATIVE, ICOMMITTER_TIMESTAMP,
+		IENCODING,
+		ISUBJECT,
+		IBODY,
+		IRED, IGREEN, IBLUE, IRESET_COLOR,
+		INEWLINE
+	};
+	struct commit_list *p;
+	char parents[1024];
+	int i;
+	enum { HEADER, SUBJECT, BODY } state;
+
+	if (INEWLINE + 1 != ARRAY_SIZE(table))
+		die("invalid interp table!");
+
+	/* these are independent of the commit */
+	interp_set_entry(table, IRED, "\033[31m");
+	interp_set_entry(table, IGREEN, "\033[32m");
+	interp_set_entry(table, IBLUE, "\033[34m");
+	interp_set_entry(table, IRESET_COLOR, "\033[m");
+	interp_set_entry(table, INEWLINE, "\n");
+
+	/* these depend on the commit */
+	if (!commit->object.parsed)
+		parse_object(commit->object.sha1);
+	interp_set_entry(table, IHASH, sha1_to_hex(commit->object.sha1));
+	interp_set_entry(table, IHASH_ABBREV,
+			find_unique_abbrev(commit->object.sha1,
+				DEFAULT_ABBREV));
+	interp_set_entry(table, ITREE, sha1_to_hex(commit->tree->object.sha1));
+	interp_set_entry(table, ITREE_ABBREV,
+			find_unique_abbrev(commit->tree->object.sha1,
+				DEFAULT_ABBREV));
+	for (i = 0, p = commit->parents;
+			p && i < sizeof(parents) - 1;
+			p = p->next)
+		i += snprintf(parents + i, sizeof(parents) - i - 1, "%s ",
+			sha1_to_hex(p->item->object.sha1));
+	interp_set_entry(table, IPARENTS, parents);
+	for (i = 0, p = commit->parents;
+			p && i < sizeof(parents) - 1;
+			p = p->next)
+		i += snprintf(parents + i, sizeof(parents) - i - 1, "%s ",
+			find_unique_abbrev(p->item->object.sha1,
+				DEFAULT_ABBREV));
+	interp_set_entry(table, IPARENTS_ABBREV, parents);
+
+	for (i = 0, state = HEADER; msg[i] && state < BODY; i++) {
+		int eol;
+		for (eol = i; msg[eol] && msg[eol] != '\n'; eol++)
+			; /* do nothing */
+
+		if (state == SUBJECT) {
+			table[ISUBJECT].value = xstrndup(msg + i, eol - i);
+			i = eol;
+		}
+		if (i == eol) {
+			state++;
+			/* strip empty lines */
+			while (msg[eol + 1] == '\n')
+				eol++;
+		} else if (!prefixcmp(msg + i, "author "))
+			fill_person(table + IAUTHOR_NAME,
+					msg + i + 7, eol - i - 7);
+		else if (!prefixcmp(msg + i, "committer "))
+			fill_person(table + ICOMMITTER_NAME,
+					msg + i + 10, eol - i - 10);
+		else if (!prefixcmp(msg + i, "encoding "))
+			table[IENCODING].value = xstrndup(msg + i, eol - i);
+		i = eol;
+	}
+	if (msg[i])
+		table[IBODY].value = xstrdup(msg + i);
+	for (i = 0; i < ARRAY_SIZE(table); i++)
+		if (!table[i].value)
+			interp_set_entry(table, i, "<unknown>");
+
+	interpolate(buf, space, user_format, table, ARRAY_SIZE(table));
+	interp_clear_table(table, ARRAY_SIZE(table));
+
+	return strlen(buf);
+}
+
 unsigned long pretty_print_commit(enum cmit_fmt fmt,
 				  const struct commit *commit,
 				  unsigned long len,
@@ -727,6 +919,9 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt,
 	char *reencoded;
 	char *encoding;
 
+	if (fmt == CMIT_FMT_USERFORMAT)
+		return format_commit_message(commit, msg, buf, space);
+
 	encoding = (git_log_output_encoding
 		    ? git_log_output_encoding
 		    : git_commit_encoding);
diff --git a/commit.h b/commit.h
index c73744463c..83507a07e4 100644
--- a/commit.h
+++ b/commit.h
@@ -47,6 +47,7 @@ enum cmit_fmt {
 	CMIT_FMT_FULLER,
 	CMIT_FMT_ONELINE,
 	CMIT_FMT_EMAIL,
+	CMIT_FMT_USERFORMAT,
 
 	CMIT_FMT_UNSPECIFIED,
 };
diff --git a/date.c b/date.c
index 542c004c2e..0ceccbe034 100644
--- a/date.c
+++ b/date.c
@@ -55,12 +55,12 @@ static struct tm *time_to_tm(unsigned long time, int tz)
 	return gmtime(&t);
 }
 
-const char *show_date(unsigned long time, int tz, int relative)
+const char *show_date(unsigned long time, int tz, enum date_mode mode)
 {
 	struct tm *tm;
 	static char timebuf[200];
 
-	if (relative) {
+	if (mode == DATE_RELATIVE) {
 		unsigned long diff;
 		struct timeval now;
 		gettimeofday(&now, NULL);
@@ -105,12 +105,16 @@ const char *show_date(unsigned long time, int tz, int relative)
 	tm = time_to_tm(time, tz);
 	if (!tm)
 		return NULL;
-	sprintf(timebuf, "%.3s %.3s %d %02d:%02d:%02d %d %+05d",
-		weekday_names[tm->tm_wday],
-		month_names[tm->tm_mon],
-		tm->tm_mday,
-		tm->tm_hour, tm->tm_min, tm->tm_sec,
-		tm->tm_year + 1900, tz);
+	if (mode == DATE_SHORT)
+		sprintf(timebuf, "%04d-%02d-%02d", tm->tm_year + 1900,
+				tm->tm_mon + 1, tm->tm_mday);
+	else
+		sprintf(timebuf, "%.3s %.3s %d %02d:%02d:%02d %d %+05d",
+				weekday_names[tm->tm_wday],
+				month_names[tm->tm_mon],
+				tm->tm_mday,
+				tm->tm_hour, tm->tm_min, tm->tm_sec,
+				tm->tm_year + 1900, tz);
 	return timebuf;
 }
 
diff --git a/log-tree.c b/log-tree.c
index ac86194047..6ce239d8f9 100644
--- a/log-tree.c
+++ b/log-tree.c
@@ -211,7 +211,7 @@ void show_log(struct rev_info *opt, const char *sep)
 				 sha1, sha1);
 			opt->diffopt.stat_sep = buffer;
 		}
-	} else {
+	} else if (opt->commit_format != CMIT_FMT_USERFORMAT) {
 		fputs(diff_get_color(opt->diffopt.color_diff, DIFF_COMMIT),
 		      stdout);
 		if (opt->commit_format != CMIT_FMT_ONELINE)
diff --git a/utf8.c b/utf8.c
index 7c80eeccb4..ea23a6e5dc 100644
--- a/utf8.c
+++ b/utf8.c
@@ -235,12 +235,19 @@ static void print_spaces(int count)
 /*
  * Wrap the text, if necessary. The variable indent is the indent for the
  * first line, indent2 is the indent for all other lines.
+ * If indent is negative, assume that already -indent columns have been
+ * consumed (and no extra indent is necessary for the first line).
  */
-void print_wrapped_text(const char *text, int indent, int indent2, int width)
+int print_wrapped_text(const char *text, int indent, int indent2, int width)
 {
 	int w = indent, assume_utf8 = is_utf8(text);
 	const char *bol = text, *space = NULL;
 
+	if (indent < 0) {
+		w = -indent;
+		space = text;
+	}
+
 	for (;;) {
 		char c = *text;
 		if (!c || isspace(c)) {
@@ -251,10 +258,9 @@ void print_wrapped_text(const char *text, int indent, int indent2, int width)
 				else
 					print_spaces(indent);
 				fwrite(start, text - start, 1, stdout);
-				if (!c) {
-					putchar('\n');
-					return;
-				} else if (c == '\t')
+				if (!c)
+					return w;
+				else if (c == '\t')
 					w |= 0x07;
 				space = text;
 				w++;
@@ -275,6 +281,7 @@ void print_wrapped_text(const char *text, int indent, int indent2, int width)
 			text++;
 		}
 	}
+	return w;
 }
 
 int is_encoding_utf8(const char *name)
diff --git a/utf8.h b/utf8.h
index a07c5a88af..15db6f1f27 100644
--- a/utf8.h
+++ b/utf8.h
@@ -5,7 +5,7 @@ int utf8_width(const char **start);
 int is_utf8(const char *text);
 int is_encoding_utf8(const char *name);
 
-void print_wrapped_text(const char *text, int indent, int indent2, int len);
+int print_wrapped_text(const char *text, int indent, int indent2, int len);
 
 #ifndef NO_ICONV
 char *reencode_string(const char *in, const char *out_encoding, const char *in_encoding);