X-Git-Url: https://git.tokkee.org/?a=blobdiff_plain;f=commit.c;h=f78ce262f6cd141b9b4b8ba1c73fc37ecc07d6f4;hb=e52a5de45ab8b61bdddf48a466cb3388b38ad7a4;hp=59ea77c577886a3ba5b4ef385099d7a564af173c;hpb=3bd5c81e0243e4ff391b38b31ef237e46eca257b;p=git.git

diff --git a/commit.c b/commit.c
index 59ea77c57..f78ce262f 100644
--- a/commit.c
+++ b/commit.c
@@ -2,6 +2,8 @@
 #include "tag.h"
 #include "commit.h"
 #include "pkt-line.h"
+#include "utf8.h"
+#include "interpolate.h"
 
 int save_commit_buffer = 1;
 
@@ -35,8 +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;
@@ -45,8 +50,15 @@ 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))
+		if (!strncmp(arg, cmt_fmts[i].n, cmt_fmts[i].cmp_len) &&
+		    !strncmp(arg, cmt_fmts[i].n, strlen(arg)))
 			return cmt_fmts[i].v;
 	}
 
@@ -248,8 +260,10 @@ int write_shallow_commits(int fd, int use_pack_protocol)
 			if (use_pack_protocol)
 				packet_write(fd, "shallow %s", hex);
 			else {
-				write(fd, hex,  40);
-				write(fd, "\n", 1);
+				if (write_in_full(fd, hex,  40) != 40)
+					break;
+				if (write_in_full(fd, "\n", 1) != 1)
+					break;
 			}
 		}
 	return count;
@@ -461,20 +475,29 @@ static int get_one_line(const char *msg, unsigned long len)
 	return ret;
 }
 
+/* High bit set, or ISO-2022-INT */
+static int non_ascii(int ch)
+{
+	ch = (ch & 0xff);
+	return ((ch & 0x80) || (ch == 0x1b));
+}
+
 static int is_rfc2047_special(char ch)
 {
-	return ((ch & 0x80) || (ch == '=') || (ch == '?') || (ch == '_'));
+	return (non_ascii(ch) || (ch == '=') || (ch == '?') || (ch == '_'));
 }
 
-static int add_rfc2047(char *buf, const char *line, int len)
+static int add_rfc2047(char *buf, const char *line, int len,
+		       const char *encoding)
 {
 	char *bp = buf;
 	int i, needquote;
-	static const char q_utf8[] = "=?utf-8?q?";
+	char q_encoding[128];
+	const char *q_encoding_fmt = "=?%s?q?";
 
 	for (i = needquote = 0; !needquote && i < len; i++) {
-		unsigned ch = line[i];
-		if (ch & 0x80)
+		int ch = line[i];
+		if (non_ascii(ch))
 			needquote++;
 		if ((i + 1 < len) &&
 		    (ch == '=' && line[i+1] == '?'))
@@ -483,8 +506,11 @@ static int add_rfc2047(char *buf, const char *line, int len)
 	if (!needquote)
 		return sprintf(buf, "%.*s", len, line);
 
-	memcpy(bp, q_utf8, sizeof(q_utf8)-1);
-	bp += sizeof(q_utf8)-1;
+	i = snprintf(q_encoding, sizeof(q_encoding), q_encoding_fmt, encoding);
+	if (sizeof(q_encoding) < i)
+		die("Insanely long encoding name %s", encoding);
+	memcpy(bp, q_encoding, i);
+	bp += i;
 	for (i = 0; i < len; i++) {
 		unsigned ch = line[i] & 0xFF;
 		if (is_rfc2047_special(ch)) {
@@ -502,7 +528,8 @@ static int add_rfc2047(char *buf, const char *line, int len)
 }
 
 static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf,
-			 const char *line, int relative_date)
+			 const char *line, int relative_date,
+			 const char *encoding)
 {
 	char *date;
 	int namelen;
@@ -530,7 +557,8 @@ static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf,
 		filler = "";
 		strcpy(buf, "From: ");
 		ret = strlen(buf);
-		ret += add_rfc2047(buf + ret, line, display_name_length);
+		ret += add_rfc2047(buf + ret, line, display_name_length,
+				   encoding);
 		memcpy(buf + ret, name_tail, namelen - display_name_length);
 		ret += namelen - display_name_length;
 		buf[ret++] = '\n';
@@ -597,17 +625,311 @@ static int add_merge_info(enum cmit_fmt fmt, char *buf, const struct commit *com
 	return offset;
 }
 
-unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit,
-				  unsigned long len, char *buf, unsigned long space,
+static char *get_header(const struct commit *commit, const char *key)
+{
+	int key_len = strlen(key);
+	const char *line = commit->buffer;
+
+	for (;;) {
+		const char *eol = strchr(line, '\n'), *next;
+
+		if (line == eol)
+			return NULL;
+		if (!eol) {
+			eol = line + strlen(line);
+			next = NULL;
+		} else
+			next = eol + 1;
+		if (!strncmp(line, key, key_len) && line[key_len] == ' ') {
+			int len = eol - line - key_len;
+			char *ret = xmalloc(len);
+			memcpy(ret, line + key_len + 1, len - 1);
+			ret[len - 1] = '\0';
+			return ret;
+		}
+		line = next;
+	}
+}
+
+static char *replace_encoding_header(char *buf, char *encoding)
+{
+	char *encoding_header = strstr(buf, "\nencoding ");
+	char *end_of_encoding_header;
+	int encoding_header_pos;
+	int encoding_header_len;
+	int new_len;
+	int need_len;
+	int buflen = strlen(buf) + 1;
+
+	if (!encoding_header)
+		return buf; /* should not happen but be defensive */
+	encoding_header++;
+	end_of_encoding_header = strchr(encoding_header, '\n');
+	if (!end_of_encoding_header)
+		return buf; /* should not happen but be defensive */
+	end_of_encoding_header++;
+
+	encoding_header_len = end_of_encoding_header - encoding_header;
+	encoding_header_pos = encoding_header - buf;
+
+	if (is_encoding_utf8(encoding)) {
+		/* we have re-coded to UTF-8; drop the header */
+		memmove(encoding_header, end_of_encoding_header,
+			buflen - (encoding_header_pos + encoding_header_len));
+		return buf;
+	}
+	new_len = strlen(encoding);
+	need_len = new_len + strlen("encoding \n");
+	if (encoding_header_len < need_len) {
+		buf = xrealloc(buf, buflen + (need_len - encoding_header_len));
+		encoding_header = buf + encoding_header_pos;
+		end_of_encoding_header = encoding_header + encoding_header_len;
+	}
+	memmove(end_of_encoding_header + (need_len - encoding_header_len),
+		end_of_encoding_header,
+		buflen - (encoding_header_pos + encoding_header_len));
+	memcpy(encoding_header + 9, encoding, strlen(encoding));
+	encoding_header[9 + new_len] = '\n';
+	return buf;
+}
+
+static char *logmsg_reencode(const struct commit *commit,
+			     char *output_encoding)
+{
+	char *encoding;
+	char *out;
+	char *utf8 = "utf-8";
+
+	if (!*output_encoding)
+		return NULL;
+	encoding = get_header(commit, "encoding");
+	if (!encoding)
+		encoding = utf8;
+	if (!strcmp(encoding, output_encoding))
+		out = strdup(commit->buffer);
+	else
+		out = reencode_string(commit->buffer,
+				      output_encoding, encoding);
+	if (out)
+		out = replace_encoding_header(out, output_encoding);
+
+	if (encoding != utf8)
+		free(encoding);
+	if (!out)
+		return NULL;
+	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,
+				  char *buf, unsigned long space,
 				  int abbrev, const char *subject,
-				  const char *after_subject, int relative_date)
+				  const char *after_subject,
+				  int relative_date)
 {
-	int hdr = 1, body = 0;
+	int hdr = 1, body = 0, seen_title = 0;
 	unsigned long offset = 0;
 	int indent = 4;
 	int parents_shown = 0;
 	const char *msg = commit->buffer;
 	int plain_non_ascii = 0;
+	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);
+	if (!encoding)
+		encoding = "utf-8";
+	reencoded = logmsg_reencode(commit, encoding);
+	if (reencoded)
+		msg = reencoded;
 
 	if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL)
 		indent = 0;
@@ -624,14 +946,14 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit
 		for (in_body = i = 0; (ch = msg[i]) && i < len; i++) {
 			if (!in_body) {
 				/* author could be non 7-bit ASCII but
-				 * the log may so; skip over the
+				 * the log may be so; skip over the
 				 * header part first.
 				 */
 				if (ch == '\n' &&
 				    i + 1 < len && msg[i+1] == '\n')
 					in_body = 1;
 			}
-			else if (ch & 0x80) {
+			else if (non_ascii(ch)) {
 				plain_non_ascii = 1;
 				break;
 			}
@@ -690,13 +1012,15 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit
 				offset += add_user_info("Author", fmt,
 							buf + offset,
 							line + 7,
-							relative_date);
+							relative_date,
+							encoding);
 			if (!memcmp(line, "committer ", 10) &&
 			    (fmt == CMIT_FMT_FULL || fmt == CMIT_FMT_FULLER))
 				offset += add_user_info("Commit", fmt,
 							buf + offset,
 							line + 10,
-							relative_date);
+							relative_date,
+							encoding);
 			continue;
 		}
 
@@ -704,6 +1028,8 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit
 			body = 1;
 
 		if (is_empty_line(line, &linelen)) {
+			if (!seen_title)
+				continue;
 			if (!body)
 				continue;
 			if (subject)
@@ -712,11 +1038,13 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit
 				break;
 		}
 
+		seen_title = 1;
 		if (subject) {
 			int slen = strlen(subject);
 			memcpy(buf + offset, subject, slen);
 			offset += slen;
-			offset += add_rfc2047(buf + offset, line, linelen);
+			offset += add_rfc2047(buf + offset, line, linelen,
+					      encoding);
 		}
 		else {
 			memset(buf + offset, ' ', indent);
@@ -727,11 +1055,17 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit
 		if (fmt == CMIT_FMT_ONELINE)
 			break;
 		if (subject && plain_non_ascii) {
-			static const char header[] =
-				"Content-Type: text/plain; charset=UTF-8\n"
+			int sz;
+			char header[512];
+			const char *header_fmt =
+				"Content-Type: text/plain; charset=%s\n"
 				"Content-Transfer-Encoding: 8bit\n";
-			memcpy(buf + offset, header, sizeof(header)-1);
-			offset += sizeof(header)-1;
+			sz = snprintf(header, sizeof(header), header_fmt,
+				      encoding);
+			if (sizeof(header) < sz)
+				die("Encoding name %s too long", encoding);
+			memcpy(buf + offset, header, sz);
+			offset += sz;
 		}
 		if (after_subject) {
 			int slen = strlen(after_subject);
@@ -755,6 +1089,8 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *commit
 	if (fmt == CMIT_FMT_EMAIL && !body)
 		buf[offset++] = '\n';
 	buf[offset] = '\0';
+
+	free(reencoded);
 	return offset;
 }
 
@@ -900,7 +1236,7 @@ void sort_in_topological_order_fn(struct commit_list ** list, int lifo,
 	free(nodes);
 }
 
-/* merge-rebase stuff */
+/* merge-base stuff */
 
 /* bits #0..15 in revision.h */
 #define PARENT1		(1u<<16)
@@ -908,6 +1244,8 @@ void sort_in_topological_order_fn(struct commit_list ** list, int lifo,
 #define STALE		(1u<<18)
 #define RESULT		(1u<<19)
 
+static const unsigned all_flags = (PARENT1 | PARENT2 | STALE | RESULT);
+
 static struct commit *interesting(struct commit_list *list)
 {
 	while (list) {
@@ -972,6 +1310,7 @@ static struct commit_list *merge_bases(struct commit *one, struct commit *two)
 	}
 
 	/* Clean up the result to remove stale ones */
+	free_commit_list(list);
 	list = result; result = NULL;
 	while (list) {
 		struct commit_list *n = list->next;
@@ -987,7 +1326,6 @@ struct commit_list *get_merge_bases(struct commit *one,
 				    struct commit *two,
                                     int cleanup)
 {
-	const unsigned all_flags = (PARENT1 | PARENT2 | STALE | RESULT);
 	struct commit_list *list;
 	struct commit **rslt;
 	struct commit_list *result;