1 files changed, 234 insertions, 230 deletions

diff --git a/builtin-shortlog.c b/builtin-shortlog.c
index 16af6199ab..b28091b445 100644
--- a/builtin-shortlog.c
+++ b/builtin-shortlog.c
@@ -2,20 +2,24 @@
 #include "cache.h"
 #include "commit.h"
 #include "diff.h"
-#include "path-list.h"
+#include "string-list.h"
 #include "revision.h"
 #include "utf8.h"
 #include "mailmap.h"
+#include "shortlog.h"
+#include "parse-options.h"
 
-static const char shortlog_usage[] =
-"git-shortlog [-n] [-s] [<commit-id>... ]";
-
-static char *common_repo_prefix;
+static char const * const shortlog_usage[] = {
+	"git shortlog [-n] [-s] [-e] [-w] [rev-opts] [--] [<commit-id>... ]",
+	"",
+	"[rev-opts] are documented in git-rev-list(1)",
+	NULL
+};
 
 static int compare_by_number(const void *a1, const void *a2)
 {
-	const struct path_list_item *i1 = a1, *i2 = a2;
-	const struct path_list *l1 = i1->util, *l2 = i2->util;
+	const struct string_list_item *i1 = a1, *i2 = a2;
+	const struct string_list *l1 = i1->util, *l2 = i2->util;
 
 	if (l1->nr < l2->nr)
 		return 1;
@@ -25,54 +29,80 @@ static int compare_by_number(const void *a1, const void *a2)
 		return -1;
 }
 
-static struct path_list mailmap = {NULL, 0, 0, 0};
+const char *format_subject(struct strbuf *sb, const char *msg,
+			   const char *line_separator);
 
-static void insert_author_oneline(struct path_list *list,
-		const char *author, int authorlen,
-		const char *oneline, int onelinelen)
+static void insert_one_record(struct shortlog *log,
+			      const char *author,
+			      const char *oneline)
 {
-	const char *dot3 = common_repo_prefix;
+	const char *dot3 = log->common_repo_prefix;
 	char *buffer, *p;
-	struct path_list_item *item;
-	struct path_list *onelines;
-
-	while (authorlen > 0 && isspace(author[authorlen - 1]))
-		authorlen--;
+	struct string_list_item *item;
+	char namebuf[1024];
+	char emailbuf[1024];
+	size_t len;
+	const char *eol;
+	const char *boemail, *eoemail;
+	struct strbuf subject = STRBUF_INIT;
+
+	boemail = strchr(author, '<');
+	if (!boemail)
+		return;
+	eoemail = strchr(boemail, '>');
+	if (!eoemail)
+		return;
+
+	/* copy author name to namebuf, to support matching on both name and email */
+	memcpy(namebuf, author, boemail - author);
+	len = boemail - author;
+	while(len > 0 && isspace(namebuf[len-1]))
+		len--;
+	namebuf[len] = 0;
+
+	/* copy email name to emailbuf, to allow email replacement as well */
+	memcpy(emailbuf, boemail+1, eoemail - boemail);
+	emailbuf[eoemail - boemail - 1] = 0;
+
+	if (!map_user(&log->mailmap, emailbuf, sizeof(emailbuf), namebuf, sizeof(namebuf))) {
+		while (author < boemail && isspace(*author))
+			author++;
+		for (len = 0;
+		     len < sizeof(namebuf) - 1 && author + len < boemail;
+		     len++)
+			namebuf[len] = author[len];
+		while (0 < len && isspace(namebuf[len-1]))
+			len--;
+		namebuf[len] = '\0';
+	}
+	else
+		len = strlen(namebuf);
 
-	buffer = xmalloc(authorlen + 1);
-	memcpy(buffer, author, authorlen);
-	buffer[authorlen] = '\0';
+	if (log->email) {
+		size_t room = sizeof(namebuf) - len - 1;
+		int maillen = strlen(emailbuf);
+		snprintf(namebuf + len, room, " <%.*s>", maillen, emailbuf);
+	}
 
-	item = path_list_insert(buffer, list);
+	item = string_list_insert(namebuf, &log->list);
 	if (item->util == NULL)
-		item->util = xcalloc(1, sizeof(struct path_list));
-	else
-		free(buffer);
+		item->util = xcalloc(1, sizeof(struct string_list));
 
+	/* Skip any leading whitespace, including any blank lines. */
+	while (*oneline && isspace(*oneline))
+		oneline++;
+	eol = strchr(oneline, '\n');
+	if (!eol)
+		eol = oneline + strlen(oneline);
 	if (!prefixcmp(oneline, "[PATCH")) {
 		char *eob = strchr(oneline, ']');
-
-		if (eob) {
-			while (isspace(eob[1]) && eob[1] != '\n')
-				eob++;
-			if (eob - oneline < onelinelen) {
-				onelinelen -= eob - oneline;
-				oneline = eob;
-			}
-		}
+		if (eob && (!eol || eob < eol))
+			oneline = eob + 1;
 	}
-
-	while (onelinelen > 0 && isspace(oneline[0])) {
+	while (*oneline && isspace(*oneline) && *oneline != '\n')
 		oneline++;
-		onelinelen--;
-	}
-
-	while (onelinelen > 0 && isspace(oneline[onelinelen - 1]))
-		onelinelen--;
-
-	buffer = xmalloc(onelinelen + 1);
-	memcpy(buffer, oneline, onelinelen);
-	buffer[onelinelen] = '\0';
+	format_subject(&subject, oneline, " ");
+	buffer = strbuf_detach(&subject, NULL);
 
 	if (dot3) {
 		int dot3len = strlen(dot3);
@@ -85,137 +115,84 @@ static void insert_author_oneline(struct path_list *list,
 		}
 	}
 
-	onelines = item->util;
-	if (onelines->nr >= onelines->alloc) {
-		onelines->alloc = alloc_nr(onelines->nr);
-		onelines->items = xrealloc(onelines->items,
-				onelines->alloc
-				* sizeof(struct path_list_item));
-	}
-
-	onelines->items[onelines->nr].util = NULL;
-	onelines->items[onelines->nr++].path = buffer;
+	string_list_append(buffer, item->util);
 }
 
-static void read_from_stdin(struct path_list *list)
+static void read_from_stdin(struct shortlog *log)
 {
-	char buffer[1024];
-
-	while (fgets(buffer, sizeof(buffer), stdin) != NULL) {
-		char *bob;
-		if ((buffer[0] == 'A' || buffer[0] == 'a') &&
-				!prefixcmp(buffer + 1, "uthor: ") &&
-				(bob = strchr(buffer + 7, '<')) != NULL) {
-			char buffer2[1024], offset = 0;
-
-			if (map_email(&mailmap, bob + 1, buffer, sizeof(buffer)))
-				bob = buffer + strlen(buffer);
-			else {
-				offset = 8;
-				while (buffer + offset < bob &&
-				       isspace(bob[-1]))
-					bob--;
-			}
-
-			while (fgets(buffer2, sizeof(buffer2), stdin) &&
-					buffer2[0] != '\n')
-				; /* chomp input */
-			if (fgets(buffer2, sizeof(buffer2), stdin)) {
-				int l2 = strlen(buffer2);
-				int i;
-				for (i = 0; i < l2; i++)
-					if (!isspace(buffer2[i]))
-						break;
-				insert_author_oneline(list,
-						buffer + offset,
-						bob - buffer - offset,
-						buffer2 + i, l2 - i);
-			}
-		}
+	char author[1024], oneline[1024];
+
+	while (fgets(author, sizeof(author), stdin) != NULL) {
+		if (!(author[0] == 'A' || author[0] == 'a') ||
+		    prefixcmp(author + 1, "uthor: "))
+			continue;
+		while (fgets(oneline, sizeof(oneline), stdin) &&
+		       oneline[0] != '\n')
+			; /* discard headers */
+		while (fgets(oneline, sizeof(oneline), stdin) &&
+		       oneline[0] == '\n')
+			; /* discard blanks */
+		insert_one_record(log, author + 8, oneline);
 	}
 }
 
-static void get_from_rev(struct rev_info *rev, struct path_list *list)
+void shortlog_add_commit(struct shortlog *log, struct commit *commit)
 {
-	char scratch[1024];
-	struct commit *commit;
+	const char *author = NULL, *buffer;
 
-	prepare_revision_walk(rev);
-	while ((commit = get_revision(rev)) != NULL) {
-		const char *author = NULL, *oneline, *buffer;
-		int authorlen = authorlen, onelinelen;
-
-		/* get author and oneline */
-		for (buffer = commit->buffer; buffer && *buffer != '\0' &&
-				*buffer != '\n'; ) {
-			const char *eol = strchr(buffer, '\n');
-
-			if (eol == NULL)
-				eol = buffer + strlen(buffer);
-			else
-				eol++;
-
-			if (!prefixcmp(buffer, "author ")) {
-				char *bracket = strchr(buffer, '<');
-
-				if (bracket == NULL || bracket > eol)
-					die("Invalid commit buffer: %s",
-					    sha1_to_hex(commit->object.sha1));
-
-				if (map_email(&mailmap, bracket + 1, scratch,
-							sizeof(scratch))) {
-					author = scratch;
-					authorlen = strlen(scratch);
-				} else {
-					if (bracket[-1] == ' ')
-						bracket--;
-
-					author = buffer + 7;
-					authorlen = bracket - buffer - 7;
-				}
-			}
-			buffer = eol;
-		}
-
-		if (author == NULL)
-			die ("Missing author: %s",
-					sha1_to_hex(commit->object.sha1));
+	buffer = commit->buffer;
+	while (*buffer && *buffer != '\n') {
+		const char *eol = strchr(buffer, '\n');
 
-		if (buffer == NULL || *buffer == '\0') {
-			oneline = "<none>";
-			onelinelen = sizeof(oneline) + 1;
-		} else {
-			char *eol;
-
-			oneline = buffer + 1;
-			eol = strchr(oneline, '\n');
-			if (eol == NULL)
-				onelinelen = strlen(oneline);
-			else
-				onelinelen = eol - oneline;
-		}
+		if (eol == NULL)
+			eol = buffer + strlen(buffer);
+		else
+			eol++;
 
-		insert_author_oneline(list,
-				author, authorlen, oneline, onelinelen);
+		if (!prefixcmp(buffer, "author "))
+			author = buffer + 7;
+		buffer = eol;
 	}
+	if (!author)
+		die("Missing author: %s",
+		    sha1_to_hex(commit->object.sha1));
+	if (log->user_format) {
+		struct strbuf buf = STRBUF_INIT;
+
+		pretty_print_commit(CMIT_FMT_USERFORMAT, commit, &buf,
+			DEFAULT_ABBREV, "", "", DATE_NORMAL, 0);
+		insert_one_record(log, author, buf.buf);
+		strbuf_release(&buf);
+		return;
+	}
+	if (*buffer)
+		buffer++;
+	insert_one_record(log, author, !*buffer ? "<none>" : buffer);
+}
 
+static void get_from_rev(struct rev_info *rev, struct shortlog *log)
+{
+	struct commit *commit;
+
+	if (prepare_revision_walk(rev))
+		die("revision walk setup failed");
+	while ((commit = get_revision(rev)) != NULL)
+		shortlog_add_commit(log, commit);
 }
 
-static int parse_uint(char const **arg, int comma)
+static int parse_uint(char const **arg, int comma, int defval)
 {
 	unsigned long ul;
 	int ret;
 	char *endp;
 
 	ul = strtoul(*arg, &endp, 10);
-	if (endp != *arg && *endp && *endp != comma)
+	if (*endp && *endp != comma)
 		return -1;
-	ret = (int) ul;
-	if (ret != ul)
+	if (ul > INT_MAX)
 		return -1;
-	*arg = endp;
-	if (**arg)
-		(*arg)++;
+	ret = *arg == endp ? defval : (int)ul;
+	*arg = *endp ? endp + 1 : endp;
 	return ret;
 }
 
@@ -224,92 +201,122 @@ static const char wrap_arg_usage[] = "-w[<width>[,<indent1>[,<indent2>]]]";
 #define DEFAULT_INDENT1 6
 #define DEFAULT_INDENT2 9
 
-static void parse_wrap_args(const char *arg, int *in1, int *in2, int *wrap)
+static int parse_wrap_args(const struct option *opt, const char *arg, int unset)
+{
+	struct shortlog *log = opt->value;
+
+	log->wrap_lines = !unset;
+	if (unset)
+		return 0;
+	if (!arg) {
+		log->wrap = DEFAULT_WRAPLEN;
+		log->in1 = DEFAULT_INDENT1;
+		log->in2 = DEFAULT_INDENT2;
+		return 0;
+	}
+
+	log->wrap = parse_uint(&arg, ',', DEFAULT_WRAPLEN);
+	log->in1 = parse_uint(&arg, ',', DEFAULT_INDENT1);
+	log->in2 = parse_uint(&arg, '\0', DEFAULT_INDENT2);
+	if (log->wrap < 0 || log->in1 < 0 || log->in2 < 0)
+		return error(wrap_arg_usage);
+	if (log->wrap &&
+	    ((log->in1 && log->wrap <= log->in1) ||
+	     (log->in2 && log->wrap <= log->in2)))
+		return error(wrap_arg_usage);
+	return 0;
+}
+
+void shortlog_init(struct shortlog *log)
 {
-	arg += 2; /* skip -w */
-
-	*wrap = parse_uint(&arg, ',');
-	if (*wrap < 0)
-		die(wrap_arg_usage);
-	*in1 = parse_uint(&arg, ',');
-	if (*in1 < 0)
-		die(wrap_arg_usage);
-	*in2 = parse_uint(&arg, '\0');
-	if (*in2 < 0)
-		die(wrap_arg_usage);
-
-	if (!*wrap)
-		*wrap = DEFAULT_WRAPLEN;
-	if (!*in1)
-		*in1 = DEFAULT_INDENT1;
-	if (!*in2)
-		*in2 = DEFAULT_INDENT2;
-	if (*wrap &&
-	    ((*in1 && *wrap <= *in1) ||
-	     (*in2 && *wrap <= *in2)))
-		die(wrap_arg_usage);
+	memset(log, 0, sizeof(*log));
+
+	read_mailmap(&log->mailmap, &log->common_repo_prefix);
+
+	log->list.strdup_strings = 1;
+	log->wrap = DEFAULT_WRAPLEN;
+	log->in1 = DEFAULT_INDENT1;
+	log->in2 = DEFAULT_INDENT2;
 }
 
 int cmd_shortlog(int argc, const char **argv, const char *prefix)
 {
-	struct rev_info rev;
-	struct path_list list = { NULL, 0, 0, 1 };
-	int i, j, sort_by_number = 0, summary = 0;
-	int wrap_lines = 0;
-	int wrap = DEFAULT_WRAPLEN;
-	int in1 = DEFAULT_INDENT1;
-	int in2 = DEFAULT_INDENT2;
-
-	/* since -n is a shadowed rev argument, parse our args first */
-	while (argc > 1) {
-		if (!strcmp(argv[1], "-n") || !strcmp(argv[1], "--numbered"))
-			sort_by_number = 1;
-		else if (!strcmp(argv[1], "-s") ||
-				!strcmp(argv[1], "--summary"))
-			summary = 1;
-		else if (!prefixcmp(argv[1], "-w")) {
-			wrap_lines = 1;
-			parse_wrap_args(argv[1], &in1, &in2, &wrap);
+	static struct shortlog log;
+	static struct rev_info rev;
+	int nongit;
+
+	static const struct option options[] = {
+		OPT_BOOLEAN('n', "numbered", &log.sort_by_number,
+			    "sort output according to the number of commits per author"),
+		OPT_BOOLEAN('s', "summary", &log.summary,
+			    "Suppress commit descriptions, only provides commit count"),
+		OPT_BOOLEAN('e', "email", &log.email,
+			    "Show the email address of each author"),
+		{ OPTION_CALLBACK, 'w', NULL, &log, "w[,i1[,i2]]",
+			"Linewrap output", PARSE_OPT_OPTARG, &parse_wrap_args },
+		OPT_END(),
+	};
+
+	struct parse_opt_ctx_t ctx;
+
+	prefix = setup_git_directory_gently(&nongit);
+	git_config(git_default_config, NULL);
+	shortlog_init(&log);
+	init_revisions(&rev, prefix);
+	parse_options_start(&ctx, argc, argv, PARSE_OPT_KEEP_DASHDASH |
+			    PARSE_OPT_KEEP_ARGV0);
+
+	for (;;) {
+		switch (parse_options_step(&ctx, options, shortlog_usage)) {
+		case PARSE_OPT_HELP:
+			exit(129);
+		case PARSE_OPT_DONE:
+			goto parse_done;
 		}
-		else if (!strcmp(argv[1], "-h") || !strcmp(argv[1], "--help"))
-			usage(shortlog_usage);
-		else
-			break;
-		argv++;
-		argc--;
+		parse_revision_opt(&rev, &ctx, options, shortlog_usage);
+	}
+parse_done:
+	argc = parse_options_end(&ctx);
+
+	if (setup_revisions(argc, argv, &rev, NULL) != 1) {
+		error("unrecognized argument: %s", argv[1]);
+		usage_with_options(shortlog_usage, options);
 	}
-	init_revisions(&rev, prefix);
-	argc = setup_revisions(argc, argv, &rev, NULL);
-	if (argc > 1)
-		die ("unrecognized argument: %s", argv[1]);
 
-	read_mailmap(&mailmap, ".mailmap", &common_repo_prefix);
+	log.user_format = rev.commit_format == CMIT_FMT_USERFORMAT;
 
+	/* assume HEAD if from a tty */
+	if (!nongit && !rev.pending.nr && isatty(0))
+		add_head_to_pending(&rev);
 	if (rev.pending.nr == 0) {
-		if (isatty(0))
-			fprintf(stderr, "(reading log to summarize from standard input)\n");
-		read_from_stdin(&list);
+		read_from_stdin(&log);
 	}
 	else
-		get_from_rev(&rev, &list);
+		get_from_rev(&rev, &log);
 
-	if (sort_by_number)
-		qsort(list.items, list.nr, sizeof(struct path_list_item),
-			compare_by_number);
+	shortlog_output(&log);
+	return 0;
+}
 
-	for (i = 0; i < list.nr; i++) {
-		struct path_list *onelines = list.items[i].util;
+void shortlog_output(struct shortlog *log)
+{
+	int i, j;
+	if (log->sort_by_number)
+		qsort(log->list.items, log->list.nr, sizeof(struct string_list_item),
+			compare_by_number);
+	for (i = 0; i < log->list.nr; i++) {
+		struct string_list *onelines = log->list.items[i].util;
 
-		if (summary) {
-			printf("%s: %d\n", list.items[i].path, onelines->nr);
+		if (log->summary) {
+			printf("%6d\t%s\n", onelines->nr, log->list.items[i].string);
 		} else {
-			printf("%s (%d):\n", list.items[i].path, onelines->nr);
+			printf("%s (%d):\n", log->list.items[i].string, onelines->nr);
 			for (j = onelines->nr - 1; j >= 0; j--) {
-				const char *msg = onelines->items[j].path;
+				const char *msg = onelines->items[j].string;
 
-				if (wrap_lines) {
-					int col = print_wrapped_text(msg, in1, in2, wrap);
-					if (col != wrap)
+				if (log->wrap_lines) {
+					int col = print_wrapped_text(msg, log->in1, log->in2, log->wrap);
+					if (col != log->wrap)
 						putchar('\n');
 				}
 				else
@@ -318,16 +325,13 @@ int cmd_shortlog(int argc, const char **argv, const char *prefix)
 			putchar('\n');
 		}
 
-		onelines->strdup_paths = 1;
-		path_list_clear(onelines, 1);
+		onelines->strdup_strings = 1;
+		string_list_clear(onelines, 0);
 		free(onelines);
-		list.items[i].util = NULL;
+		log->list.items[i].util = NULL;
 	}
 
-	list.strdup_paths = 1;
-	path_list_clear(&list, 1);
-	mailmap.strdup_paths = 1;
-	path_list_clear(&mailmap, 1);
-
-	return 0;
+	log->list.strdup_strings = 1;
+	string_list_clear(&log->list, 1);
+	clear_mailmap(&log->mailmap);
 }