Merge branch 'js/shortlog'

* js/shortlog:
  git-shortlog: make common repository prefix configurable with .mailmap
  git-shortlog: fix common repository prefix abbreviation.
  builtin git-shortlog is broken
  shortlog: fix "-n"
  shortlog: handle email addresses case-insensitively
  shortlog: read mailmap from ./.mailmap again
  shortlog: do not crash on parsing "[PATCH"
  Build in shortlog

Documentation/git-shortlog.txt

@@ -8,6 +8,7 @@ git-shortlog - Summarize 'git log' output
 SYNOPSIS
 --------
 git-log --pretty=short | 'git-shortlog' [-h] [-n] [-s]
+git-shortlog [-n|--number] [-s|--summary] [<committish>...]
 
 DESCRIPTION
 -----------

Makefile

@@ -171,7 +171,7 @@ SCRIPT_SH = \
 
 SCRIPT_PERL = \
 	git-archimport.perl git-cvsimport.perl git-relink.perl \
-	git-shortlog.perl git-rerere.perl \
+	git-rerere.perl \
 	git-cvsserver.perl \
 	git-svnimport.perl git-cvsexportcommit.perl \
 	git-send-email.perl git-svn.perl
@@ -287,6 +287,7 @@ BUILTIN_OBJS = \
 	builtin-rev-parse.o \
 	builtin-rm.o \
 	builtin-runstatus.o \
+	builtin-shortlog.o \
 	builtin-show-branch.o \
 	builtin-stripspace.o \
 	builtin-symbolic-ref.o \

builtin-shortlog.c

+#include "builtin.h"
+#include "cache.h"
+#include "commit.h"
+#include "diff.h"
+#include "path-list.h"
+#include "revision.h"
+#include <string.h>
+
+static const char shortlog_usage[] =
+"git-shortlog [-n] [-s] [<commit-id>... ]";
+
+static char *common_repo_prefix;
+
+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;
+
+	if (l1->nr < l2->nr)
+		return 1;
+	else if (l1->nr == l2->nr)
+		return 0;
+	else
+		return -1;
+}
+
+static struct path_list mailmap = {NULL, 0, 0, 0};
+
+static int read_mailmap(const char *filename)
+{
+	char buffer[1024];
+	FILE *f = fopen(filename, "r");
+
+	if (f == NULL)
+		return 1;
+	while (fgets(buffer, sizeof(buffer), f) != NULL) {
+		char *end_of_name, *left_bracket, *right_bracket;
+		char *name, *email;
+		int i;
+		if (buffer[0] == '#') {
+			static const char abbrev[] = "# repo-abbrev:";
+			int abblen = sizeof(abbrev) - 1;
+			int len = strlen(buffer);
+
+			if (len && buffer[len - 1] == '\n')
+				buffer[--len] = 0;
+			if (!strncmp(buffer, abbrev, abblen)) {
+				char *cp;
+
+				if (common_repo_prefix)
+					free(common_repo_prefix);
+				common_repo_prefix = xmalloc(len);
+
+				for (cp = buffer + abblen; isspace(*cp); cp++)
+					; /* nothing */
+				strcpy(common_repo_prefix, cp);
+			}
+			continue;
+		}
+		if ((left_bracket = strchr(buffer, '<')) == NULL)
+			continue;
+		if ((right_bracket = strchr(left_bracket + 1, '>')) == NULL)
+			continue;
+		if (right_bracket == left_bracket + 1)
+			continue;
+		for (end_of_name = left_bracket; end_of_name != buffer
+				&& isspace(end_of_name[-1]); end_of_name--)
+			/* keep on looking */
+		if (end_of_name == buffer)
+			continue;
+		name = xmalloc(end_of_name - buffer + 1);
+		strlcpy(name, buffer, end_of_name - buffer + 1);
+		email = xmalloc(right_bracket - left_bracket);
+		for (i = 0; i < right_bracket - left_bracket - 1; i++)
+			email[i] = tolower(left_bracket[i + 1]);
+		email[right_bracket - left_bracket - 1] = '\0';
+		path_list_insert(email, &mailmap)->util = name;
+	}
+	fclose(f);
+	return 0;
+}
+
+static int map_email(char *email, char *name, int maxlen)
+{
+	char *p;
+	struct path_list_item *item;
+
+	/* autocomplete common developers */
+	p = strchr(email, '>');
+	if (!p)
+		return 0;
+
+	*p = '\0';
+	/* downcase the email address */
+	for (p = email; *p; p++)
+		*p = tolower(*p);
+	item = path_list_lookup(email, &mailmap);
+	if (item != NULL) {
+		const char *realname = (const char *)item->util;
+		strncpy(name, realname, maxlen);
+		return 1;
+	}
+	return 0;
+}
+
+static void insert_author_oneline(struct path_list *list,
+		const char *author, int authorlen,
+		const char *oneline, int onelinelen)
+{
+	const char *dot3 = common_repo_prefix;
+	char *buffer, *p;
+	struct path_list_item *item;
+	struct path_list *onelines;
+
+	while (authorlen > 0 && isspace(author[authorlen - 1]))
+		authorlen--;
+
+	buffer = xmalloc(authorlen + 1);
+	memcpy(buffer, author, authorlen);
+	buffer[authorlen] = '\0';
+
+	item = path_list_insert(buffer, list);
+	if (item->util == NULL)
+		item->util = xcalloc(1, sizeof(struct path_list));
+	else
+		free(buffer);
+
+	if (!strncmp(oneline, "[PATCH", 6)) {
+		char *eob = strchr(oneline, ']');
+
+		if (eob) {
+			while (isspace(eob[1]) && eob[1] != '\n')
+				eob++;
+			if (eob - oneline < onelinelen) {
+				onelinelen -= eob - oneline;
+				oneline = eob;
+			}
+		}
+	}
+
+	while (onelinelen > 0 && isspace(oneline[0])) {
+		oneline++;
+		onelinelen--;
+	}
+
+	while (onelinelen > 0 && isspace(oneline[onelinelen - 1]))
+		onelinelen--;
+
+	buffer = xmalloc(onelinelen + 1);
+	memcpy(buffer, oneline, onelinelen);
+	buffer[onelinelen] = '\0';
+
+	if (dot3) {
+		int dot3len = strlen(dot3);
+		if (dot3len > 5) {
+			while ((p = strstr(buffer, dot3)) != NULL) {
+				int taillen = strlen(p) - dot3len;
+				memcpy(p, "/.../", 5);
+				memmove(p + 5, p + dot3len, taillen + 1);
+			}
+		}
+	}
+
+	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;
+}
+
+static void read_from_stdin(struct path_list *list)
+{
+	char buffer[1024];
+
+	while (fgets(buffer, sizeof(buffer), stdin) != NULL) {
+		char *bob;
+		if ((buffer[0] == 'A' || buffer[0] == 'a') &&
+				!strncmp(buffer + 1, "uthor: ", 7) &&
+				(bob = strchr(buffer + 7, '<')) != NULL) {
+			char buffer2[1024], offset = 0;
+
+			if (map_email(bob + 1, buffer, sizeof(buffer)))
+				bob = buffer + strlen(buffer);
+			else {
+				offset = 8;
+				while (isspace(bob[-1]))
+					bob--;
+			}
+
+			while (fgets(buffer2, sizeof(buffer2), stdin) &&
+					buffer2[0] != '\n')
+				; /* chomp input */
+			if (fgets(buffer2, sizeof(buffer2), stdin))
+				insert_author_oneline(list,
+						buffer + offset,
+						bob - buffer - offset,
+						buffer2, strlen(buffer2));
+		}
+	}
+}
+
+static void get_from_rev(struct rev_info *rev, struct path_list *list)
+{
+	char scratch[1024];
+	struct commit *commit;
+
+	prepare_revision_walk(rev);
+	while ((commit = get_revision(rev)) != NULL) {
+		char *author = NULL, *oneline, *buffer;
+		int authorlen = authorlen, onelinelen;
+
+		/* get author and oneline */
+		for (buffer = commit->buffer; buffer && *buffer != '\0' &&
+				*buffer != '\n'; ) {
+			char *eol = strchr(buffer, '\n');
+
+			if (eol == NULL)
+				eol = buffer + strlen(buffer);
+			else
+				eol++;
+
+			if (!strncmp(buffer, "author ", 7)) {
+				char *bracket = strchr(buffer, '<');
+
+				if (bracket == NULL || bracket > eol)
+					die("Invalid commit buffer: %s",
+					    sha1_to_hex(commit->object.sha1));
+
+				if (map_email(bracket + 1, scratch,
+							sizeof(scratch))) {
+					author = scratch;
+					authorlen = strlen(scratch);
+				} else {
+					while (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));
+
+		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;
+		}
+
+		insert_author_oneline(list,
+				author, authorlen, oneline, onelinelen);
+	}
+
+}
+
+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;
+
+	/* 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 (!strcmp(argv[1], "-h") || !strcmp(argv[1], "--help"))
+			usage(shortlog_usage);
+		else
+			break;
+		argv++;
+		argc--;
+	}
+	init_revisions(&rev, prefix);
+	argc = setup_revisions(argc, argv, &rev, NULL);
+	if (argc > 1)
+		die ("unrecognized argument: %s", argv[1]);
+
+	if (!access(".mailmap", R_OK))
+		read_mailmap(".mailmap");
+
+	if (rev.pending.nr == 1)
+		die ("Need a range!");
+	else if (rev.pending.nr == 0)
+		read_from_stdin(&list);
+	else
+		get_from_rev(&rev, &list);
+
+	if (sort_by_number)
+		qsort(list.items, list.nr, sizeof(struct path_list_item),
+			compare_by_number);
+
+	for (i = 0; i < list.nr; i++) {
+		struct path_list *onelines = list.items[i].util;
+
+		if (summary) {
+			printf("%s: %d\n", list.items[i].path, onelines->nr);
+		} else {
+			printf("%s (%d):\n", list.items[i].path, onelines->nr);
+			for (j = onelines->nr - 1; j >= 0; j--)
+				printf("      %s\n", onelines->items[j].path);
+			printf("\n");
+		}
+
+		onelines->strdup_paths = 1;
+		path_list_clear(onelines, 1);
+		free(onelines);
+		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;
+}
+

builtin.h

@@ -55,6 +55,7 @@ extern int cmd_rev_list(int argc, const char **argv, const char *prefix);
 extern int cmd_rev_parse(int argc, const char **argv, const char *prefix);
 extern int cmd_rm(int argc, const char **argv, const char *prefix);
 extern int cmd_runstatus(int argc, const char **argv, const char *prefix);
+extern int cmd_shortlog(int argc, const char **argv, const char *prefix);
 extern int cmd_show(int argc, const char **argv, const char *prefix);
 extern int cmd_show_branch(int argc, const char **argv, const char *prefix);
 extern int cmd_stripspace(int argc, const char **argv, const char *prefix);

git-shortlog.perl → contrib/mailmap.linux

-#!/usr/bin/perl -w
-
-use strict;
-use Getopt::Std;
-use File::Basename qw(basename dirname);
-
-our ($opt_h, $opt_n, $opt_s);
-getopts('hns');
-
-$opt_h && usage();
-
-sub usage {
-	print STDERR "Usage: ${\basename $0} [-h] [-n] [-s] < <log_data>\n";
-        exit(1);
-}
-
-my (%mailmap);
-my (%email);
-my (%map);
-my $pstate = 1;
-my $n_records = 0;
-my $n_output = 0;
-
-sub shortlog_entry($$) {
-	my ($name, $desc) = @_;
-	my $key = $name;
-
-	$desc =~ s#/pub/scm/linux/kernel/git/#/.../#g;
-	$desc =~ s#\[PATCH\] ##g;
-
-	# store description in array, in email->{desc list} map
-	if (exists $map{$key}) {
-		# grab ref
-		my $obj = $map{$key};
-
-		# add desc to array
-		push(@$obj, $desc);
-	} else {
-		# create new array, containing 1 item
-		my @arr = ($desc);
-
-		# store ref to array
-		$map{$key} = \@arr;
-	}
-}
-
-# sort comparison function
-sub by_name($$) {
-	my ($a, $b) = @_;
-
-	uc($a) cmp uc($b);
-}
-sub by_nbentries($$) {
-	my ($a, $b) = @_;
-	my $a_entries = $map{$a};
-	my $b_entries = $map{$b};
-
-	@$b_entries - @$a_entries || by_name $a, $b;
-}
-
-my $sort_method = $opt_n ? \&by_nbentries : \&by_name;
-
-sub summary_output {
-	my ($obj, $num, $key);
-
-	foreach $key (sort $sort_method keys %map) {
-		$obj = $map{$key};
-		$num = @$obj;
-		printf "%s: %u\n", $key, $num;
-		$n_output += $num;
-	}
-}
-
-sub shortlog_output {
-	my ($obj, $num, $key, $desc);
-
-	foreach $key (sort $sort_method keys %map) {
-		$obj = $map{$key};
-		$num = @$obj;
-
-		# output author
-		printf "%s (%u):\n", $key, $num;
-
-		# output author's 1-line summaries
-		foreach $desc (reverse @$obj) {
-			print "  $desc\n";
-			$n_output++;
-		}
-
-		# blank line separating author from next author
-		print "\n";
-	}
-}
-
-sub changelog_input {
-	my ($author, $desc);
-
-	while (<>) {
-		# get author and email
-		if ($pstate == 1) {
-			my ($email);
-
-			next unless /^[Aa]uthor:?\s*(.*?)\s*<(.*)>/;
-
-			$n_records++;
-
-			$author = $1;
-			$email = $2;
-			$desc = undef;
-
-			# cset author fixups
-			if (exists $mailmap{$email}) {
-				$author = $mailmap{$email};
-			} elsif (exists $mailmap{$author}) {
-				$author = $mailmap{$author};
-			} elsif (!$author) {
-				$author = $email;
-			}
-			$email{$author}{$email}++;
-			$pstate++;
-		}
-
-		# skip to blank line
-		elsif ($pstate == 2) {
-			next unless /^\s*$/;
-			$pstate++;
-		}
-
-		# skip to non-blank line
-		elsif ($pstate == 3) {
-			next unless /^\s*?(.*)/;
-
-			# skip lines that are obviously not
-			# a 1-line cset description
-			next if /^\s*From: /;
-
-			chomp;
-			$desc = $1;
-
-			&shortlog_entry($author, $desc);
-
-			$pstate = 1;
-		}
-	
-		else {
-			die "invalid parse state $pstate";
-		}
-	}
-}
-
-sub read_mailmap {
-	my ($fh, $mailmap) = @_;
-	while (<$fh>) {
-		chomp;
-		if (/^([^#].*?)\s*<(.*)>/) {
-			$mailmap->{$2} = $1;
-		}
-	}
-}
-
-sub setup_mailmap {
-	read_mailmap(\*DATA, \%mailmap);
-	if (-f '.mailmap') {
-		my $fh = undef;
-		open $fh, '<', '.mailmap';
-		read_mailmap($fh, \%mailmap);
-		close $fh;
-	}
-}
-
-sub finalize {
-	#print "\n$n_records records parsed.\n";
-
-	if ($n_records != $n_output) {
-		die "parse error: input records != output records\n";
-	}
-	if (0) {
-		for my $author (sort keys %email) {
-			my $e = $email{$author};
-			for my $email (sort keys %$e) {
-				print STDERR "$author <$email>\n";
-			}
-		}
-	}
-}
-
-&setup_mailmap;
-&changelog_input;
-$opt_s ? &summary_output : &shortlog_output;
-&finalize;
-exit(0);
-
-
-__DATA__
 #
 # Even with git, we don't always have name translations.
 # So have an email->real name table to translate the
 # (hopefully few) missing names
 #
+# repo-abbrev: /pub/scm/linux/kernel/git/
+#
 Adrian Bunk <bunk@stusta.de>
 Andreas Herrmann <aherrman@de.ibm.com>
 Andrew Morton <akpm@osdl.org>

git.c

@@ -260,6 +260,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp)
 		{ "rev-parse", cmd_rev_parse, RUN_SETUP },
 		{ "rm", cmd_rm, RUN_SETUP },
 		{ "runstatus", cmd_runstatus, RUN_SETUP },
+		{ "shortlog", cmd_shortlog, RUN_SETUP },
 		{ "show-branch", cmd_show_branch, RUN_SETUP },
 		{ "show", cmd_show, RUN_SETUP | USE_PAGER },
 		{ "stripspace", cmd_stripspace },