Merge branch 'lt/apply' into next

* lt/apply:
  apply --whitespace fixes and enhancements.
  The war on trailing whitespace
  svnimport: Convert the svn:ignore property
  svnimport: Convert executable flag
  svnimport: Mention -r in usage summary
  Make git diff-generation use a simpler spawn-like interface

4 files changed, 232 insertions, 80 deletions

diff --git a/Documentation/git-svnimport.txt b/Documentation/git-svnimport.txt
index 5c543d5d1..c95ff84f6 100644
--- a/Documentation/git-svnimport.txt
+++ b/Documentation/git-svnimport.txt
@@ -10,10 +10,10 @@ git-svnimport - Import a SVN repository into git
 SYNOPSIS
 --------
 'git-svnimport' [ -o <branch-for-HEAD> ] [ -h ] [ -v ] [ -d | -D ]
-			[ -C <GIT_repository> ] [ -i ] [ -u ] [-l limit_rev]
-			[ -b branch_subdir ] [ -T trunk_subdir ] [ -t tag_subdir ]
-			[ -s start_chg ] [ -m ] [ -M regex ]
-			<SVN_repository_URL> [ <path> ]
+		[ -C <GIT_repository> ] [ -i ] [ -u ] [-l limit_rev]
+		[ -b branch_subdir ] [ -T trunk_subdir ] [ -t tag_subdir ]
+		[ -s start_chg ] [ -m ] [ -r ] [ -M regex ]
+		[ -I <ignorefile_name> ] <SVN_repository_URL> [ <path> ]
 
 
 DESCRIPTION
@@ -65,6 +65,12 @@ When importing incrementally, you might need to edit the .git/svn2git file.
 	Prepend 'rX: ' to commit messages, where X is the imported
 	subversion revision.
 
+-I <ignorefile_name>::
+	Import the svn:ignore directory property to files with this
+	name in each directory. (The Subversion and GIT ignore
+	syntaxes are similar enough that using the Subversion patterns
+	directly with "-I .gitignore" will almost always just work.)
+
 -m::
 	Attempt to detect merges based on the commit message. This option
 	will enable default regexes that try to capture the name source
diff --git a/apply.c b/apply.c
index 244718ca1..7dbbeb47a 100644
--- a/apply.c
+++ b/apply.c
@@ -34,6 +34,15 @@ static int line_termination = '\n';
 static const char apply_usage[] =
 "git-apply [--stat] [--numstat] [--summary] [--check] [--index] [--apply] [--no-add] [--index-info] [--allow-binary-replacement] [-z] [-pNUM] <patch>...";
 
+static enum whitespace_eol {
+	nowarn,
+	warn_on_whitespace,
+	error_on_whitespace,
+	strip_and_apply,
+} new_whitespace = nowarn;
+static int whitespace_error = 0;
+static const char *patch_input_file = NULL;
+
 /*
  * For "diff-stat" like behaviour, we keep track of the biggest change
  * we've seen, and the longest filename. That allows us to do simple
@@ -815,6 +824,20 @@ static int parse_fragment(char *line, unsigned long size, struct patch *patch, s
 			oldlines--;
 			break;
 		case '+':
+			/*
+			 * We know len is at least two, since we have a '+' and
+			 * we checked that the last character was a '\n' above.
+			 * That is, an addition of an empty line would check
+			 * the '+' here.  Sneaky...
+			 */
+			if ((new_whitespace != nowarn) &&
+			    isspace(line[len-2])) {
+				fprintf(stderr, "Added whitespace\n");
+				fprintf(stderr, "%s:%d:%.*s\n",
+					patch_input_file,
+					linenr, len-2, line+1);
+				whitespace_error = 1;
+			}
 			added++;
 			newlines--;
 			break;
@@ -1092,6 +1115,27 @@ struct buffer_desc {
 	unsigned long alloc;
 };
 
+static int apply_line(char *output, const char *patch, int plen)
+{
+	/* plen is number of bytes to be copied from patch,
+	 * starting at patch+1 (patch[0] is '+').  Typically
+	 * patch[plen] is '\n'.
+	 */
+	int add_nl_to_tail = 0;
+	if ((new_whitespace == strip_and_apply) &&
+	    1 < plen && isspace(patch[plen-1])) {
+		if (patch[plen] == '\n')
+			add_nl_to_tail = 1;
+		plen--;
+		while (0 < plen && isspace(patch[plen]))
+			plen--;
+	}
+	memcpy(output, patch + 1, plen);
+	if (add_nl_to_tail)
+		output[plen++] = '\n';
+	return plen;
+}
+
 static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag)
 {
 	char *buf = desc->buffer;
@@ -1127,10 +1171,9 @@ static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag)
 				break;
 		/* Fall-through for ' ' */
 		case '+':
-			if (*patch != '+' || !no_add) {
-				memcpy(new + newsize, patch + 1, plen);
-				newsize += plen;
-			}
+			if (*patch != '+' || !no_add)
+				newsize += apply_line(new + newsize, patch,
+						      plen);
 			break;
 		case '@': case '\\':
 			/* Ignore it, we already handled it */
@@ -1699,7 +1742,7 @@ static int use_patch(struct patch *p)
 	return 1;
 }
 
-static int apply_patch(int fd)
+static int apply_patch(int fd, const char *filename)
 {
 	int newfd;
 	unsigned long offset, size;
@@ -1707,6 +1750,7 @@ static int apply_patch(int fd)
 	struct patch *list = NULL, **listp = &list;
 	int skipped_patch = 0;
 
+	patch_input_file = filename;
 	if (!buffer)
 		return -1;
 	offset = 0;
@@ -1733,6 +1777,9 @@ static int apply_patch(int fd)
 	}
 
 	newfd = -1;
+	if (whitespace_error && (new_whitespace == error_on_whitespace))
+		apply = 0;
+
 	write_index = check_index && apply;
 	if (write_index)
 		newfd = hold_index_file_for_update(&cache_file, get_index_file());
@@ -1779,7 +1826,7 @@ int main(int argc, char **argv)
 		int fd;
 
 		if (!strcmp(arg, "-")) {
-			apply_patch(0);
+			apply_patch(0, "<stdin>");
 			read_stdin = 0;
 			continue;
 		}
@@ -1839,6 +1886,21 @@ int main(int argc, char **argv)
 			line_termination = 0;
 			continue;
 		}
+		if (!strncmp(arg, "--whitespace=", 13)) {
+			if (!strcmp(arg+13, "warn")) {
+				new_whitespace = warn_on_whitespace;
+				continue;
+			}
+			if (!strcmp(arg+13, "error")) {
+				new_whitespace = error_on_whitespace;
+				continue;
+			}
+			if (!strcmp(arg+13, "strip")) {
+				new_whitespace = strip_and_apply;
+				continue;
+			}
+			die("unrecognixed whitespace option '%s'", arg+13);
+		}
 
 		if (check_index && prefix_length < 0) {
 			prefix = setup_git_directory();
@@ -1852,10 +1914,12 @@ int main(int argc, char **argv)
 		if (fd < 0)
 			usage(apply_usage);
 		read_stdin = 0;
-		apply_patch(fd);
+		apply_patch(fd, arg);
 		close(fd);
 	}
 	if (read_stdin)
-		apply_patch(0);
+		apply_patch(0, "<stdin>");
+	if (whitespace_error && new_whitespace == error_on_whitespace)
+		return 1;
 	return 0;
 }
diff --git a/diff.c b/diff.c
index 804c08c2c..c0548eed9 100644
--- a/diff.c
+++ b/diff.c
@@ -178,11 +178,12 @@ static void emit_rewrite_diff(const char *name_a,
 		copy_file('+', temp[1].name);
 }
 
-static void builtin_diff(const char *name_a,
+static const char *builtin_diff(const char *name_a,
 			 const char *name_b,
 			 struct diff_tempfile *temp,
 			 const char *xfrm_msg,
-			 int complete_rewrite)
+			 int complete_rewrite,
+			 const char **args)
 {
 	int i, next_at, cmd_size;
 	const char *const diff_cmd = "diff -L%s -L%s";
@@ -242,19 +243,24 @@ static void builtin_diff(const char *name_a,
 		}
 		if (xfrm_msg && xfrm_msg[0])
 			puts(xfrm_msg);
+		/*
+		 * we do not run diff between different kind
+		 * of objects.
+		 */
 		if (strncmp(temp[0].mode, temp[1].mode, 3))
-			/* we do not run diff between different kind
-			 * of objects.
-			 */
-			exit(0);
+			return NULL;
 		if (complete_rewrite) {
-			fflush(NULL);
 			emit_rewrite_diff(name_a, name_b, temp);
-			exit(0);
+			return NULL;
 		}
 	}
-	fflush(NULL);
-	execlp("/bin/sh","sh", "-c", cmd, NULL);
+
+	/* This is disgusting */
+	*args++ = "sh";
+	*args++ = "-c";
+	*args++ = cmd;
+	*args = NULL;
+	return "/bin/sh";
 }
 
 struct diff_filespec *alloc_filespec(const char *path)
@@ -559,6 +565,40 @@ static void remove_tempfile_on_signal(int signo)
 	raise(signo);
 }
 
+static int spawn_prog(const char *pgm, const char **arg)
+{
+	pid_t pid;
+	int status;
+
+	fflush(NULL);
+	pid = fork();
+	if (pid < 0)
+		die("unable to fork");
+	if (!pid) {
+		execvp(pgm, (char *const*) arg);
+		exit(255);
+	}
+
+	while (waitpid(pid, &status, 0) < 0) {
+		if (errno == EINTR)
+			continue;
+		return -1;
+	}
+
+	/* Earlier we did not check the exit status because
+	 * diff exits non-zero if files are different, and
+	 * we are not interested in knowing that.  It was a
+	 * mistake which made it harder to quit a diff-*
+	 * session that uses the git-apply-patch-script as
+	 * the GIT_EXTERNAL_DIFF.  A custom GIT_EXTERNAL_DIFF
+	 * should also exit non-zero only when it wants to
+	 * abort the entire diff-* session.
+	 */
+	if (WIFEXITED(status) && !WEXITSTATUS(status))
+		return 0;
+	return -1;
+}
+
 /* An external diff command takes:
  *
  * diff-cmd name infile1 infile1-sha1 infile1-mode \
@@ -573,9 +613,9 @@ static void run_external_diff(const char *pgm,
 			      const char *xfrm_msg,
 			      int complete_rewrite)
 {
+	const char *spawn_arg[10];
 	struct diff_tempfile *temp = diff_temp;
-	pid_t pid;
-	int status;
+	int retval;
 	static int atexit_asked = 0;
 	const char *othername;
 
@@ -592,59 +632,41 @@ static void run_external_diff(const char *pgm,
 		signal(SIGINT, remove_tempfile_on_signal);
 	}
 
-	fflush(NULL);
-	pid = fork();
-	if (pid < 0)
-		die("unable to fork");
-	if (!pid) {
-		if (pgm) {
-			if (one && two) {
-				const char *exec_arg[10];
-				const char **arg = &exec_arg[0];
-				*arg++ = pgm;
-				*arg++ = name;
-				*arg++ = temp[0].name;
-				*arg++ = temp[0].hex;
-				*arg++ = temp[0].mode;
-				*arg++ = temp[1].name;
-				*arg++ = temp[1].hex;
-				*arg++ = temp[1].mode;
-				if (other) {
-					*arg++ = other;
-					*arg++ = xfrm_msg;
-				}
-				*arg = NULL;
-				execvp(pgm, (char *const*) exec_arg);
+	if (pgm) {
+		const char **arg = &spawn_arg[0];
+		if (one && two) {
+			*arg++ = pgm;
+			*arg++ = name;
+			*arg++ = temp[0].name;
+			*arg++ = temp[0].hex;
+			*arg++ = temp[0].mode;
+			*arg++ = temp[1].name;
+			*arg++ = temp[1].hex;
+			*arg++ = temp[1].mode;
+			if (other) {
+				*arg++ = other;
+				*arg++ = xfrm_msg;
 			}
-			else
-				execlp(pgm, pgm, name, NULL);
+		} else {
+			*arg++ = pgm;
+			*arg++ = name;
 		}
-		/*
-		 * otherwise we use the built-in one.
-		 */
-		if (one && two)
-			builtin_diff(name, othername, temp, xfrm_msg,
-				     complete_rewrite);
-		else
+		*arg = NULL;
+	} else {
+		if (one && two) {
+			pgm = builtin_diff(name, othername, temp, xfrm_msg, complete_rewrite, spawn_arg);
+		} else
 			printf("* Unmerged path %s\n", name);
-		exit(0);
 	}
-	if (waitpid(pid, &status, 0) < 0 ||
-	    !WIFEXITED(status) || WEXITSTATUS(status)) {
-		/* Earlier we did not check the exit status because
-		 * diff exits non-zero if files are different, and
-		 * we are not interested in knowing that.  It was a
-		 * mistake which made it harder to quit a diff-*
-		 * session that uses the git-apply-patch-script as
-		 * the GIT_EXTERNAL_DIFF.  A custom GIT_EXTERNAL_DIFF
-		 * should also exit non-zero only when it wants to
-		 * abort the entire diff-* session.
-		 */
-		remove_tempfile();
+
+	retval = 0;
+	if (pgm)
+		retval = spawn_prog(pgm, spawn_arg);
+	remove_tempfile();
+	if (retval) {
 		fprintf(stderr, "external diff died, stopping at %s.\n", name);
 		exit(1);
 	}
-	remove_tempfile();
 }
 
 static void diff_fill_sha1_info(struct diff_filespec *one)
diff --git a/git-svnimport.perl b/git-svnimport.perl
index ee2940f48..0dd9fab9f 100755
--- a/git-svnimport.perl
+++ b/git-svnimport.perl
@@ -29,19 +29,21 @@ die "Need SVN:Core 1.2.1 or better" if $SVN::Core::VERSION lt "1.2.1";
 $SIG{'PIPE'}="IGNORE";
 $ENV{'TZ'}="UTC";
 
-our($opt_h,$opt_o,$opt_v,$opt_u,$opt_C,$opt_i,$opt_m,$opt_M,$opt_t,$opt_T,$opt_b,$opt_r,$opt_s,$opt_l,$opt_d,$opt_D);
+our($opt_h,$opt_o,$opt_v,$opt_u,$opt_C,$opt_i,$opt_m,$opt_M,$opt_t,$opt_T,
+    $opt_b,$opt_r,$opt_I,$opt_s,$opt_l,$opt_d,$opt_D);
 
 sub usage() {
 	print STDERR <<END;
 Usage: ${\basename $0}     # fetch/update GIT from SVN
        [-o branch-for-HEAD] [-h] [-v] [-l max_rev]
        [-C GIT_repository] [-t tagname] [-T trunkname] [-b branchname]
-       [-d|-D] [-i] [-u] [-r] [-s start_chg] [-m] [-M regex] [SVN_URL]
+       [-d|-D] [-i] [-u] [-r] [-I ignorefilename] [-s start_chg]
+       [-m] [-M regex] [SVN_URL]
 END
 	exit(1);
 }
 
-getopts("b:C:dDhil:mM:o:rs:t:T:uv") or usage();
+getopts("b:C:dDhiI:l:mM:o:rs:t:T:uv") or usage();
 usage if $opt_h;
 
 my $tag_name = $opt_t || "tags";
@@ -112,16 +114,40 @@ sub file {
 		    DIR => File::Spec->tmpdir(), UNLINK => 1);
 
 	print "... $rev $path ...\n" if $opt_v;
-	my $pool = SVN::Pool->new();
-	eval { $self->{'svn'}->get_file($path,$rev,$fh,$pool); };
-	$pool->clear;
+	my (undef, $properties);
+	eval { (undef, $properties)
+		   = $self->{'svn'}->get_file($path,$rev,$fh); };
 	if($@) {
 		return undef if $@ =~ /Attempted to get checksum/;
 		die $@;
 	}
+	my $mode;
+	if (exists $properties->{'svn:executable'}) {
+		$mode = '0755';
+	} else {
+		$mode = '0644';
+	}
 	close ($fh);
 
-	return $name;
+	return ($name, $mode);
+}
+
+sub ignore {
+	my($self,$path,$rev) = @_;
+
+	print "... $rev $path ...\n" if $opt_v;
+	my (undef,undef,$properties)
+	    = $self->{'svn'}->get_dir($path,$rev,undef);
+	if (exists $properties->{'svn:ignore'}) {
+		my ($fh, $name) = tempfile('gitsvn.XXXXXX',
+					   DIR => File::Spec->tmpdir(),
+					   UNLINK => 1);
+		print $fh $properties->{'svn:ignore'};
+		close($fh);
+		return $name;
+	} else {
+		return undef;
+	}
 }
 
 package main;
@@ -296,7 +322,7 @@ sub get_file($$$) {
 	my $svnpath = revert_split_path($branch,$path);
 
 	# now get it
-	my $name;
+	my ($name,$mode);
 	if($opt_d) {
 		my($req,$res);
 
@@ -316,8 +342,9 @@ sub get_file($$$) {
 			return undef if $res->code == 301; # directory?
 			die $res->status_line." at $url\n";
 		}
+		$mode = '0644'; # can't obtain mode via direct http request?
 	} else {
-		$name = $svn->file("$svnpath",$rev);
+		($name,$mode) = $svn->file("$svnpath",$rev);
 		return undef unless defined $name;
 	}
 
@@ -331,10 +358,37 @@ sub get_file($$$) {
 	chomp $sha;
 	close $F;
 	unlink $name;
-	my $mode = "0644"; # SV does not seem to store any file modes
 	return [$mode, $sha, $path];
 }
 
+sub get_ignore($$$$$) {
+	my($new,$old,$rev,$branch,$path) = @_;
+
+	return unless $opt_I;
+	my $svnpath = revert_split_path($branch,$path);
+	my $name = $svn->ignore("$svnpath",$rev);
+	if ($path eq '/') {
+		$path = $opt_I;
+	} else {
+		$path = File::Spec->catfile($path,$opt_I);
+	}
+	if (defined $name) {
+		my $pid = open(my $F, '-|');
+		die $! unless defined $pid;
+		if (!$pid) {
+			exec("git-hash-object", "-w", $name)
+			    or die "Cannot create object: $!\n";
+		}
+		my $sha = <$F>;
+		chomp $sha;
+		close $F;
+		unlink $name;
+		push(@$new,['0644',$sha,$path]);
+	} else {
+		push(@$old,$path);
+	}
+}
+
 sub split_path($$) {
 	my($rev,$path) = @_;
 	my $branch;
@@ -540,6 +594,9 @@ sub commit {
 						my $opath = $action->[3];
 						print STDERR "$revision: $branch: could not fetch '$opath'\n";
 					}
+				} elsif ($node_kind eq $SVN::Node::dir) {
+					get_ignore(\@new, \@old, $revision,
+						   $branch,$path);
 				}
 			} elsif ($action->[0] eq "D") {
 				push(@old,$path);
@@ -548,6 +605,9 @@ sub commit {
 				if ($node_kind eq $SVN::Node::file) {
 					my $f = get_file($revision,$branch,$path);
 					push(@new,$f) if $f;
+				} elsif ($node_kind eq $SVN::Node::dir) {
+					get_ignore(\@new, \@old, $revision,
+						   $branch,$path);
 				}
 			} else {
 				die "$revision: unknown action '".$action->[0]."' for $path\n";