Merge branch 'master' into sp/mmap

* master:
  Documentation/config.txt (and repo-config manpage): mark-up fix.
  Teach Git how to parse standard power of 2 suffixes.
  Use /dev/null for update hook stdin.
  Redirect update hook stdout to stderr.
  Remove unnecessary argc parameter from run_command_v.
  Automatically detect a bare git repository.
  Replace "GIT_DIR" with GIT_DIR_ENVIRONMENT.
  Use PATH_MAX constant for --bare.
  Force core.filemode to false on Cygwin.
  Fix formatting for urls section of fetch, pull, and push manpages
  Fix yet another subtle xdl_merge() bug
  i18n: drop "encoding" header in the output after re-coding.
  commit-tree: cope with different ways "utf-8" can be spelled.
  Move commit reencoding parameter parsing to revision.c
  Documentation: minor rewording for git-log and git-show pages.
  Documentation: i18n commit log message notes.
  t3900: test log --encoding=none
  commit re-encoding: fix confusion between no and default conversion.

Documentation/config.txt

@@ -82,13 +82,13 @@ core.logAllRefUpdates::
 	only when the file exists.  If this configuration
 	variable is set to true, missing "$GIT_DIR/logs/<ref>"
 	file is automatically created for branch heads.
-
-	This information can be used to determine what commit
-	was the tip of a branch "2 days ago".
-
-	This value is true by default in a repository that has
-	a working directory associated with it, and false by
-	default in a bare repository.
++
+This information can be used to determine what commit
+was the tip of a branch "2 days ago".
++
+This value is true by default in a repository that has
+a working directory associated with it, and false by
+default in a bare repository.
 
 core.repositoryFormatVersion::
 	Internal variable identifying the repository format and layout

Documentation/git-commit-tree.txt

@@ -81,6 +81,11 @@ Your parents must have hated you!::
 Your sysadmin must hate you!::
     The password(5) name field is longer than a giant static buffer.
 
+Discussion
+----------
+
+include::i18n.txt[]
+
 See Also
 --------
 gitlink:git-write-tree[1]

Documentation/git-commit.txt

@@ -223,6 +223,11 @@ should be recorded as a single commit.  In fact, the command
 refuses to run when given pathnames (but see `-i` option).
 
 
+DISCUSSION
+----------
+
+include::i18n.txt[]
+
 ENVIRONMENT VARIABLES
 ---------------------
 The command specified by either the VISUAL or EDITOR environment

Documentation/git-log.txt

@@ -31,7 +31,9 @@ include::pretty-formats.txt[]
 	Limits the number of commits to show.
 
 <since>..<until>::
-	Show only commits between the named two commits.
+	Show only commits between the named two commits.  When
+	either <since> or <until> is omitted, it defaults to
+	`HEAD`, i.e. the tip of the current branch.
 
 -p::
 	Show the change the commit introduces in a patch form.
@@ -63,6 +65,12 @@ git log -r --name-status release..test::
 	in the "release" branch, along with the list of paths
 	each commit modifies.
 
+Discussion
+----------
+
+include::i18n.txt[]
+
+
 Author
 ------
 Written by Linus Torvalds <torvalds@osdl.org>

Documentation/git-repo-config.txt

@@ -87,7 +87,10 @@ OPTIONS
 	git-repo-config will ensure that the output is "true" or "false"
 
 --int::
-	git-repo-config will ensure that the output is a simple decimal number
+	git-repo-config will ensure that the output is a simple
+	decimal number.  An optional value suffix of 'k', 'm', or 'g'
+	in the config file will cause the value to be multiplied
+	by 1024, 1048576, or 1073741824 prior to output.
 
 
 ENVIRONMENT

Documentation/git-rev-list.txt

@@ -21,6 +21,7 @@ SYNOPSIS
 	     [ \--stdin ]
 	     [ \--topo-order ]
 	     [ \--parents ]
+	     [ \--encoding[=<encoding>] ]
 	     [ \--(author|committer|grep)=<pattern> ]
 	     [ [\--objects | \--objects-edge] [ \--unpacked ] ]
 	     [ \--pretty | \--header ]

Documentation/git-show.txt

@@ -30,8 +30,8 @@ This manual page describes only the most frequently used options.
 
 OPTIONS
 -------
-<commitid>::
-	ID of the commit to show.
+<object>::
+	The name of the object to show.
 
 include::pretty-formats.txt[]
 
@@ -40,7 +40,8 @@ EXAMPLES
 --------
 
 git show v1.0.0::
-	Shows the tag `v1.0.0`.
+	Shows the tag `v1.0.0`, along with the object the tags
+	points at.
 
 git show v1.0.0^{tree}::
 	Shows the tree pointed to by the tag `v1.0.0`.
@@ -54,10 +55,16 @@ git show master:Makefile master:t/Makefile
 	Concatenates the contents of said Makefiles in the head
 	of the branch `master`.
 
+Discussion
+----------
+
+include::i18n.txt[]
+
 Author
 ------
 Written by Linus Torvalds <torvalds@osdl.org> and
-Junio C Hamano <junkio@cox.net>
+Junio C Hamano <junkio@cox.net>.  Significantly enhanced by
+Johannes Schindelin <Johannes.Schindelin@gmx.de>.
 
 
 Documentation

Documentation/i18n.txt

@@ -0,0 +1,57 @@
+At the core level, git is character encoding agnostic.
+
+ - The pathnames recorded in the index and in the tree objects
+   are treated as uninterpreted sequences of non-NUL bytes.
+   What readdir(2) returns are what are recorded and compared
+   with the data git keeps track of, which in turn are expected
+   to be what lstat(2) and creat(2) accepts.  There is no such
+   thing as pathname encoding translation.
+
+ - The contents of the blob objects are uninterpreted sequence
+   of bytes.  There is no encoding translation at the core
+   level.
+
+ - The commit log messages are uninterpreted sequence of non-NUL
+   bytes.
+
+Although we encourage that the commit log messages are encoded
+in UTF-8, both the core and git Porcelain are designed not to
+force UTF-8 on projects.  If all participants of a particular
+project find it more convenient to use legacy encodings, git
+does not forbid it.  However, there are a few things to keep in
+mind.
+
+. `git-commit-tree` (hence, `git-commit` which uses it) issues
+  an warning if the commit log message given to it does not look
+  like a valid UTF-8 string, unless you explicitly say your
+  project uses a legacy encoding.  The way to say this is to
+  have core.commitencoding in `.git/config` file, like this:
++
+------------
+[core]
+	commitencoding = ISO-8859-1
+------------
++
+Commit objects created with the above setting record the value
+of `core.commitencoding` in its `encoding` header.  This is to
+help other people who look at them later.  Lack of this header
+implies that the commit log message is encoded in UTF-8.
+
+. `git-log`, `git-show` and friends looks at the `encoding`
+  header of a commit object, and tries to re-code the log
+  message into UTF-8 unless otherwise specified.  You can
+  specify the desired output encoding with
+  `core.logoutputencoding` in `.git/config` file, like this:
++
+------------
+[core]
+	logoutputencoding = ISO-8859-1
+------------
++
+If you do not have this configuration variable, the value of
+`core.commitencoding` is used instead.
+
+Note that we deliberately chose not to re-code the commit log
+message when a commit is made to force UTF-8 at the commit
+object level, because re-coding to UTF-8 is not necessarily a
+reversible operation.

Documentation/pretty-formats.txt

@@ -76,3 +76,10 @@ displayed in full, regardless of whether --abbrev or
 --no-abbrev are used, and 'parents' information show the
 true parent commits, without taking grafts nor history
 simplification into account.
+
+--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.

Documentation/urls.txt

@@ -40,9 +40,11 @@ In addition to the above, as a short-hand, the name of a
 file in `$GIT_DIR/remotes` directory can be given; the
 named file should be in the following format:
 
-	URL: one of the above URL format
-	Push: <refspec>
-	Pull: <refspec>
+------------
+URL: one of the above URL format
+Push: <refspec>
+Pull: <refspec>
+------------
 
 Then such a short-hand is specified in place of
 <repository> without <refspec> parameters on the command
@@ -54,10 +56,12 @@ be specified for additional branch mappings.
 Or, equivalently, in the `$GIT_DIR/config` (note the use
 of `fetch` instead of `Pull:`):
 
+------------
 [remote "<remote>"]
 	url = <url>
 	push = <refspec>
 	fetch = <refspec>
+------------
 
 The name of a file in `$GIT_DIR/branches` directory can be
 specified as an older notation short-hand; the named
@@ -68,10 +72,15 @@ name of remote head (URL fragment notation).
 without the fragment is equivalent to have this in the
 corresponding file in the `$GIT_DIR/remotes/` directory.
 
-	URL: <url>
-	Pull: refs/heads/master:<remote>
+------------
+URL: <url>
+Pull: refs/heads/master:<remote>
+------------
+
 
 while having `<url>#<head>` is equivalent to
 
-	URL: <url>
-	Pull: refs/heads/<head>:<remote>
+------------
+URL: <url>
+Pull: refs/heads/<head>:<remote>
+------------

Makefile

@@ -72,6 +72,9 @@ all:
 # Define NO_FAST_WORKING_DIRECTORY if accessing objects in pack files is
 # generally faster on your platform than accessing the working directory.
 #
+# Define NO_TRUSTABLE_FILEMODE if your filesystem may claim to support
+# the executable mode bit, but doesn't really do so.
+#
 # Define NO_IPV6 if you lack IPv6 support and getaddrinfo().
 #
 # Define NO_SOCKADDR_STORAGE if your platform does not have struct
@@ -361,6 +364,7 @@ ifeq ($(uname_O),Cygwin)
 	NEEDS_LIBICONV = YesPlease
 	NO_C99_FORMAT = YesPlease
 	NO_FAST_WORKING_DIRECTORY = UnfortunatelyYes
+	NO_TRUSTABLE_FILEMODE = UnfortunatelyYes
 	# There are conflicting reports about this.
 	# On some boxes NO_MMAP is needed, and not so elsewhere.
 	# Try commenting this out if you suspect MMAP is more efficient
@@ -521,6 +525,9 @@ endif
 ifdef NO_FAST_WORKING_DIRECTORY
 	BASIC_CFLAGS += -DNO_FAST_WORKING_DIRECTORY
 endif
+ifdef NO_TRUSTABLE_FILEMODE
+	BASIC_CFLAGS += -DNO_TRUSTABLE_FILEMODE
+endif
 ifdef NO_IPV6
 	BASIC_CFLAGS += -DNO_IPV6
 endif

builtin-commit-tree.c

@@ -119,8 +119,7 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix)
 	}
 
 	/* Not having i18n.commitencoding is the same as having utf-8 */
-	encoding_is_utf8 = (!git_commit_encoding ||
-			    !strcmp(git_commit_encoding, "utf-8"));
+	encoding_is_utf8 = is_encoding_utf8(git_commit_encoding);
 
 	init_buffer(&buffer, &size);
 	add_buffer(&buffer, &size, "tree %s\n", sha1_to_hex(tree_sha1));

builtin-init-db.c

@@ -10,6 +10,12 @@
 #define DEFAULT_GIT_TEMPLATE_DIR "/usr/share/git-core/templates/"
 #endif
 
+#ifdef NO_TRUSTABLE_FILEMODE
+#define TEST_FILEMODE 0
+#else
+#define TEST_FILEMODE 1
+#endif
+
 static void safe_create_dir(const char *dir, int share)
 {
 	if (mkdir(dir, 0777) < 0) {
@@ -175,6 +181,7 @@ static int create_default_files(const char *git_dir, const char *template_path)
 	struct stat st1;
 	char repo_version_string[10];
 	int reinit;
+	int filemode;
 
 	if (len > sizeof(path)-50)
 		die("insane git directory %s", git_dir);
@@ -236,14 +243,14 @@ static int create_default_files(const char *git_dir, const char *template_path)
 	strcpy(path + len, "config");
 
 	/* Check filemode trustability */
-	if (!lstat(path, &st1)) {
+	filemode = TEST_FILEMODE;
+	if (TEST_FILEMODE && !lstat(path, &st1)) {
 		struct stat st2;
-		int filemode = (!chmod(path, st1.st_mode ^ S_IXUSR) &&
+		filemode = (!chmod(path, st1.st_mode ^ S_IXUSR) &&
 				!lstat(path, &st2) &&
 				st1.st_mode != st2.st_mode);
-		git_config_set("core.filemode",
-			       filemode ? "true" : "false");
 	}
+	git_config_set("core.filemode", filemode ? "true" : "false");
 
 	/* Enable logAllRefUpdates if a working tree is attached */
 	if (!is_bare_git_dir(git_dir))

builtin-push.c

@@ -275,7 +275,7 @@ static int do_push(const char *repo)
 		argv[dest_argc] = NULL;
 		if (verbose)
 			fprintf(stderr, "Pushing to %s\n", dest);
-		err = run_command_v(argc, argv);
+		err = run_command_v(argv);
 		if (!err)
 			continue;
 		switch (err) {

commit.c

@@ -624,6 +624,48 @@ static char *get_header(const struct commit *commit, const char *key)
 	}
 }
 
+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 *encoding;
@@ -633,13 +675,18 @@ static char *logmsg_reencode(const struct commit *commit)
 				 : git_commit_encoding);
 
 	if (!output_encoding)
+		output_encoding = "utf-8";
+	else if (!*output_encoding)
 		return NULL;
 	encoding = get_header(commit, "encoding");
 	if (!encoding || !strcmp(encoding, output_encoding)) {
 		free(encoding);
 		return NULL;
 	}
 	out = reencode_string(commit->buffer, output_encoding, encoding);
+	if (out)
+		out = replace_encoding_header(out, output_encoding);
+
 	free(encoding);
 	if (!out)
 		return NULL;