From: Junio C Hamano <gitster@pobox.com>
Date: Mon, 26 Jan 2009 06:27:52 +0000 (-0800)
Subject: Merge git://git.bogomips.org/git-svn
X-Git-Tag: v1.6.2-rc0~85
X-Git-Url: https://www.git.lorimer.id.au/gitweb.git/diff_plain/afc72747049af5775ab9def6224dd8082d42a57f?hp=242522d9cc9b04c4db3baf7e97135d21401c1827

Merge git://git.bogomips.org/git-svn

* git://git.bogomips.org/git-svn:
git-svn: Add test for --ignore-paths parameter
git-svn: documented --ignore-paths
git-svn: add --ignore-paths option for fetching
git-svn: fix memory leak when checking for empty symlinks
---

diff --git a/.gitignore b/.gitignore
index d9adce585a..e8f91ce8cd 100644
--- a/.gitignore
+++ b/.gitignore
@@ -144,6 +144,7 @@ git-core-*/?*
 gitk-wish
 gitweb/gitweb.cgi
 test-chmtime
+test-ctype
 test-date
 test-delta
 test-dump-cache-tree
diff --git a/Documentation/RelNotes-1.6.1.1.txt b/Documentation/RelNotes-1.6.1.1.txt
index 5cd1ca9cc6..88454c1973 100644
--- a/Documentation/RelNotes-1.6.1.1.txt
+++ b/Documentation/RelNotes-1.6.1.1.txt
@@ -4,9 +4,14 @@ GIT v1.6.1.1 Release Notes
 Fixes since v1.6.1
 ------------------
 
+* "git add frotz/nitfol" when "frotz" is a submodule should have errored
+  out, but it didn't.
+
 * "git apply" took file modes from the patch text and updated the mode
   bits of the target tree even when the patch was not about mode changes.
 
+* "git bisect view" on Cygwin did not launch gitk
+
 * "git checkout $tree" did not trigger an error.
 
 * "git commit" tried to remove COMMIT_EDITMSG from the work tree by mistake.
@@ -14,6 +19,12 @@ Fixes since v1.6.1
 * "git describe --all" complained when a commit is described with a tag,
   which was nonsense.
 
+* "git diff --no-index --" did not trigger no-index (aka "use git-diff as
+  a replacement of diff on untracked files") behaviour.
+
+* "git format-patch -1 HEAD" on a root commit failed to produce patch
+  text.
+
 * "git fsck branch" did not work as advertised; instead it behaved the same
   way as "git fsck".
 
@@ -36,14 +47,13 @@ Fixes since v1.6.1
 
 * "git mv -k" with more than one errorneous paths misbehaved.
 
+* "git read-tree -m -u" hence branch switching incorrectly lost a
+  subdirectory in rare cases.
+
 * "git rebase -i" issued an unnecessary error message upon a user error of
   marking the first commit to be "squash"ed.
 
-Other documentation updates.
-
----
-exec >/var/tmp/1
-O=v1.6.1-60-g78f111e
-echo O=$(git describe maint)
-git shortlog --no-merges $O..maint
+* "git shortlog" did not format a commit message with multi-line
+  subject correctly.
 
+Many documentation updates.
diff --git a/Documentation/config.txt b/Documentation/config.txt
index 290cb48eb9..e2b8775dd3 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -639,6 +639,12 @@ diff.suppressBlankEmpty::
 	A boolean to inhibit the standard behavior of printing a space
 	before each empty output line. Defaults to false.
 
+diff.wordRegex::
+	A POSIX Extended Regular Expression used to determine what is a "word"
+	when performing word-by-word difference calculations.  Character
+	sequences that match the regular expression are "words", all other
+	characters are *ignorable* whitespace.
+
 fetch.unpackLimit::
 	If the number of objects fetched over the git native
 	transfer is below this
diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt
index 1f8ce979bb..813a7b11b9 100644
--- a/Documentation/diff-options.txt
+++ b/Documentation/diff-options.txt
@@ -36,7 +36,7 @@ endif::git-format-patch[]
 --patch-with-raw::
 	Synonym for "-p --raw".
 
---patience:
+--patience::
 	Generate a diff using the "patience diff" algorithm.
 
 --stat[=width[,name-width]]::
@@ -94,8 +94,22 @@ endif::git-format-patch[]
 	Turn off colored diff, even when the configuration file
 	gives the default to color output.
 
---color-words::
-	Show colored word diff, i.e. color words which have changed.
+--color-words[=<regex>]::
+	Show colored word diff, i.e., color words which have changed.
+	By default, words are separated by whitespace.
++
+When a <regex> is specified, every non-overlapping match of the
+<regex> is considered a word.  Anything between these matches is
+considered whitespace and ignored(!) for the purposes of finding
+differences.  You may want to append `|[^[:space:]]` to your regular
+expression to make sure that it matches all non-whitespace characters.
+A match that contains a newline is silently truncated(!) at the
+newline.
++
+The regex can also be set via a diff driver or configuration option, see
+linkgit:gitattributes[1] or linkgit:git-config[1].  Giving it explicitly
+overrides any diff driver or configuration setting.  Diff drivers
+override configuration settings.
 
 --no-renames::
 	Turn off rename detection, even when the configuration
diff --git a/Documentation/git.txt b/Documentation/git.txt
index 17dc8b2019..cd527c6252 100644
--- a/Documentation/git.txt
+++ b/Documentation/git.txt
@@ -43,9 +43,10 @@ unreleased) version of git, that is available from 'master'
 branch of the `git.git` repository.
 Documentation for older releases are available here:
 
-* link:v1.6.1/git.html[documentation for release 1.6.1]
+* link:v1.6.1.1/git.html[documentation for release 1.6.1.1]
 
 * release notes for
+  link:RelNotes-1.6.1.1.txt[1.6.1.1],
   link:RelNotes-1.6.1.txt[1.6.1].
 
 * link:v1.6.0.6/git.html[documentation for release 1.6.0.6]
diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt
index 8af22eccac..227934f59a 100644
--- a/Documentation/gitattributes.txt
+++ b/Documentation/gitattributes.txt
@@ -317,6 +317,8 @@ patterns are available:
 
 - `bibtex` suitable for files with BibTeX coded references.
 
+- `cpp` suitable for source code in the C and C++ languages.
+
 - `html` suitable for HTML/XHTML documents.
 
 - `java` suitable for source code in the Java language.
@@ -334,6 +336,25 @@ patterns are available:
 - `tex` suitable for source code for LaTeX documents.
 
 
+Customizing word diff
+^^^^^^^^^^^^^^^^^^^^^
+
+You can customize the rules that `git diff --color-words` uses to
+split words in a line, by specifying an appropriate regular expression
+in the "diff.*.wordRegex" configuration variable.  For example, in TeX
+a backslash followed by a sequence of letters forms a command, but
+several such commands can be run together without intervening
+whitespace.  To separate them, use a regular expression such as
+
+------------------------
+[diff "tex"]
+	wordRegex = "\\\\[a-zA-Z]+|[{}]|\\\\.|[^\\{}[:space:]]+"
+------------------------
+
+A built-in pattern is provided for all languages listed in the
+previous section.
+
+
 Performing text diffs of binary files
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
diff --git a/Documentation/gittutorial.txt b/Documentation/gittutorial.txt
index 458fafdb2c..c5d5596d89 100644
--- a/Documentation/gittutorial.txt
+++ b/Documentation/gittutorial.txt
@@ -308,9 +308,7 @@ alice$ git pull /home/bob/myrepo master
 
 This merges the changes from Bob's "master" branch into Alice's
 current branch.  If Alice has made her own changes in the meantime,
-then she may need to manually fix any conflicts.  (Note that the
-"master" argument in the above command is actually unnecessary, as it
-is the default.)
+then she may need to manually fix any conflicts.
 
 The "pull" command thus performs two operations: it fetches changes
 from a remote branch, then merges them into the current branch.
diff --git a/GIT-VERSION-GEN b/GIT-VERSION-GEN
index 6c7465c758..9c9fe640fb 100755
--- a/GIT-VERSION-GEN
+++ b/GIT-VERSION-GEN
@@ -1,7 +1,7 @@
 #!/bin/sh
 
 GVF=GIT-VERSION-FILE
-DEF_VER=v1.6.0.2.GIT
+DEF_VER=v1.6.1.GIT
 
 LF='
 '
diff --git a/builtin-checkout.c b/builtin-checkout.c
index 275176d15d..6cdb320ae7 100644
--- a/builtin-checkout.c
+++ b/builtin-checkout.c
@@ -230,7 +230,7 @@ static int checkout_paths(struct tree *source_tree, const char **pathspec,
 
 	for (pos = 0; pos < active_nr; pos++) {
 		struct cache_entry *ce = active_cache[pos];
-		pathspec_match(pathspec, ps_matched, ce->name, 0);
+		match_pathspec(pathspec, ce->name, ce_namelen(ce), 0, ps_matched);
 	}
 
 	if (report_path_error(ps_matched, pathspec, 0))
@@ -239,7 +239,7 @@ static int checkout_paths(struct tree *source_tree, const char **pathspec,
 	/* Any unmerged paths? */
 	for (pos = 0; pos < active_nr; pos++) {
 		struct cache_entry *ce = active_cache[pos];
-		if (pathspec_match(pathspec, NULL, ce->name, 0)) {
+		if (match_pathspec(pathspec, ce->name, ce_namelen(ce), 0, NULL)) {
 			if (!ce_stage(ce))
 				continue;
 			if (opts->force) {
@@ -264,7 +264,7 @@ static int checkout_paths(struct tree *source_tree, const char **pathspec,
 	state.refresh_cache = 1;
 	for (pos = 0; pos < active_nr; pos++) {
 		struct cache_entry *ce = active_cache[pos];
-		if (pathspec_match(pathspec, NULL, ce->name, 0)) {
+		if (match_pathspec(pathspec, ce->name, ce_namelen(ce), 0, NULL)) {
 			if (!ce_stage(ce)) {
 				errs |= checkout_entry(ce, &state, NULL);
 				continue;
diff --git a/builtin-clone.c b/builtin-clone.c
index f7e5a7b0a0..1e9c9aa844 100644
--- a/builtin-clone.c
+++ b/builtin-clone.c
@@ -522,14 +522,23 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 					     option_upload_pack);
 
 		refs = transport_get_remote_refs(transport);
-		transport_fetch_refs(transport, refs);
+		if(refs)
+			transport_fetch_refs(transport, refs);
 	}
 
-	clear_extra_refs();
+	if (refs) {
+		clear_extra_refs();
 
-	mapped_refs = write_remote_refs(refs, &refspec, reflog_msg.buf);
+		mapped_refs = write_remote_refs(refs, &refspec, reflog_msg.buf);
 
-	head_points_at = locate_head(refs, mapped_refs, &remote_head);
+		head_points_at = locate_head(refs, mapped_refs, &remote_head);
+	}
+	else {
+		warning("You appear to have cloned an empty repository.");
+		head_points_at = NULL;
+		remote_head = NULL;
+		option_no_checkout = 1;
+	}
 
 	if (head_points_at) {
 		/* Local default branch link */
diff --git a/builtin-commit.c b/builtin-commit.c
index 7aaa5304c7..d6a3a6203a 100644
--- a/builtin-commit.c
+++ b/builtin-commit.c
@@ -166,7 +166,7 @@ static int list_paths(struct string_list *list, const char *with_tree,
 		struct cache_entry *ce = active_cache[i];
 		if (ce->ce_flags & CE_UPDATE)
 			continue;
-		if (!pathspec_match(pattern, m, ce->name, 0))
+		if (!match_pathspec(pattern, ce->name, ce_namelen(ce), 0, m))
 			continue;
 		string_list_insert(ce->name, list);
 	}
diff --git a/builtin-ls-files.c b/builtin-ls-files.c
index f72eb85475..3434031295 100644
--- a/builtin-ls-files.c
+++ b/builtin-ls-files.c
@@ -36,42 +36,6 @@ static const char *tag_other = "";
 static const char *tag_killed = "";
 static const char *tag_modified = "";
 
-
-/*
- * Match a pathspec against a filename. The first "skiplen" characters
- * are the common prefix
- */
-int pathspec_match(const char **spec, char *ps_matched,
-		   const char *filename, int skiplen)
-{
-	const char *m;
-
-	while ((m = *spec++) != NULL) {
-		int matchlen = strlen(m + skiplen);
-
-		if (!matchlen)
-			goto matched;
-		if (!strncmp(m + skiplen, filename + skiplen, matchlen)) {
-			if (m[skiplen + matchlen - 1] == '/')
-				goto matched;
-			switch (filename[skiplen + matchlen]) {
-			case '/': case '\0':
-				goto matched;
-			}
-		}
-		if (!fnmatch(m + skiplen, filename + skiplen, 0))
-			goto matched;
-		if (ps_matched)
-			ps_matched++;
-		continue;
-	matched:
-		if (ps_matched)
-			*ps_matched = 1;
-		return 1;
-	}
-	return 0;
-}
-
 static void show_dir_entry(const char *tag, struct dir_entry *ent)
 {
 	int len = prefix_len;
@@ -80,7 +44,7 @@ static void show_dir_entry(const char *tag, struct dir_entry *ent)
 	if (len >= ent->len)
 		die("git ls-files: internal error - directory entry not superset of prefix");
 
-	if (pathspec && !pathspec_match(pathspec, ps_matched, ent->name, len))
+	if (!match_pathspec(pathspec, ent->name, ent->len, len, ps_matched))
 		return;
 
 	fputs(tag, stdout);
@@ -156,7 +120,7 @@ static void show_ce_entry(const char *tag, struct cache_entry *ce)
 	if (len >= ce_namelen(ce))
 		die("git ls-files: internal error - cache entry not superset of prefix");
 
-	if (pathspec && !pathspec_match(pathspec, ps_matched, ce->name, len))
+	if (!match_pathspec(pathspec, ce->name, ce_namelen(ce), len, ps_matched))
 		return;
 
 	if (tag && *tag && show_valid_bit &&
diff --git a/bundle.c b/bundle.c
index 4977962eb5..d0dd818b31 100644
--- a/bundle.c
+++ b/bundle.c
@@ -266,6 +266,8 @@ int create_bundle(struct bundle_header *header, const char *path,
 		return error("unrecognized argument: %s'", argv[i]);
 	}
 
+	object_array_remove_duplicates(&revs.pending);
+
 	for (i = 0; i < revs.pending.nr; i++) {
 		struct object_array_entry *e = revs.pending.objects + i;
 		unsigned char sha1[20];
diff --git a/cache.h b/cache.h
index 8d965b8c98..c17fbf58a7 100644
--- a/cache.h
+++ b/cache.h
@@ -721,6 +721,10 @@ struct checkout {
 
 extern int checkout_entry(struct cache_entry *ce, const struct checkout *state, char *topath);
 extern int has_symlink_leading_path(int len, const char *name);
+extern int has_symlink_or_noent_leading_path(int len, const char *name);
+extern int has_dirs_only_path(int len, const char *name, int prefix_len);
+extern void invalidate_lstat_cache(int len, const char *name);
+extern void clear_lstat_cache(void);
 
 extern struct alternate_object_database {
 	struct alternate_object_database *next;
@@ -937,7 +941,6 @@ extern int ws_fix_copy(char *, const char *, int, unsigned, int *);
 extern int ws_blank_line(const char *line, int len, unsigned ws_rule);
 
 /* ls-files */
-int pathspec_match(const char **spec, char *matched, const char *filename, int skiplen);
 int report_path_error(const char *ps_matched, const char **pathspec, int prefix_offset);
 void overlay_tree_on_cache(const char *tree_name, const char *prefix);
 
diff --git a/color.c b/color.c
index 915d7a97f6..db4dccfb77 100644
--- a/color.c
+++ b/color.c
@@ -202,3 +202,31 @@ int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...)
 	va_end(args);
 	return r;
 }
+
+/*
+ * This function splits the buffer by newlines and colors the lines individually.
+ *
+ * Returns 0 on success.
+ */
+int color_fwrite_lines(FILE *fp, const char *color,
+		size_t count, const char *buf)
+{
+	if (!*color)
+		return fwrite(buf, count, 1, fp) != 1;
+	while (count) {
+		char *p = memchr(buf, '\n', count);
+		if (p != buf && (fputs(color, fp) < 0 ||
+				fwrite(buf, p ? p - buf : count, 1, fp) != 1 ||
+				fputs(COLOR_RESET, fp) < 0))
+			return -1;
+		if (!p)
+			return 0;
+		if (fputc('\n', fp) < 0)
+			return -1;
+		count -= p + 1 - buf;
+		buf = p + 1;
+	}
+	return 0;
+}
+
+
diff --git a/color.h b/color.h
index 70660999df..5019df82f7 100644
--- a/color.h
+++ b/color.h
@@ -20,5 +20,6 @@ void color_parse(const char *value, const char *var, char *dst);
 void color_parse_mem(const char *value, int len, const char *var, char *dst);
 int color_fprintf(FILE *fp, const char *color, const char *fmt, ...);
 int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...);
+int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
 
 #endif /* COLOR_H */
diff --git a/diff.c b/diff.c
index 82cff975b3..972b3daa65 100644
--- a/diff.c
+++ b/diff.c
@@ -23,6 +23,7 @@ static int diff_detect_rename_default;
 static int diff_rename_limit_default = 200;
 static int diff_suppress_blank_empty;
 int diff_use_color_default = -1;
+static const char *diff_word_regex_cfg;
 static const char *external_diff_cmd_cfg;
 int diff_auto_refresh_index = 1;
 static int diff_mnemonic_prefix;
@@ -92,6 +93,8 @@ int git_diff_ui_config(const char *var, const char *value, void *cb)
 	}
 	if (!strcmp(var, "diff.external"))
 		return git_config_string(&external_diff_cmd_cfg, var, value);
+	if (!strcmp(var, "diff.wordregex"))
+		return git_config_string(&diff_word_regex_cfg, var, value);
 
 	return git_diff_basic_config(var, value, cb);
 }
@@ -321,82 +324,138 @@ static int fill_mmfile(mmfile_t *mf, struct diff_filespec *one)
 struct diff_words_buffer {
 	mmfile_t text;
 	long alloc;
-	long current; /* output pointer */
-	int suppressed_newline;
+	struct diff_words_orig {
+		const char *begin, *end;
+	} *orig;
+	int orig_nr, orig_alloc;
 };
 
 static void diff_words_append(char *line, unsigned long len,
 		struct diff_words_buffer *buffer)
 {
-	if (buffer->text.size + len > buffer->alloc) {
-		buffer->alloc = (buffer->text.size + len) * 3 / 2;
-		buffer->text.ptr = xrealloc(buffer->text.ptr, buffer->alloc);
-	}
+	ALLOC_GROW(buffer->text.ptr, buffer->text.size + len, buffer->alloc);
 	line++;
 	len--;
 	memcpy(buffer->text.ptr + buffer->text.size, line, len);
 	buffer->text.size += len;
+	buffer->text.ptr[buffer->text.size] = '\0';
 }
 
 struct diff_words_data {
 	struct diff_words_buffer minus, plus;
+	const char *current_plus;
 	FILE *file;
+	regex_t *word_regex;
 };
 
-static void print_word(FILE *file, struct diff_words_buffer *buffer, int len, int color,
-		int suppress_newline)
+static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len)
 {
-	const char *ptr;
-	int eol = 0;
+	struct diff_words_data *diff_words = priv;
+	int minus_first, minus_len, plus_first, plus_len;
+	const char *minus_begin, *minus_end, *plus_begin, *plus_end;
 
-	if (len == 0)
+	if (line[0] != '@' || parse_hunk_header(line, len,
+			&minus_first, &minus_len, &plus_first, &plus_len))
 		return;
 
-	ptr  = buffer->text.ptr + buffer->current;
-	buffer->current += len;
+	/* POSIX requires that first be decremented by one if len == 0... */
+	if (minus_len) {
+		minus_begin = diff_words->minus.orig[minus_first].begin;
+		minus_end =
+			diff_words->minus.orig[minus_first + minus_len - 1].end;
+	} else
+		minus_begin = minus_end =
+			diff_words->minus.orig[minus_first].end;
 
-	if (ptr[len - 1] == '\n') {
-		eol = 1;
-		len--;
+	if (plus_len) {
+		plus_begin = diff_words->plus.orig[plus_first].begin;
+		plus_end = diff_words->plus.orig[plus_first + plus_len - 1].end;
+	} else
+		plus_begin = plus_end = diff_words->plus.orig[plus_first].end;
+
+	if (diff_words->current_plus != plus_begin)
+		fwrite(diff_words->current_plus,
+				plus_begin - diff_words->current_plus, 1,
+				diff_words->file);
+	if (minus_begin != minus_end)
+		color_fwrite_lines(diff_words->file,
+				diff_get_color(1, DIFF_FILE_OLD),
+				minus_end - minus_begin, minus_begin);
+	if (plus_begin != plus_end)
+		color_fwrite_lines(diff_words->file,
+				diff_get_color(1, DIFF_FILE_NEW),
+				plus_end - plus_begin, plus_begin);
+
+	diff_words->current_plus = plus_end;
+}
+
+/* This function starts looking at *begin, and returns 0 iff a word was found. */
+static int find_word_boundaries(mmfile_t *buffer, regex_t *word_regex,
+		int *begin, int *end)
+{
+	if (word_regex && *begin < buffer->size) {
+		regmatch_t match[1];
+		if (!regexec(word_regex, buffer->ptr + *begin, 1, match, 0)) {
+			char *p = memchr(buffer->ptr + *begin + match[0].rm_so,
+					'\n', match[0].rm_eo - match[0].rm_so);
+			*end = p ? p - buffer->ptr : match[0].rm_eo + *begin;
+			*begin += match[0].rm_so;
+			return *begin >= *end;
+		}
+		return -1;
 	}
 
-	fputs(diff_get_color(1, color), file);
-	fwrite(ptr, len, 1, file);
-	fputs(diff_get_color(1, DIFF_RESET), file);
+	/* find the next word */
+	while (*begin < buffer->size && isspace(buffer->ptr[*begin]))
+		(*begin)++;
+	if (*begin >= buffer->size)
+		return -1;
 
-	if (eol) {
-		if (suppress_newline)
-			buffer->suppressed_newline = 1;
-		else
-			putc('\n', file);
-	}
+	/* find the end of the word */
+	*end = *begin + 1;
+	while (*end < buffer->size && !isspace(buffer->ptr[*end]))
+		(*end)++;
+
+	return 0;
 }
 
-static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len)
+/*
+ * This function splits the words in buffer->text, stores the list with
+ * newline separator into out, and saves the offsets of the original words
+ * in buffer->orig.
+ */
+static void diff_words_fill(struct diff_words_buffer *buffer, mmfile_t *out,
+		regex_t *word_regex)
 {
-	struct diff_words_data *diff_words = priv;
+	int i, j;
+	long alloc = 0;
 
-	if (diff_words->minus.suppressed_newline) {
-		if (line[0] != '+')
-			putc('\n', diff_words->file);
-		diff_words->minus.suppressed_newline = 0;
-	}
+	out->size = 0;
+	out->ptr = NULL;
 
-	len--;
-	switch (line[0]) {
-		case '-':
-			print_word(diff_words->file,
-				   &diff_words->minus, len, DIFF_FILE_OLD, 1);
-			break;
-		case '+':
-			print_word(diff_words->file,
-				   &diff_words->plus, len, DIFF_FILE_NEW, 0);
-			break;
-		case ' ':
-			print_word(diff_words->file,
-				   &diff_words->plus, len, DIFF_PLAIN, 0);
-			diff_words->minus.current += len;
-			break;
+	/* fake an empty "0th" word */
+	ALLOC_GROW(buffer->orig, 1, buffer->orig_alloc);
+	buffer->orig[0].begin = buffer->orig[0].end = buffer->text.ptr;
+	buffer->orig_nr = 1;
+
+	for (i = 0; i < buffer->text.size; i++) {
+		if (find_word_boundaries(&buffer->text, word_regex, &i, &j))
+			return;
+
+		/* store original boundaries */
+		ALLOC_GROW(buffer->orig, buffer->orig_nr + 1,
+				buffer->orig_alloc);
+		buffer->orig[buffer->orig_nr].begin = buffer->text.ptr + i;
+		buffer->orig[buffer->orig_nr].end = buffer->text.ptr + j;
+		buffer->orig_nr++;
+
+		/* store one word */
+		ALLOC_GROW(out->ptr, out->size + j - i + 1, alloc);
+		memcpy(out->ptr + out->size, buffer->text.ptr + i, j - i);
+		out->ptr[out->size + j - i] = '\n';
+		out->size += j - i + 1;
+
+		i = j - 1;
 	}
 }
 
@@ -407,38 +466,36 @@ static void diff_words_show(struct diff_words_data *diff_words)
 	xdemitconf_t xecfg;
 	xdemitcb_t ecb;
 	mmfile_t minus, plus;
-	int i;
+
+	/* special case: only removal */
+	if (!diff_words->plus.text.size) {
+		color_fwrite_lines(diff_words->file,
+			diff_get_color(1, DIFF_FILE_OLD),
+			diff_words->minus.text.size, diff_words->minus.text.ptr);
+		diff_words->minus.text.size = 0;
+		return;
+	}
+
+	diff_words->current_plus = diff_words->plus.text.ptr;
 
 	memset(&xpp, 0, sizeof(xpp));
 	memset(&xecfg, 0, sizeof(xecfg));
-	minus.size = diff_words->minus.text.size;
-	minus.ptr = xmalloc(minus.size);
-	memcpy(minus.ptr, diff_words->minus.text.ptr, minus.size);
-	for (i = 0; i < minus.size; i++)
-		if (isspace(minus.ptr[i]))
-			minus.ptr[i] = '\n';
-	diff_words->minus.current = 0;
-
-	plus.size = diff_words->plus.text.size;
-	plus.ptr = xmalloc(plus.size);
-	memcpy(plus.ptr, diff_words->plus.text.ptr, plus.size);
-	for (i = 0; i < plus.size; i++)
-		if (isspace(plus.ptr[i]))
-			plus.ptr[i] = '\n';
-	diff_words->plus.current = 0;
-
+	diff_words_fill(&diff_words->minus, &minus, diff_words->word_regex);
+	diff_words_fill(&diff_words->plus, &plus, diff_words->word_regex);
 	xpp.flags = XDF_NEED_MINIMAL;
-	xecfg.ctxlen = diff_words->minus.alloc + diff_words->plus.alloc;
+	/* as only the hunk header will be parsed, we need a 0-context */
+	xecfg.ctxlen = 0;
 	xdi_diff_outf(&minus, &plus, fn_out_diff_words_aux, diff_words,
 		      &xpp, &xecfg, &ecb);
 	free(minus.ptr);
 	free(plus.ptr);
+	if (diff_words->current_plus != diff_words->plus.text.ptr +
+			diff_words->plus.text.size)
+		fwrite(diff_words->current_plus,
+			diff_words->plus.text.ptr + diff_words->plus.text.size
+			- diff_words->current_plus, 1,
+			diff_words->file);
 	diff_words->minus.text.size = diff_words->plus.text.size = 0;
-
-	if (diff_words->minus.suppressed_newline) {
-		putc('\n', diff_words->file);
-		diff_words->minus.suppressed_newline = 0;
-	}
 }
 
 typedef unsigned long (*sane_truncate_fn)(char *line, unsigned long len);
@@ -462,7 +519,10 @@ static void free_diff_words_data(struct emit_callback *ecbdata)
 			diff_words_show(ecbdata->diff_words);
 
 		free (ecbdata->diff_words->minus.text.ptr);
+		free (ecbdata->diff_words->minus.orig);
 		free (ecbdata->diff_words->plus.text.ptr);
+		free (ecbdata->diff_words->plus.orig);
+		free(ecbdata->diff_words->word_regex);
 		free(ecbdata->diff_words);
 		ecbdata->diff_words = NULL;
 	}
@@ -1325,6 +1385,12 @@ static const struct userdiff_funcname *diff_funcname_pattern(struct diff_filespe
 	return one->driver->funcname.pattern ? &one->driver->funcname : NULL;
 }
 
+static const char *userdiff_word_regex(struct diff_filespec *one)
+{
+	diff_filespec_load_driver(one);
+	return one->driver->word_regex;
+}
+
 void diff_set_mnemonic_prefix(struct diff_options *options, const char *a, const char *b)
 {
 	if (!options->a_prefix)
@@ -1485,6 +1551,21 @@ static void builtin_diff(const char *name_a,
 			ecbdata.diff_words =
 				xcalloc(1, sizeof(struct diff_words_data));
 			ecbdata.diff_words->file = o->file;
+			if (!o->word_regex)
+				o->word_regex = userdiff_word_regex(one);
+			if (!o->word_regex)
+				o->word_regex = userdiff_word_regex(two);
+			if (!o->word_regex)
+				o->word_regex = diff_word_regex_cfg;
+			if (o->word_regex) {
+				ecbdata.diff_words->word_regex = (regex_t *)
+					xmalloc(sizeof(regex_t));
+				if (regcomp(ecbdata.diff_words->word_regex,
+						o->word_regex,
+						REG_EXTENDED | REG_NEWLINE))
+					die ("Invalid regular expression: %s",
+							o->word_regex);
+			}
 		}
 		xdi_diff_outf(&mf1, &mf2, fn_out_consume, &ecbdata,
 			      &xpp, &xecfg, &ecb);
@@ -2498,6 +2579,10 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 		DIFF_OPT_CLR(options, COLOR_DIFF);
 	else if (!strcmp(arg, "--color-words"))
 		options->flags |= DIFF_OPT_COLOR_DIFF | DIFF_OPT_COLOR_DIFF_WORDS;
+	else if (!prefixcmp(arg, "--color-words=")) {
+		options->flags |= DIFF_OPT_COLOR_DIFF | DIFF_OPT_COLOR_DIFF_WORDS;
+		options->word_regex = arg + 14;
+	}
 	else if (!strcmp(arg, "--exit-code"))
 		DIFF_OPT_SET(options, EXIT_WITH_STATUS);
 	else if (!strcmp(arg, "--quiet"))
diff --git a/diff.h b/diff.h
index 4d5a32781d..23cd90c2e6 100644
--- a/diff.h
+++ b/diff.h
@@ -98,6 +98,7 @@ struct diff_options {
 
 	int stat_width;
 	int stat_name_width;
+	const char *word_regex;
 
 	/* this is set by diffcore for DIFF_FORMAT_PATCH */
 	int found_changes;
diff --git a/dir.c b/dir.c
index d55a41a5ab..cfd1ea587d 100644
--- a/dir.c
+++ b/dir.c
@@ -108,25 +108,28 @@ static int match_one(const char *match, const char *name, int namelen)
  * and a mark is left in seen[] array for pathspec element that
  * actually matched anything.
  */
-int match_pathspec(const char **pathspec, const char *name, int namelen, int prefix, char *seen)
+int match_pathspec(const char **pathspec, const char *name, int namelen,
+		int prefix, char *seen)
 {
-	int retval;
-	const char *match;
+	int i, retval = 0;
+
+	if (!pathspec)
+		return 1;
 
 	name += prefix;
 	namelen -= prefix;
 
-	for (retval = 0; (match = *pathspec++) != NULL; seen++) {
+	for (i = 0; pathspec[i] != NULL; i++) {
 		int how;
-		if (retval && *seen == MATCHED_EXACTLY)
+		const char *match = pathspec[i] + prefix;
+		if (seen && seen[i] == MATCHED_EXACTLY)
 			continue;
-		match += prefix;
 		how = match_one(match, name, namelen);
 		if (how) {
 			if (retval < how)
 				retval = how;
-			if (*seen < how)
-				*seen = how;
+			if (seen && seen[i] < how)
+				seen[i] = how;
 		}
 	}
 	return retval;
diff --git a/entry.c b/entry.c
index 5f24816eb9..05aa58d348 100644
--- a/entry.c
+++ b/entry.c
@@ -9,35 +9,25 @@ static void create_directories(const char *path, const struct checkout *state)
 	const char *slash = path;
 
 	while ((slash = strchr(slash+1, '/')) != NULL) {
-		struct stat st;
-		int stat_status;
-
 		len = slash - path;
 		memcpy(buf, path, len);
 		buf[len] = 0;
 
-		if (len <= state->base_dir_len)
-			/*
-			 * checkout-index --prefix=<dir>; <dir> is
-			 * allowed to be a symlink to an existing
-			 * directory.
-			 */
-			stat_status = stat(buf, &st);
-		else
-			/*
-			 * if there currently is a symlink, we would
-			 * want to replace it with a real directory.
-			 */
-			stat_status = lstat(buf, &st);
-
-		if (!stat_status && S_ISDIR(st.st_mode))
+		/*
+		 * For 'checkout-index --prefix=<dir>', <dir> is
+		 * allowed to be a symlink to an existing directory,
+		 * and we set 'state->base_dir_len' below, such that
+		 * we test the path components of the prefix with the
+		 * stat() function instead of the lstat() function.
+		 */
+		if (has_dirs_only_path(len, buf, state->base_dir_len))
 			continue; /* ok, it is already a directory. */
 
 		/*
-		 * We know stat_status == 0 means something exists
-		 * there and this mkdir would fail, but that is an
-		 * error codepath; we do not care, as we unlink and
-		 * mkdir again in such a case.
+		 * If this mkdir() would fail, it could be that there
+		 * is already a symlink or something else exists
+		 * there, therefore we then try to unlink it and try
+		 * one more time to create the directory.
 		 */
 		if (mkdir(buf, 0777)) {
 			if (errno == EEXIST && state->force &&
diff --git a/git-rebase--interactive.sh b/git-rebase--interactive.sh
index 21ac20c305..002929eb09 100755
--- a/git-rebase--interactive.sh
+++ b/git-rebase--interactive.sh
@@ -571,7 +571,8 @@ first and then run 'git rebase --continue' again."
 		;;
 	--)
 		shift
-		test ! -z "$REBASE_ROOT" -o $# -eq 1 -o $# -eq 2 || usage
+		test -z "$REBASE_ROOT" -a $# -ge 1 -a $# -le 2 ||
+		test ! -z "$REBASE_ROOT" -a $# -le 1 || usage
 		test -d "$DOTEST" &&
 			die "Interactive rebase already started"
 
diff --git a/http-push.c b/http-push.c
index eca4a8e5e9..59037df502 100644
--- a/http-push.c
+++ b/http-push.c
@@ -184,21 +184,22 @@ enum dav_header_flag {
 	DAV_HEADER_TIMEOUT = (1u << 2)
 };
 
-static struct curl_slist *get_dav_token_headers(struct remote_lock *lock, enum dav_header_flag options) {
+static struct curl_slist *get_dav_token_headers(struct remote_lock *lock, enum dav_header_flag options)
+{
 	struct strbuf buf = STRBUF_INIT;
 	struct curl_slist *dav_headers = NULL;
 
-	if(options & DAV_HEADER_IF) {
+	if (options & DAV_HEADER_IF) {
 		strbuf_addf(&buf, "If: (<%s>)", lock->token);
 		dav_headers = curl_slist_append(dav_headers, buf.buf);
 		strbuf_reset(&buf);
 	}
-	if(options & DAV_HEADER_LOCK) {
+	if (options & DAV_HEADER_LOCK) {
 		strbuf_addf(&buf, "Lock-Token: <%s>", lock->token);
 		dav_headers = curl_slist_append(dav_headers, buf.buf);
 		strbuf_reset(&buf);
 	}
-	if(options & DAV_HEADER_TIMEOUT) {
+	if (options & DAV_HEADER_TIMEOUT) {
 		strbuf_addf(&buf, "Timeout: Second-%ld", lock->timeout);
 		dav_headers = curl_slist_append(dav_headers, buf.buf);
 		strbuf_reset(&buf);
diff --git a/object.c b/object.c
index 50b6528001..7e6a92c88e 100644
--- a/object.c
+++ b/object.c
@@ -268,3 +268,22 @@ void add_object_array_with_mode(struct object *obj, const char *name, struct obj
 	objects[nr].mode = mode;
 	array->nr = ++nr;
 }
+
+void object_array_remove_duplicates(struct object_array *array)
+{
+	int ref, src, dst;
+	struct object_array_entry *objects = array->objects;
+
+	for (ref = 0; ref < array->nr - 1; ref++) {
+		for (src = ref + 1, dst = src;
+		     src < array->nr;
+		     src++) {
+			if (!strcmp(objects[ref].name, objects[src].name))
+				continue;
+			if (src != dst)
+				objects[dst] = objects[src];
+			dst++;
+		}
+		array->nr = dst;
+	}
+}
diff --git a/object.h b/object.h
index d962ff11d1..89dd0c47a6 100644
--- a/object.h
+++ b/object.h
@@ -82,5 +82,6 @@ int object_list_contains(struct object_list *list, struct object *obj);
 /* Object array handling .. */
 void add_object_array(struct object *obj, const char *name, struct object_array *array);
 void add_object_array_with_mode(struct object *obj, const char *name, struct object_array *array, unsigned mode);
+void object_array_remove_duplicates(struct object_array *);
 
 #endif /* OBJECT_H */
diff --git a/revision.c b/revision.c
index db60f06c98..b0651845bf 100644
--- a/revision.c
+++ b/revision.c
@@ -1263,6 +1263,7 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
 
 			if (!strcmp(arg, "--all")) {
 				handle_refs(revs, flags, for_each_ref);
+				handle_refs(revs, flags, head_ref);
 				continue;
 			}
 			if (!strcmp(arg, "--branches")) {
diff --git a/symlinks.c b/symlinks.c
index 5a5e781a15..f262b7c44b 100644
--- a/symlinks.c
+++ b/symlinks.c
@@ -1,64 +1,241 @@
 #include "cache.h"
 
-struct pathname {
+static struct cache_def {
+	char path[PATH_MAX + 1];
 	int len;
-	char path[PATH_MAX];
-};
+	int flags;
+	int track_flags;
+	int prefix_len_stat_func;
+} cache;
 
-/* Return matching pathname prefix length, or zero if not matching */
-static inline int match_pathname(int len, const char *name, struct pathname *match)
+/*
+ * Returns the length (on a path component basis) of the longest
+ * common prefix match of 'name' and the cached path string.
+ */
+static inline int longest_match_lstat_cache(int len, const char *name,
+					    int *previous_slash)
 {
-	int match_len = match->len;
-	return (len > match_len &&
-		name[match_len] == '/' &&
-		!memcmp(name, match->path, match_len)) ? match_len : 0;
+	int max_len, match_len = 0, match_len_prev = 0, i = 0;
+
+	max_len = len < cache.len ? len : cache.len;
+	while (i < max_len && name[i] == cache.path[i]) {
+		if (name[i] == '/') {
+			match_len_prev = match_len;
+			match_len = i;
+		}
+		i++;
+	}
+	/* Is the cached path string a substring of 'name'? */
+	if (i == cache.len && cache.len < len && name[cache.len] == '/') {
+		match_len_prev = match_len;
+		match_len = cache.len;
+	/* Is 'name' a substring of the cached path string? */
+	} else if ((i == len && len < cache.len && cache.path[len] == '/') ||
+		   (i == len && len == cache.len)) {
+		match_len_prev = match_len;
+		match_len = len;
+	}
+	*previous_slash = match_len_prev;
+	return match_len;
 }
 
-static inline void set_pathname(int len, const char *name, struct pathname *match)
+static inline void reset_lstat_cache(int track_flags, int prefix_len_stat_func)
 {
-	if (len < PATH_MAX) {
-		match->len = len;
-		memcpy(match->path, name, len);
-		match->path[len] = 0;
-	}
+	cache.path[0] = '\0';
+	cache.len = 0;
+	cache.flags = 0;
+	cache.track_flags = track_flags;
+	cache.prefix_len_stat_func = prefix_len_stat_func;
 }
 
-int has_symlink_leading_path(int len, const char *name)
+#define FL_DIR      (1 << 0)
+#define FL_NOENT    (1 << 1)
+#define FL_SYMLINK  (1 << 2)
+#define FL_LSTATERR (1 << 3)
+#define FL_ERR      (1 << 4)
+#define FL_FULLPATH (1 << 5)
+
+/*
+ * Check if name 'name' of length 'len' has a symlink leading
+ * component, or if the directory exists and is real, or not.
+ *
+ * To speed up the check, some information is allowed to be cached.
+ * This can be indicated by the 'track_flags' argument, which also can
+ * be used to indicate that we should check the full path.
+ *
+ * The 'prefix_len_stat_func' parameter can be used to set the length
+ * of the prefix, where the cache should use the stat() function
+ * instead of the lstat() function to test each path component.
+ */
+static int lstat_cache(int len, const char *name,
+		       int track_flags, int prefix_len_stat_func)
 {
-	static struct pathname link, nonlink;
-	char path[PATH_MAX];
+	int match_len, last_slash, last_slash_dir, previous_slash;
+	int match_flags, ret_flags, save_flags, max_len, ret;
 	struct stat st;
-	char *sp;
-	int known_dir;
 
-	/*
-	 * See if the last known symlink cache matches.
-	 */
-	if (match_pathname(len, name, &link))
-		return 1;
+	if (cache.track_flags != track_flags ||
+	    cache.prefix_len_stat_func != prefix_len_stat_func) {
+		/*
+		 * As a safeguard we clear the cache if the values of
+		 * track_flags and/or prefix_len_stat_func does not
+		 * match with the last supplied values.
+		 */
+		reset_lstat_cache(track_flags, prefix_len_stat_func);
+		match_len = last_slash = 0;
+	} else {
+		/*
+		 * Check to see if we have a match from the cache for
+		 * the 2 "excluding" path types.
+		 */
+		match_len = last_slash =
+			longest_match_lstat_cache(len, name, &previous_slash);
+		match_flags = cache.flags & track_flags & (FL_NOENT|FL_SYMLINK);
+		if (match_flags && match_len == cache.len)
+			return match_flags;
+		/*
+		 * If we now have match_len > 0, we would know that
+		 * the matched part will always be a directory.
+		 *
+		 * Also, if we are tracking directories and 'name' is
+		 * a substring of the cache on a path component basis,
+		 * we can return immediately.
+		 */
+		match_flags = track_flags & FL_DIR;
+		if (match_flags && len == match_len)
+			return match_flags;
+	}
 
 	/*
-	 * Get rid of the last known directory part
+	 * Okay, no match from the cache so far, so now we have to
+	 * check the rest of the path components.
 	 */
-	known_dir = match_pathname(len, name, &nonlink);
-
-	while ((sp = strchr(name + known_dir + 1, '/')) != NULL) {
-		int thislen = sp - name ;
-		memcpy(path, name, thislen);
-		path[thislen] = 0;
-
-		if (lstat(path, &st))
-			return 0;
-		if (S_ISDIR(st.st_mode)) {
-			set_pathname(thislen, path, &nonlink);
-			known_dir = thislen;
+	ret_flags = FL_DIR;
+	last_slash_dir = last_slash;
+	max_len = len < PATH_MAX ? len : PATH_MAX;
+	while (match_len < max_len) {
+		do {
+			cache.path[match_len] = name[match_len];
+			match_len++;
+		} while (match_len < max_len && name[match_len] != '/');
+		if (match_len >= max_len && !(track_flags & FL_FULLPATH))
+			break;
+		last_slash = match_len;
+		cache.path[last_slash] = '\0';
+
+		if (last_slash <= prefix_len_stat_func)
+			ret = stat(cache.path, &st);
+		else
+			ret = lstat(cache.path, &st);
+
+		if (ret) {
+			ret_flags = FL_LSTATERR;
+			if (errno == ENOENT)
+				ret_flags |= FL_NOENT;
+		} else if (S_ISDIR(st.st_mode)) {
+			last_slash_dir = last_slash;
 			continue;
-		}
-		if (S_ISLNK(st.st_mode)) {
-			set_pathname(thislen, path, &link);
-			return 1;
+		} else if (S_ISLNK(st.st_mode)) {
+			ret_flags = FL_SYMLINK;
+		} else {
+			ret_flags = FL_ERR;
 		}
 		break;
 	}
-	return 0;
+
+	/*
+	 * At the end update the cache.  Note that max 3 different
+	 * path types, FL_NOENT, FL_SYMLINK and FL_DIR, can be cached
+	 * for the moment!
+	 */
+	save_flags = ret_flags & track_flags & (FL_NOENT|FL_SYMLINK);
+	if (save_flags && last_slash > 0 && last_slash <= PATH_MAX) {
+		cache.path[last_slash] = '\0';
+		cache.len = last_slash;
+		cache.flags = save_flags;
+	} else if (track_flags & FL_DIR &&
+		   last_slash_dir > 0 && last_slash_dir <= PATH_MAX) {
+		/*
+		 * We have a separate test for the directory case,
+		 * since it could be that we have found a symlink or a
+		 * non-existing directory and the track_flags says
+		 * that we cannot cache this fact, so the cache would
+		 * then have been left empty in this case.
+		 *
+		 * But if we are allowed to track real directories, we
+		 * can still cache the path components before the last
+		 * one (the found symlink or non-existing component).
+		 */
+		cache.path[last_slash_dir] = '\0';
+		cache.len = last_slash_dir;
+		cache.flags = FL_DIR;
+	} else {
+		reset_lstat_cache(track_flags, prefix_len_stat_func);
+	}
+	return ret_flags;
+}
+
+/*
+ * Invalidate the given 'name' from the cache, if 'name' matches
+ * completely with the cache.
+ */
+void invalidate_lstat_cache(int len, const char *name)
+{
+	int match_len, previous_slash;
+
+	match_len = longest_match_lstat_cache(len, name, &previous_slash);
+	if (len == match_len) {
+		if ((cache.track_flags & FL_DIR) && previous_slash > 0) {
+			cache.path[previous_slash] = '\0';
+			cache.len = previous_slash;
+			cache.flags = FL_DIR;
+		} else
+			reset_lstat_cache(cache.track_flags,
+					  cache.prefix_len_stat_func);
+	}
+}
+
+/*
+ * Completely clear the contents of the cache
+ */
+void clear_lstat_cache(void)
+{
+	reset_lstat_cache(0, 0);
+}
+
+#define USE_ONLY_LSTAT  0
+
+/*
+ * Return non-zero if path 'name' has a leading symlink component
+ */
+int has_symlink_leading_path(int len, const char *name)
+{
+	return lstat_cache(len, name,
+			   FL_SYMLINK|FL_DIR, USE_ONLY_LSTAT) &
+		FL_SYMLINK;
+}
+
+/*
+ * Return non-zero if path 'name' has a leading symlink component or
+ * if some leading path component does not exists.
+ */
+int has_symlink_or_noent_leading_path(int len, const char *name)
+{
+	return lstat_cache(len, name,
+			   FL_SYMLINK|FL_NOENT|FL_DIR, USE_ONLY_LSTAT) &
+		(FL_SYMLINK|FL_NOENT);
+}
+
+/*
+ * Return non-zero if all path components of 'name' exists as a
+ * directory.  If prefix_len > 0, we will test with the stat()
+ * function instead of the lstat() function for a prefix length of
+ * 'prefix_len', thus we then allow for symlinks in the prefix part as
+ * long as those points to real existing directories.
+ */
+int has_dirs_only_path(int len, const char *name, int prefix_len)
+{
+	return lstat_cache(len, name,
+			   FL_DIR|FL_FULLPATH, prefix_len) &
+		FL_DIR;
 }
diff --git a/t/t4034-diff-words.sh b/t/t4034-diff-words.sh
new file mode 100755
index 0000000000..4508effcaa
--- /dev/null
+++ b/t/t4034-diff-words.sh
@@ -0,0 +1,200 @@
+#!/bin/sh
+
+test_description='word diff colors'
+
+. ./test-lib.sh
+
+test_expect_success setup '
+
+	git config diff.color.old red
+	git config diff.color.new green
+
+'
+
+decrypt_color () {
+	sed \
+		-e 's/.\[1m/<WHITE>/g' \
+		-e 's/.\[31m/<RED>/g' \
+		-e 's/.\[32m/<GREEN>/g' \
+		-e 's/.\[36m/<BROWN>/g' \
+		-e 's/.\[m/<RESET>/g'
+}
+
+word_diff () {
+	test_must_fail git diff --no-index "$@" pre post > output &&
+	decrypt_color < output > output.decrypted &&
+	test_cmp expect output.decrypted
+}
+
+cat > pre <<\EOF
+h(4)
+
+a = b + c
+EOF
+
+cat > post <<\EOF
+h(4),hh[44]
+
+a = b + c
+
+aa = a
+
+aeff = aeff * ( aaa )
+EOF
+
+cat > expect <<\EOF
+<WHITE>diff --git a/pre b/post<RESET>
+<WHITE>index 330b04f..5ed8eff 100644<RESET>
+<WHITE>--- a/pre<RESET>
+<WHITE>+++ b/post<RESET>
+<BROWN>@@ -1,3 +1,7 @@<RESET>
+<RED>h(4)<RESET><GREEN>h(4),hh[44]<RESET>
+<RESET>
+a = b + c<RESET>
+
+<GREEN>aa = a<RESET>
+
+<GREEN>aeff = aeff * ( aaa )<RESET>
+EOF
+
+test_expect_success 'word diff with runs of whitespace' '
+
+	word_diff --color-words
+
+'
+
+cat > expect <<\EOF
+<WHITE>diff --git a/pre b/post<RESET>
+<WHITE>index 330b04f..5ed8eff 100644<RESET>
+<WHITE>--- a/pre<RESET>
+<WHITE>+++ b/post<RESET>
+<BROWN>@@ -1,3 +1,7 @@<RESET>
+h(4),<GREEN>hh<RESET>[44]
+<RESET>
+a = b + c<RESET>
+
+<GREEN>aa = a<RESET>
+
+<GREEN>aeff = aeff * ( aaa<RESET> )
+EOF
+cp expect expect.letter-runs-are-words
+
+test_expect_success 'word diff with a regular expression' '
+
+	word_diff --color-words="[a-z]+"
+
+'
+
+test_expect_success 'set a diff driver' '
+	git config diff.testdriver.wordRegex "[^[:space:]]" &&
+	cat <<EOF > .gitattributes
+pre diff=testdriver
+post diff=testdriver
+EOF
+'
+
+test_expect_success 'option overrides .gitattributes' '
+
+	word_diff --color-words="[a-z]+"
+
+'
+
+cat > expect <<\EOF
+<WHITE>diff --git a/pre b/post<RESET>
+<WHITE>index 330b04f..5ed8eff 100644<RESET>
+<WHITE>--- a/pre<RESET>
+<WHITE>+++ b/post<RESET>
+<BROWN>@@ -1,3 +1,7 @@<RESET>
+h(4)<GREEN>,hh[44]<RESET>
+<RESET>
+a = b + c<RESET>
+
+<GREEN>aa = a<RESET>
+
+<GREEN>aeff = aeff * ( aaa )<RESET>
+EOF
+cp expect expect.non-whitespace-is-word
+
+test_expect_success 'use regex supplied by driver' '
+
+	word_diff --color-words
+
+'
+
+test_expect_success 'set diff.wordRegex option' '
+	git config diff.wordRegex "[[:alnum:]]+"
+'
+
+cp expect.letter-runs-are-words expect
+
+test_expect_success 'command-line overrides config' '
+	word_diff --color-words="[a-z]+"
+'
+
+cp expect.non-whitespace-is-word expect
+
+test_expect_success '.gitattributes override config' '
+	word_diff --color-words
+'
+
+test_expect_success 'remove diff driver regex' '
+	git config --unset diff.testdriver.wordRegex
+'
+
+cat > expect <<\EOF
+<WHITE>diff --git a/pre b/post<RESET>
+<WHITE>index 330b04f..5ed8eff 100644<RESET>
+<WHITE>--- a/pre<RESET>
+<WHITE>+++ b/post<RESET>
+<BROWN>@@ -1,3 +1,7 @@<RESET>
+h(4),<GREEN>hh[44<RESET>]
+<RESET>
+a = b + c<RESET>
+
+<GREEN>aa = a<RESET>
+
+<GREEN>aeff = aeff * ( aaa<RESET> )
+EOF
+
+test_expect_success 'use configured regex' '
+	word_diff --color-words
+'
+
+echo 'aaa (aaa)' > pre
+echo 'aaa (aaa) aaa' > post
+
+cat > expect <<\EOF
+<WHITE>diff --git a/pre b/post<RESET>
+<WHITE>index c29453b..be22f37 100644<RESET>
+<WHITE>--- a/pre<RESET>
+<WHITE>+++ b/post<RESET>
+<BROWN>@@ -1 +1 @@<RESET>
+aaa (aaa) <GREEN>aaa<RESET>
+EOF
+
+test_expect_success 'test parsing words for newline' '
+
+	word_diff --color-words="a+"
+
+
+'
+
+echo '(:' > pre
+echo '(' > post
+
+cat > expect <<\EOF
+<WHITE>diff --git a/pre b/post<RESET>
+<WHITE>index 289cb9d..2d06f37 100644<RESET>
+<WHITE>--- a/pre<RESET>
+<WHITE>+++ b/post<RESET>
+<BROWN>@@ -1 +1 @@<RESET>
+(<RED>:<RESET>
+EOF
+
+test_expect_success 'test when words are only removed at the end' '
+
+	word_diff --color-words=.
+
+'
+
+test_done
diff --git a/t/t5701-clone-local.sh b/t/t5701-clone-local.sh
index 8dfaaa456e..3559d17964 100755
--- a/t/t5701-clone-local.sh
+++ b/t/t5701-clone-local.sh
@@ -11,8 +11,8 @@ test_expect_success 'preparing origin repository' '
 	git clone --bare . x &&
 	test "$(GIT_CONFIG=a.git/config git config --bool core.bare)" = true &&
 	test "$(GIT_CONFIG=x/config git config --bool core.bare)" = true
-	git bundle create b1.bundle --all HEAD &&
-	git bundle create b2.bundle --all &&
+	git bundle create b1.bundle --all &&
+	git bundle create b2.bundle master &&
 	mkdir dir &&
 	cp b1.bundle dir/b3
 	cp b1.bundle b4
@@ -116,4 +116,20 @@ test_expect_success 'bundle clone with nonexistent HEAD' '
 	test ! -e .git/refs/heads/master
 '
 
+test_expect_success 'clone empty repository' '
+	cd "$D" &&
+	mkdir empty &&
+	(cd empty && git init) &&
+	git clone empty empty-clone &&
+	test_tick &&
+	(cd empty-clone
+	 echo "content" >> foo &&
+	 git add foo &&
+	 git commit -m "Initial commit" &&
+	 git push origin master &&
+	 expected=$(git rev-parse master) &&
+	 actual=$(git --git-dir=../empty/.git rev-parse master) &&
+	 test $actual = $expected)
+'
+
 test_done
diff --git a/t/t6014-rev-list-all.sh b/t/t6014-rev-list-all.sh
new file mode 100755
index 0000000000..991ab4a65b
--- /dev/null
+++ b/t/t6014-rev-list-all.sh
@@ -0,0 +1,38 @@
+#!/bin/sh
+
+test_description='--all includes detached HEADs'
+
+. ./test-lib.sh
+
+
+commit () {
+	test_tick &&
+	echo $1 > foo &&
+	git add foo &&
+	git commit -m "$1"
+}
+
+test_expect_success 'setup' '
+
+	commit one &&
+	commit two &&
+	git checkout HEAD^ &&
+	commit detached
+
+'
+
+test_expect_success 'rev-list --all lists detached HEAD' '
+
+	test 3 = $(git rev-list --all | wc -l)
+
+'
+
+test_expect_success 'repack does not lose detached HEAD' '
+
+	git gc &&
+	git prune --expire=now &&
+	git show HEAD
+
+'
+
+test_done
diff --git a/unpack-trees.c b/unpack-trees.c
index 15c9ef592b..16bc2ca9eb 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -61,7 +61,7 @@ static void unlink_entry(struct cache_entry *ce)
 	char *cp, *prev;
 	char *name = ce->name;
 
-	if (has_symlink_leading_path(ce_namelen(ce), ce->name))
+	if (has_symlink_or_noent_leading_path(ce_namelen(ce), ce->name))
 		return;
 	if (unlink(name))
 		return;
@@ -580,7 +580,7 @@ static int verify_absent(struct cache_entry *ce, const char *action,
 	if (o->index_only || o->reset || !o->update)
 		return 0;
 
-	if (has_symlink_leading_path(ce_namelen(ce), ce->name))
+	if (has_symlink_or_noent_leading_path(ce_namelen(ce), ce->name))
 		return 0;
 
 	if (!lstat(ce->name, &st)) {
diff --git a/userdiff.c b/userdiff.c
index 3681062ebf..d556da9751 100644
--- a/userdiff.c
+++ b/userdiff.c
@@ -6,14 +6,20 @@ static struct userdiff_driver *drivers;
 static int ndrivers;
 static int drivers_alloc;
 
-#define FUNCNAME(name, pattern) \
-	{ name, NULL, -1, { pattern, REG_EXTENDED } }
+#define PATTERNS(name, pattern, word_regex)			\
+	{ name, NULL, -1, { pattern, REG_EXTENDED }, word_regex }
 static struct userdiff_driver builtin_drivers[] = {
-FUNCNAME("html", "^[ \t]*(<[Hh][1-6][ \t].*>.*)$"),
-FUNCNAME("java",
+PATTERNS("html", "^[ \t]*(<[Hh][1-6][ \t].*>.*)$",
+	 "[^<>= \t]+|[^[:space:]]|[\x80-\xff]+"),
+PATTERNS("java",
 	 "!^[ \t]*(catch|do|for|if|instanceof|new|return|switch|throw|while)\n"
-	 "^[ \t]*(([ \t]*[A-Za-z_][A-Za-z_0-9]*){2,}[ \t]*\\([^;]*)$"),
-FUNCNAME("objc",
+	 "^[ \t]*(([ \t]*[A-Za-z_][A-Za-z_0-9]*){2,}[ \t]*\\([^;]*)$",
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
+	 "|[-+*/<>%&^|=!]="
+	 "|--|\\+\\+|<<=?|>>>?=?|&&|\\|\\|"
+	 "|[^[:space:]]|[\x80-\xff]+"),
+PATTERNS("objc",
 	 /* Negate C statements that can look like functions */
 	 "!^[ \t]*(do|for|if|else|return|switch|while)\n"
 	 /* Objective-C methods */
@@ -21,20 +27,60 @@ FUNCNAME("objc",
 	 /* C functions */
 	 "^[ \t]*(([ \t]*[A-Za-z_][A-Za-z_0-9]*){2,}[ \t]*\\([^;]*)$\n"
 	 /* Objective-C class/protocol definitions */
-	 "^(@(implementation|interface|protocol)[ \t].*)$"),
-FUNCNAME("pascal",
+	 "^(@(implementation|interface|protocol)[ \t].*)$",
+	 /* -- */
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
+	 "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"
+	 "|[^[:space:]]|[\x80-\xff]+"),
+PATTERNS("pascal",
 	 "^((procedure|function|constructor|destructor|interface|"
 		"implementation|initialization|finalization)[ \t]*.*)$"
 	 "\n"
-	 "^(.*=[ \t]*(class|record).*)$"),
-FUNCNAME("php", "^[\t ]*((function|class).*)"),
-FUNCNAME("python", "^[ \t]*((class|def)[ \t].*)$"),
-FUNCNAME("ruby", "^[ \t]*((class|module|def)[ \t].*)$"),
-FUNCNAME("bibtex", "(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$"),
-FUNCNAME("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$"),
+	 "^(.*=[ \t]*(class|record).*)$",
+	 /* -- */
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+"
+	 "|<>|<=|>=|:=|\\.\\."
+	 "|[^[:space:]]|[\x80-\xff]+"),
+PATTERNS("php", "^[\t ]*((function|class).*)",
+	 /* -- */
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+"
+	 "|[-+*/<>%&^|=!.]=|--|\\+\\+|<<=?|>>=?|===|&&|\\|\\||::|->"
+	 "|[^[:space:]]|[\x80-\xff]+"),
+PATTERNS("python", "^[ \t]*((class|def)[ \t].*)$",
+	 /* -- */
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+[jJlL]?|0[xX]?[0-9a-fA-F]+[lL]?"
+	 "|[-+*/<>%&^|=!]=|//=?|<<=?|>>=?|\\*\\*=?"
+	 "|[^[:space:]|[\x80-\xff]+"),
+	 /* -- */
+PATTERNS("ruby", "^[ \t]*((class|module|def)[ \t].*)$",
+	 /* -- */
+	 "(@|@@|\\$)?[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+|\\?(\\\\C-)?(\\\\M-)?."
+	 "|//=?|[-+*/<>%&^|=!]=|<<=?|>>=?|===|\\.{1,3}|::|[!=]~"
+	 "|[^[:space:]|[\x80-\xff]+"),
+PATTERNS("bibtex", "(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$",
+	 "[={}\"]|[^={}\" \t]+"),
+PATTERNS("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$",
+	 "\\\\[a-zA-Z@]+|\\\\.|[a-zA-Z0-9\x80-\xff]+|[^[:space:]]"),
+PATTERNS("cpp",
+	 /* Jump targets or access declarations */
+	 "!^[ \t]*[A-Za-z_][A-Za-z_0-9]*:.*$\n"
+	 /* C/++ functions/methods at top level */
+	 "^([A-Za-z_][A-Za-z_0-9]*([ \t]+[A-Za-z_][A-Za-z_0-9]*([ \t]*::[ \t]*[^[:space:]]+)?){1,}[ \t]*\\([^;]*)$\n"
+	 /* compound type at top level */
+	 "^((struct|class|enum)[^;]*)$",
+	 /* -- */
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
+	 "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"
+	 "|[^[:space:]]|[\x80-\xff]+"),
 { "default", NULL, -1, { NULL, 0 } },
 };
-#undef FUNCNAME
+#undef PATTERNS
 
 static struct userdiff_driver driver_true = {
 	"diff=true",
@@ -134,6 +180,8 @@ int userdiff_config(const char *k, const char *v)
 		return parse_string(&drv->external, k, v);
 	if ((drv = parse_driver(k, v, "textconv")))
 		return parse_string(&drv->textconv, k, v);
+	if ((drv = parse_driver(k, v, "wordregex")))
+		return parse_string(&drv->word_regex, k, v);
 
 	return 0;
 }
diff --git a/userdiff.h b/userdiff.h
index ba2945770b..c3151594f5 100644
--- a/userdiff.h
+++ b/userdiff.h
@@ -11,6 +11,7 @@ struct userdiff_driver {
 	const char *external;
 	int binary;
 	struct userdiff_funcname funcname;
+	const char *word_regex;
 	const char *textconv;
 };