Merge branch 'tb/add-renormalize'

"git add --renormalize ." is a new and safer way to record the fact
that you are correcting the end-of-line convention and other
"convert_to_git()" glitches in the in-repository data.

* tb/add-renormalize:
  add: introduce "--renormalize"

Documentation/git-add.txt

@@ -10,7 +10,7 @@ SYNOPSIS
 [verse]
 'git add' [--verbose | -v] [--dry-run | -n] [--force | -f] [--interactive | -i] [--patch | -p]
 	  [--edit | -e] [--[no-]all | --[no-]ignore-removal | [--update | -u]]
-	  [--intent-to-add | -N] [--refresh] [--ignore-errors] [--ignore-missing]
+	  [--intent-to-add | -N] [--refresh] [--ignore-errors] [--ignore-missing] [--renormalize]
 	  [--chmod=(+|-)x] [--] [<pathspec>...]
 
 DESCRIPTION
@@ -175,6 +175,13 @@ for "git add --no-all <pathspec>...", i.e. ignored removed files.
 	warning (e.g., if you are manually performing operations on
 	submodules).
 
+--renormalize::
+	Apply the "clean" process freshly to all tracked files to
+	forcibly add them again to the index.  This is useful after
+	changing `core.autocrlf` configuration or the `text` attribute
+	in order to correct files added with wrong CRLF/LF line endings.
+	This option implies `-u`.
+
 --chmod=(+|-)x::
 	Override the executable bit of the added files.  The executable
 	bit is only changed in the index, the files on disk are left

Documentation/gitattributes.txt

@@ -232,8 +232,7 @@ From a clean working directory:
 
 -------------------------------------------------
 $ echo "* text=auto" >.gitattributes
-$ git read-tree --empty   # Clean index, force re-scan of working directory
-$ git add .
+$ git add --renormalize .
 $ git status        # Show files that will be normalized
 $ git commit -m "Introduce end-of-line normalization"
 -------------------------------------------------
@@ -328,6 +327,9 @@ You can declare that a filter turns a content that by itself is unusable
 into a usable content by setting the filter.<driver>.required configuration
 variable to `true`.
 
+Note: Whenever the clean filter is changed, the repo should be renormalized:
+$ git add --renormalize .
+
 For example, in .gitattributes, you would assign the `filter`
 attribute for paths.
 

builtin/add.c

@@ -26,6 +26,7 @@ static const char * const builtin_add_usage[] = {
 };
 static int patch_interactive, add_interactive, edit_interactive;
 static int take_worktree_changes;
+static int add_renormalize;
 
 struct update_callback_data {
 	int flags;
@@ -123,6 +124,25 @@ int add_files_to_cache(const char *prefix,
 	return !!data.add_errors;
 }
 
+static int renormalize_tracked_files(const struct pathspec *pathspec, int flags)
+{
+	int i, retval = 0;
+
+	for (i = 0; i < active_nr; i++) {
+		struct cache_entry *ce = active_cache[i];
+
+		if (ce_stage(ce))
+			continue; /* do not touch unmerged paths */
+		if (!S_ISREG(ce->ce_mode) && !S_ISLNK(ce->ce_mode))
+			continue; /* do not touch non blobs */
+		if (pathspec && !ce_path_match(ce, pathspec, NULL))
+			continue;
+		retval |= add_file_to_cache(ce->name, flags | HASH_RENORMALIZE);
+	}
+
+	return retval;
+}
+
 static char *prune_directory(struct dir_struct *dir, struct pathspec *pathspec, int prefix)
 {
 	char *seen;
@@ -276,6 +296,7 @@ static struct option builtin_add_options[] = {
 	OPT_BOOL('e', "edit", &edit_interactive, N_("edit current diff and apply")),
 	OPT__FORCE(&ignored_too, N_("allow adding otherwise ignored files")),
 	OPT_BOOL('u', "update", &take_worktree_changes, N_("update tracked files")),
+	OPT_BOOL(0, "renormalize", &add_renormalize, N_("renormalize EOL of tracked files (implies -u)")),
 	OPT_BOOL('N', "intent-to-add", &intent_to_add, N_("record only the fact that the path will be added later")),
 	OPT_BOOL('A', "all", &addremove_explicit, N_("add changes from all tracked and untracked files")),
 	{ OPTION_CALLBACK, 0, "ignore-removal", &addremove_explicit,
@@ -406,7 +427,7 @@ int cmd_add(int argc, const char **argv, const char *prefix)
 			  chmod_arg[1] != 'x' || chmod_arg[2]))
 		die(_("--chmod param '%s' must be either -x or +x"), chmod_arg);
 
-	add_new_files = !take_worktree_changes && !refresh_only;
+	add_new_files = !take_worktree_changes && !refresh_only && !add_renormalize;
 	require_pathspec = !(take_worktree_changes || (0 < addremove_explicit));
 
 	hold_locked_index(&lock_file, LOCK_DIE_ON_ERROR);
@@ -500,7 +521,10 @@ int cmd_add(int argc, const char **argv, const char *prefix)
 
 	plug_bulk_checkin();
 
-	exit_status |= add_files_to_cache(prefix, &pathspec, flags);
+	if (add_renormalize)
+		exit_status |= renormalize_tracked_files(&pathspec, flags);
+	else
+		exit_status |= add_files_to_cache(prefix, &pathspec, flags);
 
 	if (add_new_files)
 		exit_status |= add_files(&dir, flags);

cache.h

@@ -711,6 +711,7 @@ extern int ie_modified(struct index_state *, const struct cache_entry *, struct
 
 #define HASH_WRITE_OBJECT 1
 #define HASH_FORMAT_CHECK 2
+#define HASH_RENORMALIZE  4
 extern int index_fd(struct object_id *oid, int fd, struct stat *st, enum object_type type, const char *path, unsigned flags);
 extern int index_path(struct object_id *oid, const char *path, struct stat *st, unsigned flags);
 

read-cache.c

@@ -641,13 +641,17 @@ int add_to_index(struct index_state *istate, const char *path, struct stat *st,
 {
 	int size, namelen, was_same;
 	mode_t st_mode = st->st_mode;
-	struct cache_entry *ce, *alias;
+	struct cache_entry *ce, *alias = NULL;
 	unsigned ce_option = CE_MATCH_IGNORE_VALID|CE_MATCH_IGNORE_SKIP_WORKTREE|CE_MATCH_RACY_IS_DIRTY;
 	int verbose = flags & (ADD_CACHE_VERBOSE | ADD_CACHE_PRETEND);
 	int pretend = flags & ADD_CACHE_PRETEND;
 	int intent_only = flags & ADD_CACHE_INTENT;
 	int add_option = (ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE|
 			  (intent_only ? ADD_CACHE_NEW_ONLY : 0));
+	int newflags = HASH_WRITE_OBJECT;
+
+	if (flags & HASH_RENORMALIZE)
+		newflags |= HASH_RENORMALIZE;
 
 	if (!S_ISREG(st_mode) && !S_ISLNK(st_mode) && !S_ISDIR(st_mode))
 		return error("%s: can only add regular files, symbolic links or git-directories", path);
@@ -688,19 +692,23 @@ int add_to_index(struct index_state *istate, const char *path, struct stat *st,
 	if (ignore_case) {
 		adjust_dirname_case(istate, ce->name);
 	}
+	if (!(flags & HASH_RENORMALIZE)) {
+		alias = index_file_exists(istate, ce->name,
+					  ce_namelen(ce), ignore_case);
+		if (alias &&
+		    !ce_stage(alias) &&
+		    !ie_match_stat(istate, alias, st, ce_option)) {
+			/* Nothing changed, really */
+			if (!S_ISGITLINK(alias->ce_mode))
+				ce_mark_uptodate(alias);
+			alias->ce_flags |= CE_ADDED;
 
-	alias = index_file_exists(istate, ce->name, ce_namelen(ce), ignore_case);
-	if (alias && !ce_stage(alias) && !ie_match_stat(istate, alias, st, ce_option)) {
-		/* Nothing changed, really */
-		if (!S_ISGITLINK(alias->ce_mode))
-			ce_mark_uptodate(alias);
-		alias->ce_flags |= CE_ADDED;
-
-		free(ce);
-		return 0;
+			free(ce);
+			return 0;
+		}
 	}
 	if (!intent_only) {
-		if (index_path(&ce->oid, path, st, HASH_WRITE_OBJECT)) {
+		if (index_path(&ce->oid, path, st, newflags)) {
 			free(ce);
 			return error("unable to index file %s", path);
 		}

sha1_file.c

@@ -74,6 +74,18 @@ static struct cached_object *find_cached_object(const unsigned char *sha1)
 	return NULL;
 }
 
+
+static enum safe_crlf get_safe_crlf(unsigned flags)
+{
+	if (flags & HASH_RENORMALIZE)
+		return SAFE_CRLF_RENORMALIZE;
+	else if (flags & HASH_WRITE_OBJECT)
+		return safe_crlf;
+	else
+		return SAFE_CRLF_FALSE;
+}
+
+
 int mkdir_in_gitdir(const char *path)
 {
 	if (mkdir(path, 0777)) {
@@ -1679,7 +1691,7 @@ static int index_mem(struct object_id *oid, void *buf, size_t size,
 	if ((type == OBJ_BLOB) && path) {
 		struct strbuf nbuf = STRBUF_INIT;
 		if (convert_to_git(&the_index, path, buf, size, &nbuf,
-				   write_object ? safe_crlf : SAFE_CRLF_FALSE)) {
+				   get_safe_crlf(flags))) {
 			buf = strbuf_detach(&nbuf, &size);
 			re_allocated = 1;
 		}
@@ -1713,7 +1725,7 @@ static int index_stream_convert_blob(struct object_id *oid, int fd,
 	assert(would_convert_to_git_filter_fd(path));
 
 	convert_to_git_filter_fd(&the_index, path, fd, &sbuf,
-				 write_object ? safe_crlf : SAFE_CRLF_FALSE);
+				 get_safe_crlf(flags));
 
 	if (write_object)
 		ret = write_sha1_file(sbuf.buf, sbuf.len, typename(OBJ_BLOB),

t/t0025-crlf-renormalize.sh

@@ -0,0 +1,30 @@
+#!/bin/sh
+
+test_description='CRLF renormalization'
+
+. ./test-lib.sh
+
+test_expect_success setup '
+	git config core.autocrlf false &&
+	printf "LINEONE\nLINETWO\nLINETHREE\n" >LF.txt &&
+	printf "LINEONE\r\nLINETWO\r\nLINETHREE\r\n" >CRLF.txt &&
+	printf "LINEONE\r\nLINETWO\nLINETHREE\n" >CRLF_mix_LF.txt &&
+	git add . &&
+	git commit -m initial
+'
+
+test_expect_success 'renormalize CRLF in repo' '
+	echo "*.txt text=auto" >.gitattributes &&
+	git add --renormalize "*.txt" &&
+	cat >expect <<-\EOF &&
+	i/lf w/crlf attr/text=auto CRLF.txt
+	i/lf w/lf attr/text=auto LF.txt
+	i/lf w/mixed attr/text=auto CRLF_mix_LF.txt
+	EOF
+	git ls-files --eol |
+	sed -e "s/	/ /g" -e "s/  */ /g" |
+	sort >actual &&
+	test_cmp expect actual
+'
+
+test_done