* This should use the pathname to decide on whether it wants to do some
* more interesting conversions (automatic gzip/unzip, general format
* conversions etc etc), but by default it just does automatic CRLF<->LF
- * translation when the "auto_crlf" option is set.
+ * translation when the "text" attribute or "auto_crlf" option is set.
*/
-#define CRLF_GUESS (-1)
-#define CRLF_BINARY 0
-#define CRLF_TEXT 1
-#define CRLF_INPUT 2
+enum action {
+ CRLF_GUESS = -1,
+ CRLF_BINARY = 0,
+ CRLF_TEXT,
+ CRLF_INPUT,
+ CRLF_CRLF,
+ CRLF_AUTO,
+};
struct text_stat {
/* NUL, CR, LF and CRLF counts */
return 0;
}
-static void check_safe_crlf(const char *path, int action,
+static enum eol determine_output_conversion(enum action action)
+{
+ switch (action) {
+ case CRLF_BINARY:
+ return EOL_UNSET;
+ case CRLF_CRLF:
+ return EOL_CRLF;
+ case CRLF_INPUT:
+ return EOL_LF;
+ case CRLF_GUESS:
+ if (!auto_crlf)
+ return EOL_UNSET;
+ /* fall through */
+ case CRLF_TEXT:
+ case CRLF_AUTO:
+ if (auto_crlf == AUTO_CRLF_TRUE)
+ return EOL_CRLF;
+ else if (auto_crlf == AUTO_CRLF_INPUT)
+ return EOL_LF;
+ else if (eol == EOL_UNSET)
+ return EOL_NATIVE;
+ }
+ return eol;
+}
+
+static void check_safe_crlf(const char *path, enum action action,
struct text_stat *stats, enum safe_crlf checksafe)
{
if (!checksafe)
return;
- if (action == CRLF_INPUT || auto_crlf <= 0) {
+ if (determine_output_conversion(action) == EOL_LF) {
/*
* CRLFs would not be restored by checkout:
* check if we'd remove CRLFs
*/
if (stats->crlf) {
if (checksafe == SAFE_CRLF_WARN)
- warning("CRLF will be replaced by LF in %s.", path);
+ warning("CRLF will be replaced by LF in %s.\nThe file will have its original line endings in your working directory.", path);
else /* i.e. SAFE_CRLF_FAIL */
die("CRLF would be replaced by LF in %s.", path);
}
- } else if (auto_crlf > 0) {
+ } else if (determine_output_conversion(action) == EOL_CRLF) {
/*
* CRLFs would be added by checkout:
* check if we have "naked" LFs
*/
if (stats->lf != stats->crlf) {
if (checksafe == SAFE_CRLF_WARN)
- warning("LF will be replaced by CRLF in %s", path);
+ warning("LF will be replaced by CRLF in %s.\nThe file will have its original line endings in your working directory.", path);
else /* i.e. SAFE_CRLF_FAIL */
die("LF would be replaced by CRLF in %s", path);
}
}
}
+static int has_cr_in_index(const char *path)
+{
+ int pos, len;
+ unsigned long sz;
+ enum object_type type;
+ void *data;
+ int has_cr;
+ struct index_state *istate = &the_index;
+
+ len = strlen(path);
+ pos = index_name_pos(istate, path, len);
+ if (pos < 0) {
+ /*
+ * We might be in the middle of a merge, in which
+ * case we would read stage #2 (ours).
+ */
+ int i;
+ for (i = -pos - 1;
+ (pos < 0 && i < istate->cache_nr &&
+ !strcmp(istate->cache[i]->name, path));
+ i++)
+ if (ce_stage(istate->cache[i]) == 2)
+ pos = i;
+ }
+ if (pos < 0)
+ return 0;
+ data = read_sha1_file(istate->cache[pos]->sha1, &type, &sz);
+ if (!data || type != OBJ_BLOB) {
+ free(data);
+ return 0;
+ }
+
+ has_cr = memchr(data, '\r', sz) != NULL;
+ free(data);
+ return has_cr;
+}
+
static int crlf_to_git(const char *path, const char *src, size_t len,
- struct strbuf *buf, int action, enum safe_crlf checksafe)
+ struct strbuf *buf, enum action action, enum safe_crlf checksafe)
{
struct text_stat stats;
char *dst;
- if ((action == CRLF_BINARY) || !auto_crlf || !len)
+ if (action == CRLF_BINARY ||
+ (action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE) || !len)
return 0;
gather_stats(src, len, &stats);
- if (action == CRLF_GUESS) {
+ if (action == CRLF_AUTO || action == CRLF_GUESS) {
/*
* We're currently not going to even try to convert stuff
* that has bare CR characters. Does anybody do that crazy
*/
if (is_binary(len, &stats))
return 0;
+
+ if (action == CRLF_GUESS) {
+ /*
+ * If the file in the index has any CR in it, do not convert.
+ * This is the new safer autocrlf handling.
+ */
+ if (has_cr_in_index(path))
+ return 0;
+ }
}
check_safe_crlf(path, action, &stats, checksafe);
if (strbuf_avail(buf) + buf->len < len)
strbuf_grow(buf, len - buf->len);
dst = buf->buf;
- if (action == CRLF_GUESS) {
+ if (action == CRLF_AUTO || action == CRLF_GUESS) {
/*
* If we guessed, we already know we rejected a file with
* lone CR, and we can strip a CR without looking at what
}
static int crlf_to_worktree(const char *path, const char *src, size_t len,
- struct strbuf *buf, int action)
+ struct strbuf *buf, enum action action)
{
char *to_free = NULL;
struct text_stat stats;
- if ((action == CRLF_BINARY) || (action == CRLF_INPUT) ||
- auto_crlf <= 0)
- return 0;
-
- if (!len)
+ if (!len || determine_output_conversion(action) != EOL_CRLF)
return 0;
gather_stats(src, len, &stats);
if (stats.lf == stats.crlf)
return 0;
- if (action == CRLF_GUESS) {
+ if (action == CRLF_AUTO || action == CRLF_GUESS) {
+ if (action == CRLF_GUESS) {
+ /* If we have any CR or CRLF line endings, we do not touch it */
+ /* This is the new safer autocrlf-handling */
+ if (stats.cr > 0 || stats.crlf > 0)
+ return 0;
+ }
+
/* If we have any bare CR characters, we're not going to touch it */
if (stats.cr != stats.crlf)
return 0;
struct child_process child_process;
struct filter_params *params = (struct filter_params *)data;
int write_err, status;
- const char *argv[] = { params->cmd, NULL };
+ const char *argv[] = { NULL, NULL };
+
+ argv[0] = params->cmd;
memset(&child_process, 0, sizeof(child_process));
child_process.argv = argv;
static void setup_convert_check(struct git_attr_check *check)
{
+ static struct git_attr *attr_text;
static struct git_attr *attr_crlf;
+ static struct git_attr *attr_eol;
static struct git_attr *attr_ident;
static struct git_attr *attr_filter;
- if (!attr_crlf) {
+ if (!attr_text) {
+ attr_text = git_attr("text");
attr_crlf = git_attr("crlf");
+ attr_eol = git_attr("eol");
attr_ident = git_attr("ident");
attr_filter = git_attr("filter");
user_convert_tail = &user_convert;
check[0].attr = attr_crlf;
check[1].attr = attr_ident;
check[2].attr = attr_filter;
+ check[3].attr = attr_eol;
+ check[4].attr = attr_text;
}
static int count_ident(const char *cp, unsigned long size)
cnt++;
break;
}
+ if (ch == '\n')
+ break;
}
}
return cnt;
dollar = memchr(src + 3, '$', len - 3);
if (!dollar)
break;
+ if (memchr(src + 3, '\n', dollar - src - 3)) {
+ /* Line break before the next dollar. */
+ continue;
+ }
+
memcpy(dst, "Id$", 3);
dst += 3;
len -= dollar + 1 - src;
struct strbuf *buf, int ident)
{
unsigned char sha1[20];
- char *to_free = NULL, *dollar;
+ char *to_free = NULL, *dollar, *spc;
int cnt;
if (!ident)
} else if (src[2] == ':') {
/*
* It's possible that an expanded Id has crept its way into the
- * repository, we cope with that by stripping the expansion out
+ * repository, we cope with that by stripping the expansion out.
+ * This is probably not a good idea, since it will cause changes
+ * on checkout, which won't go away by stash, but let's keep it
+ * for git-style ids.
*/
dollar = memchr(src + 3, '$', len - 3);
if (!dollar) {
break;
}
+ if (memchr(src + 3, '\n', dollar - src - 3)) {
+ /* Line break before the next dollar. */
+ continue;
+ }
+
+ spc = memchr(src + 4, ' ', dollar - src - 4);
+ if (spc && spc < dollar-1) {
+ /* There are spaces in unexpected places.
+ * This is probably an id from some other
+ * versioning system. Keep it for now.
+ */
+ continue;
+ }
+
len -= dollar + 1 - src;
src = dollar + 1;
} else {
;
else if (!strcmp(value, "input"))
return CRLF_INPUT;
+ else if (!strcmp(value, "auto"))
+ return CRLF_AUTO;
return CRLF_GUESS;
}
+static int git_path_check_eol(const char *path, struct git_attr_check *check)
+{
+ const char *value = check->value;
+
+ if (ATTR_UNSET(value))
+ ;
+ else if (!strcmp(value, "lf"))
+ return EOL_LF;
+ else if (!strcmp(value, "crlf"))
+ return EOL_CRLF;
+ return EOL_UNSET;
+}
+
static struct convert_driver *git_path_check_convert(const char *path,
struct git_attr_check *check)
{
return !!ATTR_TRUE(value);
}
+static enum action determine_action(enum action text_attr, enum eol eol_attr)
+{
+ if (text_attr == CRLF_BINARY)
+ return CRLF_BINARY;
+ if (eol_attr == EOL_LF)
+ return CRLF_INPUT;
+ if (eol_attr == EOL_CRLF)
+ return CRLF_CRLF;
+ return text_attr;
+}
+
int convert_to_git(const char *path, const char *src, size_t len,
struct strbuf *dst, enum safe_crlf checksafe)
{
- struct git_attr_check check[3];
- int crlf = CRLF_GUESS;
+ struct git_attr_check check[5];
+ enum action action = CRLF_GUESS;
+ enum eol eol_attr = EOL_UNSET;
int ident = 0, ret = 0;
const char *filter = NULL;
setup_convert_check(check);
if (!git_checkattr(path, ARRAY_SIZE(check), check)) {
struct convert_driver *drv;
- crlf = git_path_check_crlf(path, check + 0);
+ action = git_path_check_crlf(path, check + 4);
+ if (action == CRLF_GUESS)
+ action = git_path_check_crlf(path, check + 0);
ident = git_path_check_ident(path, check + 1);
drv = git_path_check_convert(path, check + 2);
+ eol_attr = git_path_check_eol(path, check + 3);
if (drv && drv->clean)
filter = drv->clean;
}
src = dst->buf;
len = dst->len;
}
- ret |= crlf_to_git(path, src, len, dst, crlf, checksafe);
+ action = determine_action(action, eol_attr);
+ ret |= crlf_to_git(path, src, len, dst, action, checksafe);
if (ret) {
src = dst->buf;
len = dst->len;
return ret | ident_to_git(path, src, len, dst, ident);
}
-int convert_to_working_tree(const char *path, const char *src, size_t len, struct strbuf *dst)
+static int convert_to_working_tree_internal(const char *path, const char *src,
+ size_t len, struct strbuf *dst,
+ int normalizing)
{
- struct git_attr_check check[3];
- int crlf = CRLF_GUESS;
+ struct git_attr_check check[5];
+ enum action action = CRLF_GUESS;
+ enum eol eol_attr = EOL_UNSET;
int ident = 0, ret = 0;
const char *filter = NULL;
setup_convert_check(check);
if (!git_checkattr(path, ARRAY_SIZE(check), check)) {
struct convert_driver *drv;
- crlf = git_path_check_crlf(path, check + 0);
+ action = git_path_check_crlf(path, check + 4);
+ if (action == CRLF_GUESS)
+ action = git_path_check_crlf(path, check + 0);
ident = git_path_check_ident(path, check + 1);
drv = git_path_check_convert(path, check + 2);
+ eol_attr = git_path_check_eol(path, check + 3);
if (drv && drv->smudge)
filter = drv->smudge;
}
src = dst->buf;
len = dst->len;
}
- ret |= crlf_to_worktree(path, src, len, dst, crlf);
+ /*
+ * CRLF conversion can be skipped if normalizing, unless there
+ * is a smudge filter. The filter might expect CRLFs.
+ */
+ if (filter || !normalizing) {
+ action = determine_action(action, eol_attr);
+ ret |= crlf_to_worktree(path, src, len, dst, action);
+ if (ret) {
+ src = dst->buf;
+ len = dst->len;
+ }
+ }
+ return ret | apply_filter(path, src, len, dst, filter);
+}
+
+int convert_to_working_tree(const char *path, const char *src, size_t len, struct strbuf *dst)
+{
+ return convert_to_working_tree_internal(path, src, len, dst, 0);
+}
+
+int renormalize_buffer(const char *path, const char *src, size_t len, struct strbuf *dst)
+{
+ int ret = convert_to_working_tree_internal(path, src, len, dst, 1);
if (ret) {
src = dst->buf;
len = dst->len;
}
- return ret | apply_filter(path, src, len, dst, filter);
+ return ret | convert_to_git(path, src, len, dst, 0);
}