#define CONVERT_STAT_BITS_BIN 0x4
enum crlf_action {
- CRLF_GUESS = -1,
- CRLF_BINARY = 0,
+ CRLF_UNDEFINED,
+ CRLF_BINARY,
CRLF_TEXT,
- CRLF_INPUT,
- CRLF_CRLF,
- CRLF_AUTO
+ CRLF_TEXT_INPUT,
+ CRLF_TEXT_CRLF,
+ CRLF_AUTO,
+ CRLF_AUTO_INPUT,
+ CRLF_AUTO_CRLF
};
struct text_stat {
/* NUL, CR, LF and CRLF counts */
- unsigned nul, cr, lf, crlf;
+ unsigned nul, lonecr, lonelf, crlf;
/* These are just approximations! */
unsigned printable, nonprintable;
for (i = 0; i < size; i++) {
unsigned char c = buf[i];
if (c == '\r') {
- stats->cr++;
- if (i+1 < size && buf[i+1] == '\n')
+ if (i+1 < size && buf[i+1] == '\n') {
stats->crlf++;
+ i++;
+ } else
+ stats->lonecr++;
continue;
}
if (c == '\n') {
- stats->lf++;
+ stats->lonelf++;
continue;
}
if (c == 127)
*/
static int convert_is_binary(unsigned long size, const struct text_stat *stats)
{
- if (stats->cr != stats->crlf)
+ if (stats->lonecr)
return 1;
if (stats->nul)
return 1;
static unsigned int gather_convert_stats(const char *data, unsigned long size)
{
struct text_stat stats;
+ int ret = 0;
if (!data || !size)
return 0;
gather_stats(data, size, &stats);
if (convert_is_binary(size, &stats))
- return CONVERT_STAT_BITS_BIN;
- else if (stats.crlf && stats.crlf == stats.lf)
- return CONVERT_STAT_BITS_TXT_CRLF;
- else if (stats.crlf && stats.lf)
- return CONVERT_STAT_BITS_TXT_CRLF | CONVERT_STAT_BITS_TXT_LF;
- else if (stats.lf)
- return CONVERT_STAT_BITS_TXT_LF;
- else
- return 0;
+ ret |= CONVERT_STAT_BITS_BIN;
+ if (stats.crlf)
+ ret |= CONVERT_STAT_BITS_TXT_CRLF;
+ if (stats.lonelf)
+ ret |= CONVERT_STAT_BITS_TXT_LF;
+
+ return ret;
}
static const char *gather_convert_stats_ascii(const char *data, unsigned long size)
return ret;
}
+static int text_eol_is_crlf(void)
+{
+ if (auto_crlf == AUTO_CRLF_TRUE)
+ return 1;
+ else if (auto_crlf == AUTO_CRLF_INPUT)
+ return 0;
+ if (core_eol == EOL_CRLF)
+ return 1;
+ if (core_eol == EOL_UNSET && EOL_NATIVE == EOL_CRLF)
+ return 1;
+ return 0;
+}
+
static enum eol output_eol(enum crlf_action crlf_action)
{
switch (crlf_action) {
case CRLF_BINARY:
return EOL_UNSET;
- case CRLF_CRLF:
+ case CRLF_TEXT_CRLF:
return EOL_CRLF;
- case CRLF_INPUT:
+ case CRLF_TEXT_INPUT:
return EOL_LF;
- case CRLF_GUESS:
- if (!auto_crlf)
- return EOL_UNSET;
- /* fall through */
+ case CRLF_UNDEFINED:
+ case CRLF_AUTO_CRLF:
+ case CRLF_AUTO_INPUT:
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 (core_eol == EOL_UNSET)
- return EOL_NATIVE;
+ /* fall through */
+ return text_eol_is_crlf() ? EOL_CRLF : EOL_LF;
}
+ warning("Illegal crlf_action %d\n", (int)crlf_action);
return core_eol;
}
* CRLFs would be added by checkout:
* check if we have "naked" LFs
*/
- if (stats->lf != stats->crlf) {
+ if (stats->lonelf) {
if (checksafe == SAFE_CRLF_WARN)
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 */
char *dst;
if (crlf_action == CRLF_BINARY ||
- (crlf_action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE) ||
(src && !len))
return 0;
gather_stats(src, len, &stats);
- if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) {
+ if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
if (convert_is_binary(len, &stats))
return 0;
- if (crlf_action == CRLF_GUESS) {
+ if (crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
/*
* If the file in the index has any CR in it, do not convert.
* This is the new safer autocrlf handling.
check_safe_crlf(path, crlf_action, &stats, checksafe);
- /* Optimization: No CR? Nothing to convert, regardless. */
- if (!stats.cr)
+ /* Optimization: No CRLF? Nothing to convert, regardless. */
+ if (!stats.crlf)
return 0;
/*
if (strbuf_avail(buf) + buf->len < len)
strbuf_grow(buf, len - buf->len);
dst = buf->buf;
- if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) {
+ if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
/*
* If we guessed, we already know we rejected a file with
* lone CR, and we can strip a CR without looking at what
gather_stats(src, len, &stats);
- /* No LF? Nothing to convert, regardless. */
- if (!stats.lf)
+ /* No "naked" LF? Nothing to convert, regardless. */
+ if (!stats.lonelf)
return 0;
- /* Was it already in CRLF format? */
- if (stats.lf == stats.crlf)
- return 0;
-
- if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) {
- if (crlf_action == CRLF_GUESS) {
+ if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
+ if (crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
/* 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)
+ if (stats.lonecr || stats.crlf )
return 0;
}
if (src == buf->buf)
to_free = strbuf_detach(buf, NULL);
- strbuf_grow(buf, len + stats.lf - stats.crlf);
+ strbuf_grow(buf, len + stats.lonelf);
for (;;) {
const char *nl = memchr(src, '\n', len);
if (!nl)
struct async async;
struct filter_params params;
- if (!cmd)
+ if (!cmd || !*cmd)
return 0;
if (!dst)
else if (ATTR_UNSET(value))
;
else if (!strcmp(value, "input"))
- return CRLF_INPUT;
+ return CRLF_TEXT_INPUT;
else if (!strcmp(value, "auto"))
return CRLF_AUTO;
- return CRLF_GUESS;
+ return CRLF_UNDEFINED;
}
static enum eol git_path_check_eol(struct git_attr_check *check)
}
if (!git_check_attr(path, NUM_CONV_ATTRS, ccheck)) {
- enum eol eol_attr;
ca->crlf_action = git_path_check_crlf(ccheck + 4);
- if (ca->crlf_action == CRLF_GUESS)
+ if (ca->crlf_action == CRLF_UNDEFINED)
ca->crlf_action = git_path_check_crlf(ccheck + 0);
ca->attr_action = ca->crlf_action;
ca->ident = git_path_check_ident(ccheck + 1);
ca->drv = git_path_check_convert(ccheck + 2);
- if (ca->crlf_action == CRLF_BINARY)
- return;
- eol_attr = git_path_check_eol(ccheck + 3);
- if (eol_attr == EOL_LF)
- ca->crlf_action = CRLF_INPUT;
- else if (eol_attr == EOL_CRLF)
- ca->crlf_action = CRLF_CRLF;
+ if (ca->crlf_action != CRLF_BINARY) {
+ enum eol eol_attr = git_path_check_eol(ccheck + 3);
+ if (eol_attr == EOL_LF)
+ ca->crlf_action = CRLF_TEXT_INPUT;
+ else if (eol_attr == EOL_CRLF)
+ ca->crlf_action = CRLF_TEXT_CRLF;
+ }
+ ca->attr_action = ca->crlf_action;
} else {
ca->drv = NULL;
- ca->crlf_action = CRLF_GUESS;
+ ca->crlf_action = CRLF_UNDEFINED;
ca->ident = 0;
}
+ if (ca->crlf_action == CRLF_TEXT)
+ ca->crlf_action = text_eol_is_crlf() ? CRLF_TEXT_CRLF : CRLF_TEXT_INPUT;
+ if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_FALSE)
+ ca->crlf_action = CRLF_BINARY;
+ if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_TRUE)
+ ca->crlf_action = CRLF_AUTO_CRLF;
+ if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_INPUT)
+ ca->crlf_action = CRLF_AUTO_INPUT;
}
int would_convert_to_git_filter_fd(const char *path)
convert_attrs(&ca, path);
switch (ca.attr_action) {
- case CRLF_GUESS:
+ case CRLF_UNDEFINED:
return "";
case CRLF_BINARY:
return "-text";
case CRLF_TEXT:
return "text";
- case CRLF_INPUT:
+ case CRLF_TEXT_INPUT:
return "text eol=lf";
- case CRLF_CRLF:
- return "text=auto eol=crlf";
+ case CRLF_TEXT_CRLF:
+ return "text eol=crlf";
case CRLF_AUTO:
return "text=auto";
+ case CRLF_AUTO_CRLF:
+ return "text=auto eol=crlf"; /* This is not supported yet */
+ case CRLF_AUTO_INPUT:
+ return "text=auto eol=lf"; /* This is not supported yet */
}
return "";
}
crlf_action = ca.crlf_action;
- if ((crlf_action == CRLF_BINARY) || (crlf_action == CRLF_INPUT) ||
- (crlf_action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE))
+ if ((crlf_action == CRLF_BINARY) ||
+ crlf_action == CRLF_AUTO_INPUT ||
+ (crlf_action == CRLF_TEXT_INPUT))
filter = cascade_filter(filter, &null_filter_singleton);
else if (output_eol(crlf_action) == EOL_CRLF &&
- !(crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS))
+ !(crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_CRLF))
filter = cascade_filter(filter, lf_to_crlf_filter());
return filter;