summaryrefslogtreecommitdiff
path: root/convert.c
diff options
context:
space:
mode:
Diffstat (limited to 'convert.c')
-rw-r--r--convert.c265
1 files changed, 196 insertions, 69 deletions
diff --git a/convert.c b/convert.c
index 3bb5a4dd57..9a5612e93d 100644
--- a/convert.c
+++ b/convert.c
@@ -2,6 +2,7 @@
#include "attr.h"
#include "run-command.h"
#include "quote.h"
+#include "sigchain.h"
/*
* convert.c - convert a file when checking it out and checking it in.
@@ -152,36 +153,13 @@ static void check_safe_crlf(const char *path, enum crlf_action crlf_action,
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)
+ data = read_blob_data_from_cache(path, &sz);
+ if (!data)
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;
@@ -195,9 +173,17 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
char *dst;
if (crlf_action == CRLF_BINARY ||
- (crlf_action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE) || !len)
+ (crlf_action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE) ||
+ (src && !len))
return 0;
+ /*
+ * If we are doing a dry-run and have no source buffer, there is
+ * nothing to analyze; we must assume we would convert.
+ */
+ if (!buf && !src)
+ return 1;
+
gather_stats(src, len, &stats);
if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) {
@@ -231,6 +217,13 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
if (!stats.cr)
return 0;
+ /*
+ * At this point all of our source analysis is done, and we are sure we
+ * would convert. If we are in dry-run mode, we can give an answer.
+ */
+ if (!buf)
+ return 1;
+
/* only grow if not in place */
if (strbuf_avail(buf) + buf->len < len)
strbuf_grow(buf, len - buf->len);
@@ -319,16 +312,17 @@ static int crlf_to_worktree(const char *path, const char *src, size_t len,
struct filter_params {
const char *src;
unsigned long size;
+ int fd;
const char *cmd;
const char *path;
};
-static int filter_buffer(int in, int out, void *data)
+static int filter_buffer_or_fd(int in, int out, void *data)
{
/*
* Spawn cmd and feed the buffer contents through its stdin.
*/
- struct child_process child_process;
+ struct child_process child_process = CHILD_PROCESS_INIT;
struct filter_params *params = (struct filter_params *)data;
int write_err, status;
const char *argv[] = { NULL, NULL };
@@ -351,7 +345,6 @@ static int filter_buffer(int in, int out, void *data)
argv[0] = cmd.buf;
- memset(&child_process, 0, sizeof(child_process));
child_process.argv = argv;
child_process.use_shell = 1;
child_process.in = -1;
@@ -360,12 +353,21 @@ static int filter_buffer(int in, int out, void *data)
if (start_command(&child_process))
return error("cannot fork to run external filter %s", params->cmd);
- write_err = (write_in_full(child_process.in, params->src, params->size) < 0);
+ sigchain_push(SIGPIPE, SIG_IGN);
+
+ if (params->src) {
+ write_err = (write_in_full(child_process.in, params->src, params->size) < 0);
+ } else {
+ write_err = copy_fd(params->fd, child_process.in);
+ }
+
if (close(child_process.in))
write_err = 1;
if (write_err)
error("cannot feed the input to external filter %s", params->cmd);
+ sigchain_pop(SIGPIPE);
+
status = finish_command(&child_process);
if (status)
error("external filter %s failed %d", params->cmd, status);
@@ -374,7 +376,7 @@ static int filter_buffer(int in, int out, void *data)
return (write_err || status);
}
-static int apply_filter(const char *path, const char *src, size_t len,
+static int apply_filter(const char *path, const char *src, size_t len, int fd,
struct strbuf *dst, const char *cmd)
{
/*
@@ -391,12 +393,16 @@ static int apply_filter(const char *path, const char *src, size_t len,
if (!cmd)
return 0;
+ if (!dst)
+ return 1;
+
memset(&async, 0, sizeof(async));
- async.proc = filter_buffer;
+ async.proc = filter_buffer_or_fd;
async.data = &params;
async.out = -1;
params.src = src;
params.size = len;
+ params.fd = fd;
params.cmd = cmd;
params.path = path;
@@ -429,11 +435,12 @@ static struct convert_driver {
struct convert_driver *next;
const char *smudge;
const char *clean;
+ int required;
} *user_convert, **user_convert_tail;
static int read_convert_config(const char *var, const char *value, void *cb)
{
- const char *ep, *name;
+ const char *key, *name;
int namelen;
struct convert_driver *drv;
@@ -441,10 +448,8 @@ static int read_convert_config(const char *var, const char *value, void *cb)
* External conversion drivers are configured using
* "filter.<name>.variable".
*/
- if (prefixcmp(var, "filter.") || (ep = strrchr(var, '.')) == var + 6)
+ if (parse_config_key(var, "filter", &name, &namelen, &key) < 0 || !name)
return 0;
- name = var + 7;
- namelen = ep - name;
for (drv = user_convert; drv; drv = drv->next)
if (!strncmp(drv->name, name, namelen) && !drv->name[namelen])
break;
@@ -455,8 +460,6 @@ static int read_convert_config(const char *var, const char *value, void *cb)
user_convert_tail = &(drv->next);
}
- ep++;
-
/*
* filter.<name>.smudge and filter.<name>.clean specifies
* the command line:
@@ -466,12 +469,17 @@ static int read_convert_config(const char *var, const char *value, void *cb)
* The command-line will not be interpolated in any way.
*/
- if (!strcmp("smudge", ep))
+ if (!strcmp("smudge", key))
return git_config_string(&drv->smudge, var, value);
- if (!strcmp("clean", ep))
+ if (!strcmp("clean", key))
return git_config_string(&drv->clean, var, value);
+ if (!strcmp("required", key)) {
+ drv->required = git_config_bool(var, value);
+ return 0;
+ }
+
return 0;
}
@@ -522,9 +530,12 @@ static int ident_to_git(const char *path, const char *src, size_t len,
{
char *dst, *dollar;
- if (!ident || !count_ident(src, len))
+ if (!ident || (src && !count_ident(src, len)))
return 0;
+ if (!buf)
+ return 1;
+
/* only grow if not in place */
if (strbuf_avail(buf) + buf->len < len)
strbuf_grow(buf, len - buf->len);
@@ -641,7 +652,7 @@ static int ident_to_worktree(const char *path, const char *src, size_t len,
return 1;
}
-static int git_path_check_crlf(const char *path, struct git_attr_check *check)
+static enum crlf_action git_path_check_crlf(const char *path, struct git_attr_check *check)
{
const char *value = check->value;
@@ -658,7 +669,7 @@ static int git_path_check_crlf(const char *path, struct git_attr_check *check)
return CRLF_GUESS;
}
-static int git_path_check_eol(const char *path, struct git_attr_check *check)
+static enum eol git_path_check_eol(const char *path, struct git_attr_check *check)
{
const char *value = check->value;
@@ -742,42 +753,87 @@ static void convert_attrs(struct conv_attrs *ca, const char *path)
}
}
+int would_convert_to_git_filter_fd(const char *path)
+{
+ struct conv_attrs ca;
+
+ convert_attrs(&ca, path);
+ if (!ca.drv)
+ return 0;
+
+ /*
+ * Apply a filter to an fd only if the filter is required to succeed.
+ * We must die if the filter fails, because the original data before
+ * filtering is not available.
+ */
+ if (!ca.drv->required)
+ return 0;
+
+ return apply_filter(path, NULL, 0, -1, NULL, ca.drv->clean);
+}
+
int convert_to_git(const char *path, const char *src, size_t len,
struct strbuf *dst, enum safe_crlf checksafe)
{
int ret = 0;
const char *filter = NULL;
+ int required = 0;
struct conv_attrs ca;
convert_attrs(&ca, path);
- if (ca.drv)
+ if (ca.drv) {
filter = ca.drv->clean;
+ required = ca.drv->required;
+ }
- ret |= apply_filter(path, src, len, dst, filter);
- if (ret) {
+ ret |= apply_filter(path, src, len, -1, dst, filter);
+ if (!ret && required)
+ die("%s: clean filter '%s' failed", path, ca.drv->name);
+
+ if (ret && dst) {
src = dst->buf;
len = dst->len;
}
ca.crlf_action = input_crlf_action(ca.crlf_action, ca.eol_attr);
ret |= crlf_to_git(path, src, len, dst, ca.crlf_action, checksafe);
- if (ret) {
+ if (ret && dst) {
src = dst->buf;
len = dst->len;
}
return ret | ident_to_git(path, src, len, dst, ca.ident);
}
+void convert_to_git_filter_fd(const char *path, int fd, struct strbuf *dst,
+ enum safe_crlf checksafe)
+{
+ struct conv_attrs ca;
+ convert_attrs(&ca, path);
+
+ assert(ca.drv);
+ assert(ca.drv->clean);
+
+ if (!apply_filter(path, NULL, 0, fd, dst, ca.drv->clean))
+ die("%s: clean filter '%s' failed", path, ca.drv->name);
+
+ ca.crlf_action = input_crlf_action(ca.crlf_action, ca.eol_attr);
+ crlf_to_git(path, dst->buf, dst->len, dst, ca.crlf_action, checksafe);
+ ident_to_git(path, dst->buf, dst->len, dst, ca.ident);
+}
+
static int convert_to_working_tree_internal(const char *path, const char *src,
size_t len, struct strbuf *dst,
int normalizing)
{
- int ret = 0;
+ int ret = 0, ret_filter = 0;
const char *filter = NULL;
+ int required = 0;
struct conv_attrs ca;
convert_attrs(&ca, path);
- if (ca.drv)
+ if (ca.drv) {
filter = ca.drv->smudge;
+ required = ca.drv->required;
+ }
ret |= ident_to_worktree(path, src, len, dst, ca.ident);
if (ret) {
@@ -796,7 +852,12 @@ static int convert_to_working_tree_internal(const char *path, const char *src,
len = dst->len;
}
}
- return ret | apply_filter(path, src, len, dst, filter);
+
+ ret_filter = apply_filter(path, src, len, -1, dst, filter);
+ if (!ret_filter && required)
+ die("%s: smudge filter %s failed", path, ca.drv->name);
+
+ return ret | ret_filter;
}
int convert_to_working_tree(const char *path, const char *src, size_t len, struct strbuf *dst)
@@ -811,12 +872,12 @@ int renormalize_buffer(const char *path, const char *src, size_t len, struct str
src = dst->buf;
len = dst->len;
}
- return ret | convert_to_git(path, src, len, dst, 0);
+ return ret | convert_to_git(path, src, len, dst, SAFE_CRLF_FALSE);
}
/*****************************************************************
*
- * Streaming converison support
+ * Streaming conversion support
*
*****************************************************************/
@@ -876,43 +937,109 @@ int is_null_stream_filter(struct stream_filter *filter)
/*
* LF-to-CRLF filter
*/
+
+struct lf_to_crlf_filter {
+ struct stream_filter filter;
+ unsigned has_held:1;
+ char held;
+};
+
static int lf_to_crlf_filter_fn(struct stream_filter *filter,
const char *input, size_t *isize_p,
char *output, size_t *osize_p)
{
- size_t count;
+ size_t count, o = 0;
+ struct lf_to_crlf_filter *lf_to_crlf = (struct lf_to_crlf_filter *)filter;
+
+ /*
+ * We may be holding onto the CR to see if it is followed by a
+ * LF, in which case we would need to go to the main loop.
+ * Otherwise, just emit it to the output stream.
+ */
+ if (lf_to_crlf->has_held && (lf_to_crlf->held != '\r' || !input)) {
+ output[o++] = lf_to_crlf->held;
+ lf_to_crlf->has_held = 0;
+ }
+
+ /* We are told to drain */
+ if (!input) {
+ *osize_p -= o;
+ return 0;
+ }
- if (!input)
- return 0; /* we do not keep any states */
count = *isize_p;
- if (count) {
- size_t i, o;
- for (i = o = 0; o < *osize_p && i < count; i++) {
+ if (count || lf_to_crlf->has_held) {
+ size_t i;
+ int was_cr = 0;
+
+ if (lf_to_crlf->has_held) {
+ was_cr = 1;
+ lf_to_crlf->has_held = 0;
+ }
+
+ for (i = 0; o < *osize_p && i < count; i++) {
char ch = input[i];
+
if (ch == '\n') {
- if (o + 1 < *osize_p)
- output[o++] = '\r';
- else
- break;
+ output[o++] = '\r';
+ } else if (was_cr) {
+ /*
+ * Previous round saw CR and it is not followed
+ * by a LF; emit the CR before processing the
+ * current character.
+ */
+ output[o++] = '\r';
+ }
+
+ /*
+ * We may have consumed the last output slot,
+ * in which case we need to break out of this
+ * loop; hold the current character before
+ * returning.
+ */
+ if (*osize_p <= o) {
+ lf_to_crlf->has_held = 1;
+ lf_to_crlf->held = ch;
+ continue; /* break but increment i */
+ }
+
+ if (ch == '\r') {
+ was_cr = 1;
+ continue;
}
+
+ was_cr = 0;
output[o++] = ch;
}
*osize_p -= o;
*isize_p -= i;
+
+ if (!lf_to_crlf->has_held && was_cr) {
+ lf_to_crlf->has_held = 1;
+ lf_to_crlf->held = '\r';
+ }
}
return 0;
}
+static void lf_to_crlf_free_fn(struct stream_filter *filter)
+{
+ free(filter);
+}
+
static struct stream_filter_vtbl lf_to_crlf_vtbl = {
lf_to_crlf_filter_fn,
- null_free_fn,
+ lf_to_crlf_free_fn,
};
-static struct stream_filter lf_to_crlf_filter_singleton = {
- &lf_to_crlf_vtbl,
-};
+static struct stream_filter *lf_to_crlf_filter(void)
+{
+ struct lf_to_crlf_filter *lf_to_crlf = xcalloc(1, sizeof(*lf_to_crlf));
+ lf_to_crlf->filter.vtbl = &lf_to_crlf_vtbl;
+ return (struct stream_filter *)lf_to_crlf;
+}
/*
* Cascade filter
@@ -1036,9 +1163,9 @@ static int is_foreign_ident(const char *str)
{
int i;
- if (prefixcmp(str, "$Id: "))
+ if (!skip_prefix(str, "$Id: ", &str))
return 0;
- for (i = 5; str[i]; i++) {
+ for (i = 0; str[i]; i++) {
if (isspace(str[i]) && str[i+1] != '$')
return 1;
}
@@ -1194,7 +1321,7 @@ struct stream_filter *get_stream_filter(const char *path, const unsigned char *s
else if (output_eol(crlf_action) == EOL_CRLF &&
!(crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS))
- filter = cascade_filter(filter, &lf_to_crlf_filter_singleton);
+ filter = cascade_filter(filter, lf_to_crlf_filter());
return filter;
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-10-04 12:25:48 +0000