![[tokkee]](http://tokkee.org/images/avatar.png){kind=avatar}
diff --git a/convert.c b/convert.c
index 5fdaee75714fa6a42601fbb366aeafb18f3334fb..4df75595b1f3e689a9685039c372ffb4c8688291 100644 (file)
--- a/convert.c
+++ b/convert.c
return 0;
}
-static char *crlf_to_git(const char *path, const char *src, unsigned long *sizep, int action)
+static int crlf_to_git(const char *path, const char *src, size_t len,
+ struct strbuf *buf, int action)
{
- char *buffer, *dst;
- unsigned long size, nsize;
struct text_stat stats;
+ char *dst;
- if ((action == CRLF_BINARY) || (action == CRLF_GUESS && !auto_crlf))
- return NULL;
-
- size = *sizep;
- if (!size)
- return NULL;
-
- gather_stats(src, size, &stats);
+ if ((action == CRLF_BINARY) || !auto_crlf || !len)
+ return 0;
+ gather_stats(src, len, &stats);
/* No CR? Nothing to convert, regardless. */
if (!stats.cr)
- return NULL;
+ return 0;
if (action == CRLF_GUESS) {
/*
@@ -106,24 +101,19 @@ static char *crlf_to_git(const char *path, const char *src, unsigned long *sizep
* stuff?
*/
if (stats.cr != stats.crlf)
- return NULL;
+ return 0;
/*
* And add some heuristics for binary vs text, of course...
*/
- if (is_binary(size, &stats))
- return NULL;
+ if (is_binary(len, &stats))
+ return 0;
}
- /*
- * Ok, allocate a new buffer, fill it in, and return it
- * to let the caller know that we switched buffers.
- */
- nsize = size - stats.crlf;
- buffer = xmalloc(nsize);
- *sizep = nsize;
-
- dst = buffer;
+ /* only grow if not in place */
+ if (strbuf_avail(buf) + buf->len < len)
+ strbuf_grow(buf, len - buf->len);
+ dst = buf->buf;
if (action == CRLF_GUESS) {
/*
* If we guessed, we already know we rejected a file with
@@ -134,90 +124,239 @@ static char *crlf_to_git(const char *path, const char *src, unsigned long *sizep
unsigned char c = *src++;
if (c != '\r')
*dst++ = c;
- } while (--size);
+ } while (--len);
} else {
do {
unsigned char c = *src++;
- if (! (c == '\r' && (1 < size && *src == '\n')))
+ if (! (c == '\r' && (1 < len && *src == '\n')))
*dst++ = c;
- } while (--size);
+ } while (--len);
}
-
- return buffer;
+ strbuf_setlen(buf, dst - buf->buf);
+ return 1;
}
-static char *crlf_to_worktree(const char *path, const char *src, unsigned long *sizep, int action)
+static int crlf_to_worktree(const char *path, const char *src, size_t len,
+ struct strbuf *buf, int action)
{
- char *buffer, *dst;
- unsigned long size, nsize;
+ char *to_free = NULL;
struct text_stat stats;
- unsigned char last;
if ((action == CRLF_BINARY) || (action == CRLF_INPUT) ||
- (action == CRLF_GUESS && auto_crlf <= 0))
- return NULL;
+ auto_crlf <= 0)
+ return 0;
- size = *sizep;
- if (!size)
- return NULL;
+ if (!len)
+ return 0;
- gather_stats(src, size, &stats);
+ gather_stats(src, len, &stats);
/* No LF? Nothing to convert, regardless. */
if (!stats.lf)
- return NULL;
+ return 0;
/* Was it already in CRLF format? */
if (stats.lf == stats.crlf)
- return NULL;
+ return 0;
if (action == CRLF_GUESS) {
/* If we have any bare CR characters, we're not going to touch it */
if (stats.cr != stats.crlf)
- return NULL;
+ return 0;
+
+ if (is_binary(len, &stats))
+ return 0;
+ }
- if (is_binary(size, &stats))
- return NULL;
+ /* are we "faking" in place editing ? */
+ if (src == buf->buf)
+ to_free = strbuf_detach(buf, NULL);
+
+ strbuf_grow(buf, len + stats.lf - stats.crlf);
+ for (;;) {
+ const char *nl = memchr(src, '\n', len);
+ if (!nl)
+ break;
+ if (nl > src && nl[-1] == '\r') {
+ strbuf_add(buf, src, nl + 1 - src);
+ } else {
+ strbuf_add(buf, src, nl - src);
+ strbuf_addstr(buf, "\r\n");
+ }
+ len -= nl + 1 - src;
+ src = nl + 1;
+ }
+ strbuf_add(buf, src, len);
+
+ free(to_free);
+ return 1;
+}
+
+struct filter_params {
+ const char *src;
+ unsigned long size;
+ const char *cmd;
+};
+
+static int filter_buffer(int fd, void *data)
+{
+ /*
+ * Spawn cmd and feed the buffer contents through its stdin.
+ */
+ struct child_process child_process;
+ struct filter_params *params = (struct filter_params *)data;
+ int write_err, status;
+ const char *argv[] = { "sh", "-c", params->cmd, NULL };
+
+ memset(&child_process, 0, sizeof(child_process));
+ child_process.argv = argv;
+ child_process.in = -1;
+ child_process.out = fd;
+
+ 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);
+ if (close(child_process.in))
+ write_err = 1;
+ if (write_err)
+ error("cannot feed the input to external filter %s", params->cmd);
+
+ status = finish_command(&child_process);
+ if (status)
+ error("external filter %s failed %d", params->cmd, -status);
+ return (write_err || status);
+}
+
+static int apply_filter(const char *path, const char *src, size_t len,
+ struct strbuf *dst, const char *cmd)
+{
+ /*
+ * Create a pipeline to have the command filter the buffer's
+ * contents.
+ *
+ * (child --> cmd) --> us
+ */
+ int ret = 1;
+ struct strbuf nbuf;
+ struct async async;
+ struct filter_params params;
+
+ if (!cmd)
+ return 0;
+
+ memset(&async, 0, sizeof(async));
+ async.proc = filter_buffer;
+ async.data = ¶ms;
+ params.src = src;
+ params.size = len;
+ params.cmd = cmd;
+
+ fflush(NULL);
+ if (start_async(&async))
+ return 0; /* error was already reported */
+
+ strbuf_init(&nbuf, 0);
+ if (strbuf_read(&nbuf, async.out, len) < 0) {
+ error("read from external filter %s failed", cmd);
+ ret = 0;
+ }
+ if (close(async.out)) {
+ error("read from external filter %s failed", cmd);
+ ret = 0;
+ }
+ if (finish_async(&async)) {
+ error("external filter %s failed", cmd);
+ ret = 0;
+ }
+
+ if (ret) {
+ strbuf_swap(dst, &nbuf);
+ }
+ strbuf_release(&nbuf);
+ return ret;
+}
+
+static struct convert_driver {
+ const char *name;
+ struct convert_driver *next;
+ char *smudge;
+ char *clean;
+} *user_convert, **user_convert_tail;
+
+static int read_convert_config(const char *var, const char *value)
+{
+ const char *ep, *name;
+ int namelen;
+ struct convert_driver *drv;
+
+ /*
+ * External conversion drivers are configured using
+ * "filter.<name>.variable".
+ */
+ if (prefixcmp(var, "filter.") || (ep = strrchr(var, '.')) == var + 6)
+ 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;
+ if (!drv) {
+ drv = xcalloc(1, sizeof(struct convert_driver));
+ drv->name = xmemdupz(name, namelen);
+ *user_convert_tail = drv;
+ user_convert_tail = &(drv->next);
}
+ ep++;
+
/*
- * Ok, allocate a new buffer, fill it in, and return it
- * to let the caller know that we switched buffers.
+ * filter.<name>.smudge and filter.<name>.clean specifies
+ * the command line:
+ *
+ * command-line
+ *
+ * The command-line will not be interpolated in any way.
*/
- nsize = size + stats.lf - stats.crlf;
- buffer = xmalloc(nsize);
- *sizep = nsize;
- last = 0;
-
- dst = buffer;
- do {
- unsigned char c = *src++;
- if (c == '\n' && last != '\r')
- *dst++ = '\r';
- *dst++ = c;
- last = c;
- } while (--size);
-
- return buffer;
+
+ if (!strcmp("smudge", ep)) {
+ if (!value)
+ return error("%s: lacks value", var);
+ drv->smudge = strdup(value);
+ return 0;
+ }
+
+ if (!strcmp("clean", ep)) {
+ if (!value)
+ return error("%s: lacks value", var);
+ drv->clean = strdup(value);
+ return 0;
+ }
+ return 0;
}
static void setup_convert_check(struct git_attr_check *check)
{
static struct git_attr *attr_crlf;
static struct git_attr *attr_ident;
+ static struct git_attr *attr_filter;
if (!attr_crlf) {
attr_crlf = git_attr("crlf", 4);
attr_ident = git_attr("ident", 5);
+ attr_filter = git_attr("filter", 6);
+ user_convert_tail = &user_convert;
+ git_config(read_convert_config);
}
check[0].attr = attr_crlf;
check[1].attr = attr_ident;
+ check[2].attr = attr_filter;
}
static int count_ident(const char *cp, unsigned long size)
{
/*
- * "$ident: 0000000000000000000000000000000000000000 $" <=> "$ident$"
+ * "$Id: 0000000000000000000000000000000000000000 $" <=> "$Id$"
*/
int cnt = 0;
char ch;
size--;
if (ch != '$')
continue;
- if (size < 6)
+ if (size < 3)
break;
- if (memcmp("ident", cp, 5))
+ if (memcmp("Id", cp, 2))
continue;
- ch = cp[5];
- cp += 6;
- size -= 6;
+ ch = cp[2];
+ cp += 3;
+ size -= 3;
if (ch == '$')
- cnt++; /* $ident$ */
+ cnt++; /* $Id$ */
if (ch != ':')
continue;
/*
- * "$ident: ... "; scan up to the closing dollar sign and discard.
+ * "$Id: ... "; scan up to the closing dollar sign and discard.
*/
while (size) {
ch = *cp++;
return cnt;
}
-static char *ident_to_git(const char *path, const char *src, unsigned long *sizep, int ident)
+static int ident_to_git(const char *path, const char *src, size_t len,
+ struct strbuf *buf, int ident)
{
- int cnt;
- unsigned long size;
- char *dst, *buf;
-
- if (!ident)
- return NULL;
- size = *sizep;
- cnt = count_ident(src, size);
- if (!cnt)
- return NULL;
- buf = xmalloc(size);
-
- for (dst = buf; size; size--) {
- char ch = *src++;
- *dst++ = ch;
- if ((ch == '$') && (6 <= size) &&
- !memcmp("ident:", src, 6)) {
- unsigned long rem = size - 6;
- const char *cp = src + 6;
- do {
- ch = *cp++;
- if (ch == '$')
- break;
- rem--;
- } while (rem);
- if (!rem)
- continue;
- memcpy(dst, "ident$", 6);
- dst += 6;
- size -= (cp - src);
- src = cp;
+ char *dst, *dollar;
+
+ if (!ident || !count_ident(src, len))
+ return 0;
+
+ /* only grow if not in place */
+ if (strbuf_avail(buf) + buf->len < len)
+ strbuf_grow(buf, len - buf->len);
+ dst = buf->buf;
+ for (;;) {
+ dollar = memchr(src, '$', len);
+ if (!dollar)
+ break;
+ memcpy(dst, src, dollar + 1 - src);
+ dst += dollar + 1 - src;
+ len -= dollar + 1 - src;
+ src = dollar + 1;
+
+ if (len > 3 && !memcmp(src, "Id:", 3)) {
+ dollar = memchr(src + 3, '$', len - 3);
+ if (!dollar)
+ break;
+ memcpy(dst, "Id$", 3);
+ dst += 3;
+ len -= dollar + 1 - src;
+ src = dollar + 1;
}
}
-
- *sizep = dst - buf;
- return buf;
+ memcpy(dst, src, len);
+ strbuf_setlen(buf, dst + len - buf->buf);
+ return 1;
}
-static char *ident_to_worktree(const char *path, const char *src, unsigned long *sizep, int ident)
+static int ident_to_worktree(const char *path, const char *src, size_t len,
+ struct strbuf *buf, int ident)
{
- int cnt;
- unsigned long size;
- char *dst, *buf;
unsigned char sha1[20];
+ char *to_free = NULL, *dollar;
+ int cnt;
if (!ident)
- return NULL;
+ return 0;
- size = *sizep;
- cnt = count_ident(src, size);
+ cnt = count_ident(src, len);
if (!cnt)
- return NULL;
-
- hash_sha1_file(src, size, "blob", sha1);
- buf = xmalloc(size + cnt * 43);
+ return 0;
+
+ /* are we "faking" in place editing ? */
+ if (src == buf->buf)
+ to_free = strbuf_detach(buf, NULL);
+ hash_sha1_file(src, len, "blob", sha1);
+
+ strbuf_grow(buf, len + cnt * 43);
+ for (;;) {
+ /* step 1: run to the next '$' */
+ dollar = memchr(src, '$', len);
+ if (!dollar)
+ break;
+ strbuf_add(buf, src, dollar + 1 - src);
+ len -= dollar + 1 - src;
+ src = dollar + 1;
- for (dst = buf; size; size--) {
- const char *cp;
- char ch = *src++;
- *dst++ = ch;
- if ((ch != '$') || (size < 6) || memcmp("ident", src, 5))
+ /* step 2: does it looks like a bit like Id:xxx$ or Id$ ? */
+ if (len < 3 || memcmp("Id", src, 2))
continue;
- if (src[5] == ':') {
- /* discard up to but not including the closing $ */
- unsigned long rem = size - 6;
- cp = src + 6;
- do {
- ch = *cp++;
- if (ch == '$')
- break;
- rem--;
- } while (rem);
- if (!rem)
- continue;
- size -= (cp - src);
- } else if (src[5] == '$')
- cp = src + 5;
- else
+ /* step 3: skip over Id$ or Id:xxxxx$ */
+ if (src[2] == '$') {
+ src += 3;
+ len -= 3;
+ } else if (src[2] == ':') {
+ /*
+ * It's possible that an expanded Id has crept its way into the
+ * repository, we cope with that by stripping the expansion out
+ */
+ dollar = memchr(src + 3, '$', len - 3);
+ if (!dollar) {
+ /* incomplete keyword, no more '$', so just quit the loop */
+ break;
+ }
+
+ len -= dollar + 1 - src;
+ src = dollar + 1;
+ } else {
+ /* it wasn't a "Id$" or "Id:xxxx$" */
continue;
+ }
- memcpy(dst, "ident: ", 7);
- dst += 7;
- memcpy(dst, sha1_to_hex(sha1), 40);
- dst += 40;
- *dst++ = ' ';
- size -= (cp - src);
- src = cp;
- *dst++ = *src++;
- size--;
+ /* step 4: substitute */
+ strbuf_addstr(buf, "Id: ");
+ strbuf_add(buf, sha1_to_hex(sha1), 40);
+ strbuf_addstr(buf, " $");
}
+ strbuf_add(buf, src, len);
- *sizep = dst - buf;
- return buf;
+ free(to_free);
+ return 1;
}
static int git_path_check_crlf(const char *path, struct git_attr_check *check)
return CRLF_GUESS;
}
+static struct convert_driver *git_path_check_convert(const char *path,
+ struct git_attr_check *check)
+{
+ const char *value = check->value;
+ struct convert_driver *drv;
+
+ if (ATTR_TRUE(value) || ATTR_FALSE(value) || ATTR_UNSET(value))
+ return NULL;
+ for (drv = user_convert; drv; drv = drv->next)
+ if (!strcmp(value, drv->name))
+ return drv;
+ return NULL;
+}
+
static int git_path_check_ident(const char *path, struct git_attr_check *check)
{
const char *value = check->value;
@@ -374,50 +531,62 @@ static int git_path_check_ident(const char *path, struct git_attr_check *check)
return !!ATTR_TRUE(value);
}
-char *convert_to_git(const char *path, const char *src, unsigned long *sizep)
+int convert_to_git(const char *path, const char *src, size_t len, struct strbuf *dst)
{
- struct git_attr_check check[2];
+ struct git_attr_check check[3];
int crlf = CRLF_GUESS;
- int ident = 0;
- char *buf, *buf2;
+ int ident = 0, ret = 0;
+ 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);
ident = git_path_check_ident(path, check + 1);
+ drv = git_path_check_convert(path, check + 2);
+ if (drv && drv->clean)
+ filter = drv->clean;
}
- buf = crlf_to_git(path, src, sizep, crlf);
-
- buf2 = ident_to_git(path, buf ? buf : src, sizep, ident);
- if (buf2) {
- free(buf);
- buf = buf2;
+ ret |= apply_filter(path, src, len, dst, filter);
+ if (ret) {
+ src = dst->buf;
+ len = dst->len;
}
-
- return buf;
+ ret |= crlf_to_git(path, src, len, dst, crlf);
+ if (ret) {
+ src = dst->buf;
+ len = dst->len;
+ }
+ return ret | ident_to_git(path, src, len, dst, ident);
}
-char *convert_to_working_tree(const char *path, const char *src, unsigned long *sizep)
+int convert_to_working_tree(const char *path, const char *src, size_t len, struct strbuf *dst)
{
- struct git_attr_check check[2];
+ struct git_attr_check check[3];
int crlf = CRLF_GUESS;
- int ident = 0;
- char *buf, *buf2;
+ int ident = 0, ret = 0;
+ 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);
ident = git_path_check_ident(path, check + 1);
+ drv = git_path_check_convert(path, check + 2);
+ if (drv && drv->smudge)
+ filter = drv->smudge;
}
- buf = ident_to_worktree(path, src, sizep, ident);
-
- buf2 = crlf_to_worktree(path, buf ? buf : src, sizep, crlf);
- if (buf2) {
- free(buf);
- buf = buf2;
+ ret |= ident_to_worktree(path, src, len, dst, ident);
+ if (ret) {
+ src = dst->buf;
+ len = dst->len;
}
-
- return buf;
+ ret |= crlf_to_worktree(path, src, len, dst, crlf);
+ if (ret) {
+ src = dst->buf;
+ len = dst->len;
+ }
+ return ret | apply_filter(path, src, len, dst, filter);
}