summaryrefslogtreecommitdiff
path: root/convert.c
diff options
context:
space:
mode:
Diffstat (limited to 'convert.c')
-rw-r--r--convert.c488
1 files changed, 402 insertions, 86 deletions
diff --git a/convert.c b/convert.c
index 67d69b5c0e..4e17e45ed2 100644
--- a/convert.c
+++ b/convert.c
@@ -3,6 +3,7 @@
#include "run-command.h"
#include "quote.h"
#include "sigchain.h"
+#include "pkt-line.h"
/*
* convert.c - convert a file when checking it out and checking it in.
@@ -189,33 +190,29 @@ static enum eol output_eol(enum crlf_action crlf_action)
}
static void check_safe_crlf(const char *path, enum crlf_action crlf_action,
- struct text_stat *stats, enum safe_crlf checksafe)
+ struct text_stat *old_stats, struct text_stat *new_stats,
+ enum safe_crlf checksafe)
{
- if (!checksafe)
- return;
-
- if (output_eol(crlf_action) == EOL_LF) {
+ if (old_stats->crlf && !new_stats->crlf ) {
/*
- * CRLFs would not be restored by checkout:
- * check if we'd remove CRLFs
+ * CRLFs would not be restored by checkout
*/
- if (stats->crlf) {
- if (checksafe == SAFE_CRLF_WARN)
- 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 (output_eol(crlf_action) == EOL_CRLF) {
+ if (checksafe == SAFE_CRLF_WARN)
+ warning(_("CRLF will be replaced by LF in %s.\n"
+ "The 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 (old_stats->lonelf && !new_stats->lonelf ) {
/*
- * CRLFs would be added by checkout:
- * check if we have "naked" LFs
+ * CRLFs would be added by checkout
*/
- 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 */
- die("LF would be replaced by CRLF in %s", path);
- }
+ if (checksafe == SAFE_CRLF_WARN)
+ warning(_("LF will be replaced by CRLF in %s.\n"
+ "The 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);
}
}
@@ -233,12 +230,35 @@ static int has_cr_in_index(const char *path)
return has_cr;
}
+static int will_convert_lf_to_crlf(size_t len, struct text_stat *stats,
+ enum crlf_action crlf_action)
+{
+ if (output_eol(crlf_action) != EOL_CRLF)
+ return 0;
+ /* No "naked" LF? Nothing to convert, regardless. */
+ if (!stats->lonelf)
+ return 0;
+
+ if (crlf_action == CRLF_AUTO || 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->lonecr || stats->crlf)
+ return 0;
+
+ if (convert_is_binary(len, stats))
+ return 0;
+ }
+ return 1;
+
+}
+
static int crlf_to_git(const char *path, const char *src, size_t len,
struct strbuf *buf,
enum crlf_action crlf_action, enum safe_crlf checksafe)
{
struct text_stat stats;
char *dst;
+ int convert_crlf_into_lf;
if (crlf_action == CRLF_BINARY ||
(src && !len))
@@ -252,23 +272,38 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
return 1;
gather_stats(src, len, &stats);
+ /* Optimization: No CRLF? Nothing to convert, regardless. */
+ convert_crlf_into_lf = !!stats.crlf;
if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
if (convert_is_binary(len, &stats))
return 0;
/*
- * If the file in the index has any CR in it, do not convert.
- * This is the new safer autocrlf handling.
+ * If the file in the index has any CR in it, do not
+ * convert. This is the new safer autocrlf handling,
+ * unless we want to renormalize in a merge or
+ * cherry-pick.
*/
- if (checksafe == SAFE_CRLF_RENORMALIZE)
- checksafe = SAFE_CRLF_FALSE;
- else if (has_cr_in_index(path))
- return 0;
+ if ((checksafe != SAFE_CRLF_RENORMALIZE) && has_cr_in_index(path))
+ convert_crlf_into_lf = 0;
}
- check_safe_crlf(path, crlf_action, &stats, checksafe);
-
- /* Optimization: No CRLF? Nothing to convert, regardless. */
- if (!stats.crlf)
+ if ((checksafe == SAFE_CRLF_WARN ||
+ (checksafe == SAFE_CRLF_FAIL)) && len) {
+ struct text_stat new_stats;
+ memcpy(&new_stats, &stats, sizeof(new_stats));
+ /* simulate "git add" */
+ if (convert_crlf_into_lf) {
+ new_stats.lonelf += new_stats.crlf;
+ new_stats.crlf = 0;
+ }
+ /* simulate "git checkout" */
+ if (will_convert_lf_to_crlf(len, &new_stats, crlf_action)) {
+ new_stats.crlf += new_stats.lonelf;
+ new_stats.lonelf = 0;
+ }
+ check_safe_crlf(path, crlf_action, &stats, &new_stats, checksafe);
+ }
+ if (!convert_crlf_into_lf)
return 0;
/*
@@ -314,21 +349,9 @@ static int crlf_to_worktree(const char *path, const char *src, size_t len,
return 0;
gather_stats(src, len, &stats);
-
- /* No "naked" LF? Nothing to convert, regardless. */
- if (!stats.lonelf)
+ if (!will_convert_lf_to_crlf(len, &stats, crlf_action))
return 0;
- if (crlf_action == CRLF_AUTO || 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.lonecr || stats.crlf )
- return 0;
-
- if (convert_is_binary(len, &stats))
- return 0;
- }
-
/* are we "faking" in place editing ? */
if (src == buf->buf)
to_free = strbuf_detach(buf, NULL);
@@ -395,7 +418,7 @@ static int filter_buffer_or_fd(int in, int out, void *data)
child_process.out = out;
if (start_command(&child_process))
- return error("cannot fork to run external filter %s", params->cmd);
+ return error("cannot fork to run external filter '%s'", params->cmd);
sigchain_push(SIGPIPE, SIG_IGN);
@@ -413,19 +436,19 @@ static int filter_buffer_or_fd(int in, int out, void *data)
if (close(child_process.in))
write_err = 1;
if (write_err)
- error("cannot feed the input to external filter %s", params->cmd);
+ 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);
+ error("external filter '%s' failed %d", params->cmd, status);
strbuf_release(&cmd);
return (write_err || status);
}
-static int apply_filter(const char *path, const char *src, size_t len, int fd,
+static int apply_single_file_filter(const char *path, const char *src, size_t len, int fd,
struct strbuf *dst, const char *cmd)
{
/*
@@ -434,17 +457,11 @@ static int apply_filter(const char *path, const char *src, size_t len, int fd,
*
* (child --> cmd) --> us
*/
- int ret = 1;
+ int err = 0;
struct strbuf nbuf = STRBUF_INIT;
struct async async;
struct filter_params params;
- if (!cmd || !*cmd)
- return 0;
-
- if (!dst)
- return 1;
-
memset(&async, 0, sizeof(async));
async.proc = filter_buffer_or_fd;
async.data = &params;
@@ -460,23 +477,304 @@ static int apply_filter(const char *path, const char *src, size_t len, int fd,
return 0; /* error was already reported */
if (strbuf_read(&nbuf, async.out, len) < 0) {
- error("read from external filter %s failed", cmd);
- ret = 0;
+ err = error("read from external filter '%s' failed", cmd);
}
if (close(async.out)) {
- error("read from external filter %s failed", cmd);
- ret = 0;
+ err = error("read from external filter '%s' failed", cmd);
}
if (finish_async(&async)) {
- error("external filter %s failed", cmd);
- ret = 0;
+ err = error("external filter '%s' failed", cmd);
}
- if (ret) {
+ if (!err) {
strbuf_swap(dst, &nbuf);
}
strbuf_release(&nbuf);
- return ret;
+ return !err;
+}
+
+#define CAP_CLEAN (1u<<0)
+#define CAP_SMUDGE (1u<<1)
+
+struct cmd2process {
+ struct hashmap_entry ent; /* must be the first member! */
+ unsigned int supported_capabilities;
+ const char *cmd;
+ struct child_process process;
+};
+
+static int cmd_process_map_initialized;
+static struct hashmap cmd_process_map;
+
+static int cmd2process_cmp(const struct cmd2process *e1,
+ const struct cmd2process *e2,
+ const void *unused)
+{
+ return strcmp(e1->cmd, e2->cmd);
+}
+
+static struct cmd2process *find_multi_file_filter_entry(struct hashmap *hashmap, const char *cmd)
+{
+ struct cmd2process key;
+ hashmap_entry_init(&key, strhash(cmd));
+ key.cmd = cmd;
+ return hashmap_get(hashmap, &key, NULL);
+}
+
+static int packet_write_list(int fd, const char *line, ...)
+{
+ va_list args;
+ int err;
+ va_start(args, line);
+ for (;;) {
+ if (!line)
+ break;
+ if (strlen(line) > LARGE_PACKET_DATA_MAX)
+ return -1;
+ err = packet_write_fmt_gently(fd, "%s\n", line);
+ if (err)
+ return err;
+ line = va_arg(args, const char*);
+ }
+ va_end(args);
+ return packet_flush_gently(fd);
+}
+
+static void read_multi_file_filter_status(int fd, struct strbuf *status)
+{
+ struct strbuf **pair;
+ char *line;
+ for (;;) {
+ line = packet_read_line(fd, NULL);
+ if (!line)
+ break;
+ pair = strbuf_split_str(line, '=', 2);
+ if (pair[0] && pair[0]->len && pair[1]) {
+ /* the last "status=<foo>" line wins */
+ if (!strcmp(pair[0]->buf, "status=")) {
+ strbuf_reset(status);
+ strbuf_addbuf(status, pair[1]);
+ }
+ }
+ strbuf_list_free(pair);
+ }
+}
+
+static void kill_multi_file_filter(struct hashmap *hashmap, struct cmd2process *entry)
+{
+ if (!entry)
+ return;
+
+ entry->process.clean_on_exit = 0;
+ kill(entry->process.pid, SIGTERM);
+ finish_command(&entry->process);
+
+ hashmap_remove(hashmap, entry, NULL);
+ free(entry);
+}
+
+static void stop_multi_file_filter(struct child_process *process)
+{
+ sigchain_push(SIGPIPE, SIG_IGN);
+ /* Closing the pipe signals the filter to initiate a shutdown. */
+ close(process->in);
+ close(process->out);
+ sigchain_pop(SIGPIPE);
+ /* Finish command will wait until the shutdown is complete. */
+ finish_command(process);
+}
+
+static struct cmd2process *start_multi_file_filter(struct hashmap *hashmap, const char *cmd)
+{
+ int err;
+ struct cmd2process *entry;
+ struct child_process *process;
+ const char *argv[] = { cmd, NULL };
+ struct string_list cap_list = STRING_LIST_INIT_NODUP;
+ char *cap_buf;
+ const char *cap_name;
+
+ entry = xmalloc(sizeof(*entry));
+ entry->cmd = cmd;
+ entry->supported_capabilities = 0;
+ process = &entry->process;
+
+ child_process_init(process);
+ process->argv = argv;
+ process->use_shell = 1;
+ process->in = -1;
+ process->out = -1;
+ process->clean_on_exit = 1;
+ process->clean_on_exit_handler = stop_multi_file_filter;
+
+ if (start_command(process)) {
+ error("cannot fork to run external filter '%s'", cmd);
+ return NULL;
+ }
+
+ hashmap_entry_init(entry, strhash(cmd));
+
+ sigchain_push(SIGPIPE, SIG_IGN);
+
+ err = packet_write_list(process->in, "git-filter-client", "version=2", NULL);
+ if (err)
+ goto done;
+
+ err = strcmp(packet_read_line(process->out, NULL), "git-filter-server");
+ if (err) {
+ error("external filter '%s' does not support filter protocol version 2", cmd);
+ goto done;
+ }
+ err = strcmp(packet_read_line(process->out, NULL), "version=2");
+ if (err)
+ goto done;
+ err = packet_read_line(process->out, NULL) != NULL;
+ if (err)
+ goto done;
+
+ err = packet_write_list(process->in, "capability=clean", "capability=smudge", NULL);
+
+ for (;;) {
+ cap_buf = packet_read_line(process->out, NULL);
+ if (!cap_buf)
+ break;
+ string_list_split_in_place(&cap_list, cap_buf, '=', 1);
+
+ if (cap_list.nr != 2 || strcmp(cap_list.items[0].string, "capability"))
+ continue;
+
+ cap_name = cap_list.items[1].string;
+ if (!strcmp(cap_name, "clean")) {
+ entry->supported_capabilities |= CAP_CLEAN;
+ } else if (!strcmp(cap_name, "smudge")) {
+ entry->supported_capabilities |= CAP_SMUDGE;
+ } else {
+ warning(
+ "external filter '%s' requested unsupported filter capability '%s'",
+ cmd, cap_name
+ );
+ }
+
+ string_list_clear(&cap_list, 0);
+ }
+
+done:
+ sigchain_pop(SIGPIPE);
+
+ if (err || errno == EPIPE) {
+ error("initialization for external filter '%s' failed", cmd);
+ kill_multi_file_filter(hashmap, entry);
+ return NULL;
+ }
+
+ hashmap_add(hashmap, entry);
+ return entry;
+}
+
+static int apply_multi_file_filter(const char *path, const char *src, size_t len,
+ int fd, struct strbuf *dst, const char *cmd,
+ const unsigned int wanted_capability)
+{
+ int err;
+ struct cmd2process *entry;
+ struct child_process *process;
+ struct strbuf nbuf = STRBUF_INIT;
+ struct strbuf filter_status = STRBUF_INIT;
+ const char *filter_type;
+
+ if (!cmd_process_map_initialized) {
+ cmd_process_map_initialized = 1;
+ hashmap_init(&cmd_process_map, (hashmap_cmp_fn) cmd2process_cmp, 0);
+ entry = NULL;
+ } else {
+ entry = find_multi_file_filter_entry(&cmd_process_map, cmd);
+ }
+
+ fflush(NULL);
+
+ if (!entry) {
+ entry = start_multi_file_filter(&cmd_process_map, cmd);
+ if (!entry)
+ return 0;
+ }
+ process = &entry->process;
+
+ if (!(wanted_capability & entry->supported_capabilities))
+ return 0;
+
+ if (CAP_CLEAN & wanted_capability)
+ filter_type = "clean";
+ else if (CAP_SMUDGE & wanted_capability)
+ filter_type = "smudge";
+ else
+ die("unexpected filter type");
+
+ sigchain_push(SIGPIPE, SIG_IGN);
+
+ assert(strlen(filter_type) < LARGE_PACKET_DATA_MAX - strlen("command=\n"));
+ err = packet_write_fmt_gently(process->in, "command=%s\n", filter_type);
+ if (err)
+ goto done;
+
+ err = strlen(path) > LARGE_PACKET_DATA_MAX - strlen("pathname=\n");
+ if (err) {
+ error("path name too long for external filter");
+ goto done;
+ }
+
+ err = packet_write_fmt_gently(process->in, "pathname=%s\n", path);
+ if (err)
+ goto done;
+
+ err = packet_flush_gently(process->in);
+ if (err)
+ goto done;
+
+ if (fd >= 0)
+ err = write_packetized_from_fd(fd, process->in);
+ else
+ err = write_packetized_from_buf(src, len, process->in);
+ if (err)
+ goto done;
+
+ read_multi_file_filter_status(process->out, &filter_status);
+ err = strcmp(filter_status.buf, "success");
+ if (err)
+ goto done;
+
+ err = read_packetized_to_strbuf(process->out, &nbuf) < 0;
+ if (err)
+ goto done;
+
+ read_multi_file_filter_status(process->out, &filter_status);
+ err = strcmp(filter_status.buf, "success");
+
+done:
+ sigchain_pop(SIGPIPE);
+
+ if (err || errno == EPIPE) {
+ if (!strcmp(filter_status.buf, "error")) {
+ /* The filter signaled a problem with the file. */
+ } else if (!strcmp(filter_status.buf, "abort")) {
+ /*
+ * The filter signaled a permanent problem. Don't try to filter
+ * files with the same command for the lifetime of the current
+ * Git process.
+ */
+ entry->supported_capabilities &= ~wanted_capability;
+ } else {
+ /*
+ * Something went wrong with the protocol filter.
+ * Force shutdown and restart if another blob requires filtering.
+ */
+ error("external filter '%s' failed", cmd);
+ kill_multi_file_filter(&cmd_process_map, entry);
+ }
+ } else {
+ strbuf_swap(dst, &nbuf);
+ }
+ strbuf_release(&nbuf);
+ return !err;
}
static struct convert_driver {
@@ -484,9 +782,35 @@ static struct convert_driver {
struct convert_driver *next;
const char *smudge;
const char *clean;
+ const char *process;
int required;
} *user_convert, **user_convert_tail;
+static int apply_filter(const char *path, const char *src, size_t len,
+ int fd, struct strbuf *dst, struct convert_driver *drv,
+ const unsigned int wanted_capability)
+{
+ const char *cmd = NULL;
+
+ if (!drv)
+ return 0;
+
+ if (!dst)
+ return 1;
+
+ if ((CAP_CLEAN & wanted_capability) && !drv->process && drv->clean)
+ cmd = drv->clean;
+ else if ((CAP_SMUDGE & wanted_capability) && !drv->process && drv->smudge)
+ cmd = drv->smudge;
+
+ if (cmd && *cmd)
+ return apply_single_file_filter(path, src, len, fd, dst, cmd);
+ else if (drv->process && *drv->process)
+ return apply_multi_file_filter(path, src, len, fd, dst, drv->process, wanted_capability);
+
+ return 0;
+}
+
static int read_convert_config(const char *var, const char *value, void *cb)
{
const char *key, *name;
@@ -524,6 +848,9 @@ static int read_convert_config(const char *var, const char *value, void *cb)
if (!strcmp("clean", key))
return git_config_string(&drv->clean, var, value);
+ if (!strcmp("process", key))
+ return git_config_string(&drv->process, var, value);
+
if (!strcmp("required", key)) {
drv->required = git_config_bool(var, value);
return 0;
@@ -825,7 +1152,7 @@ int would_convert_to_git_filter_fd(const char *path)
if (!ca.drv->required)
return 0;
- return apply_filter(path, NULL, 0, -1, NULL, ca.drv->clean);
+ return apply_filter(path, NULL, 0, -1, NULL, ca.drv, CAP_CLEAN);
}
const char *get_convert_attr_ascii(const char *path)
@@ -858,18 +1185,12 @@ 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) {
- filter = ca.drv->clean;
- required = ca.drv->required;
- }
- ret |= apply_filter(path, src, len, -1, dst, filter);
- if (!ret && required)
+ ret |= apply_filter(path, src, len, -1, dst, ca.drv, CAP_CLEAN);
+ if (!ret && ca.drv && ca.drv->required)
die("%s: clean filter '%s' failed", path, ca.drv->name);
if (ret && dst) {
@@ -891,9 +1212,9 @@ void convert_to_git_filter_fd(const char *path, int fd, struct strbuf *dst,
convert_attrs(&ca, path);
assert(ca.drv);
- assert(ca.drv->clean);
+ assert(ca.drv->clean || ca.drv->process);
- if (!apply_filter(path, NULL, 0, fd, dst, ca.drv->clean))
+ if (!apply_filter(path, NULL, 0, fd, dst, ca.drv, CAP_CLEAN))
die("%s: clean filter '%s' failed", path, ca.drv->name);
crlf_to_git(path, dst->buf, dst->len, dst, ca.crlf_action, checksafe);
@@ -905,15 +1226,9 @@ static int convert_to_working_tree_internal(const char *path, const char *src,
int normalizing)
{
int ret = 0, ret_filter = 0;
- const char *filter = NULL;
- int required = 0;
struct conv_attrs ca;
convert_attrs(&ca, path);
- if (ca.drv) {
- filter = ca.drv->smudge;
- required = ca.drv->required;
- }
ret |= ident_to_worktree(path, src, len, dst, ca.ident);
if (ret) {
@@ -922,9 +1237,10 @@ static int convert_to_working_tree_internal(const char *path, const char *src,
}
/*
* CRLF conversion can be skipped if normalizing, unless there
- * is a smudge filter. The filter might expect CRLFs.
+ * is a smudge or process filter (even if the process filter doesn't
+ * support smudge). The filters might expect CRLFs.
*/
- if (filter || !normalizing) {
+ if ((ca.drv && (ca.drv->smudge || ca.drv->process)) || !normalizing) {
ret |= crlf_to_worktree(path, src, len, dst, ca.crlf_action);
if (ret) {
src = dst->buf;
@@ -932,8 +1248,8 @@ static int convert_to_working_tree_internal(const char *path, const char *src,
}
}
- ret_filter = apply_filter(path, src, len, -1, dst, filter);
- if (!ret_filter && required)
+ ret_filter = apply_filter(path, src, len, -1, dst, ca.drv, CAP_SMUDGE);
+ if (!ret_filter && ca.drv && ca.drv->required)
die("%s: smudge filter %s failed", path, ca.drv->name);
return ret | ret_filter;
@@ -1385,7 +1701,7 @@ struct stream_filter *get_stream_filter(const char *path, const unsigned char *s
struct stream_filter *filter = NULL;
convert_attrs(&ca, path);
- if (ca.drv && (ca.drv->smudge || ca.drv->clean))
+ if (ca.drv && (ca.drv->process || ca.drv->smudge || ca.drv->clean))
return NULL;
if (ca.crlf_action == CRLF_AUTO || ca.crlf_action == CRLF_AUTO_CRLF)
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-19 18:35:58 +0000