summaryrefslogtreecommitdiff
path: root/convert.c
diff options
context:
space:
mode:
Diffstat (limited to 'convert.c')
-rw-r--r--convert.c1399
1 files changed, 1130 insertions, 269 deletions
diff --git a/convert.c b/convert.c
index d5aebed48d..20d7ab67bd 100644
--- a/convert.c
+++ b/convert.c
@@ -1,7 +1,12 @@
+#define NO_THE_INDEX_COMPATIBILITY_MACROS
#include "cache.h"
+#include "config.h"
#include "attr.h"
#include "run-command.h"
#include "quote.h"
+#include "sigchain.h"
+#include "pkt-line.h"
+#include "sub-process.h"
/*
* convert.c - convert a file when checking it out and checking it in.
@@ -12,18 +17,25 @@
* translation when the "text" attribute or "auto_crlf" option is set.
*/
-enum action {
- CRLF_GUESS = -1,
- CRLF_BINARY = 0,
+/* Stat bits: When BIN is set, the txt bits are unset */
+#define CONVERT_STAT_BITS_TXT_LF 0x1
+#define CONVERT_STAT_BITS_TXT_CRLF 0x2
+#define CONVERT_STAT_BITS_BIN 0x4
+
+enum crlf_action {
+ CRLF_UNDEFINED,
+ CRLF_BINARY,
CRLF_TEXT,
- CRLF_INPUT,
- CRLF_CRLF,
+ 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;
@@ -38,13 +50,15 @@ static void gather_stats(const char *buf, unsigned long size, struct text_stat *
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)
@@ -74,167 +88,242 @@ static void gather_stats(const char *buf, unsigned long size, struct text_stat *
/*
* The same heuristics as diff.c::mmfile_is_binary()
+ * We treat files with bare CR as binary
*/
-static int is_binary(unsigned long size, struct text_stat *stats)
+static int convert_is_binary(unsigned long size, const struct text_stat *stats)
{
-
+ if (stats->lonecr)
+ return 1;
if (stats->nul)
return 1;
if ((stats->printable >> 7) < stats->nonprintable)
return 1;
- /*
- * Other heuristics? Average line length might be relevant,
- * as might LF vs CR vs CRLF counts..
- *
- * NOTE! It might be normal to have a low ratio of CRLF to LF
- * (somebody starts with a LF-only file and edits it with an editor
- * that adds CRLF only to lines that are added..). But do we
- * want to support CR-only? Probably not.
- */
return 0;
}
-static enum eol determine_output_conversion(enum action action)
+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))
+ 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)
+{
+ unsigned int convert_stats = gather_convert_stats(data, size);
+
+ if (convert_stats & CONVERT_STAT_BITS_BIN)
+ return "-text";
+ switch (convert_stats) {
+ case CONVERT_STAT_BITS_TXT_LF:
+ return "lf";
+ case CONVERT_STAT_BITS_TXT_CRLF:
+ return "crlf";
+ case CONVERT_STAT_BITS_TXT_LF | CONVERT_STAT_BITS_TXT_CRLF:
+ return "mixed";
+ default:
+ return "none";
+ }
+}
+
+const char *get_cached_convert_stats_ascii(const struct index_state *istate,
+ const char *path)
+{
+ const char *ret;
+ unsigned long sz;
+ void *data = read_blob_data_from_index(istate, path, &sz);
+ ret = gather_convert_stats_ascii(data, sz);
+ free(data);
+ return ret;
+}
+
+const char *get_wt_convert_stats_ascii(const char *path)
+{
+ const char *ret = "";
+ struct strbuf sb = STRBUF_INIT;
+ if (strbuf_read_file(&sb, path, 0) >= 0)
+ ret = gather_convert_stats_ascii(sb.buf, sb.len);
+ strbuf_release(&sb);
+ 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 (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_UNDEFINED:
+ case CRLF_AUTO_CRLF:
+ return EOL_CRLF;
+ case CRLF_AUTO_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;
+ /* fall through */
+ return text_eol_is_crlf() ? EOL_CRLF : EOL_LF;
}
- return eol;
+ warning("Illegal crlf_action %d\n", (int)crlf_action);
+ return core_eol;
}
-static void check_safe_crlf(const char *path, enum action action,
- struct text_stat *stats, enum safe_crlf checksafe)
+static void check_safe_crlf(const char *path, enum crlf_action crlf_action,
+ struct text_stat *old_stats, struct text_stat *new_stats,
+ enum safe_crlf checksafe)
{
- if (!checksafe)
- return;
-
- if (determine_output_conversion(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 (determine_output_conversion(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->lf != stats->crlf) {
- 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);
}
}
-static int has_cr_in_index(const char *path)
+static int has_cr_in_index(const struct index_state *istate, 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);
+ data = read_blob_data_from_index(istate, path, &sz);
+ if (!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, enum action action, enum safe_crlf checksafe)
+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 struct index_state *istate,
+ 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 (action == CRLF_BINARY ||
- (action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE) || !len)
+ if (crlf_action == CRLF_BINARY ||
+ (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);
+ /* Optimization: No CRLF? Nothing to convert, regardless. */
+ convert_crlf_into_lf = !!stats.crlf;
- 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
- * stuff?
- */
- if (stats.cr != 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;
-
/*
- * And add some heuristics for binary vs text, of course...
+ * 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 (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;
+ if ((checksafe != SAFE_CRLF_RENORMALIZE) &&
+ has_cr_in_index(istate, path))
+ convert_crlf_into_lf = 0;
+ }
+ 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);
}
-
- check_safe_crlf(path, action, &stats, checksafe);
-
- /* Optimization: No CR? Nothing to convert, regardless. */
- if (!stats.cr)
+ if (!convert_crlf_into_lf)
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);
dst = buf->buf;
- if (action == CRLF_AUTO || 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
@@ -257,45 +346,23 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
}
static int crlf_to_worktree(const char *path, const char *src, size_t len,
- struct strbuf *buf, enum action action)
+ struct strbuf *buf, enum crlf_action crlf_action)
{
char *to_free = NULL;
struct text_stat stats;
- if (!len || determine_output_conversion(action) != EOL_CRLF)
+ if (!len || output_eol(crlf_action) != EOL_CRLF)
return 0;
gather_stats(src, len, &stats);
-
- /* No LF? Nothing to convert, regardless. */
- if (!stats.lf)
- return 0;
-
- /* Was it already in CRLF format? */
- if (stats.lf == stats.crlf)
+ if (!will_convert_lf_to_crlf(len, &stats, crlf_action))
return 0;
- 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;
-
- if (is_binary(len, &stats))
- return 0;
- }
-
/* are we "faking" in place editing ? */
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)
@@ -318,16 +385,17 @@ 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 };
@@ -350,30 +418,45 @@ 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;
child_process.out = out;
- if (start_command(&child_process))
- return error("cannot fork to run external filter %s", params->cmd);
+ if (start_command(&child_process)) {
+ strbuf_release(&cmd);
+ return error("cannot fork to run external filter '%s'", params->cmd);
+ }
+
+ sigchain_push(SIGPIPE, SIG_IGN);
+
+ if (params->src) {
+ write_err = (write_in_full(child_process.in,
+ params->src, params->size) < 0);
+ if (errno == EPIPE)
+ write_err = 0;
+ } else {
+ write_err = copy_fd(params->fd, child_process.in);
+ if (write_err == COPY_WRITE_ERROR && errno == EPIPE)
+ write_err = 0;
+ }
- 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);
+ 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,
+static int apply_single_file_filter(const char *path, const char *src, size_t len, int fd,
struct strbuf *dst, const char *cmd)
{
/*
@@ -382,20 +465,18 @@ static int apply_filter(const char *path, const char *src, size_t len,
*
* (child --> cmd) --> us
*/
- int ret = 1;
+ int err = 0;
struct strbuf nbuf = STRBUF_INIT;
struct async async;
struct filter_params params;
- if (!cmd)
- return 0;
-
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;
@@ -404,23 +485,235 @@ static int apply_filter(const char *path, const char *src, size_t len,
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)
+#define CAP_DELAY (1u<<2)
+
+struct cmd2process {
+ struct subprocess_entry subprocess; /* must be the first member! */
+ unsigned int supported_capabilities;
+};
+
+static int subprocess_map_initialized;
+static struct hashmap subprocess_map;
+
+static int start_multi_file_filter_fn(struct subprocess_entry *subprocess)
+{
+ static int versions[] = {2, 0};
+ static struct subprocess_capability capabilities[] = {
+ { "clean", CAP_CLEAN },
+ { "smudge", CAP_SMUDGE },
+ { "delay", CAP_DELAY },
+ { NULL, 0 }
+ };
+ struct cmd2process *entry = (struct cmd2process *)subprocess;
+ return subprocess_handshake(subprocess, "git-filter", versions, NULL,
+ capabilities,
+ &entry->supported_capabilities);
+}
+
+static void handle_filter_error(const struct strbuf *filter_status,
+ struct cmd2process *entry,
+ const unsigned int wanted_capability) {
+ if (!strcmp(filter_status->buf, "error"))
+ ; /* The filter signaled a problem with the file. */
+ else if (!strcmp(filter_status->buf, "abort") && wanted_capability) {
+ /*
+ * 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", entry->subprocess.cmd);
+ subprocess_stop(&subprocess_map, &entry->subprocess);
+ free(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,
+ struct delayed_checkout *dco)
+{
+ int err;
+ int can_delay = 0;
+ struct cmd2process *entry;
+ struct child_process *process;
+ struct strbuf nbuf = STRBUF_INIT;
+ struct strbuf filter_status = STRBUF_INIT;
+ const char *filter_type;
+
+ if (!subprocess_map_initialized) {
+ subprocess_map_initialized = 1;
+ hashmap_init(&subprocess_map, cmd2process_cmp, NULL, 0);
+ entry = NULL;
+ } else {
+ entry = (struct cmd2process *)subprocess_find_entry(&subprocess_map, cmd);
+ }
+
+ fflush(NULL);
+
+ if (!entry) {
+ entry = xmalloc(sizeof(*entry));
+ entry->supported_capabilities = 0;
+
+ if (subprocess_start(&subprocess_map, &entry->subprocess, cmd, start_multi_file_filter_fn)) {
+ free(entry);
+ return 0;
+ }
+ }
+ process = &entry->subprocess.process;
+
+ if (!(entry->supported_capabilities & wanted_capability))
+ return 0;
+
+ if (wanted_capability & CAP_CLEAN)
+ filter_type = "clean";
+ else if (wanted_capability & CAP_SMUDGE)
+ 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;
+
+ if ((entry->supported_capabilities & CAP_DELAY) &&
+ dco && dco->state == CE_CAN_DELAY) {
+ can_delay = 1;
+ err = packet_write_fmt_gently(process->in, "can-delay=1\n");
+ 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;
+
+ err = subprocess_read_status(process->out, &filter_status);
+ if (err)
+ goto done;
+
+ if (can_delay && !strcmp(filter_status.buf, "delayed")) {
+ string_list_insert(&dco->filters, cmd);
+ string_list_insert(&dco->paths, path);
+ } else {
+ /* The filter got the blob and wants to send us a response. */
+ err = strcmp(filter_status.buf, "success");
+ if (err)
+ goto done;
+
+ err = read_packetized_to_strbuf(process->out, &nbuf) < 0;
+ if (err)
+ goto done;
+
+ err = subprocess_read_status(process->out, &filter_status);
+ if (err)
+ goto done;
+
+ err = strcmp(filter_status.buf, "success");
+ }
+
+done:
+ sigchain_pop(SIGPIPE);
+
+ if (err)
+ handle_filter_error(&filter_status, entry, wanted_capability);
+ else
+ strbuf_swap(dst, &nbuf);
+ strbuf_release(&nbuf);
+ return !err;
+}
+
+
+int async_query_available_blobs(const char *cmd, struct string_list *available_paths)
+{
+ int err;
+ char *line;
+ struct cmd2process *entry;
+ struct child_process *process;
+ struct strbuf filter_status = STRBUF_INIT;
+
+ assert(subprocess_map_initialized);
+ entry = (struct cmd2process *)subprocess_find_entry(&subprocess_map, cmd);
+ if (!entry) {
+ error("external filter '%s' is not available anymore although "
+ "not all paths have been filtered", cmd);
+ return 0;
+ }
+ process = &entry->subprocess.process;
+ sigchain_push(SIGPIPE, SIG_IGN);
+
+ err = packet_write_fmt_gently(
+ process->in, "command=list_available_blobs\n");
+ if (err)
+ goto done;
+
+ err = packet_flush_gently(process->in);
+ if (err)
+ goto done;
+
+ while ((line = packet_read_line(process->out, NULL))) {
+ const char *path;
+ if (skip_prefix(line, "pathname=", &path))
+ string_list_insert(available_paths, xstrdup(path));
+ else
+ ; /* ignore unknown keys */
+ }
+
+ err = subprocess_read_status(process->out, &filter_status);
+ if (err)
+ goto done;
+
+ err = strcmp(filter_status.buf, "success");
+
+done:
+ sigchain_pop(SIGPIPE);
+
+ if (err)
+ handle_filter_error(&filter_status, entry, 0);
+ return !err;
}
static struct convert_driver {
@@ -428,11 +721,40 @@ 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,
+ struct delayed_checkout *dco)
+{
+ const char *cmd = NULL;
+
+ if (!drv)
+ return 0;
+
+ if (!dst)
+ return 1;
+
+ if ((wanted_capability & CAP_CLEAN) && !drv->process && drv->clean)
+ cmd = drv->clean;
+ else if ((wanted_capability & CAP_SMUDGE) && !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, dco);
+
+ return 0;
+}
+
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;
@@ -440,10 +762,8 @@ 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;
@@ -454,8 +774,6 @@ 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:
@@ -465,37 +783,21 @@ 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);
- return 0;
-}
-
-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 (!strcmp("process", key))
+ return git_config_string(&drv->process, var, value);
- 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;
- git_config(read_convert_config, NULL);
+ if (!strcmp("required", key)) {
+ drv->required = git_config_bool(var, value);
+ return 0;
}
- 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;
+
+ return 0;
}
static int count_ident(const char *cp, unsigned long size)
@@ -545,9 +847,12 @@ 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);
@@ -556,7 +861,7 @@ static int ident_to_git(const char *path, const char *src, size_t len,
dollar = memchr(src, '$', len);
if (!dollar)
break;
- memcpy(dst, src, dollar + 1 - src);
+ memmove(dst, src, dollar + 1 - src);
dst += dollar + 1 - src;
len -= dollar + 1 - src;
src = dollar + 1;
@@ -576,7 +881,7 @@ static int ident_to_git(const char *path, const char *src, size_t len,
src = dollar + 1;
}
}
- memcpy(dst, src, len);
+ memmove(dst, src, len);
strbuf_setlen(buf, dst + len - buf->buf);
return 1;
}
@@ -664,7 +969,7 @@ 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(struct attr_check_item *check)
{
const char *value = check->value;
@@ -675,13 +980,13 @@ static int git_path_check_crlf(const char *path, struct git_attr_check *check)
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 int git_path_check_eol(const char *path, struct git_attr_check *check)
+static enum eol git_path_check_eol(struct attr_check_item *check)
{
const char *value = check->value;
@@ -694,8 +999,7 @@ static int git_path_check_eol(const char *path, struct git_attr_check *check)
return EOL_UNSET;
}
-static struct convert_driver *git_path_check_convert(const char *path,
- struct git_attr_check *check)
+static struct convert_driver *git_path_check_convert(struct attr_check_item *check)
{
const char *value = check->value;
struct convert_driver *drv;
@@ -708,114 +1012,671 @@ static struct convert_driver *git_path_check_convert(const char *path,
return NULL;
}
-static int git_path_check_ident(const char *path, struct git_attr_check *check)
+static int git_path_check_ident(struct attr_check_item *check)
{
const char *value = check->value;
return !!ATTR_TRUE(value);
}
-static enum action determine_action(enum action text_attr, enum eol eol_attr)
+struct conv_attrs {
+ struct convert_driver *drv;
+ enum crlf_action attr_action; /* What attr says */
+ enum crlf_action crlf_action; /* When no attr is set, use core.autocrlf */
+ int ident;
+};
+
+static void convert_attrs(struct conv_attrs *ca, const char *path)
{
- 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;
+ static struct attr_check *check;
+
+ if (!check) {
+ check = attr_check_initl("crlf", "ident", "filter",
+ "eol", "text", NULL);
+ user_convert_tail = &user_convert;
+ git_config(read_convert_config, NULL);
+ }
+
+ if (!git_check_attr(path, check)) {
+ struct attr_check_item *ccheck = check->items;
+ ca->crlf_action = git_path_check_crlf(ccheck + 4);
+ if (ca->crlf_action == CRLF_UNDEFINED)
+ ca->crlf_action = git_path_check_crlf(ccheck + 0);
+ ca->ident = git_path_check_ident(ccheck + 1);
+ ca->drv = git_path_check_convert(ccheck + 2);
+ if (ca->crlf_action != CRLF_BINARY) {
+ enum eol eol_attr = git_path_check_eol(ccheck + 3);
+ if (ca->crlf_action == CRLF_AUTO && eol_attr == EOL_LF)
+ ca->crlf_action = CRLF_AUTO_INPUT;
+ else if (ca->crlf_action == CRLF_AUTO && eol_attr == EOL_CRLF)
+ ca->crlf_action = CRLF_AUTO_CRLF;
+ else if (eol_attr == EOL_LF)
+ ca->crlf_action = CRLF_TEXT_INPUT;
+ else if (eol_attr == EOL_CRLF)
+ ca->crlf_action = CRLF_TEXT_CRLF;
+ }
+ } else {
+ ca->drv = NULL;
+ ca->crlf_action = CRLF_UNDEFINED;
+ ca->ident = 0;
+ }
+
+ /* Save attr and make a decision for action */
+ ca->attr_action = ca->crlf_action;
+ 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)
+{
+ 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, CAP_CLEAN, NULL);
}
-int convert_to_git(const char *path, const char *src, size_t len,
+const char *get_convert_attr_ascii(const char *path)
+{
+ struct conv_attrs ca;
+
+ convert_attrs(&ca, path);
+ switch (ca.attr_action) {
+ case CRLF_UNDEFINED:
+ return "";
+ case CRLF_BINARY:
+ return "-text";
+ case CRLF_TEXT:
+ return "text";
+ case CRLF_TEXT_INPUT:
+ return "text eol=lf";
+ case CRLF_TEXT_CRLF:
+ return "text eol=crlf";
+ case CRLF_AUTO:
+ return "text=auto";
+ case CRLF_AUTO_CRLF:
+ return "text=auto eol=crlf";
+ case CRLF_AUTO_INPUT:
+ return "text=auto eol=lf";
+ }
+ return "";
+}
+
+int convert_to_git(const struct index_state *istate,
+ const char *path, const char *src, size_t len,
struct strbuf *dst, enum safe_crlf checksafe)
{
- 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;
- 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;
- }
-
- ret |= apply_filter(path, src, len, dst, filter);
- if (ret) {
+ int ret = 0;
+ struct conv_attrs ca;
+
+ convert_attrs(&ca, path);
+
+ ret |= apply_filter(path, src, len, -1, dst, ca.drv, CAP_CLEAN, NULL);
+ if (!ret && ca.drv && ca.drv->required)
+ die("%s: clean filter '%s' failed", path, ca.drv->name);
+
+ if (ret && dst) {
src = dst->buf;
len = dst->len;
}
- action = determine_action(action, eol_attr);
- ret |= crlf_to_git(path, src, len, dst, action, checksafe);
- if (ret) {
- src = dst->buf;
- len = dst->len;
+ if (checksafe != SAFE_CRLF_KEEP_CRLF) {
+ ret |= crlf_to_git(istate, path, src, len, dst, ca.crlf_action, checksafe);
+ if (ret && dst) {
+ src = dst->buf;
+ len = dst->len;
+ }
}
- return ret | ident_to_git(path, src, len, dst, ident);
+ return ret | ident_to_git(path, src, len, dst, ca.ident);
+}
+
+void convert_to_git_filter_fd(const struct index_state *istate,
+ 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 || ca.drv->process);
+
+ if (!apply_filter(path, NULL, 0, fd, dst, ca.drv, CAP_CLEAN, NULL))
+ die("%s: clean filter '%s' failed", path, ca.drv->name);
+
+ crlf_to_git(istate, 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)
-{
- 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;
- 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;
- }
-
- ret |= ident_to_worktree(path, src, len, dst, ident);
+ int normalizing, struct delayed_checkout *dco)
+{
+ int ret = 0, ret_filter = 0;
+ struct conv_attrs ca;
+
+ convert_attrs(&ca, path);
+
+ ret |= ident_to_worktree(path, src, len, dst, ca.ident);
if (ret) {
src = dst->buf;
len = dst->len;
}
/*
* 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) {
- action = determine_action(action, eol_attr);
- ret |= crlf_to_worktree(path, src, len, dst, action);
+ 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;
len = dst->len;
}
}
- return ret | apply_filter(path, src, len, dst, filter);
+
+ ret_filter = apply_filter(
+ path, src, len, -1, dst, ca.drv, CAP_SMUDGE, dco);
+ if (!ret_filter && ca.drv && ca.drv->required)
+ die("%s: smudge filter %s failed", path, ca.drv->name);
+
+ return ret | ret_filter;
+}
+
+int async_convert_to_working_tree(const char *path, const char *src,
+ size_t len, struct strbuf *dst,
+ void *dco)
+{
+ return convert_to_working_tree_internal(path, src, len, dst, 0, dco);
}
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);
+ return convert_to_working_tree_internal(path, src, len, dst, 0, NULL);
}
-int renormalize_buffer(const char *path, const char *src, size_t len, struct strbuf *dst)
+int renormalize_buffer(const struct index_state *istate, const char *path,
+ const char *src, size_t len, struct strbuf *dst)
{
- int ret = convert_to_working_tree_internal(path, src, len, dst, 1);
+ int ret = convert_to_working_tree_internal(path, src, len, dst, 1, NULL);
if (ret) {
src = dst->buf;
len = dst->len;
}
- return ret | convert_to_git(path, src, len, dst, 0);
+ return ret | convert_to_git(istate, path, src, len, dst, SAFE_CRLF_RENORMALIZE);
+}
+
+/*****************************************************************
+ *
+ * Streaming conversion support
+ *
+ *****************************************************************/
+
+typedef int (*filter_fn)(struct stream_filter *,
+ const char *input, size_t *isize_p,
+ char *output, size_t *osize_p);
+typedef void (*free_fn)(struct stream_filter *);
+
+struct stream_filter_vtbl {
+ filter_fn filter;
+ free_fn free;
+};
+
+struct stream_filter {
+ struct stream_filter_vtbl *vtbl;
+};
+
+static int null_filter_fn(struct stream_filter *filter,
+ const char *input, size_t *isize_p,
+ char *output, size_t *osize_p)
+{
+ size_t count;
+
+ if (!input)
+ return 0; /* we do not keep any states */
+ count = *isize_p;
+ if (*osize_p < count)
+ count = *osize_p;
+ if (count) {
+ memmove(output, input, count);
+ *isize_p -= count;
+ *osize_p -= count;
+ }
+ return 0;
+}
+
+static void null_free_fn(struct stream_filter *filter)
+{
+ ; /* nothing -- null instances are shared */
+}
+
+static struct stream_filter_vtbl null_vtbl = {
+ null_filter_fn,
+ null_free_fn,
+};
+
+static struct stream_filter null_filter_singleton = {
+ &null_vtbl,
+};
+
+int is_null_stream_filter(struct stream_filter *filter)
+{
+ return filter == &null_filter_singleton;
+}
+
+
+/*
+ * 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, 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;
+ }
+
+ count = *isize_p;
+ 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') {
+ 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,
+ lf_to_crlf_free_fn,
+};
+
+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
+ */
+#define FILTER_BUFFER 1024
+struct cascade_filter {
+ struct stream_filter filter;
+ struct stream_filter *one;
+ struct stream_filter *two;
+ char buf[FILTER_BUFFER];
+ int end, ptr;
+};
+
+static int cascade_filter_fn(struct stream_filter *filter,
+ const char *input, size_t *isize_p,
+ char *output, size_t *osize_p)
+{
+ struct cascade_filter *cas = (struct cascade_filter *) filter;
+ size_t filled = 0;
+ size_t sz = *osize_p;
+ size_t to_feed, remaining;
+
+ /*
+ * input -- (one) --> buf -- (two) --> output
+ */
+ while (filled < sz) {
+ remaining = sz - filled;
+
+ /* do we already have something to feed two with? */
+ if (cas->ptr < cas->end) {
+ to_feed = cas->end - cas->ptr;
+ if (stream_filter(cas->two,
+ cas->buf + cas->ptr, &to_feed,
+ output + filled, &remaining))
+ return -1;
+ cas->ptr += (cas->end - cas->ptr) - to_feed;
+ filled = sz - remaining;
+ continue;
+ }
+
+ /* feed one from upstream and have it emit into our buffer */
+ to_feed = input ? *isize_p : 0;
+ if (input && !to_feed)
+ break;
+ remaining = sizeof(cas->buf);
+ if (stream_filter(cas->one,
+ input, &to_feed,
+ cas->buf, &remaining))
+ return -1;
+ cas->end = sizeof(cas->buf) - remaining;
+ cas->ptr = 0;
+ if (input) {
+ size_t fed = *isize_p - to_feed;
+ *isize_p -= fed;
+ input += fed;
+ }
+
+ /* do we know that we drained one completely? */
+ if (input || cas->end)
+ continue;
+
+ /* tell two to drain; we have nothing more to give it */
+ to_feed = 0;
+ remaining = sz - filled;
+ if (stream_filter(cas->two,
+ NULL, &to_feed,
+ output + filled, &remaining))
+ return -1;
+ if (remaining == (sz - filled))
+ break; /* completely drained two */
+ filled = sz - remaining;
+ }
+ *osize_p -= filled;
+ return 0;
+}
+
+static void cascade_free_fn(struct stream_filter *filter)
+{
+ struct cascade_filter *cas = (struct cascade_filter *)filter;
+ free_stream_filter(cas->one);
+ free_stream_filter(cas->two);
+ free(filter);
+}
+
+static struct stream_filter_vtbl cascade_vtbl = {
+ cascade_filter_fn,
+ cascade_free_fn,
+};
+
+static struct stream_filter *cascade_filter(struct stream_filter *one,
+ struct stream_filter *two)
+{
+ struct cascade_filter *cascade;
+
+ if (!one || is_null_stream_filter(one))
+ return two;
+ if (!two || is_null_stream_filter(two))
+ return one;
+
+ cascade = xmalloc(sizeof(*cascade));
+ cascade->one = one;
+ cascade->two = two;
+ cascade->end = cascade->ptr = 0;
+ cascade->filter.vtbl = &cascade_vtbl;
+ return (struct stream_filter *)cascade;
+}
+
+/*
+ * ident filter
+ */
+#define IDENT_DRAINING (-1)
+#define IDENT_SKIPPING (-2)
+struct ident_filter {
+ struct stream_filter filter;
+ struct strbuf left;
+ int state;
+ char ident[45]; /* ": x40 $" */
+};
+
+static int is_foreign_ident(const char *str)
+{
+ int i;
+
+ if (!skip_prefix(str, "$Id: ", &str))
+ return 0;
+ for (i = 0; str[i]; i++) {
+ if (isspace(str[i]) && str[i+1] != '$')
+ return 1;
+ }
+ return 0;
+}
+
+static void ident_drain(struct ident_filter *ident, char **output_p, size_t *osize_p)
+{
+ size_t to_drain = ident->left.len;
+
+ if (*osize_p < to_drain)
+ to_drain = *osize_p;
+ if (to_drain) {
+ memcpy(*output_p, ident->left.buf, to_drain);
+ strbuf_remove(&ident->left, 0, to_drain);
+ *output_p += to_drain;
+ *osize_p -= to_drain;
+ }
+ if (!ident->left.len)
+ ident->state = 0;
+}
+
+static int ident_filter_fn(struct stream_filter *filter,
+ const char *input, size_t *isize_p,
+ char *output, size_t *osize_p)
+{
+ struct ident_filter *ident = (struct ident_filter *)filter;
+ static const char head[] = "$Id";
+
+ if (!input) {
+ /* drain upon eof */
+ switch (ident->state) {
+ default:
+ strbuf_add(&ident->left, head, ident->state);
+ /* fallthrough */
+ case IDENT_SKIPPING:
+ /* fallthrough */
+ case IDENT_DRAINING:
+ ident_drain(ident, &output, osize_p);
+ }
+ return 0;
+ }
+
+ while (*isize_p || (ident->state == IDENT_DRAINING)) {
+ int ch;
+
+ if (ident->state == IDENT_DRAINING) {
+ ident_drain(ident, &output, osize_p);
+ if (!*osize_p)
+ break;
+ continue;
+ }
+
+ ch = *(input++);
+ (*isize_p)--;
+
+ if (ident->state == IDENT_SKIPPING) {
+ /*
+ * Skipping until '$' or LF, but keeping them
+ * in case it is a foreign ident.
+ */
+ strbuf_addch(&ident->left, ch);
+ if (ch != '\n' && ch != '$')
+ continue;
+ if (ch == '$' && !is_foreign_ident(ident->left.buf)) {
+ strbuf_setlen(&ident->left, sizeof(head) - 1);
+ strbuf_addstr(&ident->left, ident->ident);
+ }
+ ident->state = IDENT_DRAINING;
+ continue;
+ }
+
+ if (ident->state < sizeof(head) &&
+ head[ident->state] == ch) {
+ ident->state++;
+ continue;
+ }
+
+ if (ident->state)
+ strbuf_add(&ident->left, head, ident->state);
+ if (ident->state == sizeof(head) - 1) {
+ if (ch != ':' && ch != '$') {
+ strbuf_addch(&ident->left, ch);
+ ident->state = 0;
+ continue;
+ }
+
+ if (ch == ':') {
+ strbuf_addch(&ident->left, ch);
+ ident->state = IDENT_SKIPPING;
+ } else {
+ strbuf_addstr(&ident->left, ident->ident);
+ ident->state = IDENT_DRAINING;
+ }
+ continue;
+ }
+
+ strbuf_addch(&ident->left, ch);
+ ident->state = IDENT_DRAINING;
+ }
+ return 0;
+}
+
+static void ident_free_fn(struct stream_filter *filter)
+{
+ struct ident_filter *ident = (struct ident_filter *)filter;
+ strbuf_release(&ident->left);
+ free(filter);
+}
+
+static struct stream_filter_vtbl ident_vtbl = {
+ ident_filter_fn,
+ ident_free_fn,
+};
+
+static struct stream_filter *ident_filter(const unsigned char *sha1)
+{
+ struct ident_filter *ident = xmalloc(sizeof(*ident));
+
+ xsnprintf(ident->ident, sizeof(ident->ident),
+ ": %s $", sha1_to_hex(sha1));
+ strbuf_init(&ident->left, 0);
+ ident->filter.vtbl = &ident_vtbl;
+ ident->state = 0;
+ return (struct stream_filter *)ident;
+}
+
+/*
+ * Return an appropriately constructed filter for the path, or NULL if
+ * the contents cannot be filtered without reading the whole thing
+ * in-core.
+ *
+ * Note that you would be crazy to set CRLF, smuge/clean or ident to a
+ * large binary blob you would want us not to slurp into the memory!
+ */
+struct stream_filter *get_stream_filter(const char *path, const unsigned char *sha1)
+{
+ struct conv_attrs ca;
+ struct stream_filter *filter = NULL;
+
+ convert_attrs(&ca, path);
+ 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)
+ return NULL;
+
+ if (ca.ident)
+ filter = ident_filter(sha1);
+
+ if (output_eol(ca.crlf_action) == EOL_CRLF)
+ filter = cascade_filter(filter, lf_to_crlf_filter());
+ else
+ filter = cascade_filter(filter, &null_filter_singleton);
+
+ return filter;
+}
+
+void free_stream_filter(struct stream_filter *filter)
+{
+ filter->vtbl->free(filter);
+}
+
+int stream_filter(struct stream_filter *filter,
+ const char *input, size_t *isize_p,
+ char *output, size_t *osize_p)
+{
+ return filter->vtbl->filter(filter, input, isize_p, output, osize_p);
}