diff options
Diffstat (limited to 'convert.c')
| -rw-r--r-- | convert.c | 787 |
1 files changed, 587 insertions, 200 deletions
@@ -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. @@ -13,18 +14,25 @@ * translation when the "text" attribute or "auto_crlf" option is set. */ +/* 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_GUESS = -1, - CRLF_BINARY = 0, + CRLF_UNDEFINED, + CRLF_BINARY, CRLF_TEXT, - CRLF_INPUT, - CRLF_CRLF, - CRLF_AUTO + CRLF_TEXT_INPUT, + CRLF_TEXT_CRLF, + CRLF_AUTO, + CRLF_AUTO_INPUT, + CRLF_AUTO_CRLF }; struct text_stat { /* NUL, CR, LF and CRLF counts */ - unsigned nul, cr, lf, crlf; + unsigned nul, lonecr, lonelf, crlf; /* These are just approximations! */ unsigned printable, nonprintable; @@ -39,13 +47,15 @@ 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) @@ -75,23 +85,84 @@ 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 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 char *path) +{ + const char *ret; + unsigned long sz; + void *data = read_blob_data_from_cache(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; } @@ -100,54 +171,48 @@ static enum eol output_eol(enum crlf_action crlf_action) switch (crlf_action) { case CRLF_BINARY: return EOL_UNSET; - case CRLF_CRLF: + case CRLF_TEXT_CRLF: return EOL_CRLF; - case CRLF_INPUT: + case CRLF_TEXT_INPUT: + return EOL_LF; + case CRLF_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 (core_eol == EOL_UNSET) - return EOL_NATIVE; + /* fall through */ + return text_eol_is_crlf() ? EOL_CRLF : EOL_LF; } + warning("Illegal crlf_action %d\n", (int)crlf_action); return core_eol; } 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->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); } } @@ -165,15 +230,37 @@ 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 || - (crlf_action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE) || (src && !len)) return 0; @@ -185,36 +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_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 (crlf_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(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, crlf_action, &stats, checksafe); - - /* Optimization: No CR? Nothing to convert, regardless. */ - if (!stats.cr) + if (!convert_crlf_into_lf) return 0; /* @@ -228,7 +317,7 @@ static int crlf_to_git(const char *path, const char *src, size_t len, if (strbuf_avail(buf) + buf->len < len) strbuf_grow(buf, len - buf->len); dst = buf->buf; - if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) { + if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) { /* * If we guessed, we already know we rejected a file with * lone CR, and we can strip a CR without looking at what @@ -260,36 +349,14 @@ static int crlf_to_worktree(const char *path, const char *src, size_t len, return 0; gather_stats(src, len, &stats); - - /* No LF? Nothing to convert, regardless. */ - if (!stats.lf) + if (!will_convert_lf_to_crlf(len, &stats, crlf_action)) return 0; - /* Was it already in CRLF format? */ - if (stats.lf == stats.crlf) - return 0; - - if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) { - if (crlf_action == CRLF_GUESS) { - /* If 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) @@ -351,32 +418,37 @@ 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); if (params->src) { - write_err = (write_in_full(child_process.in, params->src, params->size) < 0); + 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; } 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) { /* @@ -385,17 +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) - return 0; - - if (!dst) - return 1; - memset(&async, 0, sizeof(async)); async.proc = filter_buffer_or_fd; async.data = ¶ms; @@ -411,23 +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 { @@ -435,9 +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; @@ -475,6 +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; @@ -652,7 +1028,7 @@ static int ident_to_worktree(const char *path, const char *src, size_t len, return 1; } -static enum crlf_action 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; @@ -663,13 +1039,13 @@ static enum crlf_action git_path_check_crlf(const char *path, struct git_attr_ch else if (ATTR_UNSET(value)) ; else if (!strcmp(value, "input")) - return CRLF_INPUT; + return CRLF_TEXT_INPUT; else if (!strcmp(value, "auto")) return CRLF_AUTO; - return CRLF_GUESS; + return CRLF_UNDEFINED; } -static enum eol git_path_check_eol(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; @@ -682,8 +1058,7 @@ static enum eol git_path_check_eol(const char *path, struct git_attr_check *chec 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; @@ -696,61 +1071,64 @@ 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 crlf_action input_crlf_action(enum crlf_action text_attr, enum eol eol_attr) -{ - 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; -} - struct conv_attrs { struct convert_driver *drv; - enum crlf_action crlf_action; - enum eol eol_attr; + enum crlf_action attr_action; /* What attr says */ + enum crlf_action crlf_action; /* When no attr is set, use core.autocrlf */ int ident; }; -static const char *conv_attr_name[] = { - "crlf", "ident", "filter", "eol", "text", -}; -#define NUM_CONV_ATTRS ARRAY_SIZE(conv_attr_name) - static void convert_attrs(struct conv_attrs *ca, const char *path) { - int i; - static struct git_attr_check ccheck[NUM_CONV_ATTRS]; + static struct attr_check *check; - if (!ccheck[0].attr) { - for (i = 0; i < NUM_CONV_ATTRS; i++) - ccheck[i].attr = git_attr(conv_attr_name[i]); + 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, NUM_CONV_ATTRS, ccheck)) { - ca->crlf_action = git_path_check_crlf(path, ccheck + 4); - if (ca->crlf_action == CRLF_GUESS) - ca->crlf_action = git_path_check_crlf(path, ccheck + 0); - ca->ident = git_path_check_ident(path, ccheck + 1); - ca->drv = git_path_check_convert(path, ccheck + 2); - ca->eol_attr = git_path_check_eol(path, ccheck + 3); + 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->attr_action = ca->crlf_action; + ca->ident = git_path_check_ident(ccheck + 1); + ca->drv = git_path_check_convert(ccheck + 2); + if (ca->crlf_action != CRLF_BINARY) { + 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; + } + ca->attr_action = ca->crlf_action; } else { ca->drv = NULL; - ca->crlf_action = CRLF_GUESS; - ca->eol_attr = EOL_UNSET; + ca->crlf_action = CRLF_UNDEFINED; ca->ident = 0; } + if (ca->crlf_action == CRLF_TEXT) + ca->crlf_action = text_eol_is_crlf() ? CRLF_TEXT_CRLF : CRLF_TEXT_INPUT; + if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_FALSE) + ca->crlf_action = CRLF_BINARY; + if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_TRUE) + ca->crlf_action = CRLF_AUTO_CRLF; + if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_INPUT) + ca->crlf_action = CRLF_AUTO_INPUT; } int would_convert_to_git_filter_fd(const char *path) @@ -769,32 +1147,51 @@ 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) +{ + 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 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) { 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 && dst) { src = dst->buf; @@ -810,12 +1207,11 @@ 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); - 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); } @@ -825,15 +1221,9 @@ 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) { @@ -842,10 +1232,10 @@ 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) { - ca.crlf_action = input_crlf_action(ca.crlf_action, ca.eol_attr); + 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; @@ -853,8 +1243,8 @@ 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; @@ -872,7 +1262,7 @@ 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, SAFE_CRLF_FALSE); + return ret | convert_to_git(path, src, len, dst, SAFE_CRLF_RENORMALIZE); } /***************************************************************** @@ -1284,7 +1674,8 @@ static struct stream_filter *ident_filter(const unsigned char *sha1) { struct ident_filter *ident = xmalloc(sizeof(*ident)); - sprintf(ident->ident, ": %s $", sha1_to_hex(sha1)); + xsnprintf(ident->ident, sizeof(ident->ident), + ": %s $", sha1_to_hex(sha1)); strbuf_init(&ident->left, 0); ident->filter.vtbl = &ident_vtbl; ident->state = 0; @@ -1302,26 +1693,22 @@ static struct stream_filter *ident_filter(const unsigned char *sha1) struct stream_filter *get_stream_filter(const char *path, const unsigned char *sha1) { struct conv_attrs ca; - enum crlf_action crlf_action; 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.drv && (ca.drv->smudge || ca.drv->clean)) - return filter; + if (ca.crlf_action == CRLF_AUTO || ca.crlf_action == CRLF_AUTO_CRLF) + return NULL; if (ca.ident) filter = ident_filter(sha1); - crlf_action = input_crlf_action(ca.crlf_action, ca.eol_attr); - - if ((crlf_action == CRLF_BINARY) || (crlf_action == CRLF_INPUT) || - (crlf_action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE)) - filter = cascade_filter(filter, &null_filter_singleton); - - else if (output_eol(crlf_action) == EOL_CRLF && - !(crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS)) + 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; } |