diff options
Diffstat (limited to 'convert.c')
| -rw-r--r-- | convert.c | 854 |
1 files changed, 775 insertions, 79 deletions
@@ -1,6 +1,8 @@ #include "cache.h" #include "attr.h" #include "run-command.h" +#include "quote.h" +#include "sigchain.h" /* * convert.c - convert a file when checking it out and checking it in. @@ -8,13 +10,17 @@ * This should use the pathname to decide on whether it wants to do some * more interesting conversions (automatic gzip/unzip, general format * conversions etc etc), but by default it just does automatic CRLF<->LF - * translation when the "auto_crlf" option is set. + * translation when the "text" attribute or "auto_crlf" option is set. */ -#define CRLF_GUESS (-1) -#define CRLF_BINARY 0 -#define CRLF_TEXT 1 -#define CRLF_INPUT 2 +enum crlf_action { + CRLF_GUESS = -1, + CRLF_BINARY = 0, + CRLF_TEXT, + CRLF_INPUT, + CRLF_CRLF, + CRLF_AUTO +}; struct text_stat { /* NUL, CR, LF and CRLF counts */ @@ -89,49 +95,121 @@ static int is_binary(unsigned long size, struct text_stat *stats) return 0; } -static void check_safe_crlf(const char *path, int action, +static enum eol output_eol(enum crlf_action crlf_action) +{ + switch (crlf_action) { + case CRLF_BINARY: + return EOL_UNSET; + case CRLF_CRLF: + return EOL_CRLF; + case CRLF_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; + } + return core_eol; +} + +static void check_safe_crlf(const char *path, enum crlf_action crlf_action, struct text_stat *stats, enum safe_crlf checksafe) { if (!checksafe) return; - if (action == CRLF_INPUT || auto_crlf <= 0) { + if (output_eol(crlf_action) == EOL_LF) { /* * CRLFs would not be restored by checkout: * check if we'd remove CRLFs */ if (stats->crlf) { if (checksafe == SAFE_CRLF_WARN) - warning("CRLF will be replaced by LF in %s.", path); + 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 (auto_crlf > 0) { + } else if (output_eol(crlf_action) == EOL_CRLF) { /* * CRLFs would be added by checkout: * check if we have "naked" LFs */ if (stats->lf != stats->crlf) { if (checksafe == SAFE_CRLF_WARN) - warning("LF will be replaced by CRLF in %s", path); + 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); } } } +static int has_cr_in_index(const char *path) +{ + int pos, len; + unsigned long sz; + enum object_type type; + void *data; + int has_cr; + struct index_state *istate = &the_index; + + len = strlen(path); + pos = index_name_pos(istate, path, len); + if (pos < 0) { + /* + * We might be in the middle of a merge, in which + * case we would read stage #2 (ours). + */ + int i; + for (i = -pos - 1; + (pos < 0 && i < istate->cache_nr && + !strcmp(istate->cache[i]->name, path)); + i++) + if (ce_stage(istate->cache[i]) == 2) + pos = i; + } + if (pos < 0) + return 0; + data = read_sha1_file(istate->cache[pos]->sha1, &type, &sz); + if (!data || type != OBJ_BLOB) { + free(data); + return 0; + } + + has_cr = memchr(data, '\r', sz) != NULL; + free(data); + return has_cr; +} + static int crlf_to_git(const char *path, const char *src, size_t len, - struct strbuf *buf, int action, enum safe_crlf checksafe) + struct strbuf *buf, + enum crlf_action crlf_action, enum safe_crlf checksafe) { struct text_stat stats; char *dst; - if ((action == CRLF_BINARY) || !auto_crlf || !len) + if (crlf_action == CRLF_BINARY || + (crlf_action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE) || + (src && !len)) return 0; + /* + * If we are doing a dry-run and have no source buffer, there is + * nothing to analyze; we must assume we would convert. + */ + if (!buf && !src) + return 1; + gather_stats(src, len, &stats); - if (action == CRLF_GUESS) { + 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 @@ -145,19 +223,35 @@ static int crlf_to_git(const char *path, const char *src, size_t len, */ 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; + } } - check_safe_crlf(path, action, &stats, checksafe); + check_safe_crlf(path, crlf_action, &stats, checksafe); /* Optimization: No CR? Nothing to convert, regardless. */ if (!stats.cr) return 0; + /* + * At this point all of our source analysis is done, and we are sure we + * would convert. If we are in dry-run mode, we can give an answer. + */ + if (!buf) + return 1; + /* only grow if not in place */ if (strbuf_avail(buf) + buf->len < len) strbuf_grow(buf, len - buf->len); dst = buf->buf; - if (action == CRLF_GUESS) { + if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) { /* * If we guessed, we already know we rejected a file with * lone CR, and we can strip a CR without looking at what @@ -180,16 +274,12 @@ 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, int action) + struct strbuf *buf, enum crlf_action crlf_action) { char *to_free = NULL; struct text_stat stats; - if ((action == CRLF_BINARY) || (action == CRLF_INPUT) || - auto_crlf <= 0) - return 0; - - if (!len) + if (!len || output_eol(crlf_action) != EOL_CRLF) return 0; gather_stats(src, len, &stats); @@ -202,7 +292,14 @@ static int crlf_to_worktree(const char *path, const char *src, size_t len, if (stats.lf == stats.crlf) return 0; - if (action == CRLF_GUESS) { + 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; @@ -239,9 +336,10 @@ struct filter_params { const char *src; unsigned long size; const char *cmd; + const char *path; }; -static int filter_buffer(int fd, void *data) +static int filter_buffer(int in, int out, void *data) { /* * Spawn cmd and feed the buffer contents through its stdin. @@ -249,25 +347,50 @@ static int filter_buffer(int fd, void *data) struct child_process child_process; struct filter_params *params = (struct filter_params *)data; int write_err, status; - const char *argv[] = { "sh", "-c", params->cmd, NULL }; + const char *argv[] = { NULL, NULL }; + + /* apply % substitution to cmd */ + struct strbuf cmd = STRBUF_INIT; + struct strbuf path = STRBUF_INIT; + struct strbuf_expand_dict_entry dict[] = { + { "f", NULL, }, + { NULL, NULL, }, + }; + + /* quote the path to preserve spaces, etc. */ + sq_quote_buf(&path, params->path); + dict[0].value = path.buf; + + /* expand all %f with the quoted path */ + strbuf_expand(&cmd, params->cmd, strbuf_expand_dict_cb, &dict); + strbuf_release(&path); + + 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 = fd; + child_process.out = out; if (start_command(&child_process)) return error("cannot fork to run external filter %s", params->cmd); + sigchain_push(SIGPIPE, SIG_IGN); + 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); + sigchain_pop(SIGPIPE); + status = finish_command(&child_process); if (status) error("external filter %s failed %d", params->cmd, status); + + strbuf_release(&cmd); return (write_err || status); } @@ -288,12 +411,17 @@ static int apply_filter(const char *path, const char *src, size_t len, if (!cmd) return 0; + if (!dst) + return 1; + memset(&async, 0, sizeof(async)); async.proc = filter_buffer; async.data = ¶ms; + async.out = -1; params.src = src; params.size = len; params.cmd = cmd; + params.path = path; fflush(NULL); if (start_async(&async)) @@ -324,6 +452,7 @@ static struct convert_driver { struct convert_driver *next; const char *smudge; const char *clean; + int required; } *user_convert, **user_convert_tail; static int read_convert_config(const char *var, const char *value, void *cb) @@ -367,25 +496,12 @@ static int read_convert_config(const char *var, const char *value, void *cb) if (!strcmp("clean", ep)) 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_crlf; - static struct git_attr *attr_ident; - static struct git_attr *attr_filter; - - if (!attr_crlf) { - attr_crlf = git_attr("crlf", 4); - attr_ident = git_attr("ident", 5); - attr_filter = git_attr("filter", 6); - user_convert_tail = &user_convert; - git_config(read_convert_config, NULL); + if (!strcmp("required", ep)) { + drv->required = git_config_bool(var, value); + return 0; } - check[0].attr = attr_crlf; - check[1].attr = attr_ident; - check[2].attr = attr_filter; + + return 0; } static int count_ident(const char *cp, unsigned long size) @@ -423,6 +539,8 @@ static int count_ident(const char *cp, unsigned long size) cnt++; break; } + if (ch == '\n') + break; } } return cnt; @@ -433,9 +551,12 @@ 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); @@ -444,7 +565,7 @@ static int ident_to_git(const char *path, const char *src, size_t len, dollar = memchr(src, '$', len); if (!dollar) break; - memcpy(dst, src, dollar + 1 - src); + memmove(dst, src, dollar + 1 - src); dst += dollar + 1 - src; len -= dollar + 1 - src; src = dollar + 1; @@ -453,13 +574,18 @@ static int ident_to_git(const char *path, const char *src, size_t len, dollar = memchr(src + 3, '$', len - 3); if (!dollar) break; + if (memchr(src + 3, '\n', dollar - src - 3)) { + /* Line break before the next dollar. */ + continue; + } + memcpy(dst, "Id$", 3); dst += 3; len -= dollar + 1 - src; src = dollar + 1; } } - memcpy(dst, src, len); + memmove(dst, src, len); strbuf_setlen(buf, dst + len - buf->buf); return 1; } @@ -468,7 +594,7 @@ static int ident_to_worktree(const char *path, const char *src, size_t len, struct strbuf *buf, int ident) { unsigned char sha1[20]; - char *to_free = NULL, *dollar; + char *to_free = NULL, *dollar, *spc; int cnt; if (!ident) @@ -504,7 +630,10 @@ static int ident_to_worktree(const char *path, const char *src, size_t len, } else if (src[2] == ':') { /* * It's possible that an expanded Id has crept its way into the - * repository, we cope with that by stripping the expansion out + * repository, we cope with that by stripping the expansion out. + * This is probably not a good idea, since it will cause changes + * on checkout, which won't go away by stash, but let's keep it + * for git-style ids. */ dollar = memchr(src + 3, '$', len - 3); if (!dollar) { @@ -512,6 +641,20 @@ static int ident_to_worktree(const char *path, const char *src, size_t len, break; } + if (memchr(src + 3, '\n', dollar - src - 3)) { + /* Line break before the next dollar. */ + continue; + } + + spc = memchr(src + 4, ' ', dollar - src - 4); + if (spc && spc < dollar-1) { + /* There are spaces in unexpected places. + * This is probably an id from some other + * versioning system. Keep it for now. + */ + continue; + } + len -= dollar + 1 - src; src = dollar + 1; } else { @@ -530,7 +673,7 @@ static int ident_to_worktree(const char *path, const char *src, size_t len, return 1; } -static int git_path_check_crlf(const char *path, struct git_attr_check *check) +static enum crlf_action git_path_check_crlf(const char *path, struct git_attr_check *check) { const char *value = check->value; @@ -542,9 +685,24 @@ static int git_path_check_crlf(const char *path, struct git_attr_check *check) ; else if (!strcmp(value, "input")) return CRLF_INPUT; + else if (!strcmp(value, "auto")) + return CRLF_AUTO; return CRLF_GUESS; } +static enum eol git_path_check_eol(const char *path, struct git_attr_check *check) +{ + const char *value = check->value; + + if (ATTR_UNSET(value)) + ; + else if (!strcmp(value, "lf")) + return EOL_LF; + else if (!strcmp(value, "crlf")) + return EOL_CRLF; + return EOL_UNSET; +} + static struct convert_driver *git_path_check_convert(const char *path, struct git_attr_check *check) { @@ -566,63 +724,601 @@ static int git_path_check_ident(const char *path, struct git_attr_check *check) 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; + 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]; + + if (!ccheck[0].attr) { + for (i = 0; i < NUM_CONV_ATTRS; i++) + ccheck[i].attr = git_attr(conv_attr_name[i]); + 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); + } else { + ca->drv = NULL; + ca->crlf_action = CRLF_GUESS; + ca->eol_attr = EOL_UNSET; + ca->ident = 0; + } +} + int convert_to_git(const char *path, const char *src, size_t len, struct strbuf *dst, enum safe_crlf checksafe) { - struct git_attr_check check[3]; - int crlf = CRLF_GUESS; - int ident = 0, ret = 0; + int ret = 0; const char *filter = NULL; + int required = 0; + struct conv_attrs ca; - setup_convert_check(check); - if (!git_checkattr(path, ARRAY_SIZE(check), check)) { - struct convert_driver *drv; - crlf = git_path_check_crlf(path, check + 0); - ident = git_path_check_ident(path, check + 1); - drv = git_path_check_convert(path, check + 2); - if (drv && drv->clean) - filter = drv->clean; + convert_attrs(&ca, path); + if (ca.drv) { + filter = ca.drv->clean; + required = ca.drv->required; } ret |= apply_filter(path, src, len, dst, filter); - if (ret) { + if (!ret && required) + die("%s: clean filter '%s' failed", path, ca.drv->name); + + if (ret && dst) { src = dst->buf; len = dst->len; } - ret |= crlf_to_git(path, src, len, dst, crlf, checksafe); - if (ret) { + 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; len = dst->len; } - return ret | ident_to_git(path, src, len, dst, ident); + return ret | ident_to_git(path, src, len, dst, ca.ident); } -int convert_to_working_tree(const char *path, const char *src, size_t len, struct strbuf *dst) +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[3]; - int crlf = CRLF_GUESS; - int ident = 0, ret = 0; + int ret = 0, ret_filter = 0; const char *filter = NULL; + int required = 0; + struct conv_attrs ca; - setup_convert_check(check); - if (!git_checkattr(path, ARRAY_SIZE(check), check)) { - struct convert_driver *drv; - crlf = git_path_check_crlf(path, check + 0); - ident = git_path_check_ident(path, check + 1); - drv = git_path_check_convert(path, check + 2); - if (drv && drv->smudge) - filter = drv->smudge; + convert_attrs(&ca, path); + if (ca.drv) { + filter = ca.drv->smudge; + required = ca.drv->required; } - ret |= ident_to_worktree(path, src, len, dst, ident); + ret |= ident_to_worktree(path, src, len, dst, ca.ident); if (ret) { src = dst->buf; len = dst->len; } - ret |= crlf_to_worktree(path, src, len, dst, crlf); + /* + * CRLF conversion can be skipped if normalizing, unless there + * is a smudge filter. The filter might expect CRLFs. + */ + if (filter || !normalizing) { + ca.crlf_action = input_crlf_action(ca.crlf_action, ca.eol_attr); + ret |= crlf_to_worktree(path, src, len, dst, ca.crlf_action); + if (ret) { + src = dst->buf; + len = dst->len; + } + } + + ret_filter = apply_filter(path, src, len, dst, filter); + if (!ret_filter && required) + die("%s: smudge filter %s failed", path, ca.drv->name); + + return ret | ret_filter; +} + +int convert_to_working_tree(const char *path, const char *src, size_t len, struct strbuf *dst) +{ + return convert_to_working_tree_internal(path, src, len, dst, 0); +} + +int renormalize_buffer(const char *path, const char *src, size_t len, struct strbuf *dst) +{ + int ret = convert_to_working_tree_internal(path, src, len, dst, 1); if (ret) { src = dst->buf; len = dst->len; } - return ret | apply_filter(path, src, len, dst, filter); + return ret | convert_to_git(path, src, len, dst, SAFE_CRLF_FALSE); +} + +/***************************************************************** + * + * Streaming converison 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 $" */ +}; + +static int is_foreign_ident(const char *str) +{ + int i; + + if (prefixcmp(str, "$Id: ")) + return 0; + for (i = 5; 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); + case IDENT_SKIPPING: + /* fallthru */ + 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)); + + sprintf(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; + enum crlf_action crlf_action; + struct stream_filter *filter = NULL; + + convert_attrs(&ca, path); + + if (ca.drv && (ca.drv->smudge || ca.drv->clean)) + return filter; + + 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)) + filter = cascade_filter(filter, lf_to_crlf_filter()); + + 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); } |