diff options
Diffstat (limited to 'convert.c')
| -rw-r--r-- | convert.c | 397 |
1 files changed, 397 insertions, 0 deletions
@@ -813,3 +813,400 @@ int renormalize_buffer(const char *path, const char *src, size_t len, struct str } return ret | convert_to_git(path, src, len, dst, 0); } + +/***************************************************************** + * + * 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 + */ +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; + + if (!input) + return 0; /* we do not keep any states */ + count = *isize_p; + if (count) { + size_t i, o; + for (i = o = 0; o < *osize_p && i < count; i++) { + char ch = input[i]; + if (ch == '\n') { + if (o + 1 < *osize_p) + output[o++] = '\r'; + else + break; + } + output[o++] = ch; + } + + *osize_p -= o; + *isize_p -= i; + } + return 0; +} + +static struct stream_filter_vtbl lf_to_crlf_vtbl = { + lf_to_crlf_filter_fn, + null_free_fn, +}; + +static struct stream_filter lf_to_crlf_filter_singleton = { + &lf_to_crlf_vtbl, +}; + + +/* + * 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_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); +} |