diff options
Diffstat (limited to 'reftable/block.c')
| -rw-r--r-- | reftable/block.c | 176 |
1 files changed, 105 insertions, 71 deletions
diff --git a/reftable/block.c b/reftable/block.c index 298e8c56b9..3e87460cba 100644 --- a/reftable/block.c +++ b/reftable/block.c @@ -175,11 +175,6 @@ int block_writer_finish(struct block_writer *w) return w->next; } -uint8_t block_reader_type(struct block_reader *r) -{ - return r->block.data[r->header_off]; -} - int block_reader_init(struct block_reader *br, struct reftable_block *block, uint32_t header_off, uint32_t table_block_size, int hash_size) @@ -191,7 +186,8 @@ int block_reader_init(struct block_reader *br, struct reftable_block *block, uint16_t restart_count = 0; uint32_t restart_start = 0; uint8_t *restart_bytes = NULL; - uint8_t *uncompressed = NULL; + + reftable_block_done(&br->block); if (!reftable_is_block_type(typ)) { err = REFTABLE_FORMAT_ERROR; @@ -199,37 +195,57 @@ int block_reader_init(struct block_reader *br, struct reftable_block *block, } if (typ == BLOCK_TYPE_LOG) { - int block_header_skip = 4 + header_off; - uLongf dst_len = sz - block_header_skip; /* total size of dest - buffer. */ - uLongf src_len = block->len - block_header_skip; + uint32_t block_header_skip = 4 + header_off; + uLong dst_len = sz - block_header_skip; + uLong src_len = block->len - block_header_skip; /* Log blocks specify the *uncompressed* size in their header. */ - REFTABLE_ALLOC_ARRAY(uncompressed, sz); + REFTABLE_ALLOC_GROW(br->uncompressed_data, sz, + br->uncompressed_cap); /* Copy over the block header verbatim. It's not compressed. */ - memcpy(uncompressed, block->data, block_header_skip); + memcpy(br->uncompressed_data, block->data, block_header_skip); - /* Uncompress */ - if (Z_OK != - uncompress2(uncompressed + block_header_skip, &dst_len, - block->data + block_header_skip, &src_len)) { + if (!br->zstream) { + REFTABLE_CALLOC_ARRAY(br->zstream, 1); + err = inflateInit(br->zstream); + } else { + err = inflateReset(br->zstream); + } + if (err != Z_OK) { err = REFTABLE_ZLIB_ERROR; goto done; } - if (dst_len + block_header_skip != sz) { + br->zstream->next_in = block->data + block_header_skip; + br->zstream->avail_in = src_len; + br->zstream->next_out = br->uncompressed_data + block_header_skip; + br->zstream->avail_out = dst_len; + + /* + * We know both input as well as output size, and we know that + * the sizes should never be bigger than `uInt_MAX` because + * blocks can at most be 16MB large. We can thus use `Z_FINISH` + * here to instruct zlib to inflate the data in one go, which + * is more efficient than using `Z_NO_FLUSH`. + */ + err = inflate(br->zstream, Z_FINISH); + if (err != Z_STREAM_END) { + err = REFTABLE_ZLIB_ERROR; + goto done; + } + err = 0; + + if (br->zstream->total_out + block_header_skip != sz) { err = REFTABLE_FORMAT_ERROR; goto done; } /* We're done with the input data. */ reftable_block_done(block); - block->data = uncompressed; - uncompressed = NULL; + block->data = br->uncompressed_data; block->len = sz; - block->source = malloc_block_source(); - full_block_size = src_len + block_header_skip; + full_block_size = src_len + block_header_skip - br->zstream->avail_in; } else if (full_block_size == 0) { full_block_size = sz; } else if (sz < full_block_size && sz < block->len && @@ -257,18 +273,52 @@ int block_reader_init(struct block_reader *br, struct reftable_block *block, br->restart_bytes = restart_bytes; done: - reftable_free(uncompressed); return err; } -static uint32_t block_reader_restart_offset(struct block_reader *br, int i) +void block_reader_release(struct block_reader *br) +{ + inflateEnd(br->zstream); + reftable_free(br->zstream); + reftable_free(br->uncompressed_data); + reftable_block_done(&br->block); +} + +uint8_t block_reader_type(const struct block_reader *r) +{ + return r->block.data[r->header_off]; +} + +int block_reader_first_key(const struct block_reader *br, struct strbuf *key) +{ + int off = br->header_off + 4, n; + struct string_view in = { + .buf = br->block.data + off, + .len = br->block_len - off, + }; + uint8_t extra = 0; + + strbuf_reset(key); + + n = reftable_decode_key(key, &extra, in); + if (n < 0) + return n; + if (!key->len) + return REFTABLE_FORMAT_ERROR; + + return 0; +} + +static uint32_t block_reader_restart_offset(const struct block_reader *br, int i) { return get_be24(br->restart_bytes + 3 * i); } -void block_reader_start(struct block_reader *br, struct block_iter *it) +void block_iter_seek_start(struct block_iter *it, const struct block_reader *br) { - it->br = br; + it->block = br->block.data; + it->block_len = br->block_len; + it->hash_size = br->hash_size; strbuf_reset(&it->last_key); it->next_off = br->header_off + 4; } @@ -276,7 +326,7 @@ void block_reader_start(struct block_reader *br, struct block_iter *it) struct restart_needle_less_args { int error; struct strbuf needle; - struct block_reader *reader; + const struct block_reader *reader; }; static int restart_needle_less(size_t idx, void *_args) @@ -315,25 +365,17 @@ static int restart_needle_less(size_t idx, void *_args) return args->needle.len < suffix_len; } -void block_iter_copy_from(struct block_iter *dest, struct block_iter *src) -{ - dest->br = src->br; - dest->next_off = src->next_off; - strbuf_reset(&dest->last_key); - strbuf_addbuf(&dest->last_key, &src->last_key); -} - int block_iter_next(struct block_iter *it, struct reftable_record *rec) { struct string_view in = { - .buf = it->br->block.data + it->next_off, - .len = it->br->block_len - it->next_off, + .buf = (unsigned char *) it->block + it->next_off, + .len = it->block_len - it->next_off, }; struct string_view start = in; uint8_t extra = 0; int n = 0; - if (it->next_off >= it->br->block_len) + if (it->next_off >= it->block_len) return 1; n = reftable_decode_key(&it->last_key, &extra, in); @@ -343,7 +385,7 @@ int block_iter_next(struct block_iter *it, struct reftable_record *rec) return REFTABLE_FORMAT_ERROR; string_view_consume(&in, n); - n = reftable_record_decode(rec, it->last_key, extra, in, it->br->hash_size, + n = reftable_record_decode(rec, it->last_key, extra, in, it->hash_size, &it->scratch); if (n < 0) return -1; @@ -353,29 +395,13 @@ int block_iter_next(struct block_iter *it, struct reftable_record *rec) return 0; } -int block_reader_first_key(struct block_reader *br, struct strbuf *key) +void block_iter_reset(struct block_iter *it) { - int off = br->header_off + 4, n; - struct string_view in = { - .buf = br->block.data + off, - .len = br->block_len - off, - }; - uint8_t extra = 0; - - strbuf_reset(key); - - n = reftable_decode_key(key, &extra, in); - if (n < 0) - return n; - if (!key->len) - return REFTABLE_FORMAT_ERROR; - - return 0; -} - -int block_iter_seek(struct block_iter *it, struct strbuf *want) -{ - return block_reader_seek(it->br, it, want); + strbuf_reset(&it->last_key); + it->next_off = 0; + it->block = NULL; + it->block_len = 0; + it->hash_size = 0; } void block_iter_close(struct block_iter *it) @@ -384,14 +410,13 @@ void block_iter_close(struct block_iter *it) strbuf_release(&it->scratch); } -int block_reader_seek(struct block_reader *br, struct block_iter *it, - struct strbuf *want) +int block_iter_seek_key(struct block_iter *it, const struct block_reader *br, + struct strbuf *want) { struct restart_needle_less_args args = { .needle = *want, .reader = br, }; - struct block_iter next = BLOCK_ITER_INIT; struct reftable_record rec; int err = 0; size_t i; @@ -436,7 +461,9 @@ int block_reader_seek(struct block_reader *br, struct block_iter *it, it->next_off = block_reader_restart_offset(br, i - 1); else it->next_off = br->header_off + 4; - it->br = br; + it->block = br->block.data; + it->block_len = br->block_len; + it->hash_size = br->hash_size; reftable_record_init(&rec, block_reader_type(br)); @@ -448,11 +475,13 @@ int block_reader_seek(struct block_reader *br, struct block_iter *it, * far and then back up. */ while (1) { - block_iter_copy_from(&next, it); - err = block_iter_next(&next, &rec); + size_t prev_off = it->next_off; + + err = block_iter_next(it, &rec); if (err < 0) goto done; if (err > 0) { + it->next_off = prev_off; err = 0; goto done; } @@ -463,18 +492,23 @@ int block_reader_seek(struct block_reader *br, struct block_iter *it, * record does not exist in the block and can thus abort early. * In case it is equal to the sought-after key we have found * the desired record. + * + * Note that we store the next record's key record directly in + * `last_key` without restoring the key of the preceding record + * in case we need to go one record back. This is safe to do as + * `block_iter_next()` would return the ref whose key is equal + * to `last_key` now, and naturally all keys share a prefix + * with themselves. */ reftable_record_key(&rec, &it->last_key); - if (strbuf_cmp(&it->last_key, want) >= 0) + if (strbuf_cmp(&it->last_key, want) >= 0) { + it->next_off = prev_off; goto done; - - block_iter_copy_from(it, &next); + } } done: - block_iter_close(&next); reftable_record_release(&rec); - return err; } |