@matheusbsbs / matheus-bagliano / commits / 090ea12671

parse_object: avoid putting whole blob in core

Traditionally, all the callers of check_sha1_signature() first called read_sha1_file() to prepare the whole object data in core, and called this function. The function is used to revalidate what we read from the object database actually matches the object name we used to ask for the data from the object database. Update the API to allow callers to pass NULL as the object data, and have the function read and hash the object data using streaming API to recompute the object name, without having to hold everything in core at the same time. This is most useful in parse_object() that parses a blob object, because this caller does not have to keep the actual blob data around in memory after a "struct blob" is returned. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Nguyễn Thái Ngọc Duy committed Mar 7, 2012 at 17:54 UTC 090ea12671b2971b1c613f0a3d2657e8cdd35134
2 files changed +51 -2
object.c
+11
@@ -198,6 +198,17 @@ struct object *parse_object(const unsigned char *sha1)
198 if (obj && obj->parsed)
199 return obj;
200
201 + if ((obj && obj->type == OBJ_BLOB) ||
202 + (!obj && has_sha1_file(sha1) &&
203 + sha1_object_info(sha1, NULL) == OBJ_BLOB)) {
204 + if (check_sha1_signature(repl, NULL, 0, NULL) < 0) {
205 + error("sha1 mismatch %s\n", sha1_to_hex(repl));
206 + return NULL;
207 + }
208 + parse_blob_buffer(lookup_blob(sha1), NULL, 0);
209 + return lookup_object(sha1);
210 + }
211 +
212 buffer = read_sha1_file(sha1, &type, &size);
213 if (buffer) {
214 if (check_sha1_signature(repl, buffer, size, typename(type)) < 0) {
sha1_file.c
+40 -2
@@ -19,6 +19,7 @@
19 #include "pack-revindex.h"
20 #include "sha1-lookup.h"
21 #include "bulk-checkin.h"
22 +#include "streaming.h"
23
24 #ifndef O_NOATIME
25 #if defined(__linux__) && (defined(__i386__) || defined(__PPC__))
@@ -1146,10 +1147,47 @@ static const struct packed_git *has_packed_and_bad(const unsigned char *sha1)
1147 return NULL;
1148 }
1149
1149 -int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long size, const char *type)
1150 +/*
1151 + * With an in-core object data in "map", rehash it to make sure the
1152 + * object name actually matches "sha1" to detect object corruption.
1153 + * With "map" == NULL, try reading the object named with "sha1" using
1154 + * the streaming interface and rehash it to do the same.
1155 + */
1156 +int check_sha1_signature(const unsigned char *sha1, void *map,
1157 + unsigned long size, const char *type)
1158 {
1159 unsigned char real_sha1[20];
1152 - hash_sha1_file(map, size, type, real_sha1);
1160 + enum object_type obj_type;
1161 + struct git_istream *st;
1162 + git_SHA_CTX c;
1163 + char hdr[32];
1164 + int hdrlen;
1165 +
1166 + if (map) {
1167 + hash_sha1_file(map, size, type, real_sha1);
1168 + return hashcmp(sha1, real_sha1) ? -1 : 0;
1169 + }
1170 +
1171 + st = open_istream(sha1, &obj_type, &size, NULL);
1172 + if (!st)
1173 + return -1;
1174 +
1175 + /* Generate the header */
1176 + hdrlen = sprintf(hdr, "%s %lu", typename(obj_type), size) + 1;
1177 +
1178 + /* Sha1.. */
1179 + git_SHA1_Init(&c);
1180 + git_SHA1_Update(&c, hdr, hdrlen);
1181 + for (;;) {
1182 + char buf[1024 * 16];
1183 + ssize_t readlen = read_istream(st, buf, sizeof(buf));
1184 +
1185 + if (!readlen)
1186 + break;
1187 + git_SHA1_Update(&c, buf, readlen);
1188 + }
1189 + git_SHA1_Final(real_sha1, &c);
1190 + close_istream(st);
1191 return hashcmp(sha1, real_sha1) ? -1 : 0;
1192 }
1193