#include "pack-revindex.h"
#include "sha1-lookup.h"
#include "bulk-checkin.h"
+#include "streaming.h"
#ifndef O_NOATIME
#if defined(__linux__) && (defined(__i386__) || defined(__PPC__))
struct alternate_object_database *alt_odb_list;
static struct alternate_object_database **alt_odb_tail;
-static void read_info_alternates(const char * alternates, int depth);
static int git_open_noatime(const char *name);
/*
return -1;
}
}
- if (!memcmp(ent->base, objdir, pfxlen)) {
+ if (!strcmp(ent->base, objdir)) {
free(ent);
return -1;
}
}
}
-static void read_info_alternates(const char * relative_base, int depth)
+void read_info_alternates(const char * relative_base, int depth)
{
char *map;
size_t mapsz;
}
}
+static unsigned int get_max_fd_limit(void)
+{
+#ifdef RLIMIT_NOFILE
+ struct rlimit lim;
+
+ if (getrlimit(RLIMIT_NOFILE, &lim))
+ die_errno("cannot get RLIMIT_NOFILE");
+
+ return lim.rlim_cur;
+#elif defined(_SC_OPEN_MAX)
+ return sysconf(_SC_OPEN_MAX);
+#elif defined(OPEN_MAX)
+ return OPEN_MAX;
+#else
+ return 1; /* see the caller ;-) */
+#endif
+}
+
/*
* Do not call this directly as this leaks p->pack_fd on error return;
* call open_packed_git() instead.
return error("packfile %s index unavailable", p->pack_name);
if (!pack_max_fds) {
- struct rlimit lim;
- unsigned int max_fds;
-
- if (getrlimit(RLIMIT_NOFILE, &lim))
- die_errno("cannot get RLIMIT_NOFILE");
-
- max_fds = lim.rlim_cur;
+ unsigned int max_fds = get_max_fd_limit();
/* Save 3 for stdin/stdout/stderr, 22 for work */
if (25 < max_fds)
return NULL;
}
-int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long size, const char *type)
+/*
+ * With an in-core object data in "map", rehash it to make sure the
+ * object name actually matches "sha1" to detect object corruption.
+ * With "map" == NULL, try reading the object named with "sha1" using
+ * the streaming interface and rehash it to do the same.
+ */
+int check_sha1_signature(const unsigned char *sha1, void *map,
+ unsigned long size, const char *type)
{
unsigned char real_sha1[20];
- hash_sha1_file(map, size, type, real_sha1);
+ enum object_type obj_type;
+ struct git_istream *st;
+ git_SHA_CTX c;
+ char hdr[32];
+ int hdrlen;
+
+ if (map) {
+ hash_sha1_file(map, size, type, real_sha1);
+ return hashcmp(sha1, real_sha1) ? -1 : 0;
+ }
+
+ st = open_istream(sha1, &obj_type, &size, NULL);
+ if (!st)
+ return -1;
+
+ /* Generate the header */
+ hdrlen = sprintf(hdr, "%s %lu", typename(obj_type), size) + 1;
+
+ /* Sha1.. */
+ git_SHA1_Init(&c);
+ git_SHA1_Update(&c, hdr, hdrlen);
+ for (;;) {
+ char buf[1024 * 16];
+ ssize_t readlen = read_istream(st, buf, sizeof(buf));
+
+ if (!readlen)
+ break;
+ git_SHA1_Update(&c, buf, readlen);
+ }
+ git_SHA1_Final(real_sha1, &c);
+ close_istream(st);
return hashcmp(sha1, real_sha1) ? -1 : 0;
}
unlink_or_warn(tmpfile);
if (ret) {
if (ret != EEXIST) {
- return error("unable to write sha1 filename %s: %s\n", filename, strerror(ret));
+ return error("unable to write sha1 filename %s: %s", filename, strerror(ret));
}
/* FIXME!!! Collision check here ? */
}
fd = create_tmpfile(tmp_file, sizeof(tmp_file), filename);
if (fd < 0) {
if (errno == EACCES)
- return error("insufficient permission for adding an object to repository database %s\n", get_object_directory());
+ return error("insufficient permission for adding an object to repository database %s", get_object_directory());
else
- return error("unable to create temporary sha1 filename %s: %s\n", tmp_file, strerror(errno));
+ return error("unable to create temporary file: %s", strerror(errno));
}
/* Set it up */
* This also bypasses the usual "convert-to-git" dance, and that is on
* purpose. We could write a streaming version of the converting
* functions and insert that before feeding the data to fast-import
- * (or equivalent in-core API described above), but the primary
- * motivation for trying to stream from the working tree file and to
- * avoid mmaping it in core is to deal with large binary blobs, and
- * by definition they do _not_ want to get any conversion.
+ * (or equivalent in-core API described above). However, that is
+ * somewhat complicated, as we do not know the size of the filter
+ * result, which we need to know beforehand when writing a git object.
+ * Since the primary motivation for trying to stream from the working
+ * tree file and to avoid mmaping it in core is to deal with large
+ * binary blobs, they generally do not want to get any conversion, and
+ * callers should avoid this code path when filters are requested.
*/
static int index_stream(unsigned char *sha1, int fd, size_t size,
enum object_type type, const char *path,
if (!S_ISREG(st->st_mode))
ret = index_pipe(sha1, fd, type, path, flags);
- else if (size <= big_file_threshold || type != OBJ_BLOB)
+ else if (size <= big_file_threshold || type != OBJ_BLOB ||
+ (path && would_convert_to_git(path, NULL, 0, 0)))
ret = index_core(sha1, fd, size, type, path, flags);
else
ret = index_stream(sha1, fd, size, type, path, flags);