#include "fetch.h"
#include "http.h"
+#ifndef NO_EXPAT
+#include <expat.h>
+
+/* Definitions for DAV requests */
+#define DAV_PROPFIND "PROPFIND"
+#define DAV_PROPFIND_RESP ".multistatus.response"
+#define DAV_PROPFIND_NAME ".multistatus.response.href"
+#define DAV_PROPFIND_COLLECTION ".multistatus.response.propstat.prop.resourcetype.collection"
+#define PROPFIND_ALL_REQUEST "<?xml version=\"1.0\" encoding=\"utf-8\" ?>\n<D:propfind xmlns:D=\"DAV:\">\n<D:allprop/>\n</D:propfind>"
+
+/* Definitions for processing XML DAV responses */
+#ifndef XML_STATUS_OK
+enum XML_Status {
+ XML_STATUS_OK = 1,
+ XML_STATUS_ERROR = 0
+};
+#define XML_STATUS_OK 1
+#define XML_STATUS_ERROR 0
+#endif
+
+/* Flags that control remote_ls processing */
+#define PROCESS_FILES (1u << 0)
+#define PROCESS_DIRS (1u << 1)
+#define RECURSIVE (1u << 2)
+
+/* Flags that remote_ls passes to callback functions */
+#define IS_DIR (1u << 0)
+#endif
+
#define PREV_BUF_SIZE 4096
#define RANGE_HEADER_SIZE 30
+static int commits_on_stdin = 0;
+
static int got_alternates = -1;
+static int corrupt_object_found = 0;
static struct curl_slist *no_pragma_header;
struct alt_base
{
- char *base;
+ const char *base;
+ int path_len;
int got_indices;
struct packed_git *packs;
struct alt_base *next;
};
struct alternates_request {
- char *base;
+ const char *base;
char *url;
struct buffer *buffer;
struct active_request_slot *slot;
int http_specific;
};
+#ifndef NO_EXPAT
+struct xml_ctx
+{
+ char *name;
+ int len;
+ char *cdata;
+ void (*userFunc)(struct xml_ctx *ctx, int tag_closed);
+ void *userData;
+};
+
+struct remote_ls_ctx
+{
+ struct alt_base *repo;
+ char *path;
+ void (*userFunc)(struct remote_ls_ctx *ls);
+ void *userData;
+ int flags;
+ char *dentry_name;
+ int dentry_flags;
+ int rc;
+ struct remote_ls_ctx *parent;
+};
+#endif
+
static struct object_request *object_queue_head = NULL;
static size_t fwrite_sha1_file(void *ptr, size_t eltsize, size_t nmemb,
struct object_request *obj_req = (struct object_request *)data;
do {
ssize_t retval = write(obj_req->local,
- ptr + posn, size - posn);
+ (char *) ptr + posn, size - posn);
if (retval < 0)
return posn;
posn += retval;
return size;
}
-static void fetch_alternates(char *base);
+static void fetch_alternates(const char *base);
static void process_object_response(void *callback_data);
if (obj_req->local < 0) {
obj_req->state = ABORTED;
- error("Couldn't create temporary file %s for %s: %s\n",
+ error("Couldn't create temporary file %s for %s: %s",
obj_req->tmpfile, obj_req->filename, strerror(errno));
return;
}
free(obj_req->url);
return;
}
-
}
static void finish_object_request(struct object_request *obj_req)
obj_req->state = COMPLETE;
/* Use alternates if necessary */
- if (obj_req->http_code == 404) {
+ if (obj_req->http_code == 404 ||
+ obj_req->curl_result == CURLE_FILE_COULDNT_READ_FILE) {
fetch_alternates(alt->base);
if (obj_req->repo->next != NULL) {
obj_req->repo =
while (active_requests < max_requests && obj_req != NULL) {
if (obj_req->state == WAITING) {
if (has_sha1_file(obj_req->sha1))
- release_object_request(obj_req);
+ obj_req->state = COMPLETE;
else
start_object_request(obj_req);
curl_multi_perform(curlm, &num_transfers);
slot->curl = NULL;
}
slot = slot->next;
- }
+ }
}
#endif
snprintf(newreq->filename, sizeof(newreq->filename), "%s", filename);
snprintf(newreq->tmpfile, sizeof(newreq->tmpfile),
"%s.temp", filename);
+ newreq->slot = NULL;
newreq->next = NULL;
if (object_queue_head == NULL) {
FILE *indexfile;
struct active_request_slot *slot;
+ struct slot_results results;
if (has_pack_index(sha1))
return 0;
if (get_verbosely)
fprintf(stderr, "Getting index for pack %s\n", hex);
-
+
url = xmalloc(strlen(repo->base) + 64);
sprintf(url, "%s/objects/pack/pack-%s.idx", repo->base, hex);
-
+
filename = sha1_pack_index_name(sha1);
snprintf(tmpfile, sizeof(tmpfile), "%s.temp", filename);
indexfile = fopen(tmpfile, "a");
filename);
slot = get_active_slot();
+ slot->results = &results;
curl_easy_setopt(slot->curl, CURLOPT_FILE, indexfile);
curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite);
curl_easy_setopt(slot->curl, CURLOPT_URL, url);
if (start_active_slot(slot)) {
run_active_slot(slot);
- if (slot->curl_result != CURLE_OK) {
+ if (results.curl_result != CURLE_OK) {
fclose(indexfile);
return error("Unable to get pack index %s\n%s", url,
curl_errorstr);
{
struct packed_git *new_pack;
if (has_pack_file(sha1))
- return 0; // don't list this as something we can get
+ return 0; /* don't list this as something we can get */
if (fetch_index(repo, sha1))
return -1;
(struct alternates_request *)callback_data;
struct active_request_slot *slot = alt_req->slot;
struct alt_base *tail = alt;
- char *base = alt_req->base;
+ const char *base = alt_req->base;
static const char null_byte = '\0';
char *data;
int i = 0;
alt_req->url);
active_requests++;
slot->in_use = 1;
- if (start_active_slot(slot)) {
- return;
- } else {
+ if (slot->finished != NULL)
+ (*slot->finished) = 0;
+ if (!start_active_slot(slot)) {
got_alternates = -1;
slot->in_use = 0;
- return;
+ if (slot->finished != NULL)
+ (*slot->finished) = 1;
}
+ return;
}
} else if (slot->curl_result != CURLE_OK) {
- if (slot->http_code != 404) {
+ if (slot->http_code != 404 &&
+ slot->curl_result != CURLE_FILE_COULDNT_READ_FILE) {
got_alternates = -1;
return;
}
int serverlen = 0;
struct alt_base *newalt;
char *target = NULL;
+ char *path;
if (data[i] == '/') {
serverlen = strchr(base + 8, '/') - base;
okay = 1;
} else if (!memcmp(data + i, "../", 3)) {
i += 3;
serverlen = strlen(base);
- while (i + 2 < posn &&
+ while (i + 2 < posn &&
!memcmp(data + i, "../", 3)) {
do {
serverlen--;
base[serverlen - 1] != '/');
i += 3;
}
- // If the server got removed, give up.
- okay = strchr(base, ':') - base + 3 <
+ /* If the server got removed, give up. */
+ okay = strchr(base, ':') - base + 3 <
serverlen;
} else if (alt_req->http_specific) {
char *colon = strchr(data + i, ':');
okay = 1;
}
}
- // skip 'objects' at end
+ /* skip 'objects' at end */
if (okay) {
target = xmalloc(serverlen + posn - i - 6);
- strncpy(target, base, serverlen);
- strncpy(target + serverlen, data + i,
- posn - i - 7);
- target[serverlen + posn - i - 7] = '\0';
+ strlcpy(target, base, serverlen);
+ strlcpy(target + serverlen, data + i, posn - i - 6);
if (get_verbosely)
- fprintf(stderr,
+ fprintf(stderr,
"Also look at %s\n", target);
newalt = xmalloc(sizeof(*newalt));
newalt->next = NULL;
newalt->base = target;
newalt->got_indices = 0;
newalt->packs = NULL;
+ path = strstr(target, "//");
+ if (path) {
+ path = strchr(path+2, '/');
+ if (path)
+ newalt->path_len = strlen(path);
+ }
+
while (tail->next != NULL)
tail = tail->next;
tail->next = newalt;
got_alternates = 1;
}
-static void fetch_alternates(char *base)
+static void fetch_alternates(const char *base)
{
struct buffer buffer;
char *url;
char *data;
struct active_request_slot *slot;
- static struct alternates_request alt_req;
+ struct alternates_request alt_req;
/* If another request has already started fetching alternates,
wait for them to arrive and return to processing this request's
if (get_verbosely)
fprintf(stderr, "Getting alternates list for %s\n", base);
-
+
url = xmalloc(strlen(base) + 31);
sprintf(url, "%s/objects/info/http-alternates", base);
free(url);
}
+#ifndef NO_EXPAT
+static void
+xml_start_tag(void *userData, const char *name, const char **atts)
+{
+ struct xml_ctx *ctx = (struct xml_ctx *)userData;
+ const char *c = strchr(name, ':');
+ int new_len;
+
+ if (c == NULL)
+ c = name;
+ else
+ c++;
+
+ new_len = strlen(ctx->name) + strlen(c) + 2;
+
+ if (new_len > ctx->len) {
+ ctx->name = xrealloc(ctx->name, new_len);
+ ctx->len = new_len;
+ }
+ strcat(ctx->name, ".");
+ strcat(ctx->name, c);
+
+ if (ctx->cdata) {
+ free(ctx->cdata);
+ ctx->cdata = NULL;
+ }
+
+ ctx->userFunc(ctx, 0);
+}
+
+static void
+xml_end_tag(void *userData, const char *name)
+{
+ struct xml_ctx *ctx = (struct xml_ctx *)userData;
+ const char *c = strchr(name, ':');
+ char *ep;
+
+ ctx->userFunc(ctx, 1);
+
+ if (c == NULL)
+ c = name;
+ else
+ c++;
+
+ ep = ctx->name + strlen(ctx->name) - strlen(c) - 1;
+ *ep = 0;
+}
+
+static void
+xml_cdata(void *userData, const XML_Char *s, int len)
+{
+ struct xml_ctx *ctx = (struct xml_ctx *)userData;
+ if (ctx->cdata)
+ free(ctx->cdata);
+ ctx->cdata = xmalloc(len + 1);
+ strlcpy(ctx->cdata, s, len + 1);
+}
+
+static int remote_ls(struct alt_base *repo, const char *path, int flags,
+ void (*userFunc)(struct remote_ls_ctx *ls),
+ void *userData);
+
+static void handle_remote_ls_ctx(struct xml_ctx *ctx, int tag_closed)
+{
+ struct remote_ls_ctx *ls = (struct remote_ls_ctx *)ctx->userData;
+
+ if (tag_closed) {
+ if (!strcmp(ctx->name, DAV_PROPFIND_RESP) && ls->dentry_name) {
+ if (ls->dentry_flags & IS_DIR) {
+ if (ls->flags & PROCESS_DIRS) {
+ ls->userFunc(ls);
+ }
+ if (strcmp(ls->dentry_name, ls->path) &&
+ ls->flags & RECURSIVE) {
+ ls->rc = remote_ls(ls->repo,
+ ls->dentry_name,
+ ls->flags,
+ ls->userFunc,
+ ls->userData);
+ }
+ } else if (ls->flags & PROCESS_FILES) {
+ ls->userFunc(ls);
+ }
+ } else if (!strcmp(ctx->name, DAV_PROPFIND_NAME) && ctx->cdata) {
+ ls->dentry_name = xmalloc(strlen(ctx->cdata) -
+ ls->repo->path_len + 1);
+ strcpy(ls->dentry_name, ctx->cdata + ls->repo->path_len);
+ } else if (!strcmp(ctx->name, DAV_PROPFIND_COLLECTION)) {
+ ls->dentry_flags |= IS_DIR;
+ }
+ } else if (!strcmp(ctx->name, DAV_PROPFIND_RESP)) {
+ if (ls->dentry_name) {
+ free(ls->dentry_name);
+ }
+ ls->dentry_name = NULL;
+ ls->dentry_flags = 0;
+ }
+}
+
+static int remote_ls(struct alt_base *repo, const char *path, int flags,
+ void (*userFunc)(struct remote_ls_ctx *ls),
+ void *userData)
+{
+ char *url = xmalloc(strlen(repo->base) + strlen(path) + 1);
+ struct active_request_slot *slot;
+ struct slot_results results;
+ struct buffer in_buffer;
+ struct buffer out_buffer;
+ char *in_data;
+ char *out_data;
+ XML_Parser parser = XML_ParserCreate(NULL);
+ enum XML_Status result;
+ struct curl_slist *dav_headers = NULL;
+ struct xml_ctx ctx;
+ struct remote_ls_ctx ls;
+
+ ls.flags = flags;
+ ls.repo = repo;
+ ls.path = strdup(path);
+ ls.dentry_name = NULL;
+ ls.dentry_flags = 0;
+ ls.userData = userData;
+ ls.userFunc = userFunc;
+ ls.rc = 0;
+
+ sprintf(url, "%s%s", repo->base, path);
+
+ out_buffer.size = strlen(PROPFIND_ALL_REQUEST);
+ out_data = xmalloc(out_buffer.size + 1);
+ snprintf(out_data, out_buffer.size + 1, PROPFIND_ALL_REQUEST);
+ out_buffer.posn = 0;
+ out_buffer.buffer = out_data;
+
+ in_buffer.size = 4096;
+ in_data = xmalloc(in_buffer.size);
+ in_buffer.posn = 0;
+ in_buffer.buffer = in_data;
+
+ dav_headers = curl_slist_append(dav_headers, "Depth: 1");
+ dav_headers = curl_slist_append(dav_headers, "Content-Type: text/xml");
+
+ slot = get_active_slot();
+ slot->results = &results;
+ curl_easy_setopt(slot->curl, CURLOPT_INFILE, &out_buffer);
+ curl_easy_setopt(slot->curl, CURLOPT_INFILESIZE, out_buffer.size);
+ curl_easy_setopt(slot->curl, CURLOPT_READFUNCTION, fread_buffer);
+ curl_easy_setopt(slot->curl, CURLOPT_FILE, &in_buffer);
+ curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_buffer);
+ curl_easy_setopt(slot->curl, CURLOPT_URL, url);
+ curl_easy_setopt(slot->curl, CURLOPT_UPLOAD, 1);
+ curl_easy_setopt(slot->curl, CURLOPT_CUSTOMREQUEST, DAV_PROPFIND);
+ curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, dav_headers);
+
+ if (start_active_slot(slot)) {
+ run_active_slot(slot);
+ if (results.curl_result == CURLE_OK) {
+ ctx.name = xcalloc(10, 1);
+ ctx.len = 0;
+ ctx.cdata = NULL;
+ ctx.userFunc = handle_remote_ls_ctx;
+ ctx.userData = &ls;
+ XML_SetUserData(parser, &ctx);
+ XML_SetElementHandler(parser, xml_start_tag,
+ xml_end_tag);
+ XML_SetCharacterDataHandler(parser, xml_cdata);
+ result = XML_Parse(parser, in_buffer.buffer,
+ in_buffer.posn, 1);
+ free(ctx.name);
+
+ if (result != XML_STATUS_OK) {
+ ls.rc = error("XML error: %s",
+ XML_ErrorString(
+ XML_GetErrorCode(parser)));
+ }
+ } else {
+ ls.rc = -1;
+ }
+ } else {
+ ls.rc = error("Unable to start PROPFIND request");
+ }
+
+ free(ls.path);
+ free(url);
+ free(out_data);
+ free(in_buffer.buffer);
+ curl_slist_free_all(dav_headers);
+
+ return ls.rc;
+}
+
+static void process_ls_pack(struct remote_ls_ctx *ls)
+{
+ unsigned char sha1[20];
+
+ if (strlen(ls->dentry_name) == 63 &&
+ !strncmp(ls->dentry_name, "objects/pack/pack-", 18) &&
+ !strncmp(ls->dentry_name+58, ".pack", 5)) {
+ get_sha1_hex(ls->dentry_name + 18, sha1);
+ setup_index(ls->repo, sha1);
+ }
+}
+#endif
+
static int fetch_indices(struct alt_base *repo)
{
unsigned char sha1[20];
int i = 0;
struct active_request_slot *slot;
+ struct slot_results results;
if (repo->got_indices)
return 0;
if (get_verbosely)
fprintf(stderr, "Getting pack list for %s\n", repo->base);
-
+
+#ifndef NO_EXPAT
+ if (remote_ls(repo, "objects/pack/", PROCESS_FILES,
+ process_ls_pack, NULL) == 0)
+ return 0;
+#endif
+
url = xmalloc(strlen(repo->base) + 21);
sprintf(url, "%s/objects/info/packs", repo->base);
slot = get_active_slot();
+ slot->results = &results;
curl_easy_setopt(slot->curl, CURLOPT_FILE, &buffer);
curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_buffer);
curl_easy_setopt(slot->curl, CURLOPT_URL, url);
curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, NULL);
if (start_active_slot(slot)) {
run_active_slot(slot);
- if (slot->curl_result != CURLE_OK) {
- if (slot->http_code == 404) {
+ if (results.curl_result != CURLE_OK) {
+ if (results.http_code == 404 ||
+ results.curl_result == CURLE_FILE_COULDNT_READ_FILE) {
repo->got_indices = 1;
free(buffer.buffer);
return 0;
switch (data[i]) {
case 'P':
i++;
- if (i + 52 < buffer.posn &&
+ if (i + 52 <= buffer.posn &&
!strncmp(data + i, " pack-", 6) &&
!strncmp(data + i + 46, ".pack\n", 6)) {
get_sha1_hex(data + i + 6, sha1);
break;
}
default:
- while (data[i] != '\n')
+ while (i < buffer.posn && data[i] != '\n')
i++;
}
i++;
struct curl_slist *range_header = NULL;
struct active_request_slot *slot;
+ struct slot_results results;
if (fetch_indices(repo))
return -1;
filename);
slot = get_active_slot();
+ slot->results = &results;
curl_easy_setopt(slot->curl, CURLOPT_FILE, packfile);
curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite);
curl_easy_setopt(slot->curl, CURLOPT_URL, url);
if (start_active_slot(slot)) {
run_active_slot(slot);
- if (slot->curl_result != CURLE_OK) {
+ if (results.curl_result != CURLE_OK) {
fclose(packfile);
return error("Unable to get pack file %s\n%s", url,
curl_errorstr);
return 0;
}
+static void abort_object_request(struct object_request *obj_req)
+{
+ if (obj_req->local >= 0) {
+ close(obj_req->local);
+ obj_req->local = -1;
+ }
+ unlink(obj_req->tmpfile);
+ if (obj_req->slot) {
+ release_active_slot(obj_req->slot);
+ obj_req->slot = NULL;
+ }
+ release_object_request(obj_req);
+}
+
static int fetch_object(struct alt_base *repo, unsigned char *sha1)
{
char *hex = sha1_to_hex(sha1);
return error("Couldn't find request for %s in the queue", hex);
if (has_sha1_file(obj_req->sha1)) {
- release_object_request(obj_req);
+ abort_object_request(obj_req);
return 0;
}
ret = error("Request for %s aborted", hex);
} else if (obj_req->curl_result != CURLE_OK &&
obj_req->http_code != 416) {
- if (obj_req->http_code == 404)
+ if (obj_req->http_code == 404 ||
+ obj_req->curl_result == CURLE_FILE_COULDNT_READ_FILE)
ret = -1; /* Be silent, it is probably in a pack. */
else
ret = error("%s (curl_result = %d, http_code = %ld, sha1 = %s)",
obj_req->errorstr, obj_req->curl_result,
obj_req->http_code, hex);
} else if (obj_req->zret != Z_STREAM_END) {
- ret = error("File %s (%s) corrupt\n", hex, obj_req->url);
+ corrupt_object_found++;
+ ret = error("File %s (%s) corrupt", hex, obj_req->url);
} else if (memcmp(obj_req->sha1, obj_req->real_sha1, 20)) {
- ret = error("File %s has bad hash\n", hex);
+ ret = error("File %s has bad hash", hex);
} else if (obj_req->rename < 0) {
- ret = error("unable to write sha1 filename %s: %s",
- obj_req->filename,
- strerror(obj_req->rename));
+ ret = error("unable to write sha1 filename %s",
+ obj_req->filename);
}
release_object_request(obj_req);
fetch_alternates(alt->base);
altbase = altbase->next;
}
- return error("Unable to find %s under %s\n", sha1_to_hex(sha1),
+ return error("Unable to find %s under %s", sha1_to_hex(sha1),
alt->base);
}
static inline int needs_quote(int ch)
{
- switch (ch) {
- case '/': case '-': case '.':
- case 'A'...'Z': case 'a'...'z': case '0'...'9':
+ if (((ch >= 'A') && (ch <= 'Z'))
+ || ((ch >= 'a') && (ch <= 'z'))
+ || ((ch >= '0') && (ch <= '9'))
+ || (ch == '/')
+ || (ch == '-')
+ || (ch == '.'))
return 0;
- default:
- return 1;
- }
+ return 1;
}
static inline int hex(int v)
char *url;
char hex[42];
struct buffer buffer;
- char *base = alt->base;
+ const char *base = alt->base;
struct active_request_slot *slot;
+ struct slot_results results;
buffer.size = 41;
buffer.posn = 0;
buffer.buffer = hex;
hex[41] = '\0';
-
+
url = quote_ref_url(base, ref);
slot = get_active_slot();
+ slot->results = &results;
curl_easy_setopt(slot->curl, CURLOPT_FILE, &buffer);
curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_buffer);
curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, NULL);
curl_easy_setopt(slot->curl, CURLOPT_URL, url);
if (start_active_slot(slot)) {
run_active_slot(slot);
- if (slot->curl_result != CURLE_OK)
+ if (results.curl_result != CURLE_OK)
return error("Couldn't get %s for %s\n%s",
url, ref, curl_errorstr);
} else {
return 0;
}
-int main(int argc, char **argv)
+int main(int argc, const char **argv)
{
- char *commit_id;
- char *url;
+ int commits;
+ const char **write_ref = NULL;
+ char **commit_id;
+ const char *url;
+ char *path;
int arg = 1;
int rc = 0;
+ setup_git_directory();
+ git_config(git_default_config);
+
while (arg < argc && argv[arg][0] == '-') {
if (argv[arg][1] == 't') {
get_tree = 1;
} else if (argv[arg][1] == 'v') {
get_verbosely = 1;
} else if (argv[arg][1] == 'w') {
- write_ref = argv[arg + 1];
+ write_ref = &argv[arg + 1];
arg++;
} else if (!strcmp(argv[arg], "--recover")) {
get_recover = 1;
+ } else if (!strcmp(argv[arg], "--stdin")) {
+ commits_on_stdin = 1;
}
arg++;
}
- if (argc < arg + 2) {
- usage("git-http-fetch [-c] [-t] [-a] [-d] [-v] [--recover] [-w ref] commit-id url");
+ if (argc < arg + 2 - commits_on_stdin) {
+ usage("git-http-fetch [-c] [-t] [-a] [-v] [--recover] [-w ref] [--stdin] commit-id url");
return 1;
}
- commit_id = argv[arg];
- url = argv[arg + 1];
+ if (commits_on_stdin) {
+ commits = pull_targets_stdin(&commit_id, &write_ref);
+ } else {
+ commit_id = (char **) &argv[arg++];
+ commits = 1;
+ }
+ url = argv[arg];
http_init();
alt->got_indices = 0;
alt->packs = NULL;
alt->next = NULL;
+ path = strstr(url, "//");
+ if (path) {
+ path = strchr(path+2, '/');
+ if (path)
+ alt->path_len = strlen(path);
+ }
- if (pull(commit_id))
+ if (pull(commits, commit_id, write_ref, url))
rc = 1;
+ http_cleanup();
+
curl_slist_free_all(no_pragma_header);
- http_cleanup();
+ if (commits_on_stdin)
+ pull_targets_free(commits, commit_id, write_ref);
+ if (corrupt_object_found) {
+ fprintf(stderr,
+"Some loose object were found to be corrupt, but they might be just\n"
+"a false '404 Not Found' error message sent with incorrect HTTP\n"
+"status code. Suggest running git fsck-objects.\n");
+ }
return rc;
}