#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;
+
static int got_alternates = -1;
-static int corrupt_object_found = 0;
+static int corrupt_object_found;
static struct curl_slist *no_pragma_header;
struct alt_base
{
char *base;
- int path_len;
int got_indices;
struct packed_git *packs;
struct alt_base *next;
};
-static struct alt_base *alt = NULL;
+static struct alt_base *alt;
enum object_request_state {
WAITING,
};
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 struct object_request *object_queue_head;
static size_t fwrite_sha1_file(void *ptr, size_t eltsize, size_t nmemb,
void *data)
int posn = 0;
struct object_request *obj_req = (struct object_request *)data;
do {
- ssize_t retval = write(obj_req->local,
- ptr + posn, size - posn);
+ ssize_t retval = xwrite(obj_req->local,
+ (char *) ptr + posn, size - posn);
if (retval < 0)
return posn;
posn += retval;
return size;
}
-static void fetch_alternates(char *base);
+static int missing__target(int code, int result)
+{
+ return /* file:// URL -- do we ever use one??? */
+ (result == CURLE_FILE_COULDNT_READ_FILE) ||
+ /* http:// and https:// URL */
+ (code == 404 && result == CURLE_HTTP_RETURNED_ERROR) ||
+ /* ftp:// URL */
+ (code == 550 && result == CURLE_FTP_COULDNT_RETR_FILE)
+ ;
+}
+
+#define missing_target(a) missing__target((a)->http_code, (a)->curl_result)
+
+static void fetch_alternates(const char *base);
static void process_object_response(void *callback_data);
SHA1_Init(&obj_req->c);
- url = xmalloc(strlen(obj_req->repo->base) + 50);
- obj_req->url = xmalloc(strlen(obj_req->repo->base) + 50);
+ url = xmalloc(strlen(obj_req->repo->base) + 51);
+ obj_req->url = xmalloc(strlen(obj_req->repo->base) + 51);
strcpy(url, obj_req->repo->base);
posn = url + strlen(obj_req->repo->base);
- strcpy(posn, "objects/");
- posn += 8;
+ strcpy(posn, "/objects/");
+ posn += 9;
memcpy(posn, hex, 2);
posn += 2;
*(posn++) = '/';
prevlocal = open(prevfile, O_RDONLY);
if (prevlocal != -1) {
do {
- prev_read = read(prevlocal, prev_buf, PREV_BUF_SIZE);
+ prev_read = xread(prevlocal, prev_buf, PREV_BUF_SIZE);
if (prev_read>0) {
if (fwrite_sha1_file(prev_buf,
1,
SHA1_Init(&obj_req->c);
if (prev_posn>0) {
prev_posn = 0;
- lseek(obj_req->local, SEEK_SET, 0);
+ lseek(obj_req->local, 0, SEEK_SET);
ftruncate(obj_req->local, 0);
}
}
unlink(obj_req->tmpfile);
return;
}
- if (memcmp(obj_req->sha1, obj_req->real_sha1, 20)) {
+ if (hashcmp(obj_req->sha1, obj_req->real_sha1)) {
unlink(obj_req->tmpfile);
return;
}
obj_req->state = COMPLETE;
/* Use alternates if necessary */
- if (obj_req->http_code == 404 ||
- obj_req->curl_result == CURLE_FILE_COULDNT_READ_FILE) {
+ if (missing_target(obj_req)) {
fetch_alternates(alt->base);
if (obj_req->repo->next != NULL) {
obj_req->repo =
char *filename = sha1_file_name(sha1);
newreq = xmalloc(sizeof(*newreq));
- memcpy(newreq->sha1, sha1, 20);
+ hashcpy(newreq->sha1, sha1);
newreq->repo = alt;
newreq->url = NULL;
newreq->local = -1;
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) {
{
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;
return;
}
} else if (slot->curl_result != CURLE_OK) {
- if (slot->http_code != 404 &&
- slot->curl_result != CURLE_FILE_COULDNT_READ_FILE) {
+ if (!missing_target(slot)) {
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;
+ /* This counts
+ * http://git.host/pub/scm/linux.git/
+ * -----------here^
+ * so memcpy(dst, base, serverlen) will
+ * copy up to "...git.host".
+ */
+ const char *colon_ss = strstr(base,"://");
+ if (colon_ss) {
+ serverlen = (strchr(colon_ss + 3, '/')
+ - base);
+ okay = 1;
+ }
} else if (!memcmp(data + i, "../", 3)) {
+ /* Relative URL; chop the corresponding
+ * number of subpath from base (and ../
+ * from data), and concatenate the result.
+ *
+ * The code first drops ../ from data, and
+ * then drops one ../ from data and one path
+ * from base. IOW, one extra ../ is dropped
+ * from data than path is dropped from base.
+ *
+ * This is not wrong. The alternate in
+ * http://git.host/pub/scm/linux.git/
+ * to borrow from
+ * http://git.host/pub/scm/linus.git/
+ * is ../../linus.git/objects/. You need
+ * two ../../ to borrow from your direct
+ * neighbour.
+ */
i += 3;
serverlen = strlen(base);
while (i + 2 < posn &&
base[serverlen - 1] != '/');
i += 3;
}
- // If the server got removed, give up.
+ /* If the server got removed, give up. */
okay = strchr(base, ':') - base + 3 <
serverlen;
} else if (alt_req->http_specific) {
okay = 1;
}
}
- // skip 'objects' at end
+ /* skip "objects\n" 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';
+ memcpy(target, base, serverlen);
+ memcpy(target + serverlen, data + i,
+ posn - i - 7);
+ target[serverlen + posn - i - 7] = 0;
if (get_verbosely)
fprintf(stderr,
"Also look at %s\n", target);
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;
got_alternates = 1;
}
-static void fetch_alternates(char *base)
+static void fetch_alternates(const char *base)
{
struct buffer buffer;
char *url;
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 = xcalloc(len+1, 1);
- strncpy(ctx->cdata, s, len);
-}
-
-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];
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);
if (start_active_slot(slot)) {
run_active_slot(slot);
if (results.curl_result != CURLE_OK) {
- if (results.http_code == 404 ||
- results.curl_result == CURLE_FILE_COULDNT_READ_FILE) {
+ if (missing_target(&results)) {
repo->got_indices = 1;
free(buffer.buffer);
return 0;
case 'P':
i++;
if (i + 52 <= buffer.posn &&
- !strncmp(data + i, " pack-", 6) &&
- !strncmp(data + i + 46, ".pack\n", 6)) {
+ !prefixcmp(data + i, " pack-") &&
+ !prefixcmp(data + i + 46, ".pack\n")) {
get_sha1_hex(data + i + 6, sha1);
setup_index(repo, sha1);
i += 51;
return error("Unable to start request");
}
+ target->pack_size = ftell(packfile);
fclose(packfile);
ret = move_temp_to_file(tmpfile, filename);
int ret = 0;
struct object_request *obj_req = object_queue_head;
- while (obj_req != NULL && memcmp(obj_req->sha1, sha1, 20))
+ while (obj_req != NULL && hashcmp(obj_req->sha1, sha1))
obj_req = obj_req->next;
if (obj_req == NULL)
return error("Couldn't find request for %s in the queue", hex);
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 ||
- obj_req->curl_result == CURLE_FILE_COULDNT_READ_FILE)
+ if (missing_target(obj_req))
ret = -1; /* Be silent, it is probably in a pack. */
else
ret = error("%s (curl_result = %d, http_code = %ld, sha1 = %s)",
} else if (obj_req->zret != Z_STREAM_END) {
corrupt_object_found++;
ret = error("File %s (%s) corrupt", hex, obj_req->url);
- } else if (memcmp(obj_req->sha1, obj_req->real_sha1, 20)) {
+ } else if (hashcmp(obj_req->sha1, obj_req->real_sha1)) {
ret = error("File %s has bad hash", hex);
} else if (obj_req->rename < 0) {
ret = error("unable to write sha1 filename %s",
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)
int len, baselen, ch;
baselen = strlen(base);
- len = baselen + 6; /* "refs/" + NUL */
+ len = baselen + 7; /* "/refs/" + NUL */
for (cp = ref; (ch = *cp) != 0; cp++, len++)
if (needs_quote(ch))
len += 2; /* extra two hex plus replacement % */
qref = xmalloc(len);
memcpy(qref, base, baselen);
- memcpy(qref + baselen, "refs/", 5);
- for (cp = ref, dp = qref + baselen + 5; (ch = *cp) != 0; cp++) {
+ memcpy(qref + baselen, "/refs/", 6);
+ for (cp = ref, dp = qref + baselen + 6; (ch = *cp) != 0; cp++) {
if (needs_quote(ch)) {
*dp++ = '%';
*dp++ = hex((ch >> 4) & 0xF);
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;
return 0;
}
-int main(int argc, char **argv)
+int main(int argc, const char **argv)
{
- char *commit_id;
- char *url;
- char *path;
+ int commits;
+ const char **write_ref = NULL;
+ char **commit_id;
+ const char *url;
+ char *s;
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') {
} 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();
no_pragma_header = curl_slist_append(no_pragma_header, "Pragma:");
alt = xmalloc(sizeof(*alt));
- alt->base = url;
+ alt->base = xmalloc(strlen(url) + 1);
+ strcpy(alt->base, url);
+ for (s = alt->base + strlen(alt->base) - 1; *s == '/'; --s)
+ *s = 0;
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");
+"status code. Suggest running git-fsck.\n");
}
return rc;
}