http*: add helper methods for fetching objects (loose)

The code handling the fetching of loose objects in http-push.c and
http-walker.c have been refactored into new methods and a new struct
(object_http_request) in http.c. They are not meant to be invoked
elsewhere.

The new methods in http.c are
 - new_http_object_request
 - process_http_object_request
 - finish_http_object_request
 - abort_http_object_request
 - release_http_object_request

and the new struct is http_object_request.

RANGER_HEADER_SIZE and no_pragma_header is no longer made available
outside of http.c, since after the above changes, there are no other
instances of usage outside of http.c.

Remove members of the transfer_request struct in http-push.c and
http-walker.c, including filename, real_sha1 and zret, as they are used
no longer used.

Move the methods append_remote_object_url() and get_remote_object_url()
from http-push.c to http.c. Additionally, get_remote_object_url() is no
longer defined only when USE_CURL_MULTI is defined, since
non-USE_CURL_MULTI code in http.c uses it (namely, in
new_http_object_request()).

Refactor code from http-push.c::start_fetch_loose() and
http-walker.c::start_object_fetch_request() that deals with the details
of coming up with the filename to store the retrieved object, resuming
a previously aborted request, and making a new curl request, into a new
function, new_http_object_request().

Refactor code from http-walker.c::process_object_request() into the
function, process_http_object_request().

Refactor code from http-push.c::finish_request() and
http-walker.c::finish_object_request() into a new function,
finish_http_object_request(). It returns the result of the
move_temp_to_file() invocation.

Add a function, release_http_object_request(), which cleans up object
request data. http-push.c and http-walker.c invoke this function
separately; http-push.c::release_request() and
http-walker.c::release_object_request() do not invoke this function.

Add a function, abort_http_object_request(), which unlink()s the object
file and invokes release_http_object_request(). Update
http-walker.c::abort_object_request() to use this.

Signed-off-by: Tay Ray Chuan <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: rctay

http-push.c

@@ -115,18 +115,10 @@ struct transfer_request
 	struct remote_lock *lock;
 	struct curl_slist *headers;
 	struct buffer buffer;
-	char filename[PATH_MAX];
-	char tmpfile[PATH_MAX];
-	int local_fileno;
 	enum transfer_state state;
 	CURLcode curl_result;
 	char errorstr[CURL_ERROR_SIZE];
 	long http_code;
-	unsigned char real_sha1[20];
-	git_SHA_CTX c;
-	z_stream stream;
-	int zret;
-	int rename;
 	void *userData;
 	struct active_request_slot *slot;
 	struct transfer_request *next;
@@ -232,15 +224,6 @@ static struct curl_slist *get_dav_token_headers(struct remote_lock *lock, enum d
 	return dav_headers;
 }
 
-static void append_remote_object_url(struct strbuf *buf, const char *url,
-				     const char *hex,
-				     int only_two_digit_prefix)
-{
-	strbuf_addf(buf, "%sobjects/%.*s/", url, 2, hex);
-	if (!only_two_digit_prefix)
-		strbuf_addf(buf, "%s", hex+2);
-}
-
 static void finish_request(struct transfer_request *request);
 static void release_request(struct transfer_request *request);
 
@@ -254,169 +237,29 @@ static void process_response(void *callback_data)
 
 #ifdef USE_CURL_MULTI
 
-static char *get_remote_object_url(const char *url, const char *hex,
-				   int only_two_digit_prefix)
-{
-	struct strbuf buf = STRBUF_INIT;
-	append_remote_object_url(&buf, url, hex, only_two_digit_prefix);
-	return strbuf_detach(&buf, NULL);
-}
-
-static size_t fwrite_sha1_file(void *ptr, size_t eltsize, size_t nmemb,
-			       void *data)
-{
-	unsigned char expn[4096];
-	size_t size = eltsize * nmemb;
-	int posn = 0;
-	struct transfer_request *request = (struct transfer_request *)data;
-	do {
-		ssize_t retval = xwrite(request->local_fileno,
-					(char *) ptr + posn, size - posn);
-		if (retval < 0)
-			return posn;
-		posn += retval;
-	} while (posn < size);
-
-	request->stream.avail_in = size;
-	request->stream.next_in = ptr;
-	do {
-		request->stream.next_out = expn;
-		request->stream.avail_out = sizeof(expn);
-		request->zret = git_inflate(&request->stream, Z_SYNC_FLUSH);
-		git_SHA1_Update(&request->c, expn,
-				sizeof(expn) - request->stream.avail_out);
-	} while (request->stream.avail_in && request->zret == Z_OK);
-	data_received++;
-	return size;
-}
-
 static void start_fetch_loose(struct transfer_request *request)
 {
-	char *hex = sha1_to_hex(request->obj->sha1);
-	char *filename;
-	char prevfile[PATH_MAX];
-	char *url;
-	int prevlocal;
-	unsigned char prev_buf[PREV_BUF_SIZE];
-	ssize_t prev_read = 0;
-	long prev_posn = 0;
-	char range[RANGE_HEADER_SIZE];
-	struct curl_slist *range_header = NULL;
 	struct active_request_slot *slot;
+	struct http_object_request *obj_req;
 
-	filename = sha1_file_name(request->obj->sha1);
-	snprintf(request->filename, sizeof(request->filename), "%s", filename);
-	snprintf(request->tmpfile, sizeof(request->tmpfile),
-		 "%s.temp", filename);
-
-	snprintf(prevfile, sizeof(prevfile), "%s.prev", request->filename);
-	unlink_or_warn(prevfile);
-	rename(request->tmpfile, prevfile);
-	unlink_or_warn(request->tmpfile);
-
-	if (request->local_fileno != -1)
-		error("fd leakage in start: %d", request->local_fileno);
-	request->local_fileno = open(request->tmpfile,
-				     O_WRONLY | O_CREAT | O_EXCL, 0666);
-	/*
-	 * This could have failed due to the "lazy directory creation";
-	 * try to mkdir the last path component.
-	 */
-	if (request->local_fileno < 0 && errno == ENOENT) {
-		char *dir = strrchr(request->tmpfile, '/');
-		if (dir) {
-			*dir = 0;
-			mkdir(request->tmpfile, 0777);
-			*dir = '/';
-		}
-		request->local_fileno = open(request->tmpfile,
-					     O_WRONLY | O_CREAT | O_EXCL, 0666);
-	}
-
-	if (request->local_fileno < 0) {
+	obj_req = new_http_object_request(repo->url, request->obj->sha1);
+	if (obj_req == NULL) {
 		request->state = ABORTED;
-		error("Couldn't create temporary file %s for %s: %s",
-		      request->tmpfile, request->filename, strerror(errno));
 		return;
 	}
 
-	memset(&request->stream, 0, sizeof(request->stream));
-
-	git_inflate_init(&request->stream);
-
-	git_SHA1_Init(&request->c);
-
-	url = get_remote_object_url(repo->url, hex, 0);
-	request->url = xstrdup(url);
-
-	/*
-	 * If a previous temp file is present, process what was already
-	 * fetched.
-	 */
-	prevlocal = open(prevfile, O_RDONLY);
-	if (prevlocal != -1) {
-		do {
-			prev_read = xread(prevlocal, prev_buf, PREV_BUF_SIZE);
-			if (prev_read>0) {
-				if (fwrite_sha1_file(prev_buf,
-						     1,
-						     prev_read,
-						     request) == prev_read)
-					prev_posn += prev_read;
-				else
-					prev_read = -1;
-			}
-		} while (prev_read > 0);
-		close(prevlocal);
-	}
-	unlink_or_warn(prevfile);
-
-	/*
-	 * Reset inflate/SHA1 if there was an error reading the previous temp
-	 * file; also rewind to the beginning of the local file.
-	 */
-	if (prev_read == -1) {
-		memset(&request->stream, 0, sizeof(request->stream));
-		git_inflate_init(&request->stream);
-		git_SHA1_Init(&request->c);
-		if (prev_posn>0) {
-			prev_posn = 0;
-			lseek(request->local_fileno, 0, SEEK_SET);
-			ftruncate(request->local_fileno, 0);
-		}
-	}
-
-	slot = get_active_slot();
+	slot = obj_req->slot;
 	slot->callback_func = process_response;
 	slot->callback_data = request;
 	request->slot = slot;
-
-	curl_easy_setopt(slot->curl, CURLOPT_FILE, request);
-	curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_sha1_file);
-	curl_easy_setopt(slot->curl, CURLOPT_ERRORBUFFER, request->errorstr);
-	curl_easy_setopt(slot->curl, CURLOPT_URL, url);
-	curl_easy_setopt(slot->curl, CURLOPT_HTTPHEADER, no_pragma_header);
-
-	/*
-	 * If we have successfully processed data from a previous fetch
-	 * attempt, only fetch the data we don't already have.
-	 */
-	if (prev_posn>0) {
-		if (push_verbosely)
-			fprintf(stderr,
-				"Resuming fetch of object %s at byte %ld\n",
-				hex, prev_posn);
-		sprintf(range, "Range: bytes=%ld-", prev_posn);
-		range_header = curl_slist_append(range_header, range);
-		curl_easy_setopt(slot->curl,
-				 CURLOPT_HTTPHEADER, range_header);
-	}
+	request->userData = obj_req;
 
 	/* Try to get the request started, abort the request on error */
 	request->state = RUN_FETCH_LOOSE;
 	if (!start_active_slot(slot)) {
 		fprintf(stderr, "Unable to start GET request\n");
 		repo->can_update_info_refs = 0;
+		release_http_object_request(obj_req);
 		release_request(request);
 	}
 }
@@ -675,16 +518,14 @@ static void release_request(struct transfer_request *request)
 			entry->next = entry->next->next;
 	}
 
-	if (request->local_fileno != -1)
-		close(request->local_fileno);
 	free(request->url);
 	free(request);
 }
 
 static void finish_request(struct transfer_request *request)
 {
-	struct stat st;
 	struct http_pack_request *preq;
+	struct http_object_request *obj_req;
 
 	request->curl_result = request->slot->curl_result;
 	request->http_code = request->slot->http_code;
@@ -739,39 +580,17 @@ static void finish_request(struct transfer_request *request)
 			aborted = 1;
 		}
 	} else if (request->state == RUN_FETCH_LOOSE) {
-		close(request->local_fileno);
-		request->local_fileno = -1;
-
-		if (request->curl_result != CURLE_OK &&
-		    request->http_code != 416) {
-			if (stat(request->tmpfile, &st) == 0) {
-				if (st.st_size == 0)
-					unlink_or_warn(request->tmpfile);
-			}
-		} else {
-			if (request->http_code == 416)
-				warning("requested range invalid; we may already have all the data.");
-
-			git_inflate_end(&request->stream);
-			git_SHA1_Final(request->real_sha1, &request->c);
-			if (request->zret != Z_STREAM_END) {
-				unlink_or_warn(request->tmpfile);
-			} else if (hashcmp(request->obj->sha1, request->real_sha1)) {
-				unlink_or_warn(request->tmpfile);
-			} else {
-				request->rename =
-					move_temp_to_file(
-						request->tmpfile,
-						request->filename);
-				if (request->rename == 0)
-					request->obj->flags |= (LOCAL | REMOTE);
-			}
-		}
+		obj_req = (struct http_object_request *)request->userData;
+
+		if (finish_http_object_request(obj_req) == 0)
+			if (obj_req->rename == 0)
+				request->obj->flags |= (LOCAL | REMOTE);
 
 		/* Try fetching packed if necessary */
-		if (request->obj->flags & LOCAL)
+		if (request->obj->flags & LOCAL) {
+			release_http_object_request(obj_req);
 			release_request(request);
-		else
+		} else
 			start_fetch_packed(request);
 
 	} else if (request->state == RUN_FETCH_PACKED) {
@@ -843,7 +662,6 @@ static void add_fetch_request(struct object *obj)
 	request->url = NULL;
 	request->lock = NULL;
 	request->headers = NULL;
-	request->local_fileno = -1;
 	request->state = NEED_FETCH;
 	request->next = request_queue_head;
 	request_queue_head = request;
@@ -882,7 +700,6 @@ static int add_send_request(struct object *obj, struct remote_lock *lock)
 	request->url = NULL;
 	request->lock = lock;
 	request->headers = NULL;
-	request->local_fileno = -1;
 	request->state = NEED_PUSH;
 	request->next = request_queue_head;
 	request_queue_head = request;