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 <rctay89@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 40 insertions, 227 deletions

diff --git a/http-walker.c b/http-walker.c
index 8f7a975f96..700bc13112 100644
--- a/http-walker.c
+++ b/http-walker.c
@@ -3,8 +3,6 @@
 #include "walker.h"
 #include "http.h"
 
-#define PREV_BUF_SIZE 4096
-
 struct alt_base
 {
 	char *base;
@@ -25,20 +23,8 @@ struct object_request
 	struct walker *walker;
 	unsigned char sha1[20];
 	struct alt_base *repo;
-	char *url;
-	char filename[PATH_MAX];
-	char tmpfile[PATH_MAX];
-	int local;
 	enum object_request_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;
-	struct active_request_slot *slot;
+	struct http_object_request *req;
 	struct object_request *next;
 };
 
@@ -59,34 +45,6 @@ struct walker_data {
 
 static struct object_request *object_queue_head;
 
-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 object_request *obj_req = (struct object_request *)data;
-	do {
-		ssize_t retval = xwrite(obj_req->local,
-					(char *) ptr + posn, size - posn);
-		if (retval < 0)
-			return posn;
-		posn += retval;
-	} while (posn < size);
-
-	obj_req->stream.avail_in = size;
-	obj_req->stream.next_in = ptr;
-	do {
-		obj_req->stream.next_out = expn;
-		obj_req->stream.avail_out = sizeof(expn);
-		obj_req->zret = git_inflate(&obj_req->stream, Z_SYNC_FLUSH);
-		git_SHA1_Update(&obj_req->c, expn,
-				sizeof(expn) - obj_req->stream.avail_out);
-	} while (obj_req->stream.avail_in && obj_req->zret == Z_OK);
-	data_received++;
-	return size;
-}
-
 static void fetch_alternates(struct walker *walker, const char *base);
 
 static void process_object_response(void *callback_data);
@@ -94,172 +52,35 @@ static void process_object_response(void *callback_data);
 static void start_object_request(struct walker *walker,
 				 struct object_request *obj_req)
 {
-	char *hex = sha1_to_hex(obj_req->sha1);
-	char prevfile[PATH_MAX];
-	char *url;
-	char *posn;
-	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 *req;
 
-	snprintf(prevfile, sizeof(prevfile), "%s.prev", obj_req->filename);
-	unlink_or_warn(prevfile);
-	rename(obj_req->tmpfile, prevfile);
-	unlink_or_warn(obj_req->tmpfile);
-
-	if (obj_req->local != -1)
-		error("fd leakage in start: %d", obj_req->local);
-	obj_req->local = open(obj_req->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 (obj_req->local < 0 && errno == ENOENT) {
-		char *dir = strrchr(obj_req->tmpfile, '/');
-		if (dir) {
-			*dir = 0;
-			mkdir(obj_req->tmpfile, 0777);
-			*dir = '/';
-		}
-		obj_req->local = open(obj_req->tmpfile,
-				      O_WRONLY | O_CREAT | O_EXCL, 0666);
-	}
-
-	if (obj_req->local < 0) {
+	req = new_http_object_request(obj_req->repo->base, obj_req->sha1);
+	if (req == NULL) {
 		obj_req->state = ABORTED;
-		error("Couldn't create temporary file %s for %s: %s",
-		      obj_req->tmpfile, obj_req->filename, strerror(errno));
 		return;
 	}
+	obj_req->req = req;
 
-	memset(&obj_req->stream, 0, sizeof(obj_req->stream));
-
-	git_inflate_init(&obj_req->stream);
-
-	git_SHA1_Init(&obj_req->c);
-
-	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 += 9;
-	memcpy(posn, hex, 2);
-	posn += 2;
-	*(posn++) = '/';
-	strcpy(posn, hex + 2);
-	strcpy(obj_req->url, 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,
-						     obj_req) == 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(&obj_req->stream, 0, sizeof(obj_req->stream));
-		git_inflate_init(&obj_req->stream);
-		git_SHA1_Init(&obj_req->c);
-		if (prev_posn>0) {
-			prev_posn = 0;
-			lseek(obj_req->local, 0, SEEK_SET);
-			ftruncate(obj_req->local, 0);
-		}
-	}
-
-	slot = get_active_slot();
+	slot = req->slot;
 	slot->callback_func = process_object_response;
 	slot->callback_data = obj_req;
-	obj_req->slot = slot;
-
-	curl_easy_setopt(slot->curl, CURLOPT_FILE, obj_req);
-	curl_easy_setopt(slot->curl, CURLOPT_WRITEFUNCTION, fwrite_sha1_file);
-	curl_easy_setopt(slot->curl, CURLOPT_ERRORBUFFER, obj_req->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 (walker->get_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);
-	}
 
 	/* Try to get the request started, abort the request on error */
 	obj_req->state = ACTIVE;
 	if (!start_active_slot(slot)) {
 		obj_req->state = ABORTED;
-		obj_req->slot = NULL;
-		close(obj_req->local);
-		obj_req->local = -1;
-		free(obj_req->url);
+		release_http_object_request(req);
 		return;
 	}
 }
 
 static void finish_object_request(struct object_request *obj_req)
 {
-	struct stat st;
-
-	close(obj_req->local);
-	obj_req->local = -1;
-
-	if (obj_req->http_code == 416) {
-		fprintf(stderr, "Warning: requested range invalid; we may already have all the data.\n");
-	} else if (obj_req->curl_result != CURLE_OK) {
-		if (stat(obj_req->tmpfile, &st) == 0)
-			if (st.st_size == 0)
-				unlink_or_warn(obj_req->tmpfile);
+	if (finish_http_object_request(obj_req->req))
 		return;
-	}
-
-	git_inflate_end(&obj_req->stream);
-	git_SHA1_Final(obj_req->real_sha1, &obj_req->c);
-	if (obj_req->zret != Z_STREAM_END) {
-		unlink_or_warn(obj_req->tmpfile);
-		return;
-	}
-	if (hashcmp(obj_req->sha1, obj_req->real_sha1)) {
-		unlink_or_warn(obj_req->tmpfile);
-		return;
-	}
-	obj_req->rename =
-		move_temp_to_file(obj_req->tmpfile, obj_req->filename);
 
-	if (obj_req->rename == 0)
+	if (obj_req->req->rename == 0)
 		walker_say(obj_req->walker, "got %s\n", sha1_to_hex(obj_req->sha1));
 }
 
@@ -271,19 +92,16 @@ static void process_object_response(void *callback_data)
 	struct walker_data *data = walker->data;
 	struct alt_base *alt = data->alt;
 
-	obj_req->curl_result = obj_req->slot->curl_result;
-	obj_req->http_code = obj_req->slot->http_code;
-	obj_req->slot = NULL;
+	process_http_object_request(obj_req->req);
 	obj_req->state = COMPLETE;
 
 	/* Use alternates if necessary */
-	if (missing_target(obj_req)) {
+	if (missing_target(obj_req->req)) {
 		fetch_alternates(walker, alt->base);
 		if (obj_req->repo->next != NULL) {
 			obj_req->repo =
 				obj_req->repo->next;
-			close(obj_req->local);
-			obj_req->local = -1;
+			release_http_object_request(obj_req->req);
 			start_object_request(walker, obj_req);
 			return;
 		}
@@ -296,8 +114,8 @@ static void release_object_request(struct object_request *obj_req)
 {
 	struct object_request *entry = object_queue_head;
 
-	if (obj_req->local != -1)
-		error("fd leakage in release: %d", obj_req->local);
+	if (obj_req->req !=NULL && obj_req->req->localfile != -1)
+		error("fd leakage in release: %d", obj_req->req->localfile);
 	if (obj_req == object_queue_head) {
 		object_queue_head = obj_req->next;
 	} else {
@@ -307,7 +125,6 @@ static void release_object_request(struct object_request *obj_req)
 			entry->next = entry->next->next;
 	}
 
-	free(obj_req->url);
 	free(obj_req);
 }
 
@@ -335,19 +152,13 @@ static void prefetch(struct walker *walker, unsigned char *sha1)
 	struct object_request *newreq;
 	struct object_request *tail;
 	struct walker_data *data = walker->data;
-	char *filename = sha1_file_name(sha1);
 
 	newreq = xmalloc(sizeof(*newreq));
 	newreq->walker = walker;
 	hashcpy(newreq->sha1, sha1);
 	newreq->repo = data->alt;
-	newreq->url = NULL;
-	newreq->local = -1;
 	newreq->state = WAITING;
-	snprintf(newreq->filename, sizeof(newreq->filename), "%s", filename);
-	snprintf(newreq->tmpfile, sizeof(newreq->tmpfile),
-		 "%s.temp", filename);
-	newreq->slot = NULL;
+	newreq->req = NULL;
 	newreq->next = NULL;
 
 	http_is_verbose = walker->get_verbosely;
@@ -638,15 +449,6 @@ abort:
 
 static void abort_object_request(struct object_request *obj_req)
 {
-	if (obj_req->local >= 0) {
-		close(obj_req->local);
-		obj_req->local = -1;
-	}
-	unlink_or_warn(obj_req->tmpfile);
-	if (obj_req->slot) {
-		release_active_slot(obj_req->slot);
-		obj_req->slot = NULL;
-	}
 	release_object_request(obj_req);
 }
 
@@ -655,6 +457,7 @@ static int fetch_object(struct walker *walker, struct alt_base *repo, unsigned c
 	char *hex = sha1_to_hex(sha1);
 	int ret = 0;
 	struct object_request *obj_req = object_queue_head;
+	struct http_object_request *req;
 
 	while (obj_req != NULL && hashcmp(obj_req->sha1, sha1))
 		obj_req = obj_req->next;
@@ -662,6 +465,8 @@ static int fetch_object(struct walker *walker, struct alt_base *repo, unsigned c
 		return error("Couldn't find request for %s in the queue", hex);
 
 	if (has_sha1_file(obj_req->sha1)) {
+		if (obj_req->req != NULL)
+			abort_http_object_request(obj_req->req);
 		abort_object_request(obj_req);
 		return 0;
 	}
@@ -673,34 +478,42 @@ static int fetch_object(struct walker *walker, struct alt_base *repo, unsigned c
 	start_object_request(walker, obj_req);
 #endif
 
+	/*
+	 * obj_req->req might change when fetching alternates in the callback
+	 * process_object_response; therefore, the "shortcut" variable, req,
+	 * is used only after we're done with slots.
+	 */
 	while (obj_req->state == ACTIVE)
-		run_active_slot(obj_req->slot);
+		run_active_slot(obj_req->req->slot);
+
+	req = obj_req->req;
 
-	if (obj_req->local != -1) {
-		close(obj_req->local);
-		obj_req->local = -1;
+	if (req->localfile != -1) {
+		close(req->localfile);
+		req->localfile = -1;
 	}
 
 	if (obj_req->state == ABORTED) {
 		ret = error("Request for %s aborted", hex);
-	} else if (obj_req->curl_result != CURLE_OK &&
-		   obj_req->http_code != 416) {
-		if (missing_target(obj_req))
+	} else if (req->curl_result != CURLE_OK &&
+		   req->http_code != 416) {
+		if (missing_target(req))
 			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) {
+				    req->errorstr, req->curl_result,
+				    req->http_code, hex);
+	} else if (req->zret != Z_STREAM_END) {
 		walker->corrupt_object_found++;
-		ret = error("File %s (%s) corrupt", hex, obj_req->url);
-	} else if (hashcmp(obj_req->sha1, obj_req->real_sha1)) {
+		ret = error("File %s (%s) corrupt", hex, req->url);
+	} else if (hashcmp(obj_req->sha1, req->real_sha1)) {
 		ret = error("File %s has bad hash", hex);
-	} else if (obj_req->rename < 0) {
+	} else if (req->rename < 0) {
 		ret = error("unable to write sha1 filename %s",
-			    obj_req->filename);
+			    req->filename);
 	}
 
+	release_http_object_request(req);
 	release_object_request(obj_req);
 	return ret;
 }