moparisthebest/wget
1
0
Fork 0
mirror of https://github.com/moparisthebest/wget synced 2024-07-03 16:38:41 -04:00
Code Issues Releases Wiki Activity

warc: Follow the guidelines for metadata records

Browse Source 
Do not use the same UUID for the manifest and arguments records.
Write the manifest as a metadata record, not as a resource.
This commit is contained in:
Gijs van Tulder 2013-04-12 23:37:45 +02:00 committed by Giuseppe Scrivano
parent bc2891f307
commit 7df4b05f0b
3 changed files with 66 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/ChangeLog
View File

@ -1,3 +1,11 @@
2013-04-12 Gijs van Tulder <gvtulder@gmail.com>
* warc.c: Generate unique UUIDs for the manifest and the record
holding the command-line arguments.
Write the manifest to a "metadata" record to follow the WARC
implementation guidelines.
* warc.h: Declare new function warc_write_metadata_record.
2013-03-15 Darshit Shah <darnir@gmail.com>
* http.c (post_file): Rename function to body_file_send to more

64
src/warc.c
View File

@ -1083,7 +1083,7 @@ warc_write_metadata (void)
warc_uuid_str (manifest_uuid);
fflush (warc_manifest_fp);
warc_write_resource_record (manifest_uuid,
warc_write_metadata_record (manifest_uuid,
"metadata://gnu.org/software/wget/warc/MANIFEST.txt",
NULL, NULL, NULL, "text/plain",
warc_manifest_fp, -1);
@ -1098,9 +1098,9 @@ warc_write_metadata (void)
fflush (warc_tmp_fp);
fprintf (warc_tmp_fp, "%s\n", program_argstring);
warc_write_resource_record (manifest_uuid,
warc_write_resource_record (NULL,
"metadata://gnu.org/software/wget/warc/wget_arguments.txt",
NULL, NULL, NULL, "text/plain",
NULL, manifest_uuid, NULL, "text/plain",
warc_tmp_fp, -1);
/* warc_write_resource_record has closed warc_tmp_fp. */
@ -1395,20 +1395,22 @@ warc_write_response_record (char *url, char *timestamp_str,
return warc_write_ok;
}
/* Writes a resource record to the WARC file.
/* Writes a resource or metadata record to the WARC file.
warc_type is either "resource" or "metadata",
resource_uuid is the uuid of the resource (or NULL),
url is the target uri of the resource,
timestamp_str is the timestamp (generated with warc_timestamp),
concurrent_to_uuid is the uuid of the request for that generated this
concurrent_to_uuid is the uuid of the record that generated this,
resource (generated with warc_uuid_str) or NULL,
ip is the ip address of the server (or NULL),
content_type is the mime type of the body (or NULL),
body is a pointer to a file containing the resource data.
Calling this function will close body.
Returns true on success, false on error. */
bool
warc_write_resource_record (char *resource_uuid, const char *url,
const char *timestamp_str, const char *concurrent_to_uuid,
static bool
warc_write_record (const char *record_type, char *resource_uuid,
const char *url, const char *timestamp_str,
const char *concurrent_to_uuid,
ip_address *ip, const char *content_type, FILE *body,
off_t payload_offset)
{
@ -1422,7 +1424,7 @@ warc_write_resource_record (char *resource_uuid, const char *url,
content_type = "application/octet-stream";
warc_write_start_record ();
warc_write_header ("WARC-Type", "resource");
warc_write_header ("WARC-Type", record_type);
warc_write_header ("WARC-Record-ID", resource_uuid);
warc_write_header ("WARC-Warcinfo-ID", warc_current_warcinfo_uuid_str);
warc_write_header ("WARC-Concurrent-To", concurrent_to_uuid);
@ -1438,3 +1440,47 @@ warc_write_resource_record (char *resource_uuid, const char *url,
return warc_write_ok;
}
/* Writes a resource record to the WARC file.
resource_uuid is the uuid of the resource (or NULL),
url is the target uri of the resource,
timestamp_str is the timestamp (generated with warc_timestamp),
concurrent_to_uuid is the uuid of the record that generated this,
resource (generated with warc_uuid_str) or NULL,
ip is the ip address of the server (or NULL),
content_type is the mime type of the body (or NULL),
body is a pointer to a file containing the resource data.
Calling this function will close body.
Returns true on success, false on error. */
bool
warc_write_resource_record (char *resource_uuid, const char *url,
const char *timestamp_str, const char *concurrent_to_uuid,
ip_address *ip, const char *content_type, FILE *body,
off_t payload_offset)
{
return warc_write_record ("resource",
resource_uuid, url, timestamp_str, concurrent_to_uuid,
ip, content_type, body, payload_offset);
}
/* Writes a metadata record to the WARC file.
record_uuid is the uuid of the record (or NULL),
url is the target uri of the record,
timestamp_str is the timestamp (generated with warc_timestamp),
concurrent_to_uuid is the uuid of the record that generated this,
record (generated with warc_uuid_str) or NULL,
ip is the ip address of the server (or NULL),
content_type is the mime type of the body (or NULL),
body is a pointer to a file containing the record data.
Calling this function will close body.
Returns true on success, false on error. */
bool
warc_write_metadata_record (char *record_uuid, const char *url,
const char *timestamp_str, const char *concurrent_to_uuid,
ip_address *ip, const char *content_type, FILE *body,
off_t payload_offset)
{
return warc_write_record ("metadata",
record_uuid, url, timestamp_str, concurrent_to_uuid,
ip, content_type, body, payload_offset);
}

3
src/warc.h
View File

@ -19,5 +19,8 @@ bool warc_write_response_record (char *url, char *timestamp_str,
bool warc_write_resource_record (char *resource_uuid, const char *url,
const char *timestamp_str, const char *concurrent_to_uuid, ip_address *ip,
const char *content_type, FILE *body, off_t payload_offset);
bool warc_write_metadata_record (char *record_uuid, const char *url,
const char *timestamp_str, const char *concurrent_to_uuid, ip_address *ip,
const char *content_type, FILE *body, off_t payload_offset);
#endif /* WARC_H */