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: correctly write the field length in the skip length field

Browse Source
This commit is contained in:
Gijs van Tulder 2013-04-06 20:57:47 +02:00 committed by Giuseppe Scrivano
parent e3b3ea5120
commit edbeaa0c4e
2 changed files with 18 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/ChangeLog
View File

@ -1,3 +1,8 @@
2013-03-31 Gijs van Tulder <gvtulder@gmail.com>
* warc.c: Correctly write the field length in the skip length field
of .warc.gz files. (Following the GZIP spec in RFC 1952.)
2013-03-12 Darshit Shah <darnir@gmail.com> 2013-03-12 Darshit Shah <darnir@gmail.com>
* http.c (gethttp): Make wget return FILEBADFILE error and abort if * http.c (gethttp): Make wget return FILEBADFILE error and abort if

23
src/warc.c
View File

@ -165,7 +165,7 @@ warc_write_string (const char *str)
} }
#define EXTRA_GZIP_HEADER_SIZE 12 #define EXTRA_GZIP_HEADER_SIZE 14
#define GZIP_STATIC_HEADER_SIZE 10 #define GZIP_STATIC_HEADER_SIZE 10
#define FLG_FEXTRA 0x04 #define FLG_FEXTRA 0x04
#define OFF_FLG 3 #define OFF_FLG 3
@ -200,7 +200,7 @@ warc_write_start_record (void)
In warc_write_end_record we will fill this space In warc_write_end_record we will fill this space
with information about the uncompressed and with information about the uncompressed and
compressed size of the record. */ compressed size of the record. */
fprintf (warc_current_file, "XXXXXXXXXXXX"); fseek (warc_current_file, EXTRA_GZIP_HEADER_SIZE, SEEK_CUR);
fflush (warc_current_file); fflush (warc_current_file);
/* Start a new GZIP stream. */ /* Start a new GZIP stream. */
@ -342,16 +342,19 @@ warc_write_end_record (void)
/* The extra header field identifier for the WARC skip length. */ /* The extra header field identifier for the WARC skip length. */
extra_header[2] = 's'; extra_header[2] = 's';
extra_header[3] = 'l'; extra_header[3] = 'l';
/* The size of the field value (8 bytes). */
extra_header[4] = (8 & 255);
extra_header[5] = ((8 >> 8) & 255);
/* The size of the uncompressed record. */ /* The size of the uncompressed record. */
extra_header[4] = (uncompressed_size & 255); extra_header[6] = (uncompressed_size & 255);
extra_header[5] = (uncompressed_size >> 8) & 255; extra_header[7] = (uncompressed_size >> 8) & 255;
extra_header[6] = (uncompressed_size >> 16) & 255; extra_header[8] = (uncompressed_size >> 16) & 255;
extra_header[7] = (uncompressed_size >> 24) & 255; extra_header[9] = (uncompressed_size >> 24) & 255;
/* The size of the compressed record. */ /* The size of the compressed record. */
extra_header[8] = (compressed_size & 255); extra_header[10] = (compressed_size & 255);
extra_header[9] = (compressed_size >> 8) & 255; extra_header[11] = (compressed_size >> 8) & 255;
extra_header[10] = (compressed_size >> 16) & 255; extra_header[12] = (compressed_size >> 16) & 255;
extra_header[11] = (compressed_size >> 24) & 255; extra_header[13] = (compressed_size >> 24) & 255;
/* Write the extra header after the static header. */ /* Write the extra header after the static header. */
fseeko (warc_current_file, warc_current_gzfile_offset fseeko (warc_current_file, warc_current_gzfile_offset