backup/pywb
1
0
Fork 0
mirror of https://github.com/webrecorder/pywb.git synced 2025-03-15 00:03:28 +01:00
Code Issues Projects Releases Activity

tests/typo fix: add tests for truncated record detection (see: ikreymer/webarchiveplayer#14) fix typo, closes #161

Browse Source
This commit is contained in:
Ilya Kreymer 2015-12-10 12:31:58 -08:00
parent b12a24e990
commit 9b8b4d8388
3 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
pywb/warc/archiveiterator.py
View File

@ -9,6 +9,7 @@ import hashlib
import base64
import re
import sys
try: # pragma: no cover
from collections import OrderedDict

3
pywb/warc/test/test_indexing.py
View File

@ -25,12 +25,13 @@ com,example)/?example=1 20140103030341 http://example.com?example=1 warc/revisit
org,iana)/domains/example 20140128051539 http://www.iana.org/domains/example text/html 302 JZ622UA23G5ZU6Y3XAKH4LINONUEICEG - - 854 4771 example.warc
# warc all
# note: length of request record set to 1 byte less then record to test truncation handling
>>> print_cdx_index('example.warc', include_all=True)
CDX N b a m s k r M S V g
com,example)/?example=1 20140103030321 http://example.com?example=1 text/html 200 B2LTWWPUOYAH7UIPQ7ZUPQ4VMBSVC36A - - 1987 460 example.warc
com,example)/?example=1 20140103030321 http://example.com?example=1 - - - - - 706 2451 example.warc
com,example)/?example=1 20140103030341 http://example.com?example=1 warc/revisit - B2LTWWPUOYAH7UIPQ7ZUPQ4VMBSVC36A - - 896 3161 example.warc
com,example)/?example=1 20140103030341 http://example.com?example=1 - - - - - 706 4061 example.warc
com,example)/?example=1 20140103030341 http://example.com?example=1 - - - - - 703 4061 example.warc
org,iana)/domains/example 20140128051539 http://www.iana.org/domains/example text/html 302 JZ622UA23G5ZU6Y3XAKH4LINONUEICEG - - 854 4771 example.warc
# arc.gz

2
sample_archive/warcs/example.warc
View File

@ -140,7 +140,7 @@ WARC/1.0
WARC-Type: request
WARC-Record-ID: <urn:uuid:c59f3330-b241-4fca-8513-d687cd85bcfb>
WARC-Date: 2014-01-03T03:03:41Z
Content-Length: 323
Content-Length: 320
Content-Type: application/http; msgtype=request
WARC-Concurrent-To: <urn:uuid:3619f5b0-d967-44be-8f24-762098d427c4>
WARC-Target-URI: http://example.com?example=1