Mercurial > hg > cc > cirrus_work

annotate bin/test_warc.py @ 47:b59f49909bda

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
sic
author Henry S. Thompson <ht@inf.ed.ac.uk>
date Thu, 06 Jul 2023 10:19:02 +0100
parents 212da3fe3b19
children e20c64917805
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
42
689a0e311cd2 make warc.py a library, separate out testing
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
1 import warc,sys
689a0e311cd2 make warc.py a library, separate out testing
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
2
689a0e311cd2 make warc.py a library, separate out testing
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
3 OUT=open(sys.stdout.fileno(),'wb')
689a0e311cd2 make warc.py a library, separate out testing
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
4
689a0e311cd2 make warc.py a library, separate out testing
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
5 if (debug:=(sys.argv[1]=='-d')):
689a0e311cd2 make warc.py a library, separate out testing
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
6 sys.argv.pop(1)
689a0e311cd2 make warc.py a library, separate out testing
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
7
689a0e311cd2 make warc.py a library, separate out testing
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
8 def showme(wtype,buf,part):
45
212da3fe3b19 make test 1 idempotent
Henry S. Thompson <ht@inf.ed.ac.uk>
parents: 42
diff changeset
9 # This should exactly reproduce a complete warc file if called
212da3fe3b19 make test 1 idempotent
Henry S. Thompson <ht@inf.ed.ac.uk>
parents: 42
diff changeset
10 # as per version 1 below
42
689a0e311cd2 make warc.py a library, separate out testing
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
11 if debug:
45
212da3fe3b19 make test 1 idempotent
Henry S. Thompson <ht@inf.ed.ac.uk>
parents: 42
diff changeset
12 OUT.write(b"%d\n%b"%(part,buf))
212da3fe3b19 make test 1 idempotent
Henry S. Thompson <ht@inf.ed.ac.uk>
parents: 42
diff changeset
13 else:
212da3fe3b19 make test 1 idempotent
Henry S. Thompson <ht@inf.ed.ac.uk>
parents: 42
diff changeset
14 OUT.write(buf)
212da3fe3b19 make test 1 idempotent
Henry S. Thompson <ht@inf.ed.ac.uk>
parents: 42
diff changeset
15 if buf[-1]!=b'\n':
212da3fe3b19 make test 1 idempotent
Henry S. Thompson <ht@inf.ed.ac.uk>
parents: 42
diff changeset
16 OUT.write(b'\r\n')
212da3fe3b19 make test 1 idempotent
Henry S. Thompson <ht@inf.ed.ac.uk>
parents: 42
diff changeset
17 if part==7:
212da3fe3b19 make test 1 idempotent
Henry S. Thompson <ht@inf.ed.ac.uk>
parents: 42
diff changeset
18 OUT.write(b'\r\n') # to match complete file formatting
42
689a0e311cd2 make warc.py a library, separate out testing
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
19
45
212da3fe3b19 make test 1 idempotent
Henry S. Thompson <ht@inf.ed.ac.uk>
parents: 42
diff changeset
20 # 1 warc.warc(sys.argv[1],showme,[b'response','warcinfo','request','metadata'],whole=True)
42
689a0e311cd2 make warc.py a library, separate out testing
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
21
45
212da3fe3b19 make test 1 idempotent
Henry S. Thompson <ht@inf.ed.ac.uk>
parents: 42
diff changeset
22 # 2
42
689a0e311cd2 make warc.py a library, separate out testing
Henry S. Thompson <ht@inf.ed.ac.uk>
parents:
diff changeset
23 warc.warc(sys.argv[1],showme,[b'response'],parts=int(sys.argv[2]),debug=debug)