1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
|
#!/usr/bin/env python3
"""
This is a "one-time" tranform helper script for CDX backfill into sandcrawler
postgresql.
Most of this file was copied from '../python/common.py'.
"""
import json, os, sys
import base64
NORMAL_MIME = (
'application/pdf',
'application/postscript',
'text/html',
'text/xml',
)
def normalize_mime(raw):
raw = raw.lower()
for norm in NORMAL_MIME:
if raw.startswith(norm):
return norm
# Special cases
if raw.startswith('application/xml'):
return 'text/xml'
if raw.startswith('application/x-pdf'):
return 'application/pdf'
return None
def test_normalize_mime():
assert normalize_mime("asdf") is None
assert normalize_mime("application/pdf") == "application/pdf"
assert normalize_mime("application/pdf+journal") == "application/pdf"
assert normalize_mime("Application/PDF") == "application/pdf"
assert normalize_mime("application/p") is None
assert normalize_mime("application/xml+stuff") == "text/xml"
assert normalize_mime("application/x-pdf") == "application/pdf"
assert normalize_mime("application/x-html") is None
def b32_hex(s):
s = s.strip().split()[0].lower()
if s.startswith("sha1:"):
s = s[5:]
if len(s) != 32:
return s
return base64.b16encode(base64.b32decode(s.upper())).lower().decode('utf-8')
def parse_cdx_line(raw_cdx):
cdx = raw_cdx.split()
if len(cdx) < 11:
return None
surt = cdx[0]
dt = cdx[1]
url = cdx[2]
mime = normalize_mime(cdx[3])
http_status = cdx[4]
key = cdx[5]
c_size = cdx[8]
offset = cdx[9]
warc = cdx[10]
if not (key.isalnum() and c_size.isdigit() and offset.isdigit()
and http_status == "200" and len(key) == 32 and dt.isdigit()
and mime != None):
return None
if '-' in (surt, dt, url, mime, http_status, key, c_size, offset, warc):
return None
# these are the new/specific bits
sha1 = b32_hex(key)
return dict(url=url, datetime=dt, sha1hex=sha1, cdx_sha1hex=None, mimetype=mime, warc_path=warc, warc_csize=int(c_size), warc_offset=int(offset))
for l in sys.stdin:
l = l.strip()
if not l:
continue
info = parse_cdx_line(l)
if not info:
continue
print("\t".join([info['url'], info['datetime'], info['sha1hex'], info['mimetype'], info['warc_path'], str(info['warc_csize']), str(info['warc_offset'])]))
|