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
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
|
#!/usr/bin/env python
from urllib2 import urlopen
TLD_PREFIX = r"""
/**
* Regular expression to match all IANA top-level domains.
* List accurate as of 2010/02/05. List taken from:
* http://data.iana.org/TLD/tlds-alpha-by-domain.txt
* This pattern is auto-generated by frameworks/base/common/tools/make-iana-tld-pattern.py
*/
public static final String TOP_LEVEL_DOMAIN_STR =
"""
TLD_SUFFIX = '";'
URL_PREFIX = r"""
/**
* Regular expression to match all IANA top-level domains for WEB_URL.
* List accurate as of 2010/02/05. List taken from:
* http://data.iana.org/TLD/tlds-alpha-by-domain.txt
* This pattern is auto-generated by frameworks/base/common/tools/make-iana-tld-pattern.py
*/
public static final String TOP_LEVEL_DOMAIN_STR_FOR_WEB_URL =
"(?:"
"""
URL_SUFFIX = ';'
class Bucket:
def __init__(self, baseLetter):
self.base=baseLetter
self.words=[]
self.letters=[]
def dump(self, isWebUrl=False, isFirst=False, isLast=False):
if (len(self.words) == 0) and (len(self.letters) == 0):
return ''
self.words.sort()
self.letters.sort()
output = ' ';
if isFirst:
if isWebUrl:
output += '+ "'
else:
output += '"('
else:
output += '+ "|'
if len(self.words) != 0:
output += '('
if isWebUrl:
output += '?:'
firstWord = 1
for word in self.words:
if firstWord == 0:
output += '|'
firstWord = 0
for letter in word:
if letter == '-':
output += '\\\\' # escape the '-' character.
output += letter
if len(self.words) > 0 and len(self.letters) > 0:
output += '|'
if len(self.letters) == 1:
output += '%c%c' % (self.base, self.letters[0])
elif len(self.letters) > 0:
output += '%c[' % self.base
for letter in self.letters:
output += letter
output += ']'
if len(self.words) != 0:
output += ')'
if not isLast:
output += '"'
output += '\n'
return output;
def add(self, line):
length = len(line)
if line.startswith('#') or (length == 0):
return;
if length == 2:
self.letters.append(line[1:2])
else:
self.words.append(line)
def getBucket(buckets, line):
letter = line[0]
bucket = buckets.get(letter)
if bucket is None:
bucket = Bucket(letter)
buckets[letter] = bucket
return bucket
def makePattern(prefix, suffix, buckets, isWebUrl=False):
output = prefix
output += getBucket(buckets, 'a').dump(isFirst=True, isWebUrl=isWebUrl)
for letter in range(ord('b'), ord('z')):
output += getBucket(buckets, chr(letter)).dump(isWebUrl=isWebUrl)
output += getBucket(buckets, 'z').dump(isLast=True, isWebUrl=isWebUrl)
if isWebUrl:
output += '))"'
else:
output += ')'
output += suffix
print output
if __name__ == "__main__":
f = urlopen('http://data.iana.org/TLD/tlds-alpha-by-domain.txt')
domains = f.readlines()
f.close()
buckets = {}
for domain in domains:
domain = domain.lower()
if len(domain) > 0:
getBucket(buckets, domain[0]).add(domain.strip())
makePattern(TLD_PREFIX, TLD_SUFFIX, buckets, isWebUrl=False)
makePattern(URL_PREFIX, URL_SUFFIX, buckets, isWebUrl=True)
|
