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
|
#!/usr/bin/env python
"""Generate the errorcodes module starting from PostgreSQL documentation.
The script can be run at a new PostgreSQL release to refresh the module.
"""
# Copyright (C) 2010 Daniele Varrazzo <daniele.varrazzo@gmail.com>
#
# psycopg2 is free software: you can redistribute it and/or modify it
# under the terms of the GNU Lesser General Public License as published
# by the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# psycopg2 is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public
# License for more details.
import sys
import urllib2
from collections import defaultdict
from BeautifulSoup import BeautifulSoup as BS
def main():
if len(sys.argv) != 2:
print >>sys.stderr, "usage: %s /path/to/errorcodes.py" % sys.argv[0]
return 2
filename = sys.argv[1]
file_start = read_base_file(filename)
classes, errors = fetch_errors(
['8.1', '8.2', '8.3', '8.4', '9.0', '9.1', '9.2'])
f = open(filename, "w")
for line in file_start:
print >>f, line
for line in generate_module_data(classes, errors):
print >>f, line
def read_base_file(filename):
rv = []
for line in open(filename):
rv.append(line.rstrip("\n"))
if line.startswith("# autogenerated"):
return rv
raise ValueError("can't find the separator. Is this the right file?")
def parse_errors(url):
page = BS(urllib2.urlopen(url))
table = page('table')[1]('tbody')[0]
classes = {}
errors = defaultdict(dict)
for tr in table('tr'):
if tr.td.get('colspan'): # it's a class
label = ' '.join(' '.join(tr(text=True)).split()) \
.replace(u'\u2014', '-').encode('ascii')
assert label.startswith('Class')
class_ = label.split()[1]
assert len(class_) == 2
classes[class_] = label
else: # it's an error
errcode = tr.tt.string.encode("ascii")
assert len(errcode) == 5
tds = tr('td')
if len(tds) == 3:
errlabel = '_'.join(tds[1].string.split()).encode('ascii')
# double check the columns are equal
cond_name = tds[2].string.strip().upper().encode("ascii")
assert errlabel == cond_name, tr
elif len(tds) == 2:
# found in PG 9.1 docs
errlabel = tds[1].tt.string.upper().encode("ascii")
else:
assert False, tr
errors[class_][errcode] = errlabel
return classes, errors
errors_url="http://www.postgresql.org/docs/%s/static/errcodes-appendix.html"
def fetch_errors(versions):
classes = {}
errors = defaultdict(dict)
for version in versions:
c1, e1 = parse_errors(errors_url % version)
classes.update(c1)
for c, cerrs in e1.iteritems():
errors[c].update(cerrs)
return classes, errors
def generate_module_data(classes, errors):
yield ""
yield "# Error classes"
for clscode, clslabel in sorted(classes.items()):
err = clslabel.split(" - ")[1].split("(")[0] \
.strip().replace(" ", "_").replace('/', "_").upper()
yield "CLASS_%s = %r" % (err, clscode)
for clscode, clslabel in sorted(classes.items()):
yield ""
yield "# %s" % clslabel
for errcode, errlabel in sorted(errors[clscode].items()):
yield "%s = %r" % (errlabel, errcode)
if __name__ == '__main__':
sys.exit(main())
|
