summaryrefslogtreecommitdiff
path: root/test/pathological_tests.py
blob: 76cc913e174ed39472e159028d24bcba05e6ce6f (plain)
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
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import re
import argparse
import sys
import platform
import itertools
import multiprocessing
import time
from cmark import CMark

TIMEOUT = 5

parser = argparse.ArgumentParser(description='Run cmark tests.')
parser.add_argument('--program', dest='program', nargs='?', default=None,
        help='program to test')
parser.add_argument('--library-dir', dest='library_dir', nargs='?',
        default=None, help='directory containing dynamic library')
args = parser.parse_args(sys.argv[1:])

allowed_failures = {"many references": True}

cmark = CMark(prog=args.program, library_dir=args.library_dir)

def hash_collisions():
    REFMAP_SIZE = 16
    COUNT = 50000

    def badhash(ref):
        h = 0
        for c in ref:
            a = (h << 6) & 0xFFFFFFFF
            b = (h << 16) & 0xFFFFFFFF
            h = ord(c) + a + b - h
            h = h & 0xFFFFFFFF

        return (h % REFMAP_SIZE) == 0

    keys = ("x%d" % i for i in itertools.count())
    collisions = itertools.islice((k for k in keys if badhash(k)), COUNT)
    bad_key = next(collisions)

    document = ''.join("[%s]: /url\n\n[%s]\n\n" % (key, bad_key) for key in collisions)

    return document, re.compile("(<p>\[%s\]</p>\n){%d}" % (bad_key, COUNT-1))


# list of pairs consisting of input and a regex that must match the output.
pathological = {
    # note - some pythons have limit of 65535 for {num-matches} in re.
    "nested strong emph":
                (("*a **a " * 65000) + "b" + (" a** a*" * 65000),
                 re.compile("(<em>a <strong>a ){65000}b( a</strong> a</em>){65000}")),
    "many emph closers with no openers":
                 (("a_ " * 65000),
                  re.compile("(a[_] ){64999}a_")),
    "many emph openers with no closers":
                 (("_a " * 65000),
                  re.compile("(_a ){64999}_a")),
    "many link closers with no openers":
                 (("a]" * 65000),
                  re.compile("(a\]){65000}")),
    "many link openers with no closers":
                 (("[a" * 65000),
                  re.compile("(\[a){65000}")),
    "mismatched openers and closers":
                 (("*a_ " * 50000),
                  re.compile("([*]a[_] ){49999}[*]a_")),
    "openers and closers multiple of 3":
                 (("a**b" + ("c* " * 50000)),
                  re.compile("a[*][*]b(c[*] ){49999}c[*]")),
    "link openers and emph closers":
                 (("[ a_" * 50000),
                  re.compile("(\[ a_){50000}")),
    "pattern [ (]( repeated":
                 (("[ (](" * 80000),
                  re.compile("(\[ \(\]\(){80000}")),
    "hard link/emph case":
                 ("**x [a*b**c*](d)",
                  re.compile("\\*\\*x <a href=\"d\">a<em>b\\*\\*c</em></a>")),
    "nested brackets":
                 (("[" * 50000) + "a" + ("]" * 50000),
                  re.compile("\[{50000}a\]{50000}")),
    "nested block quotes":
                 ((("> " * 50000) + "a"),
                  re.compile("(<blockquote>\n){50000}")),
    "deeply nested lists":
                 ("".join(map(lambda x: ("  " * x + "* a\n"), range(0,1000))),
                  re.compile("<ul>\n(<li>a\n<ul>\n){999}<li>a</li>\n</ul>\n(</li>\n</ul>\n){999}")),
    "U+0000 in input":
                 ("abc\u0000de\u0000",
                  re.compile("abc\ufffd?de\ufffd?")),
    "backticks":
                 ("".join(map(lambda x: ("e" + "`" * x), range(1,5000))),
                  re.compile("^<p>[e`]*</p>\n$")),
    "unclosed links A":
                 ("[a](<b" * 30000,
                  re.compile("(\[a\]\(&lt;b){30000}")),
    "unclosed links B":
                 ("[a](b" * 30000,
                  re.compile("(\[a\]\(b){30000}")),
    "reference collisions": hash_collisions()
#    "many references":
#                 ("".join(map(lambda x: ("[" + str(x) + "]: u\n"), range(1,5000 * 16))) + "[0] " * 5000,
#                  re.compile("(\[0\] ){4999}"))
    }

whitespace_re = re.compile('/s+/')

results = {'passed': [], 'errored': [], 'failed': [], 'ignored': []}

def run_pathological_test(description, results):
    (inp, regex) = pathological[description]
    [rc, actual, err] = cmark.to_html(inp)
    extra = ""
    if rc != 0:
        print(description, '[ERRORED (return code %d)]' %rc)
        print(err)
        if allowed_failures[description]:
            results['ignored'].append(description)
        else:
            results['errored'].append(description)
    elif regex.search(actual):
        print(description, '[PASSED]')
        results['passed'].append(description)
    else:
        print(description, '[FAILED]')
        print(repr(actual))
        if allowed_failures[description]:
            results['ignored'].append(description)
        else:
            results['failed'].append(description)

def run_tests():
    print("Testing pathological cases:")
    for description in pathological:
        p = multiprocessing.Process(target=run_pathological_test,
                  args=(description, results,))
        p.start()
        # wait TIMEOUT seconds or until it finishes
        p.join(TIMEOUT)
        # kill it if still active
        if p.is_alive():
            print(description, '[TIMEOUT]')
            if allowed_failures[description]:
                results['ignored'].append(description)
            else:
                results['errored'].append(description)
            p.terminate()
            p.join()

    passed  = len(results['passed'])
    failed  = len(results['failed'])
    errored = len(results['errored'])
    ignored = len(results['ignored'])

    print("%d passed, %d failed, %d errored" % (passed, failed, errored))
    if ignored > 0:
        print("Ignoring these allowed failures:")
        for x in results['ignored']:
            print(x)
    if failed == 0 and errored == 0:
        exit(0)
    else:
        exit(1)

if __name__ == "__main__":
    run_tests()