summaryrefslogtreecommitdiff
path: root/tests/test_html_formatter.py
blob: 83b08e1f60a1a5f45d57c153b67e66c0199eeef3 (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
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
# -*- coding: utf-8 -*-
"""
    Pygments HTML formatter tests
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

    :copyright: Copyright 2006-2019 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import io
import os
import re
import tempfile
from os import path
from io import StringIO

from pytest import raises

from pygments.lexers import PythonLexer
from pygments.formatters import HtmlFormatter, NullFormatter
from pygments.formatters.html import escape_html

TESTDIR = path.dirname(path.abspath(__file__))
TESTFILE = path.join(TESTDIR, 'test_html_formatter.py')

with io.open(TESTFILE, encoding='utf-8') as fp:
    tokensource = list(PythonLexer().get_tokens(fp.read()))


def test_correct_output():
    hfmt = HtmlFormatter(nowrap=True)
    houtfile = StringIO()
    hfmt.format(tokensource, houtfile)

    nfmt = NullFormatter()
    noutfile = StringIO()
    nfmt.format(tokensource, noutfile)

    stripped_html = re.sub('<.*?>', '', houtfile.getvalue())
    escaped_text = escape_html(noutfile.getvalue())
    assert stripped_html == escaped_text


def test_external_css():
    # test correct behavior
    # CSS should be in /tmp directory
    fmt1 = HtmlFormatter(full=True, cssfile='fmt1.css', outencoding='utf-8')
    # CSS should be in TESTDIR (TESTDIR is absolute)
    fmt2 = HtmlFormatter(full=True, cssfile=path.join(TESTDIR, 'fmt2.css'),
                         outencoding='utf-8')
    tfile = tempfile.NamedTemporaryFile(suffix='.html')
    fmt1.format(tokensource, tfile)
    try:
        fmt2.format(tokensource, tfile)
        assert path.isfile(path.join(TESTDIR, 'fmt2.css'))
    except IOError:
        # test directory not writable
        pass
    tfile.close()

    assert path.isfile(path.join(path.dirname(tfile.name), 'fmt1.css'))
    os.unlink(path.join(path.dirname(tfile.name), 'fmt1.css'))
    try:
        os.unlink(path.join(TESTDIR, 'fmt2.css'))
    except OSError:
        pass


def test_all_options():
    def check(optdict):
        outfile = StringIO()
        fmt = HtmlFormatter(**optdict)
        fmt.format(tokensource, outfile)

    for optdict in [
        dict(nowrap=True),
        dict(linenos=True, full=True),
        dict(linenos=True, linespans='L'),
        dict(hl_lines=[1, 5, 10, 'xxx']),
        dict(hl_lines=[1, 5, 10], noclasses=True),
    ]:
        check(optdict)

    for linenos in [False, 'table', 'inline']:
        for noclasses in [False, True]:
            for linenospecial in [0, 5]:
                for anchorlinenos in [False, True]:
                    optdict = dict(
                        linenos=linenos,
                        noclasses=noclasses,
                        linenospecial=linenospecial,
                        anchorlinenos=anchorlinenos,
                    )
                    check(optdict)


def test_linenos():
    optdict = dict(linenos=True)
    outfile = StringIO()
    fmt = HtmlFormatter(**optdict)
    fmt.format(tokensource, outfile)
    html = outfile.getvalue()
    assert re.search(r"<pre>\s+1\s+2\s+3", html)


def test_linenos_with_startnum():
    optdict = dict(linenos=True, linenostart=5)
    outfile = StringIO()
    fmt = HtmlFormatter(**optdict)
    fmt.format(tokensource, outfile)
    html = outfile.getvalue()
    assert re.search(r"<pre>\s+5\s+6\s+7", html)


def test_lineanchors():
    optdict = dict(lineanchors="foo")
    outfile = StringIO()
    fmt = HtmlFormatter(**optdict)
    fmt.format(tokensource, outfile)
    html = outfile.getvalue()
    assert re.search("<pre><span></span><a name=\"foo-1\">", html)


def test_lineanchors_with_startnum():
    optdict = dict(lineanchors="foo", linenostart=5)
    outfile = StringIO()
    fmt = HtmlFormatter(**optdict)
    fmt.format(tokensource, outfile)
    html = outfile.getvalue()
    assert re.search("<pre><span></span><a name=\"foo-5\">", html)


def test_valid_output():
    # test all available wrappers
    fmt = HtmlFormatter(full=True, linenos=True, noclasses=True,
                        outencoding='utf-8')

    handle, pathname = tempfile.mkstemp('.html')
    with os.fdopen(handle, 'w+b') as tfile:
        fmt.format(tokensource, tfile)
    catname = os.path.join(TESTDIR, 'dtds', 'HTML4.soc')
    try:
        import subprocess
        po = subprocess.Popen(['nsgmls', '-s', '-c', catname, pathname],
                              stdout=subprocess.PIPE)
        ret = po.wait()
        output = po.stdout.read()
        po.stdout.close()
    except OSError:
        # nsgmls not available
        pass
    else:
        if ret:
            print(output)
        assert not ret, 'nsgmls run reported errors'

    os.unlink(pathname)


def test_get_style_defs():
    fmt = HtmlFormatter()
    sd = fmt.get_style_defs()
    assert sd.startswith('.')

    fmt = HtmlFormatter(cssclass='foo')
    sd = fmt.get_style_defs()
    assert sd.startswith('.foo')
    sd = fmt.get_style_defs('.bar')
    assert sd.startswith('.bar')
    sd = fmt.get_style_defs(['.bar', '.baz'])
    fl = sd.splitlines()[0]
    assert '.bar' in fl and '.baz' in fl


def test_unicode_options():
    fmt = HtmlFormatter(title=u'Föö',
                        cssclass=u'bär',
                        cssstyles=u'div:before { content: \'bäz\' }',
                        encoding='utf-8')
    handle, pathname = tempfile.mkstemp('.html')
    with os.fdopen(handle, 'w+b') as tfile:
        fmt.format(tokensource, tfile)


def test_ctags():
    try:
        import ctags
    except ImportError:
        # we can't check without the ctags module, but at least check the exception
        assert raises(RuntimeError, HtmlFormatter, tagsfile='support/tags')
    else:
        # this tagfile says that test_ctags() is on line 165, even if it isn't
        # anymore in the actual source
        fmt = HtmlFormatter(tagsfile='support/tags', lineanchors='L',
                            tagurlformat='%(fname)s%(fext)s')
        outfile = StringIO()
        fmt.format(tokensource, outfile)
        assert '<a href="test_html_formatter.py#L-165">test_ctags</a>' \
            in outfile.getvalue()


def test_filename():
    optdict = dict(filename="test.py")
    outfile = StringIO()
    fmt = HtmlFormatter(**optdict)
    fmt.format(tokensource, outfile)
    html = outfile.getvalue()
    assert re.search("<span class=\"filename\">test.py</span><pre>", html)