summaryrefslogtreecommitdiffstats
path: root/md_tw.py
blob: 2b3f3571d1e81eac8e9197907cf8c54950e697a2 (plain) (blame)
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
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
# -*- coding: utf-8 -*-
#
#   Copyright © 2018 rsiddharth <s@ricketyspace.net>.
#
#    This file is part of markdown-textwrap.
#
#   markdown-textwrap is free software: you can redistribute it
#   and/or modify it under the terms of the GNU General Public License
#   as published by the Free Software Foundation, either version 3 of
#   the License, or (at your option) any later version.
#
#   markdown-textwrap 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 General Public License for more details.
#
#   You should have received a copy of the GNU General Public License
#   along with markdown-textwrap (see COPYING).  If not, see
#   <http://www.gnu.org/licenses/>.

import re
import textwrap

import mistune


class TWBlockLexer(mistune.BlockLexer):
    """Text Wrap Block lexer for block grammar."""

    def __init__(self, rules=None, **kwargs):
        super(TWBlockLexer, self).__init__(rules, **kwargs)

        # from mistune
        self._block_quote_leading_pattern = re.compile(r'^ *> ?', flags=re.M)
        self._key_pattern = re.compile(r'\s+')

    # from mistune
    def _keyify(self, key):
        key = mistune.escape(key.lower(), quote=True)
        return self._key_pattern.sub(' ', key)

    def parse_block_code(self, m):
        self.tokens.append({
            'type': 'code',
            'lang': None,
            'text': m.group(0),
        })

    def parse_fences(self, m):
        self.tokens.append({
            'type': 'code',
            'lang': None,
            'text': m.group(0),
        })

    def parse_heading(self, m):
        self.tokens.append({
            'type': 'heading',
            'level': len(m.group(1)),
            'text': m.group(0),
        })

    def parse_lheading(self, m):
        """Parse setext heading."""
        self.tokens.append({
            'type': 'heading',
            'level': 1 if m.group(2) == '=' else 2,
            'text': m.group(0),
        })

    def parse_hrule(self, m):
        self.tokens.append({
            'type': 'hrule',
            'text': m.group(0)
            })

    def _process_list_item(self, cap, bull):
        cap = self.rules.list_item.findall(cap)

        _next = False
        length = len(cap)

        for i in range(length):
            item = cap[i][0]

            # slurp and remove the bullet
            space = len(item)
            bullet = ''
            bm = self.rules.list_bullet.match(item)
            if bm:
                bullet = bm.group(0)

            item = self.rules.list_bullet.sub('', item)

            # outdent
            if '\n ' in item:
                space = space - len(item)
                pattern = re.compile(r'^ {1,%d}' % space, flags=re.M)
                item = pattern.sub('', item)

            # determine whether item is loose or not
            loose = _next
            if not loose and re.search(r'\n\n(?!\s*$)', item):
                loose = True

            rest = len(item)
            if i != length - 1 and rest:
                _next = item[rest-1] == '\n'
                if not loose:
                    loose = _next

            if loose:
                t = 'loose_item_start'
            else:
                t = 'list_item_start'

            self.tokens.append({
                'type': t,
                'text': bullet,
                'spaces': len(bullet)
                })

            # recurse
            self.parse(item, self.list_rules)

            self.tokens.append({
                'type': 'list_item_end',
                'spaces': len(bullet)
                })

    def parse_block_quote(self, m):
        # slurp and clean leading >
        quote = ''
        qm = self._block_quote_leading_pattern.match(m.group(0))
        if qm:
            quote = qm.group(0)

        cap = self._block_quote_leading_pattern.sub('', m.group(0))

        self.tokens.append({
            'type': 'block_quote_start',
            'text': quote,
            'spaces': len(quote)
            })
        self.parse(cap)
        self.tokens.append({
            'type': 'block_quote_end',
            'spaces': len(quote)
            })

    def parse_def_links(self, m):
        key = self._keyify(m.group(1))
        self.def_links[key] = {
            'link': m.group(2),
            'title': m.group(3),
        }
        self.tokens.append({
            'type': 'def_links',
            'text': m.group(0)
            })

    def parse_def_footnotes(self, m):
        key = self._keyify(m.group(1))
        if key in self.def_footnotes:
            # footnote is already defined
            return

        self.def_footnotes[key] = 0

        text = m.group(2)
        multiline = False
        spaces = 0
        if '\n' in text:
            multiline = True
            lines = text.split('\n')
            whitespace = None
            for line in lines[1:]:
                space = len(line) - len(line.lstrip())
                if space and (not whitespace or space < whitespace):
                    whitespace = space
            newlines = [lines[0]]
            for line in lines[1:]:
                newlines.append(line[whitespace:])
            text = '\n'.join(newlines)

            if whitespace:
                spaces = whitespace

        self.tokens.append({
            'type': 'footnote_start',
            'key': key,
            'multiline': multiline,
            'spaces': spaces
        })

        self.parse(text, self.footnote_rules)

        self.tokens.append({
            'type': 'footnote_end',
            'key': key,
            'spaces': spaces
        })

    def parse_block_html(self, m):
        self.tokens.append({
            'type': 'block_html',
            'text': m.group(0)
            })


class TWInlineLexer(mistune.InlineLexer):
    """Text Wrap Inline level lexer for inline gramars."""

    def __init__(self, renderer, rules=None, **kwargs):
        super(TWInlineLexer, self).__init__(renderer, rules, **kwargs)

    def output(self, text, rules=None):
        # Don't parse inline text.
        return text


class TWRenderer(mistune.Renderer):
    """Text Wrap Renderer."""

    def __init__(self, **kwargs):
        super(TWRenderer, self).__init__(**kwargs)

        # Initalize textwrap.TextWrapper class
        self.tw = textwrap.TextWrapper(
            width=kwargs.get('tw_width', 72)
        )

    def tw_get(self, attr):
        """Get attribute from the local textwrap.TextWrapper instance.
        """
        return getattr(self.tw, attr, None)


    def tw_set(self, **kwargs):
        """
        Set options for the local textwrap.TextWrapper instance.
        """
        # Recognized options.
        opts = [
            'width',
            'initial_indent',
            'subsequent_indent',
            'drop_whitespace'
        ]

        for opt, val in kwargs.items():
            if not opt in opts:
                continue

            # Set option
            setattr(self.tw, opt, val)


    def tw_fill(self, text, **kwargs):
        """Wrap text.
        """
        self.tw_set(**kwargs)
        return self.tw.fill(text)

    def block_code(self, code, lang=None):
        out = '{}'.format(code)
        out = textwrap.indent(out, self.tw_get('initial_indent'),
                              lambda line: True)
        return out

    def block_quote(self,  text):
        out = '{}'.format(text.rstrip('>\n'))
        return out

    def block_html(self, html):
        out = '{}'.format(html)
        out = textwrap.indent(out, self.tw_get('initial_indent'),
                              lambda line: True)
        return out

    def paragraph(self, text):
        out = self.tw_fill(text)
        out = '{}\n{}\n'.format(out, self.tw_get('initial_indent').strip())
        return out


    def list(self, body, ordered=True):
        out = '{}\n\n\n'.format(body.rstrip())
        return out

    def list_item(self, text):
        out = '{}\n'.format(text)
        return out


class TWMarkdown(mistune.Markdown):
    """Text Wrap Markdown parser.
    """

    def __init__(self, **kwargs):
        renderer = TWRenderer(**kwargs)

        super(TWMarkdown, self).__init__(
            renderer,
            TWInlineLexer,
            TWBlockLexer
        )

    def _clean_ts(self, lines):
        out = ''

        for line in lines.split('\n'):
            out += line.rstrip() + '\n'

        return out

    def parse(self, text):
        out = super(TWMarkdown, self).parse(text)

        # Remove trailing spaces from all lines.
        out = self._clean_ts(out)

        # Add newline at the end.
        return '{}\n'.format(out.strip('\n'))

    def _add_prefix(self, prefix, initial=True, subseq=True):
        p = self.renderer.tw_get('initial_indent') + prefix

        if initial:
            self.renderer.tw_set(initial_indent=p)
        if subseq:
            self.renderer.tw_set(subsequent_indent=p)

    def _remove_prefix(self, length, initial=True, subseq=True):
        p = self.renderer.tw_get('initial_indent')[:-length]

        if initial:
            self.renderer.tw_set(initial_indent=p)
        if subseq:
            self.renderer.tw_set(subsequent_indent=p)

    def output_block_quote(self):
        # Add prefix
        self._add_prefix('> ')

        # Render block quote
        rendered_bq = super(TWMarkdown, self).output_block_quote()

        # Remove prefix
        self._remove_prefix(len('> '))

        return rendered_bq

    def output_block_html(self):
        text = self.token['text']
        return self.renderer.block_html(text)

    def output_list_item(self):
        i_indent = False # initial indent
        s_indent = True # subsequent indent
        indent = ''.ljust(self.token['spaces'])

        def process():
            nonlocal i_indent

            txt = ''
            if self.token['type'] == 'text':
                txt = self.renderer.tw_fill(self.tok_text())
            else:
                txt = self.tok()

            if not i_indent:
                txt = txt.lstrip()

                # Set initial indent after processing first item
                i_indent = True
                self._add_prefix(indent, i_indent, s_indent)

            return txt

        # Add bullet
        body = self.renderer.tw_get('initial_indent') + self.token['text']

        # Set prefix
        prefix = self._add_prefix(indent, i_indent, s_indent)

        # Process list item
        while self.pop()['type'] != 'list_item_end':
            body += process()

        # Render list item
        rendered_li = self.renderer.list_item(body)

        # Remove prefix
        self._remove_prefix(len(indent), i_indent, s_indent)

        return rendered_li


def main():
    print('USAGE: md_tw 72 file.md file2.md [...]')