File: parser.py

package info (click to toggle)
crmsh 5.0.0~rc2-1
  • links: PTS, VCS
  • area: main
  • in suites: sid
  • size: 7,792 kB
  • sloc: python: 50,329; sh: 1,207; makefile: 254; xml: 243; exp: 234; awk: 22
file content (332 lines) | stat: -rw-r--r-- 10,130 bytes parent folder | download | duplicates (2)
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
#!/usr/bin/env python3
import typing
import re
import io


class Token:
    def __init__(self, lineno: int, tpe: str, text: str):
        self.tpe = tpe
        self.lineno = lineno
        self.text = text

    def __str__(self):
        return f'Token(tpe={self.tpe}, text={self.text})'


class EmptyLineToken(Token):
    def __init__(self, lineno: int):
        super().__init__(lineno, 'emptyline', '')


class TextToken(Token):
    def __init__(self, lineno: int, indent: int, text: str):
        super().__init__(lineno, 'text', text)
        self.indent = indent


class LogToken(Token):
    def __init__(self, lineno: int, text: str):
        super().__init__(lineno, 'log', text)


class UsageToken(Token):
    def __init__(self, lineno: int, text: str):
        super().__init__(lineno, 'usage', text)


class OptionsToken(Token):
    def __init__(self, lineno: int, text: str):
        super().__init__(lineno, 'options', text)


class OptionToken(Token):
    def __init__(self, lineno: int, text: str):
        super().__init__(lineno, 'option', text)


def lexer(lines: typing.Iterator[str]):
    for lineno, line in enumerate(lines):
        line = line.rstrip()
        if not line:
            yield EmptyLineToken(lineno)
        elif re.match('(?:\033\\[\\d+m)?(?:INFO|ERROR)(?:\033\\[0m)?: ', line):
            pass
        elif re.match('usage: ', line):
            yield UsageToken(lineno, line)
        elif re.match('options:', line):
            yield OptionsToken(lineno, line)
        elif re.match('\\s+-', line):
            yield OptionToken(lineno, line)
        else:
            indent = re.search('\\S', line).start()
            yield TextToken(lineno, indent, line)


T = typing.TypeVar('T')


class LookAheadIterator(typing.Generic[T]):
    def __init__(self, it: typing.Iterator[T]):
        self._it = it
        self._lookahead_buffer = list()
        self._lookahead_index = -1

    def lookahead(self):
        if self._lookahead_index + 1 == len(self._lookahead_buffer):
            try:
                ret = next(self._it)
                self._lookahead_index += 1
                self._lookahead_buffer.append(ret)
                return ret
            except StopIteration:
                return None
        else:
            self._lookahead_index += 1
            return self._lookahead_buffer[self._lookahead_index]

    def consume(self):
        self._lookahead_buffer = self._lookahead_buffer[self._lookahead_index+1:]
        self._lookahead_index = -1

    def rollback(self):
        self._lookahead_index -= 1

    def reset(self):
        self._lookahead_index = -1


class SyntaxErrorException(Exception):
    pass


class Parser:
    def on_usage(self, text: str):
        print('<usage/>')

    def enter_description(self):
        print('<description>')

    def exit_description(self):
        print('</description>')

    def on_paragraph(self, text: str):
        print(f'<paragraph>{text}</paragraph>')

    def enter_options(self):
        print('<options>')

    def exit_options(self):
        print('</options>')

    def enter_option_group(self, name: str):
        print(f'<option_group name={name}>')

    def exit_option_group(self, name: str):
        print(f'</option_group name={name}>')

    def on_option(self, option: str, help: str):
        print(f'<option name={option}/>')

    def parse_help(self, tokens: LookAheadIterator[Token]):
        self.parse_usage(tokens)
        self.parse_description(tokens)
        self.parse_options(tokens)
        tokens.reset()

    class MatchFailure(Exception):
        pass

    def parse_usage(self, tokens: LookAheadIterator[Token]):
        token = tokens.lookahead()
        self.assert_token_tpe('usage', token)
        buf = io.StringIO()
        buf.write(token.text)
        while True:
            token = tokens.lookahead()
            if token is None:
                tokens.consume()
                self.on_usage(buf.getvalue())
            elif token.tpe == 'text':
                buf.write(' ')
                buf.write(token.text[token.indent:])
            elif token.tpe == 'option':
                buf.write(' ')
                buf.write(token.text.lstrip())
            else:
                self.assert_token_tpe('emptyline', token)
                tokens.rollback()
                self.parse_emptyline(tokens)
                self.on_usage(buf.getvalue())
                break

    def parse_description(self, tokens: LookAheadIterator[Token]):
        result = self.parse_paragraph(tokens)
        if result is not None:
            indent, paragraph = result
            self.enter_description()
            tokens.consume()
            self.on_paragraph(paragraph)
            while True:
                ret = self.parse_paragraph(tokens)
                if ret is None:
                    self.exit_description()
                    return
                indent, text = ret
                tokens.consume()
                self.on_paragraph(text)


    def parse_options(self, tokens: LookAheadIterator[Token]):
        token = tokens.lookahead()
        if token.tpe != 'options':
            return
        else:
            self.enter_options()
            self.parse_option_group(tokens)
            while self.parse_named_option_group(tokens):
                pass
            self.exit_options()

    def parse_option_group(self, tokens: LookAheadIterator[Token]):
        while True:
            ret = self.parse_option(tokens)
            if ret is None:
                break
            option, help = ret
            self.on_option(option, help)

    def parse_option(self, tokens: LookAheadIterator[Token]):
        token = tokens.lookahead()
        if token is not None and token.tpe == 'option':
            match = re.match(
                '\\s+((?:-[a-zA-Z]|--[-a-zA-Z0-9]+)(?:\\s[^, ]+)?(?:,\\s+--[-a-zA-Z0-9]+(?:\\s[^, ]+)?)?)\\s*',
                token.text,
            )
            if match is None:
                tokens.rollback()
                return None
            option = match.group(1)
            buf = io.StringIO()
            buf.write(token.text[match.end():])
            while True:
                token = tokens.lookahead()
                if token is None:
                    tokens.consume()
                    break
                elif token.tpe != 'text':
                    tokens.rollback()
                    break
                else:
                    tokens.consume()
                    if buf.tell() != 0:
                        buf.write(' ')
                    buf.write(token.text[token.indent:])
            return option, buf.getvalue()

    def parse_named_option_group(self, tokens: LookAheadIterator[Token]):
        token = tokens.lookahead()
        if token is None:
            tokens.rollback()
            return
        elif token.tpe == 'emptyline':
            tokens.rollback()
            self.parse_emptyline(tokens)
        if token.tpe == 'text' and token.indent == 0 and token.text[-1] == ':':
            group_name = token.text[:-1]
            description = list()
            while True:
                ret = self.parse_paragraph(tokens)
                if ret is None:
                    break
                indent, text = ret
                description.append(text)
            ret = self.parse_option(tokens)
            if ret is None:
                tokens.reset()
                return
            else:
                self.enter_option_group(group_name)
                for paragraph in description:
                    self.on_paragraph(paragraph)
                option, help = ret
                self.on_option(option, help)
                tokens.consume()
                while True:
                    ret = self.parse_option(tokens)
                    if ret is None:
                        break
                    option, help = ret
                    self.on_option(option, help)
                    tokens.consume()
                self.parse_emptyline(tokens)
                self.exit_option_group(group_name)
                tokens.consume()
            return True
        else:
            tokens.rollback()
            return False

    @classmethod
    def assert_token_tpe(cls, tpe: str, token: Token):
        if token.tpe != tpe:
            raise SyntaxErrorException(f'Expected: <{tpe}>. Actual: <{token.tpe}>')

    def parse_log(self, tokens: LookAheadIterator[Token]):
        # TODO: remove me
        while True:
            token = tokens.lookahead()
            if token.tpe == 'log':
                tokens.consume()
            else:
                return

    def parse_paragraph(self, tokens: LookAheadIterator[Token]):
        buf = io.StringIO()
        indent = -1
        while True:
            token = tokens.lookahead()
            if token is None:
                tokens.consume()
                break
            if token.tpe != 'text':
                tokens.rollback()
                break
            new_indent = token.indent
            if indent == -1:
                indent = new_indent
                buf.write(token.text[indent:])
            elif new_indent == indent:
                buf.write(' ')
                buf.write(token.text[indent:])
            else:
                tokens.rollback()
                break
        if indent == -1:
            return None
        else:
            token = tokens.lookahead()
            if token is not None:
                tokens.rollback()
                self.parse_emptyline(tokens)
            return indent, buf.getvalue()

    def parse_emptyline(self, tokens: LookAheadIterator[Token]):
        while True:
            token = tokens.lookahead()
            if token.tpe != 'emptyline':
                tokens.rollback()
                break


def main():
    import sys
    stdin = sys.stdin
    with open(3, buffering=1) as stdin:
        tokens = LookAheadIterator(lexer(stdin))
        Parser().parse_help(tokens)
        print('epilog starts at line {}'.format(tokens.lookahead().lineno))


if __name__ == '__main__':
    main()