summaryrefslogtreecommitdiff
path: root/tools/indenter
blob: 4e17a15b464f23842666886a96aadcc19e262265 (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
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
#!/usr/bin/env python
# -*- encoding: utf-8
##    indenter.py - Top-level indenter for all files
##
##    Copyright ©2013 Ben Longbons <b.r.longbons@gmail.com>
##
##    This file is part of The Mana World (Athena server)
##
##    This program 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.
##
##    This program 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 this program.  If not, see <http://www.gnu.org/licenses/>.

# Settings.
class LexSettings:
    pad = 2
    indent = 4
    brace = True
    nested_indent = 0 # 4

# Code.
import subprocess
import sys

def round_up(i, a):
    m = i % a
    if m:
        i += (a - m)
    return i

class Table:
    ''' Aligned output
    '''
    def __init__(self):
        self.buf = []
        self.size = 0
    def put1(self, line):
        line = line.rstrip()
        self.buf.append((line, ''))
    def put2(self, left, right):
        left = left.rstrip()
        right = right.strip()
        self.buf.append((left, right))
        if right and len(left) > self.size:
            self.size = len(left)
    def flush(self):
        self.size += LexSettings.pad
        self.size = round_up(self.size, LexSettings.indent)
        for l, r in self.buf:
            if not r:
                sys.stdout.writelines([l, '\n'])
            else:
                need = self.size - len(l)
                sys.stdout.writelines([l, ' ' * need, r, '\n'])
        del self.buf[:]
        self.size = 0

def format_lex_or_yacc_definitions():
    'definitions section (mostly used for options actually)'
    table = Table()
    in_code = False
    code = bytearray()
    for line in sys.stdin:
        if line == '%%\n':
            break
        if line == '%{\n':
            in_code = True
            continue
        if in_code:
            if line == '%}\n':
                in_code = False
                continue
            code += line
            continue
        if not line.strip() or line != line.lstrip():
            # starts with whitespace or is an empty line ('\n')
            code += line
            continue
        if code.strip():
            if LexSettings.brace:
                table.put1('%{')
            for line2 in subprocess.Popen(['indent-cpp'], stdin=subprocess.PIPE, stdout=subprocess.PIPE).communicate(code)[0].strip().split('\n'):
                table.put1(LexSettings.nested_indent * ' ' + line2)
            if LexSettings.brace:
                table.put1('%}')
                table.put1('')
        elif code:
            table.put1('')
        code = bytearray()

        if line.startswith('%'):
            # %top is flex, %code and %union are bison
            union = line.startswith('%union')
            if union or line.startswith('%top') or line.startswith('%code'):
                # TODO fix stupidity when in strings or comments
                count = line.count('{')
                #code = bytearray()
                if union:
                    assert count <= 1
                    code += line[1:]
                else:
                    if count:
                        assert count == 1
                        code += line[line.find('{'):]
                        table.put1(line[:line.find('{')])
                    else:
                        table.put1(line.rstrip())
                assert line.count('}') == 0
                for line in sys.stdin:
                    count += line.count('{') - line.count('}')
                    code += line
                    assert count >= 0
                    if count == 0:
                        break
                if union:
                    first = True
                    for line2 in indent_cpp_slop(code):
                        if first:
                            line2 = '%' + line2
                            first = False
                        table.put1(line2)
                else:
                    for line2 in indent_cpp_slop(code):
                        table.put1(LexSettings.nested_indent * ' ' + line2)
                code = bytearray()
            else:
                table.put1(line)
        elif line[0].isalpha() or line[0] == '_':
            table.put2(*line.split(None, 1))
        else:
            table.put1(line)

    assert not in_code
    del code
    del in_code
    table.flush()
    sys.stdout.write('\n%%\n')

def format_lex_rules():
    'rule section'
    table = Table()
    for line in sys.stdin:
        if line == '%%\n':
            break
        if line.startswith('<') and not line.startswith('<<'):
            raise NotImplementedError('start conditions not yet supported')
        i = 0
        p = 0
        bs = False
        while True:
            if bs:
                bs = False
                i += 1
                continue
            if line[i] == '\\':
                bs = True
                i += 1
                continue
            if not p and line[i].isspace():
                break
            if line[i] == '"':
                i += 1
                while line[i] != '"':
                    if line[i] == '\\':
                        i += 1
                    i += 1
            elif line[i] == '[':
                i += 1
                if line[i] == '^':
                    i += 1
                while line[i] != ']':
                    i += 1
            elif line[i] == '(':
                p += 1
            elif line[i] == ')':
                assert p
                p -= 1
            i += 1
        del bs
        del p
        pattern = line[:i]
        rule = bytearray(line[i:])
        del i
        count = rule.count('{') - rule.count('}')
        while count:
            blah = next(sys.stdin)
            rule += blah
            count += blah.count('{') - blah.count('}')
        rules = indent_cpp_slop(rule)
        table.put2(pattern, rules[0])
        for line in rules[1:]:
            table.put1(line)

    table.flush()
    sys.stdout.write('%%\n')

def format_yacc_rules():
    '''
        tokens are any of:
        word
        word[namedref]
        'c'
        "str"
        { code }
        break before {
        break twice before a : or |
        break twice before and thrice after a ;
        put a softspace after everything except ;
    '''
    sys.stdout.write('\n')
    softspace = '' # NOT reset by new lines
    for line in sys.stdin:
        if line == '%%\n':
            break
        line = line.strip()
        while line:
            if line.startswith("'"):
                bs = False
                for i, c in enumerate(line):
                    if bs:
                        continue
                    bs = c == '\\'
                    if i and c == "'":
                        break
                else:
                    raise Exception('broken char')
                i += 1
                word = line[:i]
                line = line[i:].lstrip()
                sys.stdout.writelines([softspace, word])
                softspace = ' '
                continue
            if line.startswith('"'):
                for i, c in enumerate(line):
                    if bs:
                        continue
                    bs = c == '\\'
                    if i and c == '"':
                        break
                else:
                    raise Exception('broken string')
                i += 1
                word = line[:i]
                line = line[i:].lstrip()
                sys.stdout.writelines([softspace, word])
                softspace = ' '
                continue
            if line.startswith(':'):
                line = line[1:].lstrip()
                sys.stdout.write('\n\n:')
                softspace = ' '
                continue
            if line.startswith('{'):
                line += '\n'
                lines = bytearray()
                # TODO fix braces in comments and strings
                lo = 1
                behold = 1
                while behold:
                    i = line.find('}', lo)
                    if i == -1:
                        behold += line[lo:].count('{')
                        lines += line
                        line = next(sys.stdin)
                        lo = 0
                    else:
                        behold -= 1
                        i += 1
                        behold += line[lo:i].count('{')
                        lo = i
                lines += line[:lo]
                for line2 in indent_cpp_slop(lines):
                    sys.stdout.writelines(['\n', line2])
                line = line[lo:].strip()
                softspace = ' '
                continue
            if line.startswith(';'):
                line = line[1:].lstrip()
                sys.stdout.write('\n\n;\n\n\n')
                softspace = ''
                continue
            if line.startswith('|'):
                line = line[1:].lstrip()
                sys.stdout.write('\n\n|')
                softspace = ' '
                continue
            # screw comments
            word, _, line = line.partition(' ')
            line = line.lstrip()
            if word.endswith(':'):
                word = word[-1]
                line = ':' + line
            sys.stdout.writelines([softspace, word])
            softspace = ' '
            continue
        # while line
    # for line in stdin
    sys.stdout.write('%%\n')

def format_lex():
    '''
    A lex file is a series of sections.

    In the initial section:
        If it begins with whitespace, it is indented code
        It might be a /* comment */
        It might be a #line
        It might be a %s, %x, %pointer, %array, %option %[a-z][0-9].*
        It might be a %{ codeblock %}
        It might be a %top { codeblock }
        It might be a name and an expansion
        A %% switches to the second section

    In a comment:
        */ is the end

    In a codeblock:
        if it started with %{, %} ends it
        if it started with %top{, } ends it if it matches the nesting

    In section 2's header:
        there may be %{ %} sections, possibly nested
        there may also be indented code
        there may be unindented code if it's inside the %{ %}

    In section 2 proper:
        pattern         action
        <sc>pattern     action
        <sc>{
            pattern     action
        }
        a %% switches to section 3

    In section 3:
        everything is just C code
    '''

    format_lex_or_yacc_definitions()
    format_lex_rules()
    format_cc()

def format_yacc():
    ''' A yacc file is a series of sections.

    In the initial section:
        whitespace and comments are ignored.
        %someoption
        =
        |
        ;
        name
        name:
        int

        'char'
        "string"
        <*>
        <>
        <something>
        %{ prologue %}
        { braced code }
        [ bracketed identifier ]
        %% switch to section 2

    In the second section:
        is actually the same! wtf?
        But in practice:

        name:
            symbol 'c' "str" { code }
        |
            symbol 'c' "str" { code } /* in any order */
        ;
        any name may instead be name[namedref]
        code may additionally contain $$, $1, $namedref

    In section 3:
        everything is C code.
    '''
    format_lex_or_yacc_definitions()
    format_yacc_rules()
    format_cc()

def format_cc():
    tail = subprocess.Popen(['indent-cpp'], stdin=subprocess.PIPE, stdout=None)
    tail.stdin.writelines(sys.stdin)

def indent_cpp_slop(code):
    return subprocess.Popen(['indent-cpp'], stdin=subprocess.PIPE, stdout=subprocess.PIPE).communicate(code)[0].strip().split('\n')

def format_ii():
    format_passthrough()

def format_passthrough():
    for line in sys.stdin:
        sys.stdout.write(line)

exts = {
        '-lpp': format_lex,
        '-ypp': format_yacc,
        '-cpp': format_cc,
        '-ipp': format_ii,
}

if __name__ == '__main__':
    import sys
    if len(sys.argv) != 2:
        sys.exit('Usage: %s -ext < input.ext > output.ext')
    func = exts.get(sys.argv[1])
    if not func:
        sys.exit('Bad -ext')
    func()