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
|
#!/usr/bin/env python
# -*- encoding: utf-8
## indent - Top-level indenter for lex 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/>.
'''
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
'''
# Settings.
pad = 2
indent = 4
brace = True
# Code.
import subprocess
import sys
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 += pad
if self.size % indent:
self.size += indent - self.size % 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
table = Table()
# definitions section (mostly used for options actually)
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 brace:
table.put1('%{')
for line2 in subprocess.Popen(['indent-cpp'], stdin=subprocess.PIPE, stdout=subprocess.PIPE).communicate(code)[0].strip().split('\n'):
# this looks bad actually
table.put1(0 * indent * ' ' + line2)
if brace:
table.put1('%}')
table.put1('')
code = bytearray()
elif code:
table.put1('')
if line.startswith('%'):
if line.startswith('%top'):
raise NotImplementedError('top block not yet supported')
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')
# rule section
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 = line[i:].strip()
del i
sys.stdout.write(line)
sys.stdout.write('%%\n')
# 3rd section is just copied verbatim ... IF it exists
tail = subprocess.Popen(['indent-cpp'], stdin=subprocess.PIPE, stdout=None)
tail.stdin.writelines(sys.stdin)
|
