Work at SourceForge, help us to make it a better place! We have an immediate need for a Support Technician in our San Francisco or Denver office.

Close

[82ddff]: plugins / exparse.py Maximize Restore History

Download this file

exparse.py    390 lines (345 with data), 12.9 kB

  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
"""Simple code to extract class & function docstrings from a module.
This code is used as an example in the library reference manual in the
section on using the parser module. Refer to the manual for a thorough
discussion of the operation of this code.
The code has been extended by Stephen Davies for the Synopsis project. It now
also recognises parameter names and values, and baseclasses. Names are now
returned in order also.
July 25, 2006
Adapted from Synopsis package, assumed GPL-compatible or at least PSF
licensed, given the content of the Synopsis README.quick.
"""
import parser
import symbol
import token
import re
line_end = ((token.NEWLINE, ''), (token.INDENT, ''), (token.DEDENT, ''))
def format(tree, depth=-1):
"""Format the given tree up to the given depth.
Numbers are replaced with their symbol or token names."""
if isinstance(tree, int):
try:
return symbol.sym_name[tree]
except KeyError:
try:
return token.tok_name[tree]
except KeyError:
return tree
if type(tree) != tuple:
return tree
if depth == 0: return '...'
ret = [format(tree[0])]
for branch in tree[1:]:
ret.append(format(branch, depth-1))
return tuple(ret)
def stringify(tree):
"""Convert the given tree to a string"""
if isinstance(tree, int): return ''
if not isinstance(tree, tuple):
return str(tree)
strs = []
for elem in tree:
strs.append(stringify(elem))
return ''.join(strs)
def get_docs(source):
return ModuleInfo(parser.suite(source).totuple(), '')
def parse(content):
stk = [get_docs(content)]
names_ = []
out = []
outt = []
docstring = {}
p = 0
lineno = 1
while stk:
cur = stk.pop()
if cur is None:
_ = outt.pop()
__ = names_.pop()
if len(outt) == 0:
out.append(_)
continue
elif isinstance(cur, list):
if len(cur) >= 1:
stk.append(cur)
stk.append(cur.pop())
continue
elif isinstance(cur, ModuleInfo):
x = ''
elif isinstance(cur, ClassInfo):
_name = cur.get_name()
x = 'class ' + _name
gbm = cur.get_base_names()
if gbm:
x += '(%s)'%(', '.join(gbm))
elif isinstance(cur, FunctionInfo):
_name = cur.get_name()
x = 'def %s(%s)'%(_name,
', '.join([(i, '%s=%s'%(i,j))[bool(j)]
for i,j in zip(cur.get_params(),
cur.get_param_defaults())]))
else:
print "huh?"
continue
if x:
z = 'def'
if isinstance(cur, ClassInfo):
z = 'class'
g = re.compile("(?:^|\s)%s\s+%s(?:[:\s\(\\\\]|$)"%(z, _name),
re.MULTILINE).search(content, p)
if g:
#we found the definition
h = g.group()
s = g.start()
s += len(h) - len(h.lstrip())
lineno += content.count('\n', p, s)
p = g.end()
y = (x, (_name.lower(), lineno, _name), len(outt)*4, [])
if len(outt):
outt[-1][-1].append(y)
doc = cur.get_docstring()
_ = '.'.join(names_)
if _:
_ += '.'
doc = ('%s%s\n%s'%(_, x.split(None, 1)[-1], doc)).rstrip()
docstring.setdefault(_name, []).append(doc)
if _name in ('__init__', '__new__') and outt:
docstring.setdefault(outt[-1][1][2], []).append(doc)
names_.append(_name)
outt.append(y)
stk.append(None)
names = [j for i,j in cur.get_names_and_info()]
names.reverse()
stk.append(names)
if outt:
out.append(outt[0])
return out, docstring
class SuiteInfoBase:
if 1:
_docstring = ''
_name = ''
def __init__(self, tree = None, env={}):
self._env = {} ; self._env.update(env)
self._names = []
## self._class_info = {}
## self._class_names = []
## self._function_info = {}
## self._function_names = []
if tree:
self._extract_info(tree)
def _extract_info(self, tree):
# extract docstring
if len(tree) == 2:
found, vars = match(DOCSTRING_STMT_PATTERN[1], tree[1])
else:
found, vars = match(DOCSTRING_STMT_PATTERN, tree[3])
if found:
self._docstring = eval(vars['docstring'])
# discover inner definitions
for node in tree[1:]:
found, vars = match(COMPOUND_STMT_PATTERN, node)
if found:
cstmt = vars['compound']
if cstmt[0] == symbol.funcdef:
name = cstmt[2][1]
self._names.append((name, FunctionInfo(cstmt, env=self._env)))
elif cstmt[0] == symbol.classdef:
name = cstmt[2][1]
self._names.append((name, ClassInfo(cstmt, env=self._env)))
#found, vars = match(IMPORT_STMT_PATTERN, node)
#we are going to ignore imports
def get_docstring(self):
return self._docstring
def get_names_and_info(self):
return self._names
def get_name(self):
return self._name
class FunctionInfo(SuiteInfoBase):
def __init__(self, tree = None, env={}):
self._name = tree[2][1]
SuiteInfoBase.__init__(self, tree and tree[-1] or None, env)
self._params = []
self._param_defaults = []
if tree[3][0] == symbol.parameters:
if tree[3][2][0] == symbol.varargslist:
args = list(tree[3][2][1:])
while args:
if args[0][0] == token.COMMA:
pass
elif args[0][0] == symbol.fpdef:
self._params.append(stringify(args[0]))
self._param_defaults.append('')
elif args[0][0] == token.EQUAL:
del args[0]
self._param_defaults[-1] = stringify(args[0])
elif args[0][0] == token.DOUBLESTAR:
del args[0]
self._params.append('**'+stringify(args[0]))
self._param_defaults.append('')
elif args[0][0] == token.STAR:
del args[0]
self._params.append('*'+stringify(args[0]))
self._param_defaults.append('')
else:
print "Unknown symbol:",args[0]
del args[0]
def get_params(self): return self._params
def get_param_defaults(self): return self._param_defaults
class ClassInfo(SuiteInfoBase):
def __init__(self, tree = None, env={}):
self._name = tree[2][1]
SuiteInfoBase.__init__(self, tree and tree[-1] or None, env)
self._bases = []
if tree[4][0] == symbol.testlist:
for test in tree[4][1:]:
found, vars = match(TEST_NAME_PATTERN, test)
if found and vars.has_key('power'):
power = vars['power']
if power[0] != symbol.power: continue
atom = power[1]
if atom[0] != symbol.atom: continue
if atom[1][0] != token.NAME: continue
name = [atom[1][1]]
for trailer in power[2:]:
if trailer[2][0] == token.NAME: name.append(trailer[2][1])
if self._env.has_key(name[0]):
name = self._env[name[0]] + name[1:]
self._bases.append(name)
#print "BASE:",name
else:
#print "BASE:",name[0]
self._bases.append(name[0])
else:
pass
def get_base_names(self):
return self._bases
class ModuleInfo(SuiteInfoBase):
def __init__(self, tree = None, name = "<string>"):
self._name = name
SuiteInfoBase.__init__(self, tree)
if tree:
found, vars = match(DOCSTRING_STMT_PATTERN, tree[1])
if found:
self._docstring = eval(vars["docstring"])
def match(pattern, data, vars=None):
"""Match `data' to `pattern', with variable extraction.
pattern
Pattern to match against, possibly containing variables.
data
Data to be checked and against which variables are extracted.
vars
Dictionary of variables which have already been found. If not
provided, an empty dictionary is created.
The `pattern' value may contain variables of the form ['varname'] which
are allowed to match anything. The value that is matched is returned as
part of a dictionary which maps 'varname' to the matched value. 'varname'
is not required to be a string object, but using strings makes patterns
and the code which uses them more readable.
This function returns two values: a boolean indicating whether a match
was found and a dictionary mapping variable names to their associated
values.
"""
if vars is None:
vars = {}
if type(pattern) is list: # 'variables' are ['varname']
vars[pattern[0]] = data
return 1, vars
if type(pattern) is not tuple:
return (pattern == data), vars
if len(data) != len(pattern):
return 0, vars
for pattern, data in map(None, pattern, data):
same, vars = match(pattern, data, vars)
if not same:
break
return same, vars
def dmatch(pattern, data, vars=None):
"""Debugging match """
if vars is None:
vars = {}
if type(pattern) is list: # 'variables' are ['varname']
vars[pattern[0]] = data
print "dmatch: pattern is list,",pattern[0],"=",data
return 1, vars
if type(pattern) is not tuple:
print "dmatch: pattern is not tuple, pattern =",format(pattern)," data =",format(data)
return (pattern == data), vars
if len(data) != len(pattern):
print "dmatch: bad length. data=",format(data,2)," pattern=",format(pattern,1)
return 0, vars
for pattern, data in map(None, pattern, data):
same, vars = dmatch(pattern, data, vars)
if not same:
print "dmatch: not same"
break
print "dmatch: same so far"
print "dmatch: returning",same,vars
return same, vars
# This pattern identifies compound statements, allowing them to be readily
# differentiated from simple statements.
#
COMPOUND_STMT_PATTERN = (
symbol.stmt,
(symbol.compound_stmt, ['compound'])
)
# This pattern will match a 'stmt' node which *might* represent a docstring;
# docstrings require that the statement which provides the docstring be the
# first statement in the class or function, which this pattern does not check.
#
DOCSTRING_STMT_PATTERN = (
symbol.stmt,
(symbol.simple_stmt,
(symbol.small_stmt,
(symbol.expr_stmt,
(symbol.testlist,
(symbol.test,
(symbol.and_test,
(symbol.not_test,
(symbol.comparison,
(symbol.expr,
(symbol.xor_expr,
(symbol.and_expr,
(symbol.shift_expr,
(symbol.arith_expr,
(symbol.term,
(symbol.factor,
(symbol.power,
(symbol.atom,
(token.STRING, ['docstring'])
)))))))))))))))),
(token.NEWLINE, '')
))
# This pattern will match a 'test' node which is a base class
#
TEST_NAME_PATTERN = (
symbol.test,
(symbol.and_test,
(symbol.not_test,
(symbol.comparison,
(symbol.expr,
(symbol.xor_expr,
(symbol.and_expr,
(symbol.shift_expr,
(symbol.arith_expr,
(symbol.term,
(symbol.factor,
['power']
))))))))))
)
# This pattern will match an import statement
# import_spec is either:
# NAME:import, dotted_name
# or:
# NAME:from, dotted_name, NAME:import, NAME [, COMMA, NAME]*
# hence you must process it manually (second form has variable length)
IMPORT_STMT_PATTERN = (
symbol.stmt, (
symbol.simple_stmt, (
symbol.small_stmt, ['import_spec']
), (
token.NEWLINE, ''
)
)
)
#
# end of file