summaryrefslogtreecommitdiff
path: root/docs/sphinxext/docscrape.py
blob: f374b3ddca25d38bc2b530fafbc8f4835b35ec93 (plain)
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
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
"""Extract reference documentation from the NumPy source tree.

"""

import inspect
import textwrap
import re
import pydoc
from StringIO import StringIO
from warnings import warn
4
class Reader(object):
    """A line-based string reader.

    """
    def __init__(self, data):
        """
        Parameters
        ----------
        data : str
           String with lines separated by '\n'.

        """
        if isinstance(data,list):
            self._str = data
        else:
            self._str = data.split('\n') # store string as list of lines

        self.reset()

    def __getitem__(self, n):
        return self._str[n]

    def reset(self):
        self._l = 0 # current line nr

    def read(self):
        if not self.eof():
            out = self[self._l]
            self._l += 1
            return out
        else:
            return ''

    def seek_next_non_empty_line(self):
        for l in self[self._l:]:
            if l.strip():
                break
            else:
                self._l += 1

    def eof(self):
        return self._l >= len(self._str)

    def read_to_condition(self, condition_func):
        start = self._l
        for line in self[start:]:
            if condition_func(line):
                return self[start:self._l]
            self._l += 1
            if self.eof():
                return self[start:self._l+1]
        return []

    def read_to_next_empty_line(self):
        self.seek_next_non_empty_line()
        def is_empty(line):
            return not line.strip()
        return self.read_to_condition(is_empty)

    def read_to_next_unindented_line(self):
        def is_unindented(line):
            return (line.strip() and (len(line.lstrip()) == len(line)))
        return self.read_to_condition(is_unindented)

    def peek(self,n=0):
        if self._l + n < len(self._str):
            return self[self._l + n]
        else:
            return ''

    def is_empty(self):
        return not ''.join(self._str).strip()


class NumpyDocString(object):
    def __init__(self,docstring):
        docstring = textwrap.dedent(docstring).split('\n')

        self._doc = Reader(docstring)
        self._parsed_data = {
            'Signature': '',
            'Summary': [''],
            'Extended Summary': [],
            'Parameters': [],
            'Returns': [],
            'Raises': [],
            'Warns': [],
            'Other Parameters': [],
            'Attributes': [],
            'Methods': [],
            'See Also': [],
            'Notes': [],
            'Warnings': [],
            'References': '',
            'Examples': '',
            'index': {}
            }

        self._parse()

    def __getitem__(self,key):
        return self._parsed_data[key]

    def __setitem__(self,key,val):
        if not self._parsed_data.has_key(key):
            warn("Unknown section %s" % key)
        else:
            self._parsed_data[key] = val

    def _is_at_section(self):
        self._doc.seek_next_non_empty_line()

        if self._doc.eof():
            return False

        l1 = self._doc.peek().strip()  # e.g. Parameters

        if l1.startswith('.. index::'):
            return True

        l2 = self._doc.peek(1).strip() #    ---------- or ==========
        return l2.startswith('-'*len(l1)) or l2.startswith('='*len(l1))

    def _strip(self,doc):
        i = 0
        j = 0
        for i,line in enumerate(doc):
            if line.strip(): break

        for j,line in enumerate(doc[::-1]):
            if line.strip(): break

        return doc[i:len(doc)-j]

    def _read_to_next_section(self):
        section = self._doc.read_to_next_empty_line()

        while not self._is_at_section() and not self._doc.eof():
            if not self._doc.peek(-1).strip(): # previous line was empty
                section += ['']

            section += self._doc.read_to_next_empty_line()

        return section

    def _read_sections(self):
        while not self._doc.eof():
            data = self._read_to_next_section()
            name = data[0].strip()

            if name.startswith('..'): # index section
                yield name, data[1:]
            elif len(data) < 2:
                yield StopIteration
            else:
                yield name, self._strip(data[2:])

    def _parse_param_list(self,content):
        r = Reader(content)
        params = []
        while not r.eof():
            header = r.read().strip()
            if ' : ' in header:
                arg_name, arg_type = header.split(' : ')[:2]
            else:
                arg_name, arg_type = header, ''

            desc = r.read_to_next_unindented_line()
            desc = dedent_lines(desc)

            params.append((arg_name,arg_type,desc))

        return params

    
    _name_rgx = re.compile(r"^\s*(:(?P<role>\w+):`(?P<name>[a-zA-Z0-9_.-]+)`|"
                           r" (?P<name2>[a-zA-Z0-9_.-]+))\s*", re.X)
    def _parse_see_also(self, content):
        """
        func_name : Descriptive text
            continued text
        another_func_name : Descriptive text
        func_name1, func_name2, :meth:`func_name`, func_name3

        """
        items = []

        def parse_item_name(text):
            """Match ':role:`name`' or 'name'"""
            m = self._name_rgx.match(text)
            if m:
                g = m.groups()
                if g[1] is None:
                    return g[3], None
                else:
                    return g[2], g[1]
            raise ValueError("%s is not a item name" % text)

        def push_item(name, rest):
            if not name:
                return
            name, role = parse_item_name(name)
            items.append((name, list(rest), role))
            del rest[:]

        current_func = None
        rest = []
        
        for line in content:
            if not line.strip(): continue

            m = self._name_rgx.match(line)
            if m and line[m.end():].strip().startswith(':'):
                push_item(current_func, rest)
                current_func, line = line[:m.end()], line[m.end():]
                rest = [line.split(':', 1)[1].strip()]
                if not rest[0]:
                    rest = []
            elif not line.startswith(' '):
                push_item(current_func, rest)
                current_func = None
                if ',' in line:
                    for func in line.split(','):
                        push_item(func, [])
                elif line.strip():
                    current_func = line
            elif current_func is not None:
                rest.append(line.strip())
        push_item(current_func, rest)
        return items

    def _parse_index(self, section, content):
        """
        .. index: default
           :refguide: something, else, and more

        """
        def strip_each_in(lst):
            return [s.strip() for s in lst]

        out = {}
        section = section.split('::')
        if len(section) > 1:
            out['default'] = strip_each_in(section[1].split(','))[0]
        for line in content:
            line = line.split(':')
            if len(line) > 2:
                out[line[1]] = strip_each_in(line[2].split(','))
        return out
    
    def _parse_summary(self):
        """Grab signature (if given) and summary"""
        if self._is_at_section():
            return

        summary = self._doc.read_to_next_empty_line()
        summary_str = " ".join([s.strip() for s in summary]).strip()
        if re.compile('^([\w., ]+=)?\s*[\w\.]+\(.*\)$').match(summary_str):
            self['Signature'] = summary_str
            if not self._is_at_section():
                self['Summary'] = self._doc.read_to_next_empty_line()
        else:
            self['Summary'] = summary

        if not self._is_at_section():
            self['Extended Summary'] = self._read_to_next_section()
    
    def _parse(self):
        self._doc.reset()
        self._parse_summary()

        for (section,content) in self._read_sections():
            if not section.startswith('..'):
                section = ' '.join([s.capitalize() for s in section.split(' ')])
            if section in ('Parameters', 'Attributes', 'Methods',
                           'Returns', 'Raises', 'Warns'):
                self[section] = self._parse_param_list(content)
            elif section.startswith('.. index::'):
                self['index'] = self._parse_index(section, content)
            elif section == 'See Also':
                self['See Also'] = self._parse_see_also(content)
            else:
                self[section] = content

    # string conversion routines

    def _str_header(self, name, symbol='-'):
        return [name, len(name)*symbol]

    def _str_indent(self, doc, indent=4):
        out = []
        for line in doc:
            out += [' '*indent + line]
        return out

    def _str_signature(self):
        if self['Signature']:
            return [self['Signature'].replace('*','\*')] + ['']
        else:
            return ['']

    def _str_summary(self):
        if self['Summary']:
            return self['Summary'] + ['']
        else:
            return []

    def _str_extended_summary(self):
        if self['Extended Summary']:
            return self['Extended Summary'] + ['']
        else:
            return []

    def _str_param_list(self, name):
        out = []
        if self[name]:
            out += self._str_header(name)
            for param,param_type,desc in self[name]:
                out += ['%s : %s' % (param, param_type)]
                out += self._str_indent(desc)
            out += ['']
        return out

    def _str_section(self, name):
        out = []
        if self[name]:
            out += self._str_header(name)
            out += self[name]
            out += ['']
        return out

    def _str_see_also(self, func_role):
        if not self['See Also']: return []
        out = []
        out += self._str_header("See Also")
        last_had_desc = True
        for func, desc, role in self['See Also']:
            if role:
                link = ':%s:`%s`' % (role, func)
            elif func_role:
                link = ':%s:`%s`' % (func_role, func)
            else:
                link = "`%s`_" % func
            if desc or last_had_desc:
                out += ['']
                out += [link]
            else:
                out[-1] += ", %s" % link
            if desc:
                out += self._str_indent([' '.join(desc)])
                last_had_desc = True
            else:
                last_had_desc = False
        out += ['']
        return out

    def _str_index(self):
        idx = self['index']
        out = []
        out += ['.. index:: %s' % idx.get('default','')]
        for section, references in idx.iteritems():
            if section == 'default':
                continue
            out += ['   :%s: %s' % (section, ', '.join(references))]
        return out

    def __str__(self, func_role=''):
        out = []
        out += self._str_signature()
        out += self._str_summary()
        out += self._str_extended_summary()
        for param_list in ('Parameters','Returns','Raises'):
            out += self._str_param_list(param_list)
        out += self._str_section('Warnings')
        out += self._str_see_also(func_role)
        for s in ('Notes','References','Examples'):
            out += self._str_section(s)
        out += self._str_index()
        return '\n'.join(out)


def indent(str,indent=4):
    indent_str = ' '*indent
    if str is None:
        return indent_str
    lines = str.split('\n')
    return '\n'.join(indent_str + l for l in lines)

def dedent_lines(lines):
    """Deindent a list of lines maximally"""
    return textwrap.dedent("\n".join(lines)).split("\n")

def header(text, style='-'):
    return text + '\n' + style*len(text) + '\n'


class FunctionDoc(NumpyDocString):
    def __init__(self, func, role='func', doc=None):
        self._f = func
        self._role = role # e.g. "func" or "meth"
        if doc is None:
            doc = inspect.getdoc(func) or ''
        try:
            NumpyDocString.__init__(self, doc)
        except ValueError, e:
            print '*'*78
            print "ERROR: '%s' while parsing `%s`" % (e, self._f)
            print '*'*78
            #print "Docstring follows:"
            #print doclines
            #print '='*78

        if not self['Signature']:
            func, func_name = self.get_func()
            try:
                # try to read signature
                argspec = inspect.getargspec(func)
                argspec = inspect.formatargspec(*argspec)
                argspec = argspec.replace('*','\*')
                signature = '%s%s' % (func_name, argspec)
            except TypeError, e:
                signature = '%s()' % func_name
            self['Signature'] = signature

    def get_func(self):
        func_name = getattr(self._f, '__name__', self.__class__.__name__)
        if inspect.isclass(self._f):
            func = getattr(self._f, '__call__', self._f.__init__)
        else:
            func = self._f
        return func, func_name
            
    def __str__(self):
        out = ''

        func, func_name = self.get_func()
        signature = self['Signature'].replace('*', '\*')

        roles = {'func': 'function',
                 'meth': 'method'}

        if self._role:
            if not roles.has_key(self._role):
                print "Warning: invalid role %s" % self._role
            out += '.. %s:: %s\n    \n\n' % (roles.get(self._role,''),
                                             func_name)

        out += super(FunctionDoc, self).__str__(func_role=self._role)
        return out


class ClassDoc(NumpyDocString):
    def __init__(self,cls,modulename='',func_doc=FunctionDoc,doc=None):
        if not inspect.isclass(cls):
            raise ValueError("Initialise using a class. Got %r" % cls)
        self._cls = cls

        if modulename and not modulename.endswith('.'):
            modulename += '.'
        self._mod = modulename
        self._name = cls.__name__
        self._func_doc = func_doc

        if doc is None:
            doc = pydoc.getdoc(cls)

        NumpyDocString.__init__(self, doc)

    @property
    def methods(self):
        return [name for name,func in inspect.getmembers(self._cls)
                if not name.startswith('_') and callable(func)]

    def __str__(self):
        out = ''
        out += super(ClassDoc, self).__str__()
        out += "\n\n"

        #for m in self.methods:
        #    print "Parsing `%s`" % m
        #    out += str(self._func_doc(getattr(self._cls,m), 'meth')) + '\n\n'
        #    out += '.. index::\n   single: %s; %s\n\n' % (self._name, m)

        return out