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
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
|
# We attempt to parse C extension files. Basically we look for
# the standard patterns that you find in extensions: <tt>rb_define_class,
# rb_define_method</tt> and so on. We also try to find the corresponding
# C source for the methods and extract comments, but if we fail
# we don't worry too much.
#
# The comments associated with a Ruby method are extracted from the C
# comment block associated with the routine that _implements_ that
# method, that is to say the method whose name is given in the
# <tt>rb_define_method</tt> call. For example, you might write:
#
# /*
# * Returns a new array that is a one-dimensional flattening of this
# * array (recursively). That is, for every element that is an array,
# * extract its elements into the new array.
# *
# * s = [ 1, 2, 3 ] #=> [1, 2, 3]
# * t = [ 4, 5, 6, [7, 8] ] #=> [4, 5, 6, [7, 8]]
# * a = [ s, t, 9, 10 ] #=> [[1, 2, 3], [4, 5, 6, [7, 8]], 9, 10]
# * a.flatten #=> [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
# */
# static VALUE
# rb_ary_flatten(ary)
# VALUE ary;
# {
# ary = rb_obj_dup(ary);
# rb_ary_flatten_bang(ary);
# return ary;
# }
#
# ...
#
# void
# Init_Array()
# {
# ...
# rb_define_method(rb_cArray, "flatten", rb_ary_flatten, 0);
#
# Here RDoc will determine from the rb_define_method line that there's a
# method called "flatten" in class Array, and will look for the implementation
# in the method rb_ary_flatten. It will then use the comment from that
# method in the HTML output. This method must be in the same source file
# as the rb_define_method.
#
# C classes can be diagramed (see /tc/dl/ruby/ruby/error.c), and RDoc
# integrates C and Ruby source into one tree
#
# The comment blocks may include special direcives:
#
# [Document-class: <i>name</i>]
# This comment block is documentation for the given class. Use this
# when the <tt>Init_xxx</tt> method is not named after the class.
#
# [Document-method: <i>name</i>]
# This comment documents the named method. Use when RDoc cannot outomatically
# find the method from it's declaration
#
# [call-seq: <i>text up to an empty line</i>]
# Because C source doesn't give descripive names to Ruby-level parameters,
# you need to document the calling sequence explicitly
#
# In additon, RDoc assumes by default that the C method implementing a
# Ruby function is in the same source file as the rb_define_method call.
# If this isn't the case, add the comment
#
# rb_define_method(....); // in: filename
#
# As an example, we might have an extension that defines multiple classes
# in its Init_xxx method. We could document them using
#
#
# /*
# * Document-class: MyClass
# *
# * Encapsulate the writing and reading of the configuration
# * file. ...
# */
#
# /*
# * Document-method: read_value
# *
# * call-seq:
# * cfg.read_value(key) -> value
# * cfg.read_value(key} { |key| } -> value
# *
# * Return the value corresponding to +key+ from the configuration.
# * In the second form, if the key isn't found, invoke the
# * block and return its value.
# */
#
# Classes and modules built in to the interpreter. We need
# these to define superclasses of user objects
require "rdoc/code_objects"
require "rdoc/parsers/parserfactory"
require "rdoc/options"
require "rdoc/rdoc"
module RDoc
KNOWN_CLASSES = {
"rb_cObject" => "Object",
"rb_cArray" => "Array",
"rb_cBignum" => "Bignum",
"rb_cClass" => "Class",
"rb_cDir" => "Dir",
"rb_cData" => "Data",
"rb_cFalseClass" => "FalseClass",
"rb_cFile" => "File",
"rb_cFixnum" => "Fixnum",
"rb_cFloat" => "Float",
"rb_cHash" => "Hash",
"rb_cInteger" => "Integer",
"rb_cIO" => "IO",
"rb_cModule" => "Module",
"rb_cNilClass" => "NilClass",
"rb_cNumeric" => "Numeric",
"rb_cProc" => "Proc",
"rb_cRange" => "Range",
"rb_cRegexp" => "Regexp",
"rb_cString" => "String",
"rb_cSymbol" => "Symbol",
"rb_cThread" => "Thread",
"rb_cTime" => "Time",
"rb_cTrueClass" => "TrueClass",
"rb_cStruct" => "Struct",
"rb_eException" => "Exception",
"rb_eStandardError" => "StandardError",
"rb_eSystemExit" => "SystemExit",
"rb_eInterrupt" => "Interrupt",
"rb_eSignal" => "Signal",
"rb_eFatal" => "Fatal",
"rb_eArgError" => "ArgError",
"rb_eEOFError" => "EOFError",
"rb_eIndexError" => "IndexError",
"rb_eRangeError" => "RangeError",
"rb_eIOError" => "IOError",
"rb_eRuntimeError" => "RuntimeError",
"rb_eSecurityError" => "SecurityError",
"rb_eSystemCallError" => "SystemCallError",
"rb_eTypeError" => "TypeError",
"rb_eZeroDivError" => "ZeroDivError",
"rb_eNotImpError" => "NotImpError",
"rb_eNoMemError" => "NoMemError",
"rb_eFloatDomainError" => "FloatDomainError",
"rb_eScriptError" => "ScriptError",
"rb_eNameError" => "NameError",
"rb_eSyntaxError" => "SyntaxError",
"rb_eLoadError" => "LoadError",
"rb_mKernel" => "Kernel",
"rb_mComparable" => "Comparable",
"rb_mEnumerable" => "Enumerable",
"rb_mPrecision" => "Precision",
"rb_mErrno" => "Errno",
"rb_mFileTest" => "FileTest",
"rb_mGC" => "GC",
"rb_mMath" => "Math",
"rb_mProcess" => "Process"
}
# See rdoc/c_parse.rb
class C_Parser
attr_accessor :progress
extend ParserFactory
parse_files_matching(/\.(c|cc|cpp|CC)$/)
@@enclosure_classes = {}
@@known_bodies = {}
# prepare to parse a C file
def initialize(top_level, file_name, body, options, stats)
@known_classes = KNOWN_CLASSES.dup
@body = handle_tab_width(handle_ifdefs_in(body))
@options = options
@stats = stats
@top_level = top_level
@classes = Hash.new
@file_dir = File.dirname(file_name)
@progress = $stderr unless options.quiet
end
# Extract the classes/modules and methods from a C file
# and return the corresponding top-level object
def scan
remove_commented_out_lines
do_classes
do_constants
do_methods
do_includes
do_aliases
@top_level
end
#######
private
#######
def progress(char)
unless @options.quiet
@progress.print(char)
@progress.flush
end
end
def warn(msg)
$stderr.puts
$stderr.puts msg
$stderr.flush
end
def remove_private_comments(comment)
comment.gsub!(/\/?\*--(.*?)\/?\*\+\+/m, '')
comment.sub!(/\/?\*--.*/m, '')
end
# remove lines that are commented out that might otherwise get
# picked up when scanning for classes and methods
def remove_commented_out_lines
@body.gsub!(%r{//.*rb_define_}, '//')
end
def handle_class_module(var_name, class_mod, class_name, parent, in_module)
progress(class_mod[0, 1])
parent_name = @known_classes[parent] || parent
if in_module
enclosure = @classes[in_module] || @@enclosure_classes[in_module]
unless enclosure
if enclosure = @known_classes[in_module]
handle_class_module(in_module, (/^rb_m/ =~ in_module ? "module" : "class"),
enclosure, nil, nil)
enclosure = @classes[in_module]
end
end
unless enclosure
warn("Enclosing class/module '#{in_module}' for " +
"#{class_mod} #{class_name} not known")
return
end
else
enclosure = @top_level
end
if class_mod == "class"
cm = enclosure.add_class(NormalClass, class_name, parent_name)
@stats.num_classes += 1
else
cm = enclosure.add_module(NormalModule, class_name)
@stats.num_modules += 1
end
cm.record_location(enclosure.toplevel)
find_class_comment(cm.full_name, cm)
@classes[var_name] = cm
@@enclosure_classes[var_name] = cm
@known_classes[var_name] = cm.full_name
end
############################################################
def find_class_comment(class_name, class_meth)
comment = nil
if @body =~ %r{((?>/\*.*?\*/\s+))
(static\s+)?void\s+Init_#{class_name}\s*(?:_\(\s*)?\(\s*(?:void\s*)\)}xmi
comment = $1
elsif @body =~ %r{Document-(class|module):\s#{class_name}\s*?\n((?>.*?\*/))}m
comment = $2
end
class_meth.comment = mangle_comment(comment) if comment
end
############################################################
def do_classes
@body.scan(/(\w+)\s* = \s*rb_define_module\s*\(\s*"(\w+)"\s*\)/mx) do
|var_name, class_name|
handle_class_module(var_name, "module", class_name, nil, nil)
end
# The '.' lets us handle SWIG-generated files
@body.scan(/([\w\.]+)\s* = \s*rb_define_class\s*
\(
\s*"(\w+)",
\s*(\w+)\s*
\)/mx) do
|var_name, class_name, parent|
handle_class_module(var_name, "class", class_name, parent, nil)
end
@body.scan(/(\w+)\s*=\s*boot_defclass\s*\(\s*"(\w+?)",\s*(\w+?)\s*\)/) do
|var_name, class_name, parent|
parent = nil if parent == "0"
handle_class_module(var_name, "class", class_name, parent, nil)
end
@body.scan(/(\w+)\s* = \s*rb_define_module_under\s*
\(
\s*(\w+),
\s*"(\w+)"
\s*\)/mx) do
|var_name, in_module, class_name|
handle_class_module(var_name, "module", class_name, nil, in_module)
end
@body.scan(/([\w\.]+)\s* = \s*rb_define_class_under\s*
\(
\s*(\w+),
\s*"(\w+)",
\s*(\w+)\s*
\s*\)/mx) do
|var_name, in_module, class_name, parent|
handle_class_module(var_name, "class", class_name, parent, in_module)
end
end
###########################################################
def do_constants
@body.scan(%r{\Wrb_define_
(
variable |
readonly_variable |
const |
global_const |
)
\s*\(
(?:\s*(\w+),)?
\s*"(\w+)",
\s*(.*?)\s*\)\s*;
}xm) do
|type, var_name, const_name, definition|
var_name = "rb_cObject" if !var_name or var_name == "rb_mKernel"
handle_constants(type, var_name, const_name, definition)
end
end
############################################################
def do_methods
@body.scan(%r{rb_define_
(
singleton_method |
method |
module_function |
private_method
)
\s*\(\s*([\w\.]+),
\s*"([^"]+)",
\s*(?:RUBY_METHOD_FUNC\(|VALUEFUNC\()?(\w+)\)?,
\s*(-?\w+)\s*\)
(?:;\s*/[*/]\s+in\s+(\w+?\.[cy]))?
}xm) do
|type, var_name, meth_name, meth_body, param_count, source_file|
#"
# Ignore top-object and weird struct.c dynamic stuff
next if var_name == "ruby_top_self"
next if var_name == "nstr"
next if var_name == "envtbl"
next if var_name == "argf" # it'd be nice to handle this one
var_name = "rb_cObject" if var_name == "rb_mKernel"
handle_method(type, var_name, meth_name,
meth_body, param_count, source_file)
end
@body.scan(%r{rb_define_attr\(
\s*([\w\.]+),
\s*"([^"]+)",
\s*(\d+),
\s*(\d+)\s*\);
}xm) do #"
|var_name, attr_name, attr_reader, attr_writer|
#var_name = "rb_cObject" if var_name == "rb_mKernel"
handle_attr(var_name, attr_name,
attr_reader.to_i != 0,
attr_writer.to_i != 0)
end
@body.scan(%r{rb_define_global_function\s*\(
\s*"([^"]+)",
\s*(?:RUBY_METHOD_FUNC\(|VALUEFUNC\()?(\w+)\)?,
\s*(-?\w+)\s*\)
(?:;\s*/[*/]\s+in\s+(\w+?\.[cy]))?
}xm) do #"
|meth_name, meth_body, param_count, source_file|
handle_method("method", "rb_mKernel", meth_name,
meth_body, param_count, source_file)
end
@body.scan(/define_filetest_function\s*\(
\s*"([^"]+)",
\s*(?:RUBY_METHOD_FUNC\(|VALUEFUNC\()?(\w+)\)?,
\s*(-?\w+)\s*\)/xm) do #"
|meth_name, meth_body, param_count|
handle_method("method", "rb_mFileTest", meth_name, meth_body, param_count)
handle_method("singleton_method", "rb_cFile", meth_name, meth_body, param_count)
end
end
############################################################
def do_aliases
@body.scan(%r{rb_define_alias\s*\(\s*(\w+),\s*"([^"]+)",\s*"([^"]+)"\s*\)}m) do
|var_name, new_name, old_name|
@stats.num_methods += 1
class_name = @known_classes[var_name] || var_name
class_obj = find_class(var_name, class_name)
class_obj.add_alias(Alias.new("", old_name, new_name, ""))
end
end
############################################################
def handle_constants(type, var_name, const_name, definition)
#@stats.num_constants += 1
class_name = @known_classes[var_name]
return unless class_name
class_obj = find_class(var_name, class_name)
unless class_obj
warn("Enclosing class/module '#{const_name}' for not known")
return
end
comment = find_const_comment(type, const_name)
# In the case of rb_define_const, the definition and comment are in
# "/* definition: comment */" form. The literal ':' and '\' characters
# can be escaped with a backslash.
if type.downcase == 'const' then
elements = mangle_comment(comment).split(':')
if elements.nil? or elements.empty? then
con = Constant.new(const_name, definition, mangle_comment(comment))
else
new_definition = elements[0..-2].join(':')
if new_definition.empty? then # Default to literal C definition
new_definition = definition
else
new_definition.gsub!("\:", ":")
new_definition.gsub!("\\", '\\')
end
new_definition.sub!(/\A(\s+)/, '')
new_comment = $1.nil? ? elements.last : "#{$1}#{elements.last.lstrip}"
con = Constant.new(const_name, new_definition,
mangle_comment(new_comment))
end
else
con = Constant.new(const_name, definition, mangle_comment(comment))
end
class_obj.add_constant(con)
end
###########################################################
def find_const_comment(type, const_name)
if @body =~ %r{((?>^\s*/\*.*?\*/\s+))
rb_define_#{type}\((?:\s*(\w+),)?\s*"#{const_name}"\s*,.*?\)\s*;}xmi
$1
elsif @body =~ %r{Document-(?:const|global|variable):\s#{const_name}\s*?\n((?>.*?\*/))}m
$1
else
''
end
end
###########################################################
def handle_attr(var_name, attr_name, reader, writer)
rw = ''
if reader
#@stats.num_methods += 1
rw << 'R'
end
if writer
#@stats.num_methods += 1
rw << 'W'
end
class_name = @known_classes[var_name]
return unless class_name
class_obj = find_class(var_name, class_name)
if class_obj
comment = find_attr_comment(attr_name)
unless comment.empty?
comment = mangle_comment(comment)
end
att = Attr.new('', attr_name, rw, comment)
class_obj.add_attribute(att)
end
end
###########################################################
def find_attr_comment(attr_name)
if @body =~ %r{((?>/\*.*?\*/\s+))
rb_define_attr\((?:\s*(\w+),)?\s*"#{attr_name}"\s*,.*?\)\s*;}xmi
$1
elsif @body =~ %r{Document-attr:\s#{attr_name}\s*?\n((?>.*?\*/))}m
$1
else
''
end
end
###########################################################
def handle_method(type, var_name, meth_name,
meth_body, param_count, source_file = nil)
progress(".")
@stats.num_methods += 1
class_name = @known_classes[var_name]
return unless class_name
class_obj = find_class(var_name, class_name)
if class_obj
if meth_name == "initialize"
meth_name = "new"
type = "singleton_method"
end
meth_obj = AnyMethod.new("", meth_name)
meth_obj.singleton =
%w{singleton_method module_function}.include?(type)
p_count = (Integer(param_count) rescue -1)
if p_count < 0
meth_obj.params = "(...)"
elsif p_count == 0
meth_obj.params = "()"
else
meth_obj.params = "(" +
(1..p_count).map{|i| "p#{i}"}.join(", ") +
")"
end
if source_file
file_name = File.join(@file_dir, source_file)
body = (@@known_bodies[source_file] ||= File.read(file_name))
else
body = @body
end
if find_body(meth_body, meth_obj, body) and meth_obj.document_self
class_obj.add_method(meth_obj)
end
end
end
############################################################
# Find the C code corresponding to a Ruby method
def find_body(meth_name, meth_obj, body, quiet = false)
case body
when %r{((?>/\*.*?\*/\s*))(?:static\s+)?VALUE\s+#{meth_name}
\s*(\([^)]*\))\s*\{.*?^\}}xm
comment, params = $1, $2
body_text = $&
remove_private_comments(comment) if comment
# see if we can find the whole body
re = Regexp.escape(body_text) + '[^(]*^\{.*?^\}'
if Regexp.new(re, Regexp::MULTILINE).match(body)
body_text = $&
end
# The comment block may have been overridden with a
# 'Document-method' block. This happens in the interpreter
# when multiple methods are vectored through to the same
# C method but those methods are logically distinct (for
# example Kernel.hash and Kernel.object_id share the same
# implementation
override_comment = find_override_comment(meth_obj.name)
comment = override_comment if override_comment
find_modifiers(comment, meth_obj) if comment
# meth_obj.params = params
meth_obj.start_collecting_tokens
meth_obj.add_token(RubyToken::Token.new(1,1).set_text(body_text))
meth_obj.comment = mangle_comment(comment)
when %r{((?>/\*.*?\*/\s*))^\s*\#\s*define\s+#{meth_name}\s+(\w+)}m
comment = $1
find_body($2, meth_obj, body, true)
find_modifiers(comment, meth_obj)
meth_obj.comment = mangle_comment(comment) + meth_obj.comment
when %r{^\s*\#\s*define\s+#{meth_name}\s+(\w+)}m
unless find_body($1, meth_obj, body, true)
warn "No definition for #{meth_name}" unless quiet
return false
end
else
# No body, but might still have an override comment
comment = find_override_comment(meth_obj.name)
if comment
find_modifiers(comment, meth_obj)
meth_obj.comment = mangle_comment(comment)
else
warn "No definition for #{meth_name}" unless quiet
return false
end
end
true
end
##################################################
#
# If the comment block contains a section that looks like
# call-seq:
# Array.new
# Array.new(10)
# use it for the parameters
def find_modifiers(comment, meth_obj)
if comment.sub!(/:nodoc:\s*^\s*\*?\s*$/m, '') or
comment.sub!(/\A\/\*\s*:nodoc:\s*\*\/\Z/, '')
meth_obj.document_self = false
end
if comment.sub!(/call-seq:(.*?)^\s*\*?\s*$/m, '') or
comment.sub!(/\A\/\*\s*call-seq:(.*?)\*\/\Z/, '')
seq = $1
seq.gsub!(/^\s*\*\s*/, '')
meth_obj.call_seq = seq
end
end
############################################################
def find_override_comment(meth_name)
name = Regexp.escape(meth_name)
if @body =~ %r{Document-method:\s#{name}\s*?\n((?>.*?\*/))}m
$1
end
end
############################################################
# Look for includes of the form
# rb_include_module(rb_cArray, rb_mEnumerable);
def do_includes
@body.scan(/rb_include_module\s*\(\s*(\w+?),\s*(\w+?)\s*\)/) do |c,m|
if cls = @classes[c]
m = @known_classes[m] || m
cls.add_include(Include.new(m, ""))
end
end
end
############################################################
# Remove the /*'s and leading asterisks from C comments
def mangle_comment(comment)
comment.sub!(%r{/\*+}) { " " * $&.length }
comment.sub!(%r{\*+/}) { " " * $&.length }
comment.gsub!(/^[ \t]*\*/m) { " " * $&.length }
comment
end
def find_class(raw_name, name)
unless @classes[raw_name]
if raw_name =~ /^rb_m/
@classes[raw_name] = @top_level.add_module(NormalModule, name)
else
@classes[raw_name] = @top_level.add_class(NormalClass, name, nil)
end
end
@classes[raw_name]
end
def handle_tab_width(body)
if /\t/ =~ body
tab_width = Options.instance.tab_width
body.split(/\n/).map do |line|
1 while line.gsub!(/\t+/) { ' ' * (tab_width*$&.length - $`.length % tab_width)} && $~ #`
line
end .join("\n")
else
body
end
end
# Remove #ifdefs that would otherwise confuse us
def handle_ifdefs_in(body)
body.gsub(/^#ifdef HAVE_PROTOTYPES.*?#else.*?\n(.*?)#endif.*?\n/m) { $1 }
end
end
end
|