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
|
# frozen_string_literal: true
##
# RDoc::Markup parses plain text documents and attempts to decompose them into
# their constituent parts. Some of these parts are high-level: paragraphs,
# chunks of verbatim text, list entries and the like. Other parts happen at
# the character level: a piece of bold text, a word in code font. This markup
# is similar in spirit to that used on WikiWiki webs, where folks create web
# pages using a simple set of formatting rules.
#
# RDoc::Markup and other markup formats do no output formatting, this is
# handled by the RDoc::Markup::Formatter subclasses.
#
# = Supported Formats
#
# Besides the RDoc::Markup format, the following formats are built in to RDoc:
#
# markdown::
# The markdown format as described by
# http://daringfireball.net/projects/markdown/. See RDoc::Markdown for
# details on the parser and supported extensions.
# rd::
# The rdtool format. See RDoc::RD for details on the parser and format.
# tomdoc::
# The TomDoc format as described by http://tomdoc.org/. See RDoc::TomDoc
# for details on the parser and supported extensions.
#
# You can choose a markup format using the following methods:
#
# per project::
# If you build your documentation with rake use RDoc::Task#markup.
#
# If you build your documentation by hand run:
#
# rdoc --markup your_favorite_format --write-options
#
# and commit <tt>.rdoc_options</tt> and ship it with your packaged gem.
# per file::
# At the top of the file use the <tt>:markup:</tt> directive to set the
# default format for the rest of the file.
# per comment::
# Use the <tt>:markup:</tt> directive at the top of a comment you want
# to write in a different format.
#
# = RDoc::Markup
#
# RDoc::Markup is extensible at runtime: you can add \new markup elements to
# be recognized in the documents that RDoc::Markup parses.
#
# RDoc::Markup is intended to be the basis for a family of tools which share
# the common requirement that simple, plain-text should be rendered in a
# variety of different output formats and media. It is envisaged that
# RDoc::Markup could be the basis for formatting RDoc style comment blocks,
# Wiki entries, and online FAQs.
#
# == Synopsis
#
# This code converts +input_string+ to HTML. The conversion takes place in
# the +convert+ method, so you can use the same RDoc::Markup converter to
# convert multiple input strings.
#
# require 'rdoc'
#
# h = RDoc::Markup::ToHtml.new(RDoc::Options.new)
#
# puts h.convert(input_string)
#
# You can extend the RDoc::Markup parser to recognize new markup
# sequences, and to add regexp handling. Here we make WikiWords significant to
# the parser, and also make the sequences {word} and \<no>text...</no> signify
# strike-through text. We then subclass the HTML output class to deal
# with these:
#
# require 'rdoc'
#
# class WikiHtml < RDoc::Markup::ToHtml
# def handle_regexp_WIKIWORD(target)
# "<font color=red>" + target.text + "</font>"
# end
# end
#
# markup = RDoc::Markup.new
# markup.add_word_pair("{", "}", :STRIKE)
# markup.add_html("no", :STRIKE)
#
# markup.add_regexp_handling(/\b([A-Z][a-z]+[A-Z]\w+)/, :WIKIWORD)
#
# wh = WikiHtml.new RDoc::Options.new, markup
# wh.add_tag(:STRIKE, "<strike>", "</strike>")
#
# puts "<body>#{wh.convert ARGF.read}</body>"
#
# == Encoding
#
# Where Encoding support is available, RDoc will automatically convert all
# documents to the same output encoding. The output encoding can be set via
# RDoc::Options#encoding and defaults to Encoding.default_external.
#
# = \RDoc Markup Reference
#
# See RDoc::MarkupReference.
#
# === Escaping Text Markup
#
# Text markup can be escaped with a backslash, as in \<tt>, which was obtained
# with <tt>\\<tt></tt>. Except in verbatim sections and between \<tt> tags,
# to produce a backslash you have to double it unless it is followed by a
# space, tab or newline. Otherwise, the HTML formatter will discard it, as it
# is used to escape potential links:
#
# * The \ must be doubled if not followed by white space: \\.
# * But not in \<tt> tags: in a Regexp, <tt>\S</tt> matches non-space.
# * This is a link to {ruby-lang}[https://www.ruby-lang.org].
# * This is not a link, however: \{ruby-lang.org}[https://www.ruby-lang.org].
# * This will not be linked to \RDoc::RDoc#document
#
# generates:
#
# * The \ must be doubled if not followed by white space: \\.
# * But not in \<tt> tags: in a Regexp, <tt>\S</tt> matches non-space.
# * This is a link to {ruby-lang}[https://www.ruby-lang.org]
# * This is not a link, however: \{ruby-lang.org}[https://www.ruby-lang.org]
# * This will not be linked to \RDoc::RDoc#document
#
# Inside \<tt> tags, more precisely, leading backslashes are removed only if
# followed by a markup character (<tt><*_+</tt>), a backslash, or a known link
# reference (a known class or method). So in the example above, the backslash
# of <tt>\S</tt> would be removed if there was a class or module named +S+ in
# the current context.
#
# This behavior is inherited from RDoc version 1, and has been kept for
# compatibility with existing RDoc documentation.
#
# === Conversion of characters
#
# HTML will convert two/three dashes to an em-dash. Other common characters are
# converted as well:
#
# em-dash:: -- or ---
# ellipsis:: ...
#
# single quotes:: 'text' or `text'
# double quotes:: "text" or ``text''
#
# copyright:: (c)
# registered trademark:: (r)
#
# produces:
#
# em-dash:: -- or ---
# ellipsis:: ...
#
# single quotes:: 'text' or `text'
# double quotes:: "text" or ``text''
#
# copyright:: (c)
# registered trademark:: (r)
#
#
# == Documenting Source Code
#
# Comment blocks can be written fairly naturally, either using <tt>#</tt> on
# successive lines of the comment, or by including the comment in
# a <tt>=begin</tt>/<tt>=end</tt> block. If you use the latter form,
# the <tt>=begin</tt> line _must_ be flagged with an +rdoc+ tag:
#
# =begin rdoc
# Documentation to be processed by RDoc.
#
# ...
# =end
#
# RDoc stops processing comments if it finds a comment line starting
# with <tt>--</tt> right after the <tt>#</tt> character (otherwise,
# it will be treated as a rule if it has three dashes or more).
# This can be used to separate external from internal comments,
# or to stop a comment being associated with a method, class, or module.
# Commenting can be turned back on with a line that starts with <tt>++</tt>.
#
# ##
# # Extract the age and calculate the date-of-birth.
# #--
# # FIXME: fails if the birthday falls on February 29th
# #++
# # The DOB is returned as a Time object.
#
# def get_dob(person)
# # ...
# end
#
# Names of classes, files, and any method names containing an underscore or
# preceded by a hash character are automatically linked from comment text to
# their description. This linking works inside the current class or module,
# and with ancestor methods (in included modules or in the superclass).
#
# Method parameter lists are extracted and displayed with the method
# description. If a method calls +yield+, then the parameters passed to yield
# will also be displayed:
#
# def fred
# ...
# yield line, address
#
# This will get documented as:
#
# fred() { |line, address| ... }
#
# You can override this using a comment containing ':yields: ...' immediately
# after the method definition
#
# def fred # :yields: index, position
# # ...
#
# yield line, address
#
# which will get documented as
#
# fred() { |index, position| ... }
#
# +:yields:+ is an example of a documentation directive. These appear
# immediately after the start of the document element they are modifying.
#
# RDoc automatically cross-references words with underscores or camel-case.
# To suppress cross-references, prefix the word with a \ character. To
# include special characters like "<tt>\n</tt>", you'll need to use
# two \ characters in normal text, but only one in \<tt> text:
#
# "\\n" or "<tt>\n</tt>"
#
# produces:
#
# "\\n" or "<tt>\n</tt>"
#
# == Directives
#
# Directives are keywords surrounded by ":" characters.
#
# === Controlling what is documented
#
# [+:nodoc:+ / <tt>:nodoc: all</tt>]
# This directive prevents documentation for the element from
# being generated. For classes and modules, methods, aliases,
# constants, and attributes directly within the affected class or
# module also will be omitted. By default, though, modules and
# classes within that class or module _will_ be documented. This is
# turned off by adding the +all+ modifier.
#
# module MyModule # :nodoc:
# class Input
# end
# end
#
# module OtherModule # :nodoc: all
# class Output
# end
# end
#
# In the above code, only class <tt>MyModule::Input</tt> will be documented.
#
# The +:nodoc:+ directive, like +:enddoc:+, +:stopdoc:+ and +:startdoc:+
# presented below, is local to the current file: if you do not want to
# document a module that appears in several files, specify +:nodoc:+ on each
# appearance, at least once per file.
#
# [+:stopdoc:+ / +:startdoc:+]
# Stop and start adding new documentation elements to the current container.
# For example, if a class has a number of constants that you don't want to
# document, put a +:stopdoc:+ before the first, and a +:startdoc:+ after the
# last. If you don't specify a +:startdoc:+ by the end of the container,
# disables documentation for the rest of the current file.
#
# [+:doc:+]
# Forces a method or attribute to be documented even if it wouldn't be
# otherwise. Useful if, for example, you want to include documentation of a
# particular private method.
#
# [+:enddoc:+]
# Document nothing further at the current level: directives +:startdoc:+ and
# +:doc:+ that appear after this will not be honored for the current container
# (file, class or module), in the current file.
#
# [+:notnew:+ / +:not_new:+ / +:not-new:+ ]
# Only applicable to the +initialize+ instance method. Normally RDoc
# assumes that the documentation and parameters for +initialize+ are
# actually for the +new+ method, and so fakes out a +new+ for the class.
# The +:notnew:+ directive stops this. Remember that +initialize+ is private,
# so you won't see the documentation unless you use the +-a+ command line
# option.
#
# === Method arguments
#
# [+:arg:+ or +:args:+ _parameters_]
# Overrides the default argument handling with exactly these parameters.
#
# ##
# # :args: a, b
#
# def some_method(*a)
# end
#
# [+:yield:+ or +:yields:+ _parameters_]
# Overrides the default yield discovery with these parameters.
#
# ##
# # :yields: key, value
#
# def each_thing &block
# @things.each(&block)
# end
#
# [+:call-seq:+]
# Lines up to the next blank line or lines with a common prefix in the
# comment are treated as the method's calling sequence, overriding the
# default parsing of method parameters and yield arguments.
#
# Multiple lines may be used.
#
# # :call-seq:
# # ARGF.readlines(sep=$/) -> array
# # ARGF.readlines(limit) -> array
# # ARGF.readlines(sep, limit) -> array
# #
# # ARGF.to_a(sep=$/) -> array
# # ARGF.to_a(limit) -> array
# # ARGF.to_a(sep, limit) -> array
# #
# # The remaining lines are documentation ...
#
# === Sections
#
# Sections allow you to group methods in a class into sensible containers. If
# you use the sections 'Public', 'Internal' and 'Deprecated' (the three
# allowed method statuses from TomDoc) the sections will be displayed in that
# order placing the most useful methods at the top. Otherwise, sections will
# be displayed in alphabetical order.
#
# [+:category:+ _section_]
# Adds this item to the named +section+ overriding the current section. Use
# this to group methods by section in RDoc output while maintaining a
# sensible ordering (like alphabetical).
#
# # :category: Utility Methods
# #
# # CGI escapes +text+
#
# def convert_string text
# CGI.escapeHTML text
# end
#
# An empty category will place the item in the default category:
#
# # :category:
# #
# # This method is in the default category
#
# def some_method
# # ...
# end
#
# Unlike the :section: directive, :category: is not sticky. The category
# only applies to the item immediately following the comment.
#
# Use the :section: directive to provide introductory text for a section of
# documentation.
#
# [+:section:+ _title_]
# Provides section introductory text in RDoc output. The title following
# +:section:+ is used as the section name and the remainder of the comment
# containing the section is used as introductory text. A section's comment
# block must be separated from following comment blocks. Use an empty title
# to switch to the default section.
#
# The :section: directive is sticky, so subsequent methods, aliases,
# attributes, and classes will be contained in this section until the
# section is changed. The :category: directive will override the :section:
# directive.
#
# A :section: comment block may have one or more lines before the :section:
# directive. These will be removed, and any identical lines at the end of
# the block are also removed. This allows you to add visual cues to the
# section.
#
# Example:
#
# # ----------------------------------------
# # :section: My Section
# # This is the section that I wrote.
# # See it glisten in the noon-day sun.
# # ----------------------------------------
#
# ##
# # Comment for some_method
#
# def some_method
# # ...
# end
#
# === Other directives
#
# [+:markup:+ _type_]
# Overrides the default markup type for this comment with the specified
# markup type. For Ruby files, if the first comment contains this directive
# it is applied automatically to all comments in the file.
#
# Unless you are converting between markup formats you should use a
# <code>.rdoc_options</code> file to specify the default documentation
# format for your entire project. See RDoc::Options@Saved+Options for
# instructions.
#
# At the top of a file the +:markup:+ directive applies to the entire file:
#
# # coding: UTF-8
# # :markup: TomDoc
#
# # TomDoc comment here ...
#
# class MyClass
# # ...
#
# For just one comment:
#
# # ...
# end
#
# # :markup: RDoc
# #
# # This is a comment in RDoc markup format ...
#
# def some_method
# # ...
#
# See Markup@CONTRIBUTING for instructions on adding a new markup format.
#
# [+:include:+ _filename_]
# Include the contents of the named file at this point. This directive
# must appear alone on one line, possibly preceded by spaces. In this
# position, it can be escaped with a \ in front of the first colon.
#
# The file will be searched for in the directories listed by the +--include+
# option, or in the current directory by default. The contents of the file
# will be shifted to have the same indentation as the ':' at the start of
# the +:include:+ directive.
#
# [+:title:+ _text_]
# Sets the title for the document. Equivalent to the <tt>--title</tt>
# command line parameter. (The command line parameter overrides any :title:
# directive in the source).
#
# [+:main:+ _name_]
# Equivalent to the <tt>--main</tt> command line parameter.
#
#--
# Original Author:: Dave Thomas, dave@pragmaticprogrammer.com
# License:: Ruby license
class RDoc::Markup
##
# An AttributeManager which handles inline markup.
attr_reader :attribute_manager
##
# Parses +str+ into an RDoc::Markup::Document.
def self.parse str
RDoc::Markup::Parser.parse str
rescue RDoc::Markup::Parser::Error => e
$stderr.puts <<-EOF
While parsing markup, RDoc encountered a #{e.class}:
#{e}
\tfrom #{e.backtrace.join "\n\tfrom "}
---8<---
#{text}
---8<---
RDoc #{RDoc::VERSION}
Ruby #{RUBY_VERSION}-p#{RUBY_PATCHLEVEL} #{RUBY_RELEASE_DATE}
Please file a bug report with the above information at:
https://github.com/ruby/rdoc/issues
EOF
raise
end
##
# Take a block of text and use various heuristics to determine its
# structure (paragraphs, lists, and so on). Invoke an event handler as we
# identify significant chunks.
def initialize attribute_manager = nil
@attribute_manager = attribute_manager || RDoc::Markup::AttributeManager.new
@output = nil
end
##
# Add to the sequences used to add formatting to an individual word (such
# as *bold*). Matching entries will generate attributes that the output
# formatters can recognize by their +name+.
def add_word_pair(start, stop, name)
@attribute_manager.add_word_pair(start, stop, name)
end
##
# Add to the sequences recognized as general markup.
def add_html(tag, name)
@attribute_manager.add_html(tag, name)
end
##
# Add to other inline sequences. For example, we could add WikiWords using
# something like:
#
# parser.add_regexp_handling(/\b([A-Z][a-z]+[A-Z]\w+)/, :WIKIWORD)
#
# Each wiki word will be presented to the output formatter.
def add_regexp_handling(pattern, name)
@attribute_manager.add_regexp_handling(pattern, name)
end
##
# We take +input+, parse it if necessary, then invoke the output +formatter+
# using a Visitor to render the result.
def convert input, formatter
document = case input
when RDoc::Markup::Document then
input
else
RDoc::Markup::Parser.parse input
end
document.accept formatter
end
autoload :Parser, "#{__dir__}/markup/parser"
autoload :PreProcess, "#{__dir__}/markup/pre_process"
# Inline markup classes
autoload :AttrChanger, "#{__dir__}/markup/attr_changer"
autoload :AttrSpan, "#{__dir__}/markup/attr_span"
autoload :Attributes, "#{__dir__}/markup/attributes"
autoload :AttributeManager, "#{__dir__}/markup/attribute_manager"
autoload :RegexpHandling, "#{__dir__}/markup/regexp_handling"
# RDoc::Markup AST
autoload :BlankLine, "#{__dir__}/markup/blank_line"
autoload :BlockQuote, "#{__dir__}/markup/block_quote"
autoload :Document, "#{__dir__}/markup/document"
autoload :HardBreak, "#{__dir__}/markup/hard_break"
autoload :Heading, "#{__dir__}/markup/heading"
autoload :Include, "#{__dir__}/markup/include"
autoload :IndentedParagraph, "#{__dir__}/markup/indented_paragraph"
autoload :List, "#{__dir__}/markup/list"
autoload :ListItem, "#{__dir__}/markup/list_item"
autoload :Paragraph, "#{__dir__}/markup/paragraph"
autoload :Table, "#{__dir__}/markup/table"
autoload :Raw, "#{__dir__}/markup/raw"
autoload :Rule, "#{__dir__}/markup/rule"
autoload :Verbatim, "#{__dir__}/markup/verbatim"
# Formatters
autoload :Formatter, "#{__dir__}/markup/formatter"
autoload :ToAnsi, "#{__dir__}/markup/to_ansi"
autoload :ToBs, "#{__dir__}/markup/to_bs"
autoload :ToHtml, "#{__dir__}/markup/to_html"
autoload :ToHtmlCrossref, "#{__dir__}/markup/to_html_crossref"
autoload :ToHtmlSnippet, "#{__dir__}/markup/to_html_snippet"
autoload :ToLabel, "#{__dir__}/markup/to_label"
autoload :ToMarkdown, "#{__dir__}/markup/to_markdown"
autoload :ToRdoc, "#{__dir__}/markup/to_rdoc"
autoload :ToTableOfContents, "#{__dir__}/markup/to_table_of_contents"
autoload :ToTest, "#{__dir__}/markup/to_test"
autoload :ToTtOnly, "#{__dir__}/markup/to_tt_only"
end
|
