summaryrefslogtreecommitdiff
path: root/lib/rdoc/parser.rb
blob: 7006265b63dac0b95cfa40dfbcbeeb8214405e47 (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
# -*- coding: us-ascii -*-
# frozen_string_literal: true

##
# A parser is simple a class that subclasses RDoc::Parser and implements #scan
# to fill in an RDoc::TopLevel with parsed data.
#
# The initialize method takes an RDoc::TopLevel to fill with parsed content,
# the name of the file to be parsed, the content of the file, an RDoc::Options
# object and an RDoc::Stats object to inform the user of parsed items.  The
# scan method is then called to parse the file and must return the
# RDoc::TopLevel object.  By calling super these items will be set for you.
#
# In order to be used by RDoc the parser needs to register the file extensions
# it can parse.  Use ::parse_files_matching to register extensions.
#
#   require 'rdoc'
#
#   class RDoc::Parser::Xyz < RDoc::Parser
#     parse_files_matching /\.xyz$/
#
#     def initialize top_level, file_name, content, options, stats
#       super
#
#       # extra initialization if needed
#     end
#
#     def scan
#       # parse file and fill in @top_level
#     end
#   end

class RDoc::Parser

  @parsers = []

  class << self

    ##
    # An Array of arrays that maps file extension (or name) regular
    # expressions to parser classes that will parse matching filenames.
    #
    # Use parse_files_matching to register a parser's file extensions.

    attr_reader :parsers

  end

  ##
  # The name of the file being parsed

  attr_reader :file_name

  ##
  # Alias an extension to another extension. After this call, files ending
  # "new_ext" will be parsed using the same parser as "old_ext"

  def self.alias_extension(old_ext, new_ext)
    old_ext = old_ext.sub(/^\.(.*)/, '\1')
    new_ext = new_ext.sub(/^\.(.*)/, '\1')

    parser = can_parse_by_name "xxx.#{old_ext}"
    return false unless parser

    RDoc::Parser.parsers.unshift [/\.#{new_ext}$/, parser]

    true
  end

  ##
  # Determines if the file is a "binary" file which basically means it has
  # content that an RDoc parser shouldn't try to consume.

  def self.binary?(file)
    return false if file =~ /\.(rdoc|txt)$/

    s = File.read(file, 1024) or return false

    return true if s[0, 2] == Marshal.dump('')[0, 2] or s.index("\x00")

    mode = 'r:utf-8' # default source encoding has been changed to utf-8
    s.sub!(/\A#!.*\n/, '')     # assume shebang line isn't longer than 1024.
    encoding = s[/^\s*\#\s*(?:-\*-\s*)?(?:en)?coding:\s*([^\s;]+?)(?:-\*-|[\s;])/, 1]
    mode = "rb:#{encoding}" if encoding
    s = File.open(file, mode) {|f| f.gets(nil, 1024)}

    not s.valid_encoding?
  end

  ##
  # Checks if +file+ is a zip file in disguise.  Signatures from
  # http://www.garykessler.net/library/file_sigs.html

  def self.zip? file
    zip_signature = File.read file, 4

    zip_signature == "PK\x03\x04" or
      zip_signature == "PK\x05\x06" or
      zip_signature == "PK\x07\x08"
  rescue
    false
  end

  ##
  # Return a parser that can handle a particular extension

  def self.can_parse file_name
    parser = can_parse_by_name file_name

    # HACK Selenium hides a jar file using a .txt extension
    return if parser == RDoc::Parser::Simple and zip? file_name

    parser
  end

  ##
  # Returns a parser that can handle the extension for +file_name+.  This does
  # not depend upon the file being readable.

  def self.can_parse_by_name file_name
    _, parser = RDoc::Parser.parsers.find { |regexp,| regexp =~ file_name }

    # The default parser must not parse binary files
    ext_name = File.extname file_name
    return parser if ext_name.empty?

    if parser == RDoc::Parser::Simple and ext_name !~ /txt|rdoc/ then
      case check_modeline file_name
      when nil, 'rdoc' then # continue
      else return nil
      end
    end

    parser
  rescue Errno::EACCES
  end

  ##
  # Returns the file type from the modeline in +file_name+

  def self.check_modeline file_name
    line = File.open file_name do |io|
      io.gets
    end

    /-\*-\s*(.*?\S)\s*-\*-/ =~ line

    return nil unless type = $1

    if /;/ =~ type then
      return nil unless /(?:\s|\A)mode:\s*([^\s;]+)/i =~ type
      type = $1
    end

    return nil if /coding:/i =~ type

    type.downcase
  rescue ArgumentError
  rescue Encoding::InvalidByteSequenceError # invalid byte sequence

  end

  ##
  # Finds and instantiates the correct parser for the given +file_name+ and
  # +content+.

  def self.for top_level, file_name, content, options, stats
    return if binary? file_name

    parser = use_markup content

    unless parser then
      parse_name = file_name

      # If no extension, look for shebang
      if file_name !~ /\.\w+$/ && content =~ %r{\A#!(.+)} then
        shebang = $1
        case shebang
        when %r{env\s+ruby}, %r{/ruby}
          parse_name = 'dummy.rb'
        end
      end

      parser = can_parse parse_name
    end

    return unless parser

    content = remove_modeline content

    parser.new top_level, file_name, content, options, stats
  rescue SystemCallError
    nil
  end

  ##
  # Record which file types this parser can understand.
  #
  # It is ok to call this multiple times.

  def self.parse_files_matching(regexp)
    RDoc::Parser.parsers.unshift [regexp, self]
  end

  ##
  # Removes an emacs-style modeline from the first line of the document

  def self.remove_modeline content
    content.sub(/\A.*-\*-\s*(.*?\S)\s*-\*-.*\r?\n/, '')
  end

  ##
  # If there is a <tt>markup: parser_name</tt> comment at the front of the
  # file, use it to determine the parser.  For example:
  #
  #   # markup: rdoc
  #   # Class comment can go here
  #
  #   class C
  #   end
  #
  # The comment should appear as the first line of the +content+.
  #
  # If the content contains a shebang or editor modeline the comment may
  # appear on the second or third line.
  #
  # Any comment style may be used to hide the markup comment.

  def self.use_markup content
    markup = content.lines.first(3).grep(/markup:\s+(\w+)/) { $1 }.first

    return unless markup

    # TODO Ruby should be returned only when the filename is correct
    return RDoc::Parser::Ruby if %w[tomdoc markdown].include? markup

    markup = Regexp.escape markup

    _, selected = RDoc::Parser.parsers.find do |_, parser|
      /^#{markup}$/i =~ parser.name.sub(/.*:/, '')
    end

    selected
  end

  ##
  # Creates a new Parser storing +top_level+, +file_name+, +content+,
  # +options+ and +stats+ in instance variables.  In +@preprocess+ an
  # RDoc::Markup::PreProcess object is created which allows processing of
  # directives.

  def initialize top_level, file_name, content, options, stats
    @top_level = top_level
    @top_level.parser = self.class
    @store = @top_level.store

    @file_name = file_name
    @content = content
    @options = options
    @stats = stats

    @preprocess = RDoc::Markup::PreProcess.new @file_name, @options.rdoc_include
    @preprocess.options = @options
  end

  autoload :RubyTools, "#{__dir__}/parser/ruby_tools"
  autoload :Text,      "#{__dir__}/parser/text"

end

# simple must come first in order to show up last in the parsers list
require_relative 'parser/simple'
require_relative 'parser/c'
require_relative 'parser/changelog'
require_relative 'parser/markdown'
require_relative 'parser/rd'
require_relative 'parser/ruby'