summaryrefslogtreecommitdiff
path: root/lib/rdoc/parser/changelog.rb
blob: a046241870c8dc7a39a09742998e7a2593c4bee3 (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
# frozen_string_literal: true

##
# A ChangeLog file parser.
#
# This parser converts a ChangeLog into an RDoc::Markup::Document.  When
# viewed as HTML a ChangeLog page will have an entry for each day's entries in
# the sidebar table of contents.
#
# This parser is meant to parse the MRI ChangeLog, but can be used to parse any
# {GNU style Change
# Log}[http://www.gnu.org/prep/standards/html_node/Style-of-Change-Logs.html].

class RDoc::Parser::ChangeLog < RDoc::Parser

  include RDoc::Parser::Text

  parse_files_matching(/(\/|\\|\A)ChangeLog[^\/\\]*\z/)

  ##
  # Attaches the +continuation+ of the previous line to the +entry_body+.
  #
  # Continued function listings are joined together as a single entry.
  # Continued descriptions are joined to make a single paragraph.

  def continue_entry_body entry_body, continuation
    return unless last = entry_body.last

    if last =~ /\)\s*\z/ and continuation =~ /\A\(/ then
      last.sub!(/\)\s*\z/, ',')
      continuation = continuation.sub(/\A\(/, '')
    end

    if last =~ /\s\z/ then
      last << continuation
    else
      last << ' ' + continuation
    end
  end

  ##
  # Creates an RDoc::Markup::Document given the +groups+ of ChangeLog entries.

  def create_document groups
    doc = RDoc::Markup::Document.new
    doc.omit_headings_below = 2
    doc.file = @top_level

    doc << RDoc::Markup::Heading.new(1, File.basename(@file_name))
    doc << RDoc::Markup::BlankLine.new

    groups.sort_by do |day,| day end.reverse_each do |day, entries|
      doc << RDoc::Markup::Heading.new(2, day.dup)
      doc << RDoc::Markup::BlankLine.new

      doc.concat create_entries entries
    end

    doc
  end

  ##
  # Returns a list of ChangeLog entries an RDoc::Markup nodes for the given
  # +entries+.

  def create_entries entries
    out = []

    entries.each do |entry, items|
      out << RDoc::Markup::Heading.new(3, entry)
      out << RDoc::Markup::BlankLine.new

      out << create_items(items)
    end

    out
  end

  ##
  # Returns an RDoc::Markup::List containing the given +items+ in the
  # ChangeLog

  def create_items items
    list = RDoc::Markup::List.new :NOTE

    items.each do |item|
      item =~ /\A(.*?(?:\([^)]+\))?):\s*/

      title = $1
      body = $'

      paragraph = RDoc::Markup::Paragraph.new body
      list_item = RDoc::Markup::ListItem.new title, paragraph
      list << list_item
    end

    list
  end

  ##
  # Groups +entries+ by date.

  def group_entries entries
    @time_cache ||= {}
    entries.group_by do |title, _|
      begin
        time = @time_cache[title]
        (time || parse_date(title)).strftime '%Y-%m-%d'
      rescue NoMethodError, ArgumentError
        time, = title.split '  ', 2
        parse_date(time).strftime '%Y-%m-%d'
      end
    end
  end

  ##
  # Parse date in ISO-8601, RFC-2822, or default of Git

  def parse_date(date)
    case date
    when /\A\s*(\d+)-(\d+)-(\d+)(?:[ T](\d+):(\d+):(\d+) *([-+]\d\d):?(\d\d))?\b/
      Time.new($1, $2, $3, $4, $5, $6, ("#{$7}:#{$8}" if $7))
    when /\A\s*\w{3}, +(\d+) (\w{3}) (\d+) (\d+):(\d+):(\d+) *(?:([-+]\d\d):?(\d\d))\b/
      Time.new($3, $2, $1, $4, $5, $6, ("#{$7}:#{$8}" if $7))
    when /\A\s*\w{3} (\w{3}) +(\d+) (\d+) (\d+):(\d+):(\d+) *(?:([-+]\d\d):?(\d\d))\b/
      Time.new($3, $1, $2, $4, $5, $6, ("#{$7}:#{$8}" if $7))
    when /\A\s*\w{3} (\w{3}) +(\d+) (\d+):(\d+):(\d+) (\d+)\b/
      Time.new($6, $1, $2, $3, $4, $5)
    else
      raise ArgumentError, "bad date: #{date}"
    end
  end

  ##
  # Parses the entries in the ChangeLog.
  #
  # Returns an Array of each ChangeLog entry in order of parsing.
  #
  # A ChangeLog entry is an Array containing the ChangeLog title (date and
  # committer) and an Array of ChangeLog items (file and function changed with
  # description).
  #
  # An example result would be:
  #
  #    [ 'Tue Dec  4 08:33:46 2012  Eric Hodel  <drbrain@segment7.net>',
  #      [ 'README.EXT:  Converted to RDoc format',
  #        'README.EXT.ja:  ditto']]

  def parse_entries
    @time_cache ||= {}

    if /\A((?:.*\n){,3})commit\s/ =~ @content
      class << self; prepend Git; end
      parse_info($1)
      return parse_entries
    end

    entries = []
    entry_name = nil
    entry_body = []

    @content.each_line do |line|
      case line
      when /^\s*$/ then
        next
      when /^\w.*/ then
        entries << [entry_name, entry_body] if entry_name

        entry_name = $&

        begin
          time = parse_date entry_name
          @time_cache[entry_name] = time
        rescue ArgumentError
          entry_name = nil
        end

        entry_body = []
      when /^(\t| {8})?\*\s*(.*)/ then # "\t* file.c (func): ..."
        entry_body << $2.dup
      when /^(\t| {8})?\s*(\(.*)/ then # "\t(func): ..."
        entry = $2

        if entry_body.last =~ /:/ then
          entry_body << entry.dup
        else
          continue_entry_body entry_body, entry
        end
      when /^(\t| {8})?\s*(.*)/ then
        continue_entry_body entry_body, $2
      end
    end

    entries << [entry_name, entry_body] if entry_name

    entries.reject! do |(entry,_)|
      entry == nil
    end

    entries
  end

  ##
  # Converts the ChangeLog into an RDoc::Markup::Document

  def scan
    @time_cache = {}

    entries = parse_entries
    grouped_entries = group_entries entries

    doc = create_document grouped_entries

    @top_level.comment = doc

    @top_level
  end

  ##
  # The extension for Git commit log

  module Git
    ##
    # Parses auxiliary info.  Currentry `base-url` to expand
    # references is effective.

    def parse_info(info)
      /^\s*base-url\s*=\s*(.*\S)/ =~ info
      @base_url = $1
    end

    ##
    # Parses the entries in the Git commit logs

    def parse_entries
      entries = []

      @content.scan(/^commit\s+(\h{20})\h*\n((?:.+\n)*)\n((?: {4}.*\n+)*)/) do
        entry_name, header, entry_body = $1, $2, $3.gsub(/^ {4}/, '')
        # header = header.scan(/^ *(\S+?): +(.*)/).to_h
        # date = header["CommitDate"] || header["Date"]
        date = header[/^ *(?:Author)?Date: +(.*)/, 1]
        author = header[/^ *Author: +(.*)/, 1]
        begin
          time = parse_date(header[/^ *CommitDate: +(.*)/, 1] || date)
          @time_cache[entry_name] = time
          author.sub!(/\s*<(.*)>/, '')
          email = $1
          entries << [entry_name, [author, email, date, entry_body]]
        rescue ArgumentError
        end
      end

      entries
    end

    ##
    # Returns a list of ChangeLog entries as
    # RDoc::Parser::ChangeLog::Git::LogEntry list for the given
    # +entries+.

    def create_entries entries
      # git log entries have no strictly itemized style like the old
      # style, just assume Markdown.
      entries.map do |commit, entry|
        LogEntry.new(@base_url, commit, *entry)
      end
    end

    LogEntry = Struct.new(:base, :commit, :author, :email, :date, :contents) do
      HEADING_LEVEL = 3

      def initialize(base, commit, author, email, date, contents)
        case contents
        when String
          contents = RDoc::Markdown.parse(contents).parts.each do |body|
            case body
            when RDoc::Markup::Heading
              body.level += HEADING_LEVEL + 1
            end
          end
          case first = contents[0]
          when RDoc::Markup::Paragraph
            contents[0] = RDoc::Markup::Heading.new(HEADING_LEVEL + 1, first.text)
          end
        end
        super
      end

      def level
        HEADING_LEVEL
      end

      def aref
        "label-#{commit}"
      end

      def label context = nil
        aref
      end

      def text
        case base
        when nil
          "#{date}"
        when /%s/
          "{#{date}}[#{base % commit}]"
        else
          "{#{date}}[#{base}#{commit}]"
        end + " {#{author}}[mailto:#{email}]"
      end

      def accept visitor
        visitor.accept_heading self
        begin
          if visitor.respond_to?(:code_object=)
            code_object = visitor.code_object
            visitor.code_object = self
          end
          contents.each do |body|
            body.accept visitor
          end
        ensure
          if visitor.respond_to?(:code_object)
            visitor.code_object = code_object
          end
        end
      end

      def pretty_print q # :nodoc:
        q.group(2, '[log_entry: ', ']') do
          q.text commit
          q.text ','
          q.breakable
          q.group(2, '[date: ', ']') { q.text date }
          q.text ','
          q.breakable
          q.group(2, '[author: ', ']') { q.text author }
          q.text ','
          q.breakable
          q.group(2, '[email: ', ']') { q.text email }
          q.text ','
          q.breakable
          q.pp contents
        end
      end
    end
  end
end