Class: Wp2txt::Article

Inherits:
Object
  • Object
show all
Includes:
Wp2txt
Defined in:
lib/wp2txt/article.rb

Overview

an article contains elements, each of which is [TYPE, string]

Constant Summary

Constants included from Wp2txt

BLANK_LINE_REGEX, CATEGORY_PATTERNS, CATEGORY_REGEX, CHRREF_TO_UTF_REGEX, CLEANUP_REGEX_01, CLEANUP_REGEX_02, CLEANUP_REGEX_03, CLEANUP_REGEX_04, CLEANUP_REGEX_05, CLEANUP_REGEX_06, CLEANUP_REGEX_07, CLEANUP_REGEX_08, COMPLEX_REGEX_01, COMPLEX_REGEX_02, COMPLEX_REGEX_03, COMPLEX_REGEX_04, COMPLEX_REGEX_05, CURLY_SQUARE_BRACKET_REGEX, DEF_MARKS_REGEX, DOUBLE_CURLY_BRACKET_REGEX, DOUBLE_SQUARE_BRACKET_REGEX, ENTITIES, ESCAPE_NOWIKI_REGEX, FORMAT_REF_REGEX, HEADING_CODA_REGEX, HEADING_ONSET_REGEX, HTML_DECODER, HTML_HASH, HTML_REGEX, IN_DEFINITION_REGEX, IN_HEADING_REGEX, IN_HTML_TABLE_REGEX, IN_HTML_TABLE_REGEX1, IN_HTML_TABLE_REGEX2, IN_INPUTBOX_REGEX, IN_INPUTBOX_REGEX1, IN_INPUTBOX_REGEX2, IN_LINK_REGEX, IN_MATH_REGEX, IN_MATH_REGEX1, IN_MATH_REGEX2, IN_ORDERED_REGEX, IN_PRE_REGEX, IN_SOURCE_REGEX, IN_SOURCE_REGEX1, IN_SOURCE_REGEX2, IN_TABLE_REGEX1, IN_TABLE_REGEX2, IN_UNORDERED_REGEX, ISOLATED_TAG_REGEX, ISOLATED_TEMPLATE_REGEX, LIST_MARKS_REGEX, MAKE_REFERENCE_REGEX_A, MAKE_REFERENCE_REGEX_B, MAKE_REFERENCE_REGEX_C, MAKE_REFERENCE_REGEX_D, ML_LINK_END_REGEX, ML_LINK_ONSET_REGEX, ML_TEMPLATE_END_REGEX, ML_TEMPLATE_ONSET_REGEX, MNDASH_REGEX, ONSET_BAR_REGEX, PRE_MARKS_REGEX, REDIRECT_REGEX, REMOVE_DIRECTIVES_REGEX, REMOVE_EMPHASIS_REGEX, REMOVE_HR_REGEX, REMOVE_INLINE_REGEX, REMOVE_ISOLATED_REGEX, REMOVE_TAG_REGEX, SINGLE_CURLY_BRACKET_REGEX, SINGLE_SQUARE_BRACKET_REGEX, TYPE_CODE_REGEX, UNESCAPE_NOWIKI_REGEX, VERSION

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods included from Wp2txt

#batch_file_mod, #chrref_to_utf, #cleanup, #collect_files, #convert_characters, #correct_inline_template, #correct_separator, #escape_nowiki, #file_mod, #format_wiki, #make_reference, #mndash, #process_external_links, #process_interwiki_links, #process_nested_structure, #remove_complex, #remove_directive, #remove_emphasis, #remove_hr, #remove_html, #remove_inbetween, #remove_ref, #remove_table, #remove_tag, #remove_templates, #rename, #sec_to_str, #special_chr, #unescape_nowiki

Constructor Details

#initialize(text, title = "", strip_tmarker = false) ⇒ Article

Returns a new instance of Article.



31
32
33
34
35
36
37
38
39
40
 
# File 'lib/wp2txt/article.rb', line 31

def initialize(text, title = "", strip_tmarker = false)
  @title = title.strip
  @strip_tmarker = strip_tmarker
  text = convert_characters(text)
  text = text.gsub(/\|\n\n+/m) { "|\n" }
  text = remove_html(text)
  text = make_reference(text)
  text = remove_ref(text)
  parse text
end

Instance Attribute Details

#categories ⇒ Object

Returns the value of attribute categories.



29
30
31
 
# File 'lib/wp2txt/article.rb', line 29

def categories
  @categories
end

#elements ⇒ Object

Returns the value of attribute elements.



29
30
31
 
# File 'lib/wp2txt/article.rb', line 29

def elements
  @elements
end

#title ⇒ Object

Returns the value of attribute title.



29
30
31
 
# File 'lib/wp2txt/article.rb', line 29

def title
  @title
end

Instance Method Details

#create_element(tpx, text) ⇒ Object 



42
43
44
 
# File 'lib/wp2txt/article.rb', line 42

def create_element(tpx, text)
  [tpx, text]
end

#parse(source) ⇒ Object 



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
 
# File 'lib/wp2txt/article.rb', line 46

def parse(source)
  @elements = []
  @categories = []
  mode = nil
  source.each_line do |line|
    matched = line.scan(CATEGORY_REGEX)
    if matched && !matched.empty?
      @categories += matched
      @categories.uniq!
    end

    case mode
    when :mw_ml_template
      scanner = StringScanner.new(line)
      str = process_nested_structure(scanner, "{{", "}}") { "" }
      mode = nil if ML_TEMPLATE_END_REGEX =~ str
      @elements.last.last << line
      next
    when :mw_ml_link
      scanner = StringScanner.new(line)
      str = process_nested_structure(scanner, "[[", "]]") { "" }
      mode = nil if ML_LINK_END_REGEX =~ str
      @elements.last.last << line
      next
    when :mw_table
      mode = nil if IN_TABLE_REGEX2 =~ line
      @elements.last.last << line
      next
    when :mw_inputbox
      mode = nil if IN_INPUTBOX_REGEX2 =~ line
      @elements.last.last << line
      next
    when :mw_source
      mode = nil if IN_SOURCE_REGEX2 =~ line
      @elements.last.last << line
      next
    when :mw_math
      mode = nil if IN_MATH_REGEX2 =~ line
      @elements.last.last << line
      next
    when :mw_htable
      mode = nil if IN_HTML_TABLE_REGEX2 =~ line
      @elements.last.last << line
      next
    end

    case line
    when ISOLATED_TEMPLATE_REGEX
      @elements << create_element(:mw_isolated_template, line)
    when ISOLATED_TAG_REGEX
      @elements << create_element(:mw_isolated_tag, line)
    when BLANK_LINE_REGEX
      @elements << create_element(:mw_blank, "\n")
    when REDIRECT_REGEX
      @elements << create_element(:mw_redirect, line)
    when IN_HEADING_REGEX
      line = line.sub(HEADING_ONSET_REGEX) { $1 }.sub(HEADING_CODA_REGEX) { $1 }
      @elements << create_element(:mw_heading, "\n" + line + "\n")
    when IN_INPUTBOX_REGEX
      @elements << create_element(:mw_inputbox, line)
    when ML_TEMPLATE_ONSET_REGEX
      @elements << create_element(:mw_ml_template, line)
      mode = :mw_ml_template
    when ML_LINK_ONSET_REGEX
      @elements << create_element(:mw_ml_link, line)
      mode = :mw_ml_link
    when IN_INPUTBOX_REGEX1
      mode = :mw_inputbox
      @elements << create_element(:mw_inputbox, line)
    when IN_SOURCE_REGEX
      @elements << create_element(:mw_source, line)
    when IN_SOURCE_REGEX1
      mode = :mw_source
      @elements << create_element(:mw_source, line)
    when IN_MATH_REGEX
      @elements << create_element(:mw_math, line)
    when IN_MATH_REGEX1
      mode = :mw_math
      @elements << create_element(:mw_math, line)
    when IN_HTML_TABLE_REGEX
      @elements << create_element(:mw_htable, line)
    when IN_HTML_TABLE_REGEX1
      mode = :mw_htable
      @elements << create_element(:mw_htable, line)
    when IN_TABLE_REGEX1
      mode = :mw_table
      @elements << create_element(:mw_table, line)
    when IN_UNORDERED_REGEX
      line = line.sub(LIST_MARKS_REGEX, "") if @strip_tmarker
      @elements << create_element(:mw_unordered, line)
    when IN_ORDERED_REGEX
      line = line.sub(LIST_MARKS_REGEX, "") if @strip_tmarker
      @elements << create_element(:mw_ordered, line)
    when IN_PRE_REGEX
      line = line.sub(PRE_MARKS_REGEX, "") if @strip_tmarker
      @elements << create_element(:mw_pre, line)
    when IN_DEFINITION_REGEX
      line = line.sub(DEF_MARKS_REGEX, "") if @strip_tmarker
      @elements << create_element(:mw_definition, line)
    when IN_LINK_REGEX
      @elements << create_element(:mw_link, line)
    else
      @elements << create_element(:mw_paragraph, "\n" + line)
    end
  end
  @elements
end