maiku 0.6.1.maiku

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (44) hide show
  1. data/lib/maruku.rb +141 -0
  2. data/lib/maruku/attributes.rb +175 -0
  3. data/lib/maruku/defaults.rb +71 -0
  4. data/lib/maruku/errors_management.rb +92 -0
  5. data/lib/maruku/ext/div.rb +133 -0
  6. data/lib/maruku/ext/math.rb +41 -0
  7. data/lib/maruku/ext/math/elements.rb +27 -0
  8. data/lib/maruku/ext/math/latex_fix.rb +12 -0
  9. data/lib/maruku/ext/math/mathml_engines/blahtex.rb +107 -0
  10. data/lib/maruku/ext/math/mathml_engines/itex2mml.rb +29 -0
  11. data/lib/maruku/ext/math/mathml_engines/none.rb +20 -0
  12. data/lib/maruku/ext/math/mathml_engines/ritex.rb +24 -0
  13. data/lib/maruku/ext/math/parsing.rb +119 -0
  14. data/lib/maruku/ext/math/to_html.rb +187 -0
  15. data/lib/maruku/ext/math/to_latex.rb +26 -0
  16. data/lib/maruku/helpers.rb +260 -0
  17. data/lib/maruku/input/charsource.rb +326 -0
  18. data/lib/maruku/input/extensions.rb +69 -0
  19. data/lib/maruku/input/html_helper.rb +189 -0
  20. data/lib/maruku/input/linesource.rb +111 -0
  21. data/lib/maruku/input/parse_block.rb +616 -0
  22. data/lib/maruku/input/parse_doc.rb +232 -0
  23. data/lib/maruku/input/parse_span_better.rb +746 -0
  24. data/lib/maruku/input/rubypants.rb +225 -0
  25. data/lib/maruku/input/type_detection.rb +147 -0
  26. data/lib/maruku/input_textile2/t2_parser.rb +163 -0
  27. data/lib/maruku/maruku.rb +33 -0
  28. data/lib/maruku/output/s5/fancy.rb +756 -0
  29. data/lib/maruku/output/s5/to_s5.rb +138 -0
  30. data/lib/maruku/output/to_html.rb +991 -0
  31. data/lib/maruku/output/to_latex.rb +590 -0
  32. data/lib/maruku/output/to_latex_entities.rb +367 -0
  33. data/lib/maruku/output/to_latex_strings.rb +64 -0
  34. data/lib/maruku/output/to_markdown.rb +164 -0
  35. data/lib/maruku/output/to_s.rb +56 -0
  36. data/lib/maruku/string_utils.rb +201 -0
  37. data/lib/maruku/structures.rb +167 -0
  38. data/lib/maruku/structures_inspect.rb +87 -0
  39. data/lib/maruku/structures_iterators.rb +61 -0
  40. data/lib/maruku/textile2.rb +1 -0
  41. data/lib/maruku/toc.rb +199 -0
  42. data/lib/maruku/usage/example1.rb +33 -0
  43. data/lib/maruku/version.rb +39 -0
  44. metadata +167 -0
@@ -0,0 +1,225 @@
1
+ #--
2
+ # Copyright (C) 2006 Andrea Censi <andrea (at) rubyforge.org>
3
+ #
4
+ # This file is part of Maruku.
5
+ #
6
+ # Maruku is free software; you can redistribute it and/or modify
7
+ # it under the terms of the GNU General Public License as published by
8
+ # the Free Software Foundation; either version 2 of the License, or
9
+ # (at your option) any later version.
10
+ #
11
+ # Maruku is distributed in the hope that it will be useful,
12
+ # but WITHOUT ANY WARRANTY; without even the implied warranty of
13
+ # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14
+ # GNU General Public License for more details.
15
+ #
16
+ # You should have received a copy of the GNU General Public License
17
+ # along with Maruku; if not, write to the Free Software
18
+ # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
19
+ #++
20
+
21
+ #
22
+ # NOTA BENE:
23
+ #
24
+ # The following algorithm is a rip-off of RubyPants written by
25
+ # Christian Neukirchen.
26
+ #
27
+ # RubyPants is a Ruby port of SmartyPants written by John Gruber.
28
+ #
29
+ # This file is distributed under the GPL, which I guess is compatible
30
+ # with the terms of the RubyPants license.
31
+ #
32
+ # -- Andrea Censi
33
+
34
+
35
+ # = RubyPants -- SmartyPants ported to Ruby
36
+ #
37
+ # Ported by Christian Neukirchen <mailto:chneukirchen@gmail.com>
38
+ # Copyright (C) 2004 Christian Neukirchen
39
+ #
40
+ # Incooporates ideas, comments and documentation by Chad Miller
41
+ # Copyright (C) 2004 Chad Miller
42
+ #
43
+ # Original SmartyPants by John Gruber
44
+ # Copyright (C) 2003 John Gruber
45
+ #
46
+
47
+ #
48
+ # = RubyPants -- SmartyPants ported to Ruby
49
+ #
50
+ #
51
+ # [snip]
52
+ #
53
+ # == Authors
54
+ #
55
+ # John Gruber did all of the hard work of writing this software in
56
+ # Perl for Movable Type and almost all of this useful documentation.
57
+ # Chad Miller ported it to Python to use with Pyblosxom.
58
+ #
59
+ # Christian Neukirchen provided the Ruby port, as a general-purpose
60
+ # library that follows the *Cloth API.
61
+ #
62
+ #
63
+ # == Copyright and License
64
+ #
65
+ # === SmartyPants license:
66
+ #
67
+ # Copyright (c) 2003 John Gruber
68
+ # (http://daringfireball.net)
69
+ # All rights reserved.
70
+ #
71
+ # Redistribution and use in source and binary forms, with or without
72
+ # modification, are permitted provided that the following conditions
73
+ # are met:
74
+ #
75
+ # * Redistributions of source code must retain the above copyright
76
+ # notice, this list of conditions and the following disclaimer.
77
+ #
78
+ # * Redistributions in binary form must reproduce the above copyright
79
+ # notice, this list of conditions and the following disclaimer in
80
+ # the documentation and/or other materials provided with the
81
+ # distribution.
82
+ #
83
+ # * Neither the name "SmartyPants" nor the names of its contributors
84
+ # may be used to endorse or promote products derived from this
85
+ # software without specific prior written permission.
86
+ #
87
+ # This software is provided by the copyright holders and contributors
88
+ # "as is" and any express or implied warranties, including, but not
89
+ # limited to, the implied warranties of merchantability and fitness
90
+ # for a particular purpose are disclaimed. In no event shall the
91
+ # copyright owner or contributors be liable for any direct, indirect,
92
+ # incidental, special, exemplary, or consequential damages (including,
93
+ # but not limited to, procurement of substitute goods or services;
94
+ # loss of use, data, or profits; or business interruption) however
95
+ # caused and on any theory of liability, whether in contract, strict
96
+ # liability, or tort (including negligence or otherwise) arising in
97
+ # any way out of the use of this software, even if advised of the
98
+ # possibility of such damage.
99
+ #
100
+ # === RubyPants license
101
+ #
102
+ # RubyPants is a derivative work of SmartyPants and smartypants.py.
103
+ #
104
+ # Redistribution and use in source and binary forms, with or without
105
+ # modification, are permitted provided that the following conditions
106
+ # are met:
107
+ #
108
+ # * Redistributions of source code must retain the above copyright
109
+ # notice, this list of conditions and the following disclaimer.
110
+ #
111
+ # * Redistributions in binary form must reproduce the above copyright
112
+ # notice, this list of conditions and the following disclaimer in
113
+ # the documentation and/or other materials provided with the
114
+ # distribution.
115
+ #
116
+ # This software is provided by the copyright holders and contributors
117
+ # "as is" and any express or implied warranties, including, but not
118
+ # limited to, the implied warranties of merchantability and fitness
119
+ # for a particular purpose are disclaimed. In no event shall the
120
+ # copyright owner or contributors be liable for any direct, indirect,
121
+ # incidental, special, exemplary, or consequential damages (including,
122
+ # but not limited to, procurement of substitute goods or services;
123
+ # loss of use, data, or profits; or business interruption) however
124
+ # caused and on any theory of liability, whether in contract, strict
125
+ # liability, or tort (including negligence or otherwise) arising in
126
+ # any way out of the use of this software, even if advised of the
127
+ # possibility of such damage.
128
+ #
129
+ #
130
+ # == Links
131
+ #
132
+ # John Gruber:: http://daringfireball.net
133
+ # SmartyPants:: http://daringfireball.net/projects/smartypants
134
+ #
135
+ # Chad Miller:: http://web.chad.org
136
+ #
137
+ # Christian Neukirchen:: http://kronavita.de/chris
138
+
139
+
140
+ module MaRuKu; module In; module Markdown; module SpanLevelParser
141
+ Punct_class = '[!"#\$\%\'()*+,\-.\/:;<=>?\@\[\\\\\]\^_`{|}~]'
142
+ Close_class = %![^\ \t\r\n\\[\{\(\-]!
143
+
144
+ Rules = [
145
+ [/---/, :mdash ],
146
+ [/--/, :ndash ],
147
+ ['...', :hellip ],
148
+ ['. . .', :hellip ],
149
+ ["``", :ldquo ],
150
+ ["''", :rdquo ],
151
+ [/<<\s/, [:laquo, :nbsp] ],
152
+ [/\s>>/, [:nbsp, :raquo] ],
153
+ [/<</, :laquo ],
154
+ [/>>/, :raquo ],
155
+
156
+ # def educate_single_backticks(str)
157
+ # ["`", :lsquo]
158
+ # ["'", :rsquo]
159
+
160
+ # Special case if the very first character is a quote followed by
161
+ # punctuation at a non-word-break. Close the quotes by brute
162
+ # force:
163
+ [/^'(?=#{Punct_class}\B)/, :rsquo],
164
+ [/^"(?=#{Punct_class}\B)/, :rdquo],
165
+ # Special case for double sets of quotes, e.g.:
166
+ # <p>He said, "'Quoted' words in a larger quote."</p>
167
+ [/"'(?=\w)/, [:ldquo, :lsquo] ],
168
+ [/'"(?=\w)/, [:lsquo, :ldquo] ],
169
+ # Special case for decade abbreviations (the '80s):
170
+ [/'(?=\d\ds)/, :rsquo ],
171
+ # Get most opening single quotes:
172
+ [/(\s)'(?=\w)/, [:one, :lsquo] ],
173
+ # Single closing quotes:
174
+ [/(#{Close_class})'/, [:one, :rsquo]],
175
+ [/'(\s|s\b|$)/, [:rsquo, :one]],
176
+ # Any remaining single quotes should be opening ones:
177
+ [/'/, :lsquo],
178
+ # Get most opening double quotes:
179
+ [/(\s)"(?=\w)/, [:one, :ldquo]],
180
+ # Double closing quotes:
181
+ [/(#{Close_class})"/, [:one, :rdquo]],
182
+ [/"(\s|s\b|$)/, [:rdquo, :one]],
183
+ # Any remaining quotes should be opening ones:
184
+ [/"/, :ldquo]
185
+ ].
186
+ map{|reg, subst| # People should do the thinking, machines should do the work.
187
+ reg = Regexp.new(Regexp.escape(reg)) if not reg.kind_of? Regexp
188
+ subst = [subst] if not subst.kind_of?Array
189
+ [reg, subst]}
190
+
191
+ # note: input will be destroyed
192
+ def apply_one_rule(reg, subst, input)
193
+ output = []
194
+ while first = input.shift
195
+ if first.kind_of?(String) && (m = reg.match(first))
196
+ output.push m. pre_match if m. pre_match.size > 0
197
+ input.unshift m.post_match if m.post_match.size > 0
198
+ subst.reverse.each do |x|
199
+ input.unshift( x == :one ? m[1] : md_entity(x.to_s) ) end
200
+ else
201
+ output.push first
202
+ end
203
+ end
204
+ return output
205
+ end
206
+
207
+ def educate(elements)
208
+ Rules.each do |reg, subst|
209
+ elements = apply_one_rule(reg, subst, elements)
210
+ end
211
+ # strips empty strings
212
+ elements.delete_if {|x| x.kind_of?(String) && x.size == 0}
213
+ final = []
214
+ # join consecutive strings
215
+ elements.each do |x|
216
+ if x.kind_of?(String) && final.last.kind_of?(String)
217
+ final.last << x
218
+ else
219
+ final << x
220
+ end
221
+ end
222
+ return final
223
+ end
224
+
225
+ end end end end
@@ -0,0 +1,147 @@
1
+ #--
2
+ # Copyright (C) 2006 Andrea Censi <andrea (at) rubyforge.org>
3
+ #
4
+ # This file is part of Maruku.
5
+ #
6
+ # Maruku is free software; you can redistribute it and/or modify
7
+ # it under the terms of the GNU General Public License as published by
8
+ # the Free Software Foundation; either version 2 of the License, or
9
+ # (at your option) any later version.
10
+ #
11
+ # Maruku is distributed in the hope that it will be useful,
12
+ # but WITHOUT ANY WARRANTY; without even the implied warranty of
13
+ # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14
+ # GNU General Public License for more details.
15
+ #
16
+ # You should have received a copy of the GNU General Public License
17
+ # along with Maruku; if not, write to the Free Software
18
+ # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
19
+ #++
20
+
21
+ class String
22
+ include MaRuKu::Strings
23
+ def md_type()
24
+ @md_type ||= line_md_type(self)
25
+ end
26
+ end
27
+
28
+ class NilClass
29
+ def md_type() nil end
30
+
31
+ end
32
+
33
+ # This code does the classification of lines for block-level parsing.
34
+ module MaRuKu; module Strings
35
+
36
+ def line_md_type(l)
37
+ # The order of evaluation is important (:text is a catch-all)
38
+ return :text if l =~ /^[a-zA-Z]/
39
+ return :code if number_of_leading_spaces(l)>=4
40
+ return :empty if l =~ /^\s*$/
41
+ return :footnote_text if l =~ FootnoteText
42
+ return :ref_definition if l =~ LinkRegex or l=~ IncompleteLink
43
+ return :abbreviation if l =~ Abbreviation
44
+ return :definition if l =~ Definition
45
+ # I had a bug with emails and urls at the beginning of the
46
+ # line that were mistaken for raw_html
47
+ return :text if l=~ /^[ ]{0,3}#{EMailAddress}/
48
+ return :text if l=~ /^[ ]{0,3}<http:/
49
+ # raw html is like PHP Markdown Extra: at most three spaces before
50
+ return :xml_instr if l =~ %r{^\s*<\?}
51
+ return :raw_html if l =~ %r{^[ ]?[ ]?[ ]?</?\s*\w+}
52
+ return :raw_html if l =~ %r{^[ ]?[ ]?[ ]?<\!\-\-}
53
+ # Something is wrong with how we parse lists! :-(
54
+ #return :ulist if l =~ /^[ ]{0,3}([\*\-\+])\s+.*\w+/
55
+ #return :olist if l =~ /^[ ]{0,3}\d+\..*\w+/
56
+ return :ulist if l =~ /^[ ]{0,1}([\*\-\+])\s+.*\w+/
57
+ return :olist if l =~ /^[ ]{0,1}\d+\..*\w+/
58
+ return :header1 if l =~ /^(=)+/
59
+ return :header2 if l =~ /^([-\s])+$/
60
+ return :header3 if l =~ /^(#)+\s*\S+/
61
+ # at least three asterisks on a line, and only whitespace
62
+ return :hrule if l =~ /^(\s*\*\s*){3,1000}$/
63
+ return :hrule if l =~ /^(\s*-\s*){3,1000}$/ # or hyphens
64
+ return :hrule if l =~ /^(\s*_\s*){3,1000}$/ # or underscores
65
+ return :quote if l =~ /^>/
66
+ return :metadata if l =~ /^@/
67
+ # if @@new_meta_data?
68
+ return :ald if l =~ AttributeDefinitionList
69
+ return :ial if l =~ InlineAttributeList
70
+ # end
71
+ # return :equation_end if l =~ EquationEnd
72
+ return :text # else, it's just text
73
+ end
74
+
75
+
76
+ # $1 = id $2 = attribute list
77
+ AttributeDefinitionList = /^\s{0,3}\{([\w\d\s]+)\}:\s*(.*)\s*$/
78
+ #
79
+ InlineAttributeList = /^\s{0,3}\{([:#\.].*)\}\s*$/
80
+ # Example:
81
+ # ^:blah blah
82
+ # ^: blah blah
83
+ # ^ : blah blah
84
+ Definition = %r{
85
+ ^ # begin of line
86
+ [ ]{0,3} # up to 3 spaces
87
+ : # colon
88
+ \s* # whitespace
89
+ (\S.*) # the text = $1
90
+ $ # end of line
91
+ }x
92
+
93
+ # Example:
94
+ # *[HTML]: Hyper Text Markup Language
95
+ Abbreviation = %r{
96
+ ^ # begin of line
97
+ [ ]{0,3} # up to 3 spaces
98
+ \* # one asterisk
99
+ \[ # opening bracket
100
+ ([^\]]+) # any non-closing bracket: id = $1
101
+ \] # closing bracket
102
+ : # colon
103
+ \s* # whitespace
104
+ (\S.*\S)* # definition=$2
105
+ \s* # strip this whitespace
106
+ $ # end of line
107
+ }x
108
+
109
+ FootnoteText = %r{
110
+ ^ # begin of line
111
+ [ ]{0,3} # up to 3 spaces
112
+ \[(\^.+)\]: # id = $1 (including '^')
113
+ \s*(\S.*)?$ # text = $2 (not obb.)
114
+ }x
115
+
116
+ # This regex is taken from BlueCloth sources
117
+ # Link defs are in the form: ^[id]: \n? url "optional title"
118
+ LinkRegex = %r{
119
+ ^[ ]{0,3}\[([^\[\]]+)\]: # id = $1
120
+ [ ]*
121
+ <?([^>\s]+)>? # url = $2
122
+ [ ]*
123
+ (?:# Titles are delimited by "quotes" or (parens).
124
+ ["(']
125
+ (.+?) # title = $3
126
+ [")'] # Matching ) or "
127
+ \s*(.+)? # stuff = $4
128
+ )? # title is optional
129
+ }x
130
+
131
+ IncompleteLink = %r{^[ ]{0,3}\[([^\[\]]+)\]:\s*$}
132
+
133
+ HeaderWithId = /^(.*)\{\#([\w_-]+)\}\s*$/
134
+
135
+ HeaderWithAttributes = /^(.*)\{(.*)\}\s*$/
136
+
137
+
138
+ # if contains a pipe, it could be a table header
139
+ MightBeTableHeader = %r{\|}
140
+ # -------------:
141
+ Sep = /\s*(\:)?\s*-+\s*(\:)?\s*/
142
+ # | -------------:| ------------------------------ |
143
+ TableSeparator = %r{^(\|?#{Sep}\|?)+\s*$}
144
+
145
+
146
+ EMailAddress = /<([^:]+@[^:]+)>/
147
+ end end
@@ -0,0 +1,163 @@
1
+ class String
2
+ Textile2_EmptyLine = /^\s*$/
3
+ Textile2_Signature = /^(\S+\.?)\.\s(.*)/
4
+
5
+ def t2_empty?
6
+ self =~ Textile2_EmptyLine
7
+ end
8
+
9
+ def t2_contains_signature?
10
+ self =~ Textile2_Signature
11
+ end
12
+
13
+ # sig, rest = t2_get_signature
14
+ def t2_get_signature
15
+ self =~ Textile2_Signature
16
+ return Textile2Signature.new($1), $2
17
+ end
18
+ end
19
+
20
+ class Textile2Signature
21
+ Reg = %r{
22
+ ^
23
+ # block name is 1
24
+ ([A-Za-z0-9]+)?
25
+ # style is 2
26
+ (
27
+ \{ # open bracket
28
+ ([^\}]+) # style spec is 3
29
+ \} # close bracket
30
+ )?
31
+ # language is 4
32
+ (\[(\w+)\])? # value is 5
33
+ # class and id
34
+ (?:
35
+ \( # open par
36
+ (\w+)? # optional class specification is 6
37
+ (?:\#(\w+))? # optional id is 7
38
+ \) # close par
39
+ )?
40
+ # alignment is 8
41
+ (\<|\>|\<\>|\=)?
42
+ # padding
43
+ (\(+)? # left is 9
44
+ (\)+)? # right is 10
45
+ # filters is 11
46
+ (\|
47
+ (?:(?:\w+)\|)+
48
+ )?
49
+ # optional final dot is 12
50
+ (\.)?
51
+ $
52
+ }x
53
+
54
+
55
+ def initialize(s)
56
+ if m = Reg.match(s)
57
+ self.block_name = m[1]
58
+ self.style = m[3]
59
+ self.lang = m[4]
60
+ self.css_class = m[6]
61
+ self.css_id = m[7]
62
+ self.text_align = {nil=>nil,'>'=>'right','<'=>'left',
63
+ '<>'=>'center','='=>'justified'}[m[8]]
64
+ self.num_left_pad = m[9] && m[9].size
65
+ self.num_right_pad = m[10] && m[10].size
66
+ self.filters = m[11] && m[11].split('|')
67
+ self.double_dot = m[12] && true
68
+ end
69
+ end
70
+
71
+
72
+ attr_accessor :block_name # or nil
73
+ attr_accessor :style # or nil
74
+ attr_accessor :lang # or nil
75
+ attr_accessor :css_class # or nil
76
+ attr_accessor :css_id # or nil
77
+ attr_accessor :text_align # {nil, 'left', 'right', 'center', 'justified'}
78
+ attr_accessor :num_left_pad # nil or 1..
79
+ attr_accessor :num_right_pad # nil or 1..
80
+ attr_accessor :filters # nil [], array of strings
81
+ attr_accessor :double_dot # nil or true
82
+
83
+
84
+ end
85
+
86
+ module MaRuKu
87
+
88
+ def self.textile2(source, params)
89
+ m = Maruku.new
90
+ m.t2_parse(source, params)
91
+ end
92
+
93
+
94
+ class MDDocument
95
+ def t2_parse(source, params)
96
+ src = LineSource.new(source)
97
+ output = BlockContext.new
98
+ t2_parse_blocks(src, output)
99
+ self.children = output.elements
100
+ end
101
+
102
+ Handling = Struct.new(:method, :parse_lines)
103
+ T2_Handling = {
104
+ nil => Handling.new(:t2_block_paragraph, true),
105
+ 'p' => Handling.new(:t2_block_paragraph, true)
106
+ }
107
+
108
+ # Input is a LineSource
109
+ def t2_parse_blocks(src, output)
110
+ while src.cur_line
111
+ l = src.shift_line
112
+
113
+ # ignore empty line
114
+ if l.t2_empty? then
115
+ src.shift_line
116
+ next
117
+ end
118
+
119
+ # TODO: lists
120
+ # TODO: xml
121
+ # TODO: `==`
122
+
123
+ signature, l =
124
+ if l.t2_contains_signature?
125
+ l.t2_get_signature
126
+ else
127
+ [Textile2Signature.new, l]
128
+ end
129
+
130
+ if handling = T2_Handling.has_key?(signature.block_name)
131
+ if self.responds_to? handling.method
132
+ # read as many non-empty lines that you can
133
+ lines = [l]
134
+ if handling.parse_lines
135
+ while not src.cur_line.t2_empty?
136
+ lines.push src.shift_line
137
+ end
138
+ end
139
+
140
+ self.send(handling.method, src, output, signature, lines)
141
+ else
142
+ maruku_error("We don't know about method #{handling.method.inspect}")
143
+ next
144
+ end
145
+ end
146
+
147
+
148
+ end
149
+ end
150
+
151
+ def t2_block_paragraph(src, output, signature, lines)
152
+ paragraph = lines.join("\n")
153
+ src2 = CharSource.new(paragraph, src)
154
+ # output =
155
+ end
156
+
157
+ def t2_parse_span(src, output)
158
+
159
+ end
160
+
161
+ end # MDDocument
162
+
163
+ end