motion-kramdown 0.5.0
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.
- checksums.yaml +7 -0
- data/README.md +84 -0
- data/lib/kramdown/compatibility.rb +36 -0
- data/lib/kramdown/converter/base.rb +259 -0
- data/lib/kramdown/converter/html.rb +461 -0
- data/lib/kramdown/converter/kramdown.rb +423 -0
- data/lib/kramdown/converter/latex.rb +600 -0
- data/lib/kramdown/converter/math_engine/itex2mml.rb +39 -0
- data/lib/kramdown/converter/math_engine/mathjax.rb +33 -0
- data/lib/kramdown/converter/math_engine/ritex.rb +38 -0
- data/lib/kramdown/converter/pdf.rb +624 -0
- data/lib/kramdown/converter/remove_html_tags.rb +53 -0
- data/lib/kramdown/converter/syntax_highlighter/coderay.rb +78 -0
- data/lib/kramdown/converter/syntax_highlighter/rouge.rb +37 -0
- data/lib/kramdown/converter/toc.rb +69 -0
- data/lib/kramdown/converter.rb +69 -0
- data/lib/kramdown/document.rb +144 -0
- data/lib/kramdown/element.rb +515 -0
- data/lib/kramdown/error.rb +17 -0
- data/lib/kramdown/options.rb +584 -0
- data/lib/kramdown/parser/base.rb +130 -0
- data/lib/kramdown/parser/gfm.rb +55 -0
- data/lib/kramdown/parser/html.rb +575 -0
- data/lib/kramdown/parser/kramdown/abbreviation.rb +67 -0
- data/lib/kramdown/parser/kramdown/autolink.rb +37 -0
- data/lib/kramdown/parser/kramdown/blank_line.rb +30 -0
- data/lib/kramdown/parser/kramdown/block_boundary.rb +33 -0
- data/lib/kramdown/parser/kramdown/blockquote.rb +39 -0
- data/lib/kramdown/parser/kramdown/codeblock.rb +56 -0
- data/lib/kramdown/parser/kramdown/codespan.rb +44 -0
- data/lib/kramdown/parser/kramdown/emphasis.rb +61 -0
- data/lib/kramdown/parser/kramdown/eob.rb +26 -0
- data/lib/kramdown/parser/kramdown/escaped_chars.rb +25 -0
- data/lib/kramdown/parser/kramdown/extensions.rb +201 -0
- data/lib/kramdown/parser/kramdown/footnote.rb +56 -0
- data/lib/kramdown/parser/kramdown/header.rb +59 -0
- data/lib/kramdown/parser/kramdown/horizontal_rule.rb +27 -0
- data/lib/kramdown/parser/kramdown/html.rb +160 -0
- data/lib/kramdown/parser/kramdown/html_entity.rb +33 -0
- data/lib/kramdown/parser/kramdown/line_break.rb +25 -0
- data/lib/kramdown/parser/kramdown/link.rb +139 -0
- data/lib/kramdown/parser/kramdown/list.rb +256 -0
- data/lib/kramdown/parser/kramdown/math.rb +54 -0
- data/lib/kramdown/parser/kramdown/paragraph.rb +54 -0
- data/lib/kramdown/parser/kramdown/smart_quotes.rb +174 -0
- data/lib/kramdown/parser/kramdown/table.rb +171 -0
- data/lib/kramdown/parser/kramdown/typographic_symbol.rb +44 -0
- data/lib/kramdown/parser/kramdown.rb +359 -0
- data/lib/kramdown/parser/markdown.rb +56 -0
- data/lib/kramdown/parser.rb +27 -0
- data/lib/kramdown/utils/configurable.rb +44 -0
- data/lib/kramdown/utils/entities.rb +347 -0
- data/lib/kramdown/utils/html.rb +75 -0
- data/lib/kramdown/utils/ordered_hash.rb +87 -0
- data/lib/kramdown/utils/string_scanner.rb +74 -0
- data/lib/kramdown/utils/unidecoder.rb +51 -0
- data/lib/kramdown/utils.rb +58 -0
- data/lib/kramdown/version.rb +15 -0
- data/lib/kramdown.rb +10 -0
- data/lib/motion-kramdown.rb +47 -0
- data/lib/rubymotion/encodings.rb +37 -0
- data/lib/rubymotion/rexml_shim.rb +25 -0
- data/lib/rubymotion/set.rb +1349 -0
- data/lib/rubymotion/version.rb +6 -0
- data/spec/document_tree.rb +48 -0
- data/spec/gfm_to_html.rb +95 -0
- data/spec/helpers/it_behaves_like.rb +27 -0
- data/spec/helpers/option_file.rb +46 -0
- data/spec/helpers/spec_options.rb +37 -0
- data/spec/helpers/tidy.rb +12 -0
- data/spec/html_to_html.rb +40 -0
- data/spec/html_to_kramdown_to_html.rb +46 -0
- data/spec/kramdown_to_xxx.rb +40 -0
- data/spec/test_location.rb +203 -0
- data/spec/test_string_scanner_kramdown.rb +19 -0
- data/spec/text_to_kramdown_to_html.rb +52 -0
- data/spec/text_to_latex.rb +33 -0
- metadata +164 -0
@@ -0,0 +1,55 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
|
3
|
+
# RM require 'kramdown/parser/kramdown'
|
4
|
+
|
5
|
+
module Kramdown
|
6
|
+
module Parser
|
7
|
+
class GFM < Kramdown::Parser::Kramdown
|
8
|
+
|
9
|
+
def initialize(source, options)
|
10
|
+
super
|
11
|
+
@span_parsers.delete(:line_break) if @options[:hard_wrap]
|
12
|
+
{:codeblock_fenced => :codeblock_fenced_gfm,
|
13
|
+
:atx_header => :atx_header_gfm}.each do |current, replacement|
|
14
|
+
i = @block_parsers.index(current)
|
15
|
+
@block_parsers.delete(current)
|
16
|
+
@block_parsers.insert(i, replacement)
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
def parse
|
21
|
+
super
|
22
|
+
add_hard_line_breaks(@root) if @options[:hard_wrap]
|
23
|
+
end
|
24
|
+
|
25
|
+
def add_hard_line_breaks(element)
|
26
|
+
element.children.map! do |child|
|
27
|
+
if child.type == :text && child.value =~ /\n/
|
28
|
+
children = []
|
29
|
+
lines = child.value.split(/\n/, -1)
|
30
|
+
omit_trailing_br = (Kramdown::Element.category(element) == :block && element.children[-1] == child &&
|
31
|
+
lines[-1].empty?)
|
32
|
+
lines.each_with_index do |line, index|
|
33
|
+
children << Element.new(:text, (index > 0 ? "\n#{line}" : line))
|
34
|
+
children << Element.new(:br) if index < lines.size - 2 ||
|
35
|
+
(index == lines.size - 2 && !omit_trailing_br)
|
36
|
+
end
|
37
|
+
children
|
38
|
+
elsif child.type == :html_element
|
39
|
+
child
|
40
|
+
else
|
41
|
+
add_hard_line_breaks(child)
|
42
|
+
child
|
43
|
+
end
|
44
|
+
end.flatten!
|
45
|
+
end
|
46
|
+
|
47
|
+
ATX_HEADER_START = /^\#{1,6}\s/
|
48
|
+
define_parser(:atx_header_gfm, ATX_HEADER_START, nil, 'parse_atx_header')
|
49
|
+
|
50
|
+
FENCED_CODEBLOCK_MATCH = /^(([~`]){3,})\s*?(\w+)?\s*?\n(.*?)^\1\2*\s*?\n/m
|
51
|
+
define_parser(:codeblock_fenced_gfm, /^[~`]{3,}/, nil, 'parse_codeblock_fenced')
|
52
|
+
|
53
|
+
end
|
54
|
+
end
|
55
|
+
end
|
@@ -0,0 +1,575 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
#
|
3
|
+
#--
|
4
|
+
# Copyright (C) 2009-2014 Thomas Leitner <t_leitner@gmx.at>
|
5
|
+
#
|
6
|
+
# This file is part of kramdown which is licensed under the MIT.
|
7
|
+
#++
|
8
|
+
#
|
9
|
+
|
10
|
+
# RM require 'rexml/parsers/baseparser'
|
11
|
+
# RM require 'strscan'
|
12
|
+
# RM require 'kramdown/utils'
|
13
|
+
|
14
|
+
module Kramdown
|
15
|
+
|
16
|
+
module Parser
|
17
|
+
|
18
|
+
# Used for parsing a HTML document.
|
19
|
+
#
|
20
|
+
# The parsing code is in the Parser module that can also be used by other parsers.
|
21
|
+
class Html < Base
|
22
|
+
|
23
|
+
# Contains all constants that are used when parsing.
|
24
|
+
module Constants
|
25
|
+
|
26
|
+
#:stopdoc:
|
27
|
+
# The following regexps are based on the ones used by REXML, with some slight modifications.
|
28
|
+
HTML_DOCTYPE_RE = /<!DOCTYPE.*?>/im
|
29
|
+
HTML_COMMENT_RE = /<!--(.*?)-->/m
|
30
|
+
HTML_INSTRUCTION_RE = /<\?(.*?)\?>/m
|
31
|
+
HTML_ATTRIBUTE_RE = /\s*(#{REXML::Parsers::BaseParser::UNAME_STR})(?:\s*=\s*(["'])(.*?)\2)?/m
|
32
|
+
HTML_TAG_RE = /<((?>#{REXML::Parsers::BaseParser::UNAME_STR}))\s*((?>\s+#{REXML::Parsers::BaseParser::UNAME_STR}(?:\s*=\s*(["']).*?\3)?)*)\s*(\/)?>/m
|
33
|
+
HTML_TAG_CLOSE_RE = /<\/(#{REXML::Parsers::BaseParser::UNAME_STR})\s*>/m
|
34
|
+
HTML_ENTITY_RE = /&([\w:][\-\w\.:]*);|&#(\d+);|&\#x([0-9a-fA-F]+);/
|
35
|
+
|
36
|
+
HTML_CONTENT_MODEL_BLOCK = %w{address applet article aside blockquote body
|
37
|
+
dd details div dl fieldset figure figcaption footer form header hgroup iframe li map menu nav
|
38
|
+
noscript object section summary td}
|
39
|
+
HTML_CONTENT_MODEL_SPAN = %w{a abbr acronym b bdo big button cite caption del dfn dt em
|
40
|
+
h1 h2 h3 h4 h5 h6 i ins label legend optgroup p q rb rbc
|
41
|
+
rp rt rtc ruby select small span strong sub sup th tt}
|
42
|
+
HTML_CONTENT_MODEL_RAW = %w{script style math option textarea pre code kbd samp var}
|
43
|
+
# The following elements are also parsed as raw since they need child elements that cannot
|
44
|
+
# be expressed using kramdown syntax: colgroup table tbody thead tfoot tr ul ol
|
45
|
+
|
46
|
+
HTML_CONTENT_MODEL = Hash.new {|h,k| h[k] = :raw}
|
47
|
+
HTML_CONTENT_MODEL_BLOCK.each {|i| HTML_CONTENT_MODEL[i] = :block}
|
48
|
+
HTML_CONTENT_MODEL_SPAN.each {|i| HTML_CONTENT_MODEL[i] = :span}
|
49
|
+
HTML_CONTENT_MODEL_RAW.each {|i| HTML_CONTENT_MODEL[i] = :raw}
|
50
|
+
|
51
|
+
# Some HTML elements like script belong to both categories (i.e. are valid in block and
|
52
|
+
# span HTML) and don't appear therefore!
|
53
|
+
# script, textarea
|
54
|
+
HTML_SPAN_ELEMENTS = %w{a abbr acronym b big bdo br button cite code del dfn em i img input
|
55
|
+
ins kbd label option q rb rbc rp rt rtc ruby samp select small span
|
56
|
+
strong sub sup tt u var}
|
57
|
+
HTML_BLOCK_ELEMENTS = %w{address article aside applet body blockquote caption col colgroup dd div dl dt fieldset
|
58
|
+
figcaption footer form h1 h2 h3 h4 h5 h6 header hgroup hr html head iframe legend menu
|
59
|
+
li map nav ol optgroup p pre section summary table tbody td th thead tfoot tr ul}
|
60
|
+
HTML_ELEMENTS_WITHOUT_BODY = %w{area base br col command embed hr img input keygen link meta param source track wbr}
|
61
|
+
end
|
62
|
+
|
63
|
+
|
64
|
+
# Contains the parsing methods. This module can be mixed into any parser to get HTML parsing
|
65
|
+
# functionality. The only thing that must be provided by the class are instance variable
|
66
|
+
# @stack for storing the needed state and @src (instance of StringScanner) for the actual
|
67
|
+
# parsing.
|
68
|
+
module Parser
|
69
|
+
|
70
|
+
include Constants
|
71
|
+
|
72
|
+
# Process the HTML start tag that has already be scanned/checked via @src.
|
73
|
+
#
|
74
|
+
# Does the common processing steps and then yields to the caller for further processing
|
75
|
+
# (first parameter is the created element; the second parameter is +true+ if the HTML
|
76
|
+
# element is already closed, ie. contains no body; the third parameter specifies whether the
|
77
|
+
# body - and the end tag - need to be handled in case closed=false).
|
78
|
+
def handle_html_start_tag(line = nil) # :yields: el, closed, handle_body
|
79
|
+
name = @src[1].downcase
|
80
|
+
closed = !@src[4].nil?
|
81
|
+
attrs = Utils::OrderedHash.new
|
82
|
+
@src[2].scan(HTML_ATTRIBUTE_RE).each {|attr,sep,val| attrs[attr.downcase] = val || ""}
|
83
|
+
|
84
|
+
el = Element.new(:html_element, name, attrs, :category => :block)
|
85
|
+
el.options[:location] = line if line
|
86
|
+
@tree.children << el
|
87
|
+
|
88
|
+
if !closed && HTML_ELEMENTS_WITHOUT_BODY.include?(el.value)
|
89
|
+
warning("The HTML tag '#{el.value}' on line #{line} cannot have any content - auto-closing it")
|
90
|
+
closed = true
|
91
|
+
end
|
92
|
+
if name == 'script' || name == 'style'
|
93
|
+
handle_raw_html_tag(name)
|
94
|
+
yield(el, false, false)
|
95
|
+
else
|
96
|
+
yield(el, closed, true)
|
97
|
+
end
|
98
|
+
end
|
99
|
+
|
100
|
+
# Handle the raw HTML tag at the current position.
|
101
|
+
def handle_raw_html_tag(name)
|
102
|
+
curpos = @src.pos
|
103
|
+
if @src.scan_until(/(?=<\/#{name}\s*>)/mi)
|
104
|
+
add_text(extract_string(curpos...@src.pos, @src), @tree.children.last, :raw)
|
105
|
+
@src.scan(HTML_TAG_CLOSE_RE)
|
106
|
+
else
|
107
|
+
add_text(@src.rest, @tree.children.last, :raw)
|
108
|
+
@src.terminate
|
109
|
+
warning("Found no end tag for '#{name}' - auto-closing it")
|
110
|
+
end
|
111
|
+
end
|
112
|
+
|
113
|
+
HTML_RAW_START = /(?=<(#{REXML::Parsers::BaseParser::UNAME_STR}|\/|!--|\?))/ # :nodoc:
|
114
|
+
|
115
|
+
# Parse raw HTML from the current source position, storing the found elements in +el+.
|
116
|
+
# Parsing continues until one of the following criteria are fulfilled:
|
117
|
+
#
|
118
|
+
# - The end of the document is reached.
|
119
|
+
# - The matching end tag for the element +el+ is found (only used if +el+ is an HTML
|
120
|
+
# element).
|
121
|
+
#
|
122
|
+
# When an HTML start tag is found, processing is deferred to #handle_html_start_tag,
|
123
|
+
# providing the block given to this method.
|
124
|
+
def parse_raw_html(el, &block)
|
125
|
+
@stack.push(@tree)
|
126
|
+
@tree = el
|
127
|
+
|
128
|
+
done = false
|
129
|
+
while !@src.eos? && !done
|
130
|
+
if result = @src.scan_until(HTML_RAW_START)
|
131
|
+
add_text(result, @tree, :text)
|
132
|
+
line = @src.current_line_number
|
133
|
+
if result = @src.scan(HTML_COMMENT_RE)
|
134
|
+
@tree.children << Element.new(:xml_comment, result, nil, :category => :block, :location => line)
|
135
|
+
elsif result = @src.scan(HTML_INSTRUCTION_RE)
|
136
|
+
@tree.children << Element.new(:xml_pi, result, nil, :category => :block, :location => line)
|
137
|
+
elsif @src.scan(HTML_TAG_RE)
|
138
|
+
if method(:handle_html_start_tag).arity == 1
|
139
|
+
handle_html_start_tag(line, &block)
|
140
|
+
else
|
141
|
+
handle_html_start_tag(&block) # DEPRECATED: method needs to accept line number in 2.0
|
142
|
+
end
|
143
|
+
elsif @src.scan(HTML_TAG_CLOSE_RE)
|
144
|
+
if @tree.value == @src[1].downcase
|
145
|
+
done = true
|
146
|
+
else
|
147
|
+
warning("Found invalidly used HTML closing tag for '#{@src[1].downcase}' on line #{line} - ignoring it")
|
148
|
+
end
|
149
|
+
else
|
150
|
+
add_text(@src.getch, @tree, :text)
|
151
|
+
end
|
152
|
+
else
|
153
|
+
add_text(@src.rest, @tree, :text)
|
154
|
+
@src.terminate
|
155
|
+
warning("Found no end tag for '#{@tree.value}' on line #{@tree.options[:location]} - auto-closing it") if @tree.type == :html_element
|
156
|
+
done = true
|
157
|
+
end
|
158
|
+
end
|
159
|
+
|
160
|
+
@tree = @stack.pop
|
161
|
+
end
|
162
|
+
|
163
|
+
end
|
164
|
+
|
165
|
+
|
166
|
+
# Converts HTML elements to native elements if possible.
|
167
|
+
class ElementConverter
|
168
|
+
|
169
|
+
# :stopdoc:
|
170
|
+
|
171
|
+
include Constants
|
172
|
+
include ::Kramdown::Utils::Entities
|
173
|
+
|
174
|
+
REMOVE_TEXT_CHILDREN = %w{html head hgroup ol ul dl table colgroup tbody thead tfoot tr select optgroup}
|
175
|
+
WRAP_TEXT_CHILDREN = %w{body section nav article aside header footer address div li dd blockquote figure
|
176
|
+
figcaption fieldset form}
|
177
|
+
REMOVE_WHITESPACE_CHILDREN = %w{body section nav article aside header footer address
|
178
|
+
div li dd blockquote figure figcaption td th fieldset form}
|
179
|
+
STRIP_WHITESPACE = %w{address article aside blockquote body caption dd div dl dt fieldset figcaption form footer
|
180
|
+
header h1 h2 h3 h4 h5 h6 legend li nav p section td th}
|
181
|
+
SIMPLE_ELEMENTS = %w{em strong blockquote hr br img p thead tbody tfoot tr td th ul ol dl li dl dt dd}
|
182
|
+
|
183
|
+
def initialize(root)
|
184
|
+
@root = root
|
185
|
+
end
|
186
|
+
|
187
|
+
def self.convert(root, el = root)
|
188
|
+
new(root).process(el)
|
189
|
+
end
|
190
|
+
|
191
|
+
# Convert the element +el+ and its children.
|
192
|
+
def process(el, do_conversion = true, preserve_text = false, parent = nil)
|
193
|
+
case el.type
|
194
|
+
when :xml_comment, :xml_pi
|
195
|
+
ptype = if parent.nil?
|
196
|
+
'div'
|
197
|
+
else
|
198
|
+
case parent.type
|
199
|
+
when :html_element then parent.value
|
200
|
+
when :code_span then 'code'
|
201
|
+
when :code_block then 'pre'
|
202
|
+
when :header then 'h1'
|
203
|
+
else parent.type.to_s
|
204
|
+
end
|
205
|
+
end
|
206
|
+
el.options.replace({:category => (HTML_CONTENT_MODEL[ptype] == :span ? :span : :block)})
|
207
|
+
return
|
208
|
+
when :html_element
|
209
|
+
when :root
|
210
|
+
el.children.each {|c| process(c)}
|
211
|
+
remove_whitespace_children(el)
|
212
|
+
return
|
213
|
+
else return
|
214
|
+
end
|
215
|
+
|
216
|
+
mname = "convert_#{el.value}"
|
217
|
+
if do_conversion && self.class.method_defined?(mname)
|
218
|
+
send(mname, el)
|
219
|
+
else
|
220
|
+
type = el.value
|
221
|
+
remove_text_children(el) if do_conversion && REMOVE_TEXT_CHILDREN.include?(type)
|
222
|
+
|
223
|
+
if do_conversion && SIMPLE_ELEMENTS.include?(type)
|
224
|
+
set_basics(el, type.intern)
|
225
|
+
process_children(el, do_conversion, preserve_text)
|
226
|
+
else
|
227
|
+
process_html_element(el, do_conversion, preserve_text)
|
228
|
+
end
|
229
|
+
|
230
|
+
if do_conversion
|
231
|
+
strip_whitespace(el) if STRIP_WHITESPACE.include?(type)
|
232
|
+
remove_whitespace_children(el) if REMOVE_WHITESPACE_CHILDREN.include?(type)
|
233
|
+
wrap_text_children(el) if WRAP_TEXT_CHILDREN.include?(type)
|
234
|
+
end
|
235
|
+
end
|
236
|
+
end
|
237
|
+
|
238
|
+
def process_children(el, do_conversion = true, preserve_text = false)
|
239
|
+
el.children.map! do |c|
|
240
|
+
if c.type == :text
|
241
|
+
process_text(c.value, preserve_text || !do_conversion)
|
242
|
+
else
|
243
|
+
process(c, do_conversion, preserve_text, el)
|
244
|
+
c
|
245
|
+
end
|
246
|
+
end.flatten!
|
247
|
+
end
|
248
|
+
|
249
|
+
# Process the HTML text +raw+: compress whitespace (if +preserve+ is +false+) and convert
|
250
|
+
# entities in entity elements.
|
251
|
+
def process_text(raw, preserve = false)
|
252
|
+
raw.gsub!(/\s+/, ' ') unless preserve
|
253
|
+
src = Kramdown::Utils::StringScanner.new(raw)
|
254
|
+
result = []
|
255
|
+
while !src.eos?
|
256
|
+
if tmp = src.scan_until(/(?=#{HTML_ENTITY_RE})/)
|
257
|
+
result << Element.new(:text, tmp)
|
258
|
+
src.scan(HTML_ENTITY_RE)
|
259
|
+
val = src[1] || (src[2] && src[2].to_i) || src[3].hex
|
260
|
+
result << if %w{lsquo rsquo ldquo rdquo}.include?(val)
|
261
|
+
Element.new(:smart_quote, val.intern)
|
262
|
+
elsif %w{mdash ndash hellip laquo raquo}.include?(val)
|
263
|
+
Element.new(:typographic_sym, val.intern)
|
264
|
+
else
|
265
|
+
begin
|
266
|
+
Element.new(:entity, entity(val), nil, :original => src.matched)
|
267
|
+
rescue ::Kramdown::Error
|
268
|
+
src.pos -= src.matched_size - 1
|
269
|
+
Element.new(:entity, ::Kramdown::Utils::Entities.entity('amp'))
|
270
|
+
end
|
271
|
+
end
|
272
|
+
else
|
273
|
+
result << Element.new(:text, src.rest)
|
274
|
+
src.terminate
|
275
|
+
end
|
276
|
+
end
|
277
|
+
result
|
278
|
+
end
|
279
|
+
|
280
|
+
def process_html_element(el, do_conversion = true, preserve_text = false)
|
281
|
+
el.options.replace(:category => HTML_SPAN_ELEMENTS.include?(el.value) ? :span : :block,
|
282
|
+
:content_model => (do_conversion ? HTML_CONTENT_MODEL[el.value] : :raw))
|
283
|
+
process_children(el, do_conversion, preserve_text)
|
284
|
+
end
|
285
|
+
|
286
|
+
def remove_text_children(el)
|
287
|
+
el.children.delete_if {|c| c.type == :text}
|
288
|
+
end
|
289
|
+
|
290
|
+
def wrap_text_children(el)
|
291
|
+
tmp = []
|
292
|
+
last_is_p = false
|
293
|
+
el.children.each do |c|
|
294
|
+
if Element.category(c) != :block || c.type == :text
|
295
|
+
if !last_is_p
|
296
|
+
tmp << Element.new(:p, nil, nil, :transparent => true)
|
297
|
+
last_is_p = true
|
298
|
+
end
|
299
|
+
tmp.last.children << c
|
300
|
+
tmp
|
301
|
+
else
|
302
|
+
tmp << c
|
303
|
+
last_is_p = false
|
304
|
+
end
|
305
|
+
end
|
306
|
+
el.children = tmp
|
307
|
+
end
|
308
|
+
|
309
|
+
def strip_whitespace(el)
|
310
|
+
return if el.children.empty?
|
311
|
+
if el.children.first.type == :text
|
312
|
+
el.children.first.value.lstrip!
|
313
|
+
end
|
314
|
+
if el.children.last.type == :text
|
315
|
+
el.children.last.value.rstrip!
|
316
|
+
end
|
317
|
+
end
|
318
|
+
|
319
|
+
def remove_whitespace_children(el)
|
320
|
+
i = -1
|
321
|
+
el.children = el.children.reject do |c|
|
322
|
+
i += 1
|
323
|
+
c.type == :text && c.value.strip.empty? &&
|
324
|
+
(i == 0 || i == el.children.length - 1 || (Element.category(el.children[i-1]) == :block &&
|
325
|
+
Element.category(el.children[i+1]) == :block))
|
326
|
+
end
|
327
|
+
end
|
328
|
+
|
329
|
+
def set_basics(el, type, opts = {})
|
330
|
+
el.type = type
|
331
|
+
el.options.replace(opts)
|
332
|
+
el.value = nil
|
333
|
+
end
|
334
|
+
|
335
|
+
def extract_text(el, raw)
|
336
|
+
raw << el.value.to_s if el.type == :text
|
337
|
+
el.children.each {|c| extract_text(c, raw)}
|
338
|
+
end
|
339
|
+
|
340
|
+
def convert_textarea(el)
|
341
|
+
process_html_element(el, true, true)
|
342
|
+
end
|
343
|
+
|
344
|
+
def convert_a(el)
|
345
|
+
if el.attr['href']
|
346
|
+
set_basics(el, :a)
|
347
|
+
process_children(el)
|
348
|
+
else
|
349
|
+
process_html_element(el, false)
|
350
|
+
end
|
351
|
+
end
|
352
|
+
|
353
|
+
EMPHASIS_TYPE_MAP = {'em' => :em, 'i' => :em, 'strong' => :strong, 'b' => :strong}
|
354
|
+
def convert_em(el)
|
355
|
+
text = ''
|
356
|
+
extract_text(el, text)
|
357
|
+
if text =~ /\A\s/ || text =~ /\s\z/
|
358
|
+
process_html_element(el, false)
|
359
|
+
else
|
360
|
+
set_basics(el, EMPHASIS_TYPE_MAP[el.value])
|
361
|
+
process_children(el)
|
362
|
+
end
|
363
|
+
end
|
364
|
+
%w{b strong i}.each do |i|
|
365
|
+
alias_method("convert_#{i}".to_sym, :convert_em)
|
366
|
+
end
|
367
|
+
|
368
|
+
def convert_h1(el)
|
369
|
+
set_basics(el, :header, :level => el.value[1..1].to_i)
|
370
|
+
extract_text(el, el.options[:raw_text] = '')
|
371
|
+
process_children(el)
|
372
|
+
end
|
373
|
+
%w{h2 h3 h4 h5 h6}.each do |i|
|
374
|
+
alias_method("convert_#{i}".to_sym, :convert_h1)
|
375
|
+
end
|
376
|
+
|
377
|
+
def convert_code(el)
|
378
|
+
raw = ''
|
379
|
+
extract_text(el, raw)
|
380
|
+
result = process_text(raw, true)
|
381
|
+
begin
|
382
|
+
str = result.inject('') do |mem, c|
|
383
|
+
if c.type == :text
|
384
|
+
mem << c.value
|
385
|
+
elsif c.type == :entity
|
386
|
+
if [60, 62, 34, 38].include?(c.value.code_point)
|
387
|
+
mem << c.value.code_point.chr
|
388
|
+
else
|
389
|
+
mem << c.value.char
|
390
|
+
end
|
391
|
+
elsif c.type == :smart_quote || c.type == :typographic_sym
|
392
|
+
mem << entity(c.value.to_s).char
|
393
|
+
else
|
394
|
+
raise "Bug - please report"
|
395
|
+
end
|
396
|
+
end
|
397
|
+
result.clear
|
398
|
+
result << Element.new(:text, str)
|
399
|
+
rescue
|
400
|
+
end
|
401
|
+
if result.length > 1 || result.first.type != :text
|
402
|
+
process_html_element(el, false, true)
|
403
|
+
else
|
404
|
+
if el.value == 'code'
|
405
|
+
set_basics(el, :codespan)
|
406
|
+
el.attr['class'].gsub!(/\s+\bhighlighter-\w+\b|\bhighlighter-\w+\b\s*/, '') if el.attr['class']
|
407
|
+
else
|
408
|
+
set_basics(el, :codeblock)
|
409
|
+
if el.children.size == 1 && el.children.first.value == 'code'
|
410
|
+
value = (el.children.first.attr['class'] || '').scan(/\blanguage-\w+\b/).first
|
411
|
+
el.attr['class'] = "#{value} #{el.attr['class']}".rstrip if value
|
412
|
+
end
|
413
|
+
end
|
414
|
+
el.value = result.first.value
|
415
|
+
el.children.clear
|
416
|
+
end
|
417
|
+
end
|
418
|
+
alias :convert_pre :convert_code
|
419
|
+
|
420
|
+
def convert_table(el)
|
421
|
+
if !is_simple_table?(el)
|
422
|
+
process_html_element(el, false)
|
423
|
+
return
|
424
|
+
end
|
425
|
+
remove_text_children(el)
|
426
|
+
process_children(el)
|
427
|
+
set_basics(el, :table)
|
428
|
+
|
429
|
+
calc_alignment = lambda do |c|
|
430
|
+
if c.type == :tr
|
431
|
+
el.options[:alignment] = c.children.map do |td|
|
432
|
+
if td.attr['style']
|
433
|
+
td.attr['style'].slice!(/(?:;\s*)?text-align:\s+(center|left|right)/)
|
434
|
+
td.attr.delete('style') if td.attr['style'].strip.empty?
|
435
|
+
$1 ? $1.to_sym : :default
|
436
|
+
else
|
437
|
+
:default
|
438
|
+
end
|
439
|
+
end
|
440
|
+
else
|
441
|
+
c.children.each {|cc| calc_alignment.call(cc)}
|
442
|
+
end
|
443
|
+
end
|
444
|
+
calc_alignment.call(el)
|
445
|
+
el.children.delete_if {|c| c.type == :html_element}
|
446
|
+
|
447
|
+
change_th_type = lambda do |c|
|
448
|
+
if c.type == :th
|
449
|
+
c.type = :td
|
450
|
+
else
|
451
|
+
c.children.each {|cc| change_th_type.call(cc)}
|
452
|
+
end
|
453
|
+
end
|
454
|
+
change_th_type.call(el)
|
455
|
+
|
456
|
+
if el.children.first.type == :tr
|
457
|
+
tbody = Element.new(:tbody)
|
458
|
+
tbody.children = el.children
|
459
|
+
el.children = [tbody]
|
460
|
+
end
|
461
|
+
end
|
462
|
+
|
463
|
+
def is_simple_table?(el)
|
464
|
+
only_phrasing_content = lambda do |c|
|
465
|
+
c.children.all? do |cc|
|
466
|
+
(cc.type == :text || !HTML_BLOCK_ELEMENTS.include?(cc.value)) && only_phrasing_content.call(cc)
|
467
|
+
end
|
468
|
+
end
|
469
|
+
check_cells = Proc.new do |c|
|
470
|
+
if c.value == 'th' || c.value == 'td'
|
471
|
+
return false if !only_phrasing_content.call(c)
|
472
|
+
else
|
473
|
+
c.children.each {|cc| check_cells.call(cc)}
|
474
|
+
end
|
475
|
+
end
|
476
|
+
check_cells.call(el)
|
477
|
+
|
478
|
+
nr_cells = 0
|
479
|
+
check_nr_cells = lambda do |t|
|
480
|
+
if t.value == 'tr'
|
481
|
+
count = t.children.select {|cc| cc.value == 'th' || cc.value == 'td'}.length
|
482
|
+
if count != nr_cells
|
483
|
+
if nr_cells == 0
|
484
|
+
nr_cells = count
|
485
|
+
else
|
486
|
+
nr_cells = -1
|
487
|
+
break
|
488
|
+
end
|
489
|
+
end
|
490
|
+
else
|
491
|
+
t.children.each {|cc| check_nr_cells.call(cc)}
|
492
|
+
end
|
493
|
+
end
|
494
|
+
check_nr_cells.call(el)
|
495
|
+
return false if nr_cells == -1
|
496
|
+
|
497
|
+
alignment = nil
|
498
|
+
check_alignment = Proc.new do |t|
|
499
|
+
if t.value == 'tr'
|
500
|
+
cur_alignment = t.children.select {|cc| cc.value == 'th' || cc.value == 'td'}.map do |cell|
|
501
|
+
md = /text-align:\s+(center|left|right|justify|inherit)/.match(cell.attr['style'].to_s)
|
502
|
+
return false if md && (md[1] == 'justify' || md[1] == 'inherit')
|
503
|
+
md.nil? ? :default : md[1]
|
504
|
+
end
|
505
|
+
alignment = cur_alignment if alignment.nil?
|
506
|
+
return false if alignment != cur_alignment
|
507
|
+
else
|
508
|
+
t.children.each {|cc| check_alignment.call(cc)}
|
509
|
+
end
|
510
|
+
end
|
511
|
+
check_alignment.call(el)
|
512
|
+
|
513
|
+
check_rows = lambda do |t, type|
|
514
|
+
t.children.all? {|r| (r.value == 'tr' || r.type == :text) && r.children.all? {|c| c.value == type || c.type == :text}}
|
515
|
+
end
|
516
|
+
check_rows.call(el, 'td') ||
|
517
|
+
(el.children.all? do |t|
|
518
|
+
t.type == :text || (t.value == 'thead' && check_rows.call(t, 'th')) ||
|
519
|
+
((t.value == 'tfoot' || t.value == 'tbody') && check_rows.call(t, 'td'))
|
520
|
+
end && el.children.any? {|t| t.value == 'tbody'})
|
521
|
+
end
|
522
|
+
|
523
|
+
def convert_script(el)
|
524
|
+
if !is_math_tag?(el)
|
525
|
+
process_html_element(el)
|
526
|
+
else
|
527
|
+
handle_math_tag(el)
|
528
|
+
end
|
529
|
+
end
|
530
|
+
|
531
|
+
def is_math_tag?(el)
|
532
|
+
el.attr['type'].to_s =~ /\bmath\/tex\b/
|
533
|
+
end
|
534
|
+
|
535
|
+
def handle_math_tag(el)
|
536
|
+
set_basics(el, :math, :category => (el.attr['type'] =~ /mode=display/ ? :block : :span))
|
537
|
+
el.value = el.children.shift.value.sub(/\A(?:%\s*)?<!\[CDATA\[\n?(.*?)(?:\s%)?\]\]>\z/m, '\1')
|
538
|
+
el.attr.delete('type')
|
539
|
+
end
|
540
|
+
|
541
|
+
end
|
542
|
+
|
543
|
+
include Parser
|
544
|
+
|
545
|
+
# Parse the source string provided on initialization as HTML document.
|
546
|
+
def parse
|
547
|
+
@stack, @tree = [], @root
|
548
|
+
@src = Kramdown::Utils::StringScanner.new(adapt_source(source))
|
549
|
+
|
550
|
+
while true
|
551
|
+
if result = @src.scan(/\s*#{HTML_INSTRUCTION_RE}/)
|
552
|
+
@tree.children << Element.new(:xml_pi, result.strip, nil, :category => :block)
|
553
|
+
elsif result = @src.scan(/\s*#{HTML_DOCTYPE_RE}/)
|
554
|
+
# ignore the doctype
|
555
|
+
elsif result = @src.scan(/\s*#{HTML_COMMENT_RE}/)
|
556
|
+
@tree.children << Element.new(:xml_comment, result.strip, nil, :category => :block)
|
557
|
+
else
|
558
|
+
break
|
559
|
+
end
|
560
|
+
end
|
561
|
+
|
562
|
+
tag_handler = lambda do |c, closed, handle_body|
|
563
|
+
parse_raw_html(c, &tag_handler) if !closed && handle_body
|
564
|
+
end
|
565
|
+
parse_raw_html(@tree, &tag_handler)
|
566
|
+
|
567
|
+
ElementConverter.convert(@tree)
|
568
|
+
end
|
569
|
+
|
570
|
+
end
|
571
|
+
|
572
|
+
end
|
573
|
+
|
574
|
+
end
|
575
|
+
|
@@ -0,0 +1,67 @@
|
|
1
|
+
# -*- coding: utf-8 -*-
|
2
|
+
#
|
3
|
+
#--
|
4
|
+
# Copyright (C) 2009-2014 Thomas Leitner <t_leitner@gmx.at>
|
5
|
+
#
|
6
|
+
# This file is part of kramdown which is licensed under the MIT.
|
7
|
+
#++
|
8
|
+
#
|
9
|
+
|
10
|
+
module Kramdown
|
11
|
+
module Parser
|
12
|
+
class Kramdown
|
13
|
+
|
14
|
+
ABBREV_DEFINITION_START = /^#{OPT_SPACE}\*\[(.+?)\]:(.*?)\n/
|
15
|
+
|
16
|
+
# Parse the link definition at the current location.
|
17
|
+
def parse_abbrev_definition
|
18
|
+
start_line_number = @src.current_line_number
|
19
|
+
@src.pos += @src.matched_size
|
20
|
+
abbrev_id, abbrev_text = @src[1], @src[2]
|
21
|
+
abbrev_text.strip!
|
22
|
+
warning("Duplicate abbreviation ID '#{abbrev_id}' on line #{start_line_number} - overwriting") if @root.options[:abbrev_defs][abbrev_id]
|
23
|
+
@root.options[:abbrev_defs][abbrev_id] = abbrev_text
|
24
|
+
@tree.children << Element.new(:eob, :abbrev_def)
|
25
|
+
true
|
26
|
+
end
|
27
|
+
define_parser(:abbrev_definition, ABBREV_DEFINITION_START)
|
28
|
+
|
29
|
+
# Replace the abbreviation text with elements.
|
30
|
+
def replace_abbreviations(el, regexps = nil)
|
31
|
+
return if @root.options[:abbrev_defs].empty?
|
32
|
+
if !regexps
|
33
|
+
sorted_abbrevs = @root.options[:abbrev_defs].keys.sort {|a,b| b.length <=> a.length}
|
34
|
+
regexps = [Regexp.union(*sorted_abbrevs.map {|k| /#{Regexp.escape(k)}/})]
|
35
|
+
regexps << /(?=(?:\W|^)#{regexps.first}(?!\w))/ # regexp should only match on word boundaries
|
36
|
+
end
|
37
|
+
el.children.map! do |child|
|
38
|
+
if child.type == :text
|
39
|
+
if child.value =~ regexps.first
|
40
|
+
result = []
|
41
|
+
strscan = Kramdown::Utils::StringScanner.new(child.value, child.options[:location])
|
42
|
+
text_lineno = strscan.current_line_number
|
43
|
+
while temp = strscan.scan_until(regexps.last)
|
44
|
+
abbr_lineno = strscan.current_line_number
|
45
|
+
abbr = strscan.scan(regexps.first) # begin of line case of abbr with \W char as first one
|
46
|
+
if abbr.nil?
|
47
|
+
temp << strscan.scan(/\W|^/)
|
48
|
+
abbr = strscan.scan(regexps.first)
|
49
|
+
end
|
50
|
+
result << Element.new(:text, temp, nil, :location => text_lineno)
|
51
|
+
result << Element.new(:abbreviation, abbr, nil, :location => abbr_lineno)
|
52
|
+
text_lineno = strscan.current_line_number
|
53
|
+
end
|
54
|
+
result << Element.new(:text, strscan.rest, nil, :location => text_lineno)
|
55
|
+
else
|
56
|
+
child
|
57
|
+
end
|
58
|
+
else
|
59
|
+
replace_abbreviations(child, regexps)
|
60
|
+
child
|
61
|
+
end
|
62
|
+
end.flatten!
|
63
|
+
end
|
64
|
+
|
65
|
+
end
|
66
|
+
end
|
67
|
+
end
|