Module: MarkdownIt::Common::Utils

Included in:
Parser, Renderer, Renderer, RulesBlock::Reference, RulesCore::Smartquotes, RulesInline::Emphasis, RulesInline::Entity, RulesInline::Image, RulesInline::Link, RulesInline::Strikethrough
Defined in:
lib/motion-markdown-it/common/utils.rb

Constant Summary collapse

UNESCAPE_MD_RE = 
/\\([\!\"\#\$\%\&\'\(\)\*\+\,\-.\/:;<=>?@\[\\\]^_`{|}~])/
ENTITY_RE = 
/&([a-z#][a-z0-9]{1,31});/i
UNESCAPE_ALL_RE = 
Regexp.new(UNESCAPE_MD_RE.source + '|' + ENTITY_RE.source, 'i')
DIGITAL_ENTITY_TEST_RE = 
/^#((?:x[a-f0-9]{1,8}|[0-9]{1,8}))/i
HTML_ESCAPE_TEST_RE = 
/[&<>"]/
HTML_ESCAPE_REPLACE_RE = 
/[&<>"]/
HTML_REPLACEMENTS = 
{
  '&' => '&amp;',
  '<' => '&lt;',
  '>' => '&gt;',
  '"' => '&quot;'
}
REGEXP_ESCAPE_RE = 
/[.?*+^$\[\]\\(){}|-]/
UNICODE_PUNCT_RE = 
UCMicro::Categories::P::REGEX

Instance Method Summary collapse

Instance Method Details

#arrayReplaceAt(src, pos, newElements) ⇒ Object

Remove element from array and put another array at those position. Useful for some operations with tokens



22
23
24
25
26
 
# File 'lib/motion-markdown-it/common/utils.rb', line 22

def arrayReplaceAt(src, pos, newElements)
  src[pos] = newElements
  src.flatten!(1)
  return src
end

#assign(obj, *args) ⇒ Object

Merge multiple hashes

Raises:

  • (ArgumentError) 


7
8
9
10
11
12
13
14
15
16
17
 
# File 'lib/motion-markdown-it/common/utils.rb', line 7

def assign(obj, *args)
  raise(ArgumentError, "#{obj} must be a Hash") if !obj.is_a?(Hash)

  args.each do |source|
    next if source.nil?
    raise(ArgumentError, "#{source} must be a Hash") if !source.is_a?(Hash)
    obj.merge!(source)
  end

  return obj
end

#escapeHtml(str) ⇒ Object 



105
106
107
108
109
110
 
# File 'lib/motion-markdown-it/common/utils.rb', line 105

def escapeHtml(str)
  if HTML_ESCAPE_TEST_RE =~ str
    return str.gsub(HTML_ESCAPE_REPLACE_RE, HTML_REPLACEMENTS)
  end
  return str
end

#escapeRE(str) ⇒ Object 



115
116
117
 
# File 'lib/motion-markdown-it/common/utils.rb', line 115

def escapeRE(str)
  str.gsub(REGEXP_ESCAPE_RE) {|s| '\\' + s}
end

#fromCodePoint(c) ⇒ Object 



50
51
52
 
# File 'lib/motion-markdown-it/common/utils.rb', line 50

def fromCodePoint(c)
  c.chr(Encoding::UTF_8)
end

#isMdAsciiPunct(ch) ⇒ Object

Markdown ASCII punctuation characters.

!, “, #, $, %, &, ‘, (, ), *, +, ,, -, ., /, :, ;, <, =, >, ?, @, [, , ], ^, _, `, {, |, }, or ~ spec.commonmark.org/0.15/#ascii-punctuation-character

Don’t confuse with unicode punctuation !!! It lacks some chars in ascii range.



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
 
# File 'lib/motion-markdown-it/common/utils.rb', line 157

def isMdAsciiPunct(ch)
  case ch
  when 0x21,  # !
       0x22,  # "
       0x23,  # #
       0x24,  # $
       0x25,  # %
       0x26,  # &
       0x27,  # '
       0x28,  # (
       0x29,  # )
       0x2A,  # *
       0x2B,  # +
       0x2C,  # ,
       0x2D,  # -
       0x2E,  # .
       0x2F,  # /
       0x3A,  # :
       0x3B,  # ;
       0x3C,  # <
       0x3D,  # =
       0x3E,  # >
       0x3F,  # ?
       0x40,  # @
       0x5B,  # [
       0x5C,  # \
       0x5D,  # ]
       0x5E,  # ^
       0x5F,  # _
       0x60,  # `
       0x7B,  # {
       0x7C,  # |
       0x7D,  # }
       0x7E   # ~
    return true
  else
    return false
  end
end

#isPunctChar(char) ⇒ Object

Currently without astral characters support.



145
146
147
 
# File 'lib/motion-markdown-it/common/utils.rb', line 145

def isPunctChar(char)
  return UNICODE_PUNCT_RE =~ char
end

#isValidEntityCode(c) ⇒ Object 



29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
 
# File 'lib/motion-markdown-it/common/utils.rb', line 29

def isValidEntityCode(c)
  # broken sequence
  return false if (c >= 0xD800 && c <= 0xDFFF)

  # never used
  return false if (c >= 0xFDD0 && c <= 0xFDEF)
  return false if ((c & 0xFFFF) === 0xFFFF || (c & 0xFFFF) === 0xFFFE)

  # control codes
  return false if (c >= 0x00 && c <= 0x08)
  return false if (c === 0x0B)
  return false if (c >= 0x0E && c <= 0x1F)
  return false if (c >= 0x7F && c <= 0x9F)

  # out of range
  return false if (c > 0x10FFFF)

  return true
end

#isWhiteSpace(code) ⇒ Object

Zs (unicode class) || [tfvrn]



122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
 
# File 'lib/motion-markdown-it/common/utils.rb', line 122

def isWhiteSpace(code)
  return true if (code >= 0x2000 && code <= 0x200A)
  case code
  when 0x09, # \t
       0x0A, # \n
       0x0B, # \v
       0x0C, # \f
       0x0D, # \r
       0x20,
       0xA0,
       0x1680,
       0x202F,
       0x205F,
       0x3000
    return true
  end
  return false
end

#normalizeReference(str) ⇒ Object

Hepler to unify [reference labels].



199
200
201
202
203
204
 
# File 'lib/motion-markdown-it/common/utils.rb', line 199

def normalizeReference(str)
  # use .toUpperCase() instead of .toLowerCase()
  # here to avoid a conflict with Object.prototype
  # members (most notably, `__proto__`)
  return str.strip.gsub(/\s+/, ' ').upcase
end

#replaceEntityPattern(match, name) ⇒ Object 



63
64
65
66
67
68
69
70
71
72
73
74
75
76
 
# File 'lib/motion-markdown-it/common/utils.rb', line 63

def replaceEntityPattern(match, name)
  code = 0

  return HTMLEntities::MAPPINGS[name].chr(Encoding::UTF_8) if HTMLEntities::MAPPINGS[name]

  if (name.charCodeAt(0) == 0x23 && DIGITAL_ENTITY_TEST_RE =~ name) # '#'
    code = name[1].downcase == 'x' ? name.slice_to_end(2).to_i(16) : name.slice_to_end(1).to_i
    if (isValidEntityCode(code))
      return fromCodePoint(code)
    end
  end

  return match
end

#unescapeAll(str) ⇒ Object 



85
86
87
88
89
90
91
92
 
# File 'lib/motion-markdown-it/common/utils.rb', line 85

def unescapeAll(str)
  return str if (str.index('\\').nil? && str.index('&').nil?)

  return str.gsub(UNESCAPE_ALL_RE) do |match|
    next $1 if ($1)
    next replaceEntityPattern(match, $2)
  end
end

#unescapeMd(str) ⇒ Object 



79
80
81
82
 
# File 'lib/motion-markdown-it/common/utils.rb', line 79

def unescapeMd(str)
  return str if !str.include?('\\')
  return str.gsub(UNESCAPE_MD_RE, '\1')
end