Module: ActiveSupport::Multibyte::Unicode

Extended by:
Unicode
Included in:
Unicode
Defined in:
lib/active_support/multibyte/unicode.rb

Defined Under Namespace

Classes: Codepoint, UnicodeDatabase

Constant Summary collapse

NORMALIZATION_FORMS =

A list of all available normalization forms. See www.unicode.org/reports/tr15/tr15-29.html for more information about normalization.

[:c, :kc, :d, :kd]
UNICODE_VERSION =

The Unicode version that is supported by the implementation

'5.2.0'
HANGUL_SBASE =

Hangul character boundaries and properties

0xAC00
HANGUL_LBASE =
0x1100
HANGUL_VBASE =
0x1161
HANGUL_TBASE =
0x11A7
HANGUL_LCOUNT =
19
HANGUL_VCOUNT =
21
HANGUL_TCOUNT =
28
HANGUL_NCOUNT =
HANGUL_VCOUNT * HANGUL_TCOUNT
HANGUL_SCOUNT =
11172
HANGUL_SLAST =
HANGUL_SBASE + HANGUL_SCOUNT
HANGUL_JAMO_FIRST =
0x1100
HANGUL_JAMO_LAST =
0x11FF
WHITESPACE =

All the unicode whitespace

[
  (0x0009..0x000D).to_a, # White_Space # Cc   [5] <control-0009>..<control-000D>
  0x0020,                # White_Space # Zs       SPACE
  0x0085,                # White_Space # Cc       <control-0085>
  0x00A0,                # White_Space # Zs       NO-BREAK SPACE
  0x1680,                # White_Space # Zs       OGHAM SPACE MARK
  0x180E,                # White_Space # Zs       MONGOLIAN VOWEL SEPARATOR
  (0x2000..0x200A).to_a, # White_Space # Zs  [11] EN QUAD..HAIR SPACE
  0x2028,                # White_Space # Zl       LINE SEPARATOR
  0x2029,                # White_Space # Zp       PARAGRAPH SEPARATOR
  0x202F,                # White_Space # Zs       NARROW NO-BREAK SPACE
  0x205F,                # White_Space # Zs       MEDIUM MATHEMATICAL SPACE
  0x3000,                # White_Space # Zs       IDEOGRAPHIC SPACE
].flatten.freeze
LEADERS_AND_TRAILERS =

BOM (byte order mark) can also be seen as whitespace, it’s a non-rendering character used to distinguish between little and big endian. This is not an issue in utf-8, so it must be ignored.

WHITESPACE + [65279]
TRAILERS_PAT =
/(#{codepoints_to_pattern(LEADERS_AND_TRAILERS)})+\Z/u
LEADERS_PAT =
/\A(#{codepoints_to_pattern(LEADERS_AND_TRAILERS)})+/u

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Instance Attribute Details

#default_normalization_formObject

The default normalization used for operations that require normalization. It can be set to any of the normalizations in NORMALIZATION_FORMS.

Example:

ActiveSupport::Multibyte::Unicode.default_normalization_form = :c


19
20
21
# File 'lib/active_support/multibyte/unicode.rb', line 19

def default_normalization_form
  @default_normalization_form
end

Class Method Details

.codepoints_to_pattern(array_of_codepoints) ⇒ Object

Returns a regular expression pattern that matches the passed Unicode codepoints



57
58
59
# File 'lib/active_support/multibyte/unicode.rb', line 57

def self.codepoints_to_pattern(array_of_codepoints) #:nodoc:
  array_of_codepoints.collect{ |e| [e].pack 'U*' }.join('|')
end

Instance Method Details

#apply_mapping(string, mapping) ⇒ Object

:nodoc:



300
301
302
303
304
305
306
307
308
309
# File 'lib/active_support/multibyte/unicode.rb', line 300

def apply_mapping(string, mapping) #:nodoc:
  u_unpack(string).map do |codepoint|
    cp = database.codepoints[codepoint]
    if cp and (ncp = cp.send(mapping)) and ncp > 0
      ncp
    else
      codepoint
    end
  end.pack('U*')
end

#compose_codepoints(codepoints) ⇒ Object

Compose decomposed characters to the composed form.



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
# File 'lib/active_support/multibyte/unicode.rb', line 166

def compose_codepoints(codepoints)
  pos = 0
  eoa = codepoints.length - 1
  starter_pos = 0
  starter_char = codepoints[0]
  previous_combining_class = -1
  while pos < eoa
    pos += 1
    lindex = starter_char - HANGUL_LBASE
    # -- Hangul
    if 0 <= lindex and lindex < HANGUL_LCOUNT
      vindex = codepoints[starter_pos+1] - HANGUL_VBASE rescue vindex = -1
      if 0 <= vindex and vindex < HANGUL_VCOUNT
        tindex = codepoints[starter_pos+2] - HANGUL_TBASE rescue tindex = -1
        if 0 <= tindex and tindex < HANGUL_TCOUNT
          j = starter_pos + 2
          eoa -= 2
        else
          tindex = 0
          j = starter_pos + 1
          eoa -= 1
        end
        codepoints[starter_pos..j] = (lindex * HANGUL_VCOUNT + vindex) * HANGUL_TCOUNT + tindex + HANGUL_SBASE
      end
      starter_pos += 1
      starter_char = codepoints[starter_pos]
    # -- Other characters
    else
      current_char = codepoints[pos]
      current = database.codepoints[current_char]
      if current.combining_class > previous_combining_class
        if ref = database.composition_map[starter_char]
          composition = ref[current_char]
        else
          composition = nil
        end
        unless composition.nil?
          codepoints[starter_pos] = composition
          starter_char = composition
          codepoints.delete_at pos
          eoa -= 1
          pos -= 1
          previous_combining_class = -1
        else
          previous_combining_class = current.combining_class
        end
      else
        previous_combining_class = current.combining_class
      end
      if current.combining_class == 0
        starter_pos = pos
        starter_char = codepoints[pos]
      end
    end
  end
  codepoints
end

#decompose_codepoints(type, codepoints) ⇒ Object

Decompose composed characters to the decomposed form.



145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
# File 'lib/active_support/multibyte/unicode.rb', line 145

def decompose_codepoints(type, codepoints)
  codepoints.inject([]) do |decomposed, cp|
    # if it's a hangul syllable starter character
    if HANGUL_SBASE <= cp and cp < HANGUL_SLAST
      sindex = cp - HANGUL_SBASE
      ncp = [] # new codepoints
      ncp << HANGUL_LBASE + sindex / HANGUL_NCOUNT
      ncp << HANGUL_VBASE + (sindex % HANGUL_NCOUNT) / HANGUL_TCOUNT
      tindex = sindex % HANGUL_TCOUNT
      ncp << (HANGUL_TBASE + tindex) unless tindex == 0
      decomposed.concat ncp
    # if the codepoint is decomposable in with the current decomposition type
    elsif (ncp = database.codepoints[cp].decomp_mapping) and (!database.codepoints[cp].decomp_type || type == :compatability)
      decomposed.concat decompose_codepoints(type, ncp.dup)
    else
      decomposed << cp
    end
  end
end

#g_pack(unpacked) ⇒ Object

Reverse operation of g_unpack.

Example:

Unicode.g_pack(Unicode.g_unpack('क्षि')) # => 'क्षि'


124
125
126
# File 'lib/active_support/multibyte/unicode.rb', line 124

def g_pack(unpacked)
  (unpacked.flatten).pack('U*')
end

#g_unpack(string) ⇒ Object

Unpack the string at grapheme boundaries. Returns a list of character lists.

Example:

Unicode.g_unpack('क्षि') # => [[2325, 2381], [2359], [2367]]
Unicode.g_unpack('Café') # => [[67], [97], [102], [233]]


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
# File 'lib/active_support/multibyte/unicode.rb', line 90

def g_unpack(string)
  codepoints = u_unpack(string)
  unpacked = []
  pos = 0
  marker = 0
  eoc = codepoints.length
  while(pos < eoc)
    pos += 1
    previous = codepoints[pos-1]
    current = codepoints[pos]
    if (
        # CR X LF
        ( previous == database.boundary[:cr] and current == database.boundary[:lf] ) or
        # L X (L|V|LV|LVT)
        ( database.boundary[:l] === previous and in_char_class?(current, [:l,:v,:lv,:lvt]) ) or
        # (LV|V) X (V|T)
        ( in_char_class?(previous, [:lv,:v]) and in_char_class?(current, [:v,:t]) ) or
        # (LVT|T) X (T)
        ( in_char_class?(previous, [:lvt,:t]) and database.boundary[:t] === current ) or
        # X Extend
        (database.boundary[:extend] === current)
      )
    else
      unpacked << codepoints[marker..pos-1]
      marker = pos
    end
  end
  unpacked
end

#in_char_class?(codepoint, classes) ⇒ Boolean

Detect whether the codepoint is in a certain character class. Returns true when it’s in the specified character class and false otherwise. Valid character classes are: :cr, :lf, :l, :v, :lv, :lvt and :t.

Primarily used by the grapheme cluster support.

Returns:

  • (Boolean)


81
82
83
# File 'lib/active_support/multibyte/unicode.rb', line 81

def in_char_class?(codepoint, classes)
  classes.detect { |c| database.boundary[c] === codepoint } ? true : false
end

#normalize(string, form = nil) ⇒ Object

Returns the KC normalization of the string by default. NFKC is considered the best normalization form for passing strings to databases and validations.

  • string - The string to perform normalization on.

  • form - The form you want to normalize in. Should be one of the following: :c, :kc, :d, or :kd. Default is ActiveSupport::Multibyte.default_normalization_form



282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
# File 'lib/active_support/multibyte/unicode.rb', line 282

def normalize(string, form=nil)
  form ||= @default_normalization_form
  # See http://www.unicode.org/reports/tr15, Table 1
  codepoints = u_unpack(string)
  case form
    when :d
      reorder_characters(decompose_codepoints(:canonical, codepoints))
    when :c
      compose_codepoints(reorder_characters(decompose_codepoints(:canonical, codepoints)))
    when :kd
      reorder_characters(decompose_codepoints(:compatability, codepoints))
    when :kc
      compose_codepoints(reorder_characters(decompose_codepoints(:compatability, codepoints)))
    else
      raise ArgumentError, "#{form} is not a valid normalization variant", caller
  end.pack('U*')
end

#reorder_characters(codepoints) ⇒ Object

Re-order codepoints so the string becomes canonical.



129
130
131
132
133
134
135
136
137
138
139
140
141
142
# File 'lib/active_support/multibyte/unicode.rb', line 129

def reorder_characters(codepoints)
  length = codepoints.length- 1
  pos = 0
  while pos < length do
    cp1, cp2 = database.codepoints[codepoints[pos]], database.codepoints[codepoints[pos+1]]
    if (cp1.combining_class > cp2.combining_class) && (cp2.combining_class > 0)
      codepoints[pos..pos+1] = cp2.code, cp1.code
      pos += (pos > 0 ? -1 : 1)
    else
      pos += 1
    end
  end
  codepoints
end

#tidy_bytes(string, force = false) ⇒ Object

Replaces all ISO-8859-1 or CP1252 characters by their UTF-8 equivalent resulting in a valid UTF-8 string.

Passing true will forcibly tidy all bytes, assuming that the string’s encoding is entirely CP1252 or ISO-8859-1.



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
# File 'lib/active_support/multibyte/unicode.rb', line 227

def tidy_bytes(string, force = false)
  if force
    return string.unpack("C*").map do |b|
      tidy_byte(b)
    end.flatten.compact.pack("C*").unpack("U*").pack("U*")
  end

  bytes = string.unpack("C*")
  conts_expected = 0
  last_lead = 0

  bytes.each_index do |i|

    byte          = bytes[i]
    is_cont       = byte > 127 && byte < 192
    is_lead       = byte > 191 && byte < 245
    is_unused     = byte > 240
    is_restricted = byte > 244

    # Impossible or highly unlikely byte? Clean it.
    if is_unused || is_restricted
      bytes[i] = tidy_byte(byte)
    elsif is_cont
      # Not expecting contination byte? Clean up. Otherwise, now expect one less.
      conts_expected == 0 ? bytes[i] = tidy_byte(byte) : conts_expected -= 1
    else
      if conts_expected > 0
        # Expected continuation, but got ASCII or leading? Clean backwards up to
        # the leading byte.
        (1..(i - last_lead)).each {|j| bytes[i - j] = tidy_byte(bytes[i - j])}
        conts_expected = 0
      end
      if is_lead
        # Final byte is leading? Clean it.
        if i == bytes.length - 1
          bytes[i] = tidy_byte(bytes.last)
        else
          # Valid leading byte? Expect continuations determined by position of
          # first zero bit, with max of 3.
          conts_expected = byte < 224 ? 1 : byte < 240 ? 2 : 3
          last_lead = i
        end
      end
    end
  end
  bytes.empty? ? "" : bytes.flatten.compact.pack("C*").unpack("U*").pack("U*")
end

#u_unpack(string) ⇒ Object

Unpack the string at codepoints boundaries. Raises an EncodingError when the encoding of the string isn’t valid UTF-8.

Example:

Unicode.u_unpack('Café') # => [67, 97, 102, 233]


68
69
70
71
72
73
74
# File 'lib/active_support/multibyte/unicode.rb', line 68

def u_unpack(string)
  begin
    string.unpack 'U*'
  rescue ArgumentError
    raise EncodingError, 'malformed UTF-8 character'
  end
end