Module: Rangu

Defined in:
lib/rangu.rb,
lib/rangu/cli.rb,
lib/rangu/version.rb

Defined Under Namespace

Classes: CLI

Constant Summary collapse

CJK =

Spacing rules adapted from pangu.py 4.0.6.1.

"\\u2e80-\\u2eff\\u2f00-\\u2fdf\\u3040-\\u309f\\u30a0-\\u30fa\\u30fc-\\u30ff" \
"\\u3100-\\u312f\\u3200-\\u32ff\\u3400-\\u4dbf\\u4e00-\\u9fff\\uf900-\\ufaff"
ANY_CJK =
/[#{CJK}]/
CONVERT_TO_FULLWIDTH_CJK_SYMBOLS_CJK =
/([#{CJK}])( *(?::+|\.) *)([#{CJK}])/
CONVERT_TO_FULLWIDTH_CJK_SYMBOLS =
/([#{CJK}]) *([~!;,?]+) */
DOTS_CJK =
/(\.{2,}|…)([#{CJK}])/
FIX_CJK_COLON_ANS =
/([#{CJK}]):([A-Z0-9()])/
CJK_QUOTE =
/([#{CJK}])([`"״])/
QUOTE_CJK =
/([`"״])([#{CJK}])/
FIX_QUOTE_ANY_QUOTE =
/([`"״]+)(\s*)(.+?)(\s*)([`"״]+)/
CJK_SINGLE_QUOTE_BUT_POSSESSIVE =
/([#{CJK}])('[^s])/
SINGLE_QUOTE_CJK =
/(')([#{CJK}])/
FIX_POSSESSIVE_SINGLE_QUOTE =
/([#{CJK}A-Za-z0-9])( )('s)/
HASH_ANS_CJK_HASH =
/([#{CJK}])(#)([#{CJK}]+)(#)([#{CJK}])/
CJK_HASH =
/([#{CJK}])(#([^ ]))/
HASH_CJK =
/(([^ ])#)([#{CJK}])/
CJK_OPERATOR_ANS =
%r{([#{CJK}])([+\-*/=&|<>])([A-Za-z0-9])}
ANS_OPERATOR_CJK =
%r{([A-Za-z0-9])([+\-*/=&|<>])([#{CJK}])}
FIX_SLASH_AS =
%r{(/) ([a-z\-_./]+)}
FIX_SLASH_AS_SLASH =
%r{([/.])([A-Za-z\-_./]+) (/)}
CJK_LEFT_BRACKET =
/([#{CJK}])([\(\[\{<>“])/
RIGHT_BRACKET_CJK =
/([)\]}<>”])([#{CJK}])/
FIX_LEFT_BRACKET_ANY_RIGHT_BRACKET =
/([\(\[\{<“]+)(\s*)(.+?)(\s*)([)\]}>”]+)/
ANS_CJK_LEFT_BRACKET_ANY_RIGHT_BRACKET =
/([A-Za-z0-9#{CJK}]) *(“)([A-Za-z0-9#{CJK}\-_ ]+)(”)/
LEFT_BRACKET_ANY_RIGHT_BRACKET_ANS_CJK =
/(“)([A-Za-z0-9#{CJK}\-_ ]+)(”) *([A-Za-z0-9#{CJK}])/
AN_LEFT_BRACKET =
/([A-Za-z0-9])([\(\[\{])/
RIGHT_BRACKET_AN =
/([)\]}])([A-Za-z0-9])/
CJK_ANS =
%r{([#{CJK}])([A-Za-z\u0370-\u03ff0-9@$%\^&*\-+\\=|/\u00a1-\u00ff\u2150-\u218f\u2700—\u27bf])}
ANS_CJK =
%r{([A-Za-z\u0370-\u03ff0-9~!$%\^&*\-+\\=|;:,./?\u00a1-\u00ff\u2150-\u218f\u2700—\u27bf])([#{CJK}])}
S_A =
/(%)([A-Za-z])/
MIDDLE_DOT =
/( *)([·•‧])( *)/
TILDES =
/~+/
EXCLAMATION_MARKS =
/!+/
SEMICOLONS =
/;+/
COLONS =
/:+/
COMMAS =
/,+/
PERIODS =
/\.+/
QUESTION_MARKS =
/\?+/
VERSION =
"1.0.0"

Class Method Summary collapse

Class Method Details

.spacing(text) ⇒ Object Also known as: spacing_text



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
# File 'lib/rangu.rb', line 58

def self.spacing(text)
  return text.dup if text.length <= 1 || !ANY_CJK.match?(text)

  new_text = normalize_fullwidth_symbols_between_cjk(text.dup)
  new_text = normalize_fullwidth_symbols_after_cjk(new_text)

  new_text = new_text.gsub(DOTS_CJK, "\\1 \\2")
  new_text = new_text.gsub(FIX_CJK_COLON_ANS, "\\1:\\2")

  new_text = new_text.gsub(CJK_QUOTE, "\\1 \\2")
  new_text = new_text.gsub(QUOTE_CJK, "\\1 \\2")
  new_text = new_text.gsub(FIX_QUOTE_ANY_QUOTE, "\\1\\3\\5")

  new_text = new_text.gsub(CJK_SINGLE_QUOTE_BUT_POSSESSIVE, "\\1 \\2")
  new_text = new_text.gsub(SINGLE_QUOTE_CJK, "\\1 \\2")
  new_text = new_text.gsub(FIX_POSSESSIVE_SINGLE_QUOTE, "\\1's")

  new_text = new_text.gsub(HASH_ANS_CJK_HASH, "\\1 \\2\\3\\4 \\5")
  new_text = new_text.gsub(CJK_HASH, "\\1 \\2")
  new_text = new_text.gsub(HASH_CJK, "\\1 \\3")

  new_text = new_text.gsub(CJK_OPERATOR_ANS, "\\1 \\2 \\3")
  new_text = new_text.gsub(ANS_OPERATOR_CJK, "\\1 \\2 \\3")

  new_text = new_text.gsub(FIX_SLASH_AS, "\\1\\2")
  new_text = new_text.gsub(FIX_SLASH_AS_SLASH, "\\1\\2\\3")

  new_text = new_text.gsub(CJK_LEFT_BRACKET, "\\1 \\2")
  new_text = new_text.gsub(RIGHT_BRACKET_CJK, "\\1 \\2")
  new_text = new_text.gsub(FIX_LEFT_BRACKET_ANY_RIGHT_BRACKET, "\\1\\3\\5")
  new_text = new_text.gsub(ANS_CJK_LEFT_BRACKET_ANY_RIGHT_BRACKET, "\\1 \\2\\3\\4")
  new_text = new_text.gsub(LEFT_BRACKET_ANY_RIGHT_BRACKET_ANS_CJK, "\\1\\2\\3 \\4")

  new_text = new_text.gsub(AN_LEFT_BRACKET, "\\1 \\2")
  new_text = new_text.gsub(RIGHT_BRACKET_AN, "\\1 \\2")

  new_text = new_text.gsub(CJK_ANS, "\\1 \\2")
  new_text = new_text.gsub(ANS_CJK, "\\1 \\2")
  new_text = new_text.gsub(S_A, "\\1 \\2")
  new_text.gsub(MIDDLE_DOT, "").strip
end

.spacing_file(path) ⇒ Object



104
105
106
# File 'lib/rangu.rb', line 104

def self.spacing_file(path)
  spacing(File.read(path, encoding: Encoding::UTF_8))
end