RubyGems - prose - Versions diffs - 0.0.1 - Mend

prose 0.0.1

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 (4) hide show

checksums.yaml ADDED Viewed

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 09b137dde0e95e9308ecdc067bf4fd562a9b1526
+  data.tar.gz: 8cf9634b26218339d84eb677dfaea9432fdd9c36
+SHA512:
+  metadata.gz: be87ec95d9bc12c36caa5d69d2192f88b9f02ed041f97fb186142c71e5a9d1f371d9ec60980ee520f8e928339182706e467aafbdbec6112c2cce433e20f74c03
+  data.tar.gz: 220d5d89073e35e652d91e89d6a71845166d5679c5ac35777af0f80713c56d727be5a6516eb33c89515a2c095142c0945f22282b61b1fb04cb20806a4af15197

data/lib/prose/prose.yaml ADDED Viewed

@@ -0,0 +1,141 @@
+0590-05FF: hebrew
+FB00–FB4F: hebrew
+00D00-0D7F: malayalam
+0530-058F: armenian
+2C80-2CFF: coptic
+10800-1083F: cypriot
+0400-04FF: cyrillic
+0500-052F: cyrillic
+2DE0-2DFF: cyrillic
+A640-A69F: cyrillic
+10A0-10FF: georgian
+2D00-2D2F: georgian
+2C00-2C5F: glagolithic
+10330-1034F: gothic
+0370-03FF: greek
+1F00-1FFF: greek
+0000-007F: latin
+0080-00FF: latin
+0100-017F: latin
+0180-024F: latin
+2C60-2C7F: latin
+A720-A7FF: latin
+1E00-1EFF: latin
+FB00-FB4F: latin
+FB00-FB4F: latin
+FF00-FFEF: latin
+1680-169F: ogham
+10300-1032F: old_italics
+101D0-101FF: phaistos
+16A0-16FF: runic
+10450-1047F: shavian
+A6A0-A6FF: bamum
+16800-16A3F: bamum
+13000-1342F: egyptian_hieroglyphs
+1200-137F: ethiopic
+1380-139F: ethiopic
+2D80-2DDF: ethiopic
+AB00-AB2F: ethiopic
+109A0-109FF: meroitic_cursive
+10980-1099F: meroitic_hieroglyphs
+07C0-07FF: nko
+10480-104AF: osmanya
+2D30-2D7F: tifinagh
+A500-A63F: vai
+0600-06FF: arabic
+0750-077F: arabic
+08A0-08FF: arabic
+FB50-FDFF: arabic
+FE70-FEFF: arabic
+10840-1085F: aramic
+10B00-10B3F: avestan
+102A0-102DF: carian
+12000-123FF: cuniform
+12400-1247F: cuniform_numbers_punctuation
+10280-1029F: lycian
+1800-18AF: mongolian
+0F00-0FFF: tibetan
+0980-09FF: bengali_assamese
+0A80-0AFF: gujarati
+0C80-0CFF: kannada
+0B00-0B7F: oriya
+0B80-0BFF: tamil
+0C00-0C7F: telugu
+11000-1107F: brahmi
+0900-097F: devanagari
+A8E0-A8FF: devanagari
+103A0-103DF: old_persian
+10380-1039F: ugaritic
+10920-1093F: lydian
+0840-085F: mandaic
+10A60-10A7F: old_south_arabian
+10B60-10B7F: pahlavi
+10B40-10B5F: parthian
+10900-1091F: phoenician
+0800-083F: samaritan
+0700-074F: syriac
+10C00-10C4F: old_turkic
+A840-A87F: phags_pa
+11100-1114F: chakma
+0A00-0A7F: gurmukhi
+11080-110CF: kaithi
+10A00-10A5F: kharoshthi
+1C00-1C4F: lepcha
+1900-194F: limbu
+ABC0-ABFF: meetei_mayek
+AAE0-AAFF: meetei_mayek
+1C50-1C7F: ol_chiki
+A880-A8DF: saurashtra
+11180-111DF: sharada
+0D80-0DFF: sinhala
+110D0-110FF: sora_sompeng
+A800-A82F: syloti_nagri
+11680-116CF: takri
+0780-07BF: thaana
+1CD0-1CFF: vedic
+1B00-1B7F: balinese
+1BC0-1BFF: batak
+1A00-1A1F: buginese
+AA00-AA5F: cham
+A980-A9DF: javanese
+A900-A92F: kayah_li
+1780-17FF: khmer
+19E0-19FF: khmer
+0E80-0EFF: lao
+1000-109F: myanmar
+AA60-AA7F: myanmar
+1980-19DF: new_tai_lue
+A930-A95F: rejang
+1B80-1BBF: sudanese
+1CC0-1CCF: sudanese
+1950-197F: tai_le
+1A20-1AAF: tai_tham
+AA80-AADF: tai_viet
+0E00-0E7F: thai
+1740-175F: buhid
+1720-173F: hanunoo
+1700-171F: tagalog
+1760-177F: tagbanwa
+3100-312F: bopomofo
+31A0-31BF: bopomofo
+1100-11FF: hangul_jamo
+A960-A97F: hangul_jamo
+D7B0-D7FF: hangul_jamo
+3130-318F: hangul_jamo
+FF00-FFEF: hangul_jamo
+AC00-D7AF: hangul
+3040-309F: hiragana
+30A0-30FF: katakana
+31F0-31FF: katakana
+FF00-FFEF: katakana
+1B000-1B0FF: kana
+3190-319F: kanbun
+A4D0-A4FF: lisu
+16F00-16F9F: miao
+A000-A48F: yi
+A490-A4CF: yi
+13A0-13FF: cherokee
+10400-1044F: deseret
+1400-167F: united_canadian_aborginal
+18B0-18FF: united_canadian_aborginal
+#0000-007F: ASCII

data/lib/prose.rb ADDED Viewed

@@ -0,0 +1,35 @@
+# -*- coding: utf-8 -*-
+require 'yaml'
+class String
+  def prose?
+    find_languages_in(self)
+  end
+  private
+  def unicode_ranges
+    @ranges ||= YAML::load( File.open( "#{File.expand_path File.dirname(__FILE__)}/prose/prose.yaml" ) )
+  end
+  def language_of letter
+    result = []
+    int_ordinal = letter.ord
+    unicode_ranges.keys.each do |key|
+      min, max = key.split("-")
+      result << unicode_ranges[key] if (min.to_i(16) < int_ordinal) and (max.to_i(16) > int_ordinal)
+    end
+    return result
+  end
+  def find_languages_in word
+    result = []
+    word.split('').each do |letter|
+      result += language_of(letter) if not letter == " "
+    end
+    return result.uniq
+  end
+end

metadata ADDED Viewed

@@ -0,0 +1,45 @@
+--- !ruby/object:Gem::Specification
+name: prose
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Edwin Rozario
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2014-02-01 00:00:00.000000000 Z
+dependencies: []
+description: Identifies language of alphabets in a string
+email:
+- rozarioed@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/prose.rb
+- lib/prose/prose.yaml
+homepage: https://github.com/EdwinRozario/Prose
+licenses: []
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project:
+rubygems_version: 2.2.0
+signing_key:
+specification_version: 4
+summary: Identify language string
+test_files: []