interscript 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 19905541367b50886e3d130aac4132cbb5e9050bff1409f924b23848ea5b3a32
+  data.tar.gz: d9d6a9531009778797f2826cf51dfc2b68b27651608be5c91ed7f343d75ff75f
+SHA512:
+  metadata.gz: 247a535a7fd1203b2331b2c6c99fa9a9e0747c3fc5ff1f5476c034d1c72ae5bd16bbf2866cf639cadd321989dd653a461eda2b0db662db303c381b2de8b18285
+  data.tar.gz: a9c259539a46c33dc5c7de38edc9b5d330727064509dbc6cc17cdfa3baf1ae950fa3e8c645e45e9e04fa3afc213f50f3e1cfe8c44470bf8024e93f3621e32b87

data/README.adoc

@@ -0,0 +1,65 @@
+= Interscript: Interoperable Script Conversion Systems and a Ruby implementation
+
+== Introducation
+
+This repository contains a number of transliteration schemes from:
+
+* BGN/PCGN
+* ICAO
+* ISO
+* UN (by UNGEGN)
+
+The goal is to achieve interoperable transliteration schemes allowing quality comparisons.
+
+
+== STATUS (work in progress!)
+
+These transliteration systems currently work:
+
+`bgnpcgn-rus-Cyrl-Latn-1947`:: BGN/PCGN Romanization of Russian
+`iso-rus-Cyrl-Latn-iso9`::     ISO 9 Romanization of Russian
+`icao-rus-Cyrl-Latn-9303`::    ICAO MRZ Romanization of Russian
+`bas-rus-Cyrl-Latn-bss`::      Bulgaria Academy of Science Streamlined System for Russian
+
+
+== Usage
+
+
+[source,sh]
+----
+# Transliterating Russian Cyrillic to Latin using the Streamlined System for Russian
+interscript samples/rus-Cyrl.txt --system=bas-rus-Cyrl-Latn-bss --output=rus-Latn.txt
+
+# Transliterating Russian Cyrillic to Latin using the BGN/PCGN Romanization of Russian
+interscript samples/rus-Cyrl.txt --system=bgnpcgn-rus-Cyrl-Latn-1947 --output=rus-Latn.txt
+----
+
+
+== ISCS system codes
+
+The system code identifying a script conversion system has a few components:
+
+e.g. `bgnpcgn-rus-Cyrl-Latn-1947`
+
+`bgnpcgn`:: the authority identifier
+`rus`:: an ISO 639-2 3-letter language code that this system applies to
+`Cyrl`:: an ISO 15924 script code, identifying the source script
+`Latn`:: an ISO 15924 script code, identifying the target script
+`1947`:: an identifier unit within the authority to identify this system
+
+
+== Covered languages
+
+Currently the schemes cover Cyrillic, Armenian, Greek, Arabic and Hebrew.
+
+
+== Sources
+
+* `rus-Cyrl-1.txt`: Copied from the XLS output from http://www.primorsk.vybory.izbirkom.ru/region/primorsk?action=show&global=true&root=254017025&tvd=4254017212287&vrn=100100067795849&prver=0&pronetvd=0&region=25&sub_region=25&type=242&vibid=4254017212287
+
+* `rus-Cyrl-2.txt`: Copied from the XLS output from http://www.yaroslavl.vybory.izbirkom.ru/region/yaroslavl?action=show&root=764013001&tvd=4764013188704&vrn=4764013188693&prver=0&pronetvd=0&region=76&sub_region=76&type=426&vibid=4764013188704
+
+
+== Credits
+
+This is a Ribose project.

data/bin/interscript

@@ -0,0 +1,22 @@
+#!/usr/bin/env ruby
+require 'rubygems'
+require_relative '../lib/interscript'
+
+if ARGV.empty?
+  puts "write source file, source format, and output file"
+else
+  args = Hash[ ARGV.flat_map{|s| s.scan(/--?([^=\s]+)(?:=(\S+))?/) } ]
+  input = ARGV[0]
+  system_code = args["system"]
+  output_file = args["output"]
+
+  raise "Please enter the system code with --system={system_code}" unless system_code
+
+  if output_file
+    Interscript.instance.transliterate_file(system_code, input, output_file)
+  else
+    puts Interscript.instance.transliterate(system_code, IO.read(input))
+  end
+end
+
+

data/lib/interscript/version.rb

@@ -0,0 +1,3 @@
+module Interscript
+  VERSION = "0.1.0"
+end

data/lib/interscript.rb

@@ -0,0 +1,53 @@
+require 'yaml'
+require 'singleton'
+
+class Interscript
+  include Singleton
+  
+  SYSTEM_DEFINITIONS_PATH = File.expand_path('../../maps', __FILE__)
+
+  def initialize
+    @systems = {}
+  end
+
+  def transliterate_file(system_code, input_file, output_file)
+    input = File.read(input_file)
+    output = transliterate(system_code, input)
+
+    File.open(output_file, "w") do |f|
+      f.puts(output)
+    end
+    puts "Output written to: #{output_file}"
+  end
+
+  def load_system_definition(system_code)
+    @systems[system_code] ||= YAML.load_file(File.join(SYSTEM_DEFINITIONS_PATH, "#{system_code}.yaml"))
+  end
+
+  def get_system(system_code)
+    @systems[system_code]
+  end
+
+  def system_char_map(system_code)
+    get_system(system_code)["map"]["characters"]
+  end
+
+  def system_rules(system_code)
+    get_system(system_code)["map"]["rules"]
+  end
+
+  def transliterate(system_code, string)
+    load_system_definition(system_code)
+
+    # TODO: also need to support regular expressions via system_rules(system_code), before system_char_map
+
+    character_map = system_char_map(system_code)
+
+    string.split('').map do |char|
+      converted_char = character_map[char] ? character_map[char] : char
+      string[char] = converted_char
+    end.join('')
+  end
+
+end
+

metadata

@@ -0,0 +1,89 @@
+--- !ruby/object:Gem::Specification
+name: interscript
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- project_contibutors
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2019-11-17 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.7'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Interoperable script conversion systems
+email: 
+executables:
+- interscript
+extensions: []
+extra_rdoc_files: []
+files:
+- README.adoc
+- bin/interscript
+- lib/interscript.rb
+- lib/interscript/version.rb
+homepage: ''
+licenses:
+- MIT
+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: []
+rubygems_version: 3.0.3
+signing_key: 
+specification_version: 4
+summary: Interoperable script conversion systems
+test_files: []