kroman 1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 5626c92e6ca422baa8e96587715da0597d279218
+  data.tar.gz: 2b039d3b0ef3a93a7353da23487390bf5a09b37b
+SHA512:
+  metadata.gz: 2d6cdd57995bad6386307a1a52acc49d130044bafc34631e8171c2e2639cf0487bb17812a63e9540b510319729cc29aec926b25dd8d7129acdec35e6aa21bbbb
+  data.tar.gz: c66ca924176b3a1314d7d068ed87e398209aa3f757e5c1b2a290bed5ab055a4b086a8bb00f877fb8e5aa68586a725b7ff9b6c67b055591d287e603a70d1285af

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/Gemfile

@@ -0,0 +1,2 @@
+source 'https://rubygems.org'
+gemspec

data/README.md

@@ -0,0 +1,40 @@
+# kroman gem
+
+The fantastic [kroman](https://github.com/cheunghy/kroman) converts hanguls to romanized syllables.
+
+This is the ruby gem wrapper around it.
+
+It has C extension, which means it's efficient, lightweight and enjoyable.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'kroman-gem'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install kroman-gem
+
+## Usage
+
+``` ruby
+Kroman.let_me_sing!("손목시계")
+=> "son-mog-si-gye"
+```
+
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/cheunghy/kroman-gem. 
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
+

data/Rakefile

@@ -0,0 +1 @@
+require 'bundler/gem_tasks'

data/ext/kroman/extconf.rb

@@ -0,0 +1,3 @@
+require "mkmf"
+
+create_makefile "kroman/kroman"

data/ext/kroman/kroman.c

@@ -0,0 +1,48 @@
+#include <ruby.h>
+#include <unistd.h>
+#include "kroman_convert.h"
+#include "kroman_process.h"
+
+static VALUE kroman_parse(VALUE self, VALUE hangul) {
+  VALUE hangul_s = rb_funcall(hangul, rb_intern("to_s"), 0);
+  char *hangul_content = RSTRING_PTR(hangul_s);
+  long hangul_length = RSTRING_LEN(hangul_s);
+
+  char in_file_name[L_tmpnam];
+  char out_file_name[L_tmpnam];
+
+  tmpnam(in_file_name);
+  tmpnam(out_file_name);
+  FILE *in_file = fopen(in_file_name, "w+");
+  FILE *out_file = fopen(out_file_name, "w+");
+
+  fwrite(hangul_content, hangul_length, 1, in_file);
+  fseek(in_file, 0, SEEK_SET);
+
+  kroman_process(in_file, out_file);
+
+  fseek(out_file, 0, SEEK_END);
+  long length = ftell(out_file);
+  fseek(out_file, 0, SEEK_SET);
+  char *buffer = malloc(length + 1);
+
+  fread(buffer, 1, length, out_file);
+  buffer[length] = 0;
+  
+  fclose(in_file);
+  fclose(out_file);
+
+  unlink(in_file_name);
+  unlink(out_file_name);
+
+  VALUE romanized = rb_str_new_cstr(buffer);
+  return romanized;
+}
+
+void Init_kroman(void) {
+  VALUE cKroman;
+  cKroman = rb_const_get(rb_cObject, rb_intern("Kroman"));
+
+  rb_define_singleton_method(cKroman, "parse", kroman_parse, 1);
+  rb_define_singleton_method(cKroman, "let_me_sing!", kroman_parse, 1);
+}

data/ext/kroman/kroman_convert.c

@@ -0,0 +1,297 @@
+#include "kroman_convert.h"
+#include <stdlib.h>
+#include <string.h>
+#define KROMAN_GA 0xac00
+#define KROMAN_HIH 0xd7a3
+#define KROMAN_HEAD_INTERVAL 588
+#define KROMAN_BODY_INTERVAL 28
+#define KROMAN_TAIL_INTERVAL 1
+/* 
+ * Referenced from
+ * http://www.programminginkorean.com/programming/hangul-in-unicode
+ * http://www.programminginkorean.com/programming/hangul-in-unicode/hangul-syllables-uac00-ud7a3/
+ * Many thanks!
+ * 
+ * heads interval 588, total 19
+ * g gg n d dd r m b bb s ss ng(0) j jj c k t p h
+ * bodies interval 28, total 21
+ * a ae ya yae eo e yeo ye o wa wae oe yo u weo we wi yu eu eui i
+ * tails interval 1, total 28
+ * 0 g gg gs n nj nh d r rk rm rb rs rt rp rh m b bs s ss ng j c k t p h
+ *
+ * starts at U+AC00, ends at U+D7A3
+ */
+
+void kroman_head_from_index(int, char *);
+void kroman_body_from_index(int, char *);
+void kroman_tail_from_index(int, char *);
+
+void kroman_convert(wchar_t character, char *retstring, bool *is_hangul) {
+  int char_int = (int)character;
+  // If it is hangul
+  if ((char_int >= KROMAN_GA) && (char_int <= KROMAN_HIH)) {
+    int head_index = (char_int - KROMAN_GA) / KROMAN_HEAD_INTERVAL;
+    int head_lefto = (char_int - KROMAN_GA) % KROMAN_HEAD_INTERVAL;
+    int body_index = head_lefto / KROMAN_BODY_INTERVAL;
+    int tail_index = head_lefto % KROMAN_BODY_INTERVAL;
+    char head_string[10];
+    kroman_head_from_index(head_index, head_string);
+    char body_string[10];
+    kroman_body_from_index(body_index, body_string);
+    char tail_string[10];
+    kroman_tail_from_index(tail_index, tail_string);
+    strcat(retstring, head_string);
+    strcat(retstring, body_string);
+    strcat(retstring, tail_string);
+    *is_hangul = true;
+  } else { // else normal wide char
+    wchar_t wchar_string[2];
+    wchar_string[0] = character;
+    wchar_string[1] = 0;
+    wcstombs(retstring, (const wchar_t *)wchar_string, 6);
+    *is_hangul = false;
+  }
+}
+
+void kroman_head_from_index(int head_index, char *retstring) {
+  char *head_string;
+
+  switch(head_index) {
+    case 0:
+      head_string = "g";
+      break;
+    case 1:
+      head_string = "gg";
+      break;
+    case 2:
+      head_string = "n";
+      break;
+    case 3:
+      head_string = "d";
+      break;
+    case 4:
+      head_string = "dd";
+      break;
+    case 5:
+      head_string = "r";
+      break;
+    case 6:
+      head_string = "m";
+      break;
+    case 7:
+      head_string = "b";
+      break;
+    case 8:
+      head_string = "bb";
+      break;
+    case 9:
+      head_string = "s";
+      break;
+    case 10:
+      head_string = "ss";
+      break;
+    case 11:
+      head_string = "";
+      break;
+    case 12:
+      head_string = "j";
+      break;
+    case 13:
+      head_string = "jj";
+      break;
+    case 14:
+      head_string = "c";
+      break;
+    case 15:
+      head_string = "k";
+      break;
+    case 16:
+      head_string = "t";
+      break;
+    case 17:
+      head_string = "p";
+      break;
+    case 18:
+      head_string = "h";
+      break;
+    default:
+      fprintf(stderr, "Error: Unknown head.\n");
+      exit(1);
+      break;
+  }
+
+  sprintf(retstring, "%s", head_string);
+}
+
+void kroman_body_from_index(int body_index, char *retstring) {
+  char *body_string;
+
+  switch(body_index) {
+    case 0:
+      body_string = "a";
+      break;
+    case 1:
+      body_string = "ae";
+      break;       
+    case 2:
+      body_string = "ya";
+      break;
+    case 3:
+      body_string = "yae";
+      break;
+    case 4:
+      body_string = "eo";
+      break;
+    case 5:
+      body_string = "e";
+      break;
+    case 6:
+      body_string = "yeo";
+      break;
+    case 7:
+      body_string = "ye";
+      break;   
+    case 8:
+      body_string = "o";
+      break;
+    case 9:
+      body_string = "wa";
+      break;
+    case 10:
+      body_string = "wae";
+      break;
+    case 11:
+      body_string = "oe";
+      break;
+    case 12:
+      body_string = "yo";
+      break;
+    case 13:
+      body_string = "u";
+      break;
+    case 14:
+      body_string = "weo";
+      break;
+    case 15:
+      body_string = "we";
+      break;
+    case 16:
+      body_string = "wi";
+      break;
+    case 17:
+      body_string = "yu";
+      break;
+    case 18:
+      body_string = "eu";
+      break;
+    case 19:
+      body_string = "eui";
+      break;
+    case 20:
+      body_string = "i";
+      break;
+    default:
+      fprintf(stderr, "Error: unknown body\n");
+      exit(1);
+      break;
+  }
+
+  sprintf(retstring, "%s", body_string);
+}
+
+void kroman_tail_from_index(int tail_index, char *retstring) {
+  char *tail_string;
+
+  switch(tail_index) {
+    case 0:
+      tail_string = "";
+      break;
+    case 1:
+      tail_string = "g";
+      break;       
+    case 2:
+      tail_string = "gg";
+      break;
+    case 3:
+      tail_string = "gs";
+      break;
+    case 4:
+      tail_string = "n";
+      break;
+    case 5:
+      tail_string = "nj";
+      break;
+    case 6:
+      tail_string = "nh";
+      break;
+    case 7:
+      tail_string = "d";
+      break;   
+    case 8:
+      tail_string = "r";
+      break;
+    case 9:
+      tail_string = "rk";
+      break;
+    case 10:
+      tail_string = "rm";
+      break;
+    case 11:
+      tail_string = "rb";
+      break;
+    case 12:
+      tail_string = "rs";
+      break;
+    case 13:
+      tail_string = "rt";
+      break;
+    case 14:
+      tail_string = "rp";
+      break;
+    case 15:
+      tail_string = "rh";
+      break;
+    case 16:
+      tail_string = "m";
+      break;
+    case 17:
+      tail_string = "b";
+      break;
+    case 18:
+      tail_string = "bs";
+      break;
+    case 19:
+      tail_string = "s";
+      break;
+    case 20:
+      tail_string = "ss";
+      break;
+    case 21:
+      tail_string = "ng";
+      break;
+    case 22:
+      tail_string = "j";
+      break;
+    case 23:
+      tail_string = "c";
+      break;
+    case 24:
+      tail_string = "k";
+      break;
+    case 25:
+      tail_string = "t";
+      break;
+    case 26:
+      tail_string = "p";
+      break;
+    case 27:
+      tail_string = "h";
+      break;
+    default:
+      fprintf(stderr, "Error: unknown tail\n");
+      exit(1);
+      break;
+  }
+
+  sprintf(retstring, "%s", tail_string);
+}

data/ext/kroman/kroman_convert.h

@@ -0,0 +1,9 @@
+#ifndef KROMAN_CONVERT_H__
+#define KROMAN_CONVERT_H__
+
+#include <wchar.h>
+#include <stdbool.h>
+
+void kroman_convert(wchar_t, char *, bool *);
+
+#endif /* KROMAN_CONVERT_H__ */

data/ext/kroman/kroman_process.c

@@ -0,0 +1,50 @@
+#include "kroman_process.h"
+#include "kroman_convert.h"
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <wchar.h>
+#include <locale.h>
+#include <stdbool.h>
+
+#define KROMAN_MAXLINE 4096
+#define KROMAN_SIZE 20
+
+void kroman_process_line(char *user_line, FILE *outstream);
+
+void kroman_process(FILE *instream, FILE *outstream) {
+  // Set current user locale, may or may not be en_US.UTF-8
+  setlocale(LC_ALL, "");
+  char *user_line = malloc(KROMAN_MAXLINE * sizeof(char));
+  while (fgets(user_line, KROMAN_MAXLINE, instream)) {
+    kroman_process_line(user_line, outstream);
+  }
+  free(user_line);
+  if (ferror(instream)) {
+    printf("Instream error occured!\n");
+    exit(1);
+  }
+}
+
+void kroman_process_line(char *user_line, FILE *outstream) {
+  wchar_t *wide_line = malloc(KROMAN_MAXLINE * sizeof(wchar_t));
+  mbstowcs(wide_line, user_line, KROMAN_MAXLINE);
+  size_t len = wcslen(wide_line);
+  bool last_is_hangul = false;
+  for (size_t i = 0; i < len; ++i) {
+    wchar_t wide_char = wide_line[i];
+    char *retstring = malloc(sizeof(char) * KROMAN_SIZE);
+    memset(retstring, 0, sizeof(char) * KROMAN_SIZE);
+    bool is_hangul;
+    kroman_convert(wide_char, retstring, &is_hangul);
+    if (last_is_hangul && is_hangul) {
+      fprintf(outstream, "-%s", retstring);
+    } else {
+      fprintf(outstream, "%s", retstring);
+    }
+    
+    last_is_hangul = is_hangul;
+    free(retstring);
+  }
+  free(wide_line);
+}

data/ext/kroman/kroman_process.h

@@ -0,0 +1,8 @@
+#ifndef KROMAN_PROCESS_H__
+#define KROMAN_PROCESS_H__
+
+#include <stdio.h>
+
+void kroman_process(FILE *, FILE *);
+
+#endif /* KROMAN_PROCESS_H__ */

data/kroman.gemspec

@@ -0,0 +1,25 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+
+require 'kroman/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "kroman"
+  spec.version       = Kroman::VERSION
+  spec.authors       = ["Zhang Kai Yu"]
+  spec.email         = ["yeannylam@gmail.com"]
+
+  spec.summary       = "Kroman converts Korean hangul to romanized syllables"
+  spec.description   = "Kroman make nice Korean songs singable"
+  spec.homepage      = "https://github.com/cheunghy/kroman-gem"
+  spec.license       = "MIT"
+
+  spec.extensions = %w[ext/kroman/extconf.rb]
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.10"
+  spec.add_development_dependency "rake", "~> 10.0"
+end

data/lib/kroman/version.rb

@@ -0,0 +1,3 @@
+module Kroman
+  VERSION = 1.0
+end

data/lib/kroman.rb

@@ -0,0 +1,3 @@
+module Kroman
+  require 'kroman/kroman'
+end

metadata

@@ -0,0 +1,87 @@
+--- !ruby/object:Gem::Specification
+name: kroman
+version: !ruby/object:Gem::Version
+  version: '1.0'
+platform: ruby
+authors:
+- Zhang Kai Yu
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-07-22 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.10'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.10'
+- !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'
+description: Kroman make nice Korean songs singable
+email:
+- yeannylam@gmail.com
+executables: []
+extensions:
+- ext/kroman/extconf.rb
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- Gemfile
+- README.md
+- Rakefile
+- ext/kroman/extconf.rb
+- ext/kroman/kroman.c
+- ext/kroman/kroman_convert.c
+- ext/kroman/kroman_convert.h
+- ext/kroman/kroman_process.c
+- ext/kroman/kroman_process.h
+- kroman.gemspec
+- lib/kroman.rb
+- lib/kroman/version.rb
+homepage: https://github.com/cheunghy/kroman-gem
+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: []
+rubyforge_project: 
+rubygems_version: 2.4.5
+signing_key: 
+specification_version: 4
+summary: Kroman converts Korean hangul to romanized syllables
+test_files: []
+has_rdoc: