formosa 0.0.1 → 0.2.0

data/lib/ext/native_syllable_composer/LibHolo.h

@@ -565,12 +565,17 @@ namespace LibHolo
 			if (FLV("a")) SETLOUDEST(p);
 			
 			// the last "ere" override
-			if (end >= 3) {
-                if (_symvec[end-1].symbolInLowerCase() == "e" && _symvec[end-2].symbolInLowerCase() == "r" && _symvec[end-3].symbolInLowerCase() == "e")
-                {
-                    SETLOUDEST(end-1);
-                }
-			}
+			string lastSymbolStr = _symvec[end-1].symbolInLowerCase();
+			
+			if (end >= 4 && (lastSymbolStr=="t" || lastSymbolStr=="p" || lastSymbolStr=="k" || lastSymbolStr=="h") &&
+ _symvec[end-2].symbolInLowerCase() == "e" && _symvec[end-3].symbolInLowerCase() == "r" && _symvec[end-4].symbolInLowerCase() == "e")
+            {
+                SETLOUDEST(end-2);
+            }			    			    
+            else if (end >= 3 && lastSymbolStr == "e" && _symvec[end-2].symbolInLowerCase() == "r" && _symvec[end-3].symbolInLowerCase() == "e")
+            {
+                SETLOUDEST(end-1);
+            }
 			
 			if (loudestVowel==end) return;
 			// fprintf(stderr, "found loudest vowel=%d (%s), loudest tone=%d\n", loudestVowel, _symvec[loudestVowel].symbol().c_str(), loudestTone);
@@ -580,8 +585,6 @@ namespace LibHolo
 			
 			for (unsigned int i=0; i<end; i++) _symvec[i].setTone(0);
 			
-			string lastSymbolStr = _symvec[end-1].symbolInLowerCase();
-			
 			// if the symbol is "i", and there's a next "u", we shift
 			// the vowel to "u"
 			
@@ -646,12 +649,12 @@ namespace LibHolo
 					// detect case
 					if (str1[0] == tolower(str1[0])) {
 						syl.insertCharacterAtCursor('o', sym1.tone());
-						syl.insertCharacterAtCursor('u');
+						syl.insertCharacterAtCursor(str1[1] == tolower(str1[1]) ? 'u' : 'U');
 					}
 					else
 					{
 						syl.insertCharacterAtCursor('O', sym1.tone());
-						syl.insertCharacterAtCursor('U');						
+						syl.insertCharacterAtCursor(str1[1] == tolower(str1[1]) ? 'u' : 'U');
 					}
 					continue;
 				}
@@ -667,11 +670,11 @@ namespace LibHolo
 						// detect case
 						if (str1[0] == tolower(str1[0])) {
 							syl.insertCharacterAtCursor('c');
-							syl.insertCharacterAtCursor('h');
+							syl.insertCharacterAtCursor(str2[0] == tolower(str2[0]) ? 'h' : 'H');
 						}
 						else {
 							syl.insertCharacterAtCursor('C');
-							syl.insertCharacterAtCursor('H');							
+							syl.insertCharacterAtCursor(str2[0] == tolower(str2[0]) ? 'h' : 'H');							
 						}
 						
 						i++;
@@ -683,11 +686,11 @@ namespace LibHolo
 						// detect case
 						if (str1[0] == tolower(str1[0])) {
 							syl.insertCharacterAtCursor('o', sym1.tone());
-							syl.insertCharacterAtCursor('e', sym2.tone());
+							syl.insertCharacterAtCursor(str2[0], sym2.tone());
 						}
 						else {
 							syl.insertCharacterAtCursor('O', sym1.tone());
-							syl.insertCharacterAtCursor('E', sym2.tone());							
+							syl.insertCharacterAtCursor(str2[0], sym2.tone());							
 						}
 						
 						i++;
@@ -699,11 +702,11 @@ namespace LibHolo
 						// detect case
 						if (str1[0] == tolower(str1[0])) {
 							syl.insertCharacterAtCursor('o', sym1.tone());
-							syl.insertCharacterAtCursor('a', sym2.tone());
+							syl.insertCharacterAtCursor(str2[0], sym2.tone());
 						}
 						else {
 							syl.insertCharacterAtCursor('O', sym1.tone());
-							syl.insertCharacterAtCursor('A', sym2.tone());
+							syl.insertCharacterAtCursor(str2[0], sym2.tone());
 						}
 						
 						i++;
@@ -715,11 +718,11 @@ namespace LibHolo
 						// detect case
 						if (str1[0] == tolower(str1[0])) {
 							syl.insertCharacterAtCursor('e', sym1.tone());
-							syl.insertCharacterAtCursor('k', sym2.tone());
+							syl.insertCharacterAtCursor(str2[0], sym2.tone());
 						}
 						else {
 							syl.insertCharacterAtCursor('E', sym1.tone());
-							syl.insertCharacterAtCursor('K', sym2.tone());
+							syl.insertCharacterAtCursor(str2[0], sym2.tone());
 						}
 						
 						i++;
@@ -736,13 +739,13 @@ namespace LibHolo
 							// detect case
 							if (str1[0] == tolower(str1[0])) {
 								syl.insertCharacterAtCursor('e', sym1.tone());
-								syl.insertCharacterAtCursor('n', sym2.tone());
-								syl.insertCharacterAtCursor('g', sym3.tone());
+								syl.insertCharacterAtCursor(str2[0], sym2.tone());
+								syl.insertCharacterAtCursor(str3[0], sym3.tone());
 							}
 							else {
 								syl.insertCharacterAtCursor('E', sym1.tone());
-								syl.insertCharacterAtCursor('N', sym2.tone());
-								syl.insertCharacterAtCursor('G', sym3.tone());
+								syl.insertCharacterAtCursor(str2[0], sym2.tone());
+								syl.insertCharacterAtCursor(str3[0], sym3.tone());
 							}
 
 							i+=2;
@@ -753,12 +756,12 @@ namespace LibHolo
 						if (lowstr1=="o" && lowstr2=="u" && lowstr3=="h") {
 							// detect case
 							if (str2[0] == tolower(str2[0])) {
-								syl.insertCharacterAtCursor('o', sym1.tone());
-								syl.insertCharacterAtCursor('h', sym2.tone());
+								syl.insertCharacterAtCursor(str1[0], sym1.tone());
+								syl.insertCharacterAtCursor(str3[0], sym2.tone());
 							}
 							else {
-								syl.insertCharacterAtCursor('O', sym1.tone());
-								syl.insertCharacterAtCursor('H', sym2.tone());
+								syl.insertCharacterAtCursor(str1[0], sym1.tone());
+								syl.insertCharacterAtCursor(str3[0], sym2.tone());
 							}
 
 							i+=2;
@@ -799,12 +802,12 @@ namespace LibHolo
 					// detect case
 					if (str1[0] == tolower(str1[0])) {
 						syl.insertCharacterAtCursor('o', sym1.tone());
-						syl.insertCharacterAtCursor('o');
+						syl.insertCharacterAtCursor(str1[1] == tolower(str1[1]) ? 'o' : 'O');
 					}
 					else
 					{
 						syl.insertCharacterAtCursor('O', sym1.tone());
-						syl.insertCharacterAtCursor('O');						
+						syl.insertCharacterAtCursor(str1[1] == tolower(str1[1]) ? 'o' : 'O');
 					}
 					continue;
 				}
@@ -820,11 +823,11 @@ namespace LibHolo
 						// detect case
 						if (str1[0] == tolower(str1[0])) {
 							syl.insertCharacterAtCursor('t');
-							syl.insertCharacterAtCursor('s');
+							syl.insertCharacterAtCursor(str2[0] == tolower(str2[0]) ? 's' : 'H');
 						}
 						else {
 							syl.insertCharacterAtCursor('T');
-							syl.insertCharacterAtCursor('S');							
+							syl.insertCharacterAtCursor(str2[0] == tolower(str2[0]) ? 's' : 'H');							
 						}
 						
 						i++;
@@ -836,11 +839,11 @@ namespace LibHolo
 						// detect case
 						if (str1[0] == tolower(str1[0])) {
 							syl.insertCharacterAtCursor('u', sym1.tone());
-							syl.insertCharacterAtCursor('e', sym2.tone());
+							syl.insertCharacterAtCursor(str2[0], sym2.tone());
 						}
 						else {
 							syl.insertCharacterAtCursor('U', sym1.tone());
-							syl.insertCharacterAtCursor('E', sym2.tone());							
+							syl.insertCharacterAtCursor(str2[0], sym2.tone());							
 						}
 						
 						i++;
@@ -852,11 +855,11 @@ namespace LibHolo
 						// detect case
 						if (str1[0] == tolower(str1[0])) {
 							syl.insertCharacterAtCursor('u', sym1.tone());
-							syl.insertCharacterAtCursor('a', sym2.tone());
+							syl.insertCharacterAtCursor(str2[0], sym2.tone());
 						}
 						else {
 							syl.insertCharacterAtCursor('U', sym1.tone());
-							syl.insertCharacterAtCursor('A', sym2.tone());
+							syl.insertCharacterAtCursor(str2[0], sym2.tone());
 						}
 						
 						i++;
@@ -868,11 +871,11 @@ namespace LibHolo
 						// detect case
 						if (str1[0] == tolower(str1[0])) {
 							syl.insertCharacterAtCursor('i', sym1.tone());
-							syl.insertCharacterAtCursor('k', sym2.tone());
+							syl.insertCharacterAtCursor(str2[0], sym2.tone());
 						}
 						else {
 							syl.insertCharacterAtCursor('I', sym1.tone());
-							syl.insertCharacterAtCursor('K', sym2.tone());
+							syl.insertCharacterAtCursor(str2[0], sym2.tone());
 						}
 						
 						i++;
@@ -889,13 +892,13 @@ namespace LibHolo
 							// detect case
 							if (str1[0] == tolower(str1[0])) {
 								syl.insertCharacterAtCursor('i', sym1.tone());
-								syl.insertCharacterAtCursor('n', sym2.tone());
-								syl.insertCharacterAtCursor('g', sym3.tone());
+								syl.insertCharacterAtCursor(str2[0], sym2.tone());
+								syl.insertCharacterAtCursor(str3[0], sym3.tone());
 							}
 							else {
 								syl.insertCharacterAtCursor('I', sym1.tone());
-								syl.insertCharacterAtCursor('N', sym2.tone());
-								syl.insertCharacterAtCursor('G', sym3.tone());
+								syl.insertCharacterAtCursor(str2[0], sym2.tone());
+								syl.insertCharacterAtCursor(str3[0], sym3.tone());
 							}
 
 							i+=2;

data/lib/ext/native_syllable_composer/compose.cpp

@@ -8,7 +8,7 @@ using namespace LibHolo;
 
 #include "ruby.h"
 
-VALUE ComposeTLSyllable(int inputType, int outputType, const char *syllable)
+VALUE ComposeTLSyllable(int inputType, int outputType, const char *syllable, int forcePOJStyle)
 {
 	int c;
 	bool composing = false;
@@ -45,8 +45,11 @@ VALUE ComposeTLSyllable(int inputType, int outputType, const char *syllable)
 				
 				if (outputType == POJSyllable)
 					output += syl.convertToPOJSyllable().composedForm();
-				else
-					output += syl.convertToTLSyllable().composedForm();
+				else {
+                    HoloSyllable tl = syl.convertToTLSyllable();
+                    tl.setForcePOJStyle(forcePOJStyle ? true : false);    
+					output += tl.composedForm();
+				}
 				
 				if (emitchar) {
 					output += string(1, emitchar);

data/lib/ext/native_syllable_composer/compose.h

@@ -4,7 +4,7 @@
 extern "C" {
 #endif
 	
-	VALUE ComposeTLSyllable(int inputType, int outputType, const char *syllable);
+	VALUE ComposeTLSyllable(int inputType, int outputType, const char *syllable, int forcePOJStyle);
 
 #ifdef __cplusplus
 }

data/lib/ext/native_syllable_composer/native_syllable_composer.c

@@ -5,16 +5,17 @@
 VALUE syllable_composer = Qnil;
 
 void Init_native_syllable_composer();
-VALUE native_syllable_composer_compose(VALUE self, VALUE rInputType, VALUE rOutputType, VALUE rSyllable);
+VALUE native_syllable_composer_compose(VALUE self, VALUE rInputType, VALUE rOutputType, VALUE rSyllable, VALUE rForcePOJStyleOutput);
 
 void Init_native_syllable_composer() {
 	syllable_composer = rb_define_module("NativeSyllableComposer");
-	rb_define_singleton_method(syllable_composer, "compose", native_syllable_composer_compose, 3);
+	rb_define_singleton_method(syllable_composer, "compose", native_syllable_composer_compose, 4);
 }
 
-VALUE native_syllable_composer_compose(VALUE self, VALUE rInputType, VALUE rOutputType, VALUE rSyllable) {
+VALUE native_syllable_composer_compose(VALUE self, VALUE rInputType, VALUE rOutputType, VALUE rSyllable, VALUE rForcePOJStyleOutput) {
 	int inputType = NUM2INT(rInputType);
 	int outputType = NUM2INT(rOutputType);
+    int forcePOJStyleOutput = NUM2INT(rForcePOJStyleOutput);
 	
 	VALUE rStr = StringValue(rSyllable);
 	
@@ -23,10 +24,10 @@ VALUE native_syllable_composer_compose(VALUE self, VALUE rInputType, VALUE rOutp
 	
 	if (!rStrPtr) return Qnil;
 	
-	char *string = (char*)calloc(1, rStrLen);
-	memcpy(string, rStrPtr,rStrLen);
+	char *string = (char*)calloc(1, rStrLen + 1);
+	memcpy(string, rStrPtr, rStrLen);
 
-	VALUE result = ComposeTLSyllable(inputType, outputType, string);
+	VALUE result = ComposeTLSyllable(inputType, outputType, string, forcePOJStyleOutput);
 	free(string);
 		
 	return result;

data/lib/formosa/syllable_utility.rb

@@ -16,8 +16,8 @@ module Formosa
       # * syllable: the query form of the syllable, such as "goa2", "tai5"
       #
       # Conversion is done automatically when input and output types are different
-      def self.compose_syllable(input_type, output_type, syllable)
-        NativeSyllableComposer.compose(input_type, output_type, syllable)
+      def self.compose_syllable(input_type, output_type, syllable, force_poj_style_output = false)
+        NativeSyllableComposer.compose(input_type, output_type, syllable, force_poj_style_output ? 1 : 0)
       end
 
       TONE_SAMPLE = ["a", "a", "á", "à", "a", "â", "ǎ", "ā", "a̍", "a̋"]

data/lib/formosa/version.rb

@@ -1,8 +1,8 @@
 module Formosa #:nodoc:
   module VERSION #:nodoc:
     MAJOR = 0
-    MINOR = 0
-    TINY  = 1
+    MINOR = 2
+    TINY  = 0
 
     STRING = [MAJOR, MINOR, TINY].join('.')
   end

data/website/index.html

@@ -35,12 +35,22 @@
       <p>Get Version</p>
       <a href="http://rubyforge.org/projects/formosa" class="numbers">0.0.1</a>
     </div>
-    <h1>&#x2192; &#8216;formosa&#8217;</h1>
+    <p>&#x2192; &#8216;Taiwanese language processing&#8217;</p>
 
 
 	<h2>What</h2>
 
 
+	<p>Formosa is a Ruby library for processing Taiwanese languages. Major languages 
+spoken in Taiwan include Holo, Hakka, Mandarin and those of the indigenous
+people. Formosa is the Ruby branch of the lib-formosa project
+(http://code.google.com/p/lib-formosa/).</p>
+
+
+	<p>Currently, we focus on the processing of the Holo (Southern Min) language,
+with necessary tools such as SyllableComposer available for general use.</p>
+
+
 	<h2>Installing</h2>
 
 
@@ -52,13 +62,18 @@
 	<h2>Demonstration of usage</h2>
 
 
-	<h2>Forum</h2>
+<pre>
+$KCODE="u"          # set the Ruby environment to use UTF-8
+require "rubygems" 
+require "formosa" 
+include Formosa::Holo                                      
+poj = SyllableType::POJ
+tl = SyllableType::TL
+SyllableUtility.compose_syllable(poj, tl, "goa2")  # =&gt; guá
+SyllableUtility.compose_syllable(tl, poj, "gua2")  # =&gt; goá
+</pre>
 
-
-	<p><a href="http://groups.google.com/group/formosa">http://groups.google.com/group/formosa</a></p>
-
-
-	<p><span class="caps">TODO</span> &#8211; create Google Group &#8211; formosa</p>
+	<h2>Forum</h2>
 
 
 	<h2>How to submit patches</h2>
@@ -73,15 +88,15 @@
 	<h2>License</h2>
 
 
-	<p>This code is free to use under the terms of the <span class="caps">MIT</span> license.</p>
+	<p>This code is free to use under the terms of the New <span class="caps">BSD</span> license.</p>
 
 
 	<h2>Contact</h2>
 
 
-	<p>Comments are welcome. Send an email to <a href="mailto:FIXME"><span class="caps">FIXME</span> full name</a> email.</p>
+	<p>Comments are welcome. Send an email to lukhnos (at) gmail (dot) com.</p>
     <p class="coda">
-      <a href="mailto:drnicwilliams@gmail.com">Dr Nic</a>, 29th July 2007<br>
+      <a href="mailto:drnicwilliams@gmail.com">Dr Nic</a>, 30th July 2007<br>
       Theme extended from <a href="http://rb2js.rubyforge.org/">Paul Battley</a>
     </p>
 </div>

data/website/index.txt

@@ -1,11 +1,20 @@
 h1. formosa
 
-h1. → 'formosa'
+→ 'Taiwanese language processing'
 
 
 h2. What
 
 
+Formosa is a Ruby library for processing Taiwanese languages. Major languages 
+spoken in Taiwan include Holo, Hakka, Mandarin and those of the indigenous
+people. Formosa is the Ruby branch of the lib-formosa project
+(http://code.google.com/p/lib-formosa/).
+
+Currently, we focus on the processing of the Holo (Southern Min) language,
+with necessary tools such as SyllableComposer available for general use.
+
+
 h2. Installing
 
 <pre syntax="ruby">sudo gem install formosa</pre>
@@ -15,14 +24,19 @@ h2. The basics
 
 h2. Demonstration of usage
 
-
+<pre>
+$KCODE="u"          # set the Ruby environment to use UTF-8
+require "rubygems"
+require "formosa"
+include Formosa::Holo                                      
+poj = SyllableType::POJ
+tl = SyllableType::TL
+SyllableUtility.compose_syllable(poj, tl, "goa2")  # => guá
+SyllableUtility.compose_syllable(tl, poj, "gua2")  # => goá
+</pre>
 
 h2. Forum
 
-"http://groups.google.com/group/formosa":http://groups.google.com/group/formosa
-
-TODO - create Google Group - formosa
-
 h2. How to submit patches
 
 Read the "8 steps for fixing other people's code":http://drnicwilliams.com/2007/06/01/8-steps-for-fixing-other-peoples-code/ and for section "8b: Submit patch to Google Groups":http://drnicwilliams.com/2007/06/01/8-steps-for-fixing-other-peoples-code/#8b-google-groups, use the Google Group above.
@@ -31,8 +45,8 @@ The trunk repository is <code>svn://rubyforge.org/var/svn/formosa/trunk</code> f
 
 h2. License
 
-This code is free to use under the terms of the MIT license. 
+This code is free to use under the terms of the New BSD license. 
 
 h2. Contact
 
-Comments are welcome. Send an email to "FIXME full name":mailto:FIXME email.
+Comments are welcome. Send an email to lukhnos (at) gmail (dot) com.

metadata

@@ -1,10 +1,10 @@
 --- !ruby/object:Gem::Specification 
-rubygems_version: 0.9.2
+rubygems_version: 0.9.4
 specification_version: 1
 name: formosa
 version: !ruby/object:Gem::Version 
-  version: 0.0.1
-date: 2007-07-30 00:00:00 +08:00
+  version: 0.2.0
+date: 2008-01-20 00:00:00 +08:00
 summary: A collection of libraries for Taiwanese languages processing
 require_paths: 
 - lib