Use BCP 47 conformant language codes for the languages and accents.

docs/add_language.md

@@ -23,18 +23,17 @@ gradual process of improvement.
 
 ## Language Code
 
-Generally, the language's international
-[ISO 639-1](http://en.wikipedia.org/wiki/ISO_639-1) code is used to identify
-the language. It is used in the filenames which contain the language's
-data. In the examples below the code **"fr"** is used as an example.
-Replace this with the code of your language.
+The language is identified using the
+[BCP 47](https://en.wikipedia.org/wiki/IETF_language_tag) language tag.
+When this is not enough to identify an accent, the
+[bcp47-data](https://github.com/rhdunn/bcp47-data) accents file describes
+the private use tags used by eSpeak NG. For example:
 
-If the language does not have a 2-letter ISO\_639-1 code, then use the
-3-letter ISO\_639-3 code. Language codes may differ from country codes.
-
-It is possible to have different variants of a language for different
-dialects. For example the sound of some phonemes are changed, or some of
-the pronunciation rules differ.
+*  `en` -- English
+*  `en-GB-scotland` -- English with a Scottish accent
+*  `en-GB-x-rp` -- English with a Received Pronunciation accent
+*  `es-419` -- Spanish with a Latin American accent
+*  `fr-CA` -- French with a Canadian accent
 
 ## Language Files
 

docs/voices.md

@@ -84,9 +84,20 @@ listed below.
 
 It selects the default behaviour and characteristics for the language,
 and sets default values for "phonemes", "dictionary" and other
-attributes. The \<language code\> should be a two-letter ISO 639-1
-language code. One or more language variant codes may be appended,
-separated by hyphens. (eg. en-uk-north).
+attributes.
+
+The \<language code\> is a
+[BCP 47](https://en.wikipedia.org/wiki/IETF_language_tag) language tag.
+When this is not enough to identify an accent, the
+[bcp47-data](https://github.com/rhdunn/bcp47-data) accents file describes
+the private use tags used by eSpeak NG. For example:
+
+*  `en` -- English
+*  `en-GB-scotland` -- English with a Scottish accent
+*  `en-GB-x-rp` -- English with a Received Pronunciation accent
+*  `es-419` -- Spanish with a Latin American accent
+*  `fr-CA` -- French with a Canadian accent
+
  
 The optional \<priority\> value gives the preference of this voice
 compared with others for the specified language. A low value indicates a

espeak-data/voices/asia/fa-Latn

@@ -1,6 +1,6 @@
 name persian-pinglish
 // Sometimes, Farsi speakers write Farsi words using English characters, particularly in Chat and SMS (texte messages).), called Pinglish
-language fa-pin
+language fa-Latn
 dictrules 1
 phonemes fa
 

espeak-data/voices/asia/hy-arevmda

@@ -1,5 +1,5 @@
 name armenian-west
-language hy-west
+language hy-arevmda
 language hy  8
 gender male
 

espeak-data/voices/asia/vi-VN-x-central

@@ -1,5 +1,5 @@
 name vietnam_hue
-language vi-hue
+language vi-vn-x-central
 phonemes vi-hue
 dictrules 1
 gender male

espeak-data/voices/asia/vi-VN-x-south

@@ -1,5 +1,5 @@
 name vietnam_sgn
-language vi-sgn
+language vi-vn-x-south
 phonemes vi-sgn
 dictrules 2
 gender male

espeak-data/voices/en

@@ -1,6 +1,5 @@
 name english
 language en-gb  2
-language en-uk  2
 language en 2
 gender male
 

espeak-data/voices/en-us

@@ -1,7 +1,6 @@
 // moving towards US English
 name english-us
 language en-us 2
-language en-r
 language en 3
 gender male
 

espeak-data/voices/es-419

@@ -1,5 +1,5 @@
 name spanish-latin-am
-language es-la
+language es-419
 language es-mx 6
 language es 6
 gender male

espeak-data/voices/mb/mb-en1

@@ -1,5 +1,5 @@
 name english-mb-en1
-language en-uk  3
+language en-gb  3
 language en 2
 gender male
 

espeak-data/voices/other/en-029

@@ -1,6 +1,5 @@
 name en-westindies
-language en-wi
-language en-uk  4
+language en-029
 language en 10
 gender male
 

espeak-data/voices/other/en-GB-scotland

@@ -1,5 +1,5 @@
 name en-scottish
-language en-sc
+language en-gb-scotland
 language en 4
 gender male
 

espeak-data/voices/other/en-GB-x-gbclan

@@ -1,6 +1,6 @@
 name english-north
-language en-uk-north
-language en-uk  3
+language en-gb-x-gbclan
+language en-gb  3
 language en 5
 gender male
 

espeak-data/voices/other/en-GB-x-gbcwmd

@@ -1,6 +1,6 @@
 name english_wmids
-language en-uk-wmids
-language en-uk 9
+language en-gb-x-gbcwmd
+language en-gb 9
 language en 9
 gender male
 

espeak-data/voices/other/en-GB-x-rp

@@ -1,6 +1,6 @@
 name english_rp
-language en-uk-rp
-language en-uk  4
+language en-gb-x-rp
+language en-gb  4
 language en 5
 gender male
 

src/espeak-ng.c

@@ -146,7 +146,7 @@ void DisplayVoices(FILE *f_out, char *language)
 	} else
 		voices = espeak_ListVoices(NULL);
 
-	fprintf(f_out, "Pty Language Age/Gender VoiceName          File          Other Languages\n");
+	fprintf(f_out, "Pty Language       Age/Gender VoiceName          File                 Other Languages\n");
 
 	for (ix = 0; (v = voices[ix]) != NULL; ix++) {
 		count = 0;
@@ -156,7 +156,7 @@ void DisplayVoices(FILE *f_out, char *language)
 			lang_name = p+1;
 
 			if (v->age == 0)
-				strcpy(age_buf, "   ");
+				strcpy(age_buf, " --");
 			else
 				sprintf(age_buf, "%3d", v->age);
 
@@ -168,7 +168,7 @@ void DisplayVoices(FILE *f_out, char *language)
 					if ((buf[j] = c) == 0)
 						break;
 				}
-				fprintf(f_out, "%2d  %-12s%s%c  %-20s %-13s ",
+				fprintf(f_out, "%2d  %-15s%s/%c      %-18s %-20s ",
 				        p[0], lang_name, age_buf, genders[v->gender], buf, v->identifier);
 			} else
 				fprintf(f_out, "(%s %d)", lang_name, p[0]);

src/speak-ng.c

@@ -153,7 +153,7 @@ void DisplayVoices(FILE *f_out, char *language)
 	} else
 		voices = espeak_ListVoices(NULL);
 
-	fprintf(f_out, "Pty Language Age/Gender VoiceName          File          Other Languages\n");
+	fprintf(f_out, "Pty Language       Age/Gender VoiceName          File                 Other Languages\n");
 
 	for (ix = 0; (v = voices[ix]) != NULL; ix++) {
 		count = 0;
@@ -163,7 +163,7 @@ void DisplayVoices(FILE *f_out, char *language)
 			lang_name = p+1;
 
 			if (v->age == 0)
-				strcpy(age_buf, "   ");
+				strcpy(age_buf, " --");
 			else
 				sprintf(age_buf, "%3d", v->age);
 
@@ -175,7 +175,7 @@ void DisplayVoices(FILE *f_out, char *language)
 					if ((buf[j] = c) == 0)
 						break;
 				}
-				fprintf(f_out, "%2d  %-12s%s%c  %-20s %-13s ",
+				fprintf(f_out, "%2d  %-15s%s/%c      %-18s %-20s ",
 				        p[0], lang_name, age_buf, genders[v->gender], buf, v->identifier);
 			} else
 				fprintf(f_out, "(%s %d)", lang_name, p[0]);