Handle language tags that indicate phonetic IPA transcription

The BCP-47 registry defines a variant subtag "fonipa" that can be used
in combination with arbitrary other language tags. For example,
"rm-CH-fonipa-sursilv" indicates the Sursilvan dialect of Romansh
as used in Switzerland, transcribed used the International Phonetic
Alphabet.

http://www.iana.org/assignments/language-subtag-registry/language-subtag-registry

2 files changed, 21 insertions, 1 deletions

diff --git a/src/hb-ot-tag.cc b/src/hb-ot-tag.cc
index 37604290..a2e5728f 100644
--- a/src/hb-ot-tag.cc
+++ b/src/hb-ot-tag.cc
@@ -733,7 +733,6 @@ static const LangTag ot_languages[] = {
 /*{"fuf?",	HB_TAG('F','T','A',' ')},*/	/* Futa */
 /*{"ar-Syrc?",	HB_TAG('G','A','R',' ')},*/	/* Garshuni */
 /*{"cfm/rnl?",	HB_TAG('H','A','L',' ')},*/	/* Halam */
-/*{"fonipa",	HB_TAG('I','P','P','H')},*/	/* Phonetic transcription—IPA conventions */
 /*{"ga-Latg?/Latg?",	HB_TAG('I','R','T',' ')},*/	/* Irish Traditional */
 /*{"krc",	HB_TAG('K','A','R',' ')},*/	/* Karachay */
 /*{"alw?/ktb?",	HB_TAG('K','E','B',' ')},*/	/* Kebena */
@@ -832,6 +831,14 @@ hb_ot_tag_from_language (hb_language_t language)
     }
   }
 
+  /*
+   * The International Phonetic Alphabet is a variant tag in BCP-47,
+   * which can be applied to any language.
+   */
+  if (strstr (lang_str, "-fonipa")) {
+    return HB_TAG('I','P','P','H');  /* Phonetic transcription—IPA conventions */
+  }
+
   /* Find a language matching in the first component */
   {
     const LangTag *lang_tag;
@@ -901,6 +908,12 @@ hb_ot_tag_to_language (hb_tag_t tag)
     }
   }
 
+  /* struct LangTag has only room for 3-letter language tags. */
+  switch (tag) {
+  case HB_TAG('I','P','P','H'):  /* Phonetic transcription—IPA conventions */
+    return hb_language_from_string ("und-fonipa", -1);
+  }
+
   /* Else return a custom language in the form of "x-hbotABCD" */
   {
     unsigned char buf[11] = "x-hbot";
diff --git a/test/api/test-ot-tag.c b/test/api/test-ot-tag.c
index b667c7d9..29e0aa22 100644
--- a/test/api/test-ot-tag.c
+++ b/test/api/test-ot-tag.c
@@ -222,6 +222,13 @@ test_ot_tag_language (void)
   test_tag_from_language ("XYZ", "xyz"); /* Unknown ISO 639-3 */
   test_tag_from_language ("XYZ", "xyz-qw"); /* Unknown ISO 639-3 */
 
+  /* International Phonetic Alphabet */
+  test_tag_from_language ("IPPH", "en-fonipa");
+  test_tag_from_language ("IPPH", "rm-CH-fonipa-sursilv-x-foobar");
+  test_tag_from_language ("IPPH", "und-fonipa");
+  test_tag_from_language ("IPPH", "zh-fonipa");
+  test_tag_to_language ("IPPH", "und-fonipa");
+
   /* Test that x-hbot overrides the base language */
   test_tag_from_language ("ABC", "fa-x-hbotabc-zxc");
   test_tag_from_language ("ABC", "fa-ir-x-hbotabc-zxc");