Comment out ot_languages where fallback suffices

src/gen-tag-table.py

@@ -895,11 +895,18 @@ def language_name_intersection (a, b):
 def get_matching_language_name (intersection, candidates):
 	return next (iter (c for c in candidates if not intersection.isdisjoint (get_variant_set (c))))
 
+def same_tag (bcp_47_tag, ot_tags):
+	return len (bcp_47_tag) == 3 and len (ot_tags) == 1 and bcp_47_tag == ot_tags[0].lower ()
+
 for language, tags in sorted (ot.from_bcp_47.items ()):
 	if language == '' or '-' in language:
 		continue
+	commented_out = same_tag (language, tags)
 	for i, tag in enumerate (tags, start=1):
-		print ('  {\"%s\",\t%s},\t/* ' % (language, hb_tag (tag)), end='')
+		print ('%s{\"%s\",\t%s},' % ('/*' if commented_out else '  ', language, hb_tag (tag)), end='')
+		if commented_out:
+			print ('*/', end='')
+		print ('\t/* ', end='')
 		bcp_47_name = bcp_47.names.get (language, '')
 		bcp_47_name_candidates = bcp_47_name.split ('\n')
 		intersection = language_name_intersection (bcp_47_name, ot.names[tag])
@@ -1040,7 +1047,8 @@ print (' * @tag: A language tag.')
 print (' *')
 print (' * Converts @tag to a BCP 47 language tag if it is ambiguous (it corresponds to')
 print (' * many language tags) and the best tag is not the alphabetically first, or if')
-print (' * the best tag consists of multiple subtags.')
+print (' * the best tag consists of multiple subtags, or if the best tag does not appear')
+print (' * in #ot_languages.')
 print (' *')
 print (' * Return value: The #hb_language_t corresponding to the BCP 47 language tag,')
 print (' * or #HB_LANGUAGE_INVALID if @tag is not ambiguous.')
@@ -1091,7 +1099,8 @@ def verify_disambiguation_dict ():
 						'%s is not a valid disambiguation for %s' % (disambiguation[ot_tag], ot_tag))
 			elif ot_tag not in disambiguation:
 				disambiguation[ot_tag] = macrolanguages[0]
-			if disambiguation[ot_tag] == sorted (primary_tags)[0] and '-' not in disambiguation[ot_tag]:
+			different_primary_tags = sorted (t for t in primary_tags if not same_tag (t, ot.from_bcp_47.get (t)))
+			if different_primary_tags and disambiguation[ot_tag] == different_primary_tags[0] and '-' not in disambiguation[ot_tag]:
 				del disambiguation[ot_tag]
 	for ot_tag in disambiguation.keys ():
 		expect (ot_tag in ot.to_bcp_47, 'unknown OT tag: %s' % ot_tag)

src/hb-ot-tag.cc

@@ -426,17 +426,30 @@ hb_ot_tag_to_language (hb_tag_t tag)
     if (ot_languages[i].tag == tag)
       return hb_language_from_string (ot_languages[i].language, -1);
 
-  /* Else return a custom language in the form of "x-hbotABCD" */
+  /* If it's three letters long, assume it's ISO 639-3 and lower-case and use it
+   * (if it's not a registered tag, calling hb_ot_tag_from_language on the
+   * result might not return the same tag as the original tag).
+   * Else return a custom language in the form of "x-hbotABCD". */
   {
-    unsigned char buf[11] = "x-hbot";
+    char buf[11] = "x-hbot";
+    char *str = buf;
     buf[6] = tag >> 24;
     buf[7] = (tag >> 16) & 0xFF;
     buf[8] = (tag >> 8) & 0xFF;
     buf[9] = tag & 0xFF;
     if (buf[9] == 0x20)
+    {
       buf[9] = '\0';
+      if (ISALPHA (buf[6]) && ISALPHA (buf[7]) && ISALPHA (buf[8]))
+      {
+	buf[6] = TOLOWER (buf[6]);
+	buf[7] = TOLOWER (buf[7]);
+	buf[8] = TOLOWER (buf[8]);
+	str += 6;
+      }
+    }
     buf[10] = '\0';
-    return hb_language_from_string ((char *) buf, -1);
+    return hb_language_from_string (str, -1);
   }
 }
 

test/api/test-ot-tag.c

@@ -281,6 +281,8 @@ test_ot_tag_language (void)
   g_assert_cmphex (HB_TAG_CHAR4 ("dflt"), ==, HB_OT_TAG_DEFAULT_LANGUAGE);
   test_language_two_way ("dflt", NULL);
 
+  test_language_two_way ("ALT", "alt");
+
   test_language_two_way ("ARA", "ar");
 
   test_language_two_way ("AZE", "az");
@@ -353,7 +355,8 @@ test_ot_tag_language (void)
   test_tag_from_language ("ZHS", "zh"); /* Chinese */
   test_tag_from_language ("ZHS", "zh-xx");
 
-  test_language_two_way ("ABC", "x-hbotabc");
+  test_language_two_way ("ABC", "abc");
+  test_language_two_way ("ABCD", "x-hbotabcd");
   test_tag_from_language ("ABC", "asdf-asdf-wer-x-hbotabc-zxc");
   test_tag_from_language ("ABC", "asdf-asdf-wer-x-hbotabc");
   test_tag_from_language ("ABCD", "asdf-asdf-wer-x-hbotabcd");