[config] Add HB_NO_LANGUAGE_LONG and enable in TINY profile

Disables 3letter language tags and more complex ones.

Fixes https://github.com/harfbuzz/harfbuzz/issues/3664

src/gen-tag-table.py

@@ -944,6 +944,8 @@ 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_len in (2, 3):
+	if language_len == 3:
+		print ('#ifndef HB_NO_LANGUAGE_LONG')
 	print ('static const LangTag ot_languages%d[] = {' % language_len)
 	for language, tags in sorted (ot.from_bcp_47.items ()):
 		if language == '' or '-' in language:
@@ -971,6 +973,8 @@ for language_len in (2, 3):
 					write ('%s%s' % (name if len (name) > len (ot_name) else ot_name, scope))
 			print (' */')
 	print ('};')
+	if language_len == 3:
+		print ('#endif')
 	print ()
 
 print ('/**')
@@ -987,7 +991,7 @@ print (' * Converts a multi-subtag BCP 47 language tag to language tags.')
 print (' *')
 print (' * Return value: Whether any language systems were retrieved.')
 print (' **/')
-print ('static bool')
+print ('static inline bool')
 print ('hb_ot_tags_from_complex_language (const char   *lang_str,')
 print ('\t\t\t\t  const char   *limit,')
 print ('\t\t\t\t  unsigned int *count /* IN/OUT */,')
@@ -1130,7 +1134,7 @@ 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.')
 print (' **/')
-print ('static hb_language_t')
+print ('static inline hb_language_t')
 print ('hb_ot_ambiguous_tag_to_language (hb_tag_t tag)')
 print ('{')
 print ('  switch (tag)')

src/hb-config.hh

@@ -64,6 +64,7 @@
 #define HB_NO_FACE_COLLECT_UNICODES
 #define HB_NO_GETENV
 #define HB_NO_HINTING
+#define HB_NO_LANGUAGE_LONG
 #define HB_NO_LANGUAGE_PRIVATE_SUBTAG
 #define HB_NO_LAYOUT_FEATURE_PARAMS
 #define HB_NO_LAYOUT_COLLECT_GLYPHS

src/hb-ot-tag-table.hh

@@ -219,6 +219,7 @@ static const LangTag ot_languages2[] = {
   {HB_TAG('z','u',' ',' '),	HB_TAG('Z','U','L',' ')},	/* Zulu */
 };
 
+#ifndef HB_NO_LANGUAGE_LONG
 static const LangTag ot_languages3[] = {
   {HB_TAG('a','a','e',' '),	HB_TAG('S','Q','I',' ')},	/* Arbëreshë Albanian -> Albanian */
   {HB_TAG('a','a','o',' '),	HB_TAG('A','R','A',' ')},	/* Algerian Saharan Arabic -> Arabic */
@@ -1621,6 +1622,7 @@ static const LangTag ot_languages3[] = {
 /*{HB_TAG('z','z','a',' '),	HB_TAG('Z','Z','A',' ')},*/	/* Zazaki [macrolanguage] */
   {HB_TAG('z','z','j',' '),	HB_TAG('Z','H','A',' ')},	/* Zuojiang Zhuang -> Zhuang */
 };
+#endif
 
 /**
  * hb_ot_tags_from_complex_language:
@@ -1636,7 +1638,7 @@ static const LangTag ot_languages3[] = {
  *
  * Return value: Whether any language systems were retrieved.
  **/
-static bool
+static inline bool
 hb_ot_tags_from_complex_language (const char   *lang_str,
 				  const char   *limit,
 				  unsigned int *count /* IN/OUT */,
@@ -2818,7 +2820,7 @@ out:
  * Return value: The #hb_language_t corresponding to the BCP 47 language tag,
  * or #HB_LANGUAGE_INVALID if @tag is not ambiguous.
  **/
-static hb_language_t
+static inline hb_language_t
 hb_ot_ambiguous_tag_to_language (hb_tag_t tag)
 {
   switch (tag)

src/hb-ot-tag.cc

@@ -263,15 +263,19 @@ hb_ot_tags_from_language (const char   *lang_str,
 			  unsigned int *count,
 			  hb_tag_t     *tags)
 {
-  const char *s;
 
+#ifndef HB_NO_LANGUAGE_LONG
   /* Check for matches of multiple subtags. */
   if (hb_ot_tags_from_complex_language (lang_str, limit, count, tags))
     return;
+#endif
 
   /* Find a language matching in the first component. */
-  s = strchr (lang_str, '-');
+#ifndef HB_NO_LANGUAGE_LONG
+  const char *s; s = strchr (lang_str, '-');
+#endif
   {
+#ifndef HB_NO_LANGUAGE_LONG
     if (s && limit - lang_str >= 6)
     {
       const char *extlang_end = strchr (s + 1, '-');
@@ -280,6 +284,7 @@ hb_ot_tags_from_language (const char   *lang_str,
 	  ISALPHA (s[1]))
 	lang_str = s + 1;
     }
+#endif
     const LangTag *ot_languages = nullptr;
     unsigned ot_languages_len = 0;
     const char *dash = strchr (lang_str, '-');
@@ -289,11 +294,13 @@ hb_ot_tags_from_language (const char   *lang_str,
       ot_languages = ot_languages2;
       ot_languages_len = ARRAY_LENGTH (ot_languages2);
     }
+#ifndef HB_NO_LANGUAGE_LONG
     else if (first_len == 3)
     {
       ot_languages = ot_languages3;
       ot_languages_len = ARRAY_LENGTH (ot_languages3);
     }
+#endif
 
     hb_tag_t lang_tag = hb_tag_from_string (lang_str, first_len);
 
@@ -320,6 +327,7 @@ hb_ot_tags_from_language (const char   *lang_str,
     }
   }
 
+#ifndef HB_NO_LANGUAGE_LONG
   if (!s)
     s = lang_str + strlen (lang_str);
   if (s - lang_str == 3) {
@@ -328,6 +336,7 @@ hb_ot_tags_from_language (const char   *lang_str,
     *count = 1;
     return;
   }
+#endif
 
   *count = 0;
 }
@@ -472,11 +481,13 @@ hb_ot_tag_to_language (hb_tag_t tag)
   if (tag == HB_OT_TAG_DEFAULT_LANGUAGE)
     return nullptr;
 
+#ifndef HB_NO_LANGUAGE_LONG
   {
     hb_language_t disambiguated_tag = hb_ot_ambiguous_tag_to_language (tag);
     if (disambiguated_tag != HB_LANGUAGE_INVALID)
       return disambiguated_tag;
   }
+#endif
 
   char buf[4];
   for (i = 0; i < ARRAY_LENGTH (ot_languages2); i++)
@@ -485,12 +496,14 @@ hb_ot_tag_to_language (hb_tag_t tag)
       hb_tag_to_string (ot_languages2[i].language, buf);
       return hb_language_from_string (buf, 2);
     }
+#ifndef HB_NO_LANGUAGE_LONG
   for (i = 0; i < ARRAY_LENGTH (ot_languages3); i++)
     if (ot_languages3[i].tag == tag)
     {
       hb_tag_to_string (ot_languages3[i].language, buf);
       return hb_language_from_string (buf, 3);
     }
+#endif
 
   /* Return a custom language in the form of "x-hbot-AABBCCDD".
    * If it's three letters long, also guess it's ISO 639-3 and lower-case and
@@ -596,6 +609,7 @@ test_langs_sorted ()
       abort();
     }
   }
+#ifndef HB_NO_LANGUAGE_LONG
   for (unsigned int i = 1; i < ARRAY_LENGTH (ot_languages3); i++)
   {
     int c = ot_languages3[i].cmp (&ot_languages3[i - 1]);
@@ -606,6 +620,7 @@ test_langs_sorted ()
       abort();
     }
   }
+#endif
 }
 
 int