ctype_uca.result, ctype_uca.test: (c885fb04) · Commits · Software / OSDI20 Artifacts / mariadb

mysql-test/r/ctype_uca.result

+106 −0

Original line number	Diff line number	Diff line
		@@ -2015,6 +2015,112 @@ Z,z,Ź,ź,Ż,ż,Ž,ž
		ǁ
		ǂ
		ǃ
		select group_concat(c1 order by c1) from t1 group by c1 collate utf8_hungarian_ci;
		group_concat(c1 order by c1)
		÷
		×
		A,a,À,Á,Â,Ã,Ä,Å,à,á,â,ã,ä,å,Ā,ā,Ă,ă,Ą,ą,Ǎ,ǎ,Ǟ,ǟ,Ǡ,ǡ,Ǻ,ǻ
		AA,Aa,aA,aa
		Æ,æ,Ǣ,ǣ,Ǽ,ǽ
		B,b
		ƀ
		Ɓ
		Ƃ,ƃ
		C,c,Ç,ç,Ć,ć,Ĉ,ĉ,Ċ,ċ,Č,č
		CH,Ch,cH,ch
		Ƈ,ƈ
		D,d,Ď,ď
		DZ,Dz,dZ,dz,Ǆ,ǅ,ǆ,Ǳ,ǲ,ǳ
		Đ,đ
		Ɖ
		Ɗ
		Ƌ,ƌ
		Ð,ð
		E,e,È,É,Ê,Ë,è,é,ê,ë,Ē,ē,Ĕ,ĕ,Ė,ė,Ę,ę,Ě,ě
		Ǝ,ǝ
		Ə
		Ɛ
		F,f
		Ƒ,ƒ
		G,g,Ĝ,ĝ,Ğ,ğ,Ġ,ġ,Ģ,ģ,Ǧ,ǧ,Ǵ,ǵ
		Ǥ,ǥ
		Ɠ
		Ɣ
		Ƣ,ƣ
		H,h,Ĥ,ĥ
		ƕ,Ƕ
		Ħ,ħ
		I,i,Ì,Í,Î,Ï,ì,í,î,ï,Ĩ,ĩ,Ī,ī,Ĭ,ĭ,Į,į,İ,Ǐ,ǐ
		IJ,Ij,iJ,ij,Ĳ,ĳ
		ı
		Ɨ
		Ɩ
		J,j,Ĵ,ĵ,ǰ
		K,k,Ķ,ķ,Ǩ,ǩ
		Ƙ,ƙ
		L,l,Ĺ,ĺ,Ļ,ļ,Ľ,ľ
		Ŀ,ŀ
		LJ,Lj,lJ,lj,Ǉ,ǈ,ǉ
		LL,Ll,lL,ll
		Ł,ł
		ƚ
		ƛ
		M,m
		N,n,Ñ,ñ,Ń,ń,Ņ,ņ,Ň,ň,Ǹ,ǹ
		NJ,Nj,nJ,nj,Ǌ,ǋ,ǌ
		Ɲ
		ƞ
		Ŋ,ŋ
		O,o,Ò,Ó,Ô,Õ,ò,ó,ô,õ,Ō,ō,Ŏ,ŏ,Ơ,ơ,Ǒ,ǒ,Ǫ,ǫ,Ǭ,ǭ
		OE,Oe,oE,oe,Œ,œ
		Ö,ö,Ő,ő
		Ø,ø,Ǿ,ǿ
		Ɔ
		Ɵ
		P,p
		Ƥ,ƥ
		Q,q
		ĸ
		R,r,Ŕ,ŕ,Ŗ,ŗ,Ř,ř
		RR,Rr,rR,rr
		Ʀ
		S,s,Ś,ś,Ŝ,ŝ,Ş,ş,Š,š,ſ
		SS,Ss,sS,ss,ß
		Ʃ
		ƪ
		T,t,Ţ,ţ,Ť,ť
		ƾ
		Ŧ,ŧ
		ƫ
		Ƭ,ƭ
		Ʈ
		U,u,Ù,Ú,Û,ù,ú,û,Ũ,ũ,Ū,ū,Ŭ,ŭ,Ů,ů,Ų,ų,Ư,ư,Ǔ,ǔ,Ǖ,ǖ,Ǘ,ǘ,Ǚ,ǚ,Ǜ,ǜ
		Ü,ü,Ű,ű
		Ɯ
		Ʊ
		V,v
		Ʋ
		W,w,Ŵ,ŵ
		X,x
		Y,y,Ý,ý,ÿ,Ŷ,ŷ,Ÿ
		Ƴ,ƴ
		Z,z,Ź,ź,Ż,ż,Ž,ž
		ƍ
		Ƶ,ƶ
		Ʒ,Ǯ,ǯ
		Ƹ,ƹ
		ƺ
		Þ,þ
		ƿ,Ƿ
		ƻ
		Ƨ,ƨ
		Ƽ,ƽ
		Ƅ,ƅ
		ŉ
		ǀ
		ǁ
		ǂ
		ǃ
		drop table t1;
		SET NAMES utf8;
		CREATE TABLE t1 (c varchar(255) NOT NULL COLLATE utf8_general_ci, INDEX (c));

mysql-test/t/ctype_uca.test

+1 −0

Original line number	Diff line number	Diff line
		@@ -212,6 +212,7 @@ select group_concat(c1 order by c1) from t1 group by c1 collate utf8_slovak_ci;
		select group_concat(c1 order by c1) from t1 group by c1 collate utf8_spanish2_ci;
		select group_concat(c1 order by c1) from t1 group by c1 collate utf8_roman_ci;
		select group_concat(c1 order by c1) from t1 group by c1 collate utf8_esperanto_ci;
		select group_concat(c1 order by c1) from t1 group by c1 collate utf8_hungarian_ci;

		drop table t1;

mysys/charset-def.c

+4 −0

Original line number	Diff line number	Diff line
		@@ -43,6 +43,7 @@ extern CHARSET_INFO my_charset_ucs2_spanish2_uca_ci;
		extern CHARSET_INFO my_charset_ucs2_roman_uca_ci;
		extern CHARSET_INFO my_charset_ucs2_persian_uca_ci;
		extern CHARSET_INFO my_charset_ucs2_esperanto_uca_ci;
		extern CHARSET_INFO my_charset_ucs2_hungarian_uca_ci;
		#endif

		#ifdef HAVE_CHARSET_utf8
		@@ -64,6 +65,7 @@ extern CHARSET_INFO my_charset_utf8_spanish2_uca_ci;
		extern CHARSET_INFO my_charset_utf8_roman_uca_ci;
		extern CHARSET_INFO my_charset_utf8_persian_uca_ci;
		extern CHARSET_INFO my_charset_utf8_esperanto_uca_ci;
		extern CHARSET_INFO my_charset_utf8_hungarian_uca_ci;
		#ifdef HAVE_UTF8_GENERAL_CS
		extern CHARSET_INFO my_charset_utf8_general_cs;
		#endif
		@@ -151,6 +153,7 @@ my_bool init_compiled_charsets(myf flags __attribute__((unused)))
		add_compiled_collation(&my_charset_ucs2_roman_uca_ci);
		add_compiled_collation(&my_charset_ucs2_persian_uca_ci);
		add_compiled_collation(&my_charset_ucs2_esperanto_uca_ci);
		add_compiled_collation(&my_charset_ucs2_hungarian_uca_ci);
		#endif
		#endif

		@@ -184,6 +187,7 @@ my_bool init_compiled_charsets(myf flags __attribute__((unused)))
		add_compiled_collation(&my_charset_utf8_roman_uca_ci);
		add_compiled_collation(&my_charset_utf8_persian_uca_ci);
		add_compiled_collation(&my_charset_utf8_esperanto_uca_ci);
		add_compiled_collation(&my_charset_utf8_hungarian_uca_ci);
		#endif
		#endif

strings/ctype-uca.c

+73 −0

Original line number	Diff line number	Diff line
		@@ -6705,6 +6705,14 @@ static const char esperanto[]=
		"& S < \\u015d <<< \\u015c"
		"& U < \\u016d <<< \\u016c";

		/*
		A simplified version of Hungarian, without consonant contractions.
		*/
		static const char hungarian[]=
		"&O < \\u00F6 <<< \\u00D6 << \\u0151 <<< \\u0150"
		"&U < \\u00FC <<< \\u00DC << \\u0171 <<< \\u0170";


		/*
		Unicode Collation Algorithm:
		Collation element (weight) scanner,
		@@ -8627,6 +8635,39 @@ CHARSET_INFO my_charset_ucs2_esperanto_uca_ci=
		};


		CHARSET_INFO my_charset_ucs2_hungarian_uca_ci=
		{
		146,0,0, /* number */
		MY_CS_COMPILED\|MY_CS_STRNXFRM\|MY_CS_UNICODE,
		"ucs2", /* cs name */
		"ucs2_hungarian_ci",/* name */
		"", /* comment */
		hungarian, /* tailoring */
		NULL, /* ctype */
		NULL, /* to_lower */
		NULL, /* to_upper */
		NULL, /* sort_order */
		NULL, /* contractions */
		NULL, /* sort_order_big*/
		NULL, /* tab_to_uni */
		NULL, /* tab_from_uni */
		my_unicase_default, /* caseinfo */
		NULL, /* state_map */
		NULL, /* ident_map */
		8, /* strxfrm_multiply */
		1, /* caseup_multiply */
		1, /* casedn_multiply */
		2, /* mbminlen */
		2, /* mbmaxlen */
		9, /* min_sort_char */
		0xFFFF, /* max_sort_char */
		' ', /* pad char */
		0, /* escape_with_backslash_is_dangerous */
		&my_charset_ucs2_handler,
		&my_collation_ucs2_uca_handler
		};


		#endif


		@@ -9252,6 +9293,38 @@ CHARSET_INFO my_charset_utf8_esperanto_uca_ci=
		&my_collation_any_uca_handler
		};

		CHARSET_INFO my_charset_utf8_hungarian_uca_ci=
		{
		210,0,0, /* number */
		MY_CS_COMPILED\|MY_CS_STRNXFRM\|MY_CS_UNICODE,
		"utf8", /* cs name */
		"utf8_hungarian_ci",/* name */
		"", /* comment */
		hungarian, /* tailoring */
		ctype_utf8, /* ctype */
		NULL, /* to_lower */
		NULL, /* to_upper */
		NULL, /* sort_order */
		NULL, /* contractions */
		NULL, /* sort_order_big*/
		NULL, /* tab_to_uni */
		NULL, /* tab_from_uni */
		my_unicase_default, /* caseinfo */
		NULL, /* state_map */
		NULL, /* ident_map */
		8, /* strxfrm_multiply */
		1, /* caseup_multiply */
		1, /* casedn_multiply */
		1, /* mbminlen */
		3, /* mbmaxlen */
		9, /* min_sort_char */
		0xFFFF, /* max_sort_char */
		' ', /* pad char */
		0, /* escape_with_backslash_is_dangerous */
		&my_charset_utf8_handler,
		&my_collation_any_uca_handler
		};

		#endif /* HAVE_CHARSET_utf8 */

		#endif /* HAVE_UCA_COLLATIONS */