Fix multiline comments & add highlights

package.json

@@ -37,7 +37,6 @@
       "scope": "source.xml",
       "path": "tree-sitter-xml",
       "highlights": "tree-sitter-xml/queries/highlights.scm",
-      "injections": "tree-sitter-xml/queries/injections.scm",
       "file-types": [
         "xml",
         "svg",

tree-sitter-dtd/grammar.js

@@ -341,7 +341,7 @@ module.exports = grammar({
 
     Comment: _ => prec.left(token(
       // FIXME: disallow '--'
-      seq('<!--', /.*/, '-->')
+      seq('<!--', /(.|[\r\n])*/, '-->')
     )),
 
     _Eq: $ => seq(O($._S), '=', O($._S))

tree-sitter-dtd/queries/highlights.scm

@@ -1 +1,122 @@
-; TODO: add queries
+;; XML declaration
+
+(XMLDecl "xml" @keyword)
+
+(XMLDecl [ "version" "encoding" ] @property)
+
+(XMLDecl (EncName) @string.special)
+
+(XMLDecl (VersionNum) @number)
+
+;; Processing instructions
+
+(PI) @embedded
+
+(PI (PITarget) @keyword)
+
+;; Element declaration
+
+(elementdecl
+  "ELEMENT" @keyword
+  (Name) @tag)
+
+(contentspec
+  (_ (Name) @property))
+
+"#PCDATA" @type.builtin
+
+[ "EMPTY" "ANY" ] @string.special.symbol
+
+[ "*" "?" "+" ] @operator
+
+;; Entity declaration
+
+(GEDecl
+  "ENTITY" @keyword
+  (Name) @constant)
+
+(GEDecl (EntityValue) @string)
+
+(NDataDecl
+  "NDATA" @keyword
+  (Name) @label)
+
+;; Parsed entity declaration
+
+(PEDecl
+  "ENTITY" @keyword
+  "%" @operator
+  (Name) @constant)
+
+(PEDecl (EntityValue) @string)
+
+;; Notation declaration
+
+(NotationDecl
+  "NOTATION" @keyword
+  (Name) @constant)
+
+(NotationDecl
+  (ExternalID
+    (SystemLiteral (URI) @string.special)))
+
+;; Attlist declaration
+
+(AttlistDecl
+  "ATTLIST" @keyword
+  (Name) @tag)
+
+(AttDef (Name) @property)
+
+(AttDef (Enumeration (Nmtoken) @string))
+
+[
+  (StringType)
+  (TokenizedType)
+] @type.builtin
+
+(NotationType "NOTATION" @type.builtin)
+
+[
+  "#REQUIRED"
+  "#IMPLIED"
+  "#FIXED"
+] @attribute
+
+;; Entities
+
+(EntityRef) @constant
+
+((EntityRef) @constant.builtin
+ (#any-of? @constant.builtin
+   "&" "<" ">" """ "'"))
+
+(CharRef) @constant
+
+(PEReference) @constant
+
+;; External references
+
+[ "PUBLIC" "SYSTEM" ] @keyword
+
+(PubidLiteral) @string.special
+
+(SystemLiteral (URI) @markup.link)
+
+;; Delimiters & punctuation
+
+[ "<?" "?>" "<!" ">" "]]>" ] @punctuation.delimiter
+
+[ "(" ")" "[" ] @punctuation.bracket
+
+[ "\"" "'" ] @punctuation.delimiter
+
+[ "," "|" "=" ] @operator
+
+;; Misc
+
+[ "INCLUDE" "IGNORE" ] @keyword
+
+(Comment) @comment
+
+(ERROR) @error

tree-sitter-dtd/src/grammar.json

@@ -1850,7 +1850,7 @@
             },
             {
               "type": "PATTERN",
-              "value": ".*"
+              "value": "(.|[\\r\\n])*"
             },
             {
               "type": "STRING",

tree-sitter-dtd/src/parser.c

@@ -1408,8 +1408,8 @@ static bool ts_lex(TSLexer *lexer, TSStateId state) {
     case 5:
       if (lookahead == '%') ADVANCE(67);
       if (lookahead == '(') ADVANCE(50);
-      if (lookahead == '1') ADVANCE(11);
-      if (lookahead == '?') ADVANCE(13);
+      if (lookahead == '1') ADVANCE(8);
+      if (lookahead == '?') ADVANCE(10);
       if (lookahead == 'E') ADVANCE(103);
       if (lookahead == 'I') ADVANCE(86);
       if (lookahead == 'N') ADVANCE(101);
@@ -1426,135 +1426,136 @@ static bool ts_lex(TSLexer *lexer, TSStateId state) {
           lookahead != '<') ADVANCE(128);
       END_STATE();
     case 7:
-      if (lookahead == '-') ADVANCE(10);
+      if (lookahead == '-') ADVANCE(42);
       END_STATE();
     case 8:
-      if (lookahead == '-') ADVANCE(8);
-      if (lookahead == '>') ADVANCE(138);
-      if (lookahead != 0 &&
-          lookahead != '\n') ADVANCE(10);
+      if (lookahead == '.') ADVANCE(37);
       END_STATE();
     case 9:
-      if (lookahead == '-') ADVANCE(8);
-      if (lookahead != 0 &&
-          lookahead != '\n') ADVANCE(10);
+      if (lookahead == '>') ADVANCE(47);
       END_STATE();
     case 10:
-      if (lookahead == '-') ADVANCE(9);
-      if (lookahead != 0 &&
-          lookahead != '\n') ADVANCE(10);
+      if (lookahead == '>') ADVANCE(134);
       END_STATE();
     case 11:
-      if (lookahead == '.') ADVANCE(40);
+      if (lookahead == '?') ADVANCE(10);
+      if (sym_Name_character_set_1(lookahead)) ADVANCE(117);
       END_STATE();
     case 12:
-      if (lookahead == '>') ADVANCE(47);
+      if (lookahead == 'A') ADVANCE(32);
       END_STATE();
     case 13:
-      if (lookahead == '>') ADVANCE(134);
+      if (lookahead == 'A') ADVANCE(51);
       END_STATE();
     case 14:
-      if (lookahead == '?') ADVANCE(13);
-      if (sym_Name_character_set_1(lookahead)) ADVANCE(117);
+      if (lookahead == 'C') ADVANCE(15);
       END_STATE();
     case 15:
-      if (lookahead == 'A') ADVANCE(35);
+      if (lookahead == 'D') ADVANCE(12);
       END_STATE();
     case 16:
-      if (lookahead == 'A') ADVANCE(51);
+      if (lookahead == 'D') ADVANCE(66);
       END_STATE();
     case 17:
-      if (lookahead == 'C') ADVANCE(18);
+      if (lookahead == 'D') ADVANCE(65);
       END_STATE();
     case 18:
-      if (lookahead == 'D') ADVANCE(15);
+      if (lookahead == 'D') ADVANCE(64);
       END_STATE();
     case 19:
-      if (lookahead == 'D') ADVANCE(66);
+      if (lookahead == 'E') ADVANCE(30);
       END_STATE();
     case 20:
-      if (lookahead == 'D') ADVANCE(65);
+      if (lookahead == 'E') ADVANCE(16);
       END_STATE();
     case 21:
-      if (lookahead == 'D') ADVANCE(64);
+      if (lookahead == 'E') ADVANCE(17);
       END_STATE();
     case 22:
-      if (lookahead == 'E') ADVANCE(33);
+      if (lookahead == 'E') ADVANCE(18);
       END_STATE();
     case 23:
-      if (lookahead == 'E') ADVANCE(19);
+      if (lookahead == 'F') ADVANCE(24);
+      if (lookahead == 'I') ADVANCE(28);
+      if (lookahead == 'P') ADVANCE(14);
+      if (lookahead == 'R') ADVANCE(19);
       END_STATE();
     case 24:
-      if (lookahead == 'E') ADVANCE(20);
+      if (lookahead == 'I') ADVANCE(34);
       END_STATE();
     case 25:
-      if (lookahead == 'E') ADVANCE(21);
+      if (lookahead == 'I') ADVANCE(31);
       END_STATE();
     case 26:
-      if (lookahead == 'F') ADVANCE(27);
-      if (lookahead == 'I') ADVANCE(31);
-      if (lookahead == 'P') ADVANCE(17);
-      if (lookahead == 'R') ADVANCE(22);
+      if (lookahead == 'I') ADVANCE(21);
       END_STATE();
     case 27:
-      if (lookahead == 'I') ADVANCE(37);
+      if (lookahead == 'L') ADVANCE(26);
       END_STATE();
     case 28:
-      if (lookahead == 'I') ADVANCE(34);
+      if (lookahead == 'M') ADVANCE(29);
       END_STATE();
     case 29:
-      if (lookahead == 'I') ADVANCE(24);
+      if (lookahead == 'P') ADVANCE(27);
       END_STATE();
     case 30:
-      if (lookahead == 'L') ADVANCE(29);
+      if (lookahead == 'Q') ADVANCE(33);
       END_STATE();
     case 31:
-      if (lookahead == 'M') ADVANCE(32);
+      if (lookahead == 'R') ADVANCE(22);
       END_STATE();
     case 32:
-      if (lookahead == 'P') ADVANCE(30);
+      if (lookahead == 'T') ADVANCE(13);
       END_STATE();
     case 33:
-      if (lookahead == 'Q') ADVANCE(36);
+      if (lookahead == 'U') ADVANCE(25);
       END_STATE();
     case 34:
-      if (lookahead == 'R') ADVANCE(25);
+      if (lookahead == 'X') ADVANCE(20);
       END_STATE();
     case 35:
-      if (lookahead == 'T') ADVANCE(16);
+      if (lookahead == ']') ADVANCE(9);
       END_STATE();
     case 36:
-      if (lookahead == 'U') ADVANCE(28);
-      END_STATE();
-    case 37:
-      if (lookahead == 'X') ADVANCE(23);
-      END_STATE();
-    case 38:
-      if (lookahead == ']') ADVANCE(12);
-      END_STATE();
-    case 39:
       if (lookahead == '\t' ||
           lookahead == '\n' ||
           lookahead == '\r' ||
           lookahead == ' ') ADVANCE(85);
       if (sym_Nmtoken_character_set_1(lookahead)) ADVANCE(121);
       END_STATE();
-    case 40:
+    case 37:
       if (('0' <= lookahead && lookahead <= '9')) ADVANCE(135);
       END_STATE();
-    case 41:
+    case 38:
       if (('0' <= lookahead && lookahead <= '9') ||
           ('A' <= lookahead && lookahead <= 'F') ||
           ('a' <= lookahead && lookahead <= 'f')) ADVANCE(126);
       END_STATE();
-    case 42:
+    case 39:
       if (('A' <= lookahead && lookahead <= 'Z') ||
           ('a' <= lookahead && lookahead <= 'z')) ADVANCE(136);
       END_STATE();
+    case 40:
+      if (lookahead != 0 &&
+          lookahead != '-' &&
+          lookahead != '>') ADVANCE(42);
+      if (lookahead == '-') ADVANCE(40);
+      if (lookahead == '>') ADVANCE(138);
+      END_STATE();
+    case 41:
+      if (lookahead != 0 &&
+          lookahead != '-') ADVANCE(42);
+      if (lookahead == '-') ADVANCE(40);
+      END_STATE();
+    case 42:
+      if (lookahead != 0 &&
+          lookahead != '-') ADVANCE(42);
+      if (lookahead == '-') ADVANCE(41);
+      END_STATE();
     case 43:
       if (eof) ADVANCE(44);
       if (lookahead == '"') ADVANCE(68);
-      if (lookahead == '#') ADVANCE(26);
+      if (lookahead == '#') ADVANCE(23);
       if (lookahead == '%') ADVANCE(67);
       if (lookahead == '\'') ADVANCE(82);
       if (lookahead == '(') ADVANCE(50);
@@ -1568,7 +1569,7 @@ static bool ts_lex(TSLexer *lexer, TSStateId state) {
       if (lookahead == '>') ADVANCE(49);
       if (lookahead == '?') ADVANCE(55);
       if (lookahead == '[') ADVANCE(46);
-      if (lookahead == ']') ADVANCE(38);
+      if (lookahead == ']') ADVANCE(35);
       if (lookahead == '|') ADVANCE(52);
       if (lookahead == '\t' ||
           lookahead == '\n' ||
@@ -1706,10 +1707,10 @@ static bool ts_lex(TSLexer *lexer, TSStateId state) {
       END_STATE();
     case 72:
       ACCEPT_TOKEN(aux_sym_EntityValue_token1);
-      if (lookahead == 'F') ADVANCE(27);
-      if (lookahead == 'I') ADVANCE(31);
-      if (lookahead == 'P') ADVANCE(17);
-      if (lookahead == 'R') ADVANCE(22);
+      if (lookahead == 'F') ADVANCE(24);
+      if (lookahead == 'I') ADVANCE(28);
+      if (lookahead == 'P') ADVANCE(14);
+      if (lookahead == 'R') ADVANCE(19);
       END_STATE();
     case 73:
       ACCEPT_TOKEN(aux_sym_EntityValue_token1);
@@ -1737,7 +1738,7 @@ static bool ts_lex(TSLexer *lexer, TSStateId state) {
       END_STATE();
     case 75:
       ACCEPT_TOKEN(aux_sym_EntityValue_token1);
-      if (lookahead == ']') ADVANCE(12);
+      if (lookahead == ']') ADVANCE(9);
       END_STATE();
     case 76:
       ACCEPT_TOKEN(aux_sym_EntityValue_token1);
@@ -2144,9 +2145,9 @@ static bool ts_lex(TSLexer *lexer, TSStateId state) {
       END_STATE();
     case 138:
       ACCEPT_TOKEN(aux_sym_Comment_token1);
-      if (lookahead == '-') ADVANCE(9);
       if (lookahead != 0 &&
-          lookahead != '\n') ADVANCE(10);
+          lookahead != '-') ADVANCE(42);
+      if (lookahead == '-') ADVANCE(41);
       END_STATE();
     case 139:
       ACCEPT_TOKEN(anon_sym_EQ);
@@ -2625,13 +2626,13 @@ static const TSLexMode ts_lex_modes[STATE_COUNT] = {
   [187] = {.lex_state = 43},
   [188] = {.lex_state = 43},
   [189] = {.lex_state = 43},
-  [190] = {.lex_state = 39},
+  [190] = {.lex_state = 36},
   [191] = {.lex_state = 43},
   [192] = {.lex_state = 43},
   [193] = {.lex_state = 43},
   [194] = {.lex_state = 43},
   [195] = {.lex_state = 43},
-  [196] = {.lex_state = 14},
+  [196] = {.lex_state = 11},
   [197] = {.lex_state = 43},
   [198] = {.lex_state = 43},
   [199] = {.lex_state = 5},
@@ -2645,11 +2646,11 @@ static const TSLexMode ts_lex_modes[STATE_COUNT] = {
   [207] = {.lex_state = 43},
   [208] = {.lex_state = 43},
   [209] = {.lex_state = 43},
-  [210] = {.lex_state = 39},
+  [210] = {.lex_state = 36},
   [211] = {.lex_state = 43},
   [212] = {.lex_state = 43},
   [213] = {.lex_state = 43},
-  [214] = {.lex_state = 39},
+  [214] = {.lex_state = 36},
   [215] = {.lex_state = 43},
   [216] = {.lex_state = 43},
   [217] = {.lex_state = 43},
@@ -2667,7 +2668,7 @@ static const TSLexMode ts_lex_modes[STATE_COUNT] = {
   [229] = {.lex_state = 43},
   [230] = {.lex_state = 43},
   [231] = {.lex_state = 5},
-  [232] = {.lex_state = 39},
+  [232] = {.lex_state = 36},
   [233] = {.lex_state = 43},
   [234] = {.lex_state = 43},
   [235] = {.lex_state = 43},
@@ -2677,11 +2678,11 @@ static const TSLexMode ts_lex_modes[STATE_COUNT] = {
   [239] = {.lex_state = 43},
   [240] = {.lex_state = 43},
   [241] = {.lex_state = 43},
-  [242] = {.lex_state = 41},
-  [243] = {.lex_state = 39},
+  [242] = {.lex_state = 38},
+  [243] = {.lex_state = 36},
   [244] = {.lex_state = 43},
   [245] = {.lex_state = 43},
-  [246] = {.lex_state = 39},
+  [246] = {.lex_state = 36},
   [247] = {.lex_state = 43},
   [248] = {.lex_state = 43},
   [249] = {.lex_state = 5},
@@ -2691,9 +2692,9 @@ static const TSLexMode ts_lex_modes[STATE_COUNT] = {
   [253] = {.lex_state = 43},
   [254] = {.lex_state = 43},
   [255] = {.lex_state = 137},
-  [256] = {.lex_state = 42},
+  [256] = {.lex_state = 39},
   [257] = {.lex_state = 43},
-  [258] = {.lex_state = 42},
+  [258] = {.lex_state = 39},
   [259] = {.lex_state = 43},
   [260] = {.lex_state = 43},
   [261] = {.lex_state = 43},
@@ -2730,14 +2731,14 @@ static const TSLexMode ts_lex_modes[STATE_COUNT] = {
   [292] = {.lex_state = 43},
   [293] = {.lex_state = 43},
   [294] = {.lex_state = 43},
-  [295] = {.lex_state = 41},
+  [295] = {.lex_state = 38},
   [296] = {.lex_state = 43},
   [297] = {.lex_state = 43},
   [298] = {.lex_state = 43},
-  [299] = {.lex_state = 41},
+  [299] = {.lex_state = 38},
   [300] = {.lex_state = 43},
   [301] = {.lex_state = 43},
-  [302] = {.lex_state = 41},
+  [302] = {.lex_state = 38},
 };
 
 static const uint16_t ts_parse_table[LARGE_STATE_COUNT][SYMBOL_COUNT] = {

tree-sitter-xml/queries/highlights.scm

@@ -1 +1,171 @@
-; TODO: add queries
+;; XML declaration
+
+(XMLDecl "xml" @keyword)
+
+(XMLDecl [ "version" "encoding" "standalone" ] @property)
+
+(XMLDecl (EncName) @string.special)
+
+(XMLDecl (VersionNum) @number)
+
+(XMLDecl [ "yes" "no" ] @boolean)
+
+;; Processing instructions
+
+(PI) @embedded
+
+(PI (PITarget) @keyword)
+
+;; Element declaration
+
+(elementdecl
+  "ELEMENT" @keyword
+  (Name) @tag)
+
+(contentspec
+  (_ (Name) @property))
+
+"#PCDATA" @type.builtin
+
+[ "EMPTY" "ANY" ] @string.special.symbol
+
+[ "*" "?" "+" ] @operator
+
+;; Entity declaration
+
+(GEDecl
+  "ENTITY" @keyword
+  (Name) @constant)
+
+(GEDecl (EntityValue) @string)
+
+(NDataDecl
+  "NDATA" @keyword
+  (Name) @label)
+
+;; Parsed entity declaration
+
+(PEDecl
+  "ENTITY" @keyword
+  "%" @operator
+  (Name) @constant)
+
+(PEDecl (EntityValue) @string)
+
+;; Notation declaration
+
+(NotationDecl
+  "NOTATION" @keyword
+  (Name) @constant)
+
+(NotationDecl
+  (ExternalID
+    (SystemLiteral (URI) @string.special)))
+
+;; Attlist declaration
+
+(AttlistDecl
+  "ATTLIST" @keyword
+  (Name) @tag)
+
+(AttDef (Name) @property)
+
+(AttDef (Enumeration (Nmtoken) @string))
+
+[
+  (StringType)
+  (TokenizedType)
+] @type.builtin
+
+(NotationType "NOTATION" @type.builtin)
+
+[
+  "#REQUIRED"
+  "#IMPLIED"
+  "#FIXED"
+] @attribute
+
+;; Entities
+
+(EntityRef) @constant
+
+((EntityRef) @constant.builtin
+ (#any-of? @constant.builtin
+   "&" "<" ">" """ "'"))
+
+(CharRef) @constant
+
+(PEReference) @constant
+
+;; External references
+
+[ "PUBLIC" "SYSTEM" ] @keyword
+
+(PubidLiteral) @string.special
+
+(SystemLiteral (URI) @markup.link)
+
+;; Processing instructions
+
+(XmlModelPI "xml-model" @keyword)
+
+(StyleSheetPI "xml-stylesheet" @keyword)
+
+(PseudoAtt (Name) @property)
+
+(PseudoAtt (PseudoAttValue) @string)
+
+;; Doctype declaration
+
+(doctypedecl "DOCTYPE" @keyword)
+
+(doctypedecl (Name) @type)
+
+;; Tags
+
+(STag (Name) @tag)
+
+(ETag (Name) @tag)
+
+(EmptyElemTag (Name) @tag)
+
+;; Attributes
+
+(Attribute (Name) @property)
+
+(Attribute (AttValue) @string)
+
+;; Text
+
+(CharData) @markup
+
+(CDSect
+  (CDStart) @markup.heading
+  (CData) @markup.raw
+  "]]>" @markup.heading)
+
+;; Delimiters & punctuation
+
+[
+ "<?" "?>"
+ "<!" "]]>"
+ "<" ">"
+ "</" "/>"
+] @punctuation.delimiter
+
+[
+  "(" ")"
+  "[" "]"
+] @punctuation.bracket
+
+[ "\"" "'" ] @punctuation.delimiter
+
+[ "," "|" "=" ] @operator
+
+;; Misc
+
+[ "INCLUDE" "IGNORE" ] @keyword
+
+(Comment) @comment
+
+(ERROR) @error

tree-sitter-xml/src/grammar.json

@@ -1886,7 +1886,7 @@
             },
             {
               "type": "PATTERN",
-              "value": ".*"
+              "value": "(.|[\\r\\n])*"
             },
             {
               "type": "STRING",

tree-sitter-xml/src/parser.c

@@ -1651,11 +1651,11 @@ static bool ts_lex(TSLexer *lexer, TSStateId state) {
     case 4:
       if (lookahead == '%') ADVANCE(67);
       if (lookahead == '(') ADVANCE(53);
-      if (lookahead == '?') ADVANCE(13);
+      if (lookahead == '?') ADVANCE(10);
       if (lookahead == 'E') ADVANCE(83);
       if (lookahead == 'I') ADVANCE(74);
       if (lookahead == 'N') ADVANCE(82);
-      if (lookahead == ']') ADVANCE(40);
+      if (lookahead == ']') ADVANCE(37);
       if (lookahead == '\t' ||
           lookahead == '\n' ||
           lookahead == '\r' ||
@@ -1674,148 +1674,149 @@ static bool ts_lex(TSLexer *lexer, TSStateId state) {
       if (lookahead == '[') ADVANCE(48);
       END_STATE();
     case 7:
-      if (lookahead == '-') ADVANCE(10);
+      if (lookahead == '-') ADVANCE(45);
       END_STATE();
     case 8:
-      if (lookahead == '-') ADVANCE(8);
-      if (lookahead == '>') ADVANCE(108);
-      if (lookahead != 0 &&
-          lookahead != '\n') ADVANCE(10);
+      if (lookahead == '.') ADVANCE(39);
       END_STATE();
     case 9:
-      if (lookahead == '-') ADVANCE(8);
-      if (lookahead != 0 &&
-          lookahead != '\n') ADVANCE(10);
+      if (lookahead == '>') ADVANCE(113);
       END_STATE();
     case 10:
-      if (lookahead == '-') ADVANCE(9);
-      if (lookahead != 0 &&
-          lookahead != '\n') ADVANCE(10);
+      if (lookahead == '>') ADVANCE(104);
       END_STATE();
     case 11:
-      if (lookahead == '.') ADVANCE(42);
+      if (lookahead == '>') ADVANCE(50);
       END_STATE();
     case 12:
-      if (lookahead == '>') ADVANCE(113);
+      if (lookahead == '?') ADVANCE(10);
+      if (sym_Name_character_set_1(lookahead)) ADVANCE(90);
       END_STATE();
     case 13:
-      if (lookahead == '>') ADVANCE(104);
+      if (lookahead == 'A') ADVANCE(33);
       END_STATE();
     case 14:
-      if (lookahead == '>') ADVANCE(50);
+      if (lookahead == 'A') ADVANCE(54);
       END_STATE();
     case 15:
-      if (lookahead == '?') ADVANCE(13);
-      if (sym_Name_character_set_1(lookahead)) ADVANCE(90);
+      if (lookahead == 'C') ADVANCE(16);
       END_STATE();
     case 16:
-      if (lookahead == 'A') ADVANCE(36);
+      if (lookahead == 'D') ADVANCE(13);
       END_STATE();
     case 17:
-      if (lookahead == 'A') ADVANCE(54);
+      if (lookahead == 'D') ADVANCE(66);
       END_STATE();
     case 18:
-      if (lookahead == 'C') ADVANCE(19);
+      if (lookahead == 'D') ADVANCE(65);
       END_STATE();
     case 19:
-      if (lookahead == 'D') ADVANCE(16);
+      if (lookahead == 'D') ADVANCE(64);
       END_STATE();
     case 20:
-      if (lookahead == 'D') ADVANCE(66);
+      if (lookahead == 'E') ADVANCE(31);
       END_STATE();
     case 21:
-      if (lookahead == 'D') ADVANCE(65);
+      if (lookahead == 'E') ADVANCE(17);
       END_STATE();
     case 22:
-      if (lookahead == 'D') ADVANCE(64);
+      if (lookahead == 'E') ADVANCE(18);
       END_STATE();
     case 23:
-      if (lookahead == 'E') ADVANCE(34);
+      if (lookahead == 'E') ADVANCE(19);
       END_STATE();
     case 24:
-      if (lookahead == 'E') ADVANCE(20);
+      if (lookahead == 'F') ADVANCE(25);
+      if (lookahead == 'I') ADVANCE(29);
+      if (lookahead == 'P') ADVANCE(15);
+      if (lookahead == 'R') ADVANCE(20);
       END_STATE();
     case 25:
-      if (lookahead == 'E') ADVANCE(21);
+      if (lookahead == 'I') ADVANCE(35);
       END_STATE();
     case 26:
-      if (lookahead == 'E') ADVANCE(22);
+      if (lookahead == 'I') ADVANCE(32);
       END_STATE();
     case 27:
-      if (lookahead == 'F') ADVANCE(28);
-      if (lookahead == 'I') ADVANCE(32);
-      if (lookahead == 'P') ADVANCE(18);
-      if (lookahead == 'R') ADVANCE(23);
+      if (lookahead == 'I') ADVANCE(22);
       END_STATE();
     case 28:
-      if (lookahead == 'I') ADVANCE(38);
+      if (lookahead == 'L') ADVANCE(27);
       END_STATE();
     case 29:
-      if (lookahead == 'I') ADVANCE(35);
+      if (lookahead == 'M') ADVANCE(30);
       END_STATE();
     case 30:
-      if (lookahead == 'I') ADVANCE(25);
+      if (lookahead == 'P') ADVANCE(28);
       END_STATE();
     case 31:
-      if (lookahead == 'L') ADVANCE(30);
+      if (lookahead == 'Q') ADVANCE(34);
       END_STATE();
     case 32:
-      if (lookahead == 'M') ADVANCE(33);
+      if (lookahead == 'R') ADVANCE(23);
       END_STATE();
     case 33:
-      if (lookahead == 'P') ADVANCE(31);
+      if (lookahead == 'T') ADVANCE(14);
       END_STATE();
     case 34:
-      if (lookahead == 'Q') ADVANCE(37);
+      if (lookahead == 'U') ADVANCE(26);
       END_STATE();
     case 35:
-      if (lookahead == 'R') ADVANCE(26);
+      if (lookahead == 'X') ADVANCE(21);
       END_STATE();
     case 36:
-      if (lookahead == 'T') ADVANCE(17);
+      if (lookahead == ']') ADVANCE(118);
       END_STATE();
     case 37:
-      if (lookahead == 'U') ADVANCE(29);
+      if (lookahead == ']') ADVANCE(11);
       END_STATE();
     case 38:
-      if (lookahead == 'X') ADVANCE(24);
-      END_STATE();
-    case 39:
-      if (lookahead == ']') ADVANCE(118);
-      END_STATE();
-    case 40:
-      if (lookahead == ']') ADVANCE(14);
-      END_STATE();
-    case 41:
       if (lookahead == '\t' ||
           lookahead == '\n' ||
           lookahead == '\r' ||
           lookahead == ' ') ADVANCE(73);
       if (sym_Nmtoken_character_set_1(lookahead)) ADVANCE(91);
       END_STATE();
-    case 42:
+    case 39:
       if (('0' <= lookahead && lookahead <= '9')) ADVANCE(105);
       END_STATE();
-    case 43:
+    case 40:
       if (('0' <= lookahead && lookahead <= '9') ||
           ('A' <= lookahead && lookahead <= 'F') ||
           ('a' <= lookahead && lookahead <= 'f')) ADVANCE(96);
       END_STATE();
-    case 44:
+    case 41:
       if (('A' <= lookahead && lookahead <= 'Z') ||
           ('a' <= lookahead && lookahead <= 'z')) ADVANCE(106);
       END_STATE();
-    case 45:
+    case 42:
       if (lookahead != 0 &&
           lookahead != '*' &&
           lookahead != '>' &&
           lookahead != ']' &&
-          lookahead != '|') ADVANCE(39);
+          lookahead != '|') ADVANCE(36);
+      END_STATE();
+    case 43:
+      if (lookahead != 0 &&
+          lookahead != '-' &&
+          lookahead != '>') ADVANCE(45);
+      if (lookahead == '-') ADVANCE(43);
+      if (lookahead == '>') ADVANCE(108);
+      END_STATE();
+    case 44:
+      if (lookahead != 0 &&
+          lookahead != '-') ADVANCE(45);
+      if (lookahead == '-') ADVANCE(43);
+      END_STATE();
+    case 45:
+      if (lookahead != 0 &&
+          lookahead != '-') ADVANCE(45);
+      if (lookahead == '-') ADVANCE(44);
       END_STATE();
     case 46:
       if (eof) ADVANCE(47);
       if (lookahead == '"') ADVANCE(68);
-      if (lookahead == '#') ADVANCE(27);
+      if (lookahead == '#') ADVANCE(24);
       if (lookahead == '%') ADVANCE(67);
       if (lookahead == '\'') ADVANCE(70);
       if (lookahead == '(') ADVANCE(53);
@@ -1823,8 +1824,8 @@ static bool ts_lex(TSLexer *lexer, TSStateId state) {
       if (lookahead == '*') ADVANCE(57);
       if (lookahead == '+') ADVANCE(59);
       if (lookahead == ',') ADVANCE(60);
-      if (lookahead == '/') ADVANCE(12);
-      if (lookahead == '1') ADVANCE(11);
+      if (lookahead == '/') ADVANCE(9);
+      if (lookahead == '1') ADVANCE(8);
       if (lookahead == ';') ADVANCE(72);
       if (lookahead == '<') ADVANCE(112);
       if (lookahead == '=') ADVANCE(109);
@@ -2090,9 +2091,9 @@ static bool ts_lex(TSLexer *lexer, TSStateId state) {
       END_STATE();
     case 108:
       ACCEPT_TOKEN(aux_sym_Comment_token1);
-      if (lookahead == '-') ADVANCE(9);
       if (lookahead != 0 &&
-          lookahead != '\n') ADVANCE(10);
+          lookahead != '-') ADVANCE(45);
+      if (lookahead == '-') ADVANCE(44);
       END_STATE();
     case 109:
       ACCEPT_TOKEN(anon_sym_EQ);
@@ -2131,7 +2132,7 @@ static bool ts_lex(TSLexer *lexer, TSStateId state) {
       END_STATE();
     case 117:
       ACCEPT_TOKEN(sym_CData);
-      if (lookahead == ']') ADVANCE(45);
+      if (lookahead == ']') ADVANCE(42);
       if (lookahead != 0) ADVANCE(119);
       END_STATE();
     case 118:
@@ -2740,27 +2741,27 @@ static const TSLexMode ts_lex_modes[STATE_COUNT] = {
   [189] = {.lex_state = 4},
   [190] = {.lex_state = 4},
   [191] = {.lex_state = 46},
-  [192] = {.lex_state = 15},
+  [192] = {.lex_state = 12},
   [193] = {.lex_state = 46},
   [194] = {.lex_state = 46},
   [195] = {.lex_state = 46},
   [196] = {.lex_state = 4},
-  [197] = {.lex_state = 15},
+  [197] = {.lex_state = 12},
   [198] = {.lex_state = 4},
   [199] = {.lex_state = 46},
   [200] = {.lex_state = 46},
   [201] = {.lex_state = 46},
-  [202] = {.lex_state = 15},
+  [202] = {.lex_state = 12},
   [203] = {.lex_state = 4},
   [204] = {.lex_state = 46},
   [205] = {.lex_state = 46},
-  [206] = {.lex_state = 15},
+  [206] = {.lex_state = 12},
   [207] = {.lex_state = 4},
   [208] = {.lex_state = 46},
   [209] = {.lex_state = 46},
   [210] = {.lex_state = 46},
   [211] = {.lex_state = 46},
-  [212] = {.lex_state = 15},
+  [212] = {.lex_state = 12},
   [213] = {.lex_state = 46},
   [214] = {.lex_state = 46},
   [215] = {.lex_state = 46},
@@ -2832,7 +2833,7 @@ static const TSLexMode ts_lex_modes[STATE_COUNT] = {
   [281] = {.lex_state = 46},
   [282] = {.lex_state = 46},
   [283] = {.lex_state = 46},
-  [284] = {.lex_state = 41},
+  [284] = {.lex_state = 38},
   [285] = {.lex_state = 46},
   [286] = {.lex_state = 46},
   [287] = {.lex_state = 46},
@@ -2859,14 +2860,14 @@ static const TSLexMode ts_lex_modes[STATE_COUNT] = {
   [308] = {.lex_state = 46},
   [309] = {.lex_state = 46},
   [310] = {.lex_state = 46},
-  [311] = {.lex_state = 41},
+  [311] = {.lex_state = 38},
   [312] = {.lex_state = 46},
   [313] = {.lex_state = 46},
   [314] = {.lex_state = 46},
   [315] = {.lex_state = 46},
   [316] = {.lex_state = 4},
   [317] = {.lex_state = 46},
-  [318] = {.lex_state = 15},
+  [318] = {.lex_state = 12},
   [319] = {.lex_state = 46},
   [320] = {.lex_state = 46},
   [321] = {.lex_state = 46},
@@ -2880,7 +2881,7 @@ static const TSLexMode ts_lex_modes[STATE_COUNT] = {
   [329] = {.lex_state = 46},
   [330] = {.lex_state = 46},
   [331] = {.lex_state = 46},
-  [332] = {.lex_state = 41},
+  [332] = {.lex_state = 38},
   [333] = {.lex_state = 46},
   [334] = {.lex_state = 46},
   [335] = {.lex_state = 46},
@@ -2889,7 +2890,7 @@ static const TSLexMode ts_lex_modes[STATE_COUNT] = {
   [338] = {.lex_state = 46},
   [339] = {.lex_state = 46},
   [340] = {.lex_state = 46},
-  [341] = {.lex_state = 41},
+  [341] = {.lex_state = 38},
   [342] = {.lex_state = 46},
   [343] = {.lex_state = 102},
   [344] = {.lex_state = 4},
@@ -2897,7 +2898,7 @@ static const TSLexMode ts_lex_modes[STATE_COUNT] = {
   [346] = {.lex_state = 46},
   [347] = {.lex_state = 46},
   [348] = {.lex_state = 46},
-  [349] = {.lex_state = 41},
+  [349] = {.lex_state = 38},
   [350] = {.lex_state = 101},
   [351] = {.lex_state = 46},
   [352] = {.lex_state = 100},
@@ -2908,7 +2909,7 @@ static const TSLexMode ts_lex_modes[STATE_COUNT] = {
   [357] = {.lex_state = 46},
   [358] = {.lex_state = 46},
   [359] = {.lex_state = 46},
-  [360] = {.lex_state = 41},
+  [360] = {.lex_state = 38},
   [361] = {.lex_state = 46},
   [362] = {.lex_state = 46},
   [363] = {.lex_state = 46},
@@ -2950,7 +2951,7 @@ static const TSLexMode ts_lex_modes[STATE_COUNT] = {
   [399] = {.lex_state = 46},
   [400] = {.lex_state = 46},
   [401] = {.lex_state = 46},
-  [402] = {.lex_state = 43},
+  [402] = {.lex_state = 40},
   [403] = {.lex_state = 4},
   [404] = {.lex_state = 46},
   [405] = {.lex_state = 46},
@@ -2958,10 +2959,10 @@ static const TSLexMode ts_lex_modes[STATE_COUNT] = {
   [407] = {.lex_state = 46},
   [408] = {.lex_state = 46},
   [409] = {.lex_state = 46},
-  [410] = {.lex_state = 44},
+  [410] = {.lex_state = 41},
   [411] = {.lex_state = 46},
   [412] = {.lex_state = 46},
-  [413] = {.lex_state = 44},
+  [413] = {.lex_state = 41},
   [414] = {.lex_state = 46},
   [415] = {.lex_state = 0},
   [416] = {.lex_state = 46},
@@ -2981,20 +2982,20 @@ static const TSLexMode ts_lex_modes[STATE_COUNT] = {
   [430] = {.lex_state = 46},
   [431] = {.lex_state = 46},
   [432] = {.lex_state = 4},
-  [433] = {.lex_state = 43},
+  [433] = {.lex_state = 40},
   [434] = {.lex_state = 46},
   [435] = {.lex_state = 107},
   [436] = {.lex_state = 46},
   [437] = {.lex_state = 46},
   [438] = {.lex_state = 4},
-  [439] = {.lex_state = 43},
+  [439] = {.lex_state = 40},
   [440] = {.lex_state = 46},
   [441] = {.lex_state = 46},
   [442] = {.lex_state = 4},
-  [443] = {.lex_state = 43},
+  [443] = {.lex_state = 40},
   [444] = {.lex_state = 46},
   [445] = {.lex_state = 4},
-  [446] = {.lex_state = 43},
+  [446] = {.lex_state = 40},
 };
 
 static const uint16_t ts_parse_table[LARGE_STATE_COUNT][SYMBOL_COUNT] = {