v. 2.3.0, in progress

README.md

@@ -59,98 +59,73 @@ An example for XML:
 // 1. a partial xml grammar in simple JSON format
 var xml_grammar = {
 
-    // prefix ID for regular expressions used in the grammar
-    "RegExpID" : "RE::",
+    // prefix ID for regular expressions, represented as strings, used in the grammar
+    "RegExpID": "RE::",
 
-    //
     // Style model
-    "Style" : {
+    "Style": {
         // lang token type  -> Editor (style) tag
+        "declaration"           : "keyword",
+        "doctype"               : "string",
+        "meta"                  : "string",
         "comment"               : "comment",
-        "meta"                  : "meta",
-        "atom"                  : "string",
         "cdata"                 : "string",
+        "atom"                  : "string",
         "open_tag"              : "keyword",
         "close_tag"             : "keyword",
         "auto_close_open_tag"   : "keyword",
         "close_open_tag"        : "keyword",
         "att"                   : "variable",
-        "id"                    : "variable",
         "number"                : "constant.numeric",
-        "string"                : "string"
+        "string"                : "string",
+        "error"                 : "invalid"
     },
 
-    //
     // Lexical model
     "Lex": {
+        "declaration:block": ["<?xml","?>"],
+        "doctype:block": ["RE::/<!doctype\\b/i",">"],
+        "meta:block": ["RE::/<\\?[_a-zA-Z][\\w\\._\\-]*/","?>"],
         "comment:comment": ["<!--","-->"],
-
         "cdata:block": ["<![CDATA[","]]>"],
-
-        "meta:block": ["RE::/<\\?[_a-zA-Z][\\w\\._\\-]*/","?>"],
-
-        "string:block": {"tokens":[[ "\"" ],[ "'" ]], "multiline":false},
-
-        "number": [
-            // dec
-            "RE::/[0-9]\\d*/",
-            // hex
-            "RE::/#[0-9a-fA-F]+/"
-        ],
-
-        // atoms
-        "atom": [
-            "RE::/&#x[a-fA-F\\d]+;/",
-            "RE::/&#[\\d]+;/",
-            "RE::/&[a-zA-Z][a-zA-Z0-9]*;/"
-        ],
-
-        // tag attribute
+        "string:line-block": [[ "\"" ],[ "'" ]],
+        "number": ["RE::/[0-9]\\d*/", "RE::/#[0-9a-fA-F]+/"],
+        "atom": ["RE::/&#x[a-fA-F\\d]+;/", "RE::/&#[\\d]+;/", "RE::/&[a-zA-Z][a-zA-Z0-9]*;/"],
         "att": "RE::/[_a-zA-Z][_a-zA-Z0-9\\-]*/",
-
-        // tags
         "open_tag": "RE::/<([_a-zA-Z][_a-zA-Z0-9\\-]*)/",
         "close_open_tag": ">",
         "auto_close_open_tag": "/>",
         "close_tag": "RE::/<\\/([_a-zA-Z][_a-zA-Z0-9\\-]*)>/",
-
         "text": "RE::/[^<&]+/",
 
         // actions
-        "ctx_start:action": {"context-start":true},
-        "ctx_end:action": {"context-end":true},
-        // allow to find duplicate xml identifiers, with action tokens
+        "ctx:action": {"context":true},
+        "\\ctx:action": {"context":false},
         "unique:action": {
             "unique": ["id", "$1"],
-            "msg": "Duplicate id attribute \"$0\""
+            "msg": "Duplicate id value \"$0\""
         },
-        // allow to find duplicate xml tag attributes, with action tokens
         "unique_att:action": {
             "unique": ["att", "$0"],
             "in-context":true,
             "msg": "Duplicate attribute \"$0\""
         },
-        // allow to match start/end tags, with action tokens
-        "match:action": {"push":"<$1>"},
-        "matched:action": {
+        "match:action": {"push":"<$1>","ci": true},
+        "\\match:action": {
             "pop": "<$1>",
-            "msg": "Tags \"$0\" and \"$1\" do not match!"
+            "ci": true,
+            "msg": "Tags \"$0\" and \"$1\" do not match"
         },
-        "nomatch:action": {"pop":null}
+        "nomatch:action": {"pop":null},
+        "out_of_place:error": "\"$2>\" can only be at the beginning of XML document"
     },
 
-    //
     // Syntax model (optional)
     "Syntax": {
-        "id_att": "'id' unique_att '=' string unique",
-
-        "tag_att": "att unique_att '=' (string | number)",
-
-        "start_tag": "open_tag match ctx_start (id_att | tag_att)* (close_open_tag | auto_close_open_tag nomatch) ctx_end",
-
-        "end_tag": "close_tag matched",
-
-        "xml": "comment | cdata | meta | start_tag | end_tag | atom | text"
+        "tag_att": "'id'.att unique_att '=' string unique | att unique_att '=' (string | number)",
+        "start_tag": "open_tag match ctx tag_att* (close_open_tag | auto_close_open_tag nomatch) \\ctx",
+        "end_tag": "close_tag \\match",
+        "xml": "(^^ $* declaration? doctype?)? (declaration.error out_of_place | doctype.error out_of_place | comment | meta | cdata | start_tag | end_tag | atom | text)*"
     },
 
     // what to parse and in what order