xqlint/lib/lexers/xquery_lexer.js

XQuery & JSONiq Quality Checker

'use strict';

var XQueryTokenizer = require('./XQueryTokenizer').XQueryTokenizer;
var Lexer = require('./lexer').Lexer;

var keys = 'after|ancestor|ancestor-or-self|and|as|ascending|attribute|before|case|cast|castable|child|collation|comment|copy|count|declare|default|delete|descendant|descendant-or-self|descending|div|document|document-node|element|else|empty|empty-sequence|end|eq|every|except|first|following|following-sibling|for|function|ge|group|gt|idiv|if|import|insert|instance|intersect|into|is|item|last|le|let|lt|mod|modify|module|namespace|namespace-node|ne|node|only|or|order|ordered|parent|preceding|preceding-sibling|processing-instruction|rename|replace|return|satisfies|schema-attribute|schema-element|self|some|stable|start|switch|text|to|treat|try|typeswitch|union|unordered|validate|where|with|xquery|contains|paragraphs|sentences|times|words|by|collectionreturn|variable|version|option|when|encoding|toswitch|catch|tumbling|sliding|window|at|using|stemming|collection|schema|while|on|nodes|index|external|then|in|updating|value|of|containsbreak|loop|continue|exit|returning|append|json|position|strict'.split('|');

var keywords = keys.map(function(val) { return { name: '\'' + val + '\'', token: 'keyword' }; });
var ncnames = keys.map(function(val) { return { name: '\'' + val + '\'', token: 'text', next: function(stack){ stack.pop(); } }; });

var cdata = 'constant.language';
var number = 'constant';
var xmlcomment = 'comment';
var pi = 'xml-pe';
var pragma = 'constant.buildin';
var n = function(name){
    return '\'' + name + '\'';
};
var Rules = {
    start: [
        { name: n('(#'), token: pragma, next: function(stack){ stack.push('Pragma'); } },
        { name: n('(:'), token: 'comment', next: function(stack){ stack.push('Comment'); } },
        { name: n('(:~'), token: 'comment.doc', next: function(stack){ stack.push('CommentDoc'); } },
        { name: n('<!--'), token: xmlcomment, next: function(stack){ stack.push('XMLComment'); } },
        { name: n('<?'), token: pi, next: function(stack) { stack.push('PI'); } },
        { name: n('\'\''), token: 'string', next: function(stack){ stack.push('AposString'); } },
        { name: n('"'), token: 'string', next: function(stack){ stack.push('QuotString'); } },
        { name: 'Annotation', token: 'support.function' },
        { name: 'ModuleDecl', token: 'keyword', next: function(stack){ stack.push('Prefix'); } },
        { name: 'OptionDecl', token: 'keyword', next: function(stack){ stack.push('_EQName'); } },
        { name: 'AttrTest', token: 'support.type' },
        { name: 'Variable', token: 'variable' },
        { name: n('<![CDATA['), token: cdata, next: function(stack){ stack.push('CData'); } },
        { name: 'IntegerLiteral', token: number },
        { name: 'DecimalLiteral', token: number },
        { name: 'DoubleLiteral', token: number },
        { name: 'Operator', token: 'keyword.operator' },
        { name: 'EQName', token: function(val) { return keys.indexOf(val) !== -1 ? 'keyword' : 'support.function'; } },
        { name: n('('), token: 'lparen' },
        { name: n(')'), token: 'rparen' },
        { name: 'Tag', token: 'meta.tag', next: function(stack){ stack.push('StartTag'); } },
        { name: n('}'), token: 'text', next: function(stack){ if(stack.length > 1) { stack.pop(); } } },
        { name: n('{'), token: 'text', next: function(stack){ stack.push('start'); } } //, next: function(stack){ if(stack.length > 1) { stack.pop(); } } }
    ].concat(keywords),
    _EQName: [
        { name: 'EQName', token: 'text', next: function(stack) { stack.pop(); } }
    ].concat(ncnames),
    Prefix: [
        { name: 'NCName', token: 'text', next: function(stack) { stack.pop(); } }
    ].concat(ncnames),
    StartTag: [
        { name: n('>'), token: 'meta.tag', next: function(stack){ stack.push('TagContent'); } },
        { name: 'QName', token: 'entity.other.attribute-name' },
        { name: n('='), token: 'text' },
        { name: n('\'\''), token: 'string', next: function(stack){ stack.push('AposAttr'); } },
        { name: n('"'), token: 'string', next: function(stack){ stack.push('QuotAttr'); } },
        { name: n('/>'), token: 'meta.tag.r', next: function(stack){ stack.pop(); } }
    ],
    TagContent: [
        { name: 'ElementContentChar', token: 'text' },
        { name: n('<![CDATA['), token: cdata, next: function(stack){ stack.push('CData'); } },
        { name: n('<!--'), token: xmlcomment, next: function(stack){ stack.push('XMLComment'); } },
        { name: 'Tag', token: 'meta.tag', next: function(stack){ stack.push('StartTag'); } },
        { name: 'PredefinedEntityRef', token: 'constant.language.escape' },
        { name: 'CharRef', token: 'constant.language.escape' },
        { name: n('{{'), token: 'text' },
        { name: n('}}'), token: 'text' },
        { name: n('{'), token: 'text', next: function(stack){ stack.push('start'); } },
        { name: 'EndTag', token: 'meta.tag', next: function(stack){ stack.pop(); stack.pop(); } }
    ],
    AposAttr: [
        { name: n('\'\''), token: 'string', next: function(stack){ stack.pop(); } },
        { name: 'EscapeApos', token: 'constant.language.escape' },
        { name: 'AposAttrContentChar', token: 'string' },
        { name: 'PredefinedEntityRef', token: 'constant.language.escape' },
        { name: 'CharRef', token: 'constant.language.escape' },
        { name: n('{{'), token: 'string' },
        { name: n('}}'), token: 'string' },
        { name: n('{'), token: 'text', next: function(stack){ stack.push('start'); } }
    ],
    QuotAttr: [
        { name: n('\"'), token: 'string', next: function(stack){ stack.pop(); } },
        { name: 'EscapeQuot', token: 'constant.language.escape' },
        { name: 'QuotAttrContentChar', token: 'string' },
        { name: 'PredefinedEntityRef', token: 'constant.language.escape' },
        { name: 'CharRef', token: 'constant.language.escape' },
        { name: n('{{'), token: 'string' },
        { name: n('}}'), token: 'string' },
        { name: n('{'), token: 'text', next: function(stack){ stack.push('start'); } }
    ],
    Pragma: [
        { name: 'PragmaContents', token: pragma },
        { name: n('#'), token: pragma },
        { name: n('#)'), token: pragma, next: function(stack){ stack.pop(); } }
    ],
    Comment: [
        { name: 'CommentContents', token: 'comment' },
        { name: n('(:'), token: 'comment', next: function(stack){ stack.push('Comment'); } },
        { name: n(':)'), token: 'comment', next: function(stack){ stack.pop(); } }
    ],
    CommentDoc: [
        { name: 'DocCommentContents', token: 'comment.doc' },
        { name: 'DocTag', token: 'comment.doc.tag' },
        { name: n('(:'), token: 'comment.doc', next: function(stack){ stack.push('CommentDoc'); } },
        { name: n(':)'), token: 'comment.doc', next: function(stack){ stack.pop(); } }
    ],
    XMLComment: [
        { name: 'DirCommentContents', token: xmlcomment },
        { name: n('-->'), token: xmlcomment, next: function(stack){ stack.pop(); } }
    ],
    CData: [
        { name: 'CDataSectionContents', token: cdata },
        { name: n(']]>'), token: cdata, next: function(stack){ stack.pop(); } }
    ],
    PI: [
        { name: 'DirPIContents', token: pi },
        { name: n('?'), token: pi },
        { name: n('?>'), token: pi, next: function(stack){ stack.pop(); } }
    ],
    AposString: [
        { name: n('\'\''), token: 'string', next: function(stack){ stack.pop(); } },
        { name: 'PredefinedEntityRef', token: 'constant.language.escape' },
        { name: 'CharRef', token: 'constant.language.escape' },
        { name: 'EscapeApos', token: 'constant.language.escape' },
        { name: 'AposChar', token: 'string' }
    ],
    QuotString: [
        { name: n('"'), token: 'string', next: function(stack){ stack.pop(); } },
        { name: 'PredefinedEntityRef', token: 'constant.language.escape' },
        { name: 'CharRef', token: 'constant.language.escape' },
        { name: 'EscapeQuot', token: 'constant.language.escape' },
        { name: 'QuotChar', token: 'string' }
    ]
};
    
exports.XQueryLexer = function(){ return new Lexer(XQueryTokenizer, Rules); };