summaryrefslogtreecommitdiff
path: root/public/vendor/codemirror/mode/xquery/xquery.js
blob: c642ee58fadc2d57581892bd9bd9de37cbb824ae (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
// CodeMirror, copyright (c) by Marijn Haverbeke and others
// Distributed under an MIT license: http://codemirror.net/LICENSE

(function(mod) {
  if (typeof exports == "object" && typeof module == "object") // CommonJS
    mod(require("../../lib/codemirror"));
  else if (typeof define == "function" && define.amd) // AMD
    define(["../../lib/codemirror"], mod);
  else // Plain browser env
    mod(CodeMirror);
})(function(CodeMirror) {
"use strict";

CodeMirror.defineMode("xquery", function() {

  // The keywords object is set to the result of this self executing
  // function. Each keyword is a property of the keywords object whose
  // value is {type: atype, style: astyle}
  var keywords = function(){
    // conveinence functions used to build keywords object
    function kw(type) {return {type: type, style: "keyword"};}
    var A = kw("keyword a")
      , B = kw("keyword b")
      , C = kw("keyword c")
      , operator = kw("operator")
      , atom = {type: "atom", style: "atom"}
      , punctuation = {type: "punctuation", style: null}
      , qualifier = {type: "axis_specifier", style: "qualifier"};

    // kwObj is what is return from this function at the end
    var kwObj = {
      'if': A, 'switch': A, 'while': A, 'for': A,
      'else': B, 'then': B, 'try': B, 'finally': B, 'catch': B,
      'element': C, 'attribute': C, 'let': C, 'implements': C, 'import': C, 'module': C, 'namespace': C,
      'return': C, 'super': C, 'this': C, 'throws': C, 'where': C, 'private': C,
      ',': punctuation,
      'null': atom, 'fn:false()': atom, 'fn:true()': atom
    };

    // a list of 'basic' keywords. For each add a property to kwObj with the value of
    // {type: basic[i], style: "keyword"} e.g. 'after' --> {type: "after", style: "keyword"}
    var basic = ['after','ancestor','ancestor-or-self','and','as','ascending','assert','attribute','before',
    'by','case','cast','child','comment','declare','default','define','descendant','descendant-or-self',
    'descending','document','document-node','element','else','eq','every','except','external','following',
    'following-sibling','follows','for','function','if','import','in','instance','intersect','item',
    'let','module','namespace','node','node','of','only','or','order','parent','precedes','preceding',
    'preceding-sibling','processing-instruction','ref','return','returns','satisfies','schema','schema-element',
    'self','some','sortby','stable','text','then','to','treat','typeswitch','union','variable','version','where',
    'xquery', 'empty-sequence'];
    for(var i=0, l=basic.length; i < l; i++) { kwObj[basic[i]] = kw(basic[i]);};

    // a list of types. For each add a property to kwObj with the value of
    // {type: "atom", style: "atom"}
    var types = ['xs:string', 'xs:float', 'xs:decimal', 'xs:double', 'xs:integer', 'xs:boolean', 'xs:date', 'xs:dateTime',
    'xs:time', 'xs:duration', 'xs:dayTimeDuration', 'xs:time', 'xs:yearMonthDuration', 'numeric', 'xs:hexBinary',
    'xs:base64Binary', 'xs:anyURI', 'xs:QName', 'xs:byte','xs:boolean','xs:anyURI','xf:yearMonthDuration'];
    for(var i=0, l=types.length; i < l; i++) { kwObj[types[i]] = atom;};

    // each operator will add a property to kwObj with value of {type: "operator", style: "keyword"}
    var operators = ['eq', 'ne', 'lt', 'le', 'gt', 'ge', ':=', '=', '>', '>=', '<', '<=', '.', '|', '?', 'and', 'or', 'div', 'idiv', 'mod', '*', '/', '+', '-'];
    for(var i=0, l=operators.length; i < l; i++) { kwObj[operators[i]] = operator;};

    // each axis_specifiers will add a property to kwObj with value of {type: "axis_specifier", style: "qualifier"}
    var axis_specifiers = ["self::", "attribute::", "child::", "descendant::", "descendant-or-self::", "parent::",
    "ancestor::", "ancestor-or-self::", "following::", "preceding::", "following-sibling::", "preceding-sibling::"];
    for(var i=0, l=axis_specifiers.length; i < l; i++) { kwObj[axis_specifiers[i]] = qualifier; };

    return kwObj;
  }();

  function chain(stream, state, f) {
    state.tokenize = f;
    return f(stream, state);
  }

  // the primary mode tokenizer
  function tokenBase(stream, state) {
    var ch = stream.next(),
        mightBeFunction = false,
        isEQName = isEQNameAhead(stream);

    // an XML tag (if not in some sub, chained tokenizer)
    if (ch == "<") {
      if(stream.match("!--", true))
        return chain(stream, state, tokenXMLComment);

      if(stream.match("![CDATA", false)) {
        state.tokenize = tokenCDATA;
        return "tag";
      }

      if(stream.match("?", false)) {
        return chain(stream, state, tokenPreProcessing);
      }

      var isclose = stream.eat("/");
      stream.eatSpace();
      var tagName = "", c;
      while ((c = stream.eat(/[^\s\u00a0=<>\"\'\/?]/))) tagName += c;

      return chain(stream, state, tokenTag(tagName, isclose));
    }
    // start code block
    else if(ch == "{") {
      pushStateStack(state,{ type: "codeblock"});
      return null;
    }
    // end code block
    else if(ch == "}") {
      popStateStack(state);
      return null;
    }
    // if we're in an XML block
    else if(isInXmlBlock(state)) {
      if(ch == ">")
        return "tag";
      else if(ch == "/" && stream.eat(">")) {
        popStateStack(state);
        return "tag";
      }
      else
        return "variable";
    }
    // if a number
    else if (/\d/.test(ch)) {
      stream.match(/^\d*(?:\.\d*)?(?:E[+\-]?\d+)?/);
      return "atom";
    }
    // comment start
    else if (ch === "(" && stream.eat(":")) {
      pushStateStack(state, { type: "comment"});
      return chain(stream, state, tokenComment);
    }
    // quoted string
    else if (  !isEQName && (ch === '"' || ch === "'"))
      return chain(stream, state, tokenString(ch));
    // variable
    else if(ch === "$") {
      return chain(stream, state, tokenVariable);
    }
    // assignment
    else if(ch ===":" && stream.eat("=")) {
      return "keyword";
    }
    // open paren
    else if(ch === "(") {
      pushStateStack(state, { type: "paren"});
      return null;
    }
    // close paren
    else if(ch === ")") {
      popStateStack(state);
      return null;
    }
    // open paren
    else if(ch === "[") {
      pushStateStack(state, { type: "bracket"});
      return null;
    }
    // close paren
    else if(ch === "]") {
      popStateStack(state);
      return null;
    }
    else {
      var known = keywords.propertyIsEnumerable(ch) && keywords[ch];

      // if there's a EQName ahead, consume the rest of the string portion, it's likely a function
      if(isEQName && ch === '\"') while(stream.next() !== '"'){}
      if(isEQName && ch === '\'') while(stream.next() !== '\''){}

      // gobble up a word if the character is not known
      if(!known) stream.eatWhile(/[\w\$_-]/);

      // gobble a colon in the case that is a lib func type call fn:doc
      var foundColon = stream.eat(":");

      // if there's not a second colon, gobble another word. Otherwise, it's probably an axis specifier
      // which should get matched as a keyword
      if(!stream.eat(":") && foundColon) {
        stream.eatWhile(/[\w\$_-]/);
      }
      // if the next non whitespace character is an open paren, this is probably a function (if not a keyword of other sort)
      if(stream.match(/^[ \t]*\(/, false)) {
        mightBeFunction = true;
      }
      // is the word a keyword?
      var word = stream.current();
      known = keywords.propertyIsEnumerable(word) && keywords[word];

      // if we think it's a function call but not yet known,
      // set style to variable for now for lack of something better
      if(mightBeFunction && !known) known = {type: "function_call", style: "variable def"};

      // if the previous word was element, attribute, axis specifier, this word should be the name of that
      if(isInXmlConstructor(state)) {
        popStateStack(state);
        return "variable";
      }
      // as previously checked, if the word is element,attribute, axis specifier, call it an "xmlconstructor" and
      // push the stack so we know to look for it on the next word
      if(word == "element" || word == "attribute" || known.type == "axis_specifier") pushStateStack(state, {type: "xmlconstructor"});

      // if the word is known, return the details of that else just call this a generic 'word'
      return known ? known.style : "variable";
    }
  }

  // handle comments, including nested
  function tokenComment(stream, state) {
    var maybeEnd = false, maybeNested = false, nestedCount = 0, ch;
    while (ch = stream.next()) {
      if (ch == ")" && maybeEnd) {
        if(nestedCount > 0)
          nestedCount--;
        else {
          popStateStack(state);
          break;
        }
      }
      else if(ch == ":" && maybeNested) {
        nestedCount++;
      }
      maybeEnd = (ch == ":");
      maybeNested = (ch == "(");
    }

    return "comment";
  }

  // tokenizer for string literals
  // optionally pass a tokenizer function to set state.tokenize back to when finished
  function tokenString(quote, f) {
    return function(stream, state) {
      var ch;

      if(isInString(state) && stream.current() == quote) {
        popStateStack(state);
        if(f) state.tokenize = f;
        return "string";
      }

      pushStateStack(state, { type: "string", name: quote, tokenize: tokenString(quote, f) });

      // if we're in a string and in an XML block, allow an embedded code block
      if(stream.match("{", false) && isInXmlAttributeBlock(state)) {
        state.tokenize = tokenBase;
        return "string";
      }


      while (ch = stream.next()) {
        if (ch ==  quote) {
          popStateStack(state);
          if(f) state.tokenize = f;
          break;
        }
        else {
          // if we're in a string and in an XML block, allow an embedded code block in an attribute
          if(stream.match("{", false) && isInXmlAttributeBlock(state)) {
            state.tokenize = tokenBase;
            return "string";
          }

        }
      }

      return "string";
    };
  }

  // tokenizer for variables
  function tokenVariable(stream, state) {
    var isVariableChar = /[\w\$_-]/;

    // a variable may start with a quoted EQName so if the next character is quote, consume to the next quote
    if(stream.eat("\"")) {
      while(stream.next() !== '\"'){};
      stream.eat(":");
    } else {
      stream.eatWhile(isVariableChar);
      if(!stream.match(":=", false)) stream.eat(":");
    }
    stream.eatWhile(isVariableChar);
    state.tokenize = tokenBase;
    return "variable";
  }

  // tokenizer for XML tags
  function tokenTag(name, isclose) {
    return function(stream, state) {
      stream.eatSpace();
      if(isclose && stream.eat(">")) {
        popStateStack(state);
        state.tokenize = tokenBase;
        return "tag";
      }
      // self closing tag without attributes?
      if(!stream.eat("/"))
        pushStateStack(state, { type: "tag", name: name, tokenize: tokenBase});
      if(!stream.eat(">")) {
        state.tokenize = tokenAttribute;
        return "tag";
      }
      else {
        state.tokenize = tokenBase;
      }
      return "tag";
    };
  }

  // tokenizer for XML attributes
  function tokenAttribute(stream, state) {
    var ch = stream.next();

    if(ch == "/" && stream.eat(">")) {
      if(isInXmlAttributeBlock(state)) popStateStack(state);
      if(isInXmlBlock(state)) popStateStack(state);
      return "tag";
    }
    if(ch == ">") {
      if(isInXmlAttributeBlock(state)) popStateStack(state);
      return "tag";
    }
    if(ch == "=")
      return null;
    // quoted string
    if (ch == '"' || ch == "'")
      return chain(stream, state, tokenString(ch, tokenAttribute));

    if(!isInXmlAttributeBlock(state))
      pushStateStack(state, { type: "attribute", tokenize: tokenAttribute});

    stream.eat(/[a-zA-Z_:]/);
    stream.eatWhile(/[-a-zA-Z0-9_:.]/);
    stream.eatSpace();

    // the case where the attribute has not value and the tag was closed
    if(stream.match(">", false) || stream.match("/", false)) {
      popStateStack(state);
      state.tokenize = tokenBase;
    }

    return "attribute";
  }

  // handle comments, including nested
  function tokenXMLComment(stream, state) {
    var ch;
    while (ch = stream.next()) {
      if (ch == "-" && stream.match("->", true)) {
        state.tokenize = tokenBase;
        return "comment";
      }
    }
  }


  // handle CDATA
  function tokenCDATA(stream, state) {
    var ch;
    while (ch = stream.next()) {
      if (ch == "]" && stream.match("]", true)) {
        state.tokenize = tokenBase;
        return "comment";
      }
    }
  }

  // handle preprocessing instructions
  function tokenPreProcessing(stream, state) {
    var ch;
    while (ch = stream.next()) {
      if (ch == "?" && stream.match(">", true)) {
        state.tokenize = tokenBase;
        return "comment meta";
      }
    }
  }


  // functions to test the current context of the state
  function isInXmlBlock(state) { return isIn(state, "tag"); }
  function isInXmlAttributeBlock(state) { return isIn(state, "attribute"); }
  function isInXmlConstructor(state) { return isIn(state, "xmlconstructor"); }
  function isInString(state) { return isIn(state, "string"); }

  function isEQNameAhead(stream) {
    // assume we've already eaten a quote (")
    if(stream.current() === '"')
      return stream.match(/^[^\"]+\"\:/, false);
    else if(stream.current() === '\'')
      return stream.match(/^[^\"]+\'\:/, false);
    else
      return false;
  }

  function isIn(state, type) {
    return (state.stack.length && state.stack[state.stack.length - 1].type == type);
  }

  function pushStateStack(state, newState) {
    state.stack.push(newState);
  }

  function popStateStack(state) {
    state.stack.pop();
    var reinstateTokenize = state.stack.length && state.stack[state.stack.length-1].tokenize;
    state.tokenize = reinstateTokenize || tokenBase;
  }

  // the interface for the mode API
  return {
    startState: function() {
      return {
        tokenize: tokenBase,
        cc: [],
        stack: []
      };
    },

    token: function(stream, state) {
      if (stream.eatSpace()) return null;
      var style = state.tokenize(stream, state);
      return style;
    },

    blockCommentStart: "(:",
    blockCommentEnd: ":)"

  };

});

CodeMirror.defineMIME("application/xquery", "xquery");

});