summaryrefslogtreecommitdiffstats
path: root/o3d/samples/third_party/codemirror/js/parsesparql.js
blob: 2f2b904f20512f29c339dc897b66d0b1f4b4d698 (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
Editor.Parser = (function() {
  function wordRegexp(words) {
    return new RegExp("^(?:" + words.join("|") + ")$", "i");
  }
  var ops = wordRegexp(["str", "lang", "langmatches", "datatype", "bound", "sameterm", "isiri", "isuri",
                        "isblank", "isliteral", "union", "a"]);
  var keywords = wordRegexp(["base", "prefix", "select", "distinct", "reduced", "construct", "describe",
                             "ask", "from", "named", "where", "order", "limit", "offset", "filter", "optional",
                             "graph", "by", "asc", "desc", ]);
  var operatorChars = /[*+\-<>=&|]/;

  var tokenizeSparql = (function() {
    function normal(source, setState) {
      var ch = source.next();
      if (ch == "$" || ch == "?") {
        source.nextWhile(matcher(/[\w\d]/));
        return "sp-var";
      }
      else if (ch == "<" && !source.applies(matcher(/[\s\u00a0=]/))) {
        source.nextWhile(matcher(/[^\s\u00a0>]/));
        if (source.equals(">")) source.next();
        return "sp-uri";
      }
      else if (ch == "\"" || ch == "'") {
        setState(inLiteral(ch));
        return null;
      }
      else if (/[{}\(\),\.;\[\]]/.test(ch)) {
        return "sp-punc";
      }
      else if (ch == "#") {
        while (!source.endOfLine()) source.next();
        return "sp-comment";
      }
      else if (operatorChars.test(ch)) {
        source.nextWhile(matcher(operatorChars));
        return "sp-operator";
      }
      else if (ch == ":") {
        source.nextWhile(matcher(/[\w\d\._\-]/));
        return "sp-prefixed";
      }
      else {
        source.nextWhile(matcher(/[_\w\d]/));
        if (source.equals(":")) {
          source.next();
          source.nextWhile(matcher(/[\w\d_\-]/));
          return "sp-prefixed";
        }
        var word = source.get(), type;
        if (ops.test(word))
          type = "sp-operator";
        else if (keywords.test(word))
          type = "sp-keyword";
        else
          type = "sp-word";
        return {style: type, content: word};
      }
    }

    function inLiteral(quote) {
      return function(source, setState) {
        var escaped = false;
        while (!source.endOfLine()) {
          var ch = source.next();
          if (ch == quote && !escaped) {
            setState(normal);
            break;
          }
          escaped = ch == "\\";
        }
        return "sp-literal";
      };
    }

    return function(source, startState) {
      return tokenizer(source, startState || normal);
    };
  })();

  function indentSparql(context) {
    return function(nextChars) {
      var firstChar = nextChars && nextChars.charAt(0);
      if (/[\]\}]/.test(firstChar))
        while (context && context.type == "pattern") context = context.prev;

      var closing = context && firstChar == matching[context.type];
      if (!context)
        return 0;
      else if (context.type == "pattern")
        return context.col;
      else if (context.align)
        return context.col - (closing ? context.width : 0);
      else
        return context.indent + (closing ? 0 : 2);
    }
  }

  function parseSparql(source) {
    var tokens = tokenizeSparql(source);
    var context = null, indent = 0, col = 0;
    function pushContext(type, width) {
      context = {prev: context, indent: indent, col: col, type: type, width: width};
    }
    function popContext() {
      context = context.prev;
    }

    var iter = {
      next: function() {
        var token = tokens.next(), type = token.style, content = token.content, width = token.value.length;

        if (content == "\n") {
          token.indentation = indentSparql(context);
          indent = col = 0;
          if (context && context.align == null) context.align = false;
        }
        else if (type == "whitespace" && col == 0) {
          indent = width;
        }
        else if (type != "sp-comment" && context && context.align == null) {
          context.align = true;
        }

        if (content != "\n") col += width;

        if (/[\[\{\(]/.test(content)) {
          pushContext(content, width);
        }
        else if (/[\]\}\)]/.test(content)) {
          while (context && context.type == "pattern")
            popContext();
          if (context && content == matching[context.type]) 
            popContext();
        }
        else if (content == "." && context && context.type == "pattern") {
          popContext();
        }
        else if ((type == "sp-word" || type == "sp-prefixed" || type == "sp-uri" || type == "sp-var" || type == "sp-literal") &&
                 context && /[\{\[]/.test(context.type)) {
          pushContext("pattern", width);
        }

        return token;
      },

      copy: function() {
        var _context = context, _indent = indent, _col = col, _tokenState = tokens.state;
        return function(source) {
          tokens = tokenizeSparql(source, _tokenState);
          context = _context;
          indent = _indent;
          col = _col;
          return iter;
        };
      }
    };
    return iter;
  }

  return {make: parseSparql, electricChars: "}]"};
})();