summaryrefslogtreecommitdiff
path: root/src/library/scala/xml/Utility.scala
blob: 00f93b9ffc718643bb64c76e29ec34f0130b318f (plain) (blame)
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
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
/*                     __                                               *\
**     ________ ___   / /  ___     Scala API                            **
**    / __/ __// _ | / /  / _ |    (c) 2003-2007, LAMP/EPFL             **
**  __\ \/ /__/ __ |/ /__/ __ |    http://scala-lang.org/               **
** /____/\___/_/ |_/____/_/ | |                                         **
**                          |/                                          **
\*                                                                      */

// $Id$


package scala.xml

import collection.mutable.{Set, HashSet}

/**
 * The <code>Utility</code> object provides utility functions for processing
 * instances of bound and not bound XML classes, as well as escaping text nodes.
 *
 * @author Burak Emir
 */
object Utility extends AnyRef with parsing.TokenTests {


  /** trims an element - call this method, when you know that it is an
   *  element (and not a text node) so you know that it will not be trimmed
   *  away. With this assumption, the function can return a <code>Node</code>,
   *  rather than a <code>Seq[Node]</code>. If you don't know, call
   *  <code>trimProper</code> and account for the fact that you may get back
   *  an empty sequence of nodes.
   *
   *  precondition: node is not a text node (it might be trimmed)
   */

  def trim(x:Node): Node = x match {
    case Elem(pre,lab,md,scp,child@_*) =>
      Elem(pre,lab,md,scp, (child flatMap trimProper):_*)
  }

  /** trim a child of an element. Attribute values and Atom nodes that are not Text nodes are unaffected
   */
  def trimProper(x:Node): Seq[Node] = x match {
    case Elem(pre,lab,md,scp,child@_*) =>
      Elem(pre,lab,md,scp, (child flatMap trimProper):_*)
    case Text(s) =>
      new TextBuffer().append(s).toText
    case _ =>
      x
  }
  /** returns a sorted attribute list */
  def sort(md: MetaData): MetaData = if((md eq Null) || (md.next eq Null)) md else {
    val key = md.key
    val smaller = sort(md.filter { m => m.key < key })
    val greater = sort(md.filter { m => m.key > key })
    smaller.append( Null ).append(md.copy ( greater ))
  }

  /** returns the node with its attribute list sorted alphabetically (prefixes are ignored) */
  def sort(n:Node): Node = n match {
	  case Elem(pre,lab,md,scp,child@_*) =>
		  Elem(pre,lab,sort(md),scp, (child map sort):_*)
	  case _ => n
  }

  /** @deprecated a string might also be Atom(s) - define your own conversion
   */
  @deprecated def view(s: String): Text = Text(s)

  /**
   * Escapes the characters &lt; &gt; &amp; and &quot; from string.
   *
   * @param text ...
   * @return     ...
   */
  final def escape(text: String): String =
    escape(text, new StringBuilder()).toString()

  /**
   * Appends escaped string to <code>s</code>.
   *
   * @param text ...
   * @param s    ...
   * @return     ...
   */
  final def escape(text: String, s: StringBuilder): StringBuilder = {
    for (c <- text.elements) c match {
      case '<' => s.append("&lt;")
      case '>' => s.append("&gt;")
      case '&' => s.append("&amp;")
      case '"' => s.append("&quot;")
      //case '\'' => s.append("&apos;") // is valid xhtml but not html, and IE doesn't know it, says jweb
      case _   => s.append(c)
    }
    s
  }

  /**
   * Appends unescaped string to <code>s</code>, amp becomes &amp;
   * lt becomes &lt; etc..
   *
   * @param ref ...
   * @param s   ...
   * @return    <code>null</code> if <code>ref</code> was not a predefined
   *            entity.
   */
  final def unescape(ref: String, s: StringBuilder): StringBuilder =
    ref match {
      case "lt"   => s.append('<')
      case "gt"   => s.append('>')
      case "amp"  => s.append('&')
      case "quot" => s.append('"')
      case "apos" => s.append('\'')
      case _   => null
    }

  /**
   * Returns a set of all namespaces used in a sequence of nodes
   * and all their descendants, including the empty namespaces.
   *
   * @param nodes ...
   * @return      ...
   */
  def collectNamespaces(nodes: Seq[Node]): Set[String] = {
    var m = new HashSet[String]()
    val it = nodes.elements
    while (it.hasNext)
      collectNamespaces(it.next, m);
    m
  }

  /**
   * Adds all namespaces in node to set.
   *
   * @param n   ...
   * @param set ...
   */
  def collectNamespaces(n: Node, set: Set[String]) {
    if (n.typeTag$ >= 0) {
      set += n.namespace
      for (a <- n.attributes) a match {
        case _:PrefixedAttribute =>
          set += a.getNamespace(n)
        case _ =>
      }
      for (i <- n.child)
        collectNamespaces(i, set)
    }
  }

  /**
   * Returs the string representation of an XML node, with comments stripped
   * the comments.
   *
   * @param n the XML node
   * @return  the string representation of node <code>n</code>.
   *
   * @see "toXML(Node, Boolean)"
   */
  def toXML(n: Node): String = toXML(n, true)

  /**
   * Return the string representation of a Node. uses namespace mapping from
   *  <code>defaultPrefixes(n)</code>.
   *
   * @param n            the XML node
   * @param stripComment ...
   * @return             ...
   *
   * @todo define a way to escape literal characters to &amp;xx; references
   */
  def toXML(n: Node, stripComment: Boolean): String = {
    val sb = new StringBuilder()
    toXML(n, TopScope, sb, stripComment)
    sb.toString()
  }


  /**
   * Appends a tree to the given stringbuffer within given namespace scope.
   *
   * @param n            the node
   * @param pscope       the parent scope
   * @param sb           stringbuffer to append to
   * @param stripComment if true, strip comments
   */
  def toXML(x: Node, pscope: NamespaceBinding, sb: StringBuilder, stripComment: Boolean) {
    x match {

      case c: Comment if !stripComment =>
        c.toString(sb)

      case x: SpecialNode =>
        x.toString(sb)

      case g: Group =>
        for (c <- g.nodes) toXML(c, x.scope, sb, stripComment)

      case _  =>
        // print tag with namespace declarations
        sb.append('<')
        x.nameToString(sb)
        if (x.attributes ne null) x.attributes.toString(sb)
        x.scope.toString(sb, pscope)
        sb.append('>')
        sequenceToXML(x.child, pscope, sb, stripComment)
        sb.append("</")
        x.nameToString(sb)
        sb.append('>')
    }
  }

  /**
   * @param children     ...
   * @param pscope       ...
   * @param sb           ...
   * @param stripComment ...
   */
  def sequenceToXML(children: Seq[Node], pscope: NamespaceBinding,
                    sb: StringBuilder, stripComment: Boolean) {
    if (children.isEmpty)
      return
    else if (children forall { y => y.isInstanceOf[Atom[Any]] && !y.isInstanceOf[Text] }) { // add space
      val it = children.elements
      val f = it.next
      toXML(f, f.scope, sb, stripComment)
      while (it.hasNext) {
        val x = it.next
        sb.append(' ')
        toXML(x, x.scope, sb, stripComment)
      }
    } else {
      for (c <- children) toXML(c, c.scope, sb, stripComment)
    }
  }

  /**
   * Returns prefix of qualified name if any.
   *
   * @param name ...
   * @return     ...
   */
  final def prefix(name: String): Option[String] = {
    val i = name.indexOf(':'.asInstanceOf[Int])
    if (i != -1) Some(name.substring(0, i)) else None
  }

  /**
   * Returns a hashcode for the given constituents of a node
   *
   * @param uri
   * @param label
   * @param attribHashCode
   * @param children
   */
  def hashCode(pre: String, label: String, attribHashCode: Int, scpeHash: Int, children: Seq[Node]) = {
    ( if(pre ne null) {41 * pre.hashCode() % 7} else {0})
    + label.hashCode() * 53
    + attribHashCode * 7
    + scpeHash * 31
    + children.hashCode()
  }

  /**
   * Returns a hashcode for the given constituents of a node
   *
   * @param uri
   * @param label
   * @param attribs
   * @param children
  def hashCode(uri: String, label: String, attribs: scala.collection.mutable.HashMap[(String,String),String], scpe: Int, children: Seq[Node]): Int = {
    41 * uri.hashCode() % 7 + label.hashCode() + attribs.toList.hashCode() + scpe + children.hashCode()
  }
   */

  /**
   * @param s ...
   * @return  ...
   */
  def systemLiteralToString(s: String): String = {
    val sb = new StringBuilder()
    systemLiteralToString(sb, s)
    sb.toString()
  }

  /**
   * @param sb ...
   * @param s  ...
   * @return   ...
   */
  def systemLiteralToString(sb: StringBuilder, s: String): StringBuilder = {
    sb.append("SYSTEM ")
    appendQuoted(s, sb)
  }

  /**
   * @param s ...
   * @return  ...
   */
  def publicLiteralToString(s: String): String = {
    val sb = new StringBuilder()
    systemLiteralToString(sb, s)
    sb.toString()
  }

  /**
   * @param sb ...
   * @param s  ...
   * @return   ...
   */
  def publicLiteralToString(sb: StringBuilder, s: String): StringBuilder = {
    sb.append("PUBLIC \"").append(s).append('"')
  }

  /**
   * Appends &quot;s&quot; if string <code>s</code> does not contain &quot;,
   * &apos;s&apos; otherwise.
   *
   * @param s  ...
   * @param sb ...
   * @return   ...
   */
  def appendQuoted(s: String, sb: StringBuilder) = {
    val ch = if (s.indexOf('"'.asInstanceOf[Int]) == -1) '"' else '\'';
    sb.append(ch).append(s).append(ch)
  }

  /**
   * Appends &quot;s&quot; and escapes and &quot; i s with \&quot;
   *
   * @param s  ...
   * @param sb ...
   * @return   ...
   */
  def appendEscapedQuoted(s: String, sb: StringBuilder): StringBuilder = {
    sb.append('"')
    for (c <- s) c match {
      case '"' => sb.append('\\'); sb.append('"')
      case _   => sb.append(c)
    }
    sb.append('"')
  }

  /**
   * @param s     ...
   * @param index ...
   * @return      ...
   */
  def getName(s: String, index: Int): String = {
    var i = index;
    val sb = new StringBuilder();
    if (i < s.length) {
      var c = s.charAt(i);
      if (isNameStart(s.charAt(i)))
        while (i < s.length && { c = s.charAt(i); isNameChar(c)}) {
          sb.append(c)
          i = i + 1
        }
      sb.toString()
    } else null
  }

  /**
   * Returns <code>null</code> if the value is a correct attribute value,
   * error message if it isn't.
   *
   * @param value ...
   * @return      ...
   */
  def checkAttributeValue(value: String): String = {
    var i = 0
    while (i < value.length) {
      value.charAt(i) match {
        case '<' =>
          return "< not allowed in attribute value";
        case '&' =>
          val n = getName(value, i+1)
          if (n eq null)
            return "malformed entity reference in attribute value ["+value+"]";
          i = i + n.length + 1
          if (i >= value.length || value.charAt(i) != ';')
            return "malformed entity reference in attribute value ["+value+"]";
        case _   =>
      }
      i = i + 1
    }
    null
  }

  /**
   * new
   *
   * @param value ...
   * @return      ...
   */
  def parseAttributeValue(value: String): Seq[Node] = {
    val zs: Seq[Char] = value
    val sb  = new StringBuilder
    var rfb: StringBuilder = null
    val nb = new NodeBuffer()
    val it = zs.elements
    while (it.hasNext) {
      var c = it.next
      c match {
        case '&' => // entity! flush buffer into text node
          it.next match {
            case '#' =>
              c = it.next
              val theChar = parseCharRef ({ ()=> c },{ () => c = it.next },{s => throw new RuntimeException(s)})
              sb.append(theChar)

            case x =>
              if (rfb eq null) rfb = new StringBuilder()
              rfb.append(x)
              c = it.next
              while (c != ';') {
                rfb.append(c)
                c = it.next
              }
              val ref = rfb.toString()
              rfb.setLength(0)
              unescape(ref,sb) match {
                case null =>
                  if (sb.length > 0) {          // flush buffer
                    nb += Text(sb.toString())
                    sb.setLength(0)
                  }
                  nb += EntityRef(sb.toString()) // add entityref
                case _ =>
              }
          }
        case x   =>
          sb.append(x)
      }
    }
    if (sb.length > 0) { // flush buffer
      val x = Text(sb.toString())
      if (nb.length == 0)
        return x
      else
        nb += x
    }
    return nb
  }

  /**
   * <pre>
   *   CharRef ::= "&amp;#" '0'..'9' {'0'..'9'} ";"
   *             | "&amp;#x" '0'..'9'|'A'..'F'|'a'..'f' { hexdigit } ";"
   * </pre>
   * <p>
   *   see [66]
   * <p>
   *
   * @param ch                ...
   * @param nextch            ...
   * @param reportSyntaxError ...
   * @return                  ...
   */
  def parseCharRef(ch: () => Char, nextch: () => Unit, reportSyntaxError:(String) => Unit): String = {
    val hex  = (ch() == 'x') && { nextch(); true }
    val base = if (hex) 16 else 10
    var i = 0
    while (ch() != ';') {
      ch() match {
        case '0' | '1' | '2' | '3' | '4' | '5' | '6' | '7' | '8' | '9' =>
          i = i * base + ch().asDigit
        case 'a' | 'b' | 'c' | 'd' | 'e' | 'f'
           | 'A' | 'B' | 'C' | 'D' | 'E' | 'F' =>
          if (! hex)
            reportSyntaxError("hex char not allowed in decimal char ref\n" +
                              "Did you mean to write &#x ?")
          else
            i = i * base + ch().asDigit
        case _ =>
          reportSyntaxError("character '" + ch() + "' not allowed in char ref\n")
      }
      nextch()
    }
    new String(io.UTF8Codec.encode(i),"utf8")
  }

}