summaryrefslogtreecommitdiff
path: root/src/library/jvm/scala/xml/include/parsing/MarkupParser.scala
blob: 541cc65ac2efb516ee9836402cdd2c62d9ee5d31 (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
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
/*                     __                                               *\
**     ________ ___   / /  ___     Scala API                            **
**    / __/ __// _ | / /  / _ |    (c) 2003-2007, LAMP/EPFL             **
**  __\ \/ /__/ __ |/ /__/ __ |    http://scala-lang.org/               **
** /____/\___/_/ |_/____/_/ | |                                         **
**                          |/                                          **
\*                                                                      */

// $Id$


package scala.xml.parsing

import scala.io.Source
import scala.xml.dtd._

/**
 * An XML parser.
 *
 * Parses XML 1.0, invokes callback methods of a MarkupHandler
 * and returns whatever the markup handler returns. Use
 * <code>ConstructingParser</code> if you just want to parse XML to
 * construct instances of <code>scala.xml.Node</code>.
 *
 * While XML elements are returned, DTD declarations - if handled - are
 * collected using side-effects.
 *
 * @author  Burak Emir
 * @version 1.0
 */
trait MarkupParser extends AnyRef with TokenTests { self:  MarkupParser with MarkupHandler =>

  val input: Source

  /** if true, does not remove surplus whitespace */
  val preserveWS: Boolean

  def externalSource(systemLiteral: String): Source

  //
  // variables, values
  //

  var curInput: Source = input

  /** the handler of the markup, returns this */
  private val handle: MarkupHandler = this

  /** stack of inputs */
  var inpStack: List[Source] = Nil

  /** holds the position in the source file */
  var pos: Int = _


  /* used when reading external subset */
  var extIndex = -1

  /** holds temporary values of pos */
  var tmppos: Int = _

  /** holds the next character */
  var ch: Char = _

  /** character buffer, for names */
  protected val cbuf = new StringBuilder()

  var dtd: DTD = null

  protected var doc: Document = null

  var eof: Boolean = false

  //
  // methods
  //

  /** &lt;? prolog ::= xml S ... ?&gt;
   */
  def xmlProcInstr(): MetaData = {
    xToken("xml")
    xSpace
    val (md,scp) = xAttributes(TopScope)
    if (scp != TopScope)
      reportSyntaxError("no xmlns definitions here, please.");
    xToken('?')
    xToken('>')
    md
  }

  /** &lt;? prolog ::= xml S?
   *  // this is a bit more lenient than necessary...
   */
  def prolog(): Tuple3[Option[String], Option[String], Option[Boolean]] = {

    //Console.println("(DEBUG) prolog")
    var n = 0
    var info_ver: Option[String] = None
    var info_enc: Option[String] = None
    var info_stdl: Option[Boolean] = None

    var m = xmlProcInstr()

    xSpaceOpt

    m("version") match {
      case null  => ;
      case Text("1.0") => info_ver = Some("1.0"); n += 1
      case _     => reportSyntaxError("cannot deal with versions != 1.0")
    }

    m("encoding") match {
      case null => ;
      case Text(enc) =>
        if (!isValidIANAEncoding(enc))
          reportSyntaxError("\"" + enc + "\" is not a valid encoding")
        else {
          info_enc = Some(enc)
          n += 1
        }
    }
    m("standalone") match {
      case null => ;
      case Text("yes") => info_stdl = Some(true);  n += 1
      case Text("no")  => info_stdl = Some(false); n += 1
      case _     => reportSyntaxError("either 'yes' or 'no' expected")
    }

    if (m.length - n != 0) {
      reportSyntaxError("VersionInfo EncodingDecl? SDDecl? or '?>' expected!");
    }
    //Console.println("[MarkupParser::prolog] finished parsing prolog!");
    Tuple3(info_ver,info_enc,info_stdl)
  }

  /** prolog, but without standalone */
  def textDecl(): Tuple2[Option[String],Option[String]] = {

    var info_ver: Option[String] = None
    var info_enc: Option[String] = None

    var m = xmlProcInstr()
    var n = 0

    m("version") match {
      case null => ;
      case Text("1.0") => info_ver = Some("1.0"); n += 1
      case _     => reportSyntaxError("cannot deal with versions != 1.0")
    }

    m("encoding") match {
      case null => ;
      case Text(enc)  =>
        if (!isValidIANAEncoding(enc))
          reportSyntaxError("\"" + enc + "\" is not a valid encoding")
        else {
          info_enc = Some(enc)
          n += 1
        }
    }

    if (m.length - n != 0) {
      reportSyntaxError("VersionInfo EncodingDecl? or '?>' expected!");
    }
    //Console.println("[MarkupParser::textDecl] finished parsing textdecl");
    Tuple2(info_ver, info_enc);
  }

  /**
   *[22]        prolog     ::=          XMLDecl? Misc* (doctypedecl Misc*)?
   *[23]        XMLDecl    ::=          '&lt;?xml' VersionInfo EncodingDecl? SDDecl? S? '?>'
   *[24]        VersionInfo        ::=          S 'version' Eq ("'" VersionNum "'" | '"' VersionNum '"')
   *[25]        Eq         ::=          S? '=' S?
   *[26]        VersionNum         ::=          '1.0'
   *[27]        Misc       ::=          Comment | PI | S
   */

  def document(): Document = {

    //Console.println("(DEBUG) document")
    doc = new Document()

    this.dtd = null
    var info_prolog: Tuple3[Option[String], Option[String], Option[Boolean]] = Tuple3(None, None, None);
    if ('<' != ch) {
      reportSyntaxError("< expected")
      return null
    }

    nextch // is prolog ?
    var children: NodeSeq = null
    if ('?' == ch) {
      //Console.println("[MarkupParser::document] starts with xml declaration");
      nextch;
      info_prolog = prolog()
      doc.version    = info_prolog._1
      doc.encoding   = info_prolog._2
      doc.standAlone = info_prolog._3

      children = content(TopScope) // DTD handled as side effect
    } else {
      //Console.println("[MarkupParser::document] does not start with xml declaration");
 //

      val ts = new NodeBuffer();
      content1(TopScope, ts); // DTD handled as side effect
      ts &+ content(TopScope);
      children = NodeSeq.fromSeq(ts);
    }
    //Console.println("[MarkupParser::document] children now: "+children.toList);
    var elemCount = 0;
    var theNode: Node = null;
    for (c <- children) c match {
      case _:ProcInstr => ;
      case _:Comment => ;
      case _:EntityRef => // todo: fix entities, shouldn't be "special"
        reportSyntaxError("no entity references alllowed here");
      case s:SpecialNode =>
        if (s.toString().trim().length > 0) //non-empty text nodes not allowed
          elemCount = elemCount + 2;
      case m:Node =>
        elemCount = elemCount + 1;
        theNode = m;
    }
    if (1 != elemCount) {
      reportSyntaxError("document must contain exactly one element")
      Console.println(children.toList)
    }

    doc.children = children
    doc.docElem = theNode
    doc
  }

  /** append Unicode character to name buffer*/
  protected def putChar(c: Char) = cbuf.append(c)

  //var xEmbeddedBlock = false;

  /** this method assign the next character to ch and advances in input */
  def nextch {
    if (curInput.hasNext) {
      ch = curInput.next
      pos = curInput.pos
    } else {
      val ilen = inpStack.length;
      //Console.println("  ilen = "+ilen+ " extIndex = "+extIndex);
      if ((ilen != extIndex) && (ilen > 0)) {
        /** for external source, inpStack == Nil ! need notify of eof! */
        pop()
      } else {
        eof = true
        ch = 0.asInstanceOf[Char]
      }
    }
  }

  //final val enableEmbeddedExpressions: Boolean = false;

  /** munch expected XML token, report syntax error for unexpected
  */
  def xToken(that: Char) {
    if (ch == that)
      nextch
    else  {
      reportSyntaxError("'" + that + "' expected instead of '" + ch + "'")
      error("FATAL")
    }
  }

  def xToken(that: Seq[Char]): Unit = {
    val it = that.elements;
    while (it.hasNext)
      xToken(it.next);
  }

  /** parse attribute and create namespace scope, metadata
   *  [41] Attributes    ::= { S Name Eq AttValue }
   */
  def xAttributes(pscope:NamespaceBinding): (MetaData,NamespaceBinding) = {
    var scope: NamespaceBinding = pscope
    var aMap: MetaData = Null
    while (isNameStart(ch)) {
      val pos = this.pos

      val qname = xName
      val _     = xEQ
      val value = xAttributeValue()

      Utility.prefix(qname) match {
        case Some("xmlns") =>
          val prefix = qname.substring(6 /*xmlns:*/ , qname.length);
          scope = new NamespaceBinding(prefix, value, scope);

        case Some(prefix)       =>
          val key = qname.substring(prefix.length+1, qname.length);
          aMap = new PrefixedAttribute(prefix, key, Text(value), aMap);

        case _             =>
          if( qname == "xmlns" )
            scope = new NamespaceBinding(null, value, scope);
          else
            aMap = new UnprefixedAttribute(qname, Text(value), aMap);
      }

      if ((ch != '/') && (ch != '>') && ('?' != ch))
        xSpace;
    }

    if(!aMap.wellformed(scope))
        reportSyntaxError( "double attribute");

    (aMap,scope)
  }

  /** attribute value, terminated by either ' or ". value may not contain &lt;.
   *       AttValue     ::= `'` { _  } `'`
   *                      | `"` { _ } `"`
   */
  def xAttributeValue(): String = {
    val endch = ch
    nextch
    while (ch != endch) {
      if ('<' == ch)
        reportSyntaxError( "'<' not allowed in attrib value" );
      putChar(ch)
      nextch
    }
    nextch
    val str = cbuf.toString()
    cbuf.length = 0

    // well-formedness constraint
    normalizeAttributeValue(str)
  }

  /** entity value, terminated by either ' or ". value may not contain &lt;.
   *       AttValue     ::= `'` { _  } `'`
   *                      | `"` { _ } `"`
   */
  def xEntityValue(): String = {
    val endch = ch
    nextch
    while (ch != endch) {
      putChar(ch)
      nextch
    }
    nextch
    val str = cbuf.toString()
    cbuf.length = 0
    str
  }


  /** parse a start or empty tag.
   *  [40] STag         ::= '&lt;' Name { S Attribute } [S]
   *  [44] EmptyElemTag ::= '&lt;' Name { S Attribute } [S]
   */
  protected def xTag(pscope:NamespaceBinding): Tuple3[String, MetaData, NamespaceBinding] = {
    val qname = xName

    xSpaceOpt
    val (aMap: MetaData, scope: NamespaceBinding) = {
      if (isNameStart(ch))
        xAttributes(pscope)
      else
        (Null, pscope)
    }
    (qname, aMap, scope)
  }

  /** [42]  '&lt;' xmlEndTag ::=  '&lt;' '/' Name S? '&gt;'
   */
  def xEndTag(n: String) = {
    xToken('/')
    val m = xName
    if (n != m)
      reportSyntaxError("expected closing tag of " + n/* +", not "+m*/);
    xSpaceOpt
    xToken('>')
  }

  /** '&lt;! CharData ::= [CDATA[ ( {char} - {char}"]]&gt;"{char} ) ']]&gt;'
   *
   * see [15]
   */
  def xCharData: NodeSeq = {
    xToken("[CDATA[")
    val pos1 = pos
    val sb: StringBuilder = new StringBuilder()
    while (true) {
      if (ch==']'  &&
         { sb.append(ch); nextch; ch == ']' } &&
         { sb.append(ch); nextch; ch == '>' } ) {
        sb.length = sb.length - 2
        nextch;
        return handle.text( pos1, sb.toString() );
      } else sb.append( ch );
      nextch;
    }
    throw FatalError("this cannot happen");
  };

  /** CharRef ::= "&amp;#" '0'..'9' {'0'..'9'} ";"
   *            | "&amp;#x" '0'..'9'|'A'..'F'|'a'..'f' { hexdigit } ";"
   *
   * see [66]
   */
  def xCharRef(ch: () => Char, nextch: () => Unit): String = {
    Utility.parseCharRef(ch, nextch, reportSyntaxError _)
    /*
    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 + Character.digit( ch(), base );
        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 + Character.digit(ch(), base);
        case _ =>
          reportSyntaxError("character '" + ch() + " not allowed in char ref\n");
      }
      nextch();
    }
    new String(Array(i.asInstanceOf[char]))
    */
  }


  /** Comment ::= '&lt;!--' ((Char - '-') | ('-' (Char - '-')))* '--&gt;'
   *
   * see [15]
   */
  def xComment: NodeSeq = {
    val sb: StringBuilder = new StringBuilder()
    xToken('-')
    xToken('-')
    while (true) {
      if (ch == '-'  && { sb.append(ch); nextch; ch == '-' }) {
        sb.length = sb.length - 1
        nextch
        xToken('>')
        return handle.comment(pos, sb.toString())
      } else sb.append(ch)
      nextch
    }
    throw FatalError("this cannot happen")
  }

  /* todo: move this into the NodeBuilder class */
  def appendText(pos: Int, ts: NodeBuffer, txt: String): Unit = {
    if (preserveWS)
      ts &+ handle.text(pos, txt);
    else
      for (t <- TextBuffer.fromString(txt).toText) {
        ts &+ handle.text(pos, t.text);
      }
  }

  /** '&lt;' content1 ::=  ... */
  def content1(pscope: NamespaceBinding, ts: NodeBuffer): Unit =
    ch match {
      case '!' =>
        nextch
      if ('[' == ch)                 // CDATA
        ts &+ xCharData
      else if ('D' == ch) // doctypedecl, parse DTD // @todo REMOVE HACK
        parseDTD()
      else // comment
        ts &+ xComment
      case '?' =>                    // PI
        nextch
        ts &+ xProcInstr
      case _   =>
        ts &+ element1(pscope)      // child
    }

  /** content1 ::=  '&lt;' content1 | '&amp;' charref ... */
  def content(pscope: NamespaceBinding): NodeSeq = {
    var ts = new NodeBuffer
    var exit = eof
    while (! exit) {
      //Console.println("in content, ch = '"+ch+"' line="+scala.io.Position.line(pos));
      /*      if( xEmbeddedBlock ) {
       ts.append( xEmbeddedExpr );
       } else {*/
        tmppos = pos;
        exit = eof;
        if(!eof)
          ch match {
          case '<' => // another tag
            //Console.println("before ch = '"+ch+"' line="+scala.io.Position.line(pos)+" pos="+pos);
            nextch;
            //Console.println("after ch = '"+ch+"' line="+scala.io.Position.line(pos)+" pos="+pos);

            if('/' ==ch)
              exit = true;                    // end tag
            else
              content1(pscope, ts)
          //case '{' =>
/*            if( xCheckEmbeddedBlock ) {
              ts.appendAll(xEmbeddedExpr);
            } else {*/
          //    val str = new StringBuilder("{");
          //    str.append(xText);
          //    appendText(tmppos, ts, str.toString());
            /*}*/
          // postcond: xEmbeddedBlock == false!
          case '&' => // EntityRef or CharRef
            nextch;
            ch match {
              case '#' => // CharacterRef
                nextch;
                val theChar = handle.text( tmppos,
                                          xCharRef ({ ()=> ch },{ () => nextch }) );
                xToken(';');
                ts &+ theChar ;
              case _ => // EntityRef
                val n = xName
                xToken(';')
                n match {
                  case "lt"    => ts &+ '<'
                  case "gt"    => ts &+ '>'
                  case "amp"   => ts &+ '&'
                  case "quot" => ts &+ '"'
                  case _ =>
                    /*
                     ts + handle.entityRef( tmppos, n ) ;
                     */
                    push(n)
                }
            }
          case _ => // text content
            //Console.println("text content?? pos = "+pos);
            appendText(tmppos, ts, xText);
          // here xEmbeddedBlock might be true
          }
    /*}*/
    }
    val list = ts.toList
    // 2do: optimize seq repr.
    new NodeSeq {
      val theSeq = list
    }
  } // content(NamespaceBinding)

  /** externalID ::= SYSTEM S syslit
   *                 PUBLIC S pubid S syslit
   */

  def externalID(): ExternalID = ch match {
    case 'S' =>
      nextch
      xToken("YSTEM")
      xSpace
      val sysID = systemLiteral()
      new SystemID(sysID)
    case 'P' =>
      nextch; xToken("UBLIC")
      xSpace
      val pubID = pubidLiteral()
      xSpace
      val sysID = systemLiteral()
      new PublicID(pubID, sysID)
  }


  /** parses document type declaration and assigns it to instance variable
   *  dtd.
   *
   *  &lt;! parseDTD ::= DOCTYPE name ... >
   */
  def parseDTD(): Unit = { // dirty but fast
    //Console.println("(DEBUG) parseDTD");
    var extID: ExternalID = null
    if (this.dtd ne null)
      reportSyntaxError("unexpected character (DOCTYPE already defined");
    xToken("DOCTYPE")
    xSpace
    val n = xName
    xSpace
    //external ID
    if ('S' == ch || 'P' == ch) {
      extID = externalID()
      xSpaceOpt
    }

    /* parse external subset of DTD
     */

    if ((null != extID) && isValidating) {

      pushExternal(extID.systemId)
      //val extSubsetSrc = externalSource( extID.systemId );

      extIndex = inpStack.length
      /*
       .indexOf(':') != -1) { // assume URI
         Source.fromFile(new java.net.URI(extID.systemLiteral));
       } else {
         Source.fromFile(extID.systemLiteral);
       }
      */
      //Console.println("I'll print it now");
      //val old = curInput;
      //tmppos = curInput.pos;
      //val oldch = ch;
      //curInput = extSubsetSrc;
      //pos = 0;
      //nextch;

      extSubset()

      pop()

      extIndex = -1

      //curInput = old;
      //pos = curInput.pos;
      //ch = curInput.ch;
      //eof = false;
      //while(extSubsetSrc.hasNext)
      //Console.print(extSubsetSrc.next);

      //Console.println("returned from external, current ch = "+ch )
    }

    if ('[' == ch) { // internal subset
      nextch
      /* TODO */
      //Console.println("hello");
      intSubset()
      //while(']' != ch)
      //  nextch;
      // TODO: do the DTD parsing?? ?!?!?!?!!
      xToken(']')
      xSpaceOpt
    }
    xToken('>')
    this.dtd = new DTD {
      /*override var*/ externalID = extID
      /*override val */decls      = handle.decls.reverse
    }
    //this.dtd.initializeEntities();
    if (doc ne null)
      doc.dtd = this.dtd

    handle.endDTD(n)
  }

  def element(pscope: NamespaceBinding): NodeSeq = {
    xToken('<')
    element1(pscope)
  }

  /** '&lt;' element ::= xmlTag1 '&gt;'  { xmlExpr | '{' simpleExpr '}' } ETag
   *               | xmlTag1 '/' '&gt;'
   */
  def element1(pscope: NamespaceBinding): NodeSeq = {
    val pos = this.pos
    val Tuple3(qname, aMap, scope) = xTag(pscope)
    val Tuple2(pre, local) = Utility.prefix(qname) match {
      case Some(p) => (p,qname.substring(p.length+1, qname.length))
      case _       => (null,qname)
    }
    val ts = {
      if (ch == '/') {  // empty element
        xToken('/')
        xToken('>')
        handle.elemStart(pos, pre, local, aMap, scope)
        NodeSeq.Empty
      }
      else {           // element with content
        xToken('>')
        handle.elemStart(pos, pre, local, aMap, scope)
        val tmp = content(scope)
        xEndTag(qname)
        tmp
      }
    }
    val res = handle.elem(pos, pre, local, aMap, scope, ts)
    handle.elemEnd(pos, pre, local)
    res
  }

  //def xEmbeddedExpr: MarkupType;

  /** Name ::= (Letter | '_' | ':') (NameChar)*
   *
   *  see  [5] of XML 1.0 specification
   */
  def xName: String = {
    if (isNameStart(ch)) {
      while (isNameChar(ch)) {
        putChar(ch)
        nextch
      }
      val n = cbuf.toString().intern()
      cbuf.length = 0
      n
    } else {
      reportSyntaxError("name expected")
      ""
    }
  }

  /** scan [S] '=' [S]*/
  def xEQ = { xSpaceOpt; xToken('='); xSpaceOpt }

  /** skip optional space S? */
  def xSpaceOpt = while (isSpace(ch) && !eof) { nextch; }

  /** scan [3] S ::= (#x20 | #x9 | #xD | #xA)+ */
  def xSpace =
    if (isSpace(ch)) { nextch; xSpaceOpt }
    else reportSyntaxError("whitespace expected")

  /** '&lt;?' ProcInstr ::= Name [S ({Char} - ({Char}'&gt;?' {Char})]'?&gt;'
   *
   * see [15]
   */
  def xProcInstr: NodeSeq = {
    val sb:StringBuilder = new StringBuilder()
    val n = xName
    if (isSpace(ch)) {
      xSpace
      while (true) {
        if (ch == '?' && { sb.append( ch ); nextch; ch == '>' }) {
          sb.length = sb.length - 1;
          nextch;
          return handle.procInstr(tmppos, n, sb.toString);
        } else
          sb.append(ch);
        nextch
      }
    };
    xToken('?')
    xToken('>')
    handle.procInstr(tmppos, n, sb.toString)
  }

  /** parse character data.
   *   precondition: xEmbeddedBlock == false (we are not in a scala block)
   */
  def xText: String = {
    //if( xEmbeddedBlock ) throw FatalError("internal error: encountered embedded block"); // assert

    /*if( xCheckEmbeddedBlock )
      return ""
    else {*/
    //Console.println("in xText! ch = '"+ch+"'");
      var exit = false;
      while (! exit) {
        //Console.println("LOOP in xText! ch = '"+ch+"' + pos="+pos);
        putChar(ch);
        val opos = pos;
        nextch;

        //Console.println("STILL LOOP in xText! ch = '"+ch+"' + pos="+pos+" opos="+opos);


        exit = eof || /*{ nextch; xCheckEmbeddedBlock }||*/( ch == '<' ) || ( ch == '&' );
      }
      val str = cbuf.toString();
      cbuf.length = 0;
      str
    /*}*/
  }

  /** attribute value, terminated by either ' or ". value may not contain &lt;.
   *       AttValue     ::= `'` { _ } `'`
   *                      | `"` { _ } `"`
   */
  def systemLiteral(): String = {
    val endch = ch
    if (ch != '\'' && ch != '"')
      reportSyntaxError("quote ' or \" expected");
    nextch
    while (ch != endch) {
      putChar(ch)
      nextch
    }
    nextch
    val str = cbuf.toString()
    cbuf.length = 0
    str
  }


  /* [12]       PubidLiteral ::=        '"' PubidChar* '"' | "'" (PubidChar - "'")* "'" */
  def pubidLiteral(): String = {
    val endch = ch
    if (ch!='\'' && ch != '"')
      reportSyntaxError("quote ' or \" expected");
    nextch
    while (ch != endch) {
      putChar(ch)
      //Console.println("hello '"+ch+"'"+isPubIDChar(ch));
      if (!isPubIDChar(ch))
        reportSyntaxError("char '"+ch+"' is not allowed in public id");
      nextch
    }
    nextch
    val str = cbuf.toString()
    cbuf.length = 0
    str
  }

  //
  //  dtd parsing
  //

  def extSubset(): Unit = {
    var textdecl:Tuple2[Option[String],Option[String]] = null;
    if (ch=='<') {
      nextch
      if (ch=='?') {
        nextch
        textdecl = textDecl()
      } else
        markupDecl1()
    }
    while (!eof)
      markupDecl()
  }

  def markupDecl1() = {
    def doInclude() = {
      xToken('['); while(']' != ch) markupDecl(); nextch // ']'
    }
    def doIgnore() = {
      xToken('['); while(']' != ch) nextch; nextch; // ']'
    }
    if ('?' == ch) {
      nextch
      xProcInstr // simply ignore processing instructions!
    } else {
      xToken('!')
      ch match {
        case '-' =>
          xComment // ignore comments

        case 'E' =>
          nextch
          if ('L' == ch) {
            nextch
            elementDecl()
          } else
            entityDecl()

        case 'A' =>
          nextch
          attrDecl()

        case 'N' =>
          nextch
          notationDecl()

        case '[' if inpStack.length >= extIndex =>
          nextch
          xSpaceOpt
          ch match {
            case '%' =>
              nextch
              val ent = xName
              xToken(';')
              xSpaceOpt
            /*
              Console.println("hello, pushing!");
            {
              val test =  replacementText(ent);
              while(test.hasNext)
                Console.print(test.next);
            } */
              push(ent)
              xSpaceOpt
              //Console.println("hello, getting name");
              val stmt = xName
              //Console.println("hello, got name");
              xSpaceOpt
            //Console.println("how can we be eof = "+eof);

            // eof = true because not external?!
              //if(!eof)
              //  error("expected only INCLUDE or IGNORE");

              //pop();

              //Console.println("hello, popped");
              stmt match {
                // parameter entity
                case "INCLUDE" =>
                  doInclude()
                case "IGNORE" =>
                  doIgnore()
              }
            case 'I' =>
              nextch
              ch match {
                case 'G' =>
                  nextch
                  xToken("NORE")
                  xSpaceOpt
                  doIgnore()
                case 'N' =>
                  nextch
                  xToken("NCLUDE")
                  doInclude()
              }
          }
        xToken(']')
        xToken('>')

        case _  =>
          curInput.reportError(pos, "unexpected character '"+ch+"', expected some markupdecl")
        while (ch!='>')
          nextch
      }
    }
  }

  def markupDecl(): Unit = ch match {
    case '%' =>                  // parameter entity reference
      nextch
      val ent = xName
      xToken(';')
      if (!isValidating)
        handle.peReference(ent)  //  n-v: just create PE-reference
      else
        push(ent)                //    v: parse replacementText

    //peReference
    case '<' =>
      nextch
      markupDecl1()
    case _ if isSpace(ch) =>
      xSpace
    case _ =>
      reportSyntaxError("markupdecl: unexpected character '"+ch+"' #" + ch.asInstanceOf[Int])
      nextch
  }

  /**  "rec-xml/#ExtSubset" pe references may not occur within markup
   declarations
   */
  def intSubset() {
    //Console.println("(DEBUG) intSubset()")
    xSpace
    while (']' != ch)
      markupDecl()
  }

  /** &lt;! element := ELEMENT
   */
  def elementDecl() {
    xToken("EMENT")
    xSpace
    val n = xName
    xSpace
    while ('>' != ch) {
      //Console.println("["+ch+"]")
      putChar(ch)
      nextch
    }
    //Console.println("END["+ch+"]")
    nextch
    val cmstr = cbuf.toString()
    cbuf.length = 0
    handle.elemDecl(n, cmstr)
  }

  /** &lt;! attlist := ATTLIST
   */
  def attrDecl() = {
    xToken("TTLIST")
    xSpace
    val n = xName
    xSpace
    var attList: List[AttrDecl] = Nil
    // later: find the elemDecl for n
    while ('>' != ch) {
      val aname = xName
      //Console.println("attribute name: "+aname);
      var defdecl: DefaultDecl = null
      xSpace
      // could be enumeration (foo,bar) parse this later :-/
      while ('"' != ch && '\'' != ch && '#' != ch && '<' != ch) {
        if (!isSpace(ch))
          cbuf.append(ch);
        nextch;
      }
      val atpe = cbuf.toString()
      cbuf.length = 0
      //Console.println("attr type: "+atpe);
      ch match {
        case '\'' | '"' =>
          val defValue = xAttributeValue() // default value
          defdecl = DEFAULT(false, defValue)

        case '#' =>
          nextch
          xName match {
            case "FIXED" =>
              xSpace
              val defValue = xAttributeValue() // default value
              defdecl = DEFAULT(true, defValue)
            case "IMPLIED" =>
              defdecl = IMPLIED
            case "REQUIRED" =>
              defdecl = REQUIRED
          }
        case _ =>
      }
      xSpaceOpt

      attList = AttrDecl(aname, atpe, defdecl) :: attList
      cbuf.length = 0
    }
    nextch
    handle.attListDecl(n, attList.reverse)
  }

  /** &lt;! element := ELEMENT
   */
  def entityDecl() = {
    //Console.println("entityDecl()")
    var isParameterEntity = false
    var entdef: EntityDef = null
    xToken("NTITY")
    xSpace
    if ('%' == ch) {
      nextch
      isParameterEntity = true
      xSpace
    }
    val n = xName
    xSpace
    ch match {
      case 'S' | 'P' => //sy
        val extID = externalID()
        if (isParameterEntity) {
          xSpaceOpt
          xToken('>')
          handle.parameterEntityDecl(n, ExtDef(extID))
        } else { // notation?
          xSpace
          if ('>' != ch) {
            xToken("NDATA")
            xSpace
            val notat = xName
            xSpaceOpt
            xToken('>')
            handle.unparsedEntityDecl(n, extID, notat)
          } else {
            nextch
            handle.parsedEntityDecl(n, ExtDef(extID))
          }
        }

      case '"' | '\'' =>
        val av = xEntityValue()
        xSpaceOpt
        xToken('>')
        if (isParameterEntity)
          handle.parameterEntityDecl(n, IntDef(av))
        else
          handle.parsedEntityDecl(n, IntDef(av))
    }
    {}
  } // entityDecl

  /** 'N' notationDecl ::= "OTATION"
   */
  def notationDecl() {
    xToken("OTATION")
    xSpace
    val notat = xName
    xSpace
    val extID = if (ch == 'S') {
      externalID();
    }
    else if (ch == 'P') {
      /** PublicID (without system, only used in NOTATION) */
      nextch
      xToken("UBLIC")
      xSpace
      val pubID = pubidLiteral()
      xSpaceOpt
      val sysID = if (ch != '>')
        systemLiteral()
      else
        null;
      new PublicID(pubID, sysID);
    } else {
      reportSyntaxError("PUBLIC or SYSTEM expected");
      error("died parsing notationdecl")
    }
    xSpaceOpt
    xToken('>')
    handle.notationDecl(notat, extID)
  }

  /**
   * report a syntax error
   */
  def reportSyntaxError(pos: Int, str: String) {
    curInput.reportError(pos, str)
    //error("MarkupParser::synerr") // DEBUG
  }

  def reportSyntaxError(str: String): Unit = reportSyntaxError(pos, str)

  /**
   * report a syntax error
   */
  def reportValidationError(pos: Int, str: String) {
    curInput.reportError(pos, str)
  }

  def push(entityName: String) {
    //Console.println("BEFORE PUSHING  "+ch)
    //Console.println("BEFORE PUSHING  "+pos)
    //Console.print("[PUSHING "+entityName+"]")
    if (!eof)
      inpStack = curInput :: inpStack

    curInput = replacementText(entityName)
    nextch
  }

  /*
  def push(src:Source) = {
    curInput = src
    nextch
  }
  */

  def pushExternal(systemId: String) {
    //Console.print("BEFORE PUSH, curInput = $"+curInput.descr)
    //Console.println(" stack = "+inpStack.map { x => "$"+x.descr })

    //Console.print("[PUSHING EXTERNAL "+systemId+"]")
    if (!eof)
      inpStack = curInput :: inpStack

    curInput = externalSource(systemId)

    //Console.print("AFTER PUSH, curInput = $"+curInput.descr)
    //Console.println(" stack = "+inpStack.map { x => "$"+x.descr })

    nextch
  }

  def pop() {
    curInput = inpStack.head
    inpStack = inpStack.tail
    ch = curInput.ch
    pos = curInput.pos
    eof = false // must be false, because of places where entity refs occur
    //Console.println("\n AFTER POP, curInput = $"+curInput.descr);
    //Console.println(inpStack.map { x => x.descr });
  }

  /** for the moment, replace only character references
   *  see spec 3.3.3
   *  precond: cbuf empty
   */
  def normalizeAttributeValue(attval: String): String = {
    val s: Seq[Char] = attval
    val it = s.elements
    while (it.hasNext) {
      it.next match {
        case ' '|'\t'|'\n'|'\r' =>
          cbuf.append(' ');
        case '&' => it.next match {
          case '#' =>
            var c = it.next
            val s = xCharRef ({ () => c }, { () => c = it.next })
            cbuf.append(s)
          case nchar =>
            val nbuf = new StringBuilder()
            var d = nchar
            do {
              nbuf.append(d)
              d = it.next
            } while(d != ';');
            nbuf.toString() match {
              case "lt"    => cbuf.append('<')
              case "gt"    => cbuf.append('>')
              case "amp"   => cbuf.append('&')
              case "apos"  => cbuf.append('\'')
              case "quot"  => cbuf.append('"')
              case "quote" => cbuf.append('"')
              case name =>
                cbuf.append('&')
                cbuf.append(name)
                cbuf.append(';')
            }
        }
        case c =>
          cbuf.append(c)
      }
    }
    val name = cbuf.toString()
    cbuf.length = 0
    name
  }

}