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
|
package scala.xml.dtd ;
import scala.util.regexp.WordExp;
import scala.util.automata._;
object ContentModel extends WordExp {
type _labelT = ElemName;
type _regexpT = RegExp;
object Translator extends WordBerrySethi {
override val lang: ContentModel.this.type = ContentModel.this;
import lang._ ;
//val re = Sequ(Star(Letter(IntConst( 3 ))));
//val aut = automatonFrom(re, 7)
}
case class ElemName(name: String) extends Label {
override def toString() = "ElemName(\""+name+"\")";
}
def parse(s: String): ContentModel = ContentModelParser.parse( s );
def getLabels(r: RegExp): scala.collection.Set[String] = {
val s = new scala.collection.mutable.HashSet[String]();
def traverse1(xs: Seq[RegExp]): Unit = {
val it = xs.elements;
while( it.hasNext )
traverse( it.next );
}
def traverse(r: RegExp): Unit = {
r match {
case Letter(ElemName( name )) => s += name;
case Star( x @ _ ) => traverse( x ); // bug if x@_*
case Sequ( xs @ _* ) => traverse1(xs);
case Alt( xs @ _* ) => traverse1(xs);
}
}
traverse( r );
return s
}
def toString(r: RegExp):String = {
val sb = new StringBuffer();
toString(r, sb);
sb.toString();
}
/* precond: rs.length >= 1 */
private def toString(rs: Seq[RegExp], sb: StringBuffer, sep: Char): Unit = {
val it = rs.elements;
val fst = it.next;
toString(fst, sb);
for(val z <- it) {
sb.append( sep );
toString( z, sb );
}
sb
}
def toString(c: ContentModel, sb: StringBuffer): StringBuffer = c match {
case ANY =>
sb.append("ANY");
case EMPTY =>
sb.append("EMPTY");
case PCDATA =>
sb.append("(#PCDATA)");
case ELEMENTS( _ ) | MIXED( _ ) =>
c.toString(sb)
}
def toString(r: RegExp, sb:StringBuffer): StringBuffer = {
r match {
case Eps =>
sb
case Sequ(rs @ _*) =>
sb.append( '(' ); toString(rs, sb, ','); sb.append( ')' );
case Alt(rs @ _*) =>
sb.append( '(' ); toString(rs, sb, '|'); sb.append( ')' );
case Star(r: RegExp) =>
sb.append( '(' ); toString(r, sb); sb.append( ")*" );
case Letter(ElemName(name)) =>
sb.append(name);
}
}
}
sealed abstract class ContentModel {
override def toString(): String = {
val sb = new StringBuffer();
toString(sb);
sb.toString();
}
def toString(sb:StringBuffer): StringBuffer;
/*
def validate(cs: NodeSeq): Boolean = this.match {
case ANY => true ;
case EMPTY => cs.length == 0;
case PCDATA => cs.length == 0
|| (cs.length == 1 && cs(0).isInstanceOf[Text]);
case m@MIXED(r) => m.runDFA(cs);
case e@ELEMENTS(r) => e.runDFA(cs);
}
*/
}
case object PCDATA extends ContentModel {
def toString(sb:StringBuffer): StringBuffer = sb.append("(#PCDATA)");
}
case object EMPTY extends ContentModel {
def toString(sb:StringBuffer): StringBuffer = sb.append("EMPTY");
}
case object ANY extends ContentModel {
def toString(sb:StringBuffer): StringBuffer = sb.append("ANY");
}
abstract class DFAContentModel extends ContentModel {
import ContentModel.{ ElemName };
def r: ContentModel.RegExp;
private var _dfa: DetWordAutom[ContentModel.ElemName] = null;
def dfa = {
if(null == _dfa) {
val nfa = ContentModel.Translator.automatonFrom(r, 1);
_dfa = new SubsetConstruction(nfa).determinize;
}
_dfa
}
/*
def getIterator(ns:NodeSeq): Iterator[String];
def runDFA(ns:NodeSeq): Boolean = {
if(null == _dfa) {
val nfa = ContentModel.Translator.automatonFrom(r, 1);
_dfa = new SubsetConstruction(nfa).determinize;
}
var q = 0;
val it = getIterator(ns);
Console.println("it empty from the start? "+(!it.hasNext));
while( it.hasNext ) {
val e = it.next;
Console.println("next = "+e);
if(null == e) {
return _dfa.isFinal(q)
} else {
Console.println(" got :"+ElemName(e));
Console.println("delta:" + _dfa.delta(q));
_dfa.delta(q).get(ElemName(e)).match {
case Some(p) => q = p;
case _ => throw ValidationException("element "+e+" not allowed here")
}
Console.println("q now " + q);
}
}
_dfa.isFinal(q)
}
*/
}
case class MIXED(r:ContentModel.RegExp) extends DFAContentModel {
import ContentModel.{ Alt, Eps, RegExp };
/*
def getIterator(ns:NodeSeq) = new Iterator[String] {
def cond(n:Node) =
!n.isInstanceOf[Text] && !n.isInstanceOf[SpecialNode];
Console.println("ns = "+ns);
val jt = ns.elements;
def hasNext = jt.hasNext;
def next = {
var r: Node = jt.next;
while(!cond(r) && jt.hasNext) {
Console.println("skipping "+r);
r = jt.next;
}
Console.println("MIXED, iterator.next, r = "+r);
if(Text("") == r)
null
else
r.label
}
}
*/
def toString(sb:StringBuffer): StringBuffer = {
sb.append("(#PCDATA|");
r match {
case Alt(Eps, rs@_*) => ContentModel.toString(Alt(rs:_*):RegExp, sb);
}
sb.append(")*");
}
}
case class ELEMENTS(r:ContentModel.RegExp) extends DFAContentModel {
/*
def getIterator(ns:NodeSeq) = new Iterator[String] {
val jt = ns.elements.buffered;
def hasNext = jt.hasNext;
def next = {
var r: Node = jt.next;
while(r.isInstanceOf[SpecialNode] && jt.hasNext) {
r = jt.head;
jt.next;
}
Console.println("MIXED, iterator.next, r = "+r);
if(r.isInstanceOf[Text])
throw ValidationException("Text not allowed here!")
else
r.label
}
}
*/
def toString(sb:StringBuffer): StringBuffer =
ContentModel.toString(r, sb);
}
|
