org.apache.lucene.util.automaton.RegExp Maven / Gradle / Ivy
Show all versions of aem-sdk-api Show documentation
/*
* dk.brics.automaton
*
* Copyright (c) 2001-2009 Anders Moeller
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. The name of the author may not be used to endorse or promote products
* derived from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR
* IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
* IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
* THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
/*
* COPIED FROM APACHE LUCENE 4.7.2
*
* Git URL: [email protected]:apache/lucene.git, tag: releases/lucene-solr/4.7.2, path: lucene/core/src/java
*
* (see https://issues.apache.org/jira/browse/OAK-10786 for details)
*/
package org.apache.lucene.util.automaton;
import java.io.IOException;
import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Map;
import java.util.Set;
import java.util.function.BooleanSupplier;
import java.util.function.Supplier;
/**
* Regular Expression extension to Automaton.
*
* Regular expressions are built from the following abstract syntax:
*
*
*
* regexp
* ::=
* unionexp
*
*
* |
*
*
*
* unionexp
* ::=
* interexp | unionexp
* (union)
*
*
* |
* interexp
*
*
*
* interexp
* ::=
* concatexp & interexp
* (intersection)
* [OPTIONAL]
*
*
* |
* concatexp
*
*
*
* concatexp
* ::=
* repeatexp concatexp
* (concatenation)
*
*
* |
* repeatexp
*
*
*
* repeatexp
* ::=
* repeatexp ?
* (zero or one occurrence)
*
*
* |
* repeatexp *
* (zero or more occurrences)
*
*
* |
* repeatexp +
* (one or more occurrences)
*
*
* |
* repeatexp {n}
* (n occurrences)
*
*
* |
* repeatexp {n,}
* (n or more occurrences)
*
*
* |
* repeatexp {n,m}
* (n to m occurrences, including both)
*
*
* |
* complexp
*
*
*
* complexp
* ::=
* ~ complexp
* (complement)
* [OPTIONAL]
*
*
* |
* charclassexp
*
*
*
* charclassexp
* ::=
* [ charclasses ]
* (character class)
*
*
* |
* [^ charclasses ]
* (negated character class)
*
*
* |
* simpleexp
*
*
*
* charclasses
* ::=
* charclass charclasses
*
*
* |
* charclass
*
*
*
* charclass
* ::=
* charexp - charexp
* (character range, including end-points)
*
*
* |
* charexp
*
*
*
* simpleexp
* ::=
* charexp
*
*
* |
* .
* (any single character)
*
*
* |
* #
* (the empty language)
* [OPTIONAL]
*
*
* |
* @
* (any string)
* [OPTIONAL]
*
*
* |
* " <Unicode string without double-quotes> "
* (a string)
*
*
* |
* ( )
* (the empty string)
*
*
* |
* ( unionexp )
* (precedence override)
*
*
* |
* < <identifier> >
* (named automaton)
* [OPTIONAL]
*
*
* |
* <n-m>
* (numerical interval)
* [OPTIONAL]
*
*
*
* charexp
* ::=
* <Unicode character>
* (a single non-reserved character)
*
*
* |
* \ <Unicode character>
* (a single character)
*
*
*
* The productions marked [OPTIONAL] are only allowed if
* specified by the syntax flags passed to the RegExp constructor.
* The reserved characters used in the (enabled) syntax must be escaped with
* backslash (\) or double-quotes ("..."). (In
* contrast to other regexp syntaxes, this is required also in character
* classes.) Be aware that dash (-) has a special meaning in
* charclass expressions. An identifier is a string not containing right
* angle bracket (>) or dash (-). Numerical
* intervals are specified by non-negative decimal integers and include both end
* points, and if n and m have the same number
* of digits, then the conforming strings must have that length (i.e. prefixed
* by 0's).
*
* @lucene.experimental
*/
public class RegExp {
enum Kind {
REGEXP_UNION, REGEXP_CONCATENATION, REGEXP_INTERSECTION, REGEXP_OPTIONAL, REGEXP_REPEAT, REGEXP_REPEAT_MIN, REGEXP_REPEAT_MINMAX, REGEXP_COMPLEMENT, REGEXP_CHAR, REGEXP_CHAR_RANGE, REGEXP_ANYCHAR, REGEXP_EMPTY, REGEXP_STRING, REGEXP_ANYSTRING, REGEXP_AUTOMATON, REGEXP_INTERVAL
}
/**
* Syntax flag, enables intersection (&).
*/
public static final int INTERSECTION = 0x0001;
/**
* Syntax flag, enables complement (~).
*/
public static final int COMPLEMENT = 0x0002;
/**
* Syntax flag, enables empty language (#).
*/
public static final int EMPTY = 0x0004;
/**
* Syntax flag, enables anystring (@).
*/
public static final int ANYSTRING = 0x0008;
/**
* Syntax flag, enables named automata (<identifier>).
*/
public static final int AUTOMATON = 0x0010;
/**
* Syntax flag, enables numerical intervals (
* <n-m>).
*/
public static final int INTERVAL = 0x0020;
/**
* Syntax flag, enables all optional regexp syntax.
*/
public static final int ALL = 0xffff;
/**
* Syntax flag, enables no optional regexp syntax.
*/
public static final int NONE = 0x0000;
private static boolean allow_mutation = false;
Kind kind;
RegExp exp1, exp2;
String s;
int c;
int min, max, digits;
int from, to;
String b;
int flags;
int pos;
RegExp() {}
/**
* Constructs new RegExp from a string. Same as
* RegExp(s, ALL).
*
* @param s regexp string
* @exception IllegalArgumentException if an error occured while parsing the
* regular expression
*/
public RegExp(String s) throws IllegalArgumentException {
this(s, ALL);
}
/**
* Constructs new RegExp from a string.
*
* @param s regexp string
* @param syntax_flags boolean 'or' of optional syntax constructs to be
* enabled
* @exception IllegalArgumentException if an error occured while parsing the
* regular expression
*/
public RegExp(String s, int syntax_flags) throws IllegalArgumentException {
b = s;
flags = syntax_flags;
RegExp e;
if (s.length() == 0) e = makeString("");
else {
e = parseUnionExp();
if (pos < b.length()) throw new IllegalArgumentException(
"end-of-string expected at position " + pos);
}
kind = e.kind;
exp1 = e.exp1;
exp2 = e.exp2;
this.s = e.s;
c = e.c;
min = e.min;
max = e.max;
digits = e.digits;
from = e.from;
to = e.to;
b = null;
}
/**
* Constructs new Automaton from this RegExp. Same
* as toAutomaton(null) (empty automaton map).
*/
public Automaton toAutomaton() {
return toAutomatonAllowMutate(null, null);
}
/**
* Constructs new Automaton from this RegExp. The
* constructed automaton is minimal and deterministic and has no transitions
* to dead states.
*
* @param automaton_provider provider of automata for named identifiers
* @exception IllegalArgumentException if this regular expression uses a named
* identifier that is not available from the automaton provider
*/
public Automaton toAutomaton(AutomatonProvider automaton_provider)
throws IllegalArgumentException {
return toAutomatonAllowMutate(null, automaton_provider);
}
/**
* Constructs new Automaton from this RegExp. The
* constructed automaton is minimal and deterministic and has no transitions
* to dead states.
*
* @param automata a map from automaton identifiers to automata (of type
* Automaton).
* @exception IllegalArgumentException if this regular expression uses a named
* identifier that does not occur in the automaton map
*/
public Automaton toAutomaton(Map automata)
throws IllegalArgumentException {
return toAutomatonAllowMutate(automata, null);
}
/**
* Sets or resets allow mutate flag. If this flag is set, then automata
* construction uses mutable automata, which is slightly faster but not thread
* safe. By default, the flag is not set.
*
* @param flag if true, the flag is set
* @return previous value of the flag
*/
public boolean setAllowMutate(boolean flag) {
boolean b = allow_mutation;
allow_mutation = flag;
return b;
}
private Automaton toAutomatonAllowMutate(Map automata,
AutomatonProvider automaton_provider) throws IllegalArgumentException {
boolean b = false;
if (allow_mutation) b = Automaton.setAllowMutate(true); // thread unsafe
Automaton a = toAutomaton(automata, automaton_provider);
if (allow_mutation) Automaton.setAllowMutate(b);
return a;
}
private Automaton toAutomaton(Map automata,
AutomatonProvider automaton_provider) throws IllegalArgumentException {
List list;
Automaton a = null;
switch (kind) {
case REGEXP_UNION:
list = new ArrayList();
findLeaves(exp1, Kind.REGEXP_UNION, list, automata, automaton_provider);
findLeaves(exp2, Kind.REGEXP_UNION, list, automata, automaton_provider);
a = BasicOperations.union(list);
MinimizationOperations.minimize(a);
break;
case REGEXP_CONCATENATION:
list = new ArrayList();
findLeaves(exp1, Kind.REGEXP_CONCATENATION, list, automata,
automaton_provider);
findLeaves(exp2, Kind.REGEXP_CONCATENATION, list, automata,
automaton_provider);
a = BasicOperations.concatenate(list);
MinimizationOperations.minimize(a);
break;
case REGEXP_INTERSECTION:
a = exp1.toAutomaton(automata, automaton_provider).intersection(
exp2.toAutomaton(automata, automaton_provider));
MinimizationOperations.minimize(a);
break;
case REGEXP_OPTIONAL:
a = exp1.toAutomaton(automata, automaton_provider).optional();
MinimizationOperations.minimize(a);
break;
case REGEXP_REPEAT:
a = exp1.toAutomaton(automata, automaton_provider).repeat();
MinimizationOperations.minimize(a);
break;
case REGEXP_REPEAT_MIN:
a = exp1.toAutomaton(automata, automaton_provider).repeat(min);
MinimizationOperations.minimize(a);
break;
case REGEXP_REPEAT_MINMAX:
a = exp1.toAutomaton(automata, automaton_provider).repeat(min, max);
MinimizationOperations.minimize(a);
break;
case REGEXP_COMPLEMENT:
a = exp1.toAutomaton(automata, automaton_provider).complement();
MinimizationOperations.minimize(a);
break;
case REGEXP_CHAR:
a = BasicAutomata.makeChar(c);
break;
case REGEXP_CHAR_RANGE:
a = BasicAutomata.makeCharRange(from, to);
break;
case REGEXP_ANYCHAR:
a = BasicAutomata.makeAnyChar();
break;
case REGEXP_EMPTY:
a = BasicAutomata.makeEmpty();
break;
case REGEXP_STRING:
a = BasicAutomata.makeString(s);
break;
case REGEXP_ANYSTRING:
a = BasicAutomata.makeAnyString();
break;
case REGEXP_AUTOMATON:
Automaton aa = null;
if (automata != null) aa = automata.get(s);
if (aa == null && automaton_provider != null) try {
aa = automaton_provider.getAutomaton(s);
} catch (IOException e) {
throw new IllegalArgumentException(e);
}
if (aa == null) throw new IllegalArgumentException("'" + s
+ "' not found");
a = aa.clone(); // always clone here (ignore allow_mutate)
break;
case REGEXP_INTERVAL:
a = BasicAutomata.makeInterval(min, max, digits);
break;
}
return a;
}
private void findLeaves(RegExp exp, Kind kind, List list,
Map automata, AutomatonProvider automaton_provider) {
if (exp.kind == kind) {
findLeaves(exp.exp1, kind, list, automata, automaton_provider);
findLeaves(exp.exp2, kind, list, automata, automaton_provider);
} else list.add(exp.toAutomaton(automata, automaton_provider));
}
/**
* Constructs string from parsed regular expression.
*/
@Override
public String toString() {
return toStringBuilder(new StringBuilder()).toString();
}
StringBuilder toStringBuilder(StringBuilder b) {
switch (kind) {
case REGEXP_UNION:
b.append("(");
exp1.toStringBuilder(b);
b.append("|");
exp2.toStringBuilder(b);
b.append(")");
break;
case REGEXP_CONCATENATION:
exp1.toStringBuilder(b);
exp2.toStringBuilder(b);
break;
case REGEXP_INTERSECTION:
b.append("(");
exp1.toStringBuilder(b);
b.append("&");
exp2.toStringBuilder(b);
b.append(")");
break;
case REGEXP_OPTIONAL:
b.append("(");
exp1.toStringBuilder(b);
b.append(")?");
break;
case REGEXP_REPEAT:
b.append("(");
exp1.toStringBuilder(b);
b.append(")*");
break;
case REGEXP_REPEAT_MIN:
b.append("(");
exp1.toStringBuilder(b);
b.append("){").append(min).append(",}");
break;
case REGEXP_REPEAT_MINMAX:
b.append("(");
exp1.toStringBuilder(b);
b.append("){").append(min).append(",").append(max).append("}");
break;
case REGEXP_COMPLEMENT:
b.append("~(");
exp1.toStringBuilder(b);
b.append(")");
break;
case REGEXP_CHAR:
b.append("\\").appendCodePoint(c);
break;
case REGEXP_CHAR_RANGE:
b.append("[\\").appendCodePoint(from).append("-\\").appendCodePoint(to).append("]");
break;
case REGEXP_ANYCHAR:
b.append(".");
break;
case REGEXP_EMPTY:
b.append("#");
break;
case REGEXP_STRING:
b.append("\"").append(s).append("\"");
break;
case REGEXP_ANYSTRING:
b.append("@");
break;
case REGEXP_AUTOMATON:
b.append("<").append(s).append(">");
break;
case REGEXP_INTERVAL:
String s1 = Integer.toString(min);
String s2 = Integer.toString(max);
b.append("<");
if (digits > 0) for (int i = s1.length(); i < digits; i++)
b.append('0');
b.append(s1).append("-");
if (digits > 0) for (int i = s2.length(); i < digits; i++)
b.append('0');
b.append(s2).append(">");
break;
}
return b;
}
/**
* Returns set of automaton identifiers that occur in this regular expression.
*/
public Set getIdentifiers() {
HashSet set = new HashSet();
getIdentifiers(set);
return set;
}
void getIdentifiers(Set set) {
switch (kind) {
case REGEXP_UNION:
case REGEXP_CONCATENATION:
case REGEXP_INTERSECTION:
exp1.getIdentifiers(set);
exp2.getIdentifiers(set);
break;
case REGEXP_OPTIONAL:
case REGEXP_REPEAT:
case REGEXP_REPEAT_MIN:
case REGEXP_REPEAT_MINMAX:
case REGEXP_COMPLEMENT:
exp1.getIdentifiers(set);
break;
case REGEXP_AUTOMATON:
set.add(s);
break;
default:
}
}
static RegExp makeUnion(RegExp exp1, RegExp exp2) {
RegExp r = new RegExp();
r.kind = Kind.REGEXP_UNION;
r.exp1 = exp1;
r.exp2 = exp2;
return r;
}
static RegExp makeConcatenation(RegExp exp1, RegExp exp2) {
if ((exp1.kind == Kind.REGEXP_CHAR || exp1.kind == Kind.REGEXP_STRING)
&& (exp2.kind == Kind.REGEXP_CHAR || exp2.kind == Kind.REGEXP_STRING)) return makeString(
exp1, exp2);
RegExp r = new RegExp();
r.kind = Kind.REGEXP_CONCATENATION;
if (exp1.kind == Kind.REGEXP_CONCATENATION
&& (exp1.exp2.kind == Kind.REGEXP_CHAR || exp1.exp2.kind == Kind.REGEXP_STRING)
&& (exp2.kind == Kind.REGEXP_CHAR || exp2.kind == Kind.REGEXP_STRING)) {
r.exp1 = exp1.exp1;
r.exp2 = makeString(exp1.exp2, exp2);
} else if ((exp1.kind == Kind.REGEXP_CHAR || exp1.kind == Kind.REGEXP_STRING)
&& exp2.kind == Kind.REGEXP_CONCATENATION
&& (exp2.exp1.kind == Kind.REGEXP_CHAR || exp2.exp1.kind == Kind.REGEXP_STRING)) {
r.exp1 = makeString(exp1, exp2.exp1);
r.exp2 = exp2.exp2;
} else {
r.exp1 = exp1;
r.exp2 = exp2;
}
return r;
}
static private RegExp makeString(RegExp exp1, RegExp exp2) {
StringBuilder b = new StringBuilder();
if (exp1.kind == Kind.REGEXP_STRING) b.append(exp1.s);
else b.appendCodePoint(exp1.c);
if (exp2.kind == Kind.REGEXP_STRING) b.append(exp2.s);
else b.appendCodePoint(exp2.c);
return makeString(b.toString());
}
static RegExp makeIntersection(RegExp exp1, RegExp exp2) {
RegExp r = new RegExp();
r.kind = Kind.REGEXP_INTERSECTION;
r.exp1 = exp1;
r.exp2 = exp2;
return r;
}
static RegExp makeOptional(RegExp exp) {
RegExp r = new RegExp();
r.kind = Kind.REGEXP_OPTIONAL;
r.exp1 = exp;
return r;
}
static RegExp makeRepeat(RegExp exp) {
RegExp r = new RegExp();
r.kind = Kind.REGEXP_REPEAT;
r.exp1 = exp;
return r;
}
static RegExp makeRepeat(RegExp exp, int min) {
RegExp r = new RegExp();
r.kind = Kind.REGEXP_REPEAT_MIN;
r.exp1 = exp;
r.min = min;
return r;
}
static RegExp makeRepeat(RegExp exp, int min, int max) {
RegExp r = new RegExp();
r.kind = Kind.REGEXP_REPEAT_MINMAX;
r.exp1 = exp;
r.min = min;
r.max = max;
return r;
}
static RegExp makeComplement(RegExp exp) {
RegExp r = new RegExp();
r.kind = Kind.REGEXP_COMPLEMENT;
r.exp1 = exp;
return r;
}
static RegExp makeChar(int c) {
RegExp r = new RegExp();
r.kind = Kind.REGEXP_CHAR;
r.c = c;
return r;
}
static RegExp makeCharRange(int from, int to) {
if (from > to)
throw new IllegalArgumentException("invalid range: from (" + from + ") cannot be > to (" + to + ")");
RegExp r = new RegExp();
r.kind = Kind.REGEXP_CHAR_RANGE;
r.from = from;
r.to = to;
return r;
}
static RegExp makeAnyChar() {
RegExp r = new RegExp();
r.kind = Kind.REGEXP_ANYCHAR;
return r;
}
static RegExp makeEmpty() {
RegExp r = new RegExp();
r.kind = Kind.REGEXP_EMPTY;
return r;
}
static RegExp makeString(String s) {
RegExp r = new RegExp();
r.kind = Kind.REGEXP_STRING;
r.s = s;
return r;
}
static RegExp makeAnyString() {
RegExp r = new RegExp();
r.kind = Kind.REGEXP_ANYSTRING;
return r;
}
static RegExp makeAutomaton(String s) {
RegExp r = new RegExp();
r.kind = Kind.REGEXP_AUTOMATON;
r.s = s;
return r;
}
static RegExp makeInterval(int min, int max, int digits) {
RegExp r = new RegExp();
r.kind = Kind.REGEXP_INTERVAL;
r.min = min;
r.max = max;
r.digits = digits;
return r;
}
private boolean peek(String s) {
return more() && s.indexOf(b.codePointAt(pos)) != -1;
}
private boolean match(int c) {
if (pos >= b.length()) return false;
if (b.codePointAt(pos) == c) {
pos += Character.charCount(c);
return true;
}
return false;
}
private boolean more() {
return pos < b.length();
}
private int next() throws IllegalArgumentException {
if (!more()) throw new IllegalArgumentException("unexpected end-of-string");
int ch = b.codePointAt(pos);
pos += Character.charCount(ch);
return ch;
}
private boolean check(int flag) {
return (flags & flag) != 0;
}
final RegExp parseUnionExp() throws IllegalArgumentException {
return iterativeParseExp(this::parseInterExp, () -> match('|'), RegExp::makeUnion);
}
final RegExp parseInterExp() throws IllegalArgumentException {
return iterativeParseExp(
this::parseConcatExp, () -> check(INTERSECTION) && match('&'), RegExp::makeIntersection);
}
final RegExp parseConcatExp() throws IllegalArgumentException {
return iterativeParseExp(
this::parseRepeatExp,
() -> (more() && !peek(")|") && (!check(INTERSECTION) || !peek("&"))),
RegExp::makeConcatenation);
}
/**
* Custom Functional Interface for a Supplying methods with signature of RegExp(RegExp
* exp1, RegExp exp2)
*/
@FunctionalInterface
private interface MakeRegexGroup {
RegExp get(RegExp exp1, RegExp exp2);
}
final RegExp iterativeParseExp(
Supplier gather, BooleanSupplier stop, MakeRegexGroup associativeReduce)
throws IllegalArgumentException {
RegExp result = gather.get();
while (stop.getAsBoolean() == true) {
RegExp e = gather.get();
result = associativeReduce.get(result, e);
}
return result;
}
final RegExp parseRepeatExp() throws IllegalArgumentException {
RegExp e = parseComplExp();
while (peek("?*+{")) {
if (match('?')) e = makeOptional(e);
else if (match('*')) e = makeRepeat(e);
else if (match('+')) e = makeRepeat(e, 1);
else if (match('{')) {
int start = pos;
while (peek("0123456789"))
next();
if (start == pos) throw new IllegalArgumentException(
"integer expected at position " + pos);
int n = Integer.parseInt(b.substring(start, pos));
int m = -1;
if (match(',')) {
start = pos;
while (peek("0123456789"))
next();
if (start != pos) m = Integer.parseInt(b.substring(start, pos));
} else m = n;
if (!match('}')) throw new IllegalArgumentException(
"expected '}' at position " + pos);
if (m == -1) e = makeRepeat(e, n);
else e = makeRepeat(e, n, m);
}
}
return e;
}
final RegExp parseComplExp() throws IllegalArgumentException {
if (check(COMPLEMENT) && match('~')) return makeComplement(parseComplExp());
else return parseCharClassExp();
}
final RegExp parseCharClassExp() throws IllegalArgumentException {
if (match('[')) {
boolean negate = false;
if (match('^')) negate = true;
RegExp e = parseCharClasses();
if (negate) e = makeIntersection(makeAnyChar(), makeComplement(e));
if (!match(']')) throw new IllegalArgumentException(
"expected ']' at position " + pos);
return e;
} else return parseSimpleExp();
}
final RegExp parseCharClasses() throws IllegalArgumentException {
RegExp e = parseCharClass();
while (more() && !peek("]"))
e = makeUnion(e, parseCharClass());
return e;
}
final RegExp parseCharClass() throws IllegalArgumentException {
int c = parseCharExp();
if (match('-')) return makeCharRange(c, parseCharExp());
else return makeChar(c);
}
final RegExp parseSimpleExp() throws IllegalArgumentException {
if (match('.')) return makeAnyChar();
else if (check(EMPTY) && match('#')) return makeEmpty();
else if (check(ANYSTRING) && match('@')) return makeAnyString();
else if (match('"')) {
int start = pos;
while (more() && !peek("\""))
next();
if (!match('"')) throw new IllegalArgumentException(
"expected '\"' at position " + pos);
return makeString(b.substring(start, pos - 1));
} else if (match('(')) {
if (match(')')) return makeString("");
RegExp e = parseUnionExp();
if (!match(')')) throw new IllegalArgumentException(
"expected ')' at position " + pos);
return e;
} else if ((check(AUTOMATON) || check(INTERVAL)) && match('<')) {
int start = pos;
while (more() && !peek(">"))
next();
if (!match('>')) throw new IllegalArgumentException(
"expected '>' at position " + pos);
String s = b.substring(start, pos - 1);
int i = s.indexOf('-');
if (i == -1) {
if (!check(AUTOMATON)) throw new IllegalArgumentException(
"interval syntax error at position " + (pos - 1));
return makeAutomaton(s);
} else {
if (!check(INTERVAL)) throw new IllegalArgumentException(
"illegal identifier at position " + (pos - 1));
try {
if (i == 0 || i == s.length() - 1 || i != s.lastIndexOf('-')) throw new NumberFormatException();
String smin = s.substring(0, i);
String smax = s.substring(i + 1);
int imin = Integer.parseInt(smin);
int imax = Integer.parseInt(smax);
int digits;
if (smin.length() == smax.length()) digits = smin.length();
else digits = 0;
if (imin > imax) {
int t = imin;
imin = imax;
imax = t;
}
return makeInterval(imin, imax, digits);
} catch (NumberFormatException e) {
throw new IllegalArgumentException(
"interval syntax error at position " + (pos - 1));
}
}
} else return makeChar(parseCharExp());
}
final int parseCharExp() throws IllegalArgumentException {
match('\\');
return next();
}
}