/** Returns a new (deterministic) automaton with the empty language. */
public static DefaultAutomaton makeEmpty() {
DefaultAutomaton a = new DefaultAutomaton();
State s = new State();
a.initial = s;
a.deterministic = true;
return a;
}
/**
* Returns a new automaton that accepts strings representing decimal non-negative integers in the
* given interval.
*
* @param min minimal value of interval
* @param max maximal value of inverval (both end points are included in the interval)
* @param digits if >0, use fixed number of digits (strings must be prefixed by 0's to obtain the
* right length) - otherwise, the number of digits is not fixed
* @throws IllegalArgumentException if min>max or if numbers in the interval cannot be expressed
* with the given fixed number of digits
*/
public static DefaultAutomaton makeInterval(int min, int max, int digits)
throws IllegalArgumentException {
DefaultAutomaton a = new DefaultAutomaton();
String x = Integer.toString(min);
String y = Integer.toString(max);
if (min > max || (digits > 0 && y.length() > digits)) throw new IllegalArgumentException();
int d;
if (digits > 0) d = digits;
else d = y.length();
StringBuilder bx = new StringBuilder();
for (int i = x.length(); i < d; i++) bx.append('0');
bx.append(x);
x = bx.toString();
StringBuilder by = new StringBuilder();
for (int i = y.length(); i < d; i++) by.append('0');
by.append(y);
y = by.toString();
Collection<State> initials = new ArrayList<State>();
a.initial = between(x, y, 0, initials, digits <= 0);
if (digits <= 0) {
ArrayList<StatePair> pairs = new ArrayList<StatePair>();
for (State p : initials) if (a.initial != p) pairs.add(new StatePair(a.initial, p));
addEpsilons(a, pairs);
a.initial.addTransition(new Transition('0', a.initial));
a.deterministic = false;
} else a.deterministic = true;
a.checkMinimizeAlways();
return a;
}
/** Returns a new (deterministic) automaton that accepts all strings. */
public static DefaultAutomaton makeAnyString() {
DefaultAutomaton a = new DefaultAutomaton();
State s = new State();
a.initial = s;
s.accept = true;
s.transitions.add(new Transition(Character.MIN_VALUE, Character.MAX_VALUE, s));
a.deterministic = true;
return a;
}
/**
* Returns a new (deterministic and minimal) automaton that accepts the union of the given set of
* strings. The input character sequences are internally sorted in-place, so the input array is
* modified.
*
* @see StringUnionOperations
*/
public static DefaultAutomaton makeStringUnion(CharSequence... strings) {
if (strings.length == 0) return makeEmpty();
Arrays.sort(strings, StringUnionOperations.LEXICOGRAPHIC_ORDER);
DefaultAutomaton a = new DefaultAutomaton();
a.setInitialState(StringUnionOperations.build(strings));
a.setDeterministic(true);
a.reduce();
a.recomputeHashCode();
return a;
}
/**
* Returns a new (deterministic) automaton that accepts a single char whose value is in the given
* interval (including both end points).
*/
public static DefaultAutomaton makeCharRange(char min, char max) {
if (min == max) return makeChar(min);
DefaultAutomaton a = new DefaultAutomaton();
State s1 = new State();
State s2 = new State();
a.initial = s1;
s2.accept = true;
if (min <= max) s1.transitions.add(new Transition(min, max, s2));
a.deterministic = true;
return a;
}
/** Returns a new (deterministic) automaton that accepts a single character in the given set. */
public static DefaultAutomaton makeCharSet(String set) {
if (set.length() == 1) return makeChar(set.charAt(0));
DefaultAutomaton a = new DefaultAutomaton();
State s1 = new State();
State s2 = new State();
a.initial = s1;
s2.accept = true;
for (int i = 0; i < set.length(); i++) s1.transitions.add(new Transition(set.charAt(i), s2));
a.deterministic = true;
a.reduce();
return a;
}
/** Constructs deterministic automaton that matches strings that contain the given substring. */
public static DefaultAutomaton makeStringMatcher(String s) {
DefaultAutomaton a = new DefaultAutomaton();
State[] states = new State[s.length() + 1];
states[0] = a.initial;
for (int i = 0; i < s.length(); i++) states[i + 1] = new State();
State f = states[s.length()];
f.accept = true;
f.transitions.add(new Transition(Character.MIN_VALUE, Character.MAX_VALUE, f));
for (int i = 0; i < s.length(); i++) {
Set<Character> done = new HashSet<Character>();
char c = s.charAt(i);
states[i].transitions.add(new Transition(c, states[i + 1]));
done.add(c);
for (int j = i; j >= 1; j--) {
char d = s.charAt(j - 1);
if (!done.contains(d) && s.substring(0, j - 1).equals(s.substring(i - j + 1, i))) {
states[i].transitions.add(new Transition(d, states[j]));
done.add(d);
}
}
char[] da = new char[done.size()];
int h = 0;
for (char w : done) da[h++] = w;
Arrays.sort(da);
int from = Character.MIN_VALUE;
int k = 0;
while (from <= Character.MAX_VALUE) {
while (k < da.length && da[k] == from) {
k++;
from++;
}
if (from <= Character.MAX_VALUE) {
int to = Character.MAX_VALUE;
if (k < da.length) {
to = da[k] - 1;
k++;
}
states[i].transitions.add(new Transition((char) from, (char) to, states[0]));
from = to + 2;
}
}
}
a.deterministic = true;
return a;
}
/**
* Constructs automaton that accept strings representing the given integer. Surrounding whitespace
* is permitted.
*
* @param value string representation of integer
*/
public static DefaultAutomaton makeIntegerValue(String value) {
boolean minus = false;
int i = 0;
while (i < value.length()) {
char c = value.charAt(i);
if (c == '-') minus = true;
if (c >= '1' && c <= '9') break;
i++;
}
StringBuilder b = new StringBuilder();
b.append(value.substring(i));
if (b.length() == 0) b.append("0");
DefaultAutomaton s;
if (minus) s = makeChar('-');
else s = makeChar('+').optional();
DefaultAutomaton ws = Datatypes.getWhitespaceAutomaton();
return (ws.concatenate(
s.concatenate(makeChar('0').repeat()).concatenate(makeString(b.toString())))
.concatenate(ws))
.minimize();
}
/**
* Constructs automaton that accept strings representing the given decimal number. Surrounding
* whitespace is permitted.
*
* @param value string representation of decimal number
*/
public static DefaultAutomaton makeDecimalValue(String value) {
boolean minus = false;
int i = 0;
while (i < value.length()) {
char c = value.charAt(i);
if (c == '-') minus = true;
if ((c >= '1' && c <= '9') || c == '.') break;
i++;
}
StringBuilder b1 = new StringBuilder();
StringBuilder b2 = new StringBuilder();
int p = value.indexOf('.', i);
if (p == -1) b1.append(value.substring(i));
else {
b1.append(value.substring(i, p));
i = value.length() - 1;
while (i > p) {
char c = value.charAt(i);
if (c >= '1' && c <= '9') break;
i--;
}
b2.append(value.substring(p + 1, i + 1));
}
if (b1.length() == 0) b1.append("0");
DefaultAutomaton s;
if (minus) s = makeChar('-');
else s = makeChar('+').optional();
DefaultAutomaton d;
if (b2.length() == 0) d = makeChar('.').concatenate(repeat(makeChar('0'), 1)).optional();
else
d = makeChar('.').concatenate(makeString(b2.toString())).concatenate(makeChar('0').repeat());
DefaultAutomaton ws = Datatypes.getWhitespaceAutomaton();
return (ws.concatenate(
s.concatenate(makeChar('0').repeat())
.concatenate(makeString(b1.toString()))
.concatenate(d))
.concatenate(ws))
.minimize();
}
/** Returns a new (deterministic) automaton that accepts a single character of the given value. */
public static DefaultAutomaton makeChar(char c) {
DefaultAutomaton a = new DefaultAutomaton();
a.singleton = Character.toString(c);
a.deterministic = true;
return a;
}
/** Returns a new (deterministic) automaton that accepts only the empty string. */
public static DefaultAutomaton makeEmptyString() {
DefaultAutomaton a = new DefaultAutomaton();
a.singleton = "";
a.deterministic = true;
return a;
}
/** Returns a new (deterministic) automaton that accepts the single given string. */
public static DefaultAutomaton makeString(String s) {
DefaultAutomaton a = new DefaultAutomaton();
a.singleton = s;
a.deterministic = true;
return a;
}