/** Just takes unsigned byte values from the BytesRef and * converts into an IntsRef. */ public static IntsRef toIntsRef(BytesRef input, IntsRefBuilder scratch) { scratch.clear(); for(int i=0;i<input.length;i++) { scratch.append(input.bytes[i+input.offset] & 0xFF); } return scratch.get(); }
/** If this automaton accepts a single input, return it. Else, return null. * The automaton must be deterministic. */ public static IntsRef getSingleton(Automaton a) { if (a.isDeterministic() == false) { throw new IllegalArgumentException("input automaton must be deterministic"); } IntsRefBuilder builder = new IntsRefBuilder(); HashSet<Integer> visited = new HashSet<>(); int s = 0; Transition t = new Transition(); while (true) { visited.add(s); if (a.isAccept(s) == false) { if (a.getNumTransitions(s) == 1) { a.getTransition(s, 0, t); if (t.min == t.max && !visited.contains(t.dest)) { builder.append(t.min); s = t.dest; continue; } } } else if (a.getNumTransitions(s) == 0) { return builder.get(); } // Automaton accepts more than one string: return null; } }
/** * Constructor. * * @param a Automaton to create finite string from. * @param startState The starting state for each path. * @param endState The state where each path should stop or -1 if only accepted states should be final. */ public FiniteStringsIterator(Automaton a, int startState, int endState) { this.a = a; this.endState = endState; this.nodes = new PathNode[16]; for (int i = 0, end = nodes.length; i < end; i++) { nodes[i] = new PathNode(); } this.string = new IntsRefBuilder(); this.pathStates = new BitSet(a.getNumStates()); this.string.setLength(0); this.emitEmptyString = a.isAccept(0); // Start iteration with node startState. if (a.getNumTransitions(startState) > 0) { pathStates.set(startState); nodes[0].resetState(a, startState); string.append(startState); } }
path.input.append(path.arc.label); path.output = fst.outputs.add(path.output, path.arc.output); if (acceptPartialPath(path) == false) {
/** * Convert a character sequence <code>s</code> into full unicode codepoints. */ private static IntsRefBuilder UTF16ToUTF32(CharSequence s, IntsRefBuilder builder) { builder.clear(); for (int charIdx = 0, charLimit = s.length(); charIdx < charLimit;) { final int utf32 = Character.codePointAt(s, charIdx); builder.append(utf32); charIdx += Character.charCount(utf32); } return builder; }
/** Just takes unsigned byte values from the BytesRef and * converts into an IntsRef. */ public static IntsRef toIntsRef(BytesRef input, IntsRefBuilder scratch) { scratch.clear(); for(int i=0;i<input.length;i++) { scratch.append(input.bytes[i+input.offset] & 0xFF); } return scratch.get(); }
/** Just takes unsigned byte values from the BytesRef and * converts into an IntsRef. */ public static IntsRef toIntsRef(BytesRef input, IntsRefBuilder scratch) { scratch.clear(); for(int i=0;i<input.length;i++) { scratch.append(input.bytes[i+input.offset] & 0xFF); } return scratch.get(); }
/** Just takes unsigned byte values from the BytesRef and * converts into an IntsRef. */ public static IntsRef toIntsRef(BytesRef input, IntsRefBuilder scratch) { scratch.clear(); for(int i=0;i<input.length;i++) { scratch.append(input.bytes[i+input.offset] & 0xFF); } return scratch.get(); }
/** If this automaton accepts a single input, return it. Else, return null. * The automaton must be deterministic. */ public static IntsRef getSingleton(Automaton a) { if (a.isDeterministic() == false) { throw new IllegalArgumentException("input automaton must be deterministic"); } IntsRefBuilder builder = new IntsRefBuilder(); HashSet<Integer> visited = new HashSet<>(); int s = 0; Transition t = new Transition(); while (true) { visited.add(s); if (a.isAccept(s) == false) { if (a.getNumTransitions(s) == 1) { a.getTransition(s, 0, t); if (t.min == t.max && !visited.contains(t.dest)) { builder.append(t.min); s = t.dest; continue; } } } else if (a.getNumTransitions(s) == 0) { return builder.get(); } // Automaton accepts more than one string: return null; } }
/** If this automaton accepts a single input, return it. Else, return null. * The automaton must be deterministic. */ public static IntsRef getSingleton(Automaton a) { if (a.isDeterministic() == false) { throw new IllegalArgumentException("input automaton must be deterministic"); } IntsRefBuilder builder = new IntsRefBuilder(); HashSet<Integer> visited = new HashSet<>(); int s = 0; Transition t = new Transition(); while (true) { visited.add(s); if (a.isAccept(s) == false) { if (a.getNumTransitions(s) == 1) { a.getTransition(s, 0, t); if (t.min == t.max && !visited.contains(t.dest)) { builder.append(t.min); s = t.dest; continue; } } } else if (a.getNumTransitions(s) == 0) { return builder.get(); } // Automaton accepts more than one string: return null; } }
/** If this automaton accepts a single input, return it. Else, return null. * The automaton must be deterministic. */ public static IntsRef getSingleton(Automaton a) { if (a.isDeterministic() == false) { throw new IllegalArgumentException("input automaton must be deterministic"); } IntsRefBuilder builder = new IntsRefBuilder(); HashSet<Integer> visited = new HashSet<>(); int s = 0; Transition t = new Transition(); while (true) { visited.add(s); if (a.isAccept(s) == false) { if (a.getNumTransitions(s) == 1) { a.getTransition(s, 0, t); if (t.min == t.max && !visited.contains(t.dest)) { builder.append(t.min); s = t.dest; continue; } } } else if (a.getNumTransitions(s) == 0) { return builder.get(); } // Automaton accepts more than one string: return null; } }
/** * Constructor. * * @param a Automaton to create finite string from. */ public FiniteStringsIterator(Automaton a) { this.a = a; this.nodes = new PathNode[16]; for (int i = 0, end = nodes.length; i < end; i++) { nodes[i] = new PathNode(); } this.string = new IntsRefBuilder(); this.pathStates = new BitSet(a.getNumStates()); this.string.setLength(0); this.emitEmptyString = a.isAccept(0); // Start iteration with node 0. if (a.getNumTransitions(0) > 0) { pathStates.set(0); nodes[0].resetState(a, 0); string.append(0); } }
/** * Constructor. * * @param a Automaton to create finite string from. */ public FiniteStringsIterator(Automaton a) { this.a = a; this.nodes = new PathNode[16]; for (int i = 0, end = nodes.length; i < end; i++) { nodes[i] = new PathNode(); } this.string = new IntsRefBuilder(); this.pathStates = new BitSet(a.getNumStates()); this.string.setLength(0); this.emitEmptyString = a.isAccept(0); // Start iteration with node 0. if (a.getNumTransitions(0) > 0) { pathStates.set(0); nodes[0].resetState(a, 0); string.append(0); } }
/** * Constructor. * * @param a Automaton to create finite string from. * @param startState The starting state for each path. * @param endState The state where each path should stop or -1 if only accepted states should be final. */ public FiniteStringsIterator(Automaton a, int startState, int endState) { this.a = a; this.endState = endState; this.nodes = new PathNode[16]; for (int i = 0, end = nodes.length; i < end; i++) { nodes[i] = new PathNode(); } this.string = new IntsRefBuilder(); this.pathStates = new BitSet(a.getNumStates()); this.string.setLength(0); this.emitEmptyString = a.isAccept(0); // Start iteration with node startState. if (a.getNumTransitions(startState) > 0) { pathStates.set(startState); nodes[0].resetState(a, startState); string.append(startState); } }