body in byte count.
* <p>
* In <code>header, each field except for checksum implies the
* length of each field. Since <code>BMPdataLength is a fixed-length
* data(512 entries), its length isn't included in <code>header.
* <code>checksum is a CRC32 value of all in body.
* <pre>
* header_info {
* u4 stateTableLength;
* u4 backwardsStateTableLength;
* u4 endStatesLength;
* u4 lookaheadStatesLength;
* u4 BMPdataLength;
* u4 nonBMPdataLength;
* u4 additionalDataLength;
* u8 checksum;
* }
* </pre>
* <p>
*
* Finally, <code>BMPindices and BMPdata are set to
* <code>charCategoryTable. nonBMPdata is set to
* <code>supplementaryCharCategoryTable.
* <pre>
* body {
* u2 stateTable[stateTableLength];
* u2 backwardsStateTable[backwardsStateTableLength];
* u1 endStates[endStatesLength];
* u1 lookaheadStates[lookaheadStatesLength];
* u2 BMPindices[512];
* u1 BMPdata[BMPdataLength];
* u4 nonBMPdata[numNonBMPdataLength];
* u1 additionalData[additionalDataLength];
* }
* </pre>
*/
protected final void readTables(String datafile)
throws IOException, MissingResourceException {
byte[] buffer = readFile(datafile);
/* Read header_info. */
int stateTableLength = getInt(buffer, 0);
int backwardsStateTableLength = getInt(buffer, 4);
int endStatesLength = getInt(buffer, 8);
int lookaheadStatesLength = getInt(buffer, 12);
int BMPdataLength = getInt(buffer, 16);
int nonBMPdataLength = getInt(buffer, 20);
int additionalDataLength = getInt(buffer, 24);
checksum = getLong(buffer, 28);
/* Read stateTable[numCategories * numRows] */
stateTable = new short[stateTableLength];
int offset = HEADER_LENGTH;
for (int i = 0; i < stateTableLength; i++, offset+=2) {
stateTable[i] = getShort(buffer, offset);
}
/* Read backwardsStateTable[numCategories * numRows] */
backwardsStateTable = new short[backwardsStateTableLength];
for (int i = 0; i < backwardsStateTableLength; i++, offset+=2) {
backwardsStateTable[i] = getShort(buffer, offset);
}
/* Read endStates[numRows] */
endStates = new boolean[endStatesLength];
for (int i = 0; i < endStatesLength; i++, offset++) {
endStates[i] = buffer[offset] == 1;
}
/* Read lookaheadStates[numRows] */
lookaheadStates = new boolean[lookaheadStatesLength];
for (int i = 0; i < lookaheadStatesLength; i++, offset++) {
lookaheadStates[i] = buffer[offset] == 1;
}
/* Read a category table and indices for BMP characters. */
short[] temp1 = new short[BMP_INDICES_LENGTH]; // BMPindices
for (int i = 0; i < BMP_INDICES_LENGTH; i++, offset+=2) {
temp1[i] = getShort(buffer, offset);
}
byte[] temp2 = new byte[BMPdataLength]; // BMPdata
System.arraycopy(buffer, offset, temp2, 0, BMPdataLength);
offset += BMPdataLength;
charCategoryTable = new CompactByteArray(temp1, temp2);
/* Read a category table for non-BMP characters. */
int[] temp3 = new int[nonBMPdataLength];
for (int i = 0; i < nonBMPdataLength; i++, offset+=4) {
temp3[i] = getInt(buffer, offset);
}
supplementaryCharCategoryTable = new SupplementaryCharacterData(temp3);
/* Read additional data */
if (additionalDataLength > 0) {
additionalData = new byte[additionalDataLength];
System.arraycopy(buffer, offset, additionalData, 0, additionalDataLength);
}
/* Set numCategories */
numCategories = stateTable.length / endStates.length;
}
protected byte[] readFile(final String datafile)
throws IOException, MissingResourceException {
BufferedInputStream is;
try {
is = AccessController.doPrivileged(
new PrivilegedExceptionAction<BufferedInputStream>() {
@Override
public BufferedInputStream run() throws Exception {
return new BufferedInputStream(getClass().getResourceAsStream("/sun/text/resources/" + datafile));
}
}
);
}
catch (PrivilegedActionException e) {
throw new InternalError(e.toString(), e);
}
int offset = 0;
/* First, read magic, version, and header_info. */
int len = LABEL_LENGTH + 5;
byte[] buf = new byte[len];
if (is.read(buf) != len) {
throw new MissingResourceException("Wrong header length",
datafile, "");
}
/* Validate the magic number. */
for (int i = 0; i < LABEL_LENGTH; i++, offset++) {
if (buf[offset] != LABEL[offset]) {
throw new MissingResourceException("Wrong magic number",
datafile, "");
}
}
/* Validate the version number. */
if (buf[offset] != supportedVersion) {
throw new MissingResourceException("Unsupported version(" + buf[offset] + ")",
datafile, "");
}
/* Read data: totalDataSize + 8(for checksum) */
len = getInt(buf, ++offset);
buf = new byte[len];
if (is.read(buf) != len) {
throw new MissingResourceException("Wrong data length",
datafile, "");
}
is.close();
return buf;
}
byte[] getAdditionalData() {
return additionalData;
}
void setAdditionalData(byte[] b) {
additionalData = b;
}
//=======================================================================
// boilerplate
//=======================================================================
/**
* Clones this iterator.
* @return A newly-constructed RuleBasedBreakIterator with the same
* behavior as this one.
*/
@Override
public Object clone() {
RuleBasedBreakIterator result = (RuleBasedBreakIterator) super.clone();
if (text != null) {
result.text = (CharacterIterator) text.clone();
}
return result;
}
/**
* Returns true if both BreakIterators are of the same class, have the same
* rules, and iterate over the same text.
*/
@Override
public boolean equals(Object that) {
try {
if (that == null) {
return false;
}
RuleBasedBreakIterator other = (RuleBasedBreakIterator) that;
if (checksum != other.checksum) {
return false;
}
if (text == null) {
return other.text == null;
} else {
return text.equals(other.text);
}
}
catch(ClassCastException e) {
return false;
}
}
/**
* Returns text
*/
@Override
public String toString() {
StringBuilder sb = new StringBuilder();
sb.append('[');
sb.append("checksum=0x");
sb.append(Long.toHexString(checksum));
sb.append(']');
return sb.toString();
}
/**
* Compute a hashcode for this BreakIterator
* @return A hash code
*/
@Override
public int hashCode() {
return (int)checksum;
}
//=======================================================================
// BreakIterator overrides
//=======================================================================
/**
* Sets the current iteration position to the beginning of the text.
* (i.e., the CharacterIterator's starting offset).
* @return The offset of the beginning of the text.
*/
@Override
public int first() {
CharacterIterator t = getText();
t.first();
return t.getIndex();
}
/**
* Sets the current iteration position to the end of the text.
* (i.e., the CharacterIterator's ending offset).
* @return The text's past-the-end offset.
*/
@Override
public int last() {
CharacterIterator t = getText();
// I'm not sure why, but t.last() returns the offset of the last character,
// rather than the past-the-end offset
t.setIndex(t.getEndIndex());
return t.getIndex();
}
/**
* Advances the iterator either forward or backward the specified number of steps.
* Negative values move backward, and positive values move forward. This is
* equivalent to repeatedly calling next() or previous().
* @param n The number of steps to move. The sign indicates the direction
* (negative is backwards, and positive is forwards).
* @return The character offset of the boundary position n boundaries away from
* the current one.
*/
@Override
public int next(int n) {
int result = current();
while (n > 0) {
result = handleNext();
--n;
}
while (n < 0) {
result = previous();
++n;
}
return result;
}
/**
* Advances the iterator to the next boundary position.
* @return The position of the first boundary after this one.
*/
@Override
public int next() {
return handleNext();
}
private int cachedLastKnownBreak = BreakIterator.DONE;
/**
* Advances the iterator backwards, to the last boundary preceding this one.
* @return The position of the last boundary position preceding this one.
*/
@Override
public int previous() {
// if we're already sitting at the beginning of the text, return DONE
CharacterIterator text = getText();
if (current() == text.getBeginIndex()) {
return BreakIterator.DONE;
}
// set things up. handlePrevious() will back us up to some valid
// break position before the current position (we back our internal
// iterator up one step to prevent handlePrevious() from returning
// the current position), but not necessarily the last one before
// where we started
int start = current();
int lastResult = cachedLastKnownBreak;
if (lastResult >= start || lastResult <= BreakIterator.DONE) {
getPrevious();
lastResult = handlePrevious();
} else {
//it might be better to check if handlePrevious() give us closer
//safe value but handlePrevious() is slow too
//So, this has to be done carefully
text.setIndex(lastResult);
}
int result = lastResult;
// iterate forward from the known break position until we pass our
// starting point. The last break position before the starting
// point is our return value
while (result != BreakIterator.DONE && result < start) {
lastResult = result;
result = handleNext();
}
// set the current iteration position to be the last break position
// before where we started, and then return that value
text.setIndex(lastResult);
cachedLastKnownBreak = lastResult;
return lastResult;
}
/**
* Returns previous character
*/
private int getPrevious() {
char c2 = text.previous();
if (Character.isLowSurrogate(c2) &&
text.getIndex() > text.getBeginIndex()) {
char c1 = text.previous();
if (Character.isHighSurrogate(c1)) {
return Character.toCodePoint(c1, c2);
} else {
text.next();
}
}
return (int)c2;
}
/**
* Returns current character
*/
int getCurrent() {
char c1 = text.current();
if (Character.isHighSurrogate(c1) &&
text.getIndex() < text.getEndIndex()) {
char c2 = text.next();
text.previous();
if (Character.isLowSurrogate(c2)) {
return Character.toCodePoint(c1, c2);
}
}
return (int)c1;
}
/**
* Returns the count of next character.
*/
private int getCurrentCodePointCount() {
char c1 = text.current();
if (Character.isHighSurrogate(c1) &&
text.getIndex() < text.getEndIndex()) {
char c2 = text.next();
text.previous();
if (Character.isLowSurrogate(c2)) {
return 2;
}
}
return 1;
}
/**
* Returns next character
*/
int getNext() {
int index = text.getIndex();
int endIndex = text.getEndIndex();
if (index == endIndex ||
(index += getCurrentCodePointCount()) >= endIndex) {
return CharacterIterator.DONE;
}
text.setIndex(index);
return getCurrent();
}
/**
* Returns the position of next character.
*/
private int getNextIndex() {
int index = text.getIndex() + getCurrentCodePointCount();
int endIndex = text.getEndIndex();
if (index > endIndex) {
return endIndex;
} else {
return index;
}
}
/**
* Throw IllegalArgumentException unless begin <= offset < end.
*/
protected static final void checkOffset(int offset, CharacterIterator text) {
if (offset < text.getBeginIndex() || offset > text.getEndIndex()) {
throw new IllegalArgumentException("offset out of bounds");
}
}
/**
* Sets the iterator to refer to the first boundary position following
* the specified position.
* @offset The position from which to begin searching for a break position.
* @return The position of the first break after the current position.
*/
@Override
public int following(int offset) {
CharacterIterator text = getText();
checkOffset(offset, text);
// Set our internal iteration position (temporarily)
// to the position passed in. If this is the _beginning_ position,
// then we can just use next() to get our return value
text.setIndex(offset);
if (offset == text.getBeginIndex()) {
cachedLastKnownBreak = handleNext();
return cachedLastKnownBreak;
}
// otherwise, we have to sync up first. Use handlePrevious() to back
// us up to a known break position before the specified position (if
// we can determine that the specified position is a break position,
// we don't back up at all). This may or may not be the last break
// position at or before our starting position. Advance forward
// from here until we've passed the starting position. The position
// we stop on will be the first break position after the specified one.
int result = cachedLastKnownBreak;
if (result >= offset || result <= BreakIterator.DONE) {
result = handlePrevious();
} else {
//it might be better to check if handlePrevious() give us closer
//safe value but handlePrevious() is slow too
//So, this has to be done carefully
text.setIndex(result);
}
while (result != BreakIterator.DONE && result <= offset) {
result = handleNext();
}
cachedLastKnownBreak = result;
return result;
}
/**
* Sets the iterator to refer to the last boundary position before the
* specified position.
* @offset The position to begin searching for a break from.
* @return The position of the last boundary before the starting position.
*/
@Override
public int preceding(int offset) {
// if we start by updating the current iteration position to the
// position specified by the caller, we can just use previous()
// to carry out this operation
CharacterIterator text = getText();
checkOffset(offset, text);
text.setIndex(offset);
return previous();
}
/**
* Returns true if the specified position is a boundary position. As a side
* effect, leaves the iterator pointing to the first boundary position at
* or after "offset".
* @param offset the offset to check.
* @return True if "offset" is a boundary position.
*/
@Override
public boolean isBoundary(int offset) {
CharacterIterator text = getText();
checkOffset(offset, text);
if (offset == text.getBeginIndex()) {
return true;
}
// to check whether this is a boundary, we can use following() on the
// position before the specified one and return true if the position we
// get back is the one the user specified
else {
return following(offset - 1) == offset;
}
}
/**
* Returns the current iteration position.
* @return The current iteration position.
*/
@Override
public int current() {
return getText().getIndex();
}
/**
* Return a CharacterIterator over the text being analyzed. This version
* of this method returns the actual CharacterIterator we're using internally.
* Changing the state of this iterator can have undefined consequences. If
* you need to change it, clone it first.
* @return An iterator over the text being analyzed.
*/
@Override
public CharacterIterator getText() {
// The iterator is initialized pointing to no text at all, so if this
// function is called while we're in that state, we have to fudge an
// iterator to return.
if (text == null) {
text = new StringCharacterIterator("");
}
return text;
}
/**
* Set the iterator to analyze a new piece of text. This function resets
* the current iteration position to the beginning of the text.
* @param newText An iterator over the text to analyze.
*/
@Override
public void setText(CharacterIterator newText) {
// Test iterator to see if we need to wrap it in a SafeCharIterator.
// The correct behavior for CharacterIterators is to allow the
// position to be set to the endpoint of the iterator. Many
// CharacterIterators do not uphold this, so this is a workaround
// to permit them to use this class.
int end = newText.getEndIndex();
boolean goodIterator;
try {
newText.setIndex(end); // some buggy iterators throw an exception here
goodIterator = newText.getIndex() == end;
}
catch(IllegalArgumentException e) {
goodIterator = false;
}
if (goodIterator) {
text = newText;
}
else {
text = new SafeCharIterator(newText);
}
text.first();
cachedLastKnownBreak = BreakIterator.DONE;
}
//=======================================================================
// implementation
//=======================================================================
/**
* This method is the actual implementation of the next() method. All iteration
* vectors through here. This method initializes the state machine to state 1
* and advances through the text character by character until we reach the end
* of the text or the state machine transitions to state 0. We update our return
* value every time the state machine passes through a possible end state.
*/
protected int handleNext() {
// if we're already at the end of the text, return DONE.
CharacterIterator text = getText();
if (text.getIndex() == text.getEndIndex()) {
return BreakIterator.DONE;
}
// no matter what, we always advance at least one character forward
int result = getNextIndex();
int lookaheadResult = 0;
// begin in state 1
int state = START_STATE;
int category;
int c = getCurrent();
// loop until we reach the end of the text or transition to state 0
while (c != CharacterIterator.DONE && state != STOP_STATE) {
// look up the current character's character category (which tells us
// which column in the state table to look at)
category = lookupCategory(c);
// if the character isn't an ignore character, look up a state
// transition in the state table
if (category != IGNORE) {
state = lookupState(state, category);
}
// if the state we've just transitioned to is a lookahead state,
// (but not also an end state), save its position. If it's
// both a lookahead state and an end state, update the break position
// to the last saved lookup-state position
if (lookaheadStates[state]) {
if (endStates[state]) {
result = lookaheadResult;
}
else {
lookaheadResult = getNextIndex();
}
}
// otherwise, if the state we've just transitioned to is an accepting
// state, update the break position to be the current iteration position
else {
if (endStates[state]) {
result = getNextIndex();
}
}
c = getNext();
}
// if we've run off the end of the text, and the very last character took us into
// a lookahead state, advance the break position to the lookahead position
// (the theory here is that if there are no characters at all after the lookahead
// position, that always matches the lookahead criteria)
if (c == CharacterIterator.DONE && lookaheadResult == text.getEndIndex()) {
result = lookaheadResult;
}
text.setIndex(result);
return result;
}
/**
* This method backs the iterator back up to a "safe position" in the text.
* This is a position that we know, without any context, must be a break position.
* The various calling methods then iterate forward from this safe position to
* the appropriate position to return. (For more information, see the description
* of buildBackwardsStateTable() in RuleBasedBreakIterator.Builder.)
*/
protected int handlePrevious() {
CharacterIterator text = getText();
int state = START_STATE;
int category = 0;
int lastCategory = 0;
int c = getCurrent();
// loop until we reach the beginning of the text or transition to state 0
while (c != CharacterIterator.DONE && state != STOP_STATE) {
// save the last character's category and look up the current
// character's category
lastCategory = category;
category = lookupCategory(c);
// if the current character isn't an ignore character, look up a
// state transition in the backwards state table
if (category != IGNORE) {
state = lookupBackwardState(state, category);
}
// then advance one character backwards
c = getPrevious();
}
// if we didn't march off the beginning of the text, we're either one or two
// positions away from the real break position. (One because of the call to
// previous() at the end of the loop above, and another because the character
// that takes us into the stop state will always be the character BEFORE
// the break position.)
if (c != CharacterIterator.DONE) {
if (lastCategory != IGNORE) {
getNext();
getNext();
}
else {
getNext();
}
}
return text.getIndex();
}
/**
* Looks up a character's category (i.e., its category for breaking purposes,
* not its Unicode category)
*/
protected int lookupCategory(int c) {
if (c < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
return charCategoryTable.elementAt((char)c);
} else {
return supplementaryCharCategoryTable.getValue(c);
}
}
/**
* Given a current state and a character category, looks up the
* next state to transition to in the state table.
*/
protected int lookupState(int state, int category) {
return stateTable[state * numCategories + category];
}
/**
* Given a current state and a character category, looks up the
* next state to transition to in the backwards state table.
*/
protected int lookupBackwardState(int state, int category) {
return backwardsStateTable[state * numCategories + category];
}
static long getLong(byte[] buf, int offset) {
long num = buf[offset]&0xFF;
for (int i = 1; i < 8; i++) {
num = num<<8 | (buf[offset+i]&0xFF);
}
return num;
}
static int getInt(byte[] buf, int offset) {
int num = buf[offset]&0xFF;
for (int i = 1; i < 4; i++) {
num = num<<8 | (buf[offset+i]&0xFF);
}
return num;
}
static short getShort(byte[] buf, int offset) {
short num = (short)(buf[offset]&0xFF);
num = (short)(num<<8 | (buf[offset+1]&0xFF));
return num;
}
/*
* This class exists to work around a bug in incorrect implementations
* of CharacterIterator, which incorrectly handle setIndex(endIndex).
* This iterator relies only on base.setIndex(n) where n is less than
* endIndex.
*
* One caveat: if the base iterator's begin and end indices change
* the change will not be reflected by this wrapper. Does that matter?
*/
// TODO: Review this class to see if it's still required.
private static final class SafeCharIterator implements CharacterIterator,
Cloneable {
private CharacterIterator base;
private int rangeStart;
private int rangeLimit;
private int currentIndex;
SafeCharIterator(CharacterIterator base) {
this.base = base;
this.rangeStart = base.getBeginIndex();
this.rangeLimit = base.getEndIndex();
this.currentIndex = base.getIndex();
}
@Override
public char first() {
return setIndex(rangeStart);
}
@Override
public char last() {
return setIndex(rangeLimit - 1);
}
@Override
public char current() {
if (currentIndex < rangeStart || currentIndex >= rangeLimit) {
return DONE;
}
else {
return base.setIndex(currentIndex);
}
}
@Override
public char next() {
currentIndex++;
if (currentIndex >= rangeLimit) {
currentIndex = rangeLimit;
return DONE;
}
else {
return base.setIndex(currentIndex);
}
}
@Override
public char previous() {
currentIndex--;
if (currentIndex < rangeStart) {
currentIndex = rangeStart;
return DONE;
}
else {
return base.setIndex(currentIndex);
}
}
@Override
public char setIndex(int i) {
if (i < rangeStart || i > rangeLimit) {
throw new IllegalArgumentException("Invalid position");
}
currentIndex = i;
return current();
}
@Override
public int getBeginIndex() {
return rangeStart;
}
@Override
public int getEndIndex() {
return rangeLimit;
}
@Override
public int getIndex() {
return currentIndex;
}
@Override
public Object clone() {
SafeCharIterator copy = null;
try {
copy = (SafeCharIterator) super.clone();
}
catch(CloneNotSupportedException e) {
throw new Error("Clone not supported: " + e);
}
CharacterIterator copyOfBase = (CharacterIterator) base.clone();
copy.base = copyOfBase;
return copy;
}
}
}
The search page
Other Java source code examples at this package level
Click here to learn more about this project
Java example source code file (RuleBasedBreakIterator.java)
The RuleBasedBreakIterator.java Java example source code/* * Copyright (c) 1999, 2013, Oracle and/or its affiliates. All rights reserved. * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. * * This code is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 only, as * published by the Free Software Foundation. Oracle designates this * particular file as subject to the "Classpath" exception as provided * by Oracle in the LICENSE file that accompanied this code. * * This code is distributed in the hope that it will be useful, but WITHOUT * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License * version 2 for more details (a copy is included in the LICENSE file that * accompanied this code). * * You should have received a copy of the GNU General Public License version * 2 along with this work; if not, write to the Free Software Foundation, * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. * * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA * or visit www.oracle.com if you need additional information or have any * questions. */ /* * * (C) Copyright Taligent, Inc. 1996, 1997 - All Rights Reserved * (C) Copyright IBM Corp. 1996 - 2002 - All Rights Reserved * * The original version of this source code and documentation * is copyrighted and owned by Taligent, Inc., a wholly-owned * subsidiary of IBM. These materials are provided under terms * of a License Agreement between Taligent and Sun. This technology * is protected by multiple US and International patents. * * This notice and attribution to Taligent may not be removed. * Taligent is a registered trademark of Taligent, Inc. */ package sun.util.locale.provider; import java.io.BufferedInputStream; import java.io.IOException; import java.security.AccessController; import java.security.PrivilegedActionException; import java.security.PrivilegedExceptionAction; import java.text.BreakIterator; import java.text.CharacterIterator; import java.text.StringCharacterIterator; import java.util.MissingResourceException; import sun.text.CompactByteArray; import sun.text.SupplementaryCharacterData; /** * <p>A subclass of BreakIterator whose behavior is specified using a list of rules. * * <p>There are two kinds of rules, which are separated by semicolons: substitutions * and <i>regular expressions. * * <p>A substitution rule defines a name that can be used in place of an expression. It * consists of a name, which is a string of characters contained in angle brackets, an equals * sign, and an expression. (There can be no whitespace on either side of the equals sign.) * To keep its syntactic meaning intact, the expression must be enclosed in parentheses or * square brackets. A substitution is visible after its definition, and is filled in using * simple textual substitution. Substitution definitions can contain other substitutions, as * long as those substitutions have been defined first. Substitutions are generally used to * make the regular expressions (which can get quite complex) shorted and easier to read. * They typically define either character categories or commonly-used subexpressions.</p> * * <p>There is one special substitution. If the description defines a substitution * called "<ignore>", the expression must be a [] expression, and the * expression defines a set of characters (the "<em>ignore characters") that * will be transparent to the BreakIterator. A sequence of characters will break the * same way it would if any ignore characters it contains are taken out. Break * positions never occur befoer ignore characters.</p> * * <p>A regular expression uses a subset of the normal Unix regular-expression syntax, and * defines a sequence of characters to be kept together. With one significant exception, the * iterator uses a longest-possible-match algorithm when matching text to regular * expressions. The iterator also treats descriptions containing multiple regular expressions * as if they were ORed together (i.e., as if they were separated by |).</p> * * <p>The special characters recognized by the regular-expression parser are as follows: * * <blockquote> * <table border="1" width="100%"> * <tr> * <td width="6%">* |
