From e193fd14346e6e808c6c266d2bb13c0c0cc6890e Mon Sep 17 00:00:00 2001 From: Gilles Debunne Date: Mon, 18 Apr 2011 14:31:12 -0700 Subject: Extracted WordIterator class. This class will be used by TextView and the IMEs to cut the text into words. New getBeginning and getEnd methods that return word limits. Added Locale to constructor. Change-Id: Ie8ad590ebca4b48517ec7b4c3768b3e41879166e --- .../text/method/ArrowKeyMovementMethod.java | 105 ---------- core/java/android/text/method/WordIterator.java | 220 +++++++++++++++++++++ 2 files changed, 220 insertions(+), 105 deletions(-) create mode 100644 core/java/android/text/method/WordIterator.java (limited to 'core/java/android/text/method') diff --git a/core/java/android/text/method/ArrowKeyMovementMethod.java b/core/java/android/text/method/ArrowKeyMovementMethod.java index b25ba8d..d432dee 100644 --- a/core/java/android/text/method/ArrowKeyMovementMethod.java +++ b/core/java/android/text/method/ArrowKeyMovementMethod.java @@ -17,23 +17,14 @@ package android.text.method; import android.graphics.Rect; -import android.text.CharSequenceIterator; -import android.text.Editable; import android.text.Layout; import android.text.Selection; import android.text.Spannable; -import android.text.Spanned; -import android.text.TextWatcher; -import android.util.Log; -import android.util.MathUtils; import android.view.KeyEvent; import android.view.MotionEvent; import android.view.View; import android.widget.TextView; -import java.text.BreakIterator; -import java.text.CharacterIterator; - /** * A movement method that provides cursor movement and selection. * Supports displaying the context menu on DPad Center. @@ -332,102 +323,6 @@ public class ArrowKeyMovementMethod extends BaseMovementMethod implements Moveme return sInstance; } - /** - * Walks through cursor positions at word boundaries. Internally uses - * {@link BreakIterator#getWordInstance()}, and caches {@link CharSequence} - * for performance reasons. - */ - private static class WordIterator implements Selection.PositionIterator { - private CharSequence mCurrent; - private boolean mCurrentDirty = false; - - private BreakIterator mIterator; - - private TextWatcher mWatcher = new TextWatcher() { - /** {@inheritDoc} */ - public void beforeTextChanged(CharSequence s, int start, int count, int after) { - // ignored - } - - /** {@inheritDoc} */ - public void onTextChanged(CharSequence s, int start, int before, int count) { - mCurrentDirty = true; - } - - /** {@inheritDoc} */ - public void afterTextChanged(Editable s) { - // ignored - } - }; - - public void setCharSequence(CharSequence incoming) { - if (mIterator == null) { - mIterator = BreakIterator.getWordInstance(); - } - - // when incoming is different object, move listeners to new sequence - // and mark as dirty so we reload contents. - if (mCurrent != incoming) { - if (mCurrent instanceof Editable) { - ((Editable) mCurrent).removeSpan(mWatcher); - } - - if (incoming instanceof Editable) { - ((Editable) incoming).setSpan( - mWatcher, 0, incoming.length(), Spanned.SPAN_INCLUSIVE_INCLUSIVE); - } - - mCurrent = incoming; - mCurrentDirty = true; - } - - if (mCurrentDirty) { - final CharacterIterator charIterator = new CharSequenceIterator(mCurrent); - mIterator.setText(charIterator); - - mCurrentDirty = false; - } - } - - private boolean isValidOffset(int offset) { - return offset >= 0 && offset <= mCurrent.length(); - } - - private boolean isLetterOrDigit(int offset) { - if (isValidOffset(offset)) { - return Character.isLetterOrDigit(mCurrent.charAt(offset)); - } else { - return false; - } - } - - /** {@inheritDoc} */ - public int preceding(int offset) { - // always round cursor index into valid string index - offset = MathUtils.constrain(offset, 0, mCurrent.length()); - - do { - offset = mIterator.preceding(offset); - if (isLetterOrDigit(offset)) break; - } while (isValidOffset(offset)); - - return offset; - } - - /** {@inheritDoc} */ - public int following(int offset) { - // always round cursor index into valid string index - offset = MathUtils.constrain(offset, 0, mCurrent.length()); - - do { - offset = mIterator.following(offset); - if (isLetterOrDigit(offset - 1)) break; - } while (isValidOffset(offset)); - - return offset; - } - } - private WordIterator mWordIterator = new WordIterator(); private static final Object LAST_TAP_DOWN = new Object(); diff --git a/core/java/android/text/method/WordIterator.java b/core/java/android/text/method/WordIterator.java new file mode 100644 index 0000000..b250414 --- /dev/null +++ b/core/java/android/text/method/WordIterator.java @@ -0,0 +1,220 @@ + +/* + * Copyright (C) 2011 The Android Open Source Project + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package android.text.method; + +import android.text.CharSequenceIterator; +import android.text.Editable; +import android.text.Selection; +import android.text.Spanned; +import android.text.TextWatcher; + +import java.text.BreakIterator; +import java.text.CharacterIterator; +import java.util.Locale; + +/** + * Walks through cursor positions at word boundaries. Internally uses + * {@link BreakIterator#getWordInstance()}, and caches {@link CharSequence} + * for performance reasons. + * + * Also provides methods to determine word boundaries. + * {@hide} + */ +public class WordIterator implements Selection.PositionIterator { + private CharSequence mCurrent; + private boolean mCurrentDirty = false; + + private BreakIterator mIterator; + + /** + * Constructs a WordIterator using the default locale. + */ + public WordIterator() { + this(Locale.getDefault()); + } + + /** + * Constructs a new WordIterator for the specified locale. + * @param locale The locale to be used when analysing the text. + */ + public WordIterator(Locale locale) { + mIterator = BreakIterator.getWordInstance(locale); + } + + private final TextWatcher mWatcher = new TextWatcher() { + /** {@inheritDoc} */ + public void beforeTextChanged(CharSequence s, int start, int count, int after) { + // ignored + } + + /** {@inheritDoc} */ + public void onTextChanged(CharSequence s, int start, int before, int count) { + mCurrentDirty = true; + } + + /** {@inheritDoc} */ + public void afterTextChanged(Editable s) { + // ignored + } + }; + + public void setCharSequence(CharSequence incoming) { + // When incoming is different object, move listeners to new sequence + // and mark as dirty so we reload contents. + if (mCurrent != incoming) { + if (mCurrent instanceof Editable) { + ((Editable) mCurrent).removeSpan(mWatcher); + } + + if (incoming instanceof Editable) { + ((Editable) incoming).setSpan( + mWatcher, 0, incoming.length(), Spanned.SPAN_INCLUSIVE_INCLUSIVE); + } + + mCurrent = incoming; + mCurrentDirty = true; + } + + if (mCurrentDirty) { + final CharacterIterator charIterator = new CharSequenceIterator(mCurrent); + mIterator.setText(charIterator); + + mCurrentDirty = false; + } + } + + /** {@inheritDoc} */ + public int preceding(int offset) { + do { + offset = mIterator.preceding(offset); + if (offset == BreakIterator.DONE || isOnLetterOrDigit(offset)) { + break; + } + } while (true); + + return offset; + } + + /** {@inheritDoc} */ + public int following(int offset) { + do { + offset = mIterator.following(offset); + if (offset == BreakIterator.DONE || isAfterLetterOrDigit(offset)) { + break; + } + } while (true); + + return offset; + } + + /** If offset is within a word, returns the index of the first character of that + * word, otherwise returns BreakIterator.DONE. + * + * The offsets that are considered to be part of a word are the indexes of its characters, + * as well as the index of its last character plus one. + * If offset is the index of a low surrogate character, BreakIterator.DONE will be returned. + * + * Valid range for offset is [0..textLength] (note the inclusive upper bound). + * The returned value is within [0..offset] or BreakIterator.DONE. + * + * @throws IllegalArgumentException is offset is not valid. + */ + public int getBeginning(int offset) { + checkOffsetIsValid(offset); + + if (isOnLetterOrDigit(offset)) { + if (mIterator.isBoundary(offset)) { + return offset; + } else { + return mIterator.preceding(offset); + } + } else { + if (isAfterLetterOrDigit(offset)) { + return mIterator.preceding(offset); + } + } + return BreakIterator.DONE; + } + + /** If offset is within a word, returns the index of the last character of that + * word plus one, otherwise returns BreakIterator.DONE. + * + * The offsets that are considered to be part of a word are the indexes of its characters, + * as well as the index of its last character plus one. + * If offset is the index of a low surrogate character, BreakIterator.DONE will be returned. + * + * Valid range for offset is [0..textLength] (note the inclusive upper bound). + * The returned value is within [offset..textLength] or BreakIterator.DONE. + * + * @throws IllegalArgumentException is offset is not valid. + */ + public int getEnd(int offset) { + checkOffsetIsValid(offset); + + if (isAfterLetterOrDigit(offset)) { + if (mIterator.isBoundary(offset)) { + return offset; + } else { + return mIterator.following(offset); + } + } else { + if (isOnLetterOrDigit(offset)) { + return mIterator.following(offset); + } + } + return BreakIterator.DONE; + } + + private boolean isAfterLetterOrDigit(int offset) { + if (offset - 1 >= 0) { + final char previousChar = mCurrent.charAt(offset - 1); + if (Character.isLetterOrDigit(previousChar)) return true; + if (offset - 2 >= 0) { + final char previousPreviousChar = mCurrent.charAt(offset - 2); + if (Character.isSurrogatePair(previousPreviousChar, previousChar)) { + final int codePoint = Character.toCodePoint(previousPreviousChar, previousChar); + return Character.isLetterOrDigit(codePoint); + } + } + } + return false; + } + + private boolean isOnLetterOrDigit(int offset) { + final int length = mCurrent.length(); + if (offset < length) { + final char currentChar = mCurrent.charAt(offset); + if (Character.isLetterOrDigit(currentChar)) return true; + if (offset + 1 < length) { + final char nextChar = mCurrent.charAt(offset + 1); + if (Character.isSurrogatePair(currentChar, nextChar)) { + final int codePoint = Character.toCodePoint(currentChar, nextChar); + return Character.isLetterOrDigit(codePoint); + } + } + } + return false; + } + + private void checkOffsetIsValid(int offset) { + if (offset < 0 || offset > mCurrent.length()) { + final String message = "Valid range is [0, " + mCurrent.length() + "]"; + throw new IllegalArgumentException(message); + } + } +} -- cgit v1.1