IRule capable of detecting words.
* - * Word rules also allow for the association of tokens with specific words. - * That is, not only can the rule be used to provide tokens for exact matches, - * but also for the generalized notion of a word in the context in which it is used. - * A word rules uses a word detector to determine what a word is.
+ * Word rules also allow for the association of tokens with specific words. That + * is, not only can the rule be used to provide tokens for exact matches, but + * also for the generalized notion of a word in the context in which it is used. + * A word rules uses a word detector to determine what a word is. + * *- * This word rule allows a word detector to be shared among different word matchers. - * Its up to the word matchers to decide if a word matches and, in this a case, which - * token is associated with that word. + * This word rule allows a word detector to be shared among different word + * matchers. Its up to the word matchers to decide if a word matches and, in + * this a case, which token is associated with that word. *
* * @see IWordDetector * @since 3.0 */ public class CombinedWordRule implements IRule { - + /** * Word matcher, that associates matched words with tokens. */ public static class WordMatcher { - + /** The table of predefined words and token for this matcher */ - private Map fWords= new HashMap(); + private Map fWords = new HashMap(); /** * Adds a word and the token to be returned if it is detected. - * - * @param word the word this rule will search for, may not benull
- * @param token the token to be returned if the word has been found, may not be null
+ *
+ * @param word
+ * the word this rule will search for, may not be
+ * null
+ * @param token
+ * the token to be returned if the word has been found, may
+ * not be null
*/
public void addWord(String word, IToken token) {
Assert.isNotNull(word);
- Assert.isNotNull(token);
-
+ Assert.isNotNull(token);
+
fWords.put(new CharacterBuffer(word), token);
}
-
+
/**
* Returns the token associated to the given word and the scanner state.
*
- * @param scanner the scanner
- * @param word the word
- * @return the token or null if none is associated by this matcher
+ * @param scanner
+ * the scanner
+ * @param word
+ * the word
+ * @return the token or null if none is associated by
+ * this matcher
*/
public IToken evaluate(ICharacterScanner scanner, CharacterBuffer word) {
- IToken token= (IToken) fWords.get(word);
+ IToken token = (IToken) fWords.get(word);
if (token != null)
return token;
return Token.UNDEFINED;
}
-
+
/**
* Removes all words.
*/
@@ -84,64 +90,70 @@ public class CombinedWordRule implements IRule {
fWords.clear();
}
}
-
+
/**
- * Character buffer, mutable or suitable for use as key in hash maps.
+ * Character buffer, mutable or suitable for use as key in hash
+ * maps.
*/
public static class CharacterBuffer {
-
+
/** Buffer content */
private char[] fContent;
+
/** Buffer content size */
- private int fLength= 0;
-
+ private int fLength = 0;
+
/** Is hash code cached? */
- private boolean fIsHashCached= false;
+ private boolean fIsHashCached = false;
+
/** The hash code */
private int fHashCode;
-
+
/**
* Initialize with the given capacity.
- *
- * @param capacity the initial capacity
+ *
+ * @param capacity
+ * the initial capacity
*/
public CharacterBuffer(int capacity) {
- fContent= new char[capacity];
+ fContent = new char[capacity];
}
-
+
/**
* Initialize with the given content.
- *
- * @param string the initial content
+ *
+ * @param string
+ * the initial content
*/
public CharacterBuffer(String content) {
- fContent= content.toCharArray();
- fLength= content.length();
+ fContent = content.toCharArray();
+ fLength = content.length();
}
-
+
/**
* Empties this buffer.
*/
public void clear() {
- fIsHashCached= false;
- fLength= 0;
+ fIsHashCached = false;
+ fLength = 0;
}
-
+
/**
* Appends the given character to the buffer.
*
- * @param c the character
+ * @param c
+ * the character
*/
public void append(char c) {
- fIsHashCached= false;
+ fIsHashCached = false;
if (fLength == fContent.length) {
- char[] old= fContent;
- fContent= new char[old.length << 1];
+ char[] old = fContent;
+ fContent = new char[old.length << 1];
System.arraycopy(old, 0, fContent, 0, old.length);
}
- fContent[fLength++]= c;
+ fContent[fLength++] = c;
}
-
+
/**
* Returns the length of the content.
*
@@ -150,7 +162,7 @@ public class CombinedWordRule implements IRule {
public int length() {
return fLength;
}
-
+
/**
* Returns the content as string.
*
@@ -159,33 +171,33 @@ public class CombinedWordRule implements IRule {
public String toString() {
return new String(fContent, 0, fLength);
}
-
+
/**
* Returns the character at the given position.
*
- * @param i the position
+ * @param i
+ * the position
* @return the character at position i
*/
public char charAt(int i) {
return fContent[i];
}
-
+
/*
* @see java.lang.Object#hashCode()
*/
public int hashCode() {
if (fIsHashCached)
return fHashCode;
-
- int hash= 0;
- for (int i= 0, n= fLength; i < n; i++)
- hash= 29*hash + fContent[i];
- fHashCode= hash;
- fIsHashCached= true;
+
+ int hash = 0;
+ for (int i = 0, n = fLength; i < n; i++)
+ hash = 29 * hash + fContent[i];
+ fHashCode = hash;
+ fIsHashCached = true;
return hash;
}
-
-
+
/*
* @see java.lang.Object#equals(java.lang.Object)
*/
@@ -194,27 +206,29 @@ public class CombinedWordRule implements IRule {
return true;
if (!(obj instanceof CharacterBuffer))
return false;
- CharacterBuffer buffer= (CharacterBuffer) obj;
- int length= buffer.length();
+ CharacterBuffer buffer = (CharacterBuffer) obj;
+ int length = buffer.length();
if (length != fLength)
return false;
- for (int i= 0; i < length; i++)
+ for (int i = 0; i < length; i++)
if (buffer.charAt(i) != fContent[i])
return false;
return true;
}
-
+
/**
* Is the content equal to the given string?
*
- * @param string the string
- * @return true iff the content is the same character sequence as in the string
+ * @param string
+ * the string
+ * @return true iff the content is the same character
+ * sequence as in the string
*/
public boolean equals(String string) {
- int length= string.length();
+ int length = string.length();
if (length != fLength)
return false;
- for (int i= 0; i < length; i++)
+ for (int i = 0; i < length; i++)
if (string.charAt(i) != fContent[i])
return false;
return true;
@@ -222,28 +236,36 @@ public class CombinedWordRule implements IRule {
}
/** Internal setting for the uninitialized column constraint */
- private static final int UNDEFINED= -1;
-
+ private static final int UNDEFINED = -1;
+
/** The word detector used by this rule */
private IWordDetector fDetector;
- /** The default token to be returned on success and if nothing else has been specified. */
+
+ /**
+ * The default token to be returned on success and if nothing else has been
+ * specified.
+ */
private IToken fDefaultToken;
+
/** The column constraint */
- private int fColumn= UNDEFINED;
+ private int fColumn = UNDEFINED;
+
/** Buffer used for pattern detection */
- private CharacterBuffer fBuffer= new CharacterBuffer(16);
-
+ private CharacterBuffer fBuffer = new CharacterBuffer(16);
+
/** List of word matchers */
- private List fMatchers= new ArrayList();
+ private List fMatchers = new ArrayList();
/**
- * Creates a rule which, with the help of an word detector, will return the token
- * associated with the detected word. If no token has been associated, the scanner
- * will be rolled back and an undefined token will be returned in order to allow
- * any subsequent rules to analyze the characters.
- *
- * @param detector the word detector to be used by this rule, may not be null
- *
+ * Creates a rule which, with the help of an word detector, will return the
+ * token associated with the detected word. If no token has been associated,
+ * the scanner will be rolled back and an undefined token will be returned
+ * in order to allow any subsequent rules to analyze the characters.
+ *
+ * @param detector
+ * the word detector to be used by this rule, may not be
+ * null
+ *
* @see #addWord(String, IToken)
*/
public CombinedWordRule(IWordDetector detector) {
@@ -251,14 +273,17 @@ public class CombinedWordRule implements IRule {
}
/**
- * Creates a rule which, with the help of an word detector, will return the token
- * associated with the detected word. If no token has been associated, the
- * specified default token will be returned.
- *
- * @param detector the word detector to be used by this rule, may not be null
- * @param defaultToken the default token to be returned on success
- * if nothing else is specified, may not be null
- *
+ * Creates a rule which, with the help of an word detector, will return the
+ * token associated with the detected word. If no token has been associated,
+ * the specified default token will be returned.
+ *
+ * @param detector
+ * the word detector to be used by this rule, may not be
+ * null
+ * @param defaultToken
+ * the default token to be returned on success if nothing else is
+ * specified, may not be null
+ *
* @see #addWord(String, IToken)
*/
public CombinedWordRule(IWordDetector detector, IToken defaultToken) {
@@ -266,14 +291,17 @@ public class CombinedWordRule implements IRule {
}
/**
- * Creates a rule which, with the help of an word detector, will return the token
- * associated with the detected word. If no token has been associated, the scanner
- * will be rolled back and an undefined token will be returned in order to allow
- * any subsequent rules to analyze the characters.
- *
- * @param detector the word detector to be used by this rule, may not be null
- * @param matcher the initial word matcher
- *
+ * Creates a rule which, with the help of an word detector, will return the
+ * token associated with the detected word. If no token has been associated,
+ * the scanner will be rolled back and an undefined token will be returned
+ * in order to allow any subsequent rules to analyze the characters.
+ *
+ * @param detector
+ * the word detector to be used by this rule, may not be
+ * null
+ * @param matcher
+ * the initial word matcher
+ *
* @see #addWord(String, IToken)
*/
public CombinedWordRule(IWordDetector detector, WordMatcher matcher) {
@@ -281,91 +309,100 @@ public class CombinedWordRule implements IRule {
}
/**
- * Creates a rule which, with the help of an word detector, will return the token
- * associated with the detected word. If no token has been associated, the
- * specified default token will be returned.
- *
- * @param detector the word detector to be used by this rule, may not be null
- * @param matcher the initial word matcher
- * @param defaultToken the default token to be returned on success
- * if nothing else is specified, may not be null
- *
+ * Creates a rule which, with the help of an word detector, will return the
+ * token associated with the detected word. If no token has been associated,
+ * the specified default token will be returned.
+ *
+ * @param detector
+ * the word detector to be used by this rule, may not be
+ * null
+ * @param matcher
+ * the initial word matcher
+ * @param defaultToken
+ * the default token to be returned on success if nothing else is
+ * specified, may not be null
+ *
* @see #addWord(String, IToken)
*/
- public CombinedWordRule(IWordDetector detector, WordMatcher matcher, IToken defaultToken) {
-
+ public CombinedWordRule(IWordDetector detector, WordMatcher matcher,
+ IToken defaultToken) {
+
Assert.isNotNull(detector);
Assert.isNotNull(defaultToken);
-
- fDetector= detector;
- fDefaultToken= defaultToken;
+
+ fDetector = detector;
+ fDefaultToken = defaultToken;
if (matcher != null)
addWordMatcher(matcher);
}
-
/**
* Adds the given matcher.
*
- * @param matcher the matcher
+ * @param matcher
+ * the matcher
*/
public void addWordMatcher(WordMatcher matcher) {
fMatchers.add(matcher);
}
-
+
/**
- * Sets a column constraint for this rule. If set, the rule's token
- * will only be returned if the pattern is detected starting at the
- * specified column. If the column is smaller then 0, the column
- * constraint is considered removed.
- *
- * @param column the column in which the pattern starts
+ * Sets a column constraint for this rule. If set, the rule's token will
+ * only be returned if the pattern is detected starting at the specified
+ * column. If the column is smaller then 0, the column constraint is
+ * considered removed.
+ *
+ * @param column
+ * the column in which the pattern starts
*/
public void setColumnConstraint(int column) {
if (column < 0)
- column= UNDEFINED;
- fColumn= column;
+ column = UNDEFINED;
+ fColumn = column;
}
-
+
/*
* @see IRule#evaluate(ICharacterScanner)
*/
public IToken evaluate(ICharacterScanner scanner) {
- int c= scanner.read();
+ int c = scanner.read();
if (fDetector.isWordStart((char) c)) {
if (fColumn == UNDEFINED || (fColumn == scanner.getColumn() - 1)) {
-
+
fBuffer.clear();
do {
fBuffer.append((char) c);
- c= scanner.read();
- } while (c != ICharacterScanner.EOF && fDetector.isWordPart((char) c));
+ c = scanner.read();
+ } while (c != ICharacterScanner.EOF
+ && fDetector.isWordPart((char) c));
scanner.unread();
-
- for (int i= 0, n= fMatchers.size(); i < n; i++) {
- IToken token= ((WordMatcher) fMatchers.get(i)).evaluate(scanner, fBuffer);
+
+ for (int i = 0, n = fMatchers.size(); i < n; i++) {
+ IToken token = ((WordMatcher) fMatchers.get(i)).evaluate(
+ scanner, fBuffer);
if (!token.isUndefined())
return token;
}
-
+
if (fDefaultToken.isUndefined())
unreadBuffer(scanner);
-
+
return fDefaultToken;
}
}
-
+
scanner.unread();
return Token.UNDEFINED;
}
-
+
/**
* Returns the characters in the buffer to the scanner.
- *
- * @param scanner the scanner to be used
+ *
+ * @param scanner
+ * the scanner to be used
*/
private void unreadBuffer(ICharacterScanner scanner) {
- for (int i= fBuffer.length() - 1; i >= 0; i--)
+ for (int i = fBuffer.length() - 1; i >= 0; i--)
scanner.unread();
}
}