mirror of https://github.com/apache/lucene.git
detabify and removed redundant (char) cast
git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@150127 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
parent
cad41dbce6
commit
812d3329d7
|
@ -62,7 +62,7 @@ public abstract class CharTokenizer extends Tokenizer {
|
|||
super(input);
|
||||
}
|
||||
|
||||
private int offset = 0, bufferIndex=0, dataLen=0;
|
||||
private int offset = 0, bufferIndex = 0, dataLen = 0;
|
||||
private static final int MAX_WORD_LEN = 255;
|
||||
private static final int IO_BUFFER_SIZE = 1024;
|
||||
private final char[] buffer = new char[MAX_WORD_LEN];
|
||||
|
@ -77,7 +77,9 @@ public abstract class CharTokenizer extends Tokenizer {
|
|||
/** Called on each token character to normalize it before it is added to the
|
||||
* token. The default implementation does nothing. Subclasses may use this
|
||||
* to, e.g., lowercase tokens. */
|
||||
protected char normalize(char c) { return c; }
|
||||
protected char normalize(char c) {
|
||||
return c;
|
||||
}
|
||||
|
||||
/** Returns the next token in the stream, or null at EOS. */
|
||||
public final Token next() throws java.io.IOException {
|
||||
|
@ -90,31 +92,31 @@ public abstract class CharTokenizer extends Tokenizer {
|
|||
if (bufferIndex >= dataLen) {
|
||||
dataLen = input.read(ioBuffer);
|
||||
bufferIndex = 0;
|
||||
};
|
||||
if (dataLen == -1) {
|
||||
if (length > 0)
|
||||
break;
|
||||
else
|
||||
return null;
|
||||
}
|
||||
else
|
||||
c = (char) ioBuffer[bufferIndex++];
|
||||
|
||||
if (isTokenChar(c)) { // if it's a token char
|
||||
;
|
||||
if (dataLen == -1) {
|
||||
if (length > 0)
|
||||
break;
|
||||
else
|
||||
return null;
|
||||
} else
|
||||
c = ioBuffer[bufferIndex++];
|
||||
|
||||
if (length == 0) // start of token
|
||||
start = offset-1;
|
||||
if (isTokenChar(c)) { // if it's a token char
|
||||
|
||||
buffer[length++] = normalize(c); // buffer it, normalized
|
||||
if (length == 0) // start of token
|
||||
start = offset - 1;
|
||||
|
||||
if (length == MAX_WORD_LEN) // buffer overflow!
|
||||
break;
|
||||
buffer[length++] = normalize(c); // buffer it, normalized
|
||||
|
||||
} else if (length > 0) // at non-Letter w/ chars
|
||||
break; // return 'em
|
||||
if (length == MAX_WORD_LEN) // buffer overflow!
|
||||
break;
|
||||
|
||||
} else if (length > 0) // at non-Letter w/ chars
|
||||
break; // return 'em
|
||||
|
||||
}
|
||||
|
||||
return new Token(new String(buffer, 0, length), start, start+length);
|
||||
return new Token(new String(buffer, 0, length), start, start + length);
|
||||
}
|
||||
}
|
||||
|
|
Loading…
Reference in New Issue