mirror of https://github.com/apache/lucene.git
LUCENE-10003: No C style array declaration (#206)
Most cases of C-style array declarations have been switched. The Google Java Format, that which we adhere to, disallows C-style array declarations: https://google.github.io/styleguide/javaguide.html#s4.8.3-arrays Some cases (esp. Snowball) can't be updated.
This commit is contained in:
David Smiley
GitHub
parent
88588e3dea
commit
8ac2673791
|
|
@ -14,7 +14,7 @@
|
|||
private static final int ZZ_PUSHBACK_2BIG = 2;
|
||||
|
||||
/* error messages for the codes above */
|
||||
private static final String ZZ_ERROR_MSG[] = {
|
||||
private static final String[] ZZ_ERROR_MSG = {
|
||||
"Unknown internal scanner error",
|
||||
"Error: could not match input",
|
||||
"Error: pushback value was too large"
|
||||
|
|
@ -32,7 +32,7 @@
|
|||
|
||||
/** this buffer contains the current text to be matched and is
|
||||
the source of the yytext() string */
|
||||
private char zzBuffer[] = new char[ZZ_BUFFERSIZE];
|
||||
private char[] zzBuffer = new char[ZZ_BUFFERSIZE];
|
||||
|
||||
/** the textposition at the last accepting state */
|
||||
private int zzMarkedPos;
|
||||
|
|
@ -110,7 +110,7 @@
|
|||
/* is the buffer big enough? */
|
||||
if (zzCurrentPos >= zzBuffer.length - zzFinalHighSurrogate) {
|
||||
/* if not: blow it up */
|
||||
char newBuffer[] = new char[zzBuffer.length*2];
|
||||
char[] newBuffer = new char[zzBuffer.length*2];
|
||||
System.arraycopy(zzBuffer, 0, newBuffer, 0, zzBuffer.length);
|
||||
zzBuffer = newBuffer;
|
||||
zzEndRead += zzFinalHighSurrogate;
|
||||
|
|
|
|||
|
|
@ -14,7 +14,7 @@
|
|||
private static final int ZZ_PUSHBACK_2BIG = 2;
|
||||
|
||||
/* error messages for the codes above */
|
||||
private static final String ZZ_ERROR_MSG[] = {
|
||||
private static final String[] ZZ_ERROR_MSG = {
|
||||
"Unknown internal scanner error",
|
||||
"Error: could not match input",
|
||||
"Error: pushback value was too large"
|
||||
|
|
@ -32,7 +32,7 @@
|
|||
|
||||
/** this buffer contains the current text to be matched and is
|
||||
the source of the yytext() string */
|
||||
private char zzBuffer[] = new char[ZZ_BUFFERSIZE];
|
||||
private char[] zzBuffer = new char[ZZ_BUFFERSIZE];
|
||||
|
||||
/** the textposition at the last accepting state */
|
||||
private int zzMarkedPos;
|
||||
|
|
|
|||
|
|
@ -740,7 +740,7 @@ index 1b27b96..94f2d4b 100644
|
|||
- public String getCurrent()
|
||||
- {
|
||||
- return current.toString();
|
||||
+ public void setCurrent(char text[], int length) {
|
||||
+ public void setCurrent(char[] text, int length) {
|
||||
+ current = text;
|
||||
+ cursor = 0;
|
||||
+ limit = length;
|
||||
|
|
@ -778,7 +778,7 @@ index 1b27b96..94f2d4b 100644
|
|||
|
||||
// current string
|
||||
- protected StringBuilder current;
|
||||
+ private char current[];
|
||||
+ private char[] current;
|
||||
|
||||
protected int cursor;
|
||||
protected int limit;
|
||||
|
|
@ -926,7 +926,7 @@ index 1b27b96..94f2d4b 100644
|
|||
+ final int newLength = limit + adjustment;
|
||||
+ //resize if necessary
|
||||
+ if (newLength > current.length) {
|
||||
+ char newBuffer[] = new char[oversize(newLength)];
|
||||
+ char[] newBuffer = new char[oversize(newLength)];
|
||||
+ System.arraycopy(current, 0, newBuffer, 0, limit);
|
||||
+ current = newBuffer;
|
||||
+ }
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
{
|
||||
"gradle/generation/jflex/skeleton.default.txt": "ca1043249c0eefdf2623a785e2b91f5608bfc3f1",
|
||||
"lucene/analysis/common/src/java/org/apache/lucene/analysis/classic/ClassicTokenizerImpl.java": "21c2cf7ba0a0cdeb43ebe624101e259c9348f6b0",
|
||||
"gradle/generation/jflex/skeleton.default.txt": "883b32da9ff37f859964af9c2c665361c621b2c2",
|
||||
"lucene/analysis/common/src/java/org/apache/lucene/analysis/classic/ClassicTokenizerImpl.java": "50f43f43859e63a5470f3c8249cad3ea9c131dc0",
|
||||
"lucene/analysis/common/src/java/org/apache/lucene/analysis/classic/ClassicTokenizerImpl.jflex": "958b028ef3f0aec36488fb2bb033cdec5858035f"
|
||||
}
|
||||
|
|
@ -1,6 +1,6 @@
|
|||
{
|
||||
"gradle/generation/jflex/skeleton.default.txt": "ca1043249c0eefdf2623a785e2b91f5608bfc3f1",
|
||||
"gradle/generation/jflex/skeleton.default.txt": "883b32da9ff37f859964af9c2c665361c621b2c2",
|
||||
"lucene/analysis/common/src/java/org/apache/lucene/analysis/charfilter/HTMLCharacterEntities.jflex": "d1aa75b9b37646efe31731394f84a063eb7eed9d",
|
||||
"lucene/analysis/common/src/java/org/apache/lucene/analysis/charfilter/HTMLStripCharFilter.java": "78f5208455706d60a9ce4b63624ed04b0fd32573",
|
||||
"lucene/analysis/common/src/java/org/apache/lucene/analysis/charfilter/HTMLStripCharFilter.jflex": "71760e2f7abe078109545a0c68aeac9125508d7c"
|
||||
"lucene/analysis/common/src/java/org/apache/lucene/analysis/charfilter/HTMLStripCharFilter.java": "8470ed427633f58905a8269c78927d7794451e55",
|
||||
"lucene/analysis/common/src/java/org/apache/lucene/analysis/charfilter/HTMLStripCharFilter.jflex": "44a271b04ad1564284982be166553584d38b5ea0"
|
||||
}
|
||||
|
|
@ -1,7 +1,7 @@
|
|||
{
|
||||
"gradle/generation/jflex/skeleton.disable.buffer.expansion.txt": "68263ff0a014904c6e89b040d868d8f399408908",
|
||||
"gradle/generation/jflex/skeleton.disable.buffer.expansion.txt": "1424f4df33c977bb150d7377c3bd61f819113091",
|
||||
"lucene/analysis/common/src/java/org/apache/lucene/analysis/email/ASCIITLD.jflex": "bb3878ea10f85f124a0a9e4ea614d3400d664dae",
|
||||
"lucene/analysis/common/src/java/org/apache/lucene/analysis/email/UAX29URLEmailTokenizerImpl.java": "2bf3efe1a1bc473eb3fe2456f50521ecd7d9b03b",
|
||||
"lucene/analysis/common/src/java/org/apache/lucene/analysis/email/UAX29URLEmailTokenizerImpl.java": "b88c349d24028f557f2c014437f3f60c968ad9de",
|
||||
"lucene/analysis/common/src/java/org/apache/lucene/analysis/email/UAX29URLEmailTokenizerImpl.jflex": "56a751d27e481fb55388f91ebf34f5a0cb8cb1b2",
|
||||
"lucene/core/src/data/jflex/UnicodeEmojiProperties.jflex": "7491dd535debc6e9e9ce367c4d3a7217e466dcae"
|
||||
}
|
||||
|
|
@ -1,5 +1,5 @@
|
|||
{
|
||||
"gradle/generation/jflex/skeleton.default.txt": "ca1043249c0eefdf2623a785e2b91f5608bfc3f1",
|
||||
"lucene/analysis/common/src/java/org/apache/lucene/analysis/wikipedia/WikipediaTokenizerImpl.java": "10b391af6953d2f7bcca86da835a1037705509ec",
|
||||
"gradle/generation/jflex/skeleton.default.txt": "883b32da9ff37f859964af9c2c665361c621b2c2",
|
||||
"lucene/analysis/common/src/java/org/apache/lucene/analysis/wikipedia/WikipediaTokenizerImpl.java": "743fb4cc4b88d36242b3d227320c85e89a6868a8",
|
||||
"lucene/analysis/common/src/java/org/apache/lucene/analysis/wikipedia/WikipediaTokenizerImpl.jflex": "a23a4b7cbcdba1fc864c0b85bc2784c8893a0f9f"
|
||||
}
|
||||
|
|
@ -1,6 +1,6 @@
|
|||
{
|
||||
"lucene/analysis/common/src/java/org/tartarus/snowball/Among.java": "5371973cc30637273366f042e1cff920e0dd14f6",
|
||||
"lucene/analysis/common/src/java/org/tartarus/snowball/SnowballProgram.java": "4e1caa344c7ac864c467ff0e615c1343e911b06b",
|
||||
"lucene/analysis/common/src/java/org/tartarus/snowball/SnowballProgram.java": "93d77707ddc746aad94c1308d2f6f4321a1aa003",
|
||||
"lucene/analysis/common/src/java/org/tartarus/snowball/SnowballStemmer.java": "85bfc728393d7804f86f0def0467a12fd4b82fd3",
|
||||
"lucene/analysis/common/src/java/org/tartarus/snowball/ext/ArabicStemmer.java": "2d43c4606bbaf96d9ac5f8be8ccf28e32164b9f0",
|
||||
"lucene/analysis/common/src/java/org/tartarus/snowball/ext/ArmenianStemmer.java": "0be0949fe1f021ef41e3f9a27280b295ab1e998c",
|
||||
|
|
|
|||
|
|
@ -63,7 +63,7 @@ public class ArabicNormalizer {
|
|||
* @param len length of input buffer
|
||||
* @return length of input buffer after normalization
|
||||
*/
|
||||
public int normalize(char s[], int len) {
|
||||
public int normalize(char[] s, int len) {
|
||||
|
||||
for (int i = 0; i < len; i++) {
|
||||
switch (s[i]) {
|
||||
|
|
|
|||
|
|
@ -43,7 +43,7 @@ public class ArabicStemmer {
|
|||
public static final char WAW = '\u0648';
|
||||
public static final char YEH = '\u064A';
|
||||
|
||||
public static final char prefixes[][] = {
|
||||
public static final char[][] prefixes = {
|
||||
("" + ALEF + LAM).toCharArray(),
|
||||
("" + WAW + ALEF + LAM).toCharArray(),
|
||||
("" + BEH + ALEF + LAM).toCharArray(),
|
||||
|
|
@ -53,7 +53,7 @@ public class ArabicStemmer {
|
|||
("" + WAW).toCharArray(),
|
||||
};
|
||||
|
||||
public static final char suffixes[][] = {
|
||||
public static final char[][] suffixes = {
|
||||
("" + HEH + ALEF).toCharArray(),
|
||||
("" + ALEF + NOON).toCharArray(),
|
||||
("" + ALEF + TEH).toCharArray(),
|
||||
|
|
@ -73,7 +73,7 @@ public class ArabicStemmer {
|
|||
* @param len length of input buffer
|
||||
* @return length of input buffer after normalization
|
||||
*/
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
len = stemPrefix(s, len);
|
||||
len = stemSuffix(s, len);
|
||||
|
||||
|
|
@ -87,7 +87,7 @@ public class ArabicStemmer {
|
|||
* @param len length of input buffer
|
||||
* @return new length of input buffer after stemming.
|
||||
*/
|
||||
public int stemPrefix(char s[], int len) {
|
||||
public int stemPrefix(char[] s, int len) {
|
||||
for (int i = 0; i < prefixes.length; i++)
|
||||
if (startsWithCheckLength(s, len, prefixes[i])) return deleteN(s, 0, len, prefixes[i].length);
|
||||
return len;
|
||||
|
|
@ -100,7 +100,7 @@ public class ArabicStemmer {
|
|||
* @param len length of input buffer
|
||||
* @return new length of input buffer after stemming
|
||||
*/
|
||||
public int stemSuffix(char s[], int len) {
|
||||
public int stemSuffix(char[] s, int len) {
|
||||
for (int i = 0; i < suffixes.length; i++)
|
||||
if (endsWithCheckLength(s, len, suffixes[i]))
|
||||
len = deleteN(s, len - suffixes[i].length, len, suffixes[i].length);
|
||||
|
|
@ -115,7 +115,7 @@ public class ArabicStemmer {
|
|||
* @param prefix prefix to check
|
||||
* @return true if the prefix matches and can be stemmed
|
||||
*/
|
||||
boolean startsWithCheckLength(char s[], int len, char prefix[]) {
|
||||
boolean startsWithCheckLength(char[] s, int len, char[] prefix) {
|
||||
if (prefix.length == 1 && len < 4) { // wa- prefix requires at least 3 characters
|
||||
return false;
|
||||
} else if (len < prefix.length + 2) { // other prefixes require only 2.
|
||||
|
|
@ -139,7 +139,7 @@ public class ArabicStemmer {
|
|||
* @param suffix suffix to check
|
||||
* @return true if the suffix matches and can be stemmed
|
||||
*/
|
||||
boolean endsWithCheckLength(char s[], int len, char suffix[]) {
|
||||
boolean endsWithCheckLength(char[] s, int len, char[] suffix) {
|
||||
if (len < suffix.length + 2) { // all suffixes require at least 2 characters after stemming
|
||||
return false;
|
||||
} else {
|
||||
|
|
|
|||
|
|
@ -33,7 +33,7 @@ public class BulgarianStemmer {
|
|||
* @param len length of input buffer
|
||||
* @return length of input buffer after normalization
|
||||
*/
|
||||
public int stem(final char s[], int len) {
|
||||
public int stem(final char[] s, int len) {
|
||||
if (len < 4) // do not stem
|
||||
return len;
|
||||
|
||||
|
|
@ -76,7 +76,7 @@ public class BulgarianStemmer {
|
|||
* @param len length of input buffer
|
||||
* @return new stemmed length
|
||||
*/
|
||||
private int removeArticle(final char s[], final int len) {
|
||||
private int removeArticle(final char[] s, final int len) {
|
||||
if (len > 6 && endsWith(s, len, "ият")) return len - 3;
|
||||
|
||||
if (len > 5) {
|
||||
|
|
@ -96,7 +96,7 @@ public class BulgarianStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int removePlural(final char s[], final int len) {
|
||||
private int removePlural(final char[] s, final int len) {
|
||||
if (len > 6) {
|
||||
if (endsWith(s, len, "овци")) return len - 3; // replace with о
|
||||
if (endsWith(s, len, "ове")) return len - 3;
|
||||
|
|
|
|||
|
|
@ -33,7 +33,7 @@ public class BengaliNormalizer {
|
|||
* @param len length of input buffer
|
||||
* @return length of input buffer after normalization
|
||||
*/
|
||||
public int normalize(char s[], int len) {
|
||||
public int normalize(char[] s, int len) {
|
||||
|
||||
for (int i = 0; i < len; i++) {
|
||||
switch (s[i]) {
|
||||
|
|
|
|||
|
|
@ -28,7 +28,7 @@ import static org.apache.lucene.analysis.util.StemmerUtil.endsWith;
|
|||
* <i>http://members.unine.ch/jacques.savoy/clef/BengaliStemmerLight.java.txt</i>
|
||||
*/
|
||||
public class BengaliStemmer {
|
||||
public int stem(char buffer[], int len) {
|
||||
public int stem(char[] buffer, int len) {
|
||||
|
||||
// 8
|
||||
if (len > 9
|
||||
|
|
|
|||
|
|
@ -28,8 +28,8 @@ import org.apache.lucene.util.ArrayUtil;
|
|||
*/
|
||||
public abstract class BaseCharFilter extends CharFilter {
|
||||
|
||||
private int offsets[];
|
||||
private int diffs[];
|
||||
private int[] offsets;
|
||||
private int[] diffs;
|
||||
private int size = 0;
|
||||
|
||||
public BaseCharFilter(Reader in) {
|
||||
|
|
|
|||
|
|
@ -29678,7 +29678,7 @@ public final class HTMLStripCharFilter extends BaseCharFilter {
|
|||
private static final int ZZ_PUSHBACK_2BIG = 2;
|
||||
|
||||
/* error messages for the codes above */
|
||||
private static final String ZZ_ERROR_MSG[] = {
|
||||
private static final String[] ZZ_ERROR_MSG = {
|
||||
"Unknown internal scanner error",
|
||||
"Error: could not match input",
|
||||
"Error: pushback value was too large"
|
||||
|
|
@ -29806,7 +29806,7 @@ public final class HTMLStripCharFilter extends BaseCharFilter {
|
|||
|
||||
/** this buffer contains the current text to be matched and is
|
||||
the source of the yytext() string */
|
||||
private char zzBuffer[] = new char[ZZ_BUFFERSIZE];
|
||||
private char[] zzBuffer = new char[ZZ_BUFFERSIZE];
|
||||
|
||||
/** the textposition at the last accepting state */
|
||||
private int zzMarkedPos;
|
||||
|
|
@ -30017,7 +30017,7 @@ public final class HTMLStripCharFilter extends BaseCharFilter {
|
|||
}
|
||||
|
||||
@Override
|
||||
public int read(char cbuf[], int off, int len) throws IOException {
|
||||
public int read(char[] cbuf, int off, int len) throws IOException {
|
||||
int i = 0;
|
||||
for ( ; i < len ; ++i) {
|
||||
int ch = read();
|
||||
|
|
@ -30131,7 +30131,7 @@ public final class HTMLStripCharFilter extends BaseCharFilter {
|
|||
/* is the buffer big enough? */
|
||||
if (zzCurrentPos >= zzBuffer.length - zzFinalHighSurrogate) {
|
||||
/* if not: blow it up */
|
||||
char newBuffer[] = new char[zzBuffer.length*2];
|
||||
char[] newBuffer = new char[zzBuffer.length*2];
|
||||
System.arraycopy(zzBuffer, 0, newBuffer, 0, zzBuffer.length);
|
||||
zzBuffer = newBuffer;
|
||||
zzEndRead += zzFinalHighSurrogate;
|
||||
|
|
|
|||
|
|
@ -212,7 +212,7 @@ InlineElment = ( [aAbBiIqQsSuU] |
|
|||
}
|
||||
|
||||
@Override
|
||||
public int read(char cbuf[], int off, int len) throws IOException {
|
||||
public int read(char[] cbuf, int off, int len) throws IOException {
|
||||
int i = 0;
|
||||
for ( ; i < len ; ++i) {
|
||||
int ch = read();
|
||||
|
|
|
|||
|
|
@ -93,9 +93,9 @@ public final class CJKBigramFilter extends TokenFilter {
|
|||
private final PositionLengthAttribute posLengthAtt = addAttribute(PositionLengthAttribute.class);
|
||||
|
||||
// buffers containing codepoint and offsets in parallel
|
||||
int buffer[] = new int[8];
|
||||
int startOffset[] = new int[8];
|
||||
int endOffset[] = new int[8];
|
||||
int[] buffer = new int[8];
|
||||
int[] startOffset = new int[8];
|
||||
int[] endOffset = new int[8];
|
||||
// length of valid buffer
|
||||
int bufferLen;
|
||||
// current buffer index
|
||||
|
|
@ -264,7 +264,7 @@ public final class CJKBigramFilter extends TokenFilter {
|
|||
index -= last;
|
||||
}
|
||||
|
||||
char termBuffer[] = termAtt.buffer();
|
||||
char[] termBuffer = termAtt.buffer();
|
||||
int len = termAtt.length();
|
||||
int start = offsetAtt.startOffset();
|
||||
int end = offsetAtt.endOffset();
|
||||
|
|
@ -300,7 +300,7 @@ public final class CJKBigramFilter extends TokenFilter {
|
|||
*/
|
||||
private void flushBigram() {
|
||||
clearAttributes();
|
||||
char termBuffer[] =
|
||||
char[] termBuffer =
|
||||
termAtt.resizeBuffer(4); // maximum bigram length in code units (2 supplementaries)
|
||||
int len1 = Character.toChars(buffer[index], termBuffer, 0);
|
||||
int len2 = len1 + Character.toChars(buffer[index + 1], termBuffer, len1);
|
||||
|
|
@ -322,7 +322,7 @@ public final class CJKBigramFilter extends TokenFilter {
|
|||
*/
|
||||
private void flushUnigram() {
|
||||
clearAttributes();
|
||||
char termBuffer[] = termAtt.resizeBuffer(2); // maximum unigram length (2 surrogates)
|
||||
char[] termBuffer = termAtt.resizeBuffer(2); // maximum unigram length (2 surrogates)
|
||||
int len = Character.toChars(buffer[index], termBuffer, 0);
|
||||
termAtt.setLength(len);
|
||||
offsetAtt.setOffset(startOffset[index], endOffset[index]);
|
||||
|
|
|
|||
|
|
@ -39,7 +39,7 @@ public class CJKWidthCharFilter extends BaseCharFilter {
|
|||
* as a fallback when they cannot properly combine with a preceding
|
||||
* character into a composed form.
|
||||
*/
|
||||
private static final char KANA_NORM[] =
|
||||
private static final char[] KANA_NORM =
|
||||
new char[] {
|
||||
0x30fb, 0x30f2, 0x30a1, 0x30a3, 0x30a5, 0x30a7, 0x30a9, 0x30e3, 0x30e5,
|
||||
0x30e7, 0x30c3, 0x30fc, 0x30a2, 0x30a4, 0x30a6, 0x30a8, 0x30aa, 0x30ab,
|
||||
|
|
@ -51,7 +51,7 @@ public class CJKWidthCharFilter extends BaseCharFilter {
|
|||
};
|
||||
|
||||
/* kana combining diffs: 0x30A6-0x30FD */
|
||||
private static final byte KANA_COMBINE_VOICED[] =
|
||||
private static final byte[] KANA_COMBINE_VOICED =
|
||||
new byte[] {
|
||||
78, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1,
|
||||
0, 1, 0, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1,
|
||||
|
|
@ -59,7 +59,7 @@ public class CJKWidthCharFilter extends BaseCharFilter {
|
|||
0, 8, 8, 8, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1
|
||||
};
|
||||
|
||||
private static final byte KANA_COMBINE_SEMI_VOICED[] =
|
||||
private static final byte[] KANA_COMBINE_SEMI_VOICED =
|
||||
new byte[] {
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 2, 0, 0, 2,
|
||||
|
|
|
|||
|
|
@ -42,7 +42,7 @@ public final class CJKWidthFilter extends TokenFilter {
|
|||
* as a fallback when they cannot properly combine with a preceding
|
||||
* character into a composed form.
|
||||
*/
|
||||
private static final char KANA_NORM[] =
|
||||
private static final char[] KANA_NORM =
|
||||
new char[] {
|
||||
0x30fb, 0x30f2, 0x30a1, 0x30a3, 0x30a5, 0x30a7, 0x30a9, 0x30e3, 0x30e5,
|
||||
0x30e7, 0x30c3, 0x30fc, 0x30a2, 0x30a4, 0x30a6, 0x30a8, 0x30aa, 0x30ab,
|
||||
|
|
@ -60,7 +60,7 @@ public final class CJKWidthFilter extends TokenFilter {
|
|||
@Override
|
||||
public boolean incrementToken() throws IOException {
|
||||
if (input.incrementToken()) {
|
||||
char text[] = termAtt.buffer();
|
||||
char[] text = termAtt.buffer();
|
||||
int length = termAtt.length();
|
||||
for (int i = 0; i < length; i++) {
|
||||
final char ch = text[i];
|
||||
|
|
@ -84,14 +84,14 @@ public final class CJKWidthFilter extends TokenFilter {
|
|||
}
|
||||
|
||||
/* kana combining diffs: 0x30A6-0x30FD */
|
||||
private static final byte KANA_COMBINE_VOICED[] =
|
||||
private static final byte[] KANA_COMBINE_VOICED =
|
||||
new byte[] {
|
||||
78, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0,
|
||||
1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8, 8, 8, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1
|
||||
};
|
||||
|
||||
private static final byte KANA_COMBINE_HALF_VOICED[] =
|
||||
private static final byte[] KANA_COMBINE_HALF_VOICED =
|
||||
new byte[] {
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
|
||||
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 2, 0, 0, 2,
|
||||
|
|
@ -100,7 +100,7 @@ public final class CJKWidthFilter extends TokenFilter {
|
|||
};
|
||||
|
||||
/** returns true if we successfully combined the voice mark */
|
||||
private static boolean combine(char text[], int pos, char ch) {
|
||||
private static boolean combine(char[] text, int pos, char ch) {
|
||||
final char prev = text[pos - 1];
|
||||
if (prev >= 0x30A6 && prev <= 0x30FD) {
|
||||
text[pos - 1] +=
|
||||
|
|
|
|||
|
|
@ -69,7 +69,7 @@ public class SoraniNormalizer {
|
|||
* @param len length of input buffer
|
||||
* @return length of input buffer after normalization
|
||||
*/
|
||||
public int normalize(char s[], int len) {
|
||||
public int normalize(char[] s, int len) {
|
||||
for (int i = 0; i < len; i++) {
|
||||
switch (s[i]) {
|
||||
case YEH:
|
||||
|
|
|
|||
|
|
@ -28,7 +28,7 @@ public class SoraniStemmer {
|
|||
* @param len length of input buffer
|
||||
* @return length of input buffer after normalization
|
||||
*/
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
// postposition
|
||||
if (len > 5 && endsWith(s, len, "دا")) {
|
||||
len -= 2;
|
||||
|
|
|
|||
|
|
@ -234,7 +234,7 @@ class ClassicTokenizerImpl {
|
|||
private static final int ZZ_PUSHBACK_2BIG = 2;
|
||||
|
||||
/* error messages for the codes above */
|
||||
private static final String ZZ_ERROR_MSG[] = {
|
||||
private static final String[] ZZ_ERROR_MSG = {
|
||||
"Unknown internal scanner error",
|
||||
"Error: could not match input",
|
||||
"Error: pushback value was too large"
|
||||
|
|
@ -278,7 +278,7 @@ class ClassicTokenizerImpl {
|
|||
/**
|
||||
* this buffer contains the current text to be matched and is the source of the yytext() string
|
||||
*/
|
||||
private char zzBuffer[] = new char[ZZ_BUFFERSIZE];
|
||||
private char[] zzBuffer = new char[ZZ_BUFFERSIZE];
|
||||
|
||||
/** the textposition at the last accepting state */
|
||||
private int zzMarkedPos;
|
||||
|
|
@ -396,7 +396,7 @@ class ClassicTokenizerImpl {
|
|||
/* is the buffer big enough? */
|
||||
if (zzCurrentPos >= zzBuffer.length - zzFinalHighSurrogate) {
|
||||
/* if not: blow it up */
|
||||
char newBuffer[] = new char[zzBuffer.length * 2];
|
||||
char[] newBuffer = new char[zzBuffer.length * 2];
|
||||
System.arraycopy(zzBuffer, 0, newBuffer, 0, zzBuffer.length);
|
||||
zzBuffer = newBuffer;
|
||||
zzEndRead += zzFinalHighSurrogate;
|
||||
|
|
|
|||
|
|
@ -155,7 +155,7 @@ public final class CommonGramsFilter extends TokenFilter {
|
|||
clearAttributes();
|
||||
|
||||
int length = buffer.length();
|
||||
char termText[] = termAttribute.buffer();
|
||||
char[] termText = termAttribute.buffer();
|
||||
if (length > termText.length) {
|
||||
termText = termAttribute.resizeBuffer(length);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -317,7 +317,7 @@ public class PatternParser extends DefaultHandler {
|
|||
/** @see org.xml.sax.ContentHandler#characters(char[], int, int) */
|
||||
@SuppressWarnings({"unchecked", "rawtypes"})
|
||||
@Override
|
||||
public void characters(char ch[], int start, int length) {
|
||||
public void characters(char[] ch, int start, int length) {
|
||||
StringBuilder chars = new StringBuilder(length);
|
||||
chars.append(ch, start, length);
|
||||
String word = readToken(chars);
|
||||
|
|
|
|||
|
|
@ -122,7 +122,7 @@ public class TernaryTree implements Cloneable {
|
|||
if (freenode + len > eq.length) {
|
||||
redimNodeArrays(eq.length + BLOCK_SIZE);
|
||||
}
|
||||
char strkey[] = new char[len--];
|
||||
char[] strkey = new char[len--];
|
||||
key.getChars(0, len, strkey, 0);
|
||||
strkey[len] = 0;
|
||||
root = insert(root, strkey, 0, val);
|
||||
|
|
@ -255,7 +255,7 @@ public class TernaryTree implements Cloneable {
|
|||
|
||||
public int find(String key) {
|
||||
int len = key.length();
|
||||
char strkey[] = new char[len + 1];
|
||||
char[] strkey = new char[len + 1];
|
||||
key.getChars(0, len, strkey, 0);
|
||||
strkey[len] = 0;
|
||||
|
||||
|
|
|
|||
|
|
@ -37,7 +37,7 @@ public final class DecimalDigitFilter extends TokenFilter {
|
|||
@Override
|
||||
public boolean incrementToken() throws IOException {
|
||||
if (input.incrementToken()) {
|
||||
char buffer[] = termAtt.buffer();
|
||||
char[] buffer = termAtt.buffer();
|
||||
int length = termAtt.length();
|
||||
|
||||
for (int i = 0; i < length; i++) {
|
||||
|
|
|
|||
|
|
@ -34,7 +34,7 @@ public class CzechStemmer {
|
|||
* @return length of input buffer after normalization
|
||||
* <p><b>NOTE</b>: Input is expected to be in lowercase, but with diacritical marks
|
||||
*/
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
len = removeCase(s, len);
|
||||
len = removePossessives(s, len);
|
||||
if (len > 0) {
|
||||
|
|
@ -43,7 +43,7 @@ public class CzechStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int removeCase(char s[], int len) {
|
||||
private int removeCase(char[] s, int len) {
|
||||
if (len > 7 && endsWith(s, len, "atech")) return len - 5;
|
||||
|
||||
if (len > 6
|
||||
|
|
@ -112,14 +112,14 @@ public class CzechStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int removePossessives(char s[], int len) {
|
||||
private int removePossessives(char[] s, int len) {
|
||||
if (len > 5 && (endsWith(s, len, "ov") || endsWith(s, len, "in") || endsWith(s, len, "ův")))
|
||||
return len - 2;
|
||||
|
||||
return len;
|
||||
}
|
||||
|
||||
private int normalize(char s[], int len) {
|
||||
private int normalize(char[] s, int len) {
|
||||
if (endsWith(s, len, "čt")) { // čt -> ck
|
||||
s[len - 2] = 'c';
|
||||
s[len - 1] = 'k';
|
||||
|
|
|
|||
|
|
@ -59,7 +59,7 @@ package org.apache.lucene.analysis.de;
|
|||
*/
|
||||
public class GermanLightStemmer {
|
||||
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
for (int i = 0; i < len; i++)
|
||||
switch (s[i]) {
|
||||
case 'ä':
|
||||
|
|
@ -110,7 +110,7 @@ public class GermanLightStemmer {
|
|||
}
|
||||
}
|
||||
|
||||
private int step1(char s[], int len) {
|
||||
private int step1(char[] s, int len) {
|
||||
if (len > 5 && s[len - 3] == 'e' && s[len - 2] == 'r' && s[len - 1] == 'n') return len - 3;
|
||||
|
||||
if (len > 4 && s[len - 2] == 'e')
|
||||
|
|
@ -129,7 +129,7 @@ public class GermanLightStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int step2(char s[], int len) {
|
||||
private int step2(char[] s, int len) {
|
||||
if (len > 5 && s[len - 3] == 'e' && s[len - 2] == 's' && s[len - 1] == 't') return len - 3;
|
||||
|
||||
if (len > 4 && s[len - 2] == 'e' && (s[len - 1] == 'r' || s[len - 1] == 'n')) return len - 2;
|
||||
|
|
|
|||
|
|
@ -59,7 +59,7 @@ package org.apache.lucene.analysis.de;
|
|||
*/
|
||||
public class GermanMinimalStemmer {
|
||||
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
if (len < 5) return len;
|
||||
|
||||
for (int i = 0; i < len; i++)
|
||||
|
|
|
|||
|
|
@ -53,7 +53,7 @@ public final class GermanNormalizationFilter extends TokenFilter {
|
|||
public boolean incrementToken() throws IOException {
|
||||
if (input.incrementToken()) {
|
||||
int state = N;
|
||||
char buffer[] = termAtt.buffer();
|
||||
char[] buffer = termAtt.buffer();
|
||||
int length = termAtt.length();
|
||||
for (int i = 0; i < length; i++) {
|
||||
final char c = buffer[i];
|
||||
|
|
|
|||
|
|
@ -39,7 +39,7 @@ public class GreekStemmer {
|
|||
* @param len The length of the char[] array.
|
||||
* @return The new length of the stemmed word.
|
||||
*/
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
if (len < 4) // too short
|
||||
return len;
|
||||
|
||||
|
|
@ -72,7 +72,7 @@ public class GreekStemmer {
|
|||
return rule22(s, len);
|
||||
}
|
||||
|
||||
private int rule0(char s[], int len) {
|
||||
private int rule0(char[] s, int len) {
|
||||
if (len > 9 && (endsWith(s, len, "καθεστωτοσ") || endsWith(s, len, "καθεστωτων")))
|
||||
return len - 4;
|
||||
|
||||
|
|
@ -131,7 +131,7 @@ public class GreekStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int rule1(char s[], int len) {
|
||||
private int rule1(char[] s, int len) {
|
||||
if (len > 4 && (endsWith(s, len, "αδεσ") || endsWith(s, len, "αδων"))) {
|
||||
len -= 4;
|
||||
if (!(endsWith(s, len, "οκ")
|
||||
|
|
@ -148,7 +148,7 @@ public class GreekStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int rule2(char s[], int len) {
|
||||
private int rule2(char[] s, int len) {
|
||||
if (len > 4 && (endsWith(s, len, "εδεσ") || endsWith(s, len, "εδων"))) {
|
||||
len -= 4;
|
||||
if (endsWith(s, len, "οπ")
|
||||
|
|
@ -163,7 +163,7 @@ public class GreekStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int rule3(char s[], int len) {
|
||||
private int rule3(char[] s, int len) {
|
||||
if (len > 5 && (endsWith(s, len, "ουδεσ") || endsWith(s, len, "ουδων"))) {
|
||||
len -= 5;
|
||||
if (endsWith(s, len, "αρκ")
|
||||
|
|
@ -188,7 +188,7 @@ public class GreekStemmer {
|
|||
private static final CharArraySet exc4 =
|
||||
new CharArraySet(Arrays.asList("θ", "δ", "ελ", "γαλ", "ν", "π", "ιδ", "παρ"), false);
|
||||
|
||||
private int rule4(char s[], int len) {
|
||||
private int rule4(char[] s, int len) {
|
||||
if (len > 3 && (endsWith(s, len, "εωσ") || endsWith(s, len, "εων"))) {
|
||||
len -= 3;
|
||||
if (exc4.contains(s, 0, len)) len++; // add back -ε
|
||||
|
|
@ -196,7 +196,7 @@ public class GreekStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int rule5(char s[], int len) {
|
||||
private int rule5(char[] s, int len) {
|
||||
if (len > 2 && endsWith(s, len, "ια")) {
|
||||
len -= 2;
|
||||
if (endsWithVowel(s, len)) len++; // add back -ι
|
||||
|
|
@ -216,7 +216,7 @@ public class GreekStemmer {
|
|||
"συναδ", "τσαμ", "υποδ", "φιλον", "φυλοδ", "χασ"),
|
||||
false);
|
||||
|
||||
private int rule6(char s[], int len) {
|
||||
private int rule6(char[] s, int len) {
|
||||
boolean removed = false;
|
||||
if (len > 3 && (endsWith(s, len, "ικα") || endsWith(s, len, "ικο"))) {
|
||||
len -= 3;
|
||||
|
|
@ -239,7 +239,7 @@ public class GreekStemmer {
|
|||
"χ"),
|
||||
false);
|
||||
|
||||
private int rule7(char s[], int len) {
|
||||
private int rule7(char[] s, int len) {
|
||||
if (len == 5 && endsWith(s, len, "αγαμε")) return len - 1;
|
||||
|
||||
if (len > 7 && endsWith(s, len, "ηθηκαμε")) len -= 7;
|
||||
|
|
@ -359,7 +359,7 @@ public class GreekStemmer {
|
|||
"ψηλοταβ"),
|
||||
false);
|
||||
|
||||
private int rule8(char s[], int len) {
|
||||
private int rule8(char[] s, int len) {
|
||||
boolean removed = false;
|
||||
|
||||
if (len > 8 && endsWith(s, len, "ιουντανε")) {
|
||||
|
|
@ -410,7 +410,7 @@ public class GreekStemmer {
|
|||
"θαρρ", "θ"),
|
||||
false);
|
||||
|
||||
private int rule9(char s[], int len) {
|
||||
private int rule9(char[] s, int len) {
|
||||
if (len > 5 && endsWith(s, len, "ησετε")) len -= 5;
|
||||
|
||||
if (len > 3 && endsWith(s, len, "ετε")) {
|
||||
|
|
@ -455,7 +455,7 @@ public class GreekStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int rule10(char s[], int len) {
|
||||
private int rule10(char[] s, int len) {
|
||||
if (len > 5 && (endsWith(s, len, "οντασ") || endsWith(s, len, "ωντασ"))) {
|
||||
len -= 5;
|
||||
if (len == 3 && endsWith(s, len, "αρχ")) {
|
||||
|
|
@ -471,7 +471,7 @@ public class GreekStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int rule11(char s[], int len) {
|
||||
private int rule11(char[] s, int len) {
|
||||
if (len > 6 && endsWith(s, len, "ομαστε")) {
|
||||
len -= 6;
|
||||
if (len == 2 && endsWith(s, len, "ον")) {
|
||||
|
|
@ -498,7 +498,7 @@ public class GreekStemmer {
|
|||
new CharArraySet(
|
||||
Arrays.asList("αλ", "αρ", "εκτελ", "ζ", "μ", "ξ", "παρακαλ", "αρ", "προ", "νισ"), false);
|
||||
|
||||
private int rule12(char s[], int len) {
|
||||
private int rule12(char[] s, int len) {
|
||||
if (len > 5 && endsWith(s, len, "ιεστε")) {
|
||||
len -= 5;
|
||||
if (exc12a.contains(s, 0, len)) len += 4; // add back -ιεστ
|
||||
|
|
@ -515,7 +515,7 @@ public class GreekStemmer {
|
|||
private static final CharArraySet exc13 =
|
||||
new CharArraySet(Arrays.asList("διαθ", "θ", "παρακαταθ", "προσθ", "συνθ"), false);
|
||||
|
||||
private int rule13(char s[], int len) {
|
||||
private int rule13(char[] s, int len) {
|
||||
if (len > 6 && endsWith(s, len, "ηθηκεσ")) {
|
||||
len -= 6;
|
||||
} else if (len > 5 && (endsWith(s, len, "ηθηκα") || endsWith(s, len, "ηθηκε"))) {
|
||||
|
|
@ -576,7 +576,7 @@ public class GreekStemmer {
|
|||
"τσα"),
|
||||
false);
|
||||
|
||||
private int rule14(char s[], int len) {
|
||||
private int rule14(char[] s, int len) {
|
||||
boolean removed = false;
|
||||
|
||||
if (len > 5 && endsWith(s, len, "ουσεσ")) {
|
||||
|
|
@ -660,7 +660,7 @@ public class GreekStemmer {
|
|||
private static final CharArraySet exc15b =
|
||||
new CharArraySet(Arrays.asList("ψοφ", "ναυλοχ"), false);
|
||||
|
||||
private int rule15(char s[], int len) {
|
||||
private int rule15(char[] s, int len) {
|
||||
boolean removed = false;
|
||||
if (len > 4 && endsWith(s, len, "αγεσ")) {
|
||||
len -= 4;
|
||||
|
|
@ -696,7 +696,7 @@ public class GreekStemmer {
|
|||
new CharArraySet(
|
||||
Arrays.asList("ν", "χερσον", "δωδεκαν", "ερημον", "μεγαλον", "επταν"), false);
|
||||
|
||||
private int rule16(char s[], int len) {
|
||||
private int rule16(char[] s, int len) {
|
||||
boolean removed = false;
|
||||
if (len > 4 && endsWith(s, len, "ησου")) {
|
||||
len -= 4;
|
||||
|
|
@ -717,7 +717,7 @@ public class GreekStemmer {
|
|||
"ασβ", "σβ", "αχρ", "χρ", "απλ", "αειμν", "δυσχρ", "ευχρ", "κοινοχρ", "παλιμψ"),
|
||||
false);
|
||||
|
||||
private int rule17(char s[], int len) {
|
||||
private int rule17(char[] s, int len) {
|
||||
if (len > 4 && endsWith(s, len, "ηστε")) {
|
||||
len -= 4;
|
||||
if (exc17.contains(s, 0, len)) len += 3; // add back the -ηστ
|
||||
|
|
@ -729,7 +729,7 @@ public class GreekStemmer {
|
|||
private static final CharArraySet exc18 =
|
||||
new CharArraySet(Arrays.asList("ν", "ρ", "σπι", "στραβομουτσ", "κακομουτσ", "εξων"), false);
|
||||
|
||||
private int rule18(char s[], int len) {
|
||||
private int rule18(char[] s, int len) {
|
||||
boolean removed = false;
|
||||
|
||||
if (len > 6 && (endsWith(s, len, "ησουνε") || endsWith(s, len, "ηθουνε"))) {
|
||||
|
|
@ -753,7 +753,7 @@ public class GreekStemmer {
|
|||
new CharArraySet(
|
||||
Arrays.asList("παρασουσ", "φ", "χ", "ωριοπλ", "αζ", "αλλοσουσ", "ασουσ"), false);
|
||||
|
||||
private int rule19(char s[], int len) {
|
||||
private int rule19(char[] s, int len) {
|
||||
boolean removed = false;
|
||||
|
||||
if (len > 6 && (endsWith(s, len, "ησουμε") || endsWith(s, len, "ηθουμε"))) {
|
||||
|
|
@ -773,13 +773,13 @@ public class GreekStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int rule20(char s[], int len) {
|
||||
private int rule20(char[] s, int len) {
|
||||
if (len > 5 && (endsWith(s, len, "ματων") || endsWith(s, len, "ματοσ"))) len -= 3;
|
||||
else if (len > 4 && endsWith(s, len, "ματα")) len -= 2;
|
||||
return len;
|
||||
}
|
||||
|
||||
private int rule21(char s[], int len) {
|
||||
private int rule21(char[] s, int len) {
|
||||
if (len > 9 && endsWith(s, len, "ιοντουσαν")) return len - 9;
|
||||
|
||||
if (len > 8
|
||||
|
|
@ -877,7 +877,7 @@ public class GreekStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int rule22(char s[], int len) {
|
||||
private int rule22(char[] s, int len) {
|
||||
if (endsWith(s, len, "εστερ") || endsWith(s, len, "εστατ")) return len - 5;
|
||||
|
||||
if (endsWith(s, len, "οτερ")
|
||||
|
|
@ -899,7 +899,7 @@ public class GreekStemmer {
|
|||
* @param suffix A {@link String} object to check if the word given ends with these characters.
|
||||
* @return True if the word ends with the suffix given , false otherwise.
|
||||
*/
|
||||
private boolean endsWith(char s[], int len, String suffix) {
|
||||
private boolean endsWith(char[] s, int len, String suffix) {
|
||||
final int suffixLen = suffix.length();
|
||||
if (suffixLen > len) return false;
|
||||
for (int i = suffixLen - 1; i >= 0; i--)
|
||||
|
|
@ -916,7 +916,7 @@ public class GreekStemmer {
|
|||
* @return True if the word contained in the leading portion of char[] array , ends with a vowel ,
|
||||
* false otherwise.
|
||||
*/
|
||||
private boolean endsWithVowel(char s[], int len) {
|
||||
private boolean endsWithVowel(char[] s, int len) {
|
||||
if (len == 0) return false;
|
||||
switch (s[len - 1]) {
|
||||
case 'α':
|
||||
|
|
@ -940,7 +940,7 @@ public class GreekStemmer {
|
|||
* @return True if the word contained in the leading portion of char[] array , ends with a vowel ,
|
||||
* false otherwise.
|
||||
*/
|
||||
private boolean endsWithVowelNoY(char s[], int len) {
|
||||
private boolean endsWithVowelNoY(char[] s, int len) {
|
||||
if (len == 0) return false;
|
||||
switch (s[len - 1]) {
|
||||
case 'α':
|
||||
|
|
|
|||
|
|
@ -38993,7 +38993,7 @@ public final class UAX29URLEmailTokenizerImpl {
|
|||
private static final int ZZ_PUSHBACK_2BIG = 2;
|
||||
|
||||
/* error messages for the codes above */
|
||||
private static final String ZZ_ERROR_MSG[] = {
|
||||
private static final String[] ZZ_ERROR_MSG = {
|
||||
"Unknown internal scanner error",
|
||||
"Error: could not match input",
|
||||
"Error: pushback value was too large"
|
||||
|
|
@ -39168,7 +39168,7 @@ public final class UAX29URLEmailTokenizerImpl {
|
|||
|
||||
/** this buffer contains the current text to be matched and is
|
||||
the source of the yytext() string */
|
||||
private char zzBuffer[] = new char[ZZ_BUFFERSIZE];
|
||||
private char[] zzBuffer = new char[ZZ_BUFFERSIZE];
|
||||
|
||||
/** the textposition at the last accepting state */
|
||||
private int zzMarkedPos;
|
||||
|
|
|
|||
|
|
@ -23,7 +23,7 @@ package org.apache.lucene.analysis.en;
|
|||
*/
|
||||
public class EnglishMinimalStemmer {
|
||||
@SuppressWarnings("fallthrough")
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
if (len < 3 || s[len - 1] != 's') return len;
|
||||
|
||||
switch (s[len - 2]) {
|
||||
|
|
|
|||
|
|
@ -59,7 +59,7 @@ package org.apache.lucene.analysis.es;
|
|||
*/
|
||||
public class SpanishLightStemmer {
|
||||
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
if (len < 5) return len;
|
||||
|
||||
for (int i = 0; i < len; i++)
|
||||
|
|
|
|||
|
|
@ -24,7 +24,7 @@ package org.apache.lucene.analysis.es;
|
|||
*/
|
||||
public class SpanishMinimalStemmer {
|
||||
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
if (len < 4 || s[len - 1] != 's') return len;
|
||||
|
||||
for (int i = 0; i < len; i++)
|
||||
|
|
|
|||
|
|
@ -57,7 +57,7 @@ public class PersianNormalizer {
|
|||
* @param len length of input buffer
|
||||
* @return length of input buffer after normalization
|
||||
*/
|
||||
public int normalize(char s[], int len) {
|
||||
public int normalize(char[] s, int len) {
|
||||
|
||||
for (int i = 0; i < len; i++) {
|
||||
switch (s[i]) {
|
||||
|
|
|
|||
|
|
@ -61,7 +61,7 @@ import static org.apache.lucene.analysis.util.StemmerUtil.*;
|
|||
*/
|
||||
public class FinnishLightStemmer {
|
||||
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
if (len < 4) return len;
|
||||
|
||||
for (int i = 0; i < len; i++)
|
||||
|
|
@ -83,7 +83,7 @@ public class FinnishLightStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int step1(char s[], int len) {
|
||||
private int step1(char[] s, int len) {
|
||||
if (len > 8) {
|
||||
if (endsWith(s, len, "kin")) return step1(s, len - 3);
|
||||
if (endsWith(s, len, "ko")) return step1(s, len - 2);
|
||||
|
|
@ -96,7 +96,7 @@ public class FinnishLightStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int step2(char s[], int len) {
|
||||
private int step2(char[] s, int len) {
|
||||
if (len > 5) {
|
||||
if (endsWith(s, len, "lla") || endsWith(s, len, "tse") || endsWith(s, len, "sti"))
|
||||
return len - 3;
|
||||
|
|
@ -109,7 +109,7 @@ public class FinnishLightStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int step3(char s[], int len) {
|
||||
private int step3(char[] s, int len) {
|
||||
if (len > 8) {
|
||||
if (endsWith(s, len, "nnen")) {
|
||||
s[len - 4] = 's';
|
||||
|
|
@ -173,7 +173,7 @@ public class FinnishLightStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int norm1(char s[], int len) {
|
||||
private int norm1(char[] s, int len) {
|
||||
if (len > 5 && endsWith(s, len, "hde")) {
|
||||
s[len - 3] = 'k';
|
||||
s[len - 2] = 's';
|
||||
|
|
@ -198,7 +198,7 @@ public class FinnishLightStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int norm2(char s[], int len) {
|
||||
private int norm2(char[] s, int len) {
|
||||
if (len > 8) {
|
||||
if (s[len - 1] == 'e' || s[len - 1] == 'o' || s[len - 1] == 'u') len--;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -61,7 +61,7 @@ import static org.apache.lucene.analysis.util.StemmerUtil.*;
|
|||
*/
|
||||
public class FrenchLightStemmer {
|
||||
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
if (len > 5 && s[len - 1] == 'x') {
|
||||
if (s[len - 3] == 'a' && s[len - 2] == 'u' && s[len - 4] != 'e') s[len - 2] = 'l';
|
||||
len--;
|
||||
|
|
@ -209,7 +209,7 @@ public class FrenchLightStemmer {
|
|||
return norm(s, len);
|
||||
}
|
||||
|
||||
private int norm(char s[], int len) {
|
||||
private int norm(char[] s, int len) {
|
||||
if (len > 4) {
|
||||
for (int i = 0; i < len; i++)
|
||||
switch (s[i]) {
|
||||
|
|
|
|||
|
|
@ -58,7 +58,7 @@ package org.apache.lucene.analysis.fr;
|
|||
* general French corpora.</i> Jacques Savoy.
|
||||
*/
|
||||
public class FrenchMinimalStemmer {
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
if (len < 6) return len;
|
||||
|
||||
if (s[len - 1] == 'x') {
|
||||
|
|
|
|||
|
|
@ -31,7 +31,7 @@ public class GalicianMinimalStemmer extends RSLPStemmerBase {
|
|||
private static final Step pluralStep =
|
||||
parse(GalicianMinimalStemmer.class, "galician.rslp").get("Plural");
|
||||
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
return pluralStep.apply(s, len);
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -44,7 +44,7 @@ public class GalicianStemmer extends RSLPStemmerBase {
|
|||
* @param len initial valid length of buffer
|
||||
* @return new valid length, stemmed
|
||||
*/
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
assert s.length >= len + 1 : "this stemmer requires an oversized array of at least 1";
|
||||
|
||||
len = plural.apply(s, len);
|
||||
|
|
|
|||
|
|
@ -43,7 +43,7 @@ public class HindiNormalizer {
|
|||
* @param len length of input buffer
|
||||
* @return length of input buffer after normalization
|
||||
*/
|
||||
public int normalize(char s[], int len) {
|
||||
public int normalize(char[] s, int len) {
|
||||
|
||||
for (int i = 0; i < len; i++) {
|
||||
switch (s[i]) {
|
||||
|
|
|
|||
|
|
@ -26,7 +26,7 @@ import static org.apache.lucene.analysis.util.StemmerUtil.*;
|
|||
* http://computing.open.ac.uk/Sites/EACLSouthAsia/Papers/p6-Ramanathan.pdf
|
||||
*/
|
||||
public class HindiStemmer {
|
||||
public int stem(char buffer[], int len) {
|
||||
public int stem(char[] buffer, int len) {
|
||||
// 5
|
||||
if ((len > 6)
|
||||
&& (endsWith(buffer, len, "ाएंगी")
|
||||
|
|
|
|||
|
|
@ -60,7 +60,7 @@ import static org.apache.lucene.analysis.util.StemmerUtil.*;
|
|||
* Portuguese, German and Hungarian Languages</i> Jacques Savoy
|
||||
*/
|
||||
public class HungarianLightStemmer {
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
for (int i = 0; i < len; i++)
|
||||
switch (s[i]) {
|
||||
case 'á':
|
||||
|
|
@ -94,7 +94,7 @@ public class HungarianLightStemmer {
|
|||
return normalize(s, len);
|
||||
}
|
||||
|
||||
private int removeCase(char s[], int len) {
|
||||
private int removeCase(char[] s, int len) {
|
||||
if (len > 6 && endsWith(s, len, "kent")) return len - 4;
|
||||
|
||||
if (len > 5) {
|
||||
|
|
@ -147,7 +147,7 @@ public class HungarianLightStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int removePossessive(char s[], int len) {
|
||||
private int removePossessive(char[] s, int len) {
|
||||
if (len > 6) {
|
||||
if (!isVowel(s[len - 5])
|
||||
&& (endsWith(s, len, "atok") || endsWith(s, len, "otok") || endsWith(s, len, "etek")))
|
||||
|
|
@ -202,7 +202,7 @@ public class HungarianLightStemmer {
|
|||
}
|
||||
|
||||
@SuppressWarnings("fallthrough")
|
||||
private int removePlural(char s[], int len) {
|
||||
private int removePlural(char[] s, int len) {
|
||||
if (len > 3 && s[len - 1] == 'k')
|
||||
switch (s[len - 2]) {
|
||||
case 'a':
|
||||
|
|
@ -215,7 +215,7 @@ public class HungarianLightStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int normalize(char s[], int len) {
|
||||
private int normalize(char[] s, int len) {
|
||||
if (len > 3)
|
||||
switch (s[len - 1]) {
|
||||
case 'a':
|
||||
|
|
|
|||
|
|
@ -94,7 +94,7 @@ public class HunspellStemFilterFactory extends TokenFilterFactory implements Res
|
|||
|
||||
@Override
|
||||
public void inform(ResourceLoader loader) throws IOException {
|
||||
String dicts[] = dictionaryFiles.split(",");
|
||||
String[] dicts = dictionaryFiles.split(",");
|
||||
|
||||
InputStream affix = null;
|
||||
List<InputStream> dictionaries = new ArrayList<>();
|
||||
|
|
|
|||
|
|
@ -25,7 +25,7 @@ import java.nio.charset.StandardCharsets;
|
|||
// many hunspell dictionaries use this encoding, yet java does not have it?!?!
|
||||
final class ISO8859_14Decoder extends CharsetDecoder {
|
||||
|
||||
static final char TABLE[] =
|
||||
static final char[] TABLE =
|
||||
new char[] {
|
||||
0x00A0, 0x1E02, 0x1E03, 0x00A3, 0x010A, 0x010B, 0x1E0A, 0x00A7,
|
||||
0x1E80, 0x00A9, 0x1E82, 0x1E0B, 0x1EF2, 0x00AD, 0x00AE, 0x0178,
|
||||
|
|
|
|||
|
|
@ -42,7 +42,7 @@ public class IndonesianStemmer {
|
|||
* <p>Use <code>stemDerivational</code> to control whether full stemming or only light
|
||||
* inflectional stemming is done.
|
||||
*/
|
||||
public int stem(char text[], int length, boolean stemDerivational) {
|
||||
public int stem(char[] text, int length, boolean stemDerivational) {
|
||||
flags = 0;
|
||||
numSyllables = 0;
|
||||
for (int i = 0; i < length; i++) if (isVowel(text[i])) numSyllables++;
|
||||
|
|
@ -54,7 +54,7 @@ public class IndonesianStemmer {
|
|||
return length;
|
||||
}
|
||||
|
||||
private int stemDerivational(char text[], int length) {
|
||||
private int stemDerivational(char[] text, int length) {
|
||||
int oldLength = length;
|
||||
if (numSyllables > 2) length = removeFirstOrderPrefix(text, length);
|
||||
if (oldLength != length) { // a rule is fired
|
||||
|
|
@ -82,7 +82,7 @@ public class IndonesianStemmer {
|
|||
}
|
||||
}
|
||||
|
||||
private int removeParticle(char text[], int length) {
|
||||
private int removeParticle(char[] text, int length) {
|
||||
if (endsWith(text, length, "kah")
|
||||
|| endsWith(text, length, "lah")
|
||||
|| endsWith(text, length, "pun")) {
|
||||
|
|
@ -93,7 +93,7 @@ public class IndonesianStemmer {
|
|||
return length;
|
||||
}
|
||||
|
||||
private int removePossessivePronoun(char text[], int length) {
|
||||
private int removePossessivePronoun(char[] text, int length) {
|
||||
if (endsWith(text, length, "ku") || endsWith(text, length, "mu")) {
|
||||
numSyllables--;
|
||||
return length - 2;
|
||||
|
|
@ -107,7 +107,7 @@ public class IndonesianStemmer {
|
|||
return length;
|
||||
}
|
||||
|
||||
private int removeFirstOrderPrefix(char text[], int length) {
|
||||
private int removeFirstOrderPrefix(char[] text, int length) {
|
||||
if (startsWith(text, length, "meng")) {
|
||||
flags |= REMOVED_MENG;
|
||||
numSyllables--;
|
||||
|
|
@ -198,7 +198,7 @@ public class IndonesianStemmer {
|
|||
return length;
|
||||
}
|
||||
|
||||
private int removeSecondOrderPrefix(char text[], int length) {
|
||||
private int removeSecondOrderPrefix(char[] text, int length) {
|
||||
if (startsWith(text, length, "ber")) {
|
||||
flags |= REMOVED_BER;
|
||||
numSyllables--;
|
||||
|
|
@ -240,7 +240,7 @@ public class IndonesianStemmer {
|
|||
return length;
|
||||
}
|
||||
|
||||
private int removeSuffix(char text[], int length) {
|
||||
private int removeSuffix(char[] text, int length) {
|
||||
if (endsWith(text, length, "kan")
|
||||
&& (flags & REMOVED_KE) == 0
|
||||
&& (flags & REMOVED_PENG) == 0
|
||||
|
|
|
|||
|
|
@ -71,7 +71,7 @@ public class IndicNormalizer {
|
|||
* <p>the columns are: ch1, ch2, ch3, res, flags ch1, ch2, and ch3 are the decomposition res is
|
||||
* the composition, and flags are the scripts to which it applies.
|
||||
*/
|
||||
private static final int decompositions[][] = {
|
||||
private static final int[][] decompositions = {
|
||||
/* devanagari, gujarati vowel candra O */
|
||||
{0x05, 0x3E, 0x45, 0x11, flag(DEVANAGARI) | flag(GUJARATI)},
|
||||
/* devanagari short O */
|
||||
|
|
@ -243,7 +243,7 @@ public class IndicNormalizer {
|
|||
* @param len valid length
|
||||
* @return normalized length
|
||||
*/
|
||||
public int normalize(char text[], int len) {
|
||||
public int normalize(char[] text, int len) {
|
||||
for (int i = 0; i < len; i++) {
|
||||
final Character.UnicodeBlock block = Character.UnicodeBlock.of(text[i]);
|
||||
final ScriptData sd = scripts.get(block);
|
||||
|
|
@ -257,7 +257,7 @@ public class IndicNormalizer {
|
|||
|
||||
/** Compose into standard form any compositions in the decompositions table. */
|
||||
private int compose(
|
||||
int ch0, Character.UnicodeBlock block0, ScriptData sd, char text[], int pos, int len) {
|
||||
int ch0, Character.UnicodeBlock block0, ScriptData sd, char[] text, int pos, int len) {
|
||||
if (pos + 1 >= len) /* need at least 2 chars! */ return len;
|
||||
|
||||
final int ch1 = text[pos + 1] - sd.base;
|
||||
|
|
|
|||
|
|
@ -59,7 +59,7 @@ package org.apache.lucene.analysis.it;
|
|||
*/
|
||||
public class ItalianLightStemmer {
|
||||
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
if (len < 6) return len;
|
||||
|
||||
for (int i = 0; i < len; i++)
|
||||
|
|
|
|||
|
|
@ -34,7 +34,7 @@ import static org.apache.lucene.analysis.util.StemmerUtil.*;
|
|||
*/
|
||||
public class LatvianStemmer {
|
||||
/** Stem a latvian word. returns the new adjusted length. */
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
int numVowels = numVowels(s, len);
|
||||
|
||||
for (int i = 0; i < affixes.length; i++) {
|
||||
|
|
@ -48,7 +48,7 @@ public class LatvianStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
static final Affix affixes[] = {
|
||||
static final Affix[] affixes = {
|
||||
new Affix("ajiem", 3, false), new Affix("ajai", 3, false),
|
||||
new Affix("ajam", 2, false), new Affix("ajām", 2, false),
|
||||
new Affix("ajos", 2, false), new Affix("ajās", 2, false),
|
||||
|
|
@ -71,7 +71,7 @@ public class LatvianStemmer {
|
|||
};
|
||||
|
||||
static class Affix {
|
||||
char affix[]; // suffix
|
||||
char[] affix; // suffix
|
||||
int vc; // vowel count of the suffix
|
||||
boolean palatalizes; // true if we should fire palatalization rules.
|
||||
|
||||
|
|
@ -92,7 +92,7 @@ public class LatvianStemmer {
|
|||
* <li>z -> ž
|
||||
* </ul>
|
||||
*/
|
||||
private int unpalatalize(char s[], int len) {
|
||||
private int unpalatalize(char[] s, int len) {
|
||||
// we check the character removed: if it's -u then
|
||||
// it's 2,5, or 6 gen pl., and these two can only apply then.
|
||||
if (s[len] == 'u') {
|
||||
|
|
@ -160,7 +160,7 @@ public class LatvianStemmer {
|
|||
* Count the vowels in the string, we always require at least one in the remaining stem to accept
|
||||
* it.
|
||||
*/
|
||||
private int numVowels(char s[], int len) {
|
||||
private int numVowels(char[] s, int len) {
|
||||
int n = 0;
|
||||
for (int i = 0; i < len; i++) {
|
||||
switch (s[i]) {
|
||||
|
|
|
|||
|
|
@ -188,7 +188,7 @@ public final class ASCIIFoldingFilter extends TokenFilter {
|
|||
* @lucene.internal
|
||||
*/
|
||||
public static final int foldToASCII(
|
||||
char input[], int inputPos, char output[], int outputPos, int length) {
|
||||
char[] input, int inputPos, char[] output, int outputPos, int length) {
|
||||
final int end = inputPos + length;
|
||||
for (int pos = inputPos; pos < end; ++pos) {
|
||||
final char c = input[pos];
|
||||
|
|
|
|||
|
|
@ -88,7 +88,7 @@ public class FingerprintFilter extends TokenFilter {
|
|||
private final boolean buildSingleOutputToken() throws IOException {
|
||||
inputEnded = false;
|
||||
|
||||
char clonedLastTerm[] = null;
|
||||
char[] clonedLastTerm = null;
|
||||
uniqueTerms = new CharArraySet(8, false);
|
||||
int outputTokenSize = 0;
|
||||
while (input.incrementToken()) {
|
||||
|
|
@ -96,7 +96,7 @@ public class FingerprintFilter extends TokenFilter {
|
|||
continue;
|
||||
}
|
||||
|
||||
final char term[] = termAttribute.buffer();
|
||||
final char[] term = termAttribute.buffer();
|
||||
final int length = termAttribute.length();
|
||||
|
||||
if (!uniqueTerms.contains(term, 0, length)) {
|
||||
|
|
@ -150,8 +150,8 @@ public class FingerprintFilter extends TokenFilter {
|
|||
new Comparator<Object>() {
|
||||
@Override
|
||||
public int compare(Object o1, Object o2) {
|
||||
char v1[] = (char[]) o1;
|
||||
char v2[] = (char[]) o2;
|
||||
char[] v1 = (char[]) o1;
|
||||
char[] v2 = (char[]) o2;
|
||||
int len1 = v1.length;
|
||||
int len2 = v2.length;
|
||||
int lim = Math.min(len1, len2);
|
||||
|
|
|
|||
|
|
@ -121,7 +121,7 @@ public final class HyphenatedWordsFilter extends TokenFilter {
|
|||
restoreState(savedState);
|
||||
savedState = null;
|
||||
|
||||
char term[] = termAttribute.buffer();
|
||||
char[] term = termAttribute.buffer();
|
||||
int length = hyphenated.length();
|
||||
if (length > termAttribute.length()) {
|
||||
term = termAttribute.resizeBuffer(length);
|
||||
|
|
|
|||
|
|
@ -47,7 +47,7 @@ public final class RemoveDuplicatesTokenFilter extends TokenFilter {
|
|||
@Override
|
||||
public boolean incrementToken() throws IOException {
|
||||
while (input.incrementToken()) {
|
||||
final char term[] = termAttribute.buffer();
|
||||
final char[] term = termAttribute.buffer();
|
||||
final int length = termAttribute.length();
|
||||
final int posIncrement = posIncAttribute.getPositionIncrement();
|
||||
|
||||
|
|
@ -58,7 +58,7 @@ public final class RemoveDuplicatesTokenFilter extends TokenFilter {
|
|||
boolean duplicate = (posIncrement == 0 && previous.contains(term, 0, length));
|
||||
|
||||
// clone the term, and add to the set of seen terms.
|
||||
char saved[] = new char[length];
|
||||
char[] saved = new char[length];
|
||||
System.arraycopy(term, 0, saved, 0, length);
|
||||
previous.add(saved);
|
||||
|
||||
|
|
|
|||
|
|
@ -183,7 +183,7 @@ public final class WordDelimiterFilter extends TokenFilter {
|
|||
// used for accumulating position increment gaps
|
||||
private int accumPosInc = 0;
|
||||
|
||||
private char savedBuffer[] = new char[1024];
|
||||
private char[] savedBuffer = new char[1024];
|
||||
private int savedStartOffset;
|
||||
private int savedEndOffset;
|
||||
private String savedType;
|
||||
|
|
@ -377,9 +377,9 @@ public final class WordDelimiterFilter extends TokenFilter {
|
|||
first = true;
|
||||
}
|
||||
|
||||
private AttributeSource.State buffered[] = new AttributeSource.State[8];
|
||||
private int startOff[] = new int[8];
|
||||
private int posInc[] = new int[8];
|
||||
private AttributeSource.State[] buffered = new AttributeSource.State[8];
|
||||
private int[] startOff = new int[8];
|
||||
private int[] posInc = new int[8];
|
||||
private int bufferedLen = 0;
|
||||
private int bufferedPos = 0;
|
||||
private boolean first;
|
||||
|
|
@ -616,7 +616,7 @@ public final class WordDelimiterFilter extends TokenFilter {
|
|||
* @param offset Offset in the concetenation to add the text
|
||||
* @param length Length of the text to append
|
||||
*/
|
||||
void append(char text[], int offset, int length) {
|
||||
void append(char[] text, int offset, int length) {
|
||||
buffer.append(text, offset, length);
|
||||
subwordCount++;
|
||||
}
|
||||
|
|
@ -627,7 +627,7 @@ public final class WordDelimiterFilter extends TokenFilter {
|
|||
if (termAttribute.length() < buffer.length()) {
|
||||
termAttribute.resizeBuffer(buffer.length());
|
||||
}
|
||||
char termbuffer[] = termAttribute.buffer();
|
||||
char[] termbuffer = termAttribute.buffer();
|
||||
|
||||
buffer.getChars(0, buffer.length(), termbuffer, 0);
|
||||
termAttribute.setLength(buffer.length());
|
||||
|
|
|
|||
|
|
@ -173,7 +173,7 @@ public class WordDelimiterFilterFactory extends TokenFilterFactory implements Re
|
|||
}
|
||||
|
||||
// ensure the table is always at least as big as DEFAULT_WORD_DELIM_TABLE for performance
|
||||
byte types[] =
|
||||
byte[] types =
|
||||
new byte
|
||||
[Math.max(
|
||||
typeMap.lastKey() + 1, WordDelimiterIterator.DEFAULT_WORD_DELIM_TABLE.length)];
|
||||
|
|
|
|||
|
|
@ -608,7 +608,7 @@ public final class WordDelimiterGraphFilter extends TokenFilter {
|
|||
* @param offset Offset in the concetenation to add the text
|
||||
* @param length Length of the text to append
|
||||
*/
|
||||
void append(char text[], int offset, int length) {
|
||||
void append(char[] text, int offset, int length) {
|
||||
buffer.append(text, offset, length);
|
||||
subwordCount++;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -160,7 +160,7 @@ public class WordDelimiterGraphFilterFactory extends TokenFilterFactory
|
|||
}
|
||||
|
||||
// ensure the table is always at least as big as DEFAULT_WORD_DELIM_TABLE for performance
|
||||
byte types[] =
|
||||
byte[] types =
|
||||
new byte
|
||||
[Math.max(
|
||||
typeMap.lastKey() + 1, WordDelimiterIterator.DEFAULT_WORD_DELIM_TABLE.length)];
|
||||
|
|
|
|||
|
|
@ -40,7 +40,7 @@ public final class WordDelimiterIterator {
|
|||
|
||||
public static final byte[] DEFAULT_WORD_DELIM_TABLE;
|
||||
|
||||
char text[];
|
||||
char[] text;
|
||||
int length;
|
||||
|
||||
/** start position of text, excluding leading delimiters */
|
||||
|
|
@ -207,7 +207,7 @@ public final class WordDelimiterIterator {
|
|||
* @param text New text
|
||||
* @param length length of the text
|
||||
*/
|
||||
void setText(char text[], int length) {
|
||||
void setText(char[] text, int length) {
|
||||
this.text = text;
|
||||
this.length = this.endBounds = length;
|
||||
current = startBounds = end = 0;
|
||||
|
|
|
|||
|
|
@ -82,7 +82,7 @@ public class NorwegianLightStemmer {
|
|||
useNynorsk = (flags & NYNORSK) != 0;
|
||||
}
|
||||
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
// Remove posessive -s (bilens -> bilen) and continue checking
|
||||
if (len > 4 && s[len - 1] == 's') len--;
|
||||
|
||||
|
|
|
|||
|
|
@ -78,7 +78,7 @@ public class NorwegianMinimalStemmer {
|
|||
useNynorsk = (flags & NYNORSK) != 0;
|
||||
}
|
||||
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
// Remove genitiv s
|
||||
if (len > 4 && s[len - 1] == 's') len--;
|
||||
|
||||
|
|
|
|||
|
|
@ -61,7 +61,7 @@ import static org.apache.lucene.analysis.util.StemmerUtil.*;
|
|||
*/
|
||||
public class PortugueseLightStemmer {
|
||||
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
if (len < 4) return len;
|
||||
|
||||
len = removeSuffix(s, len);
|
||||
|
|
@ -119,7 +119,7 @@ public class PortugueseLightStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int removeSuffix(char s[], int len) {
|
||||
private int removeSuffix(char[] s, int len) {
|
||||
if (len > 4 && endsWith(s, len, "es"))
|
||||
switch (s[len - 3]) {
|
||||
case 'r':
|
||||
|
|
@ -169,7 +169,7 @@ public class PortugueseLightStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int normFeminine(char s[], int len) {
|
||||
private int normFeminine(char[] s, int len) {
|
||||
if (len > 7
|
||||
&& (endsWith(s, len, "inha") || endsWith(s, len, "iaca") || endsWith(s, len, "eira"))) {
|
||||
s[len - 1] = 'o';
|
||||
|
|
|
|||
|
|
@ -31,7 +31,7 @@ public class PortugueseMinimalStemmer extends RSLPStemmerBase {
|
|||
private static final Step pluralStep =
|
||||
parse(PortugueseMinimalStemmer.class, "portuguese.rslp").get("Plural");
|
||||
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
return pluralStep.apply(s, len);
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -43,7 +43,7 @@ public class PortugueseStemmer extends RSLPStemmerBase {
|
|||
* @param len initial valid length of buffer
|
||||
* @return new valid length, stemmed
|
||||
*/
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
assert s.length >= len + 1 : "this stemmer requires an oversized array of at least 1";
|
||||
|
||||
len = plural.apply(s, len);
|
||||
|
|
|
|||
|
|
@ -94,8 +94,8 @@ public abstract class RSLPStemmerBase {
|
|||
|
||||
/** A basic rule, with no exceptions. */
|
||||
protected static class Rule {
|
||||
protected final char suffix[];
|
||||
protected final char replacement[];
|
||||
protected final char[] suffix;
|
||||
protected final char[] replacement;
|
||||
protected final int min;
|
||||
|
||||
/**
|
||||
|
|
@ -112,12 +112,12 @@ public abstract class RSLPStemmerBase {
|
|||
}
|
||||
|
||||
/** @return true if the word matches this rule. */
|
||||
public boolean matches(char s[], int len) {
|
||||
public boolean matches(char[] s, int len) {
|
||||
return (len - suffix.length >= min && endsWith(s, len, suffix));
|
||||
}
|
||||
|
||||
/** @return new valid length of the string after firing this rule. */
|
||||
public int replace(char s[], int len) {
|
||||
public int replace(char[] s, int len) {
|
||||
if (replacement.length > 0) {
|
||||
System.arraycopy(replacement, 0, s, len - suffix.length, replacement.length);
|
||||
}
|
||||
|
|
@ -140,7 +140,7 @@ public abstract class RSLPStemmerBase {
|
|||
}
|
||||
|
||||
@Override
|
||||
public boolean matches(char s[], int len) {
|
||||
public boolean matches(char[] s, int len) {
|
||||
return super.matches(s, len) && !exceptions.contains(s, 0, len);
|
||||
}
|
||||
}
|
||||
|
|
@ -167,7 +167,7 @@ public abstract class RSLPStemmerBase {
|
|||
}
|
||||
|
||||
@Override
|
||||
public boolean matches(char s[], int len) {
|
||||
public boolean matches(char[] s, int len) {
|
||||
if (!super.matches(s, len)) return false;
|
||||
|
||||
for (int i = 0; i < exceptions.length; i++) if (endsWith(s, len, exceptions[i])) return false;
|
||||
|
|
@ -179,7 +179,7 @@ public abstract class RSLPStemmerBase {
|
|||
/** A step containing a list of rules. */
|
||||
protected static class Step {
|
||||
protected final String name;
|
||||
protected final Rule rules[];
|
||||
protected final Rule[] rules;
|
||||
protected final int min;
|
||||
protected final char[][] suffixes;
|
||||
|
||||
|
|
@ -191,7 +191,7 @@ public abstract class RSLPStemmerBase {
|
|||
* @param min minimum word size. if this is 0 it is automatically calculated.
|
||||
* @param suffixes optional list of conditional suffixes. may be null.
|
||||
*/
|
||||
public Step(String name, Rule rules[], int min, String suffixes[]) {
|
||||
public Step(String name, Rule[] rules, int min, String[] suffixes) {
|
||||
this.name = name;
|
||||
this.rules = rules;
|
||||
if (min == 0) {
|
||||
|
|
@ -209,7 +209,7 @@ public abstract class RSLPStemmerBase {
|
|||
}
|
||||
|
||||
/** @return new valid length of the string after applying the entire step. */
|
||||
public int apply(char s[], int len) {
|
||||
public int apply(char[] s, int len) {
|
||||
if (len < min) return len;
|
||||
|
||||
if (suffixes != null) {
|
||||
|
|
@ -275,8 +275,8 @@ public abstract class RSLPStemmerBase {
|
|||
String name = matcher.group(1);
|
||||
int min = Integer.parseInt(matcher.group(2));
|
||||
int type = Integer.parseInt(matcher.group(3));
|
||||
String suffixes[] = parseList(matcher.group(4));
|
||||
Rule rules[] = parseRules(r, type);
|
||||
String[] suffixes = parseList(matcher.group(4));
|
||||
Rule[] rules = parseRules(r, type);
|
||||
return new Step(name, rules, min, suffixes);
|
||||
}
|
||||
|
||||
|
|
@ -322,7 +322,7 @@ public abstract class RSLPStemmerBase {
|
|||
|
||||
private static String[] parseList(String s) {
|
||||
if (s.length() == 0) return null;
|
||||
String list[] = s.split(",");
|
||||
String[] list = s.split(",");
|
||||
for (int i = 0; i < list.length; i++) list[i] = parseString(list[i].trim());
|
||||
return list;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -61,12 +61,12 @@ import static org.apache.lucene.analysis.util.StemmerUtil.*;
|
|||
*/
|
||||
public class RussianLightStemmer {
|
||||
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
len = removeCase(s, len);
|
||||
return normalize(s, len);
|
||||
}
|
||||
|
||||
private int normalize(char s[], int len) {
|
||||
private int normalize(char[] s, int len) {
|
||||
if (len > 3)
|
||||
switch (s[len - 1]) {
|
||||
case 'ь':
|
||||
|
|
@ -78,7 +78,7 @@ public class RussianLightStemmer {
|
|||
return len;
|
||||
}
|
||||
|
||||
private int removeCase(char s[], int len) {
|
||||
private int removeCase(char[] s, int len) {
|
||||
if (len > 6 && (endsWith(s, len, "иями") || endsWith(s, len, "оями"))) return len - 4;
|
||||
|
||||
if (len > 5
|
||||
|
|
|
|||
|
|
@ -85,11 +85,11 @@ public final class SnowballFilter extends TokenFilter {
|
|||
public final boolean incrementToken() throws IOException {
|
||||
if (input.incrementToken()) {
|
||||
if (!keywordAttr.isKeyword()) {
|
||||
char termBuffer[] = termAtt.buffer();
|
||||
char[] termBuffer = termAtt.buffer();
|
||||
final int length = termAtt.length();
|
||||
stemmer.setCurrent(termBuffer, length);
|
||||
stemmer.stem();
|
||||
final char finalTerm[] = stemmer.getCurrentBuffer();
|
||||
final char[] finalTerm = stemmer.getCurrentBuffer();
|
||||
final int newLength = stemmer.getCurrentBufferLength();
|
||||
if (finalTerm != termBuffer) termAtt.copyBuffer(finalTerm, 0, newLength);
|
||||
else termAtt.setLength(newLength);
|
||||
|
|
|
|||
|
|
@ -40,7 +40,7 @@ public final class SerbianNormalizationFilter extends TokenFilter {
|
|||
@Override
|
||||
public boolean incrementToken() throws IOException {
|
||||
if (input.incrementToken()) {
|
||||
char buffer[] = termAtt.buffer();
|
||||
char[] buffer = termAtt.buffer();
|
||||
int length = termAtt.length();
|
||||
for (int i = 0; i < length; i++) {
|
||||
final char c = buffer[i];
|
||||
|
|
|
|||
|
|
@ -37,7 +37,7 @@ public final class SerbianNormalizationRegularFilter extends TokenFilter {
|
|||
@Override
|
||||
public boolean incrementToken() throws IOException {
|
||||
if (input.incrementToken()) {
|
||||
char buffer[] = termAtt.buffer();
|
||||
char[] buffer = termAtt.buffer();
|
||||
int length = termAtt.length();
|
||||
for (int i = 0; i < length; i++) {
|
||||
final char c = buffer[i];
|
||||
|
|
|
|||
|
|
@ -61,7 +61,7 @@ import static org.apache.lucene.analysis.util.StemmerUtil.*;
|
|||
*/
|
||||
public class SwedishLightStemmer {
|
||||
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
if (len > 4 && s[len - 1] == 's') len--;
|
||||
|
||||
if (len > 7 && (endsWith(s, len, "elser") || endsWith(s, len, "heten"))) return len - 5;
|
||||
|
|
|
|||
|
|
@ -62,7 +62,7 @@ import static org.apache.lucene.analysis.util.StemmerUtil.endsWith;
|
|||
*/
|
||||
public class SwedishMinimalStemmer {
|
||||
|
||||
public int stem(char s[], int len) {
|
||||
public int stem(char[] s, int len) {
|
||||
if (len > 4 && s[len - 1] == 's') len--;
|
||||
|
||||
if (len > 6
|
||||
|
|
|
|||
|
|
@ -87,19 +87,19 @@ public class SolrSynonymParser extends SynonymMap.Parser {
|
|||
}
|
||||
|
||||
// TODO: we could process this more efficiently.
|
||||
String sides[] = split(line, "=>");
|
||||
String[] sides = split(line, "=>");
|
||||
if (sides.length > 1) { // explicit mapping
|
||||
if (sides.length != 2) {
|
||||
throw new IllegalArgumentException(
|
||||
"more than one explicit mapping specified on the same line");
|
||||
}
|
||||
String inputStrings[] = split(sides[0], ",");
|
||||
String[] inputStrings = split(sides[0], ",");
|
||||
CharsRef[] inputs = new CharsRef[inputStrings.length];
|
||||
for (int i = 0; i < inputs.length; i++) {
|
||||
inputs[i] = analyze(unescape(inputStrings[i]).trim(), new CharsRefBuilder());
|
||||
}
|
||||
|
||||
String outputStrings[] = split(sides[1], ",");
|
||||
String[] outputStrings = split(sides[1], ",");
|
||||
CharsRef[] outputs = new CharsRef[outputStrings.length];
|
||||
for (int i = 0; i < outputs.length; i++) {
|
||||
outputs[i] = analyze(unescape(outputStrings[i]).trim(), new CharsRefBuilder());
|
||||
|
|
@ -111,7 +111,7 @@ public class SolrSynonymParser extends SynonymMap.Parser {
|
|||
}
|
||||
}
|
||||
} else {
|
||||
String inputStrings[] = split(line, ",");
|
||||
String[] inputStrings = split(line, ",");
|
||||
CharsRef[] inputs = new CharsRef[inputStrings.length];
|
||||
for (int i = 0; i < inputs.length; i++) {
|
||||
inputs[i] = analyze(unescape(inputStrings[i]).trim(), new CharsRefBuilder());
|
||||
|
|
|
|||
|
|
@ -235,7 +235,7 @@ public class SynonymMap {
|
|||
final byte[] spare = new byte[5];
|
||||
|
||||
Set<CharsRef> keys = workingSet.keySet();
|
||||
CharsRef sortedKeys[] = keys.toArray(new CharsRef[keys.size()]);
|
||||
CharsRef[] sortedKeys = keys.toArray(new CharsRef[keys.size()]);
|
||||
Arrays.sort(sortedKeys, CharsRef.getUTF16SortedAsUTF8Comparator());
|
||||
|
||||
final IntsRefBuilder scratchIntsRef = new IntsRefBuilder();
|
||||
|
|
|
|||
|
|
@ -47,7 +47,7 @@ public class WordnetSynonymParser extends SynonymMap.Parser {
|
|||
try {
|
||||
String line = null;
|
||||
String lastSynSetID = "";
|
||||
CharsRef synset[] = new CharsRef[8];
|
||||
CharsRef[] synset = new CharsRef[8];
|
||||
int synsetSize = 0;
|
||||
|
||||
while ((line = br.readLine()) != null) {
|
||||
|
|
@ -88,7 +88,7 @@ public class WordnetSynonymParser extends SynonymMap.Parser {
|
|||
return analyze(text, reuse);
|
||||
}
|
||||
|
||||
private void addInternal(CharsRef synset[], int size) {
|
||||
private void addInternal(CharsRef[] synset, int size) {
|
||||
if (size <= 1) {
|
||||
return; // nothing to do
|
||||
}
|
||||
|
|
|
|||
|
|
@ -90,7 +90,7 @@ public final class TurkishLowerCaseFilter extends TokenFilter {
|
|||
}
|
||||
|
||||
/** lookahead for a combining dot above. other NSMs may be in between. */
|
||||
private boolean isBeforeDot(char s[], int pos, int len) {
|
||||
private boolean isBeforeDot(char[] s, int pos, int len) {
|
||||
for (int i = pos; i < len; ) {
|
||||
final int ch = Character.codePointAt(s, i, len);
|
||||
if (Character.getType(ch) != Character.NON_SPACING_MARK) return false;
|
||||
|
|
@ -104,7 +104,7 @@ public final class TurkishLowerCaseFilter extends TokenFilter {
|
|||
/**
|
||||
* delete a character in-place. rarely happens, only if COMBINING_DOT_ABOVE is found after an i
|
||||
*/
|
||||
private int delete(char s[], int pos, int len) {
|
||||
private int delete(char[] s, int pos, int len) {
|
||||
if (pos < len) System.arraycopy(s, pos + 1, s, pos, len - pos - 1);
|
||||
|
||||
return len - 1;
|
||||
|
|
|
|||
|
|
@ -26,7 +26,7 @@ import java.util.Locale;
|
|||
* @lucene.internal
|
||||
*/
|
||||
public abstract class CharArrayIterator implements CharacterIterator {
|
||||
private char array[];
|
||||
private char[] array;
|
||||
private int start;
|
||||
private int index;
|
||||
private int length;
|
||||
|
|
@ -51,7 +51,7 @@ public abstract class CharArrayIterator implements CharacterIterator {
|
|||
* @param start offset into buffer
|
||||
* @param length maximum length to examine
|
||||
*/
|
||||
public void setText(final char array[], int start, int length) {
|
||||
public void setText(final char[] array, int start, int length) {
|
||||
this.array = array;
|
||||
this.start = start;
|
||||
this.index = start;
|
||||
|
|
|
|||
|
|
@ -101,13 +101,13 @@ public class OpenStringBuilder implements Appendable, CharSequence {
|
|||
unsafeWrite((char) b);
|
||||
}
|
||||
|
||||
public void unsafeWrite(char b[], int off, int len) {
|
||||
public void unsafeWrite(char[] b, int off, int len) {
|
||||
System.arraycopy(b, off, buf, this.len, len);
|
||||
this.len += len;
|
||||
}
|
||||
|
||||
protected void resize(int len) {
|
||||
char newbuf[] = new char[Math.max(buf.length << 1, len)];
|
||||
char[] newbuf = new char[Math.max(buf.length << 1, len)];
|
||||
System.arraycopy(buf, 0, newbuf, 0, size());
|
||||
buf = newbuf;
|
||||
}
|
||||
|
|
@ -131,7 +131,7 @@ public class OpenStringBuilder implements Appendable, CharSequence {
|
|||
write(b, 0, b.length);
|
||||
}
|
||||
|
||||
public void write(char b[], int off, int len) {
|
||||
public void write(char[] b, int off, int len) {
|
||||
reserve(len);
|
||||
unsafeWrite(b, off, len);
|
||||
}
|
||||
|
|
@ -153,7 +153,7 @@ public class OpenStringBuilder implements Appendable, CharSequence {
|
|||
}
|
||||
|
||||
public char[] toCharArray() {
|
||||
char newbuf[] = new char[size()];
|
||||
char[] newbuf = new char[size()];
|
||||
System.arraycopy(buf, 0, newbuf, 0, size());
|
||||
return newbuf;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -37,7 +37,7 @@ import org.apache.lucene.util.AttributeFactory;
|
|||
*/
|
||||
public abstract class SegmentingTokenizerBase extends Tokenizer {
|
||||
protected static final int BUFFERMAX = 1024;
|
||||
protected final char buffer[] = new char[BUFFERMAX];
|
||||
protected final char[] buffer = new char[BUFFERMAX];
|
||||
/** true length of text in the buffer */
|
||||
private int length = 0;
|
||||
/** length in buffer that can be evaluated safely, up to a safe end point */
|
||||
|
|
|
|||
|
|
@ -33,7 +33,7 @@ public class StemmerUtil {
|
|||
* @param prefix Prefix string to test
|
||||
* @return true if <code>s</code> starts with <code>prefix</code>
|
||||
*/
|
||||
public static boolean startsWith(char s[], int len, String prefix) {
|
||||
public static boolean startsWith(char[] s, int len, String prefix) {
|
||||
final int prefixLen = prefix.length();
|
||||
if (prefixLen > len) return false;
|
||||
for (int i = 0; i < prefixLen; i++) if (s[i] != prefix.charAt(i)) return false;
|
||||
|
|
@ -48,7 +48,7 @@ public class StemmerUtil {
|
|||
* @param suffix Suffix string to test
|
||||
* @return true if <code>s</code> ends with <code>suffix</code>
|
||||
*/
|
||||
public static boolean endsWith(char s[], int len, String suffix) {
|
||||
public static boolean endsWith(char[] s, int len, String suffix) {
|
||||
final int suffixLen = suffix.length();
|
||||
if (suffixLen > len) return false;
|
||||
for (int i = suffixLen - 1; i >= 0; i--)
|
||||
|
|
@ -65,7 +65,7 @@ public class StemmerUtil {
|
|||
* @param suffix Suffix string to test
|
||||
* @return true if <code>s</code> ends with <code>suffix</code>
|
||||
*/
|
||||
public static boolean endsWith(char s[], int len, char suffix[]) {
|
||||
public static boolean endsWith(char[] s, int len, char[] suffix) {
|
||||
final int suffixLen = suffix.length;
|
||||
if (suffixLen > len) return false;
|
||||
for (int i = suffixLen - 1; i >= 0; i--)
|
||||
|
|
@ -82,7 +82,7 @@ public class StemmerUtil {
|
|||
* @param len length of input buffer
|
||||
* @return length of input buffer after deletion
|
||||
*/
|
||||
public static int delete(char s[], int pos, int len) {
|
||||
public static int delete(char[] s, int pos, int len) {
|
||||
assert pos < len;
|
||||
if (pos < len - 1) { // don't arraycopy if asked to delete last character
|
||||
System.arraycopy(s, pos + 1, s, pos, len - pos - 1);
|
||||
|
|
@ -99,7 +99,7 @@ public class StemmerUtil {
|
|||
* @param nChars number of characters to delete
|
||||
* @return length of input buffer after deletion
|
||||
*/
|
||||
public static int deleteN(char s[], int pos, int len, int nChars) {
|
||||
public static int deleteN(char[] s, int pos, int len, int nChars) {
|
||||
assert pos + nChars <= len;
|
||||
if (pos + nChars < len) { // don't arraycopy if asked to delete the last characters
|
||||
System.arraycopy(s, pos + nChars, s, pos, len - pos - nChars);
|
||||
|
|
|
|||
|
|
@ -326,7 +326,7 @@ class WikipediaTokenizerImpl {
|
|||
private static final int ZZ_PUSHBACK_2BIG = 2;
|
||||
|
||||
/* error messages for the codes above */
|
||||
private static final String ZZ_ERROR_MSG[] = {
|
||||
private static final String[] ZZ_ERROR_MSG = {
|
||||
"Unknown internal scanner error",
|
||||
"Error: could not match input",
|
||||
"Error: pushback value was too large"
|
||||
|
|
@ -377,7 +377,7 @@ class WikipediaTokenizerImpl {
|
|||
/**
|
||||
* this buffer contains the current text to be matched and is the source of the yytext() string
|
||||
*/
|
||||
private char zzBuffer[] = new char[ZZ_BUFFERSIZE];
|
||||
private char[] zzBuffer = new char[ZZ_BUFFERSIZE];
|
||||
|
||||
/** the textposition at the last accepting state */
|
||||
private int zzMarkedPos;
|
||||
|
|
@ -537,7 +537,7 @@ class WikipediaTokenizerImpl {
|
|||
/* is the buffer big enough? */
|
||||
if (zzCurrentPos >= zzBuffer.length - zzFinalHighSurrogate) {
|
||||
/* if not: blow it up */
|
||||
char newBuffer[] = new char[zzBuffer.length * 2];
|
||||
char[] newBuffer = new char[zzBuffer.length * 2];
|
||||
System.arraycopy(zzBuffer, 0, newBuffer, 0, zzBuffer.length);
|
||||
zzBuffer = newBuffer;
|
||||
zzEndRead += zzFinalHighSurrogate;
|
||||
|
|
|
|||
|
|
@ -65,7 +65,7 @@ public class SnowballProgram implements Serializable {
|
|||
* @param text character array containing input
|
||||
* @param length valid length of text.
|
||||
*/
|
||||
public void setCurrent(char text[], int length) {
|
||||
public void setCurrent(char[] text, int length) {
|
||||
current = text;
|
||||
cursor = 0;
|
||||
limit = length;
|
||||
|
|
@ -101,7 +101,7 @@ public class SnowballProgram implements Serializable {
|
|||
}
|
||||
|
||||
// current string
|
||||
private char current[];
|
||||
private char[] current;
|
||||
|
||||
protected int cursor;
|
||||
protected int limit;
|
||||
|
|
@ -346,7 +346,7 @@ public class SnowballProgram implements Serializable {
|
|||
final int newLength = limit + adjustment;
|
||||
// resize if necessary
|
||||
if (newLength > current.length) {
|
||||
char newBuffer[] = new char[oversize(newLength)];
|
||||
char[] newBuffer = new char[oversize(newLength)];
|
||||
System.arraycopy(current, 0, newBuffer, 0, limit);
|
||||
current = newBuffer;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -200,7 +200,7 @@ public class TestAnalyzers extends BaseTokenStreamTestCase {
|
|||
|
||||
/** blast some random strings through the analyzer */
|
||||
public void testRandomStrings() throws Exception {
|
||||
Analyzer analyzers[] =
|
||||
Analyzer[] analyzers =
|
||||
new Analyzer[] {
|
||||
new WhitespaceAnalyzer(),
|
||||
new SimpleAnalyzer(),
|
||||
|
|
@ -215,7 +215,7 @@ public class TestAnalyzers extends BaseTokenStreamTestCase {
|
|||
|
||||
/** blast some random large strings through the analyzer */
|
||||
public void testRandomHugeStrings() throws Exception {
|
||||
Analyzer analyzers[] =
|
||||
Analyzer[] analyzers =
|
||||
new Analyzer[] {
|
||||
new WhitespaceAnalyzer(),
|
||||
new SimpleAnalyzer(),
|
||||
|
|
|
|||
|
|
@ -283,7 +283,7 @@ public class TestBugInSomething extends BaseTokenStreamTestCase {
|
|||
new HashSet<>(
|
||||
Arrays.asList("rrdpafa", "pupmmlu", "xlq", "dyy", "zqrxrrck", "o", "hsrlfvcha")),
|
||||
false);
|
||||
final byte table[] =
|
||||
final byte[] table =
|
||||
new byte[] {
|
||||
-57, 26, 1, 48, 63, -23, 55, -84, 18, 120, -97, 103, 58, 13, 84, 89, 57, -13, -63, 5, 28,
|
||||
97, -54, -94, 102, -108, -5, 5, 46, 40, 43, 78, 43, -72, 36, 29, 124, -106, -22, -51, 65,
|
||||
|
|
|
|||
|
|
@ -379,7 +379,7 @@ public class TestRandomChains extends BaseTokenStreamTestCase {
|
|||
put(
|
||||
byte[].class,
|
||||
random -> {
|
||||
byte bytes[] = new byte[random.nextInt(256)];
|
||||
byte[] bytes = new byte[random.nextInt(256)];
|
||||
random.nextBytes(bytes);
|
||||
return bytes;
|
||||
});
|
||||
|
|
@ -802,7 +802,7 @@ public class TestRandomChains extends BaseTokenStreamTestCase {
|
|||
final Constructor<? extends Tokenizer> ctor =
|
||||
tokenizers.get(random.nextInt(tokenizers.size()));
|
||||
final StringBuilder descr = new StringBuilder();
|
||||
final Object args[] = newTokenizerArgs(random, ctor.getParameterTypes());
|
||||
final Object[] args = newTokenizerArgs(random, ctor.getParameterTypes());
|
||||
if (broken(ctor, args)) {
|
||||
continue;
|
||||
}
|
||||
|
|
@ -823,7 +823,7 @@ public class TestRandomChains extends BaseTokenStreamTestCase {
|
|||
while (true) {
|
||||
final Constructor<? extends CharFilter> ctor =
|
||||
charfilters.get(random.nextInt(charfilters.size()));
|
||||
final Object args[] = newCharFilterArgs(random, spec.reader, ctor.getParameterTypes());
|
||||
final Object[] args = newCharFilterArgs(random, spec.reader, ctor.getParameterTypes());
|
||||
if (broken(ctor, args)) {
|
||||
continue;
|
||||
}
|
||||
|
|
@ -860,7 +860,7 @@ public class TestRandomChains extends BaseTokenStreamTestCase {
|
|||
new ConditionalTokenFilter(
|
||||
spec.stream,
|
||||
in -> {
|
||||
final Object args[] = newFilterArgs(random, in, ctor.getParameterTypes());
|
||||
final Object[] args = newFilterArgs(random, in, ctor.getParameterTypes());
|
||||
if (broken(ctor, args)) {
|
||||
return in;
|
||||
}
|
||||
|
|
@ -885,7 +885,7 @@ public class TestRandomChains extends BaseTokenStreamTestCase {
|
|||
};
|
||||
break;
|
||||
} else {
|
||||
final Object args[] = newFilterArgs(random, spec.stream, ctor.getParameterTypes());
|
||||
final Object[] args = newFilterArgs(random, spec.stream, ctor.getParameterTypes());
|
||||
if (broken(ctor, args)) {
|
||||
continue;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -86,7 +86,7 @@ public class TestStopAnalyzer extends BaseTokenStreamTestCase {
|
|||
CharArraySet stopWordsSet = new CharArraySet(asSet("good", "test", "analyzer"), false);
|
||||
StopAnalyzer newStop = new StopAnalyzer(stopWordsSet);
|
||||
String s = "This is a good test of the english stop analyzer with positions";
|
||||
int expectedIncr[] = {1, 1, 1, 3, 1, 1, 1, 2, 1};
|
||||
int[] expectedIncr = {1, 1, 1, 3, 1, 1, 1, 2, 1};
|
||||
try (TokenStream stream = newStop.tokenStream("test", s)) {
|
||||
assertNotNull(stream);
|
||||
int i = 0;
|
||||
|
|
|
|||
|
|
@ -51,7 +51,7 @@ public class TestTypeTokenFilter extends BaseTokenStreamTestCase {
|
|||
}
|
||||
}
|
||||
log(sb.toString());
|
||||
String stopTypes[] = new String[] {"<NUM>"};
|
||||
String[] stopTypes = new String[] {"<NUM>"};
|
||||
Set<String> stopSet = asSet(stopTypes);
|
||||
|
||||
// with increments
|
||||
|
|
|
|||
|
|
@ -39,7 +39,7 @@ public class TestUAX29URLEmailAnalyzer extends BaseTokenStreamTestCase {
|
|||
|
||||
public void testHugeDoc() throws IOException {
|
||||
StringBuilder sb = new StringBuilder();
|
||||
char whitespace[] = new char[4094];
|
||||
char[] whitespace = new char[4094];
|
||||
Arrays.fill(whitespace, ' ');
|
||||
sb.append(whitespace);
|
||||
sb.append("testing 1234");
|
||||
|
|
|
|||
|
|
@ -81,7 +81,7 @@ public class TestUAX29URLEmailTokenizer extends BaseTokenStreamTestCase {
|
|||
|
||||
public void testHugeDoc() throws IOException {
|
||||
StringBuilder sb = new StringBuilder();
|
||||
char whitespace[] = new char[4094];
|
||||
char[] whitespace = new char[4094];
|
||||
Arrays.fill(whitespace, ' ');
|
||||
sb.append(whitespace);
|
||||
sb.append("testing 1234");
|
||||
|
|
|
|||
|
|
@ -192,7 +192,7 @@ public class TestCapitalizationFilter extends BaseTokenStreamTestCase {
|
|||
|
||||
static void assertCapitalizesTo(
|
||||
Tokenizer tokenizer,
|
||||
String expected[],
|
||||
String[] expected,
|
||||
boolean onlyFirstWord,
|
||||
CharArraySet keep,
|
||||
boolean forceFirstLetter,
|
||||
|
|
@ -216,7 +216,7 @@ public class TestCapitalizationFilter extends BaseTokenStreamTestCase {
|
|||
|
||||
static void assertCapitalizesTo(
|
||||
String input,
|
||||
String expected[],
|
||||
String[] expected,
|
||||
boolean onlyFirstWord,
|
||||
CharArraySet keep,
|
||||
boolean forceFirstLetter,
|
||||
|
|
|
|||
|
|
@ -30,10 +30,10 @@ import org.apache.lucene.store.ByteBuffersDirectory;
|
|||
import org.apache.lucene.store.Directory;
|
||||
|
||||
public class TestQueryAutoStopWordAnalyzer extends BaseTokenStreamTestCase {
|
||||
String variedFieldValues[] = {
|
||||
String[] variedFieldValues = {
|
||||
"the", "quick", "brown", "fox", "jumped", "over", "the", "lazy", "boring", "dog"
|
||||
};
|
||||
String repetitiveFieldValues[] = {"boring", "boring", "vaguelyboring"};
|
||||
String[] repetitiveFieldValues = {"boring", "boring", "vaguelyboring"};
|
||||
Directory dir;
|
||||
Analyzer appAnalyzer;
|
||||
IndexReader reader;
|
||||
|
|
|
|||
|
|
@ -1194,9 +1194,9 @@ public class TestShingleFilter extends BaseTokenStreamTestCase {
|
|||
protected void shingleFilterTestCommon(
|
||||
ShingleFilter filter, Token[] tokensToCompare, int[] positionIncrements, String[] types)
|
||||
throws IOException {
|
||||
String text[] = new String[tokensToCompare.length];
|
||||
int startOffsets[] = new int[tokensToCompare.length];
|
||||
int endOffsets[] = new int[tokensToCompare.length];
|
||||
String[] text = new String[tokensToCompare.length];
|
||||
int[] startOffsets = new int[tokensToCompare.length];
|
||||
int[] endOffsets = new int[tokensToCompare.length];
|
||||
|
||||
for (int i = 0; i < tokensToCompare.length; i++) {
|
||||
text[i] = new String(tokensToCompare[i].buffer(), 0, tokensToCompare[i].length());
|
||||
|
|
|
|||
|
|
@ -33,7 +33,7 @@ public class TestCharArrayIterator extends LuceneTestCase {
|
|||
BreakIterator bi = BreakIterator.getWordInstance(Locale.getDefault());
|
||||
CharArrayIterator ci = CharArrayIterator.newWordInstance();
|
||||
for (int i = 0; i < 10000; i++) {
|
||||
char text[] = TestUtil.randomUnicodeString(random()).toCharArray();
|
||||
char[] text = TestUtil.randomUnicodeString(random()).toCharArray();
|
||||
ci.setText(text, 0, text.length);
|
||||
consume(bi, ci);
|
||||
}
|
||||
|
|
@ -45,7 +45,7 @@ public class TestCharArrayIterator extends LuceneTestCase {
|
|||
BreakIterator bi = BreakIterator.getWordInstance(Locale.getDefault());
|
||||
Segment ci = new Segment();
|
||||
for (int i = 0; i < 10000; i++) {
|
||||
char text[] = _TestUtil.randomUnicodeString(random).toCharArray();
|
||||
char[] text = _TestUtil.randomUnicodeString(random).toCharArray();
|
||||
ci.array = text;
|
||||
ci.offset = 0;
|
||||
ci.count = text.length;
|
||||
|
|
@ -63,7 +63,7 @@ public class TestCharArrayIterator extends LuceneTestCase {
|
|||
BreakIterator bi = BreakIterator.getSentenceInstance(Locale.getDefault());
|
||||
CharArrayIterator ci = CharArrayIterator.newSentenceInstance();
|
||||
for (int i = 0; i < 10000; i++) {
|
||||
char text[] = TestUtil.randomUnicodeString(random()).toCharArray();
|
||||
char[] text = TestUtil.randomUnicodeString(random()).toCharArray();
|
||||
ci.setText(text, 0, text.length);
|
||||
consume(bi, ci);
|
||||
}
|
||||
|
|
@ -75,7 +75,7 @@ public class TestCharArrayIterator extends LuceneTestCase {
|
|||
BreakIterator bi = BreakIterator.getSentenceInstance(Locale.getDefault());
|
||||
Segment ci = new Segment();
|
||||
for (int i = 0; i < 10000; i++) {
|
||||
char text[] = _TestUtil.randomUnicodeString(random).toCharArray();
|
||||
char[] text = _TestUtil.randomUnicodeString(random).toCharArray();
|
||||
ci.array = text;
|
||||
ci.offset = 0;
|
||||
ci.count = text.length;
|
||||
|
|
@ -145,7 +145,7 @@ public class TestCharArrayIterator extends LuceneTestCase {
|
|||
});
|
||||
|
||||
// clone()
|
||||
char text[] = "testing".toCharArray();
|
||||
char[] text = "testing".toCharArray();
|
||||
ci.setText(text, 0, text.length);
|
||||
ci.next();
|
||||
CharArrayIterator ci2 = ci.clone();
|
||||
|
|
|
|||
|
|
@ -116,7 +116,7 @@ public class TestSegmentingTokenizerBase extends BaseTokenStreamTestCase {
|
|||
/** Tests terms which span across boundaries */
|
||||
public void testHugeDoc() throws IOException {
|
||||
StringBuilder sb = new StringBuilder();
|
||||
char whitespace[] = new char[4094];
|
||||
char[] whitespace = new char[4094];
|
||||
Arrays.fill(whitespace, '\n');
|
||||
sb.append(whitespace);
|
||||
sb.append("testing 1234");
|
||||
|
|
@ -131,10 +131,10 @@ public class TestSegmentingTokenizerBase extends BaseTokenStreamTestCase {
|
|||
sb.append('a');
|
||||
}
|
||||
String input = sb.toString();
|
||||
char token[] = new char[1024];
|
||||
char[] token = new char[1024];
|
||||
Arrays.fill(token, 'a');
|
||||
String expectedToken = new String(token);
|
||||
String expected[] = {
|
||||
String[] expected = {
|
||||
expectedToken, expectedToken, expectedToken,
|
||||
expectedToken, expectedToken, expectedToken,
|
||||
expectedToken, expectedToken, expectedToken,
|
||||
|
|
|
|||
|
|
@ -413,7 +413,7 @@ public class TestWikipediaTokenizer extends BaseTokenStreamTestCase {
|
|||
// now check the flags, TODO: add way to check flags from BaseTokenStreamTestCase?
|
||||
tf = new WikipediaTokenizer(newAttributeFactory(), WikipediaTokenizer.BOTH, untoks);
|
||||
tf.setReader(new StringReader(test));
|
||||
int expectedFlags[] =
|
||||
int[] expectedFlags =
|
||||
new int[] {
|
||||
UNTOKENIZED_TOKEN_FLAG,
|
||||
0,
|
||||
|
|
|
|||
|
|
@ -113,7 +113,7 @@ public final class ICUTransformFilter extends TokenFilter {
|
|||
|
||||
/** Wrap a {@link CharTermAttribute} with the Replaceable API. */
|
||||
static final class ReplaceableTermAttribute implements Replaceable {
|
||||
private char buffer[];
|
||||
private char[] buffer;
|
||||
private int length;
|
||||
private CharTermAttribute token;
|
||||
|
||||
|
|
@ -135,7 +135,7 @@ public final class ICUTransformFilter extends TokenFilter {
|
|||
|
||||
@Override
|
||||
public void copy(int start, int limit, int dest) {
|
||||
char text[] = new char[limit - start];
|
||||
char[] text = new char[limit - start];
|
||||
getChars(start, limit, text, 0);
|
||||
replace(dest, dest, text, 0, limit - start);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -30,7 +30,7 @@ import com.ibm.icu.text.UnicodeSet;
|
|||
final class BreakIteratorWrapper {
|
||||
private final CharArrayIterator textIterator = new CharArrayIterator();
|
||||
private final RuleBasedBreakIterator rbbi;
|
||||
private char text[];
|
||||
private char[] text;
|
||||
private int start;
|
||||
private int status;
|
||||
|
||||
|
|
@ -90,7 +90,7 @@ final class BreakIteratorWrapper {
|
|||
return false;
|
||||
}
|
||||
|
||||
void setText(char text[], int start, int length) {
|
||||
void setText(char[] text, int start, int length) {
|
||||
this.text = text;
|
||||
this.start = start;
|
||||
textIterator.setText(text, start, length);
|
||||
|
|
|
|||
|
|
@ -24,7 +24,7 @@ import java.text.CharacterIterator;
|
|||
* @lucene.experimental
|
||||
*/
|
||||
final class CharArrayIterator implements CharacterIterator {
|
||||
private char array[];
|
||||
private char[] array;
|
||||
private int start;
|
||||
private int index;
|
||||
private int length;
|
||||
|
|
@ -49,7 +49,7 @@ final class CharArrayIterator implements CharacterIterator {
|
|||
* @param start offset into buffer
|
||||
* @param length maximum length to examine
|
||||
*/
|
||||
void setText(final char array[], int start, int length) {
|
||||
void setText(final char[] array, int start, int length) {
|
||||
this.array = array;
|
||||
this.start = start;
|
||||
this.index = start;
|
||||
|
|
|
|||
|
|
@ -39,13 +39,13 @@ import com.ibm.icu.text.BreakIterator;
|
|||
*/
|
||||
final class CompositeBreakIterator {
|
||||
private final ICUTokenizerConfig config;
|
||||
private final BreakIteratorWrapper wordBreakers[] =
|
||||
private final BreakIteratorWrapper[] wordBreakers =
|
||||
new BreakIteratorWrapper[1 + UCharacter.getIntPropertyMaxValue(UProperty.SCRIPT)];
|
||||
|
||||
private BreakIteratorWrapper rbbi;
|
||||
private final ScriptIterator scriptIterator;
|
||||
|
||||
private char text[];
|
||||
private char[] text;
|
||||
|
||||
CompositeBreakIterator(ICUTokenizerConfig config) {
|
||||
this.config = config;
|
||||
|
|
@ -111,7 +111,7 @@ final class CompositeBreakIterator {
|
|||
* @param start offset into buffer
|
||||
* @param length maximum length to examine
|
||||
*/
|
||||
void setText(final char text[], int start, int length) {
|
||||
void setText(final char[] text, int start, int length) {
|
||||
this.text = text;
|
||||
scriptIterator.setText(text, start, length);
|
||||
if (scriptIterator.next()) {
|
||||
|
|
|
|||
|
|
@ -39,7 +39,7 @@ import org.apache.lucene.util.AttributeFactory;
|
|||
*/
|
||||
public final class ICUTokenizer extends Tokenizer {
|
||||
private static final int IOBUFFER = 4096;
|
||||
private final char buffer[] = new char[IOBUFFER];
|
||||
private final char[] buffer = new char[IOBUFFER];
|
||||
/** true length of text in the buffer */
|
||||
private int length = 0;
|
||||
/** length in buffer that can be evaluated safely, up to a safe end point */
|
||||
|
|
|
|||
|
|
@ -111,7 +111,7 @@ public class ICUTokenizerFactory extends TokenizerFactory implements ResourceLoa
|
|||
if (tailored.isEmpty()) {
|
||||
config = new DefaultICUTokenizerConfig(cjkAsWords, myanmarAsWords);
|
||||
} else {
|
||||
final BreakIterator breakers[] =
|
||||
final BreakIterator[] breakers =
|
||||
new BreakIterator[1 + UCharacter.getIntPropertyMaxValue(UProperty.SCRIPT)];
|
||||
for (Map.Entry<Integer, String> entry : tailored.entrySet()) {
|
||||
int code = entry.getKey();
|
||||
|
|
|
|||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue