Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Use Arrays.compareUnsigned instead of iterating compare in IDVersionSegmentTermsEnum and OrdsSegmentTermsEnum.

This commit is contained in:
zhouhui 2024-09-13 10:51:42 +08:00
parent 3a8f75ccfc
commit 6149b5d94b
2 changed files with 34 additions and 82 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
lucene/codecs/src/java/org/apache/lucene/codecs/blocktreeords/OrdsSegmentTermsEnum.java
View File

@ -18,6 +18,7 @@ package org.apache.lucene.codecs.blocktreeords;
import java.io.IOException;
import java.io.PrintStream;
import java.util.Arrays;
import org.apache.lucene.codecs.BlockTermState;
import org.apache.lucene.codecs.blocktreeords.FSTOrdsOutputs.Output;
import org.apache.lucene.index.BaseTermsEnum;
@ -308,31 +309,18 @@ public final class OrdsSegmentTermsEnum extends BaseTermsEnum {
}
if (cmp == 0) {
final int targetUptoMid = targetUpto;
// Second compare the rest of the term, but
// don't save arc/output/frame; we only do this
// to find out if the target term is before,
// equal or after the current term
final int targetLimit2 = Math.min(target.length, term.length());
while (targetUpto < targetLimit2) {
cmp =
(term.byteAt(targetUpto) & 0xFF) - (target.bytes[target.offset + targetUpto] & 0xFF);
// if (DEBUG) {
// System.out.println(" cycle2 targetUpto=" + targetUpto + " (vs limit=" +
// targetLimit + ") cmp=" + cmp + " (targetLabel=" + (char) (target.bytes[target.offset +
// targetUpto]) + " vs termLabel=" + (char) (term.bytes[targetUpto]) + ")");
// }
if (cmp != 0) {
break;
}
targetUpto++;
}
if (cmp == 0) {
cmp = term.length() - target.length;
}
targetUpto = targetUptoMid;
cmp =
Arrays.compareUnsigned(
term.bytes(),
targetUpto,
term.length(),
target.bytes,
target.offset + targetUpto,
target.offset + target.length);
}
if (cmp < 0) {
@ -600,28 +588,16 @@ public final class OrdsSegmentTermsEnum extends BaseTermsEnum {
}
if (cmp == 0) {
final int targetUptoMid = targetUpto;
// Second compare the rest of the term, but
// don't save arc/output/frame:
final int targetLimit2 = Math.min(target.length, term.length());
while (targetUpto < targetLimit2) {
cmp =
(term.byteAt(targetUpto) & 0xFF) - (target.bytes[target.offset + targetUpto] & 0xFF);
// if (DEBUG) {
// System.out.println(" cycle2 targetUpto=" + targetUpto + " (vs limit=" + targetLimit
// + ") cmp=" + cmp + " (targetLabel=" + (char) (target.bytes[target.offset + targetUpto])
// + " vs termLabel=" + (char) (term.bytes[targetUpto]) + ")");
// }
if (cmp != 0) {
break;
}
targetUpto++;
}
if (cmp == 0) {
cmp = term.length() - target.length;
}
targetUpto = targetUptoMid;
cmp =
Arrays.compareUnsigned(
term.bytes(),
targetUpto,
term.length(),
target.bytes,
target.offset + targetUpto,
target.offset + target.length);
}
if (cmp < 0) {

58
lucene/sandbox/src/java/org/apache/lucene/sandbox/codecs/idversion/IDVersionSegmentTermsEnum.java
View File

@ -18,6 +18,7 @@ package org.apache.lucene.sandbox.codecs.idversion;
import java.io.IOException;
import java.io.PrintStream;
import java.util.Arrays;
import org.apache.lucene.codecs.BlockTermState;
import org.apache.lucene.index.BaseTermsEnum;
import org.apache.lucene.index.ImpactsEnum;
@ -331,31 +332,18 @@ public final class IDVersionSegmentTermsEnum extends BaseTermsEnum {
}
if (cmp == 0) {
final int targetUptoMid = targetUpto;
// Second compare the rest of the term, but
// don't save arc/output/frame; we only do this
// to find out if the target term is before,
// equal or after the current term
final int targetLimit2 = Math.min(target.length, term.length());
while (targetUpto < targetLimit2) {
cmp =
(term.byteAt(targetUpto) & 0xFF) - (target.bytes[target.offset + targetUpto] & 0xFF);
// if (DEBUG) {
// System.out.println(" cycle2 targetUpto=" + targetUpto + " (vs limit=" +
// targetLimit + ") cmp=" + cmp + " (targetLabel=" + (char) (target.bytes[target.offset +
// targetUpto]) + " vs termLabel=" + (char) (term.bytes[targetUpto]) + ")");
// }
if (cmp != 0) {
break;
}
targetUpto++;
}
if (cmp == 0) {
cmp = term.length() - target.length;
}
targetUpto = targetUptoMid;
cmp =
Arrays.compareUnsigned(
term.bytes(),
targetUpto,
term.length(),
target.bytes,
target.offset + targetUpto,
target.offset + target.length);
}
if (cmp < 0) {
@ -718,28 +706,16 @@ public final class IDVersionSegmentTermsEnum extends BaseTermsEnum {
}
if (cmp == 0) {
final int targetUptoMid = targetUpto;
// Second compare the rest of the term, but
// don't save arc/output/frame:
final int targetLimit2 = Math.min(target.length, term.length());
while (targetUpto < targetLimit2) {
cmp =
(term.byteAt(targetUpto) & 0xFF) - (target.bytes[target.offset + targetUpto] & 0xFF);
// if (DEBUG) {
// System.out.println(" cycle2 targetUpto=" + targetUpto + " (vs limit=" + targetLimit
// + ") cmp=" + cmp + " (targetLabel=" + (char) (target.bytes[target.offset + targetUpto])
// + " vs termLabel=" + (char) (term.bytes[targetUpto]) + ")");
// }
if (cmp != 0) {
break;
}
targetUpto++;
}
if (cmp == 0) {
cmp = term.length() - target.length;
}
targetUpto = targetUptoMid;
cmp =
Arrays.compareUnsigned(
term.bytes(),
targetUpto,
term.length(),
target.bytes,
target.offset + targetUpto,
target.offset + target.length);
}
if (cmp < 0) {