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

LUCENE-1540: Improvements to contrib.benchmark for TREC collections - bring back case insensitivity to path names using Locale.ENGLISH - port/merged from 3x r1067705. 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1067772 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Doron Cohen 2011-02-06 21:25:53 +00:00
parent ece1524805
commit 5ab6a5e7dd
1 changed files with 4 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
modules/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/TrecDocParser.java
View File

@ -20,6 +20,7 @@ package org.apache.lucene.benchmark.byTask.feeds;
import java.io.File; import java.io.File;
import java.io.IOException; import java.io.IOException;
import java.util.HashMap; import java.util.HashMap;
import java.util.Locale;
import java.util.Map; import java.util.Map;
/** /**
@ -29,12 +30,7 @@ import java.util.Map;
public abstract class TrecDocParser { public abstract class TrecDocParser {
/** Types of trec parse paths, */ /** Types of trec parse paths, */
public enum ParsePathType { GOV2("gov2"), FBIS("fbis"), FT("ft"), FR94("fr94"), LATIMES("latimes"); public enum ParsePathType { GOV2, FBIS, FT, FR94, LATIMES }
public final String dirName;
private ParsePathType(String dirName) {
this.dirName = dirName;
}
}
/** trec parser type used for unknown extensions */ /** trec parser type used for unknown extensions */
public static final ParsePathType DEFAULT_PATH_TYPE = ParsePathType.GOV2; public static final ParsePathType DEFAULT_PATH_TYPE = ParsePathType.GOV2;
@ -51,7 +47,7 @@ public abstract class TrecDocParser {
static final Map<String,ParsePathType> pathName2Type = new HashMap<String,ParsePathType>(); static final Map<String,ParsePathType> pathName2Type = new HashMap<String,ParsePathType>();
static { static {
for (ParsePathType ppt : ParsePathType.values()) { for (ParsePathType ppt : ParsePathType.values()) {
pathName2Type.put(ppt.dirName,ppt); pathName2Type.put(ppt.name().toUpperCase(Locale.ENGLISH),ppt);
} }
} }
@ -64,7 +60,7 @@ public abstract class TrecDocParser {
public static ParsePathType pathType(File f) { public static ParsePathType pathType(File f) {
int pathLength = 0; int pathLength = 0;
while (f != null && ++pathLength < MAX_PATH_LENGTH) { while (f != null && ++pathLength < MAX_PATH_LENGTH) {
ParsePathType ppt = pathName2Type.get(f.getName()); ParsePathType ppt = pathName2Type.get(f.getName().toUpperCase(Locale.ENGLISH));
if (ppt!=null) { if (ppt!=null) {
return ppt; return ppt;
} }