You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by kk...@apache.org on 2020/11/05 22:51:57 UTC
[tika] branch main updated: Simplify some sort statement use
List.sort and lambda
This is an automated email from the ASF dual-hosted git repository.
kkrugler pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
The following commit(s) were added to refs/heads/main by this push:
new 53fef89 Simplify some sort statement use List.sort and lambda
new 44c0c83 Merge pull request #376 from PeterAlfredLee/simplifySort
53fef89 is described below
commit 53fef890942bdf69d455abbbecc17cd22d6621d6
Author: PeterAlfredLee <pe...@gmail.com>
AuthorDate: Tue Nov 3 15:57:22 2020 +0800
Simplify some sort statement use List.sort and lambda
---
.../java/org/apache/tika/batch/fs/FSDirectoryCrawler.java | 2 +-
.../main/java/org/apache/tika/language/LanguageProfile.java | 7 +------
.../src/main/java/org/apache/tika/eval/AbstractProfiler.java | 7 +------
.../org/apache/tika/eval/textstats/TextProfileSignature.java | 2 +-
.../main/java/org/apache/tika/example/RollbackSoftware.java | 6 +-----
.../org/apache/tika/parser/apple/AppleSingleFileParser.java | 12 +-----------
.../parser/microsoft/ooxml/xps/XPSPageContentHandler.java | 2 +-
.../tika/parser/recognition/ObjectRecognitionParser.java | 9 +--------
.../java/org/apache/tika/parser/geo/NameEntityExtractor.java | 11 ++---------
.../java/org/apache/tika/server/resource/TikaParsers.java | 6 +-----
.../java/org/apache/tika/server/resource/TikaWelcome.java | 2 +-
11 files changed, 12 insertions(+), 54 deletions(-)
diff --git a/tika-batch/src/main/java/org/apache/tika/batch/fs/FSDirectoryCrawler.java b/tika-batch/src/main/java/org/apache/tika/batch/fs/FSDirectoryCrawler.java
index 5177956..db00132 100644
--- a/tika-batch/src/main/java/org/apache/tika/batch/fs/FSDirectoryCrawler.java
+++ b/tika-batch/src/main/java/org/apache/tika/batch/fs/FSDirectoryCrawler.java
@@ -99,7 +99,7 @@ public class FSDirectoryCrawler extends FileResourceCrawler {
if (crawlOrder == CRAWL_ORDER.RANDOM) {
Collections.shuffle(files);
} else if (crawlOrder == CRAWL_ORDER.SORTED) {
- Collections.sort(files, pathComparator);
+ files.sort(pathComparator);
}
int numFiles = 0;
diff --git a/tika-core/src/main/java/org/apache/tika/language/LanguageProfile.java b/tika-core/src/main/java/org/apache/tika/language/LanguageProfile.java
index 477976f..89c755a 100644
--- a/tika-core/src/main/java/org/apache/tika/language/LanguageProfile.java
+++ b/tika-core/src/main/java/org/apache/tika/language/LanguageProfile.java
@@ -262,12 +262,7 @@ public class LanguageProfile {
private List<Map.Entry<String, Counter>> getSortedNgrams() {
List<Map.Entry<String, Counter>> entries = new ArrayList<Map.Entry<String, Counter>>(ngrams.size());
entries.addAll(ngrams.entrySet());
- Collections.sort(entries, new Comparator<Map.Entry<String, Counter>>() {
- @Override
- public int compare(Map.Entry<String, Counter> o1, Map.Entry<String, Counter> o2) {
- return o1.getKey().compareTo(o2.getKey());
- }
- });
+ entries.sort(Map.Entry.comparingByKey());
return entries;
}
diff --git a/tika-eval/src/main/java/org/apache/tika/eval/AbstractProfiler.java b/tika-eval/src/main/java/org/apache/tika/eval/AbstractProfiler.java
index ed13e45..432543d 100644
--- a/tika-eval/src/main/java/org/apache/tika/eval/AbstractProfiler.java
+++ b/tika-eval/src/main/java/org/apache/tika/eval/AbstractProfiler.java
@@ -568,12 +568,7 @@ public abstract class AbstractProfiler extends FileResourceConsumer {
for (Map.Entry<String, MutableInt> e : blocks.entrySet()) {
pairs.add(Pair.of(e.getKey(), e.getValue().intValue()));
}
- Collections.sort(pairs, new Comparator<Pair<String, Integer>>() {
- @Override
- public int compare(Pair<String, Integer> o1, Pair<String, Integer> o2) {
- return o2.getValue().compareTo(o1.getValue());
- }
- });
+ pairs.sort((o1, o2) -> o2.getValue().compareTo(o1.getValue()));
StringBuilder sb = new StringBuilder();
for (int i = 0; i < 20 && i < pairs.size(); i++) {
diff --git a/tika-eval/src/main/java/org/apache/tika/eval/textstats/TextProfileSignature.java b/tika-eval/src/main/java/org/apache/tika/eval/textstats/TextProfileSignature.java
index 7628e49..c151110 100644
--- a/tika-eval/src/main/java/org/apache/tika/eval/textstats/TextProfileSignature.java
+++ b/tika-eval/src/main/java/org/apache/tika/eval/textstats/TextProfileSignature.java
@@ -74,7 +74,7 @@ public class TextProfileSignature implements TokenCountStatsCalculator<String> {
profile.add(new Token((e.getValue().intValue() / quant) * quant, e.getKey()));
}
}
- Collections.sort(profile, new TokenComparator());
+ profile.sort(new TokenComparator());
StringBuffer newText = new StringBuffer();
int i = 0;
for (Token t : profile) {
diff --git a/tika-example/src/main/java/org/apache/tika/example/RollbackSoftware.java b/tika-example/src/main/java/org/apache/tika/example/RollbackSoftware.java
index 6890b75..fa85561 100755
--- a/tika-example/src/main/java/org/apache/tika/example/RollbackSoftware.java
+++ b/tika-example/src/main/java/org/apache/tika/example/RollbackSoftware.java
@@ -61,11 +61,7 @@ public class RollbackSoftware {
List<Link> links = handler.getLinks();
if (links.size() < 2)
throw new IOException("Must have installed at least 2 versions!");
- Collections.sort(links, new Comparator<Link>() {
- public int compare(Link o1, Link o2) {
- return o1.getText().compareTo(o2.getText());
- }
- });
+ links.sort(Comparator.comparing(Link::getText));
this.updateVersion(links.get(links.size() - 2).getText());
}
diff --git a/tika-parser-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/apple/AppleSingleFileParser.java b/tika-parser-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/apple/AppleSingleFileParser.java
index c1007f2..c7e67d6 100644
--- a/tika-parser-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/apple/AppleSingleFileParser.java
+++ b/tika-parser-modules/tika-parser-apple-module/src/main/java/org/apache/tika/parser/apple/AppleSingleFileParser.java
@@ -160,7 +160,7 @@ public class AppleSingleFileParser extends AbstractParser {
throw new TikaException("AppleSingleFile missing field info");
}
//make absolutely sure these are in order!
- Collections.sort(fieldInfoList, new FieldInfoComparator());
+ fieldInfoList.sort(Comparator.comparingLong(fieldInfo -> fieldInfo.offset));
return fieldInfoList;
}
@@ -189,14 +189,4 @@ public class AppleSingleFileParser extends AbstractParser {
this.length = length;
}
}
-
- private static class FieldInfoComparator implements Comparator<FieldInfo> {
-
- @Override
- public int compare(FieldInfo o1, FieldInfo o2) {
- return (o1.offset > o2.offset) ? 1 :
- (o1.offset == o2.offset) ? 0 : -1 ;
- }
- }
-
}
diff --git a/tika-parser-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSPageContentHandler.java b/tika-parser-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSPageContentHandler.java
index d18825d..25ba69a 100644
--- a/tika-parser-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSPageContentHandler.java
+++ b/tika-parser-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/ooxml/xps/XPSPageContentHandler.java
@@ -319,7 +319,7 @@ class XPSPageContentHandler extends DefaultHandler {
//in most xps files in our test corpus, this is never triggered
//because the runs are already ordered correctly
if (maxY > -1.0f && addedNewRow && glyphRun.originY < maxY) {
- Collections.sort(rows, ROW_SORTER);
+ rows.sort(ROW_SORTER);
}
if (glyphRun.originY > maxY) {
maxY = glyphRun.originY;
diff --git a/tika-parsers-advanced/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/recognition/ObjectRecognitionParser.java b/tika-parsers-advanced/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/recognition/ObjectRecognitionParser.java
index a5a126b..62a3fa6 100644
--- a/tika-parsers-advanced/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/recognition/ObjectRecognitionParser.java
+++ b/tika-parsers-advanced/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/recognition/ObjectRecognitionParser.java
@@ -73,13 +73,6 @@ public class ObjectRecognitionParser extends AbstractParser implements Initializ
public static final String MD_KEY_IMG_CAP = "CAPTION";
public static final String MD_REC_IMPL_KEY =
ObjectRecognitionParser.class.getPackage().getName() + ".object.rec.impl";
- private static final Comparator<RecognisedObject> DESC_CONFIDENCE_SORTER =
- new Comparator<RecognisedObject>() {
- @Override
- public int compare(RecognisedObject o1, RecognisedObject o2) {
- return Double.compare(o2.getConfidence(), o1.getConfidence());
- }
- };
private ObjectRecogniser recogniser;
@@ -126,7 +119,7 @@ public class ObjectRecognitionParser extends AbstractParser implements Initializ
List<String> xhtmlIds = new ArrayList<String>();
String xhtmlStartVal = null;
count = 0;
- Collections.sort(objects, DESC_CONFIDENCE_SORTER);
+ objects.sort((o1, o2) -> Double.compare(o2.getConfidence(), o1.getConfidence()));
// first process all the MD objects
for (RecognisedObject object : objects) {
if (object instanceof CaptionObject) {
diff --git a/tika-parsers-advanced/tika-parser-nlp-module/src/main/java/org/apache/tika/parser/geo/NameEntityExtractor.java b/tika-parsers-advanced/tika-parser-nlp-module/src/main/java/org/apache/tika/parser/geo/NameEntityExtractor.java
index c998e40..85793c6 100644
--- a/tika-parsers-advanced/tika-parser-nlp-module/src/main/java/org/apache/tika/parser/geo/NameEntityExtractor.java
+++ b/tika-parsers-advanced/tika-parser-nlp-module/src/main/java/org/apache/tika/parser/geo/NameEntityExtractor.java
@@ -98,16 +98,9 @@ public class NameEntityExtractor {
tf.put(this.locationNameEntities.get(i), 1);
}
int max = 0;
- List<Map.Entry<String, Integer>> list = new ArrayList<Map.Entry<String, Integer>>(
- tf.entrySet());
+ List<Map.Entry<String, Integer>> list = new ArrayList<>(tf.entrySet());
Collections.shuffle(list);
- Collections.sort(list, new Comparator<Map.Entry<String, Integer>>() {
- public int compare(Map.Entry<String, Integer> o1,
- Map.Entry<String, Integer> o2) {
- // Descending Order
- return o2.getValue().compareTo(o1.getValue());
- }
- });
+ list.sort((o1, o2) -> o2.getValue().compareTo(o1.getValue()));
this.locationNameEntities.clear();// update so that they are in
// descending order
diff --git a/tika-server/src/main/java/org/apache/tika/server/resource/TikaParsers.java b/tika-server/src/main/java/org/apache/tika/server/resource/TikaParsers.java
index 6461cab..1c5dfae 100644
--- a/tika-server/src/main/java/org/apache/tika/server/resource/TikaParsers.java
+++ b/tika-server/src/main/java/org/apache/tika/server/resource/TikaParsers.java
@@ -232,11 +232,7 @@ public class TikaParsers {
((CompositeParser) p).getParsers(EMPTY_PC).values());
// Sort it by class name
childParsers = new ArrayList<Parser>(children);
- Collections.sort(childParsers, new Comparator<Parser>() { @Override
- public int compare(Parser p1, Parser p2) {
- return p1.getClass().getName().compareTo(p2.getClass().getName());
- }
- });
+ childParsers.sort(Comparator.comparing(parser -> parser.getClass().getName()));
} else {
supportedTypes = p.getSupportedTypes(EMPTY_PC);
}
diff --git a/tika-server/src/main/java/org/apache/tika/server/resource/TikaWelcome.java b/tika-server/src/main/java/org/apache/tika/server/resource/TikaWelcome.java
index 3408027..0b4e35f 100644
--- a/tika-server/src/main/java/org/apache/tika/server/resource/TikaWelcome.java
+++ b/tika-server/src/main/java/org/apache/tika/server/resource/TikaWelcome.java
@@ -121,7 +121,7 @@ public class TikaWelcome {
}
}
}
- Collections.sort(found, new Comparator<Endpoint>() {
+ found.sort(new Comparator<Endpoint>() {
@Override
public int compare(Endpoint e1, Endpoint e2) {
int res = e1.path.compareTo(e2.path);