Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(2043)

Unified Diff: boilerpipe-core/src/main/de/l3s/boilerpipe/filters/heuristics/BlockProximityFusion.java

Issue 290993004: Fix final content and title extraction. (Closed) Base URL: https://code.google.com/p/dom-distiller/@master
Patch Set: Created 6 years, 7 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View side-by-side diff with in-line comments
Download patch
« no previous file with comments | « no previous file | src/com/dom_distiller/client/ContentExtractor.java » ('j') | no next file with comments »
Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
Index: boilerpipe-core/src/main/de/l3s/boilerpipe/filters/heuristics/BlockProximityFusion.java
diff --git a/boilerpipe-core/src/main/de/l3s/boilerpipe/filters/heuristics/BlockProximityFusion.java b/boilerpipe-core/src/main/de/l3s/boilerpipe/filters/heuristics/BlockProximityFusion.java
index 510c47fc6e913aeab31aec5cfe61d2412e920988..8399b5b92f1d2ce09ed9310b5ad0af8115a69749 100644
--- a/boilerpipe-core/src/main/de/l3s/boilerpipe/filters/heuristics/BlockProximityFusion.java
+++ b/boilerpipe-core/src/main/de/l3s/boilerpipe/filters/heuristics/BlockProximityFusion.java
@@ -17,18 +17,19 @@
*/
package de.l3s.boilerpipe.filters.heuristics;
-import java.util.Iterator;
-import java.util.List;
-
import de.l3s.boilerpipe.BoilerpipeFilter;
import de.l3s.boilerpipe.BoilerpipeProcessingException;
import de.l3s.boilerpipe.document.TextBlock;
import de.l3s.boilerpipe.document.TextDocument;
+import de.l3s.boilerpipe.labels.DefaultLabels;
+
+import java.util.Iterator;
+import java.util.List;
/**
* Fuses adjacent blocks if their distance (in blocks) does not exceed a certain limit.
* This probably makes sense only in cases where an upstream filter already has removed some blocks.
- *
+ *
* @author Christian Kohlschütter
*/
public final class BlockProximityFusion implements BoilerpipeFilter {
@@ -52,7 +53,7 @@ public final class BlockProximityFusion implements BoilerpipeFilter {
* Creates a new {@link BlockProximityFusion} instance.
*
* @param maxBlocksDistance The maximum distance in blocks.
- * @param contentOnly
+ * @param contentOnly
*/
public BlockProximityFusion(final int maxBlocksDistance,
final boolean contentOnly, final boolean sameTagLevelOnly) {
@@ -61,6 +62,7 @@ public final class BlockProximityFusion implements BoilerpipeFilter {
this.sameTagLevelOnly = sameTagLevelOnly;
}
+ @Override
public boolean process(TextDocument doc)
throws BoilerpipeProcessingException {
List<TextBlock> textBlocks = doc.getTextBlocks();
@@ -110,6 +112,9 @@ public final class BlockProximityFusion implements BoilerpipeFilter {
if(ok && sameTagLevelOnly && prevBlock.getTagLevel() != block.getTagLevel()) {
ok = false;
}
+ if (prevBlock.hasLabel(DefaultLabels.TITLE) != block.hasLabel(DefaultLabels.TITLE)) {
+ ok = false;
+ }
if (ok) {
prevBlock.mergeNext(block);
it.remove();
« no previous file with comments | « no previous file | src/com/dom_distiller/client/ContentExtractor.java » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld 408576698