Skip to content

Commit 9c79e45

Browse files
committed
Add draft for html_to_text function #708
1 parent a51ad45 commit 9c79e45

File tree

2 files changed

+9
-0
lines changed

2 files changed

+9
-0
lines changed

metafix/build.gradle

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -18,6 +18,7 @@ dependencies {
1818
implementation "org.eclipse.emf:org.eclipse.emf.ecore:${versions.xtext}" // Workaround for hbz/lobid-resources#1462
1919
implementation "org.eclipse.xtext:org.eclipse.xtext.xbase:${versions.xtext}"
2020
implementation "org.eclipse.xtext:org.eclipse.xtext:${versions.xtext}"
21+
implementation "org.jsoup:jsoup:1.13.1"
2122
implementation "org.slf4j:slf4j-api:${versions.slf4j}"
2223

2324
testImplementation "com.github.tomakehurst:wiremock-jre8:${versions.wiremock}"

metafix/src/main/java/org/metafacture/metafix/FixMethod.java

Lines changed: 8 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -27,6 +27,8 @@
2727
import org.slf4j.Logger;
2828
import org.slf4j.LoggerFactory;
2929

30+
import org.jsoup.Jsoup;
31+
3032
import java.io.File;
3133
import java.io.IOException;
3234
import java.util.Arrays;
@@ -520,6 +522,12 @@ public void apply(final Metafix metafix, final Record record, final List<String>
520522
);
521523
}
522524
},
525+
html_to_text {
526+
@Override
527+
public void apply(final Metafix metafix, final Record record, final List<String> params, final Map<String, String> options) {
528+
record.transform(params.get(0), s -> Jsoup.parse(s).wholeText());
529+
}
530+
},
523531
index {
524532
@Override
525533
public void apply(final Metafix metafix, final Record record, final List<String> params, final Map<String, String> options) {

0 commit comments

Comments
 (0)