Skip to content

Uniform figDesc between sentence segmentation and non-sentence segmentation #1287

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
lfoppiano wants to merge 1 commit into
base: master
Choose a base branch
from
+15 −20
Open

Uniform figDesc between sentence segmentation and non-sentence segmentation #1287

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 8 additions & 10 deletions grobid-core/src/main/java/org/grobid/core/data/Figure.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -385,7 +385,7 @@ public String toTEI(GrobidAnalysisConfig config, Document doc, TEIFormatter form
addXmlId(desc, "_" + divID);
}

// if the segment has been parsed with the full text model we further extract the clusters
// if the segment has been parsed with the full-text model, we further extract the clusters
// to get the bibliographical references
if (StringUtils.isNotBlank(labeledCaption)) {
TaggingTokenClusteror clusteror = new TaggingTokenClusteror(GrobidModels.FULLTEXT, labeledCaption, captionLayoutTokens);
Expand Down Expand Up @@ -432,19 +432,17 @@ public String toTEI(GrobidAnalysisConfig config, Document doc, TEIFormatter form

if (StringUtils.isNotBlank(desc.getValue()) && config.isWithSentenceSegmentation()) {
formatter.segmentIntoSentences(desc, this.captionLayoutTokens, config, doc.getLanguage(), doc.getPDFAnnotations());
}

// we need a sentence segmentation of the figure caption, for that we need to introduce
// a <div>, then a <p>
desc.setLocalName("p");
desc.setLocalName("p");

Element div = XmlBuilderUtils.teiElement("div");
div.appendChild(desc);
Element div = XmlBuilderUtils.teiElement("div");
div.appendChild(desc);

Element figDesc = XmlBuilderUtils.teiElement("figDesc");
figDesc.appendChild(div);
Element figDesc = XmlBuilderUtils.teiElement("figDesc");
figDesc.appendChild(div);

desc = figDesc;
}
desc = figDesc;

figureElement.appendChild(desc);
}
Expand Down
17 changes: 7 additions & 10 deletions grobid-core/src/main/java/org/grobid/core/data/Table.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -150,19 +150,16 @@ public String toTEI(GrobidAnalysisConfig config, Document doc, TEIFormatter form

if (StringUtils.isNotBlank(desc.getValue()) && config.isWithSentenceSegmentation()) {
formatter.segmentIntoSentences(desc, this.captionLayoutTokens, config, doc.getLanguage(), doc.getPDFAnnotations());
}
desc.setLocalName("p");

// we need a sentence segmentation of the table caption, for that we need to introduce
// a <div>, then a <p>
desc.setLocalName("p");

Element div = XmlBuilderUtils.teiElement("div");
div.appendChild(desc);
Element div = XmlBuilderUtils.teiElement("div");
div.appendChild(desc);

Element figDesc = XmlBuilderUtils.teiElement("figDesc");
figDesc.appendChild(div);
Element figDesc = XmlBuilderUtils.teiElement("figDesc");
figDesc.appendChild(div);

desc = figDesc;
}
desc = figDesc;
}
} else {
desc.appendChild(LayoutTokensUtil.normalizeText(caption.toString()).trim());
Expand Down