Skip to content
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

Fix missing coordinates in paragraphs continuation #1076

Merged
merged 2 commits into from
Jan 21, 2024
Merged

Fix missing coordinates in paragraphs continuation #1076

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4d0acef
add missing coordinates when the paragraph continues after a referenc…
lfoppiano Jan 18, 2024
0d7913d
visualise paragraphs or sentences mutually exclusively if the segment…
lfoppiano Jan 18, 2024
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
7 changes: 7 additions & 0 deletions grobid-core/src/main/java/org/grobid/core/document/TEIFormatter.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1488,6 +1488,13 @@ public StringBuilder toTEITextPiece(StringBuilder buffer,

curDiv.appendChild(curParagraph);
curParagraphTokens = new ArrayList<>();
} else {
if (config.isGenerateTeiCoordinates("p")) {
String coords = LayoutTokensUtil.getCoordsString(clusterTokens);
if (curParagraph.getAttribute("coords") != null && !curParagraph.getAttributeValue("coords").contains(coords)) {
curParagraph.addAttribute(new Attribute("coords", curParagraph.getAttributeValue("coords") + ";" + coords));
}
}
}
curParagraph.appendChild(clusterContent);
curParagraphTokens.addAll(clusterTokens);
Expand Down
16 changes: 15 additions & 1 deletion grobid-service/src/main/resources/web/grobid/grobid.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ var grobid = (function($) {

var block = 0;

var elementCoords = ['s', 'biblStruct', 'persName', 'figure', 'formula', 'head', 'note', 'title', 'affiliation'];
var elementCoords = ['p', 's', 'biblStruct', 'persName', 'figure', 'formula', 'head', 'note', 'title', 'affiliation'];

function defineBaseURL(ext) {
var baseUrl = null;
Expand Down Expand Up @@ -239,10 +239,15 @@ var grobid = (function($) {

function ShowRequest1(formData, jqForm, options) {
var addCoordinates = false;
var segmentSentences = false;
for(var formd in formData) {
if (formData[formd].name == 'teiCoordinates') {
addCoordinates = true;
}
if (formData[formd].name == 'segmentSentences') {
segmentSentences = true;
}

}
if (addCoordinates) {
for (var i in elementCoords) {
Expand All @@ -252,6 +257,15 @@ var grobid = (function($) {
"type": "checkbox",
"required": false
}
if (segmentSentences === false) {
if (elementCoords[i] === "s") {
continue;
}
} else {
if (elementCoords[i] === "p") {
continue;
}
}
additionalFormData["value"] = elementCoords[i]
formData.push(additionalFormData)
}
Expand Down
Loading