Skip to content

Commit

Permalink
Implimented arXivId Parsing for PDF with arXivId (#12335)
Browse files Browse the repository at this point in the history 
* Implimented arXivId Parsing forPDF with arXivId

* added Optional parameter

* merged fixes

* removed csl-styles

* fixed null arxiv issue on external imports

* Improved getArxivId Implementation

* reduced nesting and added arxiv constant

* reduced nesting

* modified testcase

* fix abbrev repo

* removed unnecessary 'if' clause

* Use EPRINTTYPE

Co-authored-by: Carl Christian Snethlage <50491877+calixtus@users.noreply.github.com>
Co-authored-by: Christoph <siedlerkiller@gmail.com>
Co-authored-by: Ruslan <ruslanpopov1512@gmail.com>
Co-authored-by: Subhramit Basu Bhowmick <74734844+subhramit@users.noreply.github.com>

* Update src/main/java/org/jabref/logic/importer/fileformat/PdfContentImporter.java

Co-authored-by: Ruslan <ruslanpopov1512@gmail.com>

* WIP

Co-authored-by: Carl Christian Snethlage <50491877+calixtus@users.noreply.github.com>
Co-authored-by: Christoph <siedlerkiller@gmail.com>
Co-authored-by: Ruslan <ruslanpopov1512@gmail.com>
Co-authored-by: Subhramit Basu Bhowmick <74734844+subhramit@users.noreply.github.com>

* Add completion using arXiv ID

Co-authored-by: Carl Christian Snethlage <50491877+calixtus@users.noreply.github.com>
Co-authored-by: Christoph <siedlerkiller@gmail.com>
Co-authored-by: Ruslan <ruslanpopov1512@gmail.com>
Co-authored-by: Subhramit Basu Bhowmick <74734844+subhramit@users.noreply.github.com>

* Adapt test case

Co-authored-by: Carl Christian Snethlage <50491877+calixtus@users.noreply.github.com>
Co-authored-by: Christoph <siedlerkiller@gmail.com>
Co-authored-by: Ruslan <ruslanpopov1512@gmail.com>
Co-authored-by: Subhramit Basu Bhowmick <74734844+subhramit@users.noreply.github.com>

* Fix test name

* "Fix2 number and year extraction for arXiv

---------

Co-authored-by: Siedlerchr <siedlerkiller@gmail.com>
Co-authored-by: Oliver Kopp <kopp.dev@gmail.com>
Co-authored-by: Carl Christian Snethlage <50491877+calixtus@users.noreply.github.com>
Co-authored-by: Ruslan <ruslanpopov1512@gmail.com>
Co-authored-by: Subhramit Basu Bhowmick <74734844+subhramit@users.noreply.github.com>
  • Loading branch information
@ar-rana @Siedlerchr
@koppor @calixtus @InAnYan @subhramit
6 people authored Jan 20, 2025
1 parent add35ab commit 4aa313d
Show file tree
Hide file tree
Showing 4 changed files with 83 additions and 2 deletions.
36 changes: 34 additions & 2 deletions src/main/java/org/jabref/logic/importer/fileformat/PdfContentImporter.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@
import org.jabref.model.entry.BibEntry;
import org.jabref.model.entry.LinkedFile;
import org.jabref.model.entry.field.StandardField;
import org.jabref.model.entry.identifier.ArXivIdentifier;
import org.jabref.model.entry.identifier.DOI;
import org.jabref.model.entry.types.EntryType;
import org.jabref.model.entry.types.StandardEntryType;
Expand Down Expand Up @@ -51,6 +52,8 @@ public class PdfContentImporter extends PdfImporter {

private static final Pattern YEAR_EXTRACT_PATTERN = Pattern.compile("\\d{4}");

private static final int ARXIV_PREFIX_LENGTH = "arxiv:".length();

// input lines into several lines
private String[] lines;

Expand Down Expand Up @@ -372,11 +375,13 @@ Optional<BibEntry> getEntryFromPDFContent(String firstpageContents, String lineS
String volume = null;
String number = null;
String pages = null;
String arXivId = null;
// year is a class variable as the method extractYear() uses it;
String publisher = null;

EntryType type = StandardEntryType.InProceedings;
if (curString.length() > 4) {
arXivId = getArXivId(null);
// special case: possibly conference as first line on the page
extractYear();
doi = getDoi(null);
Expand All @@ -396,6 +401,7 @@ Optional<BibEntry> getEntryFromPDFContent(String firstpageContents, String lineS
}
}

arXivId = getArXivId(arXivId);
// start: title
fillCurStringWithNonEmptyLines();
title = streamlineTitle(curString);
Expand Down Expand Up @@ -515,6 +521,7 @@ Optional<BibEntry> getEntryFromPDFContent(String firstpageContents, String lineS
}
} else {
doi = getDoi(doi);
arXivId = getArXivId(arXivId);

if ((publisher == null) && curString.contains("IEEE")) {
// IEEE has the conference things at the end
Expand All @@ -539,8 +546,7 @@ Optional<BibEntry> getEntryFromPDFContent(String firstpageContents, String lineS
}
}

BibEntry entry = new BibEntry();
entry.setType(type);
BibEntry entry = new BibEntry(type);

// TODO: institution parsing missing

Expand All @@ -565,6 +571,15 @@ Optional<BibEntry> getEntryFromPDFContent(String firstpageContents, String lineS
if (doi != null) {
entry.setField(StandardField.DOI, doi);
}
if (arXivId != null) {
entry.setField(StandardField.EPRINT, arXivId);
assert !arXivId.startsWith("arxiv");
entry.setField(StandardField.EPRINTTYPE, "arXiv");

// Quick workaround to avoid wrong year and number parsing
number = null; // "Germany" in org.jabref.logic.importer.fileformat.PdfContentImporterTest.extractArXivFromPage
year = null; // "2408" in org.jabref.logic.importer.fileformat.PdfContentImporterTest.extractArXivFromPage
}
if (series != null) {
entry.setField(StandardField.SERIES, series);
}
Expand Down Expand Up @@ -600,6 +615,23 @@ private String getDoi(String doi) {
return doi;
}

private String getArXivId(String arXivId) {
if (arXivId != null) {
return arXivId;
}

String arXiv = curString.split(" ")[0];
arXivId = ArXivIdentifier.parse(arXiv).map(ArXivIdentifier::asString).orElse(null);

if (arXivId == null || curString.length() < arXivId.length() + ARXIV_PREFIX_LENGTH) {
return arXivId;
}

proceedToNextNonEmptyLine();

return arXivId;
}

private String getFirstPageContents(PDDocument document) throws IOException {
PDFTextStripper stripper = new PDFTextStripper();

Expand Down
8 changes: 8 additions & 0 deletions src/main/java/org/jabref/logic/importer/fileformat/PdfMergeMetadataImporter.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@
import org.jabref.logic.importer.FetcherException;
import org.jabref.logic.importer.ImportFormatPreferences;
import org.jabref.logic.importer.ParserResult;
import org.jabref.logic.importer.fetcher.ArXivFetcher;
import org.jabref.logic.importer.fetcher.DoiFetcher;
import org.jabref.logic.importer.fetcher.isbntobibtex.IsbnFetcher;
import org.jabref.logic.importer.util.FileFieldParser;
Expand Down Expand Up @@ -108,6 +109,13 @@ public ParserResult importDatabase(Path filePath) throws IOException {
LOGGER.error("Fetching failed for ISBN \"{}\".", candidate.getField(StandardField.ISBN).get(), e);
}
}
if (candidate.hasField(StandardField.EPRINT)) {
try {
new ArXivFetcher(importFormatPreferences).performSearchById(candidate.getField(StandardField.EPRINT).get()).ifPresent(fetchedCandidates::add);
} catch (FetcherException e) {
LOGGER.error("Fetching failed for arXiv ID \"{}\".", candidate.getField(StandardField.EPRINT).get(), e);
}
}
}
candidates.addAll(0, fetchedCandidates);
BibEntry entry = new BibEntry();
Expand Down
3 changes: 3 additions & 0 deletions src/main/java/org/jabref/model/entry/field/StandardField.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -51,9 +51,12 @@ public enum StandardField implements Field {
EDITORCTYPE("editorctype", FieldProperty.EDITOR_TYPE),
EID("eid"),
ENTRYSET("entryset", FieldProperty.MULTIPLE_ENTRY_LINK),

// For the syntax of a "combined" field, see {@link org.jabref.logic.cleanup.EprintCleanupTest.cleanupCompleteEntry} for examples
EPRINT("eprint", FieldProperty.VERBATIM, FieldProperty.IDENTIFIER),
EPRINTCLASS("eprintclass"),
EPRINTTYPE("eprinttype"),

EVENTDATE("eventdate", FieldProperty.DATE),
EVENTTITLE("eventtitle"),
EVENTTITLEADDON("eventtitleaddon"),
Expand Down
38 changes: 38 additions & 0 deletions src/test/java/org/jabref/logic/importer/fileformat/PdfContentImporterTest.java
View file
Original file line number Diff line number Diff line change
Expand Up @@ -129,6 +129,44 @@ British Journal of Nutrition (2008), 99, 1–11 doi: 10.1017/S0007114507795296
assertEquals(Optional.of(entry), importer.getEntryFromPDFContent(firstPageContent, "\n", Optional.empty()));
}

@Test
void extractArXivFromPage() {
BibEntry entry = new BibEntry(StandardEntryType.TechReport)
.withField(StandardField.AUTHOR, "Filippo Riccaa and Alessandro Marchettob and Andrea Stoccoc")
.withField(StandardField.TITLE, "A Multi-Year Grey Literature Review on AI-assisted Test Automation")
.withField(StandardField.EPRINT, "2408.06224v1")
.withField(StandardField.EPRINTTYPE, "arXiv")
.withField((StandardField.KEYWORDS), "Test Automation Artificial Intelligence AI-assisted Test Automation Grey Literature Automated Test Generation Self-Healing Test Scripts");

// This is from https://arxiv.org/abs/2408.06224
String firstPageContent = """
A Multi-Year Grey Literature Review on AI-assisted Test Automation
Filippo Riccaa, Alessandro Marchettob and Andrea Stoccoc
aUniversity of Genoa, Via Balbi 5, Genova, 16126, Italy
bUniversity of Trento, Via Sommarive 9, Trento, 38123, Italy
cTechnical University of Munich, Boltzmannstraße 3, Munich, 85748, Germany
dfortiss GmbH, Guerickestraße 25, Munich, 80805, Germany
Keywords:
Test Automation
Artificial Intelligence
AI-assisted Test Automation
Grey Literature
Automated Test Generation
Self-Healing Test Scripts
*Corresponding author
filippo.ricca@unige.it (F. Ricca)
https://person.dibris.unige.it/ricca-filippo/ (F. Ricca)
ORCID(s): 0000-0002-3928-5408 (F. Ricca); 0000-0002-6833-896X (A. Marchetto); 0000-0001-8956-3894 (A. Stocco)
arXiv:2408.06224v1 [cs.SE] 12 Aug 2024""";

assertEquals(Optional.of(entry), importer.getEntryFromPDFContent(firstPageContent, "\n", Optional.empty()));
}

@ParameterizedTest
@MethodSource("providePdfData")
void pdfTitleExtraction(String expectedTitle, String filePath) throws Exception {
Expand Down

0 comments on commit 4aa313d

Please sign in to comment.