add pdf to bib (#12138)

* add pdf to bib

1. remove double space in unit test
2. fix a logic bug about space.
3. skip the normal space in the title character
4. rename pdf use last name not first name

* fix EqualsAvoidsNull issue

fix EqualsAvoidsNull

* fix unit test issue

fix unit test issue

* remove doi

remove doi

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

@@ -254,6 +254,9 @@ private boolean isUnwantedText(TextPosition previousTextPosition, TextPosition t
             if (textPosition == null || previousTextPosition == null) {
                 return false;
             }
+            if (StringUtil.isBlank(textPosition.getUnicode())) {
+                return true;
+            }
             // The title usually don't in the bottom 10% of a page.
             if ((textPosition.getPageHeight() - textPosition.getYDirAdj())
                     < (textPosition.getPageHeight() * 0.1)) {
@@ -294,11 +297,11 @@ private boolean isLegalTitle(String candidateText) {
         }
 
         private boolean isThereSpace(TextPosition previous, TextPosition current) {
-            float XspaceThreshold = 0.5F;
+            float XspaceThreshold = 1F;
             float YspaceThreshold = previous.getFontSizeInPt();
             float Xgap = current.getXDirAdj() - (previous.getXDirAdj() + previous.getWidthDirAdj());
             float Ygap = current.getYDirAdj() - (previous.getYDirAdj() - previous.getHeightDir());
-            return Xgap > XspaceThreshold || Ygap > YspaceThreshold;
+            return Math.abs(Xgap) > XspaceThreshold || Math.abs(Ygap) > YspaceThreshold;
         }
     }
 

src/test/java/org/jabref/logic/importer/fileformat/PdfContentImporterTest.java

@@ -139,7 +139,7 @@ void pdfTitleExtraction(String expectedTitle, String filePath) throws Exception
 
     private static Stream<Arguments> providePdfData() {
         return Stream.of(
-                Arguments.of("Fundamentals of Distributed Computing:  A Practical Tour of Vector Clock Systems", "/pdfs/PdfContentImporter/Roberto2002.pdf"),
+                Arguments.of("Fundamentals of Distributed Computing: A Practical Tour of Vector Clock Systems", "/pdfs/PdfContentImporter/Baldoni2002.pdf"),
                 Arguments.of("On How We Can Teach – Exploring New Ways in Professional Software Development for Students", "/pdfs/PdfContentImporter/Kriha2018.pdf"),
                 Arguments.of("JabRef Example for Reference Parsing", "/pdfs/IEEE/ieee-paper.pdf"),
                 Arguments.of("Paper Title", "/org/jabref/logic/importer/util/LNCS-minimal.pdf"),

src/test/resources/pdfs/PdfContentImporter/pdfContentImporterTest-pdfs.bib

@@ -126,3 +126,11 @@ @inproceedings{Keim2024TraceLinks
 doi  = {10.1145/3597503.3639130}
 }
 
+@inproceedings{Baldoni2002Fundamentals,
+author = {Roberto Baldoni and Matthias Klusch}
+abstract = {A distributed computation consists of a set of processes that cooperate to achieve a common goal. A main characteristic of these computations is that the processes do not already share a common global memory and that they communicate only by exchanging messages over a communication network. Moreover, message transfer delays are finite yet unpredictable. This computation model defines what is known as the asynchronous distributed system model, which includes systems that span large geographic areas and are subject to unpredictable loads.}
+title = {Fundamentals of Distributed Computing: A Practical Tour of Vector Clock Systems}
+url = {https://www.computer.org/csdl/magazine/ds/2002/02/o2001/13rRUEgs2Q8}
+year = {2002}
+file = {Baldoni2002.pdf}
+}