Migrate to PDFBox 3.0.0-RC1

tabulapdf · Sep 5, 2023 · 8fe2837 · 8fe2837
1 parent 8bfa3ad
commit 8fe2837
Show file tree

Hide file tree

Showing 8 changed files with 19 additions and 27 deletions.
diff --git a/pom.xml b/pom.xml
@@ -262,7 +262,7 @@
     <dependency>
         <groupId>org.apache.pdfbox</groupId>
         <artifactId>pdfbox</artifactId>
-        <version>2.0.28</version>
+        <version>3.0.0</version>
     </dependency>
 
     <dependency>

diff --git a/src/main/java/technology/tabula/CommandLineApp.java b/src/main/java/technology/tabula/CommandLineApp.java
@@ -158,7 +158,7 @@ public void extractFileInto(File pdfFile, File outputFile) throws ParseException
     private void extractFile(File pdfFile, Appendable outFile) throws ParseException {
         PDDocument pdfDocument = null;
         try {
-            pdfDocument = this.password == null ? PDDocument.load(pdfFile) : PDDocument.load(pdfFile, this.password);
+            pdfDocument = this.password == null ? org.apache.pdfbox.Loader.loadPDF(pdfFile) : org.apache.pdfbox.Loader.loadPDF(pdfFile, this.password);
             PageIterator pageIterator = getPageIterator(pdfDocument);
             List<Table> tables = new ArrayList<>();
 

diff --git a/src/main/java/technology/tabula/debug/Debug.java b/src/main/java/technology/tabula/debug/Debug.java
@@ -215,7 +215,7 @@ public static void renderPage(String pdfPath, String outPath, int pageNumber, Re
                                   boolean drawColumns, boolean drawCharacters, boolean drawArea, boolean drawCells,
                                   boolean drawUnprocessedRulings, boolean drawProjectionProfile, boolean drawClippingPaths,
                                   boolean drawDetectedTables) throws IOException {
-        PDDocument document = PDDocument.load(new File(pdfPath));
+        PDDocument document = org.apache.pdfbox.Loader.loadPDF(new File(pdfPath));
 
         ObjectExtractor oe = new ObjectExtractor(document);
 
@@ -349,7 +349,7 @@ public static void main(String[] args) throws IOException {
 
             if (pages == null) {
                 // user specified all pages
-                PDDocument document = PDDocument.load(pdfFile);
+                PDDocument document = org.apache.pdfbox.Loader.loadPDF(pdfFile);
 
                 int numPages = document.getNumberOfPages();
                 pages = new ArrayList<>(numPages);

diff --git a/src/main/java/technology/tabula/detectors/NurminenDetectionAlgorithm.java b/src/main/java/technology/tabula/detectors/NurminenDetectionAlgorithm.java
@@ -804,8 +804,7 @@ private List<Ruling> getVerticalRulings(BufferedImage image) {
     private PDDocument removeText(PDPage page) throws IOException {
 
         PDFStreamParser parser = new PDFStreamParser(page);
-        parser.parse();
-        List<Object> tokens = parser.getTokens();
+        List<Object> tokens = parser.parse();
         List<Object> newTokens = new ArrayList<>();
         for (Object token : tokens) {
             if (token instanceof Operator) {

diff --git a/src/test/java/technology/tabula/TestObjectExtractor.java b/src/test/java/technology/tabula/TestObjectExtractor.java
@@ -12,24 +12,17 @@
 
 public class TestObjectExtractor {
 
-    /*@Test(expected=IOException.class)
-    public void testWrongPasswordRaisesException() throws IOException {
-        PDDocument pdf_document = PDDocument.load(new File("src/test/resources/technology/tabula/encrypted.pdf"));
-        ObjectExtractor oe = new ObjectExtractor(pdf_document, "wrongpass"); 
-        oe.extract().next();
-    }*/
-
     @Test(expected = IOException.class)
     public void testEmptyOnEncryptedFileRaisesException() throws IOException {
-        PDDocument pdf_document = PDDocument.load(new File("src/test/resources/technology/tabula/encrypted.pdf"));
+        PDDocument pdf_document = org.apache.pdfbox.Loader.loadPDF(new File("src/test/resources/technology/tabula/encrypted.pdf"));
         try (ObjectExtractor oe = new ObjectExtractor(pdf_document)) {
           oe.extract().next();
         }
     }
 
     @Test
     public void testCanReadPDFWithOwnerEncryption() throws IOException {
-        PDDocument pdf_document = PDDocument.load(new File("src/test/resources/technology/tabula/S2MNCEbirdisland.pdf"));
+        PDDocument pdf_document = org.apache.pdfbox.Loader.loadPDF(new File("src/test/resources/technology/tabula/S2MNCEbirdisland.pdf"));
         try (ObjectExtractor oe = new ObjectExtractor(pdf_document)) {
           PageIterator pi = oe.extract();
           int i = 0;
@@ -44,7 +37,7 @@ public void testCanReadPDFWithOwnerEncryption() throws IOException {
 
     @Test
     public void testGoodPassword() throws IOException {
-        PDDocument pdf_document = PDDocument.load(new File("src/test/resources/technology/tabula/encrypted.pdf"), "userpassword");
+        PDDocument pdf_document = org.apache.pdfbox.Loader.loadPDF(new File("src/test/resources/technology/tabula/encrypted.pdf"), "userpassword");
         try (ObjectExtractor oe = new ObjectExtractor(pdf_document)) {
           List<Page> pages = new ArrayList<>();
           PageIterator pi = oe.extract();
@@ -58,7 +51,7 @@ public void testGoodPassword() throws IOException {
 
     @Test
     public void testTextExtractionDoesNotRaise() throws IOException {
-        PDDocument pdf_document = PDDocument.load(new File("src/test/resources/technology/tabula/rotated_page.pdf"));
+        PDDocument pdf_document = org.apache.pdfbox.Loader.loadPDF(new File("src/test/resources/technology/tabula/rotated_page.pdf"));
         try (ObjectExtractor oe = new ObjectExtractor(pdf_document)) {
           PageIterator pi = oe.extract();
 
@@ -70,7 +63,7 @@ public void testTextExtractionDoesNotRaise() throws IOException {
 
     @Test
     public void testShouldDetectRulings() throws IOException {
-        PDDocument pdf_document = PDDocument.load(new File("src/test/resources/technology/tabula/should_detect_rulings.pdf"));
+        PDDocument pdf_document = org.apache.pdfbox.Loader.loadPDF(new File("src/test/resources/technology/tabula/should_detect_rulings.pdf"));
         try (ObjectExtractor oe = new ObjectExtractor(pdf_document)) {
           PageIterator pi = oe.extract();
 
@@ -85,7 +78,7 @@ public void testShouldDetectRulings() throws IOException {
 
     @Test
     public void testDontThrowNPEInShfill() throws IOException {
-        PDDocument pdf_document = PDDocument.load(new File("src/test/resources/technology/tabula/labor.pdf"));
+        PDDocument pdf_document = org.apache.pdfbox.Loader.loadPDF(new File("src/test/resources/technology/tabula/labor.pdf"));
 
         try (ObjectExtractor oe = new ObjectExtractor(pdf_document)) {
           PageIterator pi = oe.extract();
@@ -101,7 +94,7 @@ public void testDontThrowNPEInShfill() throws IOException {
 
     @Test
     public void testExtractOnePage() throws IOException {
-        PDDocument pdf_document = PDDocument.load(new File("src/test/resources/technology/tabula/S2MNCEbirdisland.pdf"));
+        PDDocument pdf_document = org.apache.pdfbox.Loader.loadPDF(new File("src/test/resources/technology/tabula/S2MNCEbirdisland.pdf"));
         assertEquals(2, pdf_document.getNumberOfPages());
 
         try (ObjectExtractor oe = new ObjectExtractor(pdf_document)) {
@@ -114,7 +107,7 @@ public void testExtractOnePage() throws IOException {
 
     @Test(expected = IndexOutOfBoundsException.class)
     public void testExtractWrongPageNumber() throws IOException {
-        PDDocument pdf_document = PDDocument.load(new File("src/test/resources/technology/tabula/S2MNCEbirdisland.pdf"));
+        PDDocument pdf_document = org.apache.pdfbox.Loader.loadPDF(new File("src/test/resources/technology/tabula/S2MNCEbirdisland.pdf"));
         assertEquals(2, pdf_document.getNumberOfPages());
 
         try (ObjectExtractor oe = new ObjectExtractor(pdf_document)) {
@@ -124,7 +117,7 @@ public void testExtractWrongPageNumber() throws IOException {
 
     @Test
     public void testTextElementsContainedInPage() throws IOException {
-        PDDocument pdf_document = PDDocument.load(new File("src/test/resources/technology/tabula/cs-en-us-pbms.pdf"));
+        PDDocument pdf_document = org.apache.pdfbox.Loader.loadPDF(new File("src/test/resources/technology/tabula/cs-en-us-pbms.pdf"));
 
         try (ObjectExtractor oe = new ObjectExtractor(pdf_document)) {
           Page page = oe.extractPage(1);
@@ -137,7 +130,7 @@ public void testTextElementsContainedInPage() throws IOException {
     }
 
     @Test public void testDoNotNPEInPointComparator() throws IOException {
-        PDDocument pdf_document = PDDocument.load(new File("src/test/resources/technology/tabula/npe_issue_206.pdf"));
+        PDDocument pdf_document = org.apache.pdfbox.Loader.loadPDF(new File("src/test/resources/technology/tabula/npe_issue_206.pdf"));
 
         try (ObjectExtractor oe = new ObjectExtractor(pdf_document)) {
             Page p = oe.extractPage(1);

diff --git a/src/test/java/technology/tabula/TestTableDetection.java b/src/test/java/technology/tabula/TestTableDetection.java
@@ -162,7 +162,7 @@ public void testDetectionOfTables() throws Exception {
         NodeList tables = regionDocument.getElementsByTagName("table");
 
         // tabula extractors
-        PDDocument pdfDocument = PDDocument.load(this.pdf);
+        PDDocument pdfDocument = org.apache.pdfbox.Loader.loadPDF(this.pdf);
         ObjectExtractor extractor = new ObjectExtractor(pdfDocument);
 
         // parse expected tables from the ground truth dataset

diff --git a/src/test/java/technology/tabula/TestUtils.java b/src/test/java/technology/tabula/TestUtils.java
@@ -122,7 +122,7 @@ public void testQuickSortLongList() {
 
     @Test
     public void testJPEG2000DoesNotRaise() throws IOException {
-        PDDocument pdf_document = PDDocument.load(new File("src/test/resources/technology/tabula/jpeg2000.pdf"));
+        PDDocument pdf_document = org.apache.pdfbox.Loader.loadPDF(new File("src/test/resources/technology/tabula/jpeg2000.pdf"));
         PDPage page = pdf_document.getPage(0);
         Utils.pageConvertToImage(pdf_document, page, 360, ImageType.RGB);
     }

diff --git a/src/test/java/technology/tabula/UtilsForTesting.java b/src/test/java/technology/tabula/UtilsForTesting.java
@@ -23,8 +23,8 @@ public static Page getAreaFromPage(String path, int page, float top, float left,
     public static Page getPage(String path, int pageNumber) throws IOException {
         ObjectExtractor oe = null;
         try {
-            PDDocument document = PDDocument
-                    .load(new File(path));
+            PDDocument document = org.apache.pdfbox.Loader
+                    .loadPDF(new File(path));
             oe = new ObjectExtractor(document);
             Page page = oe.extract(pageNumber);
             return page;