Update PDFBox to version 3.0.0 (#355)

* WIP update PDFBox to version 3.0.0 * Pass bytes to loader function * Remove unused imports
codeforamerica · Aug 24, 2023 · 161cbe5 · 161cbe5
1 parent 514c28e
commit 161cbe5
Show file tree

Hide file tree

Showing 6 changed files with 77 additions and 74 deletions.
diff --git a/build.gradle b/build.gradle
@@ -79,7 +79,7 @@ dependencies {
     implementation 'org.webjars.npm:dropzone:5.9.3'
     implementation 'com.amazonaws:aws-java-sdk-s3:1.12.364'
     implementation 'com.smartystreets.api:smartystreets-java-sdk:3.14.0'
-    implementation 'org.apache.pdfbox:pdfbox:2.0.29'
+    implementation 'org.apache.pdfbox:pdfbox:3.0.0'
     implementation 'org.yaml:snakeyaml:2.1'
     implementation 'com.mailgun:mailgun-java:1.0.8'
     implementation 'com.google.crypto.tink:tink:1.10.0'

diff --git a/src/main/java/formflow/library/FileController.java b/src/main/java/formflow/library/FileController.java
@@ -21,6 +21,7 @@
 import java.util.zip.ZipEntry;
 import java.util.zip.ZipOutputStream;
 import lombok.extern.slf4j.Slf4j;
+import org.apache.pdfbox.Loader;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.encryption.InvalidPasswordException;
 import org.springframework.beans.factory.annotation.Value;
@@ -120,7 +121,7 @@ public ResponseEntity<?> upload(
 
       String fileExtension = Files.getFileExtension(Objects.requireNonNull(file.getOriginalFilename()));
       if (fileExtension.equals("pdf")) {
-        try (PDDocument ignored = PDDocument.load(file.getInputStream())) {
+        try (PDDocument ignored = Loader.loadPDF(file.getBytes())) {
         } catch (InvalidPasswordException e) {
           // TODO update when we add internationalization to use locale for message source
           String message = messageSource.getMessage("upload-documents.error-password-protected", null, null);

diff --git a/src/main/java/formflow/library/pdf/PDFBoxFieldFiller.java b/src/main/java/formflow/library/pdf/PDFBoxFieldFiller.java
@@ -6,6 +6,7 @@
 import org.apache.pdfbox.pdmodel.interactive.form.PDCheckBox;
 import org.apache.pdfbox.pdmodel.interactive.form.PDField;
 import org.apache.pdfbox.pdmodel.interactive.form.PDTextField;
+import org.apache.pdfbox.Loader;
 import org.jetbrains.annotations.NotNull;
 import org.springframework.core.io.ByteArrayResource;
 import org.springframework.core.io.Resource;
@@ -36,7 +37,7 @@ public PdfFile fill(String pathToPdfResource, Collection<PdfField> fields) {
   @NotNull
   private PDDocument fillOutPdfs(Collection<PdfField> fields, Resource pdfResource) {
     try {
-      PDDocument loadedDoc = PDDocument.load(pdfResource.getInputStream());
+      PDDocument loadedDoc = Loader.loadPDF(pdfResource.getContentAsByteArray());
       PDAcroForm acroForm = loadedDoc.getDocumentCatalog().getAcroForm();
       acroForm.setNeedAppearances(true);
       fillAcroForm(fields, acroForm);

diff --git a/src/main/java/formflow/library/pdf/PdfFile.java b/src/main/java/formflow/library/pdf/PdfFile.java
@@ -1,6 +1,7 @@
 package formflow.library.pdf;
 
 import lombok.extern.slf4j.Slf4j;
+import org.apache.pdfbox.Loader;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.springframework.boot.system.ApplicationTemp;
 
@@ -67,7 +68,7 @@ public byte[] fileBytes() throws IOException {
    * @throws IOException Thrown if the file cannot be read in.
    */
   public void finalizeForSending() throws IOException {
-    PDDocument pdDocument = PDDocument.load(fileBytes());
+    PDDocument pdDocument = Loader.loadPDF(fileBytes());
     pdDocument.getDocumentCatalog().getAcroForm().flatten();
     pdDocument.save(path);
     pdDocument.close();

diff --git a/src/test/java/formflow/library/pdf/PDFBoxFieldFillerTest.java b/src/test/java/formflow/library/pdf/PDFBoxFieldFillerTest.java
@@ -1,5 +1,6 @@
 package formflow.library.pdf;
 
+import org.apache.pdfbox.Loader;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.interactive.form.PDAcroForm;
 import org.junit.jupiter.api.Test;
@@ -13,70 +14,70 @@
 
 class PDFBoxFieldFillerTest {
 
-    private final PDFBoxFieldFiller pdfBoxFieldFiller = new PDFBoxFieldFiller();
-    private final String pdf = "/pdfs/testPdf.pdf";
-
-    @Test
-    void shouldMapAllFieldTypes() throws IOException {
-        String expectedFieldValue = "Michael";
-        String radioValue = "option2";
-        String checkboxSelectedValue = "Yes";
-        String unselectedCheckboxValue = "Off";
-
-        Collection<PdfField> fields = List.of(
-                new PdfField("TEXT_FIELD", expectedFieldValue),
-                new PdfField("RADIO_BUTTON", radioValue),
-                new PdfField("CHECKBOX_OPTION_1", checkboxSelectedValue),
-                new PdfField("CHECKBOX_OPTION_3", checkboxSelectedValue)
-        );
-
-        PdfFile pdfFile = pdfBoxFieldFiller.fill(pdf, fields);
-        PDDocument pdDocument = PDDocument.load(pdfFile.fileBytes());
-        PDAcroForm acroForm = pdDocument.getDocumentCatalog().getAcroForm();
-
-        assertThat(acroForm.getField("TEXT_FIELD").getValueAsString()).isEqualTo(expectedFieldValue);
-        assertThat(acroForm.getField("RADIO_BUTTON").getValueAsString()).isEqualTo(radioValue);
-        assertThat(acroForm.getField("CHECKBOX_OPTION_1").getValueAsString()).isEqualTo(checkboxSelectedValue);
-        assertThat(acroForm.getField("CHECKBOX_OPTION_2").getValueAsString()).isEqualTo(unselectedCheckboxValue);
-        assertThat(acroForm.getField("CHECKBOX_OPTION_3").getValueAsString()).isEqualTo(checkboxSelectedValue);
-
-        pdDocument.close();
-    }
-
-    @Test
-    void shouldSetNullTextFieldsAsEmptyString() throws IOException {
-        Collection<PdfField> fields = List.of(
-                new PdfField("TEXT_FIELD", null)
-        );
-        PdfFile pdfFile = pdfBoxFieldFiller.fill(pdf, fields);
-
-        PDDocument pdDocument = PDDocument.load(pdfFile.fileBytes());
-        assertThat(pdDocument.getDocumentCatalog().getAcroForm().getField("TEXT_FIELD").getValueAsString()).isEqualTo("");
-        pdDocument.close();
-    }
-
-    @Test
-    void shouldNotThrowException_whenFieldIsNotFound() {
-        assertThatCode(() -> pdfBoxFieldFiller.fill(pdf,
-                        List.of(new PdfField("definitely-not-a-field", ""))
-                )
-        ).doesNotThrowAnyException();
-    }
-
-    @Test
-    void shouldSupportEmojis() throws IOException {
-        String submittedValue = "Michael😃";
-        String expectedValue = "Michael😃";
-
-        Collection<PdfField> fields = List.of(
-                new PdfField("TEXT_FIELD", submittedValue)
-        );
-
-        PdfFile pdfFile = pdfBoxFieldFiller.fill(pdf, fields);
-        PDDocument pdDocument = PDDocument.load(pdfFile.fileBytes());
-        PDAcroForm acroForm = pdDocument.getDocumentCatalog().getAcroForm();
-
-        assertThat(acroForm.getField("TEXT_FIELD").getValueAsString()).isEqualTo(expectedValue);
-        pdDocument.close();
-    }
+  private final PDFBoxFieldFiller pdfBoxFieldFiller = new PDFBoxFieldFiller();
+  private final String pdf = "/pdfs/testPdf.pdf";
+
+  @Test
+  void shouldMapAllFieldTypes() throws IOException {
+    String expectedFieldValue = "Michael";
+    String radioValue = "option2";
+    String checkboxSelectedValue = "Yes";
+    String unselectedCheckboxValue = "Off";
+
+    Collection<PdfField> fields = List.of(
+        new PdfField("TEXT_FIELD", expectedFieldValue),
+        new PdfField("RADIO_BUTTON", radioValue),
+        new PdfField("CHECKBOX_OPTION_1", checkboxSelectedValue),
+        new PdfField("CHECKBOX_OPTION_3", checkboxSelectedValue)
+    );
+
+    PdfFile pdfFile = pdfBoxFieldFiller.fill(pdf, fields);
+    PDDocument pdDocument = Loader.loadPDF(pdfFile.fileBytes());
+    PDAcroForm acroForm = pdDocument.getDocumentCatalog().getAcroForm();
+
+    assertThat(acroForm.getField("TEXT_FIELD").getValueAsString()).isEqualTo(expectedFieldValue);
+    assertThat(acroForm.getField("RADIO_BUTTON").getValueAsString()).isEqualTo(radioValue);
+    assertThat(acroForm.getField("CHECKBOX_OPTION_1").getValueAsString()).isEqualTo(checkboxSelectedValue);
+    assertThat(acroForm.getField("CHECKBOX_OPTION_2").getValueAsString()).isEqualTo(unselectedCheckboxValue);
+    assertThat(acroForm.getField("CHECKBOX_OPTION_3").getValueAsString()).isEqualTo(checkboxSelectedValue);
+
+    pdDocument.close();
+  }
+
+  @Test
+  void shouldSetNullTextFieldsAsEmptyString() throws IOException {
+    Collection<PdfField> fields = List.of(
+        new PdfField("TEXT_FIELD", null)
+    );
+    PdfFile pdfFile = pdfBoxFieldFiller.fill(pdf, fields);
+
+    PDDocument pdDocument = Loader.loadPDF(pdfFile.fileBytes());
+    assertThat(pdDocument.getDocumentCatalog().getAcroForm().getField("TEXT_FIELD").getValueAsString()).isEqualTo("");
+    pdDocument.close();
+  }
+
+  @Test
+  void shouldNotThrowException_whenFieldIsNotFound() {
+    assertThatCode(() -> pdfBoxFieldFiller.fill(pdf,
+            List.of(new PdfField("definitely-not-a-field", ""))
+        )
+    ).doesNotThrowAnyException();
+  }
+
+  @Test
+  void shouldSupportEmojis() throws IOException {
+    String submittedValue = "Michael😃";
+    String expectedValue = "Michael😃";
+
+    Collection<PdfField> fields = List.of(
+        new PdfField("TEXT_FIELD", submittedValue)
+    );
+
+    PdfFile pdfFile = pdfBoxFieldFiller.fill(pdf, fields);
+    PDDocument pdDocument = Loader.loadPDF(pdfFile.fileBytes());
+    PDAcroForm acroForm = pdDocument.getDocumentCatalog().getAcroForm();
+
+    assertThat(acroForm.getField("TEXT_FIELD").getValueAsString()).isEqualTo(expectedValue);
+    pdDocument.close();
+  }
 }
diff --git a/src/test/java/formflow/library/pdf/PdfFileTest.java b/src/test/java/formflow/library/pdf/PdfFileTest.java
@@ -1,10 +1,9 @@
 package formflow.library.pdf;
 
-import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.Loader;
 import org.junit.jupiter.api.AfterEach;
 import org.junit.jupiter.api.BeforeEach;
 import org.junit.jupiter.api.Test;
-import org.openqa.selenium.Pdf;
 import org.springframework.boot.system.ApplicationTemp;
 
 import java.io.IOException;
@@ -42,7 +41,7 @@ void finalizeForSendingRemovesFieldsToLockEditingAndPreserveViewCompatibility()
     byte[] originalBytes = tempPdfFile.fileBytes();
     tempPdfFile.finalizeForSending();
 
-    assertThat(PDDocument.load(tempPdfFile.fileBytes()).getDocumentCatalog().getAcroForm().getFields()).isEmpty();
+    assertThat(Loader.loadPDF(tempPdfFile.fileBytes()).getDocumentCatalog().getAcroForm().getFields()).isEmpty();
     assertThat(originalBytes.length).isGreaterThan(tempPdfFile.fileBytes().length);
   }
 
@@ -112,4 +111,4 @@ void createPdfFilesAndEnsureDeletion() throws IOException {
     assertThat(Files.exists(Path.of(twoPdfFile.path()))).isFalse();
     assertThat(Files.exists(Path.of(threePdfFile.path()))).isFalse();
   }
-}
+}