Support StructTreeRoot comparison, fix minor bugs

DEVSIX-8413

Author: Eugene Bochilo

commons/src/main/java/com/itextpdf/commons/utils/Pair.java

@@ -0,0 +1,63 @@
+/*
+    This file is part of the iText (R) project.
+    Copyright (c) 1998-2024 Apryse Group NV
+    Authors: Apryse Software.
+
+    This program is offered under a commercial and under the AGPL license.
+    For commercial licensing, contact us at https://itextpdf.com/sales.  For AGPL licensing, see below.
+
+    AGPL licensing:
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU Affero General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Affero General Public License for more details.
+
+    You should have received a copy of the GNU Affero General Public License
+    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+package com.itextpdf.commons.utils;
+
+/**
+ * Class which represents a pair of key and value.
+ *
+ * @param <K> key parameter type.
+ * @param <V> value parameter type.
+ */
+public class Pair<K, V> {
+    private final K key;
+    private final V value;
+
+    /**
+     * Creates key-value pair.
+     *
+     * @param key key parameter
+     * @param value value parameter
+     */
+    public Pair(K key, V value) {
+        this.key = key;
+        this.value = value;
+    }
+
+    /**
+     * Gets key parameter.
+     *
+     * @return key parameter.
+     */
+    public K getKey() {
+        return key;
+    }
+
+    /**
+     * Gets value parameter.
+     *
+     * @return value parameter.
+     */
+    public V getValue() {
+        return value;
+    }
+}

io/src/main/java/com/itextpdf/io/source/PdfTokenizer.java

@@ -259,7 +259,9 @@ public long getNextEof() throws java.io.IOException {
                 // 6 stands for '%%EOF' length + 1
                 return currentPosition + eofPosition + 6;
             }
-        } while (!str.isEmpty());
+            // Change current position to ensure '%%EOF' is not cut in half.
+            file.seek(file.getPosition() - 4);
+        } while (str.length() > 4);
         throw new IOException(IoExceptionMessageConstant.PDF_EOF_NOT_FOUND, this);
     }
 

io/src/test/java/com/itextpdf/io/source/PdfTokenizerTest.java

@@ -233,6 +233,24 @@ public void getNextEofLongTextTest() throws IOException {
         }
     }
 
+    @Test
+    public void getNextEofWhichIsCutTest() throws IOException {
+        StringBuilder stringBuilder = new StringBuilder();
+        // We append 'a' 124 times because buffer has 128 bytes length.
+        // This way '%%EOF' is cut and first string only contains '%%EO'
+        for (int i = 0; i < 124; ++i) {
+            stringBuilder.append("a");
+        }
+        stringBuilder.append("%%EOF");
+
+        RandomAccessSourceFactory factory = new RandomAccessSourceFactory();
+        try (PdfTokenizer tok = new PdfTokenizer(new RandomAccessFileOrArray(
+                factory.createSource(stringBuilder.toString().getBytes(StandardCharsets.ISO_8859_1))))) {
+            long eofPosition = tok.getNextEof();
+            Assert.assertEquals(124 + 6, eofPosition);
+        }
+    }
+
     @Test
     public void getNextEofSeveralEofTest() throws IOException {
         String data = "some text %%EOFto test \nget%%EOFting end of\n fil%%EOFe logic%%EOF";
@@ -245,6 +263,17 @@ public void getNextEofSeveralEofTest() throws IOException {
         }
     }
 
+    @Test
+    public void getNextEofNoEofTest() throws IOException {
+        String data = "some text to test \ngetting end of\n file logic";
+
+        RandomAccessSourceFactory factory = new RandomAccessSourceFactory();
+        try (PdfTokenizer tok = new PdfTokenizer(new RandomAccessFileOrArray(
+                factory.createSource(data.getBytes(StandardCharsets.ISO_8859_1))))) {
+            Assert.assertThrows(com.itextpdf.io.exceptions.IOException.class, () -> tok.getNextEof());
+        }
+    }
+
     @Test
     public void getDecodedStringContentTest() throws IOException {
         String data = "/Name1 15";

kernel/src/main/java/com/itextpdf/kernel/pdf/PdfArray.java

@@ -29,6 +29,7 @@ This file is part of the iText (R) project.
 
 import java.util.ArrayList;
 import java.util.Collection;
+import java.util.Collections;
 import java.util.Iterator;
 import java.util.List;
 
@@ -325,6 +326,15 @@ public List<PdfObject> subList(int fromIndex, int toIndex) {
         return list.subList(fromIndex, toIndex);
     }
 
+    /**
+     * Returns unmodifiable {@link List} representation of this PdfArray.
+     *
+     * @return unmodifiable {@link List} representation of this PdfArray
+     */
+    public List<PdfObject> toList() {
+        return Collections.unmodifiableList(list);
+    }
+
     @Override
     public byte getType() {
         return ARRAY;
@@ -351,7 +361,7 @@ public PdfObject get(int index, boolean asDirect) {
             return list.get(index);
         else {
             PdfObject obj = list.get(index);
-            if (obj.getType() == INDIRECT_REFERENCE)
+            if (obj != null && obj.getType() == INDIRECT_REFERENCE)
                 return ((PdfIndirectReference) obj).getRefersTo(true);
             else
                 return obj;

kernel/src/test/java/com/itextpdf/kernel/pdf/PdfRevisionsReaderTest.java

@@ -199,7 +199,7 @@ public void documentWithStreamAndTableXref() throws IOException {
 
             DocumentRevision secondRevision = revisionsReader.getAllRevisions().get(1);
             assertResultingRevision(secondRevision, 1, 2, 3, 4, 5, 6, 7, 8);
-            Assert.assertEquals(1550, secondRevision.getEofOffset());
+            Assert.assertEquals(1381, secondRevision.getEofOffset());
 
             DocumentRevision firstRevision = revisionsReader.getAllRevisions().get(2);
             assertResultingRevision(firstRevision);