/* ==================================================================== Licensed to the Apache Software Foundation (ASF) under one or more contributor license agreements. See the NOTICE file distributed with this work for additional information regarding copyright ownership. The ASF licenses this file to You under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. ==================================================================== */ package org.apache.poi.hwpf.usermodel; import static org.apache.poi.POIDataSamples.getDocumentInstance; import static org.apache.poi.POITestCase.assertContains; import static org.apache.poi.POITestCase.assertNotContained; import static org.apache.poi.hwpf.HWPFTestDataSamples.openSampleFile; import static org.junit.jupiter.api.Assertions.assertDoesNotThrow; import static org.junit.jupiter.api.Assertions.assertEquals; import static org.junit.jupiter.api.Assertions.assertNotNull; import static org.junit.jupiter.api.Assertions.assertThrows; import static org.junit.jupiter.api.Assertions.assertTrue; import java.io.ByteArrayInputStream; import java.io.ByteArrayOutputStream; import java.io.File; import java.io.IOException; import java.io.InputStream; import java.nio.charset.StandardCharsets; import java.util.Arrays; import java.util.Collection; import java.util.List; import org.apache.commons.codec.digest.DigestUtils; import org.apache.poi.extractor.ExtractorFactory; import org.apache.poi.extractor.POITextExtractor; import org.apache.poi.hwpf.HWPFDocument; import org.apache.poi.hwpf.HWPFOldDocument; import org.apache.poi.hwpf.HWPFTestDataSamples; import org.apache.poi.hwpf.converter.AbstractWordUtils; import org.apache.poi.hwpf.converter.WordToHtmlConverter; import org.apache.poi.hwpf.converter.WordToTextConverter; import org.apache.poi.hwpf.extractor.Word6Extractor; import org.apache.poi.hwpf.extractor.WordExtractor; import org.apache.poi.hwpf.model.FileInformationBlock; import org.apache.poi.hwpf.model.PicturesTable; import org.apache.poi.hwpf.model.SubdocumentType; import org.apache.poi.poifs.filesystem.POIFSFileSystem; import org.apache.poi.util.IOUtils; import org.apache.poi.util.XMLHelper; import org.junit.jupiter.api.Test; import org.junit.jupiter.params.ParameterizedTest; import org.junit.jupiter.params.provider.CsvSource; import org.junit.jupiter.params.provider.ValueSource; import org.w3c.dom.Document; /** * Test different problems reported in the Apache Bugzilla * against HWPF */ class TestBugs { private static void assertEqualsIgnoreNewline(String expected, String actual) { String newExpected = expected.replaceAll("\r\n", "\n") .replaceAll("\r", "\n").trim(); String newActual = actual.replaceAll("\r\n", "\n") .replaceAll("\r", "\n").trim(); assertEquals(newExpected, newActual); } private static void assertTableStructures(Range expected, Range actual) { assertEquals(expected.numParagraphs(), actual.numParagraphs()); for (int p = 0; p < expected.numParagraphs(); p++) { Paragraph expParagraph = expected.getParagraph(p); Paragraph actParagraph = actual.getParagraph(p); assertEqualsIgnoreNewline(expParagraph.text(), actParagraph.text()); assertEquals(expParagraph.isInTable(), actParagraph.isInTable(), "Different isInTable flags for paragraphs #" + p + " -- " + expParagraph + " -- " + actParagraph + "."); assertEquals(expParagraph.isTableRowEnd(), actParagraph.isTableRowEnd()); if (expParagraph.isInTable() && actParagraph.isInTable()) { Table expTable, actTable; try { expTable = expected.getTable(expParagraph); actTable = actual.getTable(actParagraph); } catch (Exception exc) { continue; } assertEquals(expTable.numRows(), actTable.numRows()); assertEquals(expTable.numParagraphs(), actTable.numParagraphs()); } } } private String getText(String sampleFile) throws IOException { HWPFDocument doc = openSampleFile(sampleFile); WordExtractor extractor = new WordExtractor(doc); try { return extractor.getText(); } finally { extractor.close(); doc.close(); } } /** * Bug 34898 - WordExtractor doesn't read the whole string from the file */ @Test void test34898() throws IOException { assertEqualsIgnoreNewline("\u30c7\u30a3\u30ec\u30af\u30c8\u30ea", getText("Bug34898.doc").trim()); } /** * [RESOLVED INVALID] 41898 - Word 2003 pictures cannot be extracted */ @Test void test41898() throws IOException { HWPFDocument doc = openSampleFile("Bug41898.doc"); List pics = doc.getPicturesTable().getAllPictures(); assertNotNull(pics); assertEquals(1, pics.size()); Picture pic = pics.get(0); assertNotNull(pic.suggestFileExtension()); assertNotNull(pic.suggestFullFileName()); assertNotNull(pic.getContent()); assertNotNull(pic.getRawContent()); /* * This is a file with empty EMF image, but present Office Drawing * --sergey */ final Collection officeDrawings = doc .getOfficeDrawingsMain().getOfficeDrawings(); assertNotNull(officeDrawings); assertEquals(1, officeDrawings.size()); OfficeDrawing officeDrawing = officeDrawings.iterator().next(); assertNotNull(officeDrawing); assertEquals(1044, officeDrawing.getShapeId()); doc.close(); } /** * Bug 44331 - HWPFDocument.write destroys fields */ @SuppressWarnings("deprecation") @Test void test44431() throws IOException { HWPFDocument doc1 = openSampleFile("Bug44431.doc"); WordExtractor extractor1 = new WordExtractor(doc1); try { HWPFDocument doc2 = HWPFTestDataSamples.writeOutAndReadBack(doc1); try (WordExtractor extractor2 = new WordExtractor(doc2)) { assertEqualsIgnoreNewline(extractor1.getFooterText(), extractor2.getFooterText()); assertEqualsIgnoreNewline(extractor1.getHeaderText(), extractor2.getHeaderText()); assertEqualsIgnoreNewline(Arrays.toString(extractor1.getParagraphText()), Arrays.toString(extractor2.getParagraphText())); assertEqualsIgnoreNewline(extractor1.getText(), extractor2.getText()); } } finally { extractor1.close(); doc1.close(); } } /** * Bug 44331 - HWPFDocument.write destroys fields */ @Test void test44431_2() throws IOException { assertEqualsIgnoreNewline("File name=FieldsTest.doc\n" + "\n" + "\n" + "STYLEREF test\n" + "\n" + "\n" + "\n" + "TEST TABLE OF CONTENTS\n" + "\n" + "Heading paragraph in next page\t2\n" + "Another heading paragraph in further page\t3\n" + "Another heading paragraph in further page\t3\n" + "\n" + "\n" + "Heading paragraph in next page\n" + "Another heading paragraph in further page\n" + "\n" + "\n" + "\n" + "Page 3 of 3", getText("Bug44431.doc")); } /** * Bug 45473 - HWPF cannot read file after save */ @Test void test45473() throws IOException { // Fetch the current text HWPFDocument doc1 = openSampleFile("Bug45473.doc"); WordExtractor wordExtractor = new WordExtractor(doc1); final String text1; try { text1 = wordExtractor.getText().trim(); } finally { wordExtractor.close(); doc1.close(); } // Re-load, then re-save and re-check doc1 = openSampleFile("Bug45473.doc"); HWPFDocument doc2 = HWPFTestDataSamples.writeOutAndReadBack(doc1); WordExtractor wordExtractor2 = new WordExtractor(doc2); final String text2; try { text2 = wordExtractor2.getText().trim(); } finally { wordExtractor2.close(); doc1.close(); } // the text in the saved document has some differences in line // separators but we tolerate that assertEqualsIgnoreNewline(text1.replaceAll("\n", ""), text2.replaceAll("\n", "")); } /** * Bug 46220 - images are not properly extracted */ @Test void test46220() throws IOException { HWPFDocument doc = openSampleFile("Bug46220.doc"); // reference checksums as in Bugzilla String[] md5 = {"851be142bce6d01848e730cb6903f39e", "7fc6d8fb58b09ababd036d10a0e8c039", "a7dc644c40bc2fbf17b2b62d07f99248", "72d07b8db5fad7099d90bc4c304b4666"}; List pics = doc.getPicturesTable().getAllPictures(); assertEquals(4, pics.size()); for (int i = 0; i < pics.size(); i++) { Picture pic = pics.get(i); byte[] data = pic.getRawContent(); // use Apache Commons Codec utils to compute md5 assertEqualsIgnoreNewline(md5[i], DigestUtils.md5Hex(data)); } doc.close(); } /** * [RESOLVED FIXED] Bug 46817 - Regression: Text from some table cells * missing */ @Test void test46817() throws IOException { String text = getText("Bug46817.doc").trim(); assertContains(text, "Nazwa wykonawcy"); assertContains(text, "kujawsko-pomorskie"); assertContains(text, "ekomel@ekomel.com.pl"); } /** * [FAILING] Bug 47286 - Word documents saves in wrong format if source * contains form elements */ @Test void test47286() throws IOException { // Fetch the current text HWPFDocument doc1 = openSampleFile("Bug47286.doc"); WordExtractor wordExtractor = new WordExtractor(doc1); final String text1; try { text1 = wordExtractor.getText().trim(); } finally { wordExtractor.close(); doc1.close(); } // Re-load, then re-save and re-check doc1 = openSampleFile("Bug47286.doc"); HWPFDocument doc2 = HWPFTestDataSamples.writeOutAndReadBack(doc1); WordExtractor wordExtractor2 = new WordExtractor(doc2); final String text2; try { text2 = wordExtractor2.getText().trim(); } finally { wordExtractor2.close(); doc1.close(); } // the text in the saved document has some differences in line // separators but we tolerate that assertEqualsIgnoreNewline(text1.replaceAll("\n", ""), text2.replaceAll("\n", "")); assertEquals(doc1.getCharacterTable().getTextRuns().size(), doc2 .getCharacterTable().getTextRuns().size()); assertTableStructures(doc1.getRange(), doc2.getRange()); } /** * [RESOLVED FIXED] Bug 47287 - StringIndexOutOfBoundsException in * CharacterRun.replaceText() */ @Test void test47287() throws IOException { try (HWPFDocument doc = openSampleFile("Bug47287.doc")) { String[] values = { "1-1", "1-2", "1-3", "1-4", "1-5", "1-6", "1-7", "1-8", "1-9", "1-10", "1-11", "1-12", "1-13", "1-14", "1-15", }; int usedVal = 0; String PLACEHOLDER = "\u2002\u2002\u2002\u2002\u2002"; Range r = doc.getRange(); for (int x = 0; x < r.numSections(); x++) { Section s = r.getSection(x); for (int y = 0; y < s.numParagraphs(); y++) { Paragraph p = s.getParagraph(y); for (int z = 0; z < p.numCharacterRuns(); z++) { boolean isFound = false; // character run CharacterRun run = p.getCharacterRun(z); // character run text String text = run.text(); String oldText = text; int c = text.indexOf("FORMTEXT "); if (c < 0) { int k = text.indexOf(PLACEHOLDER); if (k >= 0) { text = text.substring(0, k) + values[usedVal] + text.substring(k + PLACEHOLDER.length()); usedVal++; isFound = true; } } else { for (; c >= 0; c = text.indexOf("FORMTEXT ", c + "FORMTEXT ".length())) { int k = text.indexOf(PLACEHOLDER, c); if (k >= 0) { text = text.substring(0, k) + values[usedVal] + text.substring(k + PLACEHOLDER.length()); usedVal++; isFound = true; } } } if (isFound) { run.replaceText(oldText, text, 0); } } } } String docText = r.text(); assertContains(docText, "1-1"); assertContains(docText, "1-12"); assertNotContained(docText, "1-13"); assertNotContained(docText, "1-15"); } } /** * [RESOLVED FIXED] Bug 47731 - Word Extractor considers text copied from * some website as an embedded object */ @Test void test47731() throws Exception { String foundText = getText("Bug47731.doc"); assertContains(foundText, "Soak the rice in water for three to four hours"); } /** * Bug 4774 - text extracted by WordExtractor is broken */ @Test void test47742() throws Exception { // (1) extract text from MS Word document via POI String foundText = getText("Bug47742.doc"); // (2) read text from text document (retrieved by saving the word // document as text file using encoding UTF-8) try (InputStream is = getDocumentInstance() .openResourceAsStream("Bug47742-text.txt")) { byte[] expectedBytes = IOUtils.toByteArray(is); // strip-off the unicode marker String expectedText = new String(expectedBytes, StandardCharsets.UTF_8).substring(1); assertEqualsIgnoreNewline(expectedText, foundText); } } /** * Bug 47958 - Exception during Escher walk of pictures */ @Test void test47958() throws IOException { try (HWPFDocument doc = openSampleFile("Bug47958.doc")) { assertDoesNotThrow(doc.getPicturesTable()::getAllPictures); } } /** * [RESOLVED FIXED] Bug 48065 - Problems with save output of HWPF (losing * formatting) */ @Test void test48065() throws IOException { try (HWPFDocument doc1 = openSampleFile("Bug48065.doc"); HWPFDocument doc2 = HWPFTestDataSamples.writeOutAndReadBack(doc1)) { Range expected = doc1.getRange(); Range actual = doc2.getRange(); assertEqualsIgnoreNewline( expected.text().replace("\r", "\n").replaceAll("\n\n", "\n"), actual.text().replace("\r", "\n").replaceAll("\n\n", "\n")); assertTableStructures(expected, actual); } } @Test void test49933() throws IOException { try (HWPFOldDocument doc = HWPFTestDataSamples.openOldSampleFile("Bug49933.doc"); Word6Extractor extractor = new Word6Extractor(doc)) { assertContains(extractor.getText(), "best.wine.jump.ru"); } } /** * Bug 50936 - Exception parsing MS Word 8.0 file */ @ParameterizedTest @ValueSource(strings = {"Bug50936_1.doc", "Bug50936_2.doc", "Bug50936_3.doc"}) void test50936(String filename) throws Exception { try (HWPFDocument hwpfDocument = openSampleFile(filename)) { assertNotNull(hwpfDocument.getPicturesTable().getAllPictures()); } } /** * [RESOLVED FIXED] Bug 51604 - replace text fails for doc (poi 3.8 beta * release from download site ) */ @Test void test51604() throws IOException { try (HWPFDocument document = openSampleFile("Bug51604.doc")) { Range range = document.getRange(); int numParagraph = range.numParagraphs(); int counter = 0; for (int i = 0; i < numParagraph; i++) { Paragraph paragraph = range.getParagraph(i); int numCharRuns = paragraph.numCharacterRuns(); for (int j = 0; j < numCharRuns; j++) { CharacterRun charRun = paragraph.getCharacterRun(j); String text = charRun.text(); charRun.replaceText(text, "+" + (++counter)); } } try (HWPFDocument document2 = HWPFTestDataSamples.writeOutAndReadBack(document)) { String text = document2.getDocumentText(); assertEqualsIgnoreNewline("+1+2+3+4+5+6+7+8+9+10+11+12", text); } } } /** * [RESOLVED FIXED] Bug 51604 - replace text fails for doc (poi 3.8 beta * release from download site ) */ @Test void test51604p2() { HWPFDocument doc = openSampleFile("Bug51604.doc"); Range range = doc.getRange(); int numParagraph = range.numParagraphs(); replaceText(range, numParagraph); doc = HWPFTestDataSamples.writeOutAndReadBack(doc); final FileInformationBlock fileInformationBlock = doc.getFileInformationBlock(); int totalLength = 0; for (SubdocumentType type : SubdocumentType.values()) { final int partLength = fileInformationBlock.getSubdocumentTextStreamLength(type); assert (partLength >= 0); totalLength += partLength; } assertEquals(doc.getText().length(), totalLength); } private void replaceText(Range range, int numParagraph) { for (int i = 0; i < numParagraph; i++) { Paragraph paragraph = range.getParagraph(i); int numCharRuns = paragraph.numCharacterRuns(); for (int j = 0; j < numCharRuns; j++) { CharacterRun charRun = paragraph.getCharacterRun(j); String text = charRun.text(); if (text.contains("Header")) { charRun.replaceText(text, "added"); } } } } /** * [RESOLVED FIXED] Bug 51604 - replace text fails for doc (poi 3.8 beta * release from download site ) */ @Test void test51604p3() throws Exception { try (HWPFDocument doc = openSampleFile("Bug51604.doc")) { FileInformationBlock fib = doc.getFileInformationBlock(); byte[] originalData = Arrays.copyOfRange(doc.getTableStream(), fib.getFcDop(), fib.getFcDop() + fib.getLcbDop()); ByteArrayOutputStream outputStream = new ByteArrayOutputStream(); doc.getDocProperties().writeTo(outputStream); final byte[] oldData = outputStream.toByteArray(); assertEqualsIgnoreNewline(Arrays.toString(originalData), Arrays.toString(oldData)); Range range = doc.getRange(); int numParagraph = range.numParagraphs(); replaceText(range, numParagraph); try (HWPFDocument doc2 = HWPFTestDataSamples.writeOutAndReadBack(doc)) { outputStream = new ByteArrayOutputStream(); doc2.getDocProperties().writeTo(outputStream); final byte[] newData = outputStream.toByteArray(); assertEqualsIgnoreNewline(Arrays.toString(oldData), Arrays.toString(newData)); } } } /** * [FIXED] Bug 51902 - Picture.fillRawImageContent - * ArrayIndexOutOfBoundsException */ @Test void testBug51890() throws IOException { Object[][] exp = { {0, PictureType.UNKNOWN}, {500, PictureType.PNG}, {2020, PictureType.UNKNOWN}, {2354, PictureType.UNKNOWN}, {3281, PictureType.UNKNOWN}, {4235, PictureType.UNKNOWN}, {5126, PictureType.BMP}, {6923, PictureType.BMP}, }; try (HWPFDocument doc = openSampleFile("Bug51890.doc")) { int idx = 0; for (Picture picture : doc.getPicturesTable().getAllPictures()) { assertEquals(exp[idx][0], picture.getStartOffset()); assertEquals(exp[idx][1], picture.suggestPictureType()); idx++; } } } /** * Bug 51944 - PAPFormattedDiskPage.getPAPX - IndexOutOfBounds */ @Test void testBug51944() throws Exception { HWPFOldDocument doc = HWPFTestDataSamples.openOldSampleFile("Bug51944.doc"); assertNotNull(WordToTextConverter.getText(doc)); } @ParameterizedTest @CsvSource({ // Bug 51834 - Opening and Writing .doc file results in corrupt document // we don't have Java test for this file - it should be checked using // Microsoft BFF Validator. But check read-write-read anyway. -- sergey "Bug51834.doc, true", // Bug 52032 - ArrayIndexOutOfBoundsException with no stack trace (broken after revision 1178063) "Bug52032_1.doc, true", "Bug52032_2.doc, true", "Bug52032_3.doc, true", // Bug 53380 - ArrayIndexOutOfBounds Exception parsing word 97 document "Bug53380_1.doc, true", "Bug53380_2.doc, true", "Bug53380_3.doc, true", "Bug53380_4.doc, true", // Bug 61268 - NegativeArraySizeException parsing word 97 document "Bug61268.doc, false", // Regression tests - testRegressionIn315beta2 "cap.stanford.edu_profiles_viewbiosketch_facultyid=4009&name=m_maciver.doc, true", "ca.kwsymphony.www_education_School_Concert_Seat_Booking_Form_2011-12.doc, true", // Bug 33519 - HWPF fails to read a file "Bug33519.doc, false", // Bug 51671 - HWPFDocument.write based on POIFSFileSystem throws a NullPointerException "empty.doc, true" }) void testBug51834(String file, boolean doReadBack) throws Exception { try (HWPFDocument doc = openSampleFile(file)) { assertNotNull(WordToTextConverter.getText(doc)); if (doReadBack) { try (HWPFDocument doc2 = HWPFTestDataSamples.writeOutAndReadBack(doc)) { assertNotNull(WordToTextConverter.getText(doc2)); } } } } /** * java.lang.UnsupportedOperationException: Non-extended character * Pascal strings are not supported right now *

* Disabled pending a fix for the bug */ @Test void test56880() throws IOException { try (HWPFDocument doc = openSampleFile("56880.doc")) { assertEqualsIgnoreNewline("Check Request", doc.getRange().text()); } } private int section2LeftMargin = 1440; private int section2RightMargin = 1440; private int section2TopMargin = 1440; private int section2BottomMargin = 1440; @Test @SuppressWarnings("SuspiciousNameCombination") void testHWPFSections() { HWPFDocument document = openSampleFile("Bug53453Section.doc"); Range overallRange = document.getOverallRange(); int numParas = overallRange.numParagraphs(); for (int i = 0; i < numParas; i++) { Paragraph para = overallRange.getParagraph(i); int numSections = para.numSections(); for (int j = 0; j < numSections; j++) { Section section = para.getSection(j); if (para.text().trim().equals("Section1")) { assertSection1Margin(section); } else if (para.text().trim().equals("Section2")) { assertSection2Margin(section); // Change the margin widths this.section2BottomMargin = (int) (1.5 * AbstractWordUtils.TWIPS_PER_INCH); this.section2TopMargin = (int) (1.75 * AbstractWordUtils.TWIPS_PER_INCH); this.section2LeftMargin = (int) (0.5 * AbstractWordUtils.TWIPS_PER_INCH); this.section2RightMargin = (int) (0.75 * AbstractWordUtils.TWIPS_PER_INCH); section.setMarginBottom(this.section2BottomMargin); section.setMarginLeft(this.section2LeftMargin); section.setMarginRight(this.section2RightMargin); section.setMarginTop(this.section2TopMargin); } } } // Save away and re-read the document to prove the changes are permanent document = HWPFTestDataSamples.writeOutAndReadBack(document); overallRange = document.getOverallRange(); numParas = overallRange.numParagraphs(); for (int i = 0; i < numParas; i++) { Paragraph para = overallRange.getParagraph(i); int numSections = para.numSections(); for (int j = 0; j < numSections; j++) { Section section = para.getSection(j); if (para.text().trim().equals("Section1")) { // No changes to the margins in Section1 assertSection1Margin(section); } else if (para.text().trim().equals("Section2")) { // The margins in Section2 have kept the new settings. assertSection2Margin(section); } } } } @SuppressWarnings("Duplicates") private void assertSection1Margin(Section section) { int section1BottomMargin = 1440; assertEquals(section1BottomMargin, section.getMarginBottom()); // These are the values the are expected to be read when the file // is checked. int section1LeftMargin = 1440; assertEquals(section1LeftMargin, section.getMarginLeft()); int section1RightMargin = 1440; assertEquals(section1RightMargin, section.getMarginRight()); int section1TopMargin = 1440; assertEquals(section1TopMargin, section.getMarginTop()); int section1NumColumns = 1; assertEquals(section1NumColumns, section.getNumColumns()); } @SuppressWarnings("Duplicates") private void assertSection2Margin(Section section) { assertEquals(section2BottomMargin, section.getMarginBottom()); assertEquals(section2LeftMargin, section.getMarginLeft()); assertEquals(section2RightMargin, section.getMarginRight()); assertEquals(section2TopMargin, section.getMarginTop()); int section2NumColumns = 3; assertEquals(section2NumColumns, section.getNumColumns()); } /** * [RESOLVED FIXED] Bug 57603 - failed to create Word 2003 with seven or more columns */ @Test void test57603SevenRowTable() throws Exception { try (HWPFDocument hwpfDocument = openSampleFile("57603-seven_columns.doc")) { HWPFTestDataSamples.writeOutAndReadBack(hwpfDocument); } } @Test void test57843() throws IOException { File f = getDocumentInstance().getFile("57843.doc"); try (POIFSFileSystem fs = new POIFSFileSystem(f, true); HWPFOldDocument doc = new HWPFOldDocument(fs)) { assertNotNull(doc); } } @Test void test61911() throws IOException { try (HWPFDocument document = openSampleFile("61911.doc")) { PicturesTable picturesTable = document.getPicturesTable(); List pictures = picturesTable.getAllPictures(); assertNotNull(pictures); assertEquals(0, pictures.size()); } } @Test void test61490CellCountInTable() throws Exception { try (HWPFDocument doc = openSampleFile("61490.doc")) { Range range = doc.getRange(); TableIterator tableIter = new TableIterator(range); assertTrue(tableIter.hasNext()); Table table = tableIter.next(); TableRow row = table.getRow(2); assertEquals(3, row.numCells()); for (int cellIdx = 0; cellIdx < row.numCells(); cellIdx++) { TableCell cell = row.getCell(cellIdx); assertEquals("3" + (cellIdx + 1), cell.text().trim()); } } } @Test void test59322() throws Exception { try (HWPFDocument doc = openSampleFile("59322.doc")) { Document document = XMLHelper.newDocumentBuilder().newDocument(); WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(document); wordToHtmlConverter.processDocument(doc); assertNotNull(document); } } @Test void test64132() throws IOException { try (HWPFDocument doc = openSampleFile("64132.doc")) { assertNotNull(doc); PicturesTable picturesTable = doc.getPicturesTable(); List pictures = picturesTable.getAllPictures(); assertNotNull(pictures); } } // @Test void test58805() throws IOException { try (HWPFDocument doc = openSampleFile("header_footer_replace.doc")) { Range oRange = doc.getHeaderStoryRange(); for (int i = 0; i < oRange.numCharacterRuns(); i++) { CharacterRun run = oRange.getCharacterRun(i); run.replaceText("_TEST_", "This text is longer than the initial text. It goes on and on without interruption."); } ByteArrayOutputStream out = new ByteArrayOutputStream(); doc.write(out); out.flush(); POITextExtractor extractor = ExtractorFactory.createExtractor(new ByteArrayInputStream(out.toByteArray())); assertThrows(IllegalArgumentException.class, () -> /*String text =*/ extractor.getText()); // assertFalse(text.contains("_TEST_"), "Had: " + text); } } }