You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@pdfbox.apache.org by ti...@apache.org on 2017/10/26 15:23:53 UTC
svn commit: r1813419 -
/pdfbox/trunk/pdfbox/src/test/java/org/apache/pdfbox/pdfparser/TestPDFParser.java
Author: tilman
Date: Thu Oct 26 15:23:53 2017
New Revision: 1813419
URL: http://svn.apache.org/viewvc?rev=1813419&view=rev
Log:
PDFBOX-3974: don't download the test files, these have been downloaded to target/pdfs subdir in previous build phase
Modified:
pdfbox/trunk/pdfbox/src/test/java/org/apache/pdfbox/pdfparser/TestPDFParser.java
Modified: pdfbox/trunk/pdfbox/src/test/java/org/apache/pdfbox/pdfparser/TestPDFParser.java
URL: http://svn.apache.org/viewvc/pdfbox/trunk/pdfbox/src/test/java/org/apache/pdfbox/pdfparser/TestPDFParser.java?rev=1813419&r1=1813418&r2=1813419&view=diff
==============================================================================
--- pdfbox/trunk/pdfbox/src/test/java/org/apache/pdfbox/pdfparser/TestPDFParser.java (original)
+++ pdfbox/trunk/pdfbox/src/test/java/org/apache/pdfbox/pdfparser/TestPDFParser.java Thu Oct 26 15:23:53 2017
@@ -28,13 +28,9 @@ import java.io.File;
import java.io.FileInputStream;
import java.io.FilenameFilter;
import java.io.IOException;
-import java.io.InputStream;
-import java.net.MalformedURLException;
import java.net.URISyntaxException;
-import java.net.URL;
import org.apache.pdfbox.cos.COSDocument;
-import org.apache.pdfbox.io.IOUtils;
import org.apache.pdfbox.io.MemoryUsageSetting;
import org.apache.pdfbox.io.RandomAccessBufferedFileInputStream;
import org.apache.pdfbox.io.RandomAccessRead;
@@ -48,9 +44,9 @@ import org.junit.Test;
public class TestPDFParser
{
-
private static final String PATH_OF_PDF = "src/test/resources/input/yaddatest.pdf";
private static final File tmpDirectory = new File(System.getProperty("java.io.tmpdir"));
+ private static final File TARGETPDFDIR = new File("target/pdfs");
private int numberOfTmpFiles = 0;
@@ -127,27 +123,12 @@ public class TestPDFParser
* file. An incorrect algorithm would result in an outline dictionary being mistaken for an
* /Info.
*
- * @throws MalformedURLException
* @throws IOException
*/
@Test
- public void testPDFBox3208() throws MalformedURLException, IOException
+ public void testPDFBox3208() throws IOException
{
- byte[] byteArray;
- try
- {
- try (InputStream is = new URL("https://issues.apache.org/jira/secure/attachment/12784025/PDFBOX-3208-L33MUTT2SVCWGCS6UIYL5TH3PNPXHIS6.pdf").openStream())
- {
- byteArray = IOUtils.toByteArray(is);
- }
- }
- catch (IOException ex)
- {
- System.err.println("URL loading failed, testPDFBox3208 will be skipped");
- return;
- }
-
- try (PDDocument doc = PDDocument.load(byteArray))
+ try (PDDocument doc = PDDocument.load(new File(TARGETPDFDIR,"PDFBOX-3208-L33MUTT2SVCWGCS6UIYL5TH3PNPXHIS6.pdf")))
{
PDDocumentInformation di = doc.getDocumentInformation();
assertEquals("Liquent Enterprise Services", di.getAuthor());
@@ -165,27 +146,12 @@ public class TestPDFParser
* Test whether the /Info is retrieved correctly when rebuilding the trailer of a corrupt file,
* despite the /Info dictionary not having a modification date.
*
- * @throws MalformedURLException
* @throws IOException
*/
@Test
- public void testPDFBox3940() throws MalformedURLException, IOException
+ public void testPDFBox3940() throws IOException
{
- byte[] byteArray;
- try
- {
- try (InputStream is = new URL("https://issues.apache.org/jira/secure/attachment/12888957/079977.pdf").openStream())
- {
- byteArray = IOUtils.toByteArray(is);
- }
- }
- catch (IOException ex)
- {
- System.err.println("URL loading failed, testPDFBox3940 will be skipped");
- return;
- }
-
- try (PDDocument doc = PDDocument.load(byteArray))
+ try (PDDocument doc = PDDocument.load(new File(TARGETPDFDIR,"PDFBOX-3940-079977.pdf")))
{
PDDocumentInformation di = doc.getDocumentInformation();
assertEquals("Unknown", di.getAuthor());
@@ -201,54 +167,24 @@ public class TestPDFParser
/**
* PDFBOX-3783: test parsing of file with trash after %%EOF.
*
- * @throws MalformedURLException
* @throws IOException
*/
@Test
- public void testPDFBox3783() throws MalformedURLException, IOException
+ public void testPDFBox3783() throws IOException
{
- byte[] byteArray;
- try
- {
- try (InputStream is = new URL("https://issues.apache.org/jira/secure/attachment/12867102/PDFBOX-3783-72GLBIGUC6LB46ELZFBARRJTLN4RBSQM.pdf").openStream())
- {
- byteArray = IOUtils.toByteArray(is);
- }
- }
- catch (IOException ex)
- {
- System.err.println("URL loading failed, testPDFBox3783 will be skipped");
- return;
- }
-
- PDDocument.load(byteArray).close();
+ PDDocument.load(new File(TARGETPDFDIR,"PDFBOX-3783-72GLBIGUC6LB46ELZFBARRJTLN4RBSQM.pdf")).close();
}
/**
* PDFBOX-3785, PDFBOX-3957:
* Test whether truncated file with several revisions has correct page count.
*
- * @throws MalformedURLException
* @throws IOException
*/
@Test
- public void testPDFBox3785() throws MalformedURLException, IOException
+ public void testPDFBox3785() throws IOException
{
- byte[] byteArray;
- try
- {
- try (InputStream is = new URL("https://issues.apache.org/jira/secure/attachment/12867113/202097.pdf").openStream())
- {
- byteArray = IOUtils.toByteArray(is);
- }
- }
- catch (IOException ex)
- {
- System.err.println("URL loading failed, testPDFBox3785 will be skipped");
- return;
- }
-
- try (PDDocument doc = PDDocument.load(byteArray))
+ try (PDDocument doc = PDDocument.load(new File(TARGETPDFDIR,"PDFBOX-3785-202097.pdf")))
{
assertEquals(11, doc.getNumberOfPages());
}
@@ -257,105 +193,45 @@ public class TestPDFParser
/**
* PDFBOX-3947: test parsing of file with broken object stream.
*
- * @throws MalformedURLException
* @throws IOException
*/
@Test
- public void testPDFBox3947() throws MalformedURLException, IOException
+ public void testPDFBox3947() throws IOException
{
- byte[] byteArray;
- try
- {
- try (InputStream is = new URL("https://issues.apache.org/jira/secure/attachment/12890031/670064.pdf").openStream())
- {
- byteArray = IOUtils.toByteArray(is);
- }
- }
- catch (IOException ex)
- {
- System.err.println("URL loading failed, testPDFBox3947 will be skipped");
- return;
- }
-
- PDDocument.load(byteArray).close();
+ PDDocument.load(new File(TARGETPDFDIR, "PDFBOX-3947-670064.pdf")).close();
}
/**
* PDFBOX-3948: test parsing of file with object stream containing some unexpected newlines.
*
- * @throws MalformedURLException
* @throws IOException
*/
@Test
- public void testPDFBox3948() throws MalformedURLException, IOException
+ public void testPDFBox3948() throws IOException
{
- byte[] byteArray;
- try
- {
- try (InputStream is = new URL("https://issues.apache.org/jira/secure/attachment/12890034/EUWO6SQS5TM4VGOMRD3FLXZHU35V2CP2.pdf").openStream())
- {
- byteArray = IOUtils.toByteArray(is);
- }
- }
- catch (IOException ex)
- {
- System.err.println("URL loading failed, testPDFBox3948 will be skipped");
- return;
- }
-
- PDDocument.load(byteArray).close();
+ PDDocument.load(new File(TARGETPDFDIR, "PDFBOX-3948-EUWO6SQS5TM4VGOMRD3FLXZHU35V2CP2.pdf")).close();
}
/**
* PDFBOX-3949: test parsing of file with incomplete object stream.
*
- * @throws MalformedURLException
* @throws IOException
*/
@Test
- public void testPDFBox3949() throws MalformedURLException, IOException
+ public void testPDFBox3949() throws IOException
{
- byte[] byteArray;
- try
- {
- try (InputStream is = new URL("https://issues.apache.org/jira/secure/attachment/12890037/MKFYUGZWS3OPXLLVU2Z4LWCTVA5WNOGF.pdf").openStream())
- {
- byteArray = IOUtils.toByteArray(is);
- }
- }
- catch (IOException ex)
- {
- System.err.println("URL loading failed, testPDFBox3949 will be skipped");
- return;
- }
-
- PDDocument.load(byteArray).close();
+ PDDocument.load(new File(TARGETPDFDIR, "PDFBOX-3949-MKFYUGZWS3OPXLLVU2Z4LWCTVA5WNOGF.pdf")).close();
}
/**
* PDFBOX-3950: test parsing and rendering of truncated file with missing pages.
*
- * @throws MalformedURLException
* @throws IOException
*/
@Test
- public void testPDFBox3950() throws MalformedURLException, IOException
+ public void testPDFBox3950() throws IOException
{
- byte[] byteArray;
- try
- {
- try (InputStream is = new URL("https://issues.apache.org/jira/secure/attachment/12890042/23EGDHXSBBYQLKYOKGZUOVYVNE675PRD.pdf").openStream())
- {
- byteArray = IOUtils.toByteArray(is);
- }
- }
- catch (IOException ex)
- {
- System.err.println("URL loading failed, testPDFBox3950 will be skipped");
- return;
- }
-
- try (PDDocument doc = PDDocument.load(byteArray))
+ try (PDDocument doc = PDDocument.load(new File(TARGETPDFDIR, "PDFBOX-3950-23EGDHXSBBYQLKYOKGZUOVYVNE675PRD.pdf")))
{
assertEquals(4, doc.getNumberOfPages());
PDFRenderer renderer = new PDFRenderer(doc);
@@ -380,27 +256,12 @@ public class TestPDFParser
/**
* PDFBOX-3951: test parsing of truncated file.
*
- * @throws MalformedURLException
* @throws IOException
*/
@Test
- public void testPDFBox3951() throws MalformedURLException, IOException
+ public void testPDFBox3951() throws IOException
{
- byte[] byteArray;
- try
- {
- try (InputStream is = new URL("https://issues.apache.org/jira/secure/attachment/12890047/FIHUZWDDL2VGPOE34N6YHWSIGSH5LVGZ.pdf").openStream())
- {
- byteArray = IOUtils.toByteArray(is);
- }
- }
- catch (IOException ex)
- {
- System.err.println("URL loading failed, testPDFBox3951 will be skipped");
- return;
- }
-
- try (PDDocument doc = PDDocument.load(byteArray))
+ try (PDDocument doc = PDDocument.load(new File(TARGETPDFDIR, "PDFBOX-3951-FIHUZWDDL2VGPOE34N6YHWSIGSH5LVGZ.pdf")))
{
assertEquals(143, doc.getNumberOfPages());
}
@@ -409,27 +270,12 @@ public class TestPDFParser
/**
* PDFBOX-3964: test parsing of broken file.
*
- * @throws MalformedURLException
* @throws IOException
*/
@Test
- public void testPDFBox3964() throws MalformedURLException, IOException
+ public void testPDFBox3964() throws IOException
{
- byte[] byteArray;
- try
- {
- try (InputStream is = new URL("https://issues.apache.org/jira/secure/attachment/12892097/c687766d68ac766be3f02aaec5e0d713_2.pdf").openStream())
- {
- byteArray = IOUtils.toByteArray(is);
- }
- }
- catch (IOException ex)
- {
- System.err.println("URL loading failed, testPDFBox3964 will be skipped");
- return;
- }
-
- try (PDDocument doc = PDDocument.load(byteArray))
+ try (PDDocument doc = PDDocument.load(new File(TARGETPDFDIR, "PDFBOX-3964-c687766d68ac766be3f02aaec5e0d713_2.pdf")))
{
assertEquals(10, doc.getNumberOfPages());
}
@@ -439,27 +285,12 @@ public class TestPDFParser
* Test whether /Info dictionary is retrieved correctly in brute force search for the
* Info/Catalog dictionaries.
*
- * @throws MalformedURLException
* @throws IOException
*/
@Test
- public void testPDFBox3977() throws MalformedURLException, IOException
+ public void testPDFBox3977() throws IOException
{
- byte[] byteArray;
- try
- {
- try (InputStream is = new URL("https://issues.apache.org/jira/secure/attachment/12893582/63NGFQRI44HQNPIPEJH5W2TBM6DJZWMI.pdf").openStream())
- {
- byteArray = IOUtils.toByteArray(is);
- }
- }
- catch (IOException ex)
- {
- System.err.println("URL loading failed, testPDFBox3977 will be skipped");
- return;
- }
-
- try (PDDocument doc = PDDocument.load(byteArray))
+ try (PDDocument doc = PDDocument.load(new File(TARGETPDFDIR,"PDFBOX-3977-63NGFQRI44HQNPIPEJH5W2TBM6DJZWMI.pdf")))
{
PDDocumentInformation di = doc.getDocumentInformation();
assertEquals("QuarkXPress(tm) 6.52", di.getCreator());
@@ -473,26 +304,12 @@ public class TestPDFParser
/**
* Test parsing the "genko_oc_shiryo1.pdf" file, which is susceptible to regression.
*
- * @throws Exception
+ * @throws IOException
*/
@Test
- public void testParseGenko() throws Exception
+ public void testParseGenko() throws IOException
{
- byte[] byteArray;
- try
- {
- try (InputStream is = new URL("https://issues.apache.org/jira/secure/attachment/12867433/genko_oc_shiryo1.pdf").openStream())
- {
- byteArray = IOUtils.toByteArray(is);
- }
- }
- catch (IOException ex)
- {
- System.err.println("URL loading failed, testParseGenko will be skipped");
- return;
- }
-
- PDDocument.load(byteArray).close();
+ PDDocument.load(new File(TARGETPDFDIR, "genko_oc_shiryo1.pdf")).close();
}
private void executeParserTest(RandomAccessRead source, MemoryUsageSetting memUsageSetting) throws IOException