Author: lehmi
Date: Thu Oct 26 06:01:14 2023
New Revision: 1913337
URL: http://svn.apache.org/viewvc?rev=1913337&view=rev
Log:
PDFBOX-5670: allow repeatable subcommands based on a proposal by Marcelo Modesto
Added:
pdfbox/trunk/tools/src/test/resources/org/apache/pdfbox/hello3.pdf (with
props)
Modified:
pdfbox/trunk/tools/src/main/java/org/apache/pdfbox/tools/ExtractText.java
pdfbox/trunk/tools/src/main/java/org/apache/pdfbox/tools/PDFBox.java
pdfbox/trunk/tools/src/test/java/org/apache/pdfbox/tools/TestExtractText.java
Modified:
pdfbox/trunk/tools/src/main/java/org/apache/pdfbox/tools/ExtractText.java
URL:
http://svn.apache.org/viewvc/pdfbox/trunk/tools/src/main/java/org/apache/pdfbox/tools/ExtractText.java?rev=1913337&r1=1913336&r2=1913337&view=diff
==============================================================================
--- pdfbox/trunk/tools/src/main/java/org/apache/pdfbox/tools/ExtractText.java
(original)
+++ pdfbox/trunk/tools/src/main/java/org/apache/pdfbox/tools/ExtractText.java
Thu Oct 26 06:01:14 2023
@@ -21,6 +21,7 @@ import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.PrintStream;
+import java.io.PrintWriter;
import java.io.Writer;
import java.util.Map;
import java.util.Set;
@@ -112,6 +113,12 @@ public final class ExtractText implemen
@Option(names = {"-o", "--output"}, description = "the exported text file")
private File outfile;
+ @Option(names = "-addFileName", description = "Print PDF file name to the
output text")
+ private boolean addFileName = false;
+
+ @Option(names = "-append", description = "Use append mode for output file")
+ private boolean append = false;
+
/**
* Constructor.
*/
@@ -150,8 +157,19 @@ public final class ExtractText implemen
outfile = new File(outPath);
}
+ if (toHTML && !STD_ENCODING.equals(encoding))
+ {
+ encoding = STD_ENCODING;
+ SYSOUT.println("The encoding parameter is ignored when writing
html output.");
+ }
+
+ if (toConsole && encoding != null)
+ {
+ SYSOUT.println("The encoding parameter is ignored when writing to
the console.");
+ }
+
try (PDDocument document = Loader.loadPDF(infile, password);
- Writer output = toConsole ? new OutputStreamWriter( SYSOUT,
encoding ) : new OutputStreamWriter( new FileOutputStream( outfile ), encoding
))
+ Writer output = createOutputWriter())
{
long startTime = startProcessing("Loading PDF " + infile);
@@ -164,14 +182,14 @@ public final class ExtractText implemen
stopProcessing("Time for loading: ", startTime);
- if (toHTML && !STD_ENCODING.equals(encoding))
+ startTime = startProcessing("Starting text extraction");
+
+ if (addFileName)
{
- encoding = STD_ENCODING;
- SYSOUT.println("The encoding parameter is ignored when writing
html output.");
+ output.write("PDF file: " + infile);
+ output.write(System.getProperty("line.separator"));
}
- startTime = startProcessing("Starting text extraction");
-
if (debug)
{
SYSERR.println("Writing to " + outfile.getAbsolutePath());
@@ -252,6 +270,7 @@ public final class ExtractText implemen
}
}
}
+ output.flush();
stopProcessing("Time for extraction: ", startTime);
}
catch (IOException ioe)
@@ -263,6 +282,25 @@ public final class ExtractText implemen
return 0;
}
+ private Writer createOutputWriter() throws IOException
+ {
+ if (toConsole)
+ {
+ return new PrintWriter(SYSOUT)
+ {
+ @Override
+ public void close()
+ {
+ // don't close the console
+ };
+ };
+ }
+ else
+ {
+ return new OutputStreamWriter(new FileOutputStream(outfile,
append), encoding);
+ }
+ }
+
private void extractPages(int startPage, int endPage,
PDFTextStripper stripper, PDDocument document, Writer output,
boolean rotationMagic, boolean alwaysNext) throws IOException
Modified: pdfbox/trunk/tools/src/main/java/org/apache/pdfbox/tools/PDFBox.java
URL:
http://svn.apache.org/viewvc/pdfbox/trunk/tools/src/main/java/org/apache/pdfbox/tools/PDFBox.java?rev=1913337&r1=1913336&r2=1913337&view=diff
==============================================================================
--- pdfbox/trunk/tools/src/main/java/org/apache/pdfbox/tools/PDFBox.java
(original)
+++ pdfbox/trunk/tools/src/main/java/org/apache/pdfbox/tools/PDFBox.java Thu
Oct 26 06:01:14 2023
@@ -30,11 +30,10 @@ import picocli.CommandLine.Spec;
* Used as the main class in the runnable standalone PDFBox jar.
*/
@Command(name="pdfbox",
- customSynopsis = "pdfbox [COMMAND] [OPTIONS]",
- footer = {
- "See 'pdfbox help <command>' to read about a specific subcommand"
- },
- versionProvider = Version.class)
+ subcommandsRepeatable = true,
+ customSynopsis = "pdfbox [COMMAND] [OPTIONS]",
+ footer = { "See 'pdfbox help <command>' to read about a specific
subcommand" },
+ versionProvider = Version.class)
public final class PDFBox implements Runnable
{
@Spec CommandLine.Model.CommandSpec spec;
Modified:
pdfbox/trunk/tools/src/test/java/org/apache/pdfbox/tools/TestExtractText.java
URL:
http://svn.apache.org/viewvc/pdfbox/trunk/tools/src/test/java/org/apache/pdfbox/tools/TestExtractText.java?rev=1913337&r1=1913336&r2=1913337&view=diff
==============================================================================
---
pdfbox/trunk/tools/src/test/java/org/apache/pdfbox/tools/TestExtractText.java
(original)
+++
pdfbox/trunk/tools/src/test/java/org/apache/pdfbox/tools/TestExtractText.java
Thu Oct 26 06:01:14 2023
@@ -18,11 +18,20 @@ package org.apache.pdfbox.tools;
import static org.junit.jupiter.api.Assertions.assertEquals;
import static org.junit.jupiter.api.Assertions.assertTrue;
+import static org.junit.jupiter.api.Assertions.assertFalse;
import java.io.ByteArrayOutputStream;
import java.io.PrintStream;
+import java.io.UnsupportedEncodingException;
+import java.nio.file.Path;
+import java.nio.file.Files;
+import java.nio.file.Paths;
+import java.nio.file.InvalidPathException;
import org.junit.jupiter.api.Test;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.io.TempDir;
import picocli.CommandLine;
@@ -32,6 +41,36 @@ import picocli.CommandLine;
*/
class TestExtractText
{
+
+ final PrintStream originalOut = System.out;
+ final ByteArrayOutputStream out = new ByteArrayOutputStream();
+ PrintStream printStream = null;
+
+ @BeforeEach
+ public void setUpStreams()
+ {
+ out.reset();
+ try
+ {
+ printStream = new PrintStream(out, true, "utf-8");
+ System.setOut(printStream);
+ }
+ catch (UnsupportedEncodingException e)
+ {
+ // shouldn't happen at all
+ e.printStackTrace();
+ }
+ }
+
+ @AfterEach
+ public void restoreStreams()
+ {
+ System.setOut(originalOut);
+ if (printStream != null)
+ {
+ printStream.close();
+ }
+ }
/**
* Run the text extraction test using a pdf with embedded pdfs.
@@ -41,25 +80,177 @@ class TestExtractText
@Test
void testEmbeddedPDFs() throws Exception
{
- ByteArrayOutputStream outBytes = new ByteArrayOutputStream();
- PrintStream stdout = System.out;
- System.setOut(new PrintStream(outBytes));
+ ExtractText app = new ExtractText();
+ CommandLine cmd = new CommandLine(app);
+ int exitCode = cmd.execute("-i",
"src/test/resources/org/apache/pdfbox/testPDFPackage.pdf",
+ "-console");
+ assertEquals(0, exitCode);
+
+ String result = out.toString("UTF-8");
+ assertTrue(result.contains("PDF1"));
+ assertTrue(result.contains("PDF2"));
+ assertFalse(result
+ .contains("PDF file:
src/test/resources/org/apache/pdfbox/testPDFPackage.pdf"));
+ assertFalse(result.contains("Hello"));
+ assertFalse(result.contains("World."));
+ assertFalse(result.contains("PDF file:
src/test/resources/org/apache/pdfbox/hello3.pdf"));
+ }
+
+ /**
+ * Run the text extraction with -addFileName
+ *
+ * @throws Exception if something went wrong
+ */
+ @Test
+ void testAddFileName() throws Exception
+ {
+ ExtractText app = new ExtractText();
+ CommandLine cmd = new CommandLine(app);
+ int exitCode = cmd.execute("-i",
"src/test/resources/org/apache/pdfbox/testPDFPackage.pdf",
+ "-console", "-addFileName");
+ assertEquals(0, exitCode);
+
+ String result = out.toString("UTF-8");
+ assertTrue(result.contains("PDF1"));
+ assertTrue(result.contains("PDF2"));
+ assertTrue(result
+ .contains("PDF file:
src/test/resources/org/apache/pdfbox/testPDFPackage.pdf"));
+ assertFalse(result.contains("Hello"));
+ assertFalse(result.contains("World."));
+ assertFalse(result.contains("PDF file:
src/test/resources/org/apache/pdfbox/hello3.pdf"));
+ }
+
+ /**
+ * Run the text extraction as a PDFBox repeatable subcommand
+ *
+ * @throws Exception if something went wrong
+ */
+ @Test
+ void testPDFBoxRepeatableSubcommand() throws Exception
+ {
+ // Please, copy from pdfbox/src/test/resources/input/hello3.pdf
+
assertTrue(Files.exists(Paths.get("src/test/resources/org/apache/pdfbox/hello3.pdf")));
+
+ PDFBox.main(new String[] { "export:text", "-i",
+ "src/test/resources/org/apache/pdfbox/testPDFPackage.pdf",
"-console",
+ "export:text", "-i",
"src/test/resources/org/apache/pdfbox/hello3.pdf",
+ "-console" });
+
+ String result = out.toString("UTF-8");
+ assertTrue(result.contains("PDF1"));
+ assertTrue(result.contains("PDF2"));
+ assertFalse(result
+ .contains("PDF file:
src/test/resources/org/apache/pdfbox/testPDFPackage.pdf"));
+ assertTrue(result.contains("Hello"));
+ assertTrue(result.contains("World."));
+ assertFalse(result.contains("PDF file:
src/test/resources/org/apache/pdfbox/hello3.pdf"));
+ }
+
+ /**
+ * Run the text extraction as a PDFBox repeatable subcommand with
-addFileName
+ *
+ * @throws Exception if something went wrong
+ */
+ @Test
+ void testPDFBoxRepeatableSubcommandAddFileName() throws Exception
+ {
+
assertTrue(Files.exists(Paths.get("src/test/resources/org/apache/pdfbox/hello3.pdf")));
+
+ PDFBox.main(new String[] { "export:text", "-i",
+ "src/test/resources/org/apache/pdfbox/testPDFPackage.pdf",
"-console",
+ "-addFileName", "export:text", "-i",
+ "src/test/resources/org/apache/pdfbox/hello3.pdf", "-console",
"-addFileName" });
+
+ String result = out.toString("UTF-8");
+ assertTrue(result.contains("PDF1"));
+ assertTrue(result.contains("PDF2"));
+ assertTrue(result
+ .contains("PDF file:
src/test/resources/org/apache/pdfbox/testPDFPackage.pdf"));
+ assertTrue(result.contains("Hello"));
+ assertTrue(result.contains("World."));
+ assertTrue(result.contains("PDF file:
src/test/resources/org/apache/pdfbox/hello3.pdf"));
+ }
+
+ /**
+ * Run the text extraction as a PDFBox repeatable subcommand with
-addFileName, with -o <outfile> and without
+ * -append
+ *
+ * @throws Exception if something went wrong
+ */
+ @Test
+ void testPDFBoxRepeatableSubcommandAddFileNameOutfile(@TempDir Path
tempDir) throws Exception
+ {
+
assertTrue(Files.exists(Paths.get("src/test/resources/org/apache/pdfbox/hello3.pdf")));
+
+ Path path = null;
+
+ try
+ {
+ path = tempDir.resolve("outfile.txt");
+ Files.deleteIfExists(path);
+ }
+ catch (InvalidPathException ipe)
+ {
+ System.err.println(
+ "Error creating temporary test file in " +
this.getClass().getSimpleName());
+ }
+ assertFalse(path == null);
+
+ PDFBox.main(new String[] { "export:text", "-i",
+ "src/test/resources/org/apache/pdfbox/testPDFPackage.pdf",
"-encoding", "UTF-8",
+ "-addFileName", "-o", path.toString(), "export:text", "-o",
path.toString(), "-i",
+ "src/test/resources/org/apache/pdfbox/hello3.pdf",
"-encoding", "UTF-8",
+ "-addFileName" });
+
+ String result = new String(Files.readAllBytes(path), "UTF-8");
+ assertFalse(result.contains("PDF1"));
+ assertFalse(result.contains("PDF2"));
+ assertFalse(result
+ .contains("PDF file:
src/test/resources/org/apache/pdfbox/testPDFPackage.pdf"));
+ assertTrue(result.contains("Hello"));
+ assertTrue(result.contains("World."));
+ assertTrue(result.contains("PDF file:
src/test/resources/org/apache/pdfbox/hello3.pdf"));
+ }
+
+ /**
+ * Run the text extraction as a PDFBox repeatable subcommand with
-addFileName, -o <outfile> and -append
+ *
+ * @throws Exception if something went wrong
+ */
+ @Test
+ void testPDFBoxRepeatableSubcommandAddFileNameOutfileAppend(@TempDir Path
tempDir)
+ throws Exception
+ {
+
assertTrue(Files.exists(Paths.get("src/test/resources/org/apache/pdfbox/hello3.pdf")));
+
+ Path path = null;
+
try
{
- ExtractText app = new ExtractText();
- CommandLine cmd = new CommandLine(app);
- int exitCode = cmd.execute("-i",
"src/test/resources/org/apache/pdfbox/testPDFPackage.pdf",
- "-console", "-encoding", "UTF-8");
- assertEquals(0, exitCode);
- }
- finally
+ path = tempDir.resolve("outfile.txt");
+ Files.deleteIfExists(path);
+ }
+ catch (InvalidPathException ipe)
{
- // Restore stdout
- System.setOut(stdout);
+ System.err.println(
+ "Error creating temporary test file in " +
this.getClass().getSimpleName());
}
+ assertFalse(path == null);
- String result = outBytes.toString("UTF-8");
+ PDFBox.main(new String[] { "export:text", "-i",
+ "src/test/resources/org/apache/pdfbox/testPDFPackage.pdf",
"-encoding", "UTF-8",
+ "-addFileName", "-o", path.toString(), "export:text", "-i",
+ "src/test/resources/org/apache/pdfbox/hello3.pdf",
"-encoding", "UTF-8",
+ "-addFileName", "-o", path.toString(), "-append" });
+
+ String result = new String(Files.readAllBytes(path), "UTF-8");
assertTrue(result.contains("PDF1"));
assertTrue(result.contains("PDF2"));
+ assertTrue(result
+ .contains("PDF file:
src/test/resources/org/apache/pdfbox/testPDFPackage.pdf"));
+ assertTrue(result.contains("Hello"));
+ assertTrue(result.contains("World."));
+ assertTrue(result.contains("PDF file:
src/test/resources/org/apache/pdfbox/hello3.pdf"));
}
+
}
Added: pdfbox/trunk/tools/src/test/resources/org/apache/pdfbox/hello3.pdf
URL:
http://svn.apache.org/viewvc/pdfbox/trunk/tools/src/test/resources/org/apache/pdfbox/hello3.pdf?rev=1913337&view=auto
==============================================================================
Binary file - no diff available.
Propchange: pdfbox/trunk/tools/src/test/resources/org/apache/pdfbox/hello3.pdf
------------------------------------------------------------------------------
svn:mime-type = application/pdf
