Skip to content

Adding in a demo test.. There is some debugging as well #291

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
epugh wants to merge 8 commits into from
+56 −0
Closed

Adding in a demo test.. There is some debugging as well #291

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
e8ba769
Adding in a demo test.. There is some debugging as well
epugh Oct 20, 2019
9e3bb49
confirm Tesseract ran
epugh Oct 21, 2019
2e3a60d
remove debugging lines
epugh Oct 21, 2019
ccb8abe
bool not boolean
epugh Oct 21, 2019
d61ab39
if we have a TesseractOCRConfig, then populate context so the PDFPars…
epugh Oct 21, 2019
239c92a
use small PDF to drastically speed up test
epugh Oct 21, 2019
f50546e
unwind hard coded change
epugh Oct 21, 2019
19c6a85
clean method, and add better todo
epugh Oct 21, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 21 additions & 0 deletions tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,7 @@
import java.util.Enumeration;
import java.util.HashMap;
import java.util.HashSet;
import java.util.Iterator;
import java.util.List;
import java.util.Locale;
import java.util.Map;
Expand Down Expand Up @@ -98,6 +99,8 @@
import org.apache.tika.parser.PasswordProvider;
import org.apache.tika.parser.RecursiveParserWrapper;
import org.apache.tika.parser.html.BoilerpipeContentHandler;
import org.apache.tika.parser.ocr.TesseractOCRConfig;
import org.apache.tika.parser.ocr.TesseractOCRParser;
import org.apache.tika.parser.pdf.PDFParserConfig;
import org.apache.tika.parser.utils.CommonsDigester;
import org.apache.tika.sax.BasicContentHandlerFactory;
Expand Down Expand Up @@ -193,6 +196,23 @@ private void extractInlineImagesFromPDFs() {
context.set(PDFParserConfig.class, pdfParserConfig);
}
}

private void enableOCRPDF() throws TikaException, IOException, SAXException {

configure();

CompositeParser parser = (CompositeParser)config.getParser();
Iterator<Parser> iter = parser.getAllComponentParsers().iterator();
while(iter.hasNext()) {
Parser p = iter.next();
if (p instanceof TesseractOCRParser) {
TesseractOCRConfig tesseractOCRConfig = ((TesseractOCRParser) p).getDefaultConfig();
context.set(TesseractOCRConfig.class, tesseractOCRConfig);
// TODO Should we mimic the warn from extractInlineImagesFromPDFs?
}
}

}

private class OutputType {
public void process(
Expand Down Expand Up @@ -452,6 +472,7 @@ public void process(String arg) throws Exception {
extractDir = new File(dirPath);
} else if (arg.equals("-z") || arg.equals("--extract")) {
extractInlineImagesFromPDFs();
enableOCRPDF();
type = NO_OUTPUT;
context.set(EmbeddedDocumentExtractor.class, new FileEmbeddedDocumentExtractor());
} else if (arg.equals("-r") || arg.equals("--pretty-print")) {
Expand Down
12 changes: 12 additions & 0 deletions tika-app/src/test/java/org/apache/tika/cli/TikaCLITest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -470,6 +470,18 @@ public void testConfig() throws Exception {
assertTrue(content.contains("apple"));
assertTrue(content.contains("org.apache.tika.parser.html.HtmlParser"));
}

@Test
public void testModifyAndRunTesseractViaConfig() throws Exception {
String[] params = new String[]{"--config="+testDataFile.toString()+"/tika-config-ocr-pdf.xml", "--jsonRecursive","--extract","--pretty-print","-v","-x", resourcePrefix+"testPDF_bom.pdf"};
TikaCLI.main(params);
String content = outContent.toString(UTF_8.name());
assertTrue(content.contains("org.apache.tika.parser.ocr.TesseractOCRParser"));
assertTrue(content.contains("Hello"));
assertTrue(content.contains("bbox"));
assertTrue(content.contains("ocr_line"));

}

@Test
public void testConfigIgnoreInit() throws Exception {
Expand Down
Binary file added tika-app/src/test/resources/test-data/testPDF_bom.pdf
View file
Open in desktop
Binary file not shown.
23 changes: 23 additions & 0 deletions tika-app/src/test/resources/test-data/tika-config-ocr-pdf.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<properties>
<parsers>
<parser class="org.apache.tika.parser.DefaultParser">
<parser-exclude class="org.apache.tika.parser.ocr.TesseractOCRParser"/>
<parser-exclude class="org.apache.tika.parser.pdf.PDFParser"/>
</parser>
<parser class="org.apache.tika.parser.ocr.TesseractOCRParser">
<params>
<param name="tesseractPath" type="string">/usr/local/bin/</param>
<param name="tessdataPath" type="string">/usr/local/Cellar/tesseract/4.1.0/share/tessdata</param>
<param name="outputType" type="string">hocr</param>
</params>
</parser>
<parser class="org.apache.tika.parser.pdf.PDFParser">
<params>
<param name="ocrStrategy" type="string">ocr_only</param>
<param name="extractInlineImages" type="bool">true</param>
</params>
</parser>

</parsers>
</properties>