Dependencies:
- Guava > 19
- PDFBox > 2.0
- A helper class which wraps IOException in a RuntimeException
Last active
January 25, 2017 09:32
-
-
Save digulla/641e045016763085e04ea617f4a195df to your computer and use it in GitHub Desktop.
Support code to write unit tests that validate PDF documents
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import java.awt.geom.Rectangle2D; | |
| import org.apache.pdfbox.text.PDFTextStripperByArea; | |
| public class PageRegion { | |
| private String name; | |
| private Rectangle2D rect; | |
| // Coordinates are in the order in which the Apache PDF-Box Debugger displays them | |
| public PageRegion(String name, double y1, double x1, double y2, double x2) { | |
| this.name = name; | |
| double x = Math.min(x1, x2); | |
| double y = Math.min(y1, y2); | |
| double width = Math.abs(x1 - x2) + 1; | |
| double height = Math.abs(y1 - y2) + 1; | |
| this.rect = new Rectangle2D.Double(x, y, width, height); | |
| } | |
| public String getName() { | |
| return name; | |
| } | |
| public void addTo(PDFTextStripperByArea stripper) { | |
| stripper.addRegion(name, rect); | |
| } | |
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import static org.junit.Assert.assertEquals; | |
| import java.io.File; | |
| import java.io.IOException; | |
| import java.util.ArrayList; | |
| import java.util.List; | |
| import java.util.stream.Collectors; | |
| import org.apache.pdfbox.pdmodel.PDDocument; | |
| import org.apache.pdfbox.text.PDFTextStripper; | |
| import org.apache.pdfbox.text.PDFTextStripperByArea; | |
| import com.google.common.base.Preconditions; | |
| import tools.RuntimeIOException; | |
| public class ReportTextExtractor { | |
| private PDDocument document; | |
| private File file; | |
| public ReportTextExtractor(File file) { | |
| this.file = file; | |
| try { | |
| document = PDDocument.load(file); | |
| } catch (IOException e) { | |
| throw new RuntimeIOException("Error loading " + file.getAbsolutePath(), e); | |
| } | |
| } | |
| private PDFTextStripperByArea byAreaStripper; | |
| protected PDFTextStripperByArea createByAreaStripper() { | |
| PDFTextStripperByArea result; | |
| try { | |
| result = new PDFTextStripperByArea(); | |
| } catch (IOException e) { | |
| throw new RuntimeIOException(e); | |
| } | |
| result.setAddMoreFormatting(true); | |
| result.setSortByPosition(true); | |
| return result; | |
| } | |
| public ReportTextExtractor addRegion(PageRegion region) { | |
| if (byAreaStripper == null) { | |
| byAreaStripper = createByAreaStripper(); | |
| } | |
| region.addTo(byAreaStripper); | |
| return this; | |
| } | |
| private boolean processed = false; | |
| private int page = 0; | |
| public String getText(PageRegion region) { | |
| if (byAreaStripper == null) { | |
| throw new IllegalStateException("Add some region, first!"); | |
| } | |
| Preconditions.checkArgument(byAreaStripper.getRegions().contains(region.getName()), | |
| "Unknown region [%s]; valid names are: %s", region.getName(), byAreaStripper.getRegions()); | |
| if (!processed) { | |
| try { | |
| byAreaStripper.extractRegions(document.getPage(page)); | |
| } catch (IOException e) { | |
| throw new RuntimeIOException("Error processing page " + page, e); | |
| } | |
| processed = true; | |
| } | |
| String result = byAreaStripper.getTextForRegion(region.getName()); | |
| result = postProcess(result); | |
| return result; | |
| } | |
| /** Get all the text of the document at once */ | |
| public static String getText(File file) { | |
| return new ReportTextExtractor(file).getText(); | |
| } | |
| public String getText() { | |
| PDFTextStripper stripper; | |
| try { | |
| stripper = new PDFTextStripper(); | |
| } catch (IOException e) { | |
| throw new RuntimeIOException(e); | |
| } | |
| stripper.setAddMoreFormatting(true); | |
| stripper.setSortByPosition(true); | |
| try { | |
| String result = stripper.getText(document); | |
| result = postProcess(result); | |
| return result; | |
| } catch (IOException e) { | |
| throw new RuntimeIOException("Error getting text from " + file.getAbsolutePath(), e); | |
| } finally { | |
| close(); | |
| } | |
| } | |
| protected String postProcess(String result) { | |
| return result.trim() | |
| .replace("\r\n", "\n"); | |
| } | |
| public void mustContain(PageRegion region, String... fragments) { | |
| String text = getText(region); | |
| mustContain(text, fragments); | |
| } | |
| public void mustContain(String text, String... fragments) { | |
| List<String> missing = new ArrayList<>(); | |
| for(String fragment: fragments) { | |
| if (!text.contains(fragment)) { | |
| missing.add(fragment); | |
| } | |
| } | |
| if (!missing.isEmpty()) { | |
| String expected = missing.stream() | |
| .collect(Collectors.joining("\n---\n")); | |
| assertEquals(expected, text); | |
| } | |
| } | |
| public void close() { | |
| if (document != null) { | |
| try { | |
| document.close(); | |
| } catch (IOException e) { | |
| throw new RuntimeIOException(e); | |
| } | |
| document = null; | |
| } | |
| } | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment