Home Explore Help
Register Sign In
lqb
/
java-wkhtmltopdf-wrapper
1
0
Fork 0
Files Issues 0 Pull Requests 0 Wiki
Browse Source

fix encoding of special chars, add simple test

Patrick Brueckner 10 years ago
parent
2bd8c29ac8
commit
e43748db90
3 changed files with 51 additions and 2 deletions
Unified View Show Diff Stats
  1. 14 1
      pom.xml
  2. 1 1
      src/main/java/br/eti/mertz/wkhtmltopdf/wrapper/Pdf.java
  3. 36 0
      src/tests/java/br/eti/mertz/wkhtmltopdf/wrapper/PdfTest.java

+ 14 - 1
pom.xml
View File 

@@ -12,6 +12,19 @@
 
 			<version>1.12.6</version>
 
 			<version>1.12.6</version>
 
 		</dependency>
 
 		</dependency>
 
 
 
-	</dependencies>
 
+        <dependency>
 
+            <groupId>junit</groupId>
 
+            <artifactId>junit</artifactId>
 
+            <version>4.11</version>
 
+            <scope>test</scope>
 
+        </dependency>
 
+
 
+        <dependency>
 
+            <groupId>org.apache.pdfbox</groupId>
 
+            <artifactId>pdfbox</artifactId>
 
+            <version>1.8.9</version>
 
+        </dependency>
 
+
 
+    </dependencies>
 
 
 
 </project>
 
 </project>

+ 1 - 1
src/main/java/br/eti/mertz/wkhtmltopdf/wrapper/Pdf.java
View File 

@@ -94,7 +94,7 @@ public class Pdf implements PdfService {
 
         Process process = runtime.exec(command);
 
         Process process = runtime.exec(command);
 
         if(htmlFromString) {
 
         if(htmlFromString) {
 
             OutputStream stdInStream = process.getOutputStream();
 
             OutputStream stdInStream = process.getOutputStream();
 
-            stdInStream.write(htmlInput.getBytes());
 
+            stdInStream.write(htmlInput.getBytes("UTF-8"));
 
             stdInStream.close();
 
             stdInStream.close();
 
         }
 
         }
 
         InputStream stdOutStream = process.getInputStream();
 
         InputStream stdOutStream = process.getInputStream();

+ 36 - 0
src/tests/java/br/eti/mertz/wkhtmltopdf/wrapper/PdfTest.java
View File 

@@ -0,0 +1,36 @@
 
+package br.eti.mertz.wkhtmltopdf.wrapper;
 
+
 
+import org.apache.pdfbox.pdfparser.PDFParser;
 
+import org.apache.pdfbox.pdmodel.PDDocument;
 
+import org.apache.pdfbox.util.PDFTextStripper;
 
+import org.junit.Assert;
 
+import org.junit.Test;
 
+
 
+import java.io.ByteArrayInputStream;
 
+
 
+import static org.hamcrest.core.StringContains.containsString;
 
+
 
+public class PdfTest {
 
+
 
+    @Test
 
+    public void testPdfFromStringTo() throws Exception {
 
+
 
+        // GIVEN a html template containing special characters that java stores in utf-16 internally
 
+        Pdf pdf = new Pdf();
 
+        pdf.addHtmlInput("<html><head><meta charset=\"utf-8\"></head><h1>Müller</h1></html>");
 
+
 
+        // WHEN
 
+        byte[] pdfBytes =  pdf.getPDF();
 
+
 
+        PDFParser parser = new PDFParser(new ByteArrayInputStream(pdfBytes));
 
+
 
+        // that is a valid PDF (otherwise an IOException occurs)
 
+        parser.parse();
 
+        PDFTextStripper pdfTextStripper = new PDFTextStripper();
 
+        String pdfText = pdfTextStripper.getText(new PDDocument(parser.getDocument()));
 
+
 
+        Assert.assertThat("document should contain the creditorName", pdfText, containsString("Müller"));
 
+
 
+
 
+    }
 
+}