Update dependencies and bump version to 1.0.4

pom.xml

@@ -5,7 +5,7 @@
 
 	<groupId>io.committed.krill</groupId>
 	<artifactId>krill</artifactId>
-	<version>1.0.3</version>
+	<version>1.0.4</version>
 	<name>krill</name>
 	<description>Uses Apache Tika (https://tika.apache.org/) and PDFBox (https://pdfbox.apache.org/) with subsequent post processing to generate a HTML representation of a document (PDF, CSV, XLS, etc) together with it metadata.</description>
 	<url>http://github.com/commitd/krill</url>
@@ -44,19 +44,19 @@
 		<java.version>1.8</java.version>
 		<dependency.locations.enabled>false</dependency.locations.enabled>
 
-		<commons-io.version>2.5</commons-io.version>
+		<commons-io.version>2.6</commons-io.version>
 		<commons-csv.version>1.5</commons-csv.version>
-		<slf4j.version>1.7.19</slf4j.version>
-		<tika.version>1.16</tika.version>
-		<jbig2-imageio.version>3.0.0</jbig2-imageio.version>
-		<guava.version>23.0</guava.version>
-		<jsoup.version>1.10.3</jsoup.version>
+		<slf4j.version>1.7.25</slf4j.version>
+		<tika.version>1.18</tika.version>
+		<jbig2-imageio.version>3.0.1</jbig2-imageio.version>
+		<guava.version>25.1-jre</guava.version>
+		<jsoup.version>1.11.3</jsoup.version>
 
-		<assertj.version>3.8.0</assertj.version>
+		<assertj.version>3.10.0</assertj.version>
 		<junit.version>4.12</junit.version>
 		<!-- there is something odd with versioning of the expected-failure plugin -->
 		<junit.expected-failure.version>0.0.9</junit.expected-failure.version>
-		<mockito.version>1.10.19</mockito.version>
+		<mockito.version>2.19.0</mockito.version>
 
 		<maven.compiler.plugin.version>2.3.2</maven.compiler.plugin.version>
 		<maven.checkstyle.plugin.version>2.17</maven.checkstyle.plugin.version>
@@ -151,7 +151,7 @@
 
 		<dependency>
 			<groupId>org.mockito</groupId>
-			<artifactId>mockito-all</artifactId>
+			<artifactId>mockito-core</artifactId>
 			<version>${mockito.version}</version>
 			<scope>test</scope>
 		</dependency>

src/main/java/io/committed/krill/extraction/tika/TikaFormatExtractor.java

@@ -9,6 +9,7 @@
 import java.util.Set;
 
 import org.apache.tika.exception.TikaException;
+import org.apache.tika.exception.ZeroByteFileException;
 import org.apache.tika.metadata.Metadata;
 import org.apache.tika.metadata.TikaMetadataKeys;
 import org.apache.tika.mime.MediaType;
@@ -153,6 +154,8 @@ public Extraction parse(final InputStream stream, final String source)
       parser.parse(stream,
           new XHTMLContentHandler(new NoHeadTagInBodyContentHandler(handler), tikaMetadata),
           tikaMetadata, context);
+    } catch (ZeroByteFileException exception){
+      //If a file is zero bytes, then we don't want to throw an exception but continue with an empty HTML string
     } catch (IOException | SAXException | TikaException | NullPointerException exception) {
       throw new ExtractionException("Failed to parse stream", exception);
     }

src/main/java/org/apache/pdfbox/rendering/RendererPackageWorkaround.java

@@ -27,7 +27,7 @@ public class RendererPackageWorkaround {
    */
   public RendererPackageWorkaround() throws RuntimeException {
     try {
-      pageDrawer = new PageDrawer(new PageDrawerParameters(null, null));
+      pageDrawer = new PageDrawer(new PageDrawerParameters(null, null, true));
       method = PageDrawer.class.getDeclaredMethod("createGlyph2D", PDFont.class);
     } catch (NoSuchMethodException | SecurityException | IOException e) {
       throw new RuntimeException(e);

src/test/java/io/committed/krill/extraction/tika/csv/CsvEmptyTikaFormatExtractorIT.java

@@ -14,8 +14,7 @@ public CsvEmptyTikaFormatExtractorIT() {
 
   @Test
   public void testBody() {
-    assertBody("" + "<main class=\"SpreadSheet\"> \n" + " <article class=\"Sheet\"> \n"
-        + "  <table></table> \n" + " </article> \n" + "</main>");
+    assertBody("" );
   }
 
 }

src/test/java/io/committed/krill/extraction/tika/html5/Html5BlockTikaFormatExtractorIT.java

@@ -24,7 +24,7 @@ public void testBody() {
             + "    A div can be used to define a new block element without any specific semantics. \n"
             + "  </div> \n"
             + "  <p>Sometimes it is useful to include larger blocks of preformatted text, which is typically rendered using a monospace font. This is useful when attempting to create diagrams using text:</p> \n"
-            + "  <pre>\n" + "    Top ---&amp;gt;        +----+\n" + "                    |    |\n"
+            + "  <pre>" + "    Top ---&amp;gt;        +----+\n" + "                    |    |\n"
             + " Bottom ---&amp;gt;        +----+\n" + "</pre> \n" + " </section> \n" + "</main>");
   }
 

src/test/java/io/committed/krill/extraction/tika/pptx/PptxPlainSimpleTitleAndSlidesTikaFormatExtractorIT.java

@@ -20,14 +20,14 @@ public void testBody() {
     // NOTE: That don't get lists
 
     assertBody("" + "<main class=\"SlideShow\"> \n" + " <article class=\"Slide\"> \n"
-        + "  <section class=\"\"> \n" + "   <p>Title</p> \n" + "   <p>Subtitle</p> \n"
+        + "  <section> \n" + "   <p>Title</p> \n" + "   <p>Subtitle</p> \n"
         + "  </section> \n" + "  <aside> \n" + "   <p>Notes</p> \n" + "   <p>1</p> \n"
         + "  </aside> \n" + " </article> \n" + " <article class=\"Slide\"> \n"
-        + "  <section class=\"\"> \n" + "   <p>Heading</p> \n" + "   <p>First bullet point</p> \n"
+        + "  <section> \n" + "   <p>Heading</p> \n" + "   <p>First bullet point</p> \n"
         + "   <p>Second bullet point</p> \n" + "   <p>Nested bullet point</p> \n"
         + "  </section> \n" + "  <aside> \n" + "   <p>More notes</p> \n" + "   <p>2</p> \n"
         + "  </aside> \n" + " </article> \n" + " <article class=\"Slide\"> \n"
-        + "  <section class=\"\"> \n" + "   <p>Heading</p> \n"
+        + "  <section> \n" + "   <p>Heading</p> \n"
         + "   <p>First section, first bullet</p> \n" + "   <p>First section, second bullet</p> \n"
         + "   <p>Second section, first bullet</p> \n" + "   <p>Second section, second bullet</p> \n"
         + "  </section> \n" + " </article> \n" + "</main>");

src/test/java/io/committed/krill/extraction/tika/pptx/PptxPlainSimpleTitleSlideTikaFormatExtractorIT.java

@@ -15,7 +15,7 @@ public PptxPlainSimpleTitleSlideTikaFormatExtractorIT() {
   @Test
   public void testBody() {
     assertBody("" + "<main class=\"SlideShow\"> \n" + " <article class=\"Slide\"> \n"
-        + "  <section class=\"\"> \n" + "   <p>Title</p> \n" + "   <p>Subtitle</p> \n"
+        + "  <section> \n" + "   <p>Title</p> \n" + "   <p>Subtitle</p> \n"
         + "  </section> \n" + "  <aside> \n" + "   <p>Notes</p> \n" + "   <p>1</p> \n"
         + "  </aside> \n" + " </article> \n" + "</main>");
   }