Use docx parsing in Mammoth

1 files changed, 53 insertions, 24 deletions

diff --git a/src/main/java/org/zwobble/mammoth/Mammoth.java b/src/main/java/org/zwobble/mammoth/Mammoth.java
index e266f77..c639634 100644
--- a/src/main/java/org/zwobble/mammoth/Mammoth.java
+++ b/src/main/java/org/zwobble/mammoth/Mammoth.java
@@ -1,56 +1,85 @@
 package org.zwobble.mammoth;
 
+import com.google.common.base.Joiner;
+import com.google.common.collect.ImmutableBiMap;
+import com.google.common.collect.ImmutableMap;
+import org.zwobble.mammoth.documents.*;
+import org.zwobble.mammoth.docx.BodyXmlReader;
+import org.zwobble.mammoth.docx.DocumentXmlReader;
+import org.zwobble.mammoth.docx.Styles;
+import org.zwobble.mammoth.xml.XmlElement;
+import org.zwobble.mammoth.xml.parsing.XmlParser;
+
 import java.io.File;
 import java.io.IOException;
 import java.io.InputStream;
 import java.util.zip.ZipEntry;
 import java.util.zip.ZipFile;
 
-import org.zwobble.mammoth.xml.XmlElement;
-import org.zwobble.mammoth.xml.XmlNodeVisitor;
-import org.zwobble.mammoth.xml.parsing.XmlParser;
-import org.zwobble.mammoth.xml.XmlTextNode;
-
-import com.google.common.base.Joiner;
-import com.google.common.base.Strings;
-import com.google.common.collect.ImmutableBiMap;
-
 import static com.google.common.collect.Iterables.transform;
 
 public class Mammoth {
+    private static ImmutableBiMap<String, String> XML_NAMESPACES = ImmutableBiMap.<String, String>builder()
+        .put("w", "http://schemas.openxmlformats.org/wordprocessingml/2006/main")
+        .put("wp", "http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing")
+        .put("a", "http://schemas.openxmlformats.org/drawingml/2006/main")
+        .put("pic", "http://schemas.openxmlformats.org/drawingml/2006/picture")
+        .put("content-types", "http://schemas.openxmlformats.org/package/2006/content-types")
+        .put("r", "http://schemas.openxmlformats.org/officeDocument/2006/relationships")
+        .put("relationships", "http://schemas.openxmlformats.org/package/2006/relationships")
+        .put("v", "urn:schemas-microsoft-com:vml")
+        .put("mc", "http://schemas.openxmlformats.org/markup-compatibility/2006")
+        .put("office-word", "urn:schemas-microsoft-com:office:word")
+        .build();
 
     public static String convertToHtml(File file) {
         try (ZipFile zipFile = new ZipFile(file)) {
             ZipEntry entry = zipFile.getEntry("word/document.xml");
             XmlElement documentXml = parseXml(zipFile.getInputStream(entry));
-            String text = extractText(documentXml);
-            if (Strings.isNullOrEmpty(text)) {
-                return "";
-            } else {
-                return "<p>" + text + "</p>";                
-            }
+
+            Styles styles = new Styles(ImmutableMap.of(), ImmutableMap.of());
+            Document document = new DocumentXmlReader(new BodyXmlReader(styles)).readElement(documentXml);
+            return convertToHtml(document);
         } catch (IOException e) {
             throw new UnsupportedOperationException("Should return a result of failure");   
         }
     }
 
-    private static XmlElement parseXml(InputStream inputStream) {
-        return new XmlParser(ImmutableBiMap.of()).parseStream(inputStream);
+    private static String convertToHtml(Document document) {
+        return convertChildrenToHtml(document);
+    }
+
+    private static String convertChildrenToHtml(HasChildren element) {
+        return Joiner.on("").join(transform(
+            element.getChildren(),
+            Mammoth::convertToHtml));
     }
 
-    private static String extractText(XmlElement documentXml) {
-        return documentXml.accept(new XmlNodeVisitor<String>() {
+    private static String convertToHtml(DocumentElement element) {
+        return element.accept(new DocumentElementVisitor<String>() {
             @Override
-            public String visit(XmlElement element) {
-                return Joiner.on("").join(
-                    transform(element.children(), child -> child.accept(this)));
+            public String visit(ParagraphElement paragraph) {
+                String content = convertChildrenToHtml(paragraph);
+                if (content.isEmpty()) {
+                    return "";
+                } else {
+                    return "<p>" + content + "</p>";
+                }
             }
 
             @Override
-            public String visit(XmlTextNode textNode) {
-                return textNode.getValue();
+            public String visit(RunElement run) {
+                return convertChildrenToHtml(run);
+            }
+
+            @Override
+            public String visit(TextElement text) {
+                return text.getValue();
             }
         });
     }
 
+    private static XmlElement parseXml(InputStream inputStream) {
+        return new XmlParser(XML_NAMESPACES).parseStream(inputStream);
+    }
 }