Support soft hyphens

3 files changed, 16 insertions, 0 deletions

diff --git a/NEWS b/NEWS
index 4ab6809..d56d1ac 100644
--- a/NEWS
+++ b/NEWS
@@ -1,3 +1,7 @@
+# 1.4.2
+
+* Support soft hyphens.
+
 # 1.4.1
 
 * Read the children of v:rect elements.
diff --git a/src/main/java/org/zwobble/mammoth/internal/docx/StatefulBodyXmlReader.java b/src/main/java/org/zwobble/mammoth/internal/docx/StatefulBodyXmlReader.java
index 931bc8a..d5f594f 100644
--- a/src/main/java/org/zwobble/mammoth/internal/docx/StatefulBodyXmlReader.java
+++ b/src/main/java/org/zwobble/mammoth/internal/docx/StatefulBodyXmlReader.java
@@ -91,6 +91,8 @@ class StatefulBodyXmlReader {
                 return success(Tab.TAB);
             case "w:noBreakHyphen":
                 return success(new Text("\u2011"));
+            case "w:softHyphen":
+                return success(new Text("\u00ad"));
             case "w:br":
                 return readBreak(element);
 
diff --git a/src/test/java/org/zwobble/mammoth/tests/docx/BodyXmlTests.java b/src/test/java/org/zwobble/mammoth/tests/docx/BodyXmlTests.java
index b11c5b1..aaaf1e2 100644
--- a/src/test/java/org/zwobble/mammoth/tests/docx/BodyXmlTests.java
+++ b/src/test/java/org/zwobble/mammoth/tests/docx/BodyXmlTests.java
@@ -688,6 +688,16 @@ public class BodyXmlTests {
     }
 
     @Test
+    public void softHyphenElementIsReadAsSoftHyphenCharacter() {
+        XmlElement element = element("w:softHyphen");
+
+        assertThat(
+            readSuccess(bodyReader(), element),
+            isTextElement("\u00ad")
+        );
+    }
+
+    @Test
     public void brWithoutExplicitTypeIsReadAsLineBreak() {
         XmlElement element = element("w:br");