Read [Content_Types].xml to find content types of files

3 files changed, 47 insertions, 2 deletions

diff --git a/lib/content-types-reader.js b/lib/content-types-reader.js
index 5240d21..0346b8c 100644
--- a/lib/content-types-reader.js
+++ b/lib/content-types-reader.js
@@ -1,10 +1,37 @@
+var readXmlFromZipFile = require("./office-xml-reader").readXmlFromZipFile;
+
 exports.readContentTypesFromZipFile = readContentTypesFromZipFile;
+exports.readContentTypesFromXml = readContentTypesFromXml;
 
 
 function readContentTypesFromZipFile(file) {
+    return readXmlFromZipFile(file, "[Content_Types].xml")
+        .then(function(xml) {
+            return xml ? readContentTypesFromXml(xml) : defaultContentTypes;
+        });
+}
+
+function readContentTypesFromXml(xml) {
+    var extensionDefaults = {};
+    
+    xml.root.children.forEach(function(child) {
+        if (child.name === "content-types:Default") {
+            extensionDefaults[child.attributes.Extension] = child.attributes.ContentType;
+        }
+    });
+    
     return {
         findContentType: function(path) {
-            return "image/png";
+            var pathParts = path.split(".");
+            var extension = pathParts[pathParts.length - 1];
+            return extensionDefaults[extension];
         }
     }
 }
+
+
+var defaultContentTypes = {
+    findContentType: function(path) {
+        return null;
+    }
+};
diff --git a/lib/office-xml-reader.js b/lib/office-xml-reader.js
index 7aa8bab..04b73fb 100644
--- a/lib/office-xml-reader.js
+++ b/lib/office-xml-reader.js
@@ -10,7 +10,8 @@ var xmlNamespaceMap = {
     "http://schemas.openxmlformats.org/officeDocument/2006/relationships": "r",
     "http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing": "wp",
     "http://schemas.openxmlformats.org/drawingml/2006/main": "a",
-    "http://schemas.openxmlformats.org/drawingml/2006/picture": "pic"
+    "http://schemas.openxmlformats.org/drawingml/2006/picture": "pic",
+    "http://schemas.openxmlformats.org/package/2006/content-types": "content-types"
 };
 
 
diff --git a/tests/content-types-reader.tests.js b/tests/content-types-reader.tests.js
new file mode 100644
index 0000000..7cd7295
--- /dev/null
+++ b/tests/content-types-reader.tests.js
@@ -0,0 +1,17 @@
+var assert = require("assert");
+
+var readContentTypesFromXml = require("../lib/content-types-reader").readContentTypesFromXml;
+var XmlElement = require("../lib/xmlreader").Element;
+var test = require("./testing").test;
+
+
+describe('readContentTypesFromXml', function() {
+    test('reads default-per-extension from XML', function() {
+        var contentTypes = readContentTypesFromXml({
+            root: new XmlElement("content-types:Types", {}, [
+                new XmlElement("content-types:Default", {Extension: "png", ContentType: "image/png"})
+            ])
+        });
+        assert.equal(contentTypes.findContentType("word/media/hat.png"), "image/png");
+    });
+});