Ticket #290: ms2007.patch

.cc

@@ -351 +351 @@
             cout << "\"" << cmd << "\" failed - skipping\n";
             return;
         }
+    } else if (startswith(mimetype, "application/vnd.openxmlformats-officedocument.wordprocessingml."))
+    {
+    // Inspired by http://mjr.towers.org.uk/comp/sxw2text
+    string safefile = shell_protect(file);
+    string cmd = "unzip -p " + safefile + " word/document.xml";
+    try {
+        XmlParser xmlparser;
+        xmlparser.parse_html(stdout_to_string(cmd));
+        dump = xmlparser.dump;
+    } catch (ReadError) {
+        cout << "\"" << cmd << "\" failed - skipping\n";
+        return;
+    }
+    } else if (startswith(mimetype, "application/vnd.openxmlformats-officedocument.spreadsheetml."))
+    {
+    // Inspired by http://mjr.towers.org.uk/comp/sxw2text
+    string safefile = shell_protect(file);
+    string cmd = "unzip -p " + safefile + " xl/sharedStrings.xml";
+    try {
+        XmlParser xmlparser;
+        xmlparser.parse_html(stdout_to_string(cmd));
+        dump = xmlparser.dump;
+    } catch (ReadError) {
+        cout << "\"" << cmd << "\" failed - skipping\n";
+        return;
+    }
+    } else if (startswith(mimetype, "application/vnd.openxmlformats-officedocument.presentationml."))
+    {
+    // Inspired by http://mjr.towers.org.uk/comp/sxw2text
+    string safefile = shell_protect(file);
+    string cmd = "unzip -p " + safefile + " ppt/slides/slide*.xml";
+    try {
+        XmlParser xmlparser;
+        xmlparser.parse_html(stdout_to_string(cmd));
+        dump = xmlparser.dump;
+    } catch (ReadError) {
+        cout << "\"" << cmd << "\" failed - skipping\n";
+        return;
+    }
     } else if (mimetype == "application/vnd.wordperfect") {
         // Looking at the source of wpd2html and wpd2text I think both output
         // utf-8, but it's hard to be sure without sample Unicode .wpd files
@@ -730 +769 @@
     // Some other word processor formats:
     mime_map["doc"] = "application/msword";
     mime_map["dot"] = "application/msword"; // Word template
+    mime_map["docx"] = "application/vnd.openxmlformats-officedocument.wordprocessingml.document"; //Word 2007
     mime_map["wpd"] = "application/vnd.wordperfect";
     mime_map["wps"] = "application/vnd.ms-works";
     mime_map["wpt"] = "application/vnd.ms-works"; // Works template
@@ -740 +780 @@
     mime_map["xls"] = "application/vnd.ms-excel";
     mime_map["xlb"] = "application/vnd.ms-excel";
     mime_map["xlt"] = "application/vnd.ms-excel"; // Excel template
+    mime_map["xlsx"] = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"; //Excel 2007
     mime_map["ppt"] = "application/vnd.ms-powerpoint";
     mime_map["pps"] = "application/vnd.ms-powerpoint"; // Powerpoint slideshow
+    mime_map["pptx"] = "application/vnd.openxmlformats-officedocument.presentationml.presentation"; //PowerPoint 2007
     // Perl:
     mime_map["pl"] = "text/x-perl";
     mime_map["pm"] = "text/x-perl";