From 504f59e38e57b543ac87f73df53fe3a6ba34e26d Mon Sep 17 00:00:00 2001
From: Michael Williamson <mike@zwobble.org>
Date: Fri, 29 Mar 2013 18:57:02 +0000
Subject: Very basic conversion from docx to HTML

---
 .gitignore                               |  1 +
 lib/index.js                             | 49 +++++++++++++++++++++
 lib/xmlreader.js                         | 75 ++++++++++++++++++++++++++++++++
 makefile                                 |  4 ++
 package.json                             | 19 ++++++++
 tests/mammoth.tests.js                   | 38 ++++++++++++++++
 tests/test-data/simple/word/document.xml | 18 ++++++++
 tests/testing.js                         | 10 +++++
 tests/xmlreader.tests.js                 | 59 +++++++++++++++++++++++++
 9 files changed, 273 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 lib/index.js
 create mode 100644 lib/xmlreader.js
 create mode 100644 makefile
 create mode 100644 package.json
 create mode 100644 tests/mammoth.tests.js
 create mode 100644 tests/test-data/simple/word/document.xml
 create mode 100644 tests/testing.js
 create mode 100644 tests/xmlreader.tests.js

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..07e6e47
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+/node_modules
diff --git a/lib/index.js b/lib/index.js
new file mode 100644
index 0000000..11364b3
--- /dev/null
+++ b/lib/index.js
@@ -0,0 +1,49 @@
+var q = require("q");
+var xmlreader = require("./xmlreader");
+
+exports.Converter = Converter;
+
+function Converter() {
+}
+
+Converter.prototype.convertToHtml = function(docxFile) {
+    return docxFile.read("word/document.xml").then(function(documentXmlString) {
+        return parseXml(documentXmlString);
+    }).then(function(documentXml) {
+        var body = documentXml.root.first("w:body");
+        
+        var html = body.children.map(elementToHtml).join("");
+        
+        return {
+            html: html
+        }; 
+    });
+}
+
+function parseXml(string) {
+    return xmlreader.read(string);
+}
+
+function elementToHtml(element) {
+    if (element.type === "element") {
+        var handler = elementConverters[element.name];
+        if (handler) {
+            return handler(element);
+        } else {
+            return "";
+        }
+    }
+}
+
+var elementConverters = {
+    "w:p": function(element) {
+        var innerHtml = element.children.map(elementToHtml).join("");
+        return "<p>" + innerHtml + "</p>";
+    },
+    "w:r": function(element) {
+        return element.children.map(elementToHtml).join("");
+    },
+    "w:t": function(element) {
+        return element.children[0].value;
+    }
+};
diff --git a/lib/xmlreader.js b/lib/xmlreader.js
new file mode 100644
index 0000000..67dda38
--- /dev/null
+++ b/lib/xmlreader.js
@@ -0,0 +1,75 @@
+var q = require("q");
+var sax = require("sax");
+var _ = require("underscore");
+
+exports.read = read;
+
+function read(xmlString) {
+    var parser = sax.parser(true, {xmlns: true, position: false});
+    
+    //~ parser.onerror = function(error) {
+        //~ Q.fcall(function () {
+            //~ throw new Error("Can't do it");
+        //~ });
+    //~ };
+    
+    var rootElement = {children: []};
+    var currentElement = rootElement;
+    var stack = [];
+    
+    var deferred = q.defer();
+    
+    parser.onopentag = function(node) {
+        var attributes = mapValues(node.attributes, function(attribute) {
+            return attribute.value;
+        });
+        
+        var element = new Element(node.name, attributes);
+        currentElement.children.push(element);
+        stack.push(currentElement);
+        currentElement = element
+    };
+    
+    parser.onclosetag = function(node) {
+        currentElement = stack.pop();
+    };
+    
+    parser.ontext = function(text) {
+        if (currentElement !== rootElement) {
+            currentElement.children.push({
+                type: "text",
+                value: text
+            });
+        }
+    };
+    
+    parser.onend = function() {
+        deferred.resolve({
+            root: rootElement.children[0]
+        });
+    };
+    
+    parser.write(xmlString).close();
+    
+    return deferred.promise;
+}
+
+function mapValues(input, mapper, context) {
+    return _.reduce(input, function (obj, v, k) {
+        obj[k] = mapper.call(context, v, k, input);
+        return obj;
+    }, {}, context);
+}
+
+function Element(name, attributes) {
+    this.type = "element";
+    this.name = name;
+    this.attributes = attributes;
+    this.children = [];
+}
+
+Element.prototype.first = function(name) {
+    return _.find(this.children, function(child) {
+        return child.name == name;
+    });
+}
diff --git a/makefile b/makefile
new file mode 100644
index 0000000..6fb8f49
--- /dev/null
+++ b/makefile
@@ -0,0 +1,4 @@
+.PHONY: test
+
+test:
+	node_modules/.bin/mocha tests
diff --git a/package.json b/package.json
new file mode 100644
index 0000000..a13b491
--- /dev/null
+++ b/package.json
@@ -0,0 +1,19 @@
+{
+    "name": "mammoth",
+    "version": "0.1.0",
+    "author": "Michael Williamson <mike@zwobble.org>",
+    "description": "Convert Word documents to simple HTML",
+    "main": "./lib/index.js",
+    "repository": {
+        "type": "git",
+        "url": "https://github.com/mwilliamson/mammoth.js.git"
+    },
+    "dependencies": {
+        "q": "~0.9.2",
+        "sax": "~0.5.2",
+        "underscore": "~1.4.4"
+    },
+    "devDependencies": {
+        "mocha": "~1.8"
+    }
+}
diff --git a/tests/mammoth.tests.js b/tests/mammoth.tests.js
new file mode 100644
index 0000000..05ef218
--- /dev/null
+++ b/tests/mammoth.tests.js
@@ -0,0 +1,38 @@
+var assert = require("assert");
+var path = require("path");
+var fs = require("fs");
+var mammoth = require("../")
+var q = require("q");
+var test = require("./testing").test;
+
+
+describe('mammoth', function() {
+    test('should convert docx containing one one paragraph to single p element', function() {
+        var docxFile = createFakeDocxFile({
+            "word/document.xml": testData("simple/word/document.xml")
+        });
+        return convertToHtml(docxFile).then(function(result) {
+            assert.equal("<p>Hello.</p>", result.html);
+        });
+    })
+})
+
+function createFakeDocxFile(files) {
+    function read(path) {
+        return files[path];
+    }
+    
+    return {
+        read: read
+    };
+}
+
+function testData(testDataPath) {
+    var fullPath = path.join(__dirname, "test-data", testDataPath);
+    return q.nfcall(fs.readFile, fullPath, "utf-8");
+}
+
+function convertToHtml(docxFile) {
+    var converter = new mammoth.Converter();
+    return converter.convertToHtml(docxFile);
+}
diff --git a/tests/test-data/simple/word/document.xml b/tests/test-data/simple/word/document.xml
new file mode 100644
index 0000000..1723398
--- /dev/null
+++ b/tests/test-data/simple/word/document.xml
@@ -0,0 +1,18 @@
+<?xml version="1.0" ?>
+<w:document mc:Ignorable="w14 wp14" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math" xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:v="urn:schemas-microsoft-com:vml" xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:w10="urn:schemas-microsoft-com:office:word" xmlns:w14="http://schemas.microsoft.com/office/word/2010/wordml" xmlns:wne="http://schemas.microsoft.com/office/word/2006/wordml" xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing" xmlns:wp14="http://schemas.microsoft.com/office/word/2010/wordprocessingDrawing" xmlns:wpc="http://schemas.microsoft.com/office/word/2010/wordprocessingCanvas" xmlns:wpg="http://schemas.microsoft.com/office/word/2010/wordprocessingGroup" xmlns:wpi="http://schemas.microsoft.com/office/word/2010/wordprocessingInk" xmlns:wps="http://schemas.microsoft.com/office/word/2010/wordprocessingShape">
+  <w:body>
+    <w:p w:rsidR="00E01ECE" w:rsidRDefault="000636A7">
+      <w:r>
+        <w:t>Hello.</w:t>
+      </w:r>
+      <w:bookmarkStart w:id="0" w:name="_GoBack"/>
+      <w:bookmarkEnd w:id="0"/>
+    </w:p>
+    <w:sectPr w:rsidR="00E01ECE">
+      <w:pgSz w:h="16838" w:w="11906"/>
+      <w:pgMar w:bottom="1440" w:footer="708" w:gutter="0" w:header="708" w:left="1440" w:right="1440" w:top="1440"/>
+      <w:cols w:space="708"/>
+      <w:docGrid w:linePitch="360"/>
+    </w:sectPr>
+  </w:body>
+</w:document>
diff --git a/tests/testing.js b/tests/testing.js
new file mode 100644
index 0000000..ac413c8
--- /dev/null
+++ b/tests/testing.js
@@ -0,0 +1,10 @@
+exports.test = test;
+
+function test(name, func) {
+    it(name, function(done) {
+        var result = func();
+        result.then(function() {
+            done()
+        }).done();
+    });
+}
diff --git a/tests/xmlreader.tests.js b/tests/xmlreader.tests.js
new file mode 100644
index 0000000..ad11e62
--- /dev/null
+++ b/tests/xmlreader.tests.js
@@ -0,0 +1,59 @@
+var assert = require("assert");
+
+var xmlreader = require("../lib/xmlreader");
+var test = require("./testing").test;
+
+
+describe('xmlreader.read', function() {
+    test('should read self-closing element', function() {
+        return xmlreader.read("<body/>").then(function(result) {
+            assert.deepEqual({type: "element", name: "body", attributes: {}, children: []}, result.root);
+        });
+    })
+    
+    test('should read empty element with separate closing tag', function() {
+        return xmlreader.read("<body></body>").then(function(result) {
+            assert.deepEqual({type: "element", name: "body", attributes: {}, children: []}, result.root);
+        });
+    })
+    
+    test('should read attributes of tags', function() {
+        return xmlreader.read('<body name="bob"/>').then(function(result) {
+            assert.deepEqual({name: "bob"}, result.root.attributes);
+        });
+    })
+    
+    test('can read text element', function() {
+        return xmlreader.read('<body>Hello!</body>').then(function(result) {
+            assert.deepEqual({type: "text", value: "Hello!"}, result.root.children[0]);
+        });
+    })
+    
+    test('should read element with children', function() {
+        return xmlreader.read("<body><a/><b/></body>").then(function(result) {
+            var root = result.root;
+            assert.equal(2, root.children.length);
+            assert.equal("a", root.children[0].name);
+            assert.equal("b", root.children[1].name);
+        });
+    })
+
+    test('should read element with namespace declaration', function() {
+        return xmlreader.read("<w:body/>").then(function(result) {
+            assert.deepEqual("w:body", result.root.name);
+        });
+    })
+    
+    test('can find first element with name', function() {
+        return xmlreader.read('<body><a/><b index="1"/><b index="2"/></body>').then(function(result) {
+            var first = result.root.first("b");
+            assert.equal("1", first.attributes.index);
+        });
+    })
+    
+    test('whitespace between xml declaration and root tag is ignored', function() {
+        return xmlreader.read('<?xml version="1.0" ?>\n<body/>').then(function(result) {
+            assert.deepEqual("body", result.root.name);
+        });
+    })
+});
-- 
cgit v1.2.3