mailparser 0.5.2 → 0.6.2

package/README.md

@@ -9,6 +9,12 @@ MailParser
 Handles even large attachments with ease - attachments can be parsed
 in chunks and streamed if needed.
 
+### Community version
+
+This module is unmaintained. For an upgrade see [Mailparser2](https://gitlab.com/nodemailer/mailparser2). The upgraded version is more effective, has vastly better stream handling through Streams3 interface and is able to build up more accurate versions of HTML and Text contents.
+
+### Usage
+
 **MailParser** parses raw source of e-mail messages into a structured object.
 
 No need to worry about charsets or decoding *quoted-printable* or
@@ -65,9 +71,9 @@ When the parsing ends an `'end'` event is emitted which has an
 object with parsed e-mail structure as a parameter.
 
 ```javascript
-    mailparser.on("end", function(mail){
-        mail; // object structure for parsed e-mail
-    });
+mailparser.on("end", function(mail){
+    mail; // object structure for parsed e-mail
+});
 ```
 ### Parsed mail object
 
@@ -90,21 +96,23 @@ object with parsed e-mail structure as a parameter.
 This example decodes an e-mail from a string
 
 ```javascript
-var MailParser = require("mailparser").MailParser,
-    mailparser = new MailParser();
+var MailParser = require("mailparser").MailParser;
+var mailparser = new MailParser();
 
 var email = "From: 'Sender Name' <sender@example.com>\r\n"+
             "To: 'Receiver Name' <receiver@example.com>\r\n"+
             "Subject: Hello world!\r\n"+
             "\r\n"+
             "How are you today?";
-    // setup an event listener when the parsing finishes
+
+// setup an event listener when the parsing finishes
 mailparser.on("end", function(mail_object){
     console.log("From:", mail_object.from); //[{address:'sender@example.com',name:'Sender Name'}]
     console.log("Subject:", mail_object.subject); // Hello world!
     console.log("Text body:", mail_object.text); // How are you today?
 });
-    // send the email source to the parser
+
+// send the email source to the parser
 mailparser.write(email);
 mailparser.end();
 ```
@@ -112,10 +120,11 @@ mailparser.end();
 
 This example pipes a `readableStream` file to **MailParser**
 ```javascript
-var MailParser = require("mailparser").MailParser,
-    mailparser = new MailParser(),
-    fs = require("fs");
-    mailparser.on("end", function(mail_object){
+var MailParser = require("mailparser").MailParser;
+var mailparser = new MailParser();
+var fs = require("fs");
+
+mailparser.on("end", function(mail_object){
     console.log("Subject:", mail_object.subject);
 });
 
@@ -139,17 +148,17 @@ mailparser.on("end", function(mail_object){
 
 By default attachments will be included in the attachment objects as Buffers.
 ```javascript
-    attachments = [{
-        contentType: 'image/png',
-        fileName: 'image.png',
-        contentDisposition: 'attachment',
-        contentId: '5.1321281380971@localhost',
-        transferEncoding: 'base64',
-        length: 126,
-        generatedFileName: 'image.png',
-        checksum: 'e4cef4c6e26037bcf8166905207ea09b',
-        content: <Buffer ...>
-    }];
+attachments = [{
+    contentType: 'image/png',
+    fileName: 'image.png',
+    contentDisposition: 'attachment',
+    contentId: '5.1321281380971@localhost',
+    transferEncoding: 'base64',
+    length: 126,
+    generatedFileName: 'image.png',
+    checksum: 'e4cef4c6e26037bcf8166905207ea09b',
+    content: <Buffer ...>
+}];
 ```
 The property `generatedFileName` is usually the same as `fileName` but if several
 different attachments with the same name exist or there is no `fileName` set, an
@@ -176,6 +185,7 @@ object. The parameter provided includes file information (`contentType`,
 var mp = new MailParser({
     streamAttachments: true
 }
+
 mp.on("attachment", function(attachment, mail){
     var output = fs.createWriteStream(attachment.generatedFileName);
     attachment.stream.pipe(output);

package/lib/mailparser.js

@@ -269,6 +269,7 @@ MailParser.prototype._process = function(finalPart) {
 MailParser.prototype._processStateHeader = function(line) {
     var attachment, lastPos = this._currentNode.headers.length - 1,
         textContent = false,
+        rootNode,
         extension;
 
     // Check if the header ends and body starts
@@ -309,7 +310,7 @@ MailParser.prototype._processStateHeader = function(line) {
             this._currentNode.meta.generatedFileName = this._generateFileName(this._currentNode.meta.fileName, this._currentNode.meta.contentType);
 
             this._currentNode.meta.contentId = this._currentNode.meta.contentId ||
-                crypto.createHash("md5").update(this._currentNode.meta.generatedFileName).digest("hex") + "@mailparser";
+                crypto.createHash("md5").update(new Buffer(this._currentNode.meta.generatedFileName, 'utf-8')).digest("hex") + "@mailparser";
 
             extension = this._currentNode.meta.generatedFileName.split(".").pop().toLowerCase();
 
@@ -330,8 +331,14 @@ MailParser.prototype._processStateHeader = function(line) {
                     this._currentNode.stream = new Streams.BinaryStream();
                 }
                 attachment.stream = this._currentNode.stream;
+                
+                rootNode = this._currentNode;
+                
+                while (rootNode.parentNode) {
+                    rootNode = rootNode.parentNode;
+                }
 
-                this.emit("attachment", attachment, this._currentNode.parentNode || this._currentNode);
+                this.emit("attachment", attachment, rootNode);
             } else {
                 this._currentNode.content = undefined;
             }
@@ -589,7 +596,7 @@ MailParser.prototype._createMimeNode = function(parentNode) {
 MailParser.prototype._parseHeaderLineWithParams = function(value) {
     var key, parts, returnValue = {};
 
-    parts = value.match(/(?:[^;"]+|"[^"]*")+/g) ||  [value];
+    parts = value.match(/(?:[^;"]+|"[^"]*")+/g) || [value];
     returnValue.defaultValue = parts.shift().toLowerCase();
 
     for (var i = 0, len = parts.length; i < len; i++) {
@@ -790,10 +797,10 @@ MailParser.prototype._detectFilename = function(value) {
 
     if (fileName) {
         parts = fileName.split("'");
-        encoding = parts.shift();
+        encoding = (parts.length > 1) ? parts[0] : "us-ascii";
         name = parts.pop();
         if (name) {
-            return this._replaceMimeWords(this._replaceMimeWords("=?" + (encoding || "us-ascii") + "?Q?" + name.replace(/%/g, "=") + "?="));
+            return this._replaceMimeWords(this._replaceMimeWords("=?" + encoding + "?Q?" + name.replace(/%/g, "=") + "?="));
         }
     }
     return "";
@@ -866,7 +873,7 @@ MailParser.prototype._parsePriority = function(value) {
             case "low":
                 return "low";
             case "urgent":
-            case "hight":
+            case "high":
                 return "high";
         }
     }
@@ -949,8 +956,8 @@ MailParser.prototype._finalizeContents = function() {
 
         if (!this._currentNode.attachment) {
 
-            if (this._currentNode.meta.contentType == "text/html") {
-                this._currentNode.meta.charset = this._detectHTMLCharset(this._currentNode.content) || this._currentNode.meta.charset || this.options.defaultCharset || "iso-8859-1";
+            if (this._currentNode.meta.contentType == "text/html" && !this._currentNode.meta.charset) {
+                this._currentNode.meta.charset = this._detectHTMLCharset(this._currentNode.content) || this.options.defaultCharset || "iso-8859-1";
             }
 
             if (this._currentNode.meta.transferEncoding == "quoted-printable") {
@@ -1036,16 +1043,29 @@ MailParser.prototype._processMimeTree = function() {
     }
 
     if (this.mailData.text.length) {
-        for (i = 0, len = this.mailData.text.length; i < len; i++) {
-            if (!returnValue.text && this.mailData.text[i].content) {
-                returnValue.text = this.mailData.text[i].content;
-            } else if (this.mailData.text[i].content) {
-                returnValue.text += this.mailData.text[i].content;
-            }
+      var len = this.mailData.text.length;
+      // if we have both html and text, process text till the length of html assuming its alternative for html
+      if (this.mailData.html.length) {
+        len = Math.min(len, this.mailData.html.length);
+      }
+      for (i = 0, len; i < len; i++) {
+        if (!returnValue.text && this.mailData.text[i].content) {
+          returnValue.text = this.mailData.text[i].content;
+        } else if (this.mailData.text[i].content) {
+          returnValue.text += this.mailData.text[i].content;
+        }
+      }
+      // all remaining text contents if present assumed as additional content and concatenated with html as well as text
+      for (len = this.mailData.text.length; i < len; i++) {
+        if (this.mailData.text[i].content) {
+          // concatenate to both text and html so that text and html are always same content
+          // user should be able to chose any one of them
+          returnValue.text += this.mailData.text[i].content;
+          returnValue.html += this.mailData.text[i].content;
         }
+      }
     }
 
-
     if (this.mailData.calendar.length) {
         returnValue.alternatives = [];
         for (i = 0, len = this.mailData.calendar.length; i < len; i++) {
@@ -1490,4 +1510,4 @@ MailParser.prototype._detectHTMLCharset = function(html) {
     }
 
     return charset;
-};
+};

package/lib/streams.js

@@ -196,12 +196,12 @@ UUEStream.prototype.decode = function(buffer) {
     var filename;
 
     var re = /^begin [0-7]{3} (.*)/;
-    filename = buffer.slice(0, Math.min(buffer.length, 1024)).toString().match(re)[1] || '';
+    filename = buffer.slice(0, Math.min(buffer.length, 1024)).toString().match(re) || '';
     if (!filename) {
         return new Buffer(0);
     }
 
-    buffer = uue.decodeFile(buffer.toString('ascii').replace(/\r\n/g, '\n'), filename);
+    buffer = uue.decodeFile(buffer.toString('ascii').replace(/\r\n/g, '\n'), filename[1]);
 
     if (this.charset.toLowerCase() == "binary") {
         // do nothing

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "mailparser",
   "description": "Asynchronous and non-blocking parser for mime encoded e-mail messages",
-  "version": "0.5.2",
+  "version": "0.6.2",
   "author": "Andris Reinman",
   "maintainers": [{
     "name": "andris",
@@ -17,13 +17,13 @@
   "main": "./lib/mailparser",
   "license": "MIT",
   "dependencies": {
-    "mimelib": "^0.2.19",
-    "encoding": "^0.1.11",
+    "mimelib": "^0.3.0",
+    "encoding": "^0.1.12",
     "mime": "^1.3.4",
-    "uue": "^2.1.1"
+    "uue": "^3.1.0"
   },
   "devDependencies": {
-    "nodeunit": "^0.9.1"
+    "nodeunit": "^0.10.2"
   },
   "keywords": [
     "e-mail",

package/test/mailparser.js

@@ -340,21 +340,6 @@ exports["Text encodings"] = {
         });
     },
 
-    "HTML encoding: Conflicting headers": function(test) {
-        var encodedText = "Content-Type: text/html; charset=iso-8859-1\r\n" +
-            "\r\n" +
-            "<html><head><meta charset=\"utf-8\"/></head><body>ÕÄÖÜ",
-            mail = new Buffer(encodedText, "utf-8");
-
-        test.expect(1);
-
-        var mailparser = new MailParser();
-        mailparser.end(mail);
-        mailparser.on("end", function(mail) {
-            test.equal((mail.html || "").substr(-4), "ÕÄÖÜ");
-            test.done();
-        });
-    },
     "HTML encoding: Header defined": function(test) {
         var encodedText = "Content-Type: text/html; charset=iso-UTF-8\r\n" +
             "\r\n" +
@@ -461,7 +446,7 @@ exports["Attachment Content-Id"] = {
         var mailparser = new MailParser();
         mailparser.end(mail);
         mailparser.on("end", function(mail) {
-            test.equal(mail.attachments && mail.attachments[0] && mail.attachments[0].contentId, "ef694232fea1c01c16fb8a03a0ca710c@mailparser");
+            test.equal(mail.attachments && mail.attachments[0] && mail.attachments[0].contentId, "7c7cf35ce5becf62faea56ed8d0ad6e4@mailparser");
             test.done();
         });
     },
@@ -516,6 +501,24 @@ exports["Attachment filename"] = {
             test.done();
         });
     },
+    "Content-Disposition filename*X": function(test) {
+        var encodedText = "Content-Type: application/octet-stream\r\n" +
+            "Content-Transfer-Encoding: QUOTED-PRINTABLE\r\n" +
+            "Content-Disposition: attachment;\r\n" +
+            "    filename*0=OA;\r\n" +
+            "    filename*1=U;\r\n" +
+            "    filename*2=.txt\r\n" +
+            "\r\n" +
+            "=00=01=02=03=FD=FE=FF",
+            mail = new Buffer(encodedText, "utf-8");
+
+        var mailparser = new MailParser();
+        mailparser.end(mail);
+        mailparser.on("end", function(mail) {
+            test.equal(mail.attachments && mail.attachments[0] && mail.attachments[0].content && mail.attachments[0].fileName, "OAU.txt");
+            test.done();
+        });
+    },
     "Content-Disposition filename*X*": function(test) {
         var encodedText = "Content-Type: application/octet-stream\r\n" +
             "Content-Transfer-Encoding: QUOTED-PRINTABLE\r\n" +
@@ -566,6 +569,23 @@ exports["Attachment filename"] = {
             test.done();
         });
     },
+    "Content-Type ; name": function(test) {
+        var encodedText = "Content-Type: ; name=\"test\"\r\n" +
+            "Content-Transfer-Encoding: QUOTED-PRINTABLE\r\n" +
+            "\r\n" +
+            "=00=01=02=03=FD=FE=FF",
+            mail = new Buffer(encodedText, "utf-8");
+
+        var mailparser = new MailParser();
+
+        mailparser.write(mail);
+        mailparser.end();
+
+        mailparser.on("end", function(mail) {
+            test.equal(mail.attachments && mail.attachments[0] && mail.attachments[0].fileName, "test");
+            test.done();
+        });
+    },
     "Content-Type name*": function(test) {
         var encodedText = "Content-Type: application/octet-stream;\r\n" +
             "    name*=UTF-8''%C3%95%C3%84%C3%96%C3%9C\r\n" +
@@ -1508,7 +1528,7 @@ exports["Attachment info"] = {
 };
 
 exports["Advanced nested HTML"] = function(test) {
-    var mail = fs.readFileSync(__dirname + "/nested.eml");
+    var mail = fs.readFileSync(__dirname + "/ali.eml");
 
     test.expect(2);
     var mailparser = new MailParser();
@@ -1519,12 +1539,31 @@ exports["Advanced nested HTML"] = function(test) {
 
     mailparser.end();
     mailparser.on("end", function(mail) {
+        console.log(require('util').inspect(mail, false, 22));
         test.equal(mail.text, "\nDear Sir,\n\nGood evening.\n\n\n \n\n\n\nThe footer\n");
         test.equal(mail.html, "<p>Dear Sir</p>\n<p>Good evening.</p>\n<p></p><p>The footer</p>\n");
         test.done();
     });
 };
 
+exports["Additional text"] = function(test) {
+  var mail = fs.readFileSync(__dirname + "/mixed.eml");
+
+  test.expect(2);
+  var mailparser = new MailParser();
+
+  for (var i = 0, len = mail.length; i < len; i++) {
+    mailparser.write(new Buffer([mail[i]]));
+  }
+
+  mailparser.end();
+  mailparser.on("end", function(mail) {
+    test.equal(mail.text, "\nThis e-mail message has been scanned for Viruses and Content and cleared\nGood Morning;\n\n");
+    test.equal(mail.html, "<HTML><HEAD>\n</HEAD><BODY> \n\n<HR>\nThis e-mail message has been scanned for Viruses and Content and cleared\n<HR>\n</BODY></HTML>\nGood Morning;\n\n");
+    test.done();
+  });
+};
+
 exports["MBOX format"] = {
     "Not a mbox": function(test) {
         var encodedText = "Content-Type: text/plain; charset=utf-8\r\n" +

package/test/mixed.eml

@@ -0,0 +1,37 @@
+Content-Type: multipart/mixed;
+	boundary="--=b73b47c7-75f9-4775-93eb-475a43310901"
+
+
+----=b73b47c7-75f9-4775-93eb-475a43310901
+Content-Type: multipart/alternative;
+	boundary="--=4d3d5f03-fd7a-40f2-ab55-6bd2de649863"
+
+----=4d3d5f03-fd7a-40f2-ab55-6bd2de649863
+Content-Type: text/plain
+Content-Transfer-Encoding: 7bit
+
+
+This e-mail message has been scanned for Viruses and Content and cleared
+
+----=4d3d5f03-fd7a-40f2-ab55-6bd2de649863
+Content-Type: text/html
+Content-Transfer-Encoding: quoted-printable
+
+<HTML><HEAD>
+</HEAD><BODY>=20
+
+<HR>
+This e-mail message has been scanned for Viruses and Content and cleared
+<HR>
+</BODY></HTML>
+
+----=4d3d5f03-fd7a-40f2-ab55-6bd2de649863--
+
+----=b73b47c7-75f9-4775-93eb-475a43310901
+Content-Type: text/plain; charset="UTF-8"
+Content-Transfer-Encoding: quoted-printable
+
+Good Morning;
+
+
+----=b73b47c7-75f9-4775-93eb-475a43310901--