Start of eml

src/core/config/Categories.json

@@ -54,7 +54,8 @@
             "From MessagePack",
             "To Braille",
             "From Braille",
-            "Parse TLV"
+            "Parse TLV",
+            "Parse Internet Message Format"
         ]
     },
     {

src/core/lib/ChrEnc.mjs

@@ -56,3 +56,50 @@ export const IO_FORMAT = {
     "Simplified Chinese GB18030 (54936)": 54936,
 };
 
+/**
+ * Preferred MIME encoding format mappings.
+ */
+export const MIME_FORMAT = {
+    "utf-8": 65001,
+    "utf-7": 65000,
+    "unicode": 1200,
+    "ibm500": 500,
+    "ebcdic-cp-us": 37,
+    "windows-874": 874,
+    "shift_jis": 932,
+    "gbk": 936,
+    "gb2312": 936,
+    "ks_c_5601-1987": 949,
+    "big5": 950,
+    "windows-1250": 1250,
+    "windows-1251": 1251,
+    "windows-1252": 1252,
+    "windows-1253": 1253,
+    "windows-1254": 1254,
+    "windows-1255": 1255,
+    "windows-1256": 1256,
+    "windows-1257": 1257,
+    "windows-1258": 1258,
+    "us-ascii": 20127,
+    "koi8-r": 20866,
+    "koi8-u": 21866,
+    "iso-8859-1": 28591,
+    "iso-8859-2": 28592,
+    "iso-8859-3": 28593,
+    "iso-8859-4": 28594,
+    "iso-8859-5": 28595,
+    "iso-8859-6": 28596,
+    "iso-8859-7": 28597,
+    "iso-8859-8": 28598,
+    "iso-8859-9": 28599,
+    "iso-8859-10": 28600,
+    "iso-8859-11": 28601,
+    "iso-8859-13": 28603,
+    "iso-8859-14": 28604,
+    "iso-8859-15": 28605,
+    "iso-8859-16": 28606,
+    "iso-2022": 50222,
+    "x-euc": 51932,
+    "euc-kr": 51949,
+    "gb18030": 54936,
+};

src/core/operations/ParseIMF.mjs

@@ -0,0 +1,181 @@
+/**
+ * @author bwhitn [brian.m.whitney@outlook.com]
+ * @copyright Crown Copyright 2016
+ * @license Apache-2.0
+ */
+
+ import Operation from "../Operation";
+ import OperationError from "../errors/OperationError";
+ import cptable from "../vendor/js-codepage/cptable.js";
+ import {fromBase64} from "../lib/Base64";
+ import {MIME_FORMAT} from "../lib/ChrEnc";
+
+
+ //TODO: fix function header
+ /**
+  * Return the conetent encoding for a mime section from a header object.
+  * CONTENT_TYPE returns the content type of a mime header from a header object.
+  * Returns the filename from a mime header object.
+  * Returns the boundary value for the mime section from a header object.
+  * @constant
+  * @default
+  */
+ const FIELD_ITEM = {
+     FILENAME: [/filename=".*?([^~#%&*\][\\:<>?/|]+)"/, "content-disposition"],
+     CONTENT_TYPE: [/\s*([^;\s]+)/, "content-type"],
+     BOUNDARY: [/boundary="(.+?)"/, "content-type"],
+     CHARSET: [/charset=([a-z0-9-]+)/, "content-type"],
+     TRANSER_ENCODING: [/\s*([A-Za-z0-9-]+)\s*/, "content-transfer-encoding"],
+ }
+
+ /**
+  * @constant
+  * @default
+  */
+ //TODO: should 8 bit and 7 bit be treated the same?
+ const DECODER = {
+     "base64": function (input) {
+         return Utils.fromBase64(input, Base64.ALPHABET, "string", true);
+     },
+     "quoted-printable": function (input) {
+         return QuotedPrintable.mimeDecode(input);
+     },
+     "7bit": function (input) {
+         return input;
+     },
+     "8bit": function (input) {
+         return input;
+     },
+ }
+
+
+ class ParseIMF extends Operation {
+
+   /**
+    * Internet MessageFormat constructor
+    */
+  constructor() {
+    super();
+    this.name = "Parse Internet Message Format";
+    this.module = "Default";
+    this.description = ["Parser an IMF formatted messages following RFC5322.",
+      "<br><br>",
+      "Parses an IMF formated message. These often have the file extention &quot;.eml&quote; and contain the email headers and body. The output will be a file list of the headers and mime parts.",
+    ].join("\n");
+    this.infoURL = "https://tools.ietf.org/html/rfc5322";
+    this.inputType = "string";
+    this.outputType = "string";
+    this.args = [];
+    }
+
+    /**
+      * Basic Email Parser that displays the header and mime sections as files.
+      *
+      * @param {string} input
+      * @param {Object[]} args
+      * @returns {string}
+      */
+  run(input, args) {
+    if (!input) {
+        return;
+    }
+    let headerBody = Email._splitHeaderFromBody(input);
+    let header = headerBody[0];
+    let headerArray = Email._parseHeader(header);
+    if (args[0]) {
+        header = Email._replaceDecodeWord(header);
+    }
+    return JSON.stringify(headerArray);
+  }
+
+  /**
+   * Breaks the header from the body and returns [header, body]
+   *
+   * @param {string} input
+   * @returns {string[]}
+   */
+  splitHeaderFromBody(input) {
+      const emlRegex = /^([\x20-\x7e\n\r\t]+?)(?:\r?\n){2}([\x20-\x7e\t\n\r]*)/;
+      let splitEmail = emlRegex.exec(input);
+      if (splitEmail) {
+          //TODO: Array splice vs shift?
+          splitEmail.shift();
+          return splitEmail;
+      }
+  }
+
+  /**
+   * Takes a string and decodes quoted words inside them
+   * These take the form of =?utf-8?Q?Hello?=
+   *
+   * @param {string} input
+   * @returns {string}
+   */
+  replaceDecodeWord(input) {
+      return input.replace(/=\?([^?]+)\?(Q|B)\?([^?]+)\?=/g, function (a, charEnc, contEnc, input) {
+          //TODO fix Q encoding as it isn't identical to quoted-printable. ie _=" "
+          contEnc = (contEnc === "B") ? "base64" : "quoted-printable";
+          return this.decodeMimeData(input, charEnc, contEnc);
+      });
+  }
+
+  /**
+   * Breaks a header into a object to be used by other functions.
+   * It removes any line feeds or carriage returns from the values and
+   * replaces it with a space.
+   *
+   * @param {string} input
+   * @returns {object}
+   */
+  parseHeader(input) {
+      const sectionRegex = /([A-Z-]+):\s+([\x20-\x7e\r\n\t]+?)(?=$|\r?\n\S)/gi;
+      let header = {}, section;
+      while ((section = sectionRegex.exec(input))) {
+          let fieldName = section[1].toLowerCase();
+          let fieldValue = section[2].replace(/\n|\r/g, " ");
+          if (header[fieldName]) {
+              header[fieldName].push(fieldValue);
+          } else {
+              header[fieldName] = [fieldValue];
+          }
+      }
+      return header;
+  }
+
+  /**
+   * Return decoded MIME data given the character encoding and content encoding.
+   *
+   * @param {string} input
+   * @param {string} charEnc
+   * @param {string} contEnc
+   * @returns {string}
+   */
+  decodeMimeData(input, charEnc, contEnc) {
+      //TODO: make exceptions for unknown charEnc and contEnc?
+      input = this.DECODER[contEnc](input);
+      if (charEnc) {
+          input = cptable.utils.decode(this.MIME_FORMAT[charEnc.toLowerCase()], input);
+      }
+      return input;
+  }
+
+  /**
+   * Returns a header item given a header object, itemName, and index number.
+   *
+   * @param {object} header
+   * @param {object} FIELD_ITEM
+   * @param {integer} fieldNum
+   * @returns {string}
+   */
+  getHeaderItem(header, fieldItem, fieldNum = 0){
+      if (fieldItem[1] in header && header[fieldItem[1]].length > fieldNum) {
+          let field = header[fieldItem[1]][fieldNum], item;
+          if ((item = fieldItem[0].exec(field))) {
+              return item[1];
+          }
+      }
+  }
+
+}
+
+export default ParseIMF