Update of /cvsroot/mrpostman/mrpostman/src/org/mrbook/mrpostman/maildotcom In directory sc8-pr-cvs1:/tmp/cvs-serv10610/mrpostman/src/org/mrbook/mrpostman/maildotcom Added Files: Attachment.java MailMessage.java PatternTest.java MailDotComMessageParser.java MailDotComMessageParserTest.java MailIdentifier.java Log Message: --- NEW FILE: Attachment.java --- /* * -*- mode: java; c-basic-indent: 4; indent-tabs-mode: nil -*- * :indentSize=4:noTabs=true:tabSize=4:indentOnTab=true:indentOnEnter=true:mode=java: * ex: set tabstop=4 expandtab: * * MrPostman - webmail <-> email gateway * Copyright (C) 2002-2003 MrPostman Development Group * Projectpage: http://mrbook.org/mrpostman/ * * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * In particular, this implies that users are responsible for * using MrPostman after reading the terms and conditions given * by their web-mail provider. * * You should have received a copy of the GNU General Public License * Named LICENSE in the base directory of this distribution, * if not, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ package org.mrbook.mrpostman.maildotcom; import java.util.Collection; import java.util.LinkedHashMap; import java.util.ArrayList; import java.util.Iterator; /** * @author chris * Represents an Attachment in the MailDotComMessageParser */ public class Attachment { private String partId = null; private String filename = null; private String url = null; private LinkedHashMap headerLines = null; private ArrayList bodyLines; private String bodyDelimiter = null; /** * */ public Attachment() { super(); headerLines = new LinkedHashMap(); bodyLines = new ArrayList(); } /** * @return */ public String getFilename() { return filename; } /** * @return */ public String getPartId() { return partId; } /** * @param string */ public void setFilename(String string) { filename = string; } /** * @param string */ public void setPartId(String string) { partId = string; } /** * @return */ public String getUrl() { return url; } /** * @param string */ public void setUrl(String string) { url = string; } public void addHeaderLine(String headerKeyStr, String headerValueStr) { headerLines.put(headerKeyStr, headerValueStr); } public void addBodyLine(String line) { bodyLines.add(line); } public String toString() { StringBuffer buff = new StringBuffer(); if (!isEmbeddedAttachment()) { buff.append("Attachment URL: ").append(url); buff.append("\nFilename: ").append(filename); buff.append("\nPartId: ").append(partId); buff.append(headerLines.toString()).append("\n"); } else { buff.append("Inline Attachement\n"); buff.append(headerLines.toString()).append("\n"); for (Iterator it = bodyLines.iterator(); it.hasNext(); ) { buff.append((String)it.next()).append("\n"); } } return buff.toString(); } /** * @return */ public boolean isEmbeddedAttachment() { return bodyLines.size() > 0; } /** * @param string */ public void setBodyDelimiter(String string) { bodyDelimiter = string; } /** * @return */ public String getBodyDelimiter() { return bodyDelimiter; } public String getHeader(String key) { return (String)headerLines.get(key); } public Collection getBodyLines() { return bodyLines; } public LinkedHashMap getHeaders() { return headerLines; } } --- NEW FILE: MailMessage.java --- /* * -*- mode: java; c-basic-indent: 4; indent-tabs-mode: nil -*- * :indentSize=4:noTabs=true:tabSize=4:indentOnTab=true:indentOnEnter=true:mode=java: * ex: set tabstop=4 expandtab: * * MrPostman - webmail <-> email gateway * Copyright (C) 2002-2003 MrPostman Development Group * Projectpage: http://mrbook.org/mrpostman/ * * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * In particular, this implies that users are responsible for * using MrPostman after reading the terms and conditions given * by their web-mail provider. * * You should have received a copy of the GNU General Public License * Named LICENSE in the base directory of this distribution, * if not, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ package org.mrbook.mrpostman.maildotcom; import java.util.Collection; import java.util.ArrayList; import java.util.Iterator; import java.util.LinkedHashMap; /** * Helper class to represent a Message * @author chris * */ public class MailMessage { private LinkedHashMap headerLines = null; private ArrayList attachments = null; private ArrayList bodyLines; private String boundary; private int attachmentCount; private LinkedHashMap bodyHeaderLines = null; /** * Counter used when generating part numbers when constructing MIME encoded message... */ private int tmpPartCount = 0; public MailMessage() { headerLines = new LinkedHashMap(); bodyLines = new ArrayList(); bodyHeaderLines = new LinkedHashMap(); attachments = new ArrayList(); attachmentCount = -1; } public void addBodyLine(String line) { bodyLines.add(line); } public void addHeaderLine(String key, String value) { headerLines.put(key, value); } public String getHeader(String key) { return (String)headerLines.get(key); } public void addBodyHeaderLine(String key, String value) { bodyHeaderLines.put(key, value); } public String getBodyHeader(String key) { return (String)bodyHeaderLines.get(key); } public void addAttachment(Attachment attachment) { attachments.add(attachment); } public Attachment getCurrentAttachment() { return (Attachment) attachments.get(attachmentCount); } public String toString() { StringBuffer buff = new StringBuffer(); for(Iterator it = headerLines.keySet().iterator(); it.hasNext();) { String hdrKey = (String)it.next(); String value = (String)headerLines.get(hdrKey); buff.append(hdrKey + ": " + value).append("\n"); } buff.append("\n"); for(Iterator it = bodyHeaderLines.keySet().iterator(); it.hasNext();) { String hdrKey = (String)it.next(); String value = (String)bodyHeaderLines.get(hdrKey); buff.append(hdrKey + ": " + value).append("\n"); } buff.append("\n"); for(Iterator it = bodyLines.iterator(); it.hasNext();) { buff.append((String)it.next()).append("\n"); } buff.append(attachments); return buff.toString(); } /** * @return */ public int getAttachmentCount() { return attachmentCount; } /** * @param i */ public void setAttachmentCount(int i) { attachmentCount = i; } public void incrementAttachmentCount() { attachmentCount++; } public int getNumberAttachments() { return attachments.size(); } public Collection getBodyLines() { return bodyLines; } /** * Return the Attachment at specified index (starting from 0) * @throws IndexOutOfBoundsException if invalid index passed * @param index * @return */ public Attachment getAttachment(int index) throws IndexOutOfBoundsException { return (Attachment)attachments.get(index); } /** * @return */ public String getBoundary() { return boundary; } /** * @param string */ public void setBoundary(String string) { boundary = string; } /** * @return */ public int getTmpPartCount() { return tmpPartCount; } /** * @param i */ public void setTmpPartCount(int i) { tmpPartCount = i; } public LinkedHashMap getBodyHeaders() { return bodyHeaderLines; } public LinkedHashMap getHeaders() { return headerLines; } /** * Utility method to return a LinkedHasMap (as used in our Header lists) into * a flat list of encoded header lines i.e. "key: value" * @return Collection */ public static Collection getHeadersAsCollection(LinkedHashMap lhmap) { ArrayList list = new ArrayList(lhmap.keySet().size()); for(Iterator it = lhmap.keySet().iterator(); it.hasNext();) { String hdrKey = (String)it.next(); String value = (String)lhmap.get(hdrKey); list.add(hdrKey + ": " + value); } return list; } } --- NEW FILE: PatternTest.java --- /* * -*- mode: java; c-basic-indent: 4; indent-tabs-mode: nil -*- * :indentSize=4:noTabs=true:tabSize=4:indentOnTab=true:indentOnEnter=true:mode=java: * ex: set tabstop=4 expandtab: * * MrPostman - webmail <-> email gateway * Copyright (C) 2002-2003 MrPostman Development Group * Projectpage: http://mrbook.org/mrpostman/ * * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * In particular, this implies that users are responsible for * using MrPostman after reading the terms and conditions given * by their web-mail provider. * * You should have received a copy of the GNU General Public License * Named LICENSE in the base directory of this distribution, * if not, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ package org.mrbook.mrpostman.maildotcom; import java.util.regex.Matcher; import java.util.regex.Pattern; /** * @author chris * Simple class to test Patterns during development */ public class PatternTest { /** * */ public PatternTest() { super(); } public static void main(String[] args) { String line = "<A HREF=\"/getattach/attach1.zip?folder=INBOX&msg_uid=1073739904&filename=attach1.zip&partsno=3\" target=\"_blank\"><FONT COLOR=\"BLUE\">attach1.zip</FONT></A></STRONG><BR>"; Pattern attachPattern = Pattern.compile("^.*?<A HREF=\"(/getattach/(.*)\\?folder=INBOX&msg_uid=(.*)&filename=(.*)&partsno=(.*))\".*?>.*$"); Matcher match = attachPattern.matcher(line); if (match.find()) { System.out.println(match.group(1)); System.out.println(match.group(2)); System.out.println(match.group(3)); } else { System.out.println("No match"); } } } --- NEW FILE: MailDotComMessageParser.java --- /* * -*- mode: java; c-basic-indent: 4; indent-tabs-mode: nil -*- * :indentSize=4:noTabs=true:tabSize=4:indentOnTab=true:indentOnEnter=true:mode=java: * ex: set tabstop=4 expandtab: * * MrPostman - webmail <-> email gateway * Copyright (C) 2002-2003 MrPostman Development Group * Projectpage: http://mrbook.org/mrpostman/ * * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * In particular, this implies that users are responsible for * using MrPostman after reading the terms and conditions given * by their web-mail provider. * * You should have received a copy of the GNU General Public License * Named LICENSE in the base directory of this distribution, * if not, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ package org.mrbook.mrpostman.maildotcom; import java.util.regex.Matcher; import java.util.regex.Pattern; import java.util.logging.Logger; import java.io.BufferedReader; import java.io.IOException; /** * @author chris * * Parse the message data returned from Mail.com into an object representation suitable for encoding into a * MIME message */ public class MailDotComMessageParser { private static Logger logger = Logger.getLogger( "org.mrbook.mrpostman.maildotcom.MailDotComMessageParser"); //State settings private static final int START = 0; private static final int PROCESSING_HEADER = 1; private static final int FINDING_BODY = 2; private static final int PROCESSING_BODY = 3; private static final int FINDING_ATTACHMENT = 4; private static final int PROCESSING_ATTACHMENT = 5; private static final int PROCESSING_INLINE_ATTACHMENT = 6; private static final int STOPPED = 9; private static final int DONE = 10; /** * Represents the state of the parser. */ private int state = START; /** * Represents the delimeter used around the body of the message. Can be either * TEXT_BODY_DELIM or HTML_BODY_DELIM */ private String bodyDelimiter = null; private MailMessage message = null; //Message and attachment patterns... private Pattern bfieldpattern = Pattern.compile("<b>([^:]*):.*</b>"); private Pattern bbfieldpattern = Pattern.compile("<B>([^:]*):.*</B>\\s*(.*)\\s*<BR>"); private Pattern attachPattern = Pattern.compile("^.*?<A HREF=\"(/getattach/(.*)\\?folder=INBOX&msg_uid=(.*)&filename=(.*)&partsno=(\\d+))\".*?>.*$"); //Pattern.compile("<a target=\"_blank\" href=\"(.*)\">"); private Pattern attachStartPattern = Pattern.compile("^<HR SIZE=1>$"); private static final String TEXT_BODY_START_DELIM = "<PRE>"; private static final String TEXT_BODY_END_DELIM = "</PRE>"; private static final String HTML_BODY_START_DELIM = "<XHTML>"; private static final String HTML_BODY_END_DELIM = "</XHTML>"; /** * */ public MailDotComMessageParser() { super(); state = START; } /** * Process the message. * This method is called for each line in the received message * Returns the number of body lines processed. This is used to stop parsing if this is just a TOP command */ MailMessage processMessage(BufferedReader br, int numLines) throws IOException { //The message may be embedded between <PRE> </PRE> tags if sent in Text //or in <xhtml></xhtml> if sent in HTML //The same message may contain both if sent in both TEXT and HTM but the others will be as different //body parts boolean insidePre = false; boolean insideXHTML = false; int lineNo = 0; logger.finest("*** Starting message processing ***"); //Create our structure to store the parsed message content... message = new MailMessage(); String line = null; //We start by finding and processing the header... state = PROCESSING_HEADER; while ((line = br.readLine()) != null && state != DONE) { logger.finest("MailDotComMessageParser html: " + line); // TODO - I suspect this may happen - but am not sure so if you // see this in your log let me know! - CH if (line.indexOf("Your Mail.com session is sponsored by:") > -1) { logger.warning("*** SPONSOR PAGE ***"); } //Process the header... switch (state) { case PROCESSING_HEADER : processMessageHeader(br, line); break; case FINDING_BODY : processMessageFindStartOfBody(br, line); break; case PROCESSING_BODY : processMessageBody(br, line); break; case FINDING_ATTACHMENT : findingAttachments(br, line); break; case PROCESSING_ATTACHMENT : processAttachments(br, line); break; case PROCESSING_INLINE_ATTACHMENT : processInlineAttachmentBody(br, line); break; } //A TOP command can stop this processing prematurely... if (numLines > -1) { if (lineNo >= numLines) { state = STOPPED; break; } } } //end while logger.finest(message.toString()); logger.finest("*** Finished message processing ***"); return message; } /** * Process the message header. * * @param message * @param br * @param numLines * @param line * @return * @throws IOException */ void processMessageHeader( BufferedReader br, String line) throws IOException { String headerKeyStr = null; String headerValueStr = null; String line2 = null; boolean processedHeader = false; //There are two formats for header values, we'll handle them both.. Matcher match = bfieldpattern.matcher(line); if (match.find()) { /* In this case the header key is on one line, the value is on the next. e.g. <b>To:</b> MrPostman <mrp...@ma...><br> */ headerKeyStr = match.group(1); line2 = br.readLine(); headerValueStr = unescape(line2.substring(0, line2.length() - 4)); } else { match = bbfieldpattern.matcher(line); if (match.find()) { /* key and header on same line. e.g. <b>Return-Path:</b> <ch...@so...><br> */ headerKeyStr = match.group(1); headerValueStr = unescape(match.group(2)); } } //If we found a header line then process this information here... if (headerKeyStr != null) { message.addHeaderLine(headerKeyStr, headerValueStr); logger.fine( "Found header: " + headerKeyStr + " : " + headerValueStr); } else { //We may have processed all our header fields, we'll know this if they have sent //a </p> on its own if (line.equals("</p>")) { logger.fine("Finished processing header, </p> found."); state = FINDING_BODY; } } } /** * Process the message and wait for start of message body * * If we have processed the header, check for body part content-type lines * and the start of the body data (if present). e.g. * <b>Content-Type:</b> text/html; charset=us-ascii<br> * <b>Content-Transfer-Encoding:</b> 7bit<br> * <br> * <xhtml> * * or * * <PRE>hi this is the body text * </PRE> * * @param message * @param br * @param line * @return * @throws IOException */ void processMessageFindStartOfBody( BufferedReader br, String line) throws IOException { // For messages with a body type other than TEXT additional content-type lines // will be present... Matcher match = bbfieldpattern.matcher(line); if (match.find()) { /* key and header on same line. e.g. <b>Content-Type:</b> text/html; charset=us-ascii<br> */ String headerKeyStr = match.group(1); String headerValueStr = unescape(match.group(2)); logger.fine( "Found body part header: " + headerKeyStr + " : " + headerValueStr); message.addBodyHeaderLine(headerKeyStr, headerValueStr); } else if (line.toUpperCase().startsWith(TEXT_BODY_START_DELIM)) { bodyDelimiter = TEXT_BODY_START_DELIM; state = PROCESSING_BODY; logger.fine( "We have entered body - delimited by " + TEXT_BODY_START_DELIM); //we'll strip the pre tag message.addBodyLine(line.substring(TEXT_BODY_START_DELIM.length())); } else if (line.toUpperCase().startsWith(HTML_BODY_START_DELIM)) { bodyDelimiter = HTML_BODY_START_DELIM; state = PROCESSING_BODY; logger.fine( "We have entered body - delimited by " + HTML_BODY_START_DELIM); //we'll leave the xhtml tags complete message.addBodyLine(line); } } /** * Process the message body. * * @param message * @param br * @param line * @return * @throws IOException */ void processMessageBody( BufferedReader br, String line) throws IOException { boolean addLineToBody = false; if (bodyDelimiter.equals(TEXT_BODY_START_DELIM)) { // check if we have finished the body part... if (line.toUpperCase().startsWith(TEXT_BODY_END_DELIM)) { logger.fine( "We are have left body - delimited by " + TEXT_BODY_END_DELIM); bodyDelimiter = null; state = FINDING_ATTACHMENT; } else { //Add this line to our body content... addLineToBody = true; } } else if (bodyDelimiter.equals(HTML_BODY_START_DELIM)) { // check if we have finished the body part... if (line.toUpperCase().startsWith(HTML_BODY_END_DELIM)) { logger.fine( "We are have left body - delimited by " + HTML_BODY_END_DELIM); bodyDelimiter = null; state = FINDING_ATTACHMENT; // include the </xhtml> end tag in the body content... addLineToBody = true; } else { //Add this line to our body content... addLineToBody = true; } } if (addLineToBody) { message.addBodyLine(line); } } /** * Find any attachments in the message. * This method is called for each line in the received message after the main body has been processed. * * Attachments always start with: * <hr size="1"> */ private void findingAttachments(BufferedReader br, String line) { //Check for attachment start... Matcher match = attachStartPattern.matcher(line.toUpperCase()); if (match.find()) { Attachment attachment = new Attachment(); message.incrementAttachmentCount(); message.addAttachment(attachment); logger.fine("Found attachment start."); state = PROCESSING_ATTACHMENT; } } /** * Process any attachments in the message. * This method is called for each line in the received message after the main body has been processed. * * Attachments which are not inline will appear similar to this: * <hr size="1"> * <b>Content-Type:</b> application/zip; name="attach2.zip"<br> * <b>Content-Transfer-Encoding:</b> base64<br> * <b>Content-Disposition:</b> inline; filename="attach2.zip"<br> * <br> * <br><strong><a target="_blank" href="http://mail01.mail.com/getattach/attach2.zip?folder=INBOX&msg_uid=1073240058&filename=attach2.zip&partsno=2"><font color="BLUE">attach2.zip</font></a></strong><br> * */ private void processAttachments(BufferedReader br, String line) { // Attachments will have content type header lines... Matcher match = bbfieldpattern.matcher(line); if (match.find()) { /* key and header on same line. e.g. <b>Content-Type:</b> text/html; charset=us-ascii<br> */ String headerKeyStr = match.group(1); String headerValueStr = unescape(match.group(2)); logger.fine( "Found attachment header: " + headerKeyStr + " : " + headerValueStr); message.getCurrentAttachment().addHeaderLine(headerKeyStr, headerValueStr); } //Attachments can be inline for mime types which the browser can display or as links... //Check for attachment links... match = attachPattern.matcher(line); if (match.find()) { String attachmentUrl = match.group(1); String filename = match.group(4); String partno = match.group(5); message.getCurrentAttachment().setFilename(filename); message.getCurrentAttachment().setUrl(attachmentUrl); message.getCurrentAttachment().setPartId(partno); logger.fine("Found attachment: " + message.getCurrentAttachment().toString()); //finished this attachment... state = FINDING_ATTACHMENT; } //Check for inline attachments... if (line.toUpperCase().startsWith(TEXT_BODY_START_DELIM)) { message.getCurrentAttachment().setBodyDelimiter(TEXT_BODY_START_DELIM); state = PROCESSING_INLINE_ATTACHMENT; logger.fine("We have entered inline attachment body - delimited by " + TEXT_BODY_START_DELIM); //we'll strip the pre tag message.getCurrentAttachment().addBodyLine(line.substring(TEXT_BODY_START_DELIM.length())); } else if (line.toUpperCase().startsWith(HTML_BODY_START_DELIM)) { message.getCurrentAttachment().setBodyDelimiter(HTML_BODY_START_DELIM); state = PROCESSING_INLINE_ATTACHMENT; logger.fine("We have entered inline attachment body - delimited by " + HTML_BODY_START_DELIM); //we'll leave the xhtml tags complete message.getCurrentAttachment().addBodyLine(line); } } /** * Process the inline attachment body. * * @param message * @param br * @param line * @return * @throws IOException */ void processInlineAttachmentBody( BufferedReader br, String line) throws IOException { boolean addLineToBody = false; if (message.getCurrentAttachment().getBodyDelimiter().equals(TEXT_BODY_START_DELIM)) { // check if we have finished the body part... if (line.toUpperCase().startsWith(TEXT_BODY_END_DELIM)) { logger.fine( "We are have left body - delimited by " + TEXT_BODY_END_DELIM); state = FINDING_ATTACHMENT; } else { //Add this line to our body content... addLineToBody = true; } } else if (message.getCurrentAttachment().getBodyDelimiter().equals(HTML_BODY_START_DELIM)) { // check if we have finished the body part... if (line.toUpperCase().startsWith(HTML_BODY_END_DELIM)) { logger.fine( "We are have left body - delimited by " + HTML_BODY_END_DELIM); state = FINDING_ATTACHMENT; // include the </xhtml> end tag in the body content... addLineToBody = true; } else { //Add this line to our body content... addLineToBody = true; } } if (addLineToBody) { message.getCurrentAttachment().addBodyLine(line); } } private String unescape(String mystr) { String line = mystr.replaceAll("\\&", "\\&"); line = line.replaceAll("\\<", "<"); line = line.replaceAll("\\>", ">"); line = line.replaceAll("\\"", "\""); line = line.replaceAll("\\"", "\""); return line; } /** * @return */ public MailMessage getMessage() { return message; } } --- NEW FILE: MailDotComMessageParserTest.java --- /* * -*- mode: java; c-basic-indent: 4; indent-tabs-mode: nil -*- * :indentSize=4:noTabs=true:tabSize=4:indentOnTab=true:indentOnEnter=true:mode=java: * ex: set tabstop=4 expandtab: * * MrPostman - webmail <-> email gateway * Copyright (C) 2002-2003 MrPostman Development Group * Projectpage: http://mrbook.org/mrpostman/ * * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * In particular, this implies that users are responsible for * using MrPostman after reading the terms and conditions given * by their web-mail provider. * * You should have received a copy of the GNU General Public License * Named LICENSE in the base directory of this distribution, * if not, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ package org.mrbook.mrpostman.maildotcom; import java.io.*; import java.util.ArrayList; import java.util.Collection; import java.util.Iterator; import junit.framework.TestCase; //TODO - Add test case with two embedded attachments public class MailDotComMessageParserTest extends TestCase { //FILE1 = HTML with TXT attachment... public static final String MSG_FILE1 = "test/mesg1.mail.htm"; //FILE2 = HTML with ZIP attachment... public static final String MSG_FILE2 = "test/mesg2.mail.htm"; //FILE3 = TEXT body... public static final String MSG_FILE3 = "test/mesg3.mail.htm"; //FILE4 = HTML with HTML attachment... public static final String MSG_FILE4 = "test/mesg4.mail.htm"; //FILE5 - HTML with image attachment... public static final String MSG_FILE5 = "test/mesg5.mail.htm"; //FILE6 - HTML with 2 zip attachments... public static final String MSG_FILE6 = "test/mesg6.mail.htm"; //FILE7 - Multipart/alternative HTML and TEXT public static final String MSG_FILE7 = "test/mesg7.mail.htm"; public MailDotComMessageParserTest(String name) { super(name); } /** * This code will verify that the html message body code is working correctly * This code will also verify that the inline text attachment code is working correctly * @throws Exception */ public void testParserFile1() throws Exception { try { MailMessage msg = runParser(MSG_FILE1); // check headers... assertEquals(msg.getHeader("From"), "Chris Humphreys <ch...@so...>"); assertEquals(msg.getHeader("To"), "MrPostman <mrp...@ma...>"); assertEquals(msg.getHeader("Subject"), "test html with txt attachment"); assertEquals(msg.getHeader("Date"), "Sat, 10 Jan 2004 13:02:56 +0000"); // check msg body... assertEquals(msg.getBodyHeader("Content-Type"), "text/html; charset=us-ascii"); assertTrue(comparePartBodies(msg.getBodyLines(), createMsg1Body())); // check attachment... assertEquals(1, msg.getNumberAttachments()); assertTrue(msg.getAttachment(0).isEmbeddedAttachment()); assertEquals(msg.getAttachment(0).getHeader("Content-Type"), "text/plain; name=\"attach1.txt\""); assertEquals((String)msg.getAttachment(0).getBodyLines().iterator().next(), "text of attachment"); //correct! } catch (Exception e) { fail("Exception " + e.getMessage()); } } /** * This test will verify that the attachment link code is working correctly * @throws Exception */ public void testParserFile2() throws Exception { try { MailMessage msg = runParser(MSG_FILE2); // check headers... assertEquals(msg.getHeader("From"), "Chris Humphreys <ch...@so...>"); assertEquals(msg.getHeader("To"), "MrPostman <mrp...@ma...>"); assertEquals(msg.getHeader("Subject"), "test with zip attachment"); assertEquals(msg.getHeader("Date"), "Sun, 04 Jan 2004 18:14:06 +0000"); // we'll assume msg body works ok as it is similar to test1. // check attachment... assertEquals(1, msg.getNumberAttachments()); assertFalse(msg.getAttachment(0).isEmbeddedAttachment()); assertEquals(msg.getAttachment(0).getHeader("Content-Type"), "application/zip; name=\"attach2.zip\""); assertEquals(msg.getAttachment(0).getFilename(), "attach2.zip"); assertEquals(msg.getAttachment(0).getUrl(), "/getattach/attach2.zip?folder=INBOX&msg_uid=1073240058&filename=attach2.zip&partsno=2"); //correct! } catch (Exception e) { fail("Exception " + e.getMessage()); } } /** * This test verifies that the Header code and the TEXT body code works correctly. * @throws Exception */ public void testParserFile3() throws Exception { try { MailMessage msg = runParser(MSG_FILE3); // check headers... assertEquals(msg.getHeader("From"), "Chris Humphreys <ch...@so...>"); assertEquals(msg.getHeader("To"), "MrPostman <mrp...@ma...>"); assertEquals(msg.getHeader("Subject"), "single body text"); assertEquals(msg.getHeader("Date"), "Tue, 06 Jan 2004 21:36:38 +0000"); // check msg body... assertEquals(msg.getHeader("Content-Type"), "text/plain; charset=us-ascii; format=flowed"); assertEquals(msg.getHeader("Content-Transfer-Encoding"), "7bit"); assertEquals((String)msg.getBodyLines().iterator().next(),"hi this is the body text"); // check attachment... assertEquals(0, msg.getNumberAttachments()); // correct! } catch (Exception e) { fail("Exception " + e.getMessage()); } } /** * This test verifies the inline HTML attachment code works correctly * @throws Exception */ public void testParserFile4() throws Exception { try { MailMessage msg = runParser(MSG_FILE4); //we'll assume headers work correctly... //we'all assume html body works correctly... // check attachment... assertEquals(1, msg.getNumberAttachments()); assertTrue(msg.getAttachment(0).isEmbeddedAttachment()); assertEquals(msg.getAttachment(0).getHeader("Content-Type"), "text/html; name=\"attach3.html\""); assertTrue(comparePartBodies(msg.getAttachment(0).getBodyLines(), createMsg4AttachmentBody())); //correct! } catch (Exception e) { fail("Exception " + e.getMessage()); } } /** * This test verifies that image attachment code works correctly * This message has an blank html body and JPG attachment * @throws Exception */ public void testParserFile5() throws Exception { try { MailMessage msg = runParser(MSG_FILE5); // we'll assume headers work correctly... //we'all assume html body works correctly... // check attachment... assertEquals(1, msg.getNumberAttachments()); assertFalse(msg.getAttachment(0).isEmbeddedAttachment()); assertEquals(msg.getAttachment(0).getHeader("Content-Type"), "image/jpeg; name=\"gui-1.jpg\""); assertEquals(msg.getAttachment(0).getUrl(), "/getattach/gui-1.jpg?folder=INBOX&msg_uid=1073739625&filename=gui-1.jpg&partsno=2"); assertEquals(msg.getAttachment(0).getFilename(), "gui-1.jpg"); //correct! } catch (Exception e) { fail("Exception " + e.getMessage()); } } /** * This test verifies that multiple non-embedded attachment code * works correctly * @throws Exception */ public void testParserFile6() throws Exception { try { MailMessage msg = runParser(MSG_FILE6); //we'll assume headers work correctly... //we'all assume html body works correctly... // check attachment... assertEquals(2, msg.getNumberAttachments()); assertFalse(msg.getAttachment(0).isEmbeddedAttachment()); assertEquals(msg.getAttachment(0).getHeader("Content-Type"), "application/zip; name=\"attach2.zip\""); assertEquals(msg.getAttachment(0).getUrl(), "/getattach/attach2.zip?folder=INBOX&msg_uid=1073739904&filename=attach2.zip&partsno=2"); assertEquals(msg.getAttachment(0).getFilename(), "attach2.zip"); assertFalse(msg.getAttachment(1).isEmbeddedAttachment()); assertEquals(msg.getAttachment(1).getHeader("Content-Type"), "application/zip; name=\"attach1.zip\""); assertEquals(msg.getAttachment(1).getUrl(), "/getattach/attach1.zip?folder=INBOX&msg_uid=1073739904&filename=attach1.zip&partsno=3"); assertEquals(msg.getAttachment(1).getFilename(), "attach1.zip"); //correct! } catch (Exception e) { fail("Exception " + e.getMessage()); } } /** * This test verifies that the Header code and the TEXT body code works correctly. * Mail.com will infact just return the HTML version and ignore the TEXT version * @throws Exception */ public void testParserFile7() throws Exception { try { MailMessage msg = runParser(MSG_FILE7); // check headers... assertEquals(msg.getHeader("From"), "Chris Humphreys <ch...@so...>"); assertEquals(msg.getHeader("To"), "MrPostman <mrp...@ma...>"); assertEquals(msg.getHeader("Subject"), "multipart alternative"); assertEquals(msg.getHeader("Date"), "Sun, 11 Jan 2004 19:19:06 +0000"); // check msg body... assertEquals(msg.getBodyHeader("Content-Type"), "text/html; charset=us-ascii"); assertEquals(msg.getBodyHeader("Content-Transfer-Encoding"), "7bit"); assertTrue(comparePartBodies(msg.getBodyLines(), createMsg7Body())); // check attachment... assertEquals(0, msg.getNumberAttachments()); // correct! } catch (Exception e) { fail("Exception " + e.getMessage()); } } private MailMessage runParser(String fileName) throws Exception { BufferedReader br = new BufferedReader( new FileReader(fileName)); MailDotComMessageParser parser = new MailDotComMessageParser(); parser.processMessage(br, -1); MailMessage message = parser.getMessage(); return message; } private Collection createMsg1Body() { //see message1.eml //Note: it is given that mail.com will convert the file to xhtml ArrayList bodyLines = new ArrayList(); bodyLines.add("<xhtml>"); bodyLines.add("<head>"); bodyLines.add(" <xmeta http-equiv=\"Content-Type\" content=\"text/html;charset=ISO-8859-1\">"); bodyLines.add(" <title></title>"); bodyLines.add("</head>"); bodyLines.add("<xbody text=\"#000000\" bgcolor=\"#ffffff\">"); bodyLines.add("hi there html body<br>"); bodyLines.add("</xbody>"); bodyLines.add("</xhtml>"); return bodyLines; } private Collection createMsg4AttachmentBody() { //see message4.eml //Note: it is given that mail.com will convert the file to xhtml ArrayList bodyLines = new ArrayList(); bodyLines.add("<xhtml>"); bodyLines.add("<xbody>"); bodyLines.add("attachment"); bodyLines.add("</xbody>"); bodyLines.add("</xhtml>"); return bodyLines; } private Collection createMsg7Body() { //see message7.eml //Note: it is given that mail.com will convert the file to xhtml ArrayList bodyLines = new ArrayList(); bodyLines.add("<xhtml>"); bodyLines.add("<head>"); bodyLines.add(" <xmeta http-equiv=\"Content-Type\" content=\"text/html;charset=ISO-8859-1\">"); bodyLines.add(" <title></title>"); bodyLines.add("</head>"); bodyLines.add("<xbody text=\"#000000\" bgcolor=\"#ffffff\">"); bodyLines.add("There are two bodies on this message!<br>"); bodyLines.add("</xbody>"); bodyLines.add("</xhtml>"); return bodyLines; } private boolean comparePartBodies(Collection bodyALines, Collection bodyBLines) { Iterator itB = bodyBLines.iterator(); Iterator itA = bodyALines.iterator(); boolean equal = true; while (true) { if (itA.hasNext()) { if (!itB.hasNext()) { equal = false; break; } else { //we have two lines, lets compare them... String lineA = (String)itA.next(); if (!lineA.equals((String)itB.next())) { equal = false; break; } } } else { if (itB.hasNext()) { equal = false; break; } else { break; } } } return equal; } } --- NEW FILE: MailIdentifier.java --- /* * -*- mode: java; c-basic-indent: 4; indent-tabs-mode: nil -*- * :indentSize=4:noTabs=true:tabSize=4:indentOnTab=true:indentOnEnter=true:mode=java: * ex: set tabstop=4 expandtab: * * MrPostman - webmail <-> email gateway * Copyright (C) 2002-2003 MrPostman Development Group * Projectpage: http://mrbook.org/mrpostman/ * * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * In particular, this implies that users are responsible for * using MrPostman after reading the terms and conditions given * by their web-mail provider. * * You should have received a copy of the GNU General Public License * Named LICENSE in the base directory of this distribution, * if not, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ package org.mrbook.mrpostman.maildotcom; /** * @author chris * * Represents a MailIdentifier */ public class MailIdentifier { String MailID = null; String author = null; String date = null; String subject = null; boolean unread = false; boolean flagged = false; int size; boolean retrieveSuccess = false; /** * */ public MailIdentifier() { super(); } public String toString() { return new String( "MailID=" + MailID + ", unread=" + unread + " flagged=" + flagged + " size=" + size); } } |
