001/**
002The contents of this file are subject to the Mozilla Public License Version 1.1
003(the "License"); you may not use this file except in compliance with the License.
004You may obtain a copy of the License at http://www.mozilla.org/MPL/
005Software distributed under the License is distributed on an "AS IS" basis,
006WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License for the
007specific language governing rights and limitations under the License.
008
009The Original Code is "GroupPointer.java".  Description:
010"A GroupPointer is used when parsing traditionally encoded HL7 messages"
011
012The Initial Developer of the Original Code is University Health Network. Copyright (C)
0132001.  All Rights Reserved.
014
015Contributor(s): ______________________________________.
016
017Alternatively, the contents of this file may be used under the terms of the
018GNU General Public License (the  "GPL"), in which case the provisions of the GPL are
019applicable instead of those above.  If you wish to allow use of your version of this
020file only under the terms of the GPL and not to allow others to use your version
021of this file under the MPL, indicate your decision by deleting  the provisions above
022and replace  them with the notice and other provisions required by the GPL License.
023If you do not delete the provisions above, a recipient may use your version of
024this file under either the MPL or the GPL.
025
026*/
027
028package ca.uhn.hl7v2.parser;
029
030import java.util.StringTokenizer;
031
032/**
033 * Detects message encoding (ER7 / XML) without relying on any
034 * external dependencies
035 */
036public class EncodingDetector {
037
038        /**
039         * Non instantiable
040         */
041        private EncodingDetector() {
042                // nothing
043        }
044        
045        /**
046         * Returns true if the message is ER7 (pipe-and-hat) encoded
047         */
048    public static boolean isEr7Encoded(String theMessage) {
049        // quit if the string is too short
050        if (theMessage.length() < 4)
051            return false;
052
053        // see if it looks like this message is | encoded ...
054        boolean ok = true;
055
056        // string should start with "MSH"
057        if (!theMessage.startsWith("MSH"))
058            return false;
059
060        // 4th character of each segment should be field delimiter
061        char fourthChar = theMessage.charAt(3);
062        StringTokenizer st = new StringTokenizer(theMessage, String.valueOf(PipeParser.SEGMENT_DELIMITER), false);
063        while (st.hasMoreTokens()) {
064            String x = st.nextToken();
065            if (x.length() > 0) {
066                if (Character.isWhitespace(x.charAt(0)))
067                    x = PipeParser.stripLeadingWhitespace(x);
068                if (x.length() >= 4 && x.charAt(3) != fourthChar)
069                    return false;
070            }
071        }
072
073        // should be at least 11 field delimiters (because MSH-12 is required)
074        int nextFieldDelimLoc = 0;
075        for (int i = 0; i < 11; i++) {
076            nextFieldDelimLoc = theMessage.indexOf(fourthChar, nextFieldDelimLoc + 1);
077            if (nextFieldDelimLoc < 0)
078                return false;
079        }
080        
081        return ok;
082        }
083
084    
085        /**
086         * Returns true if the message is XML encoded. Note that this 
087         * message does not perform a very robust check, and does not
088         * validate for well-formedness. It is only intended to perform
089         * a simple check for XML vs. ER7 messages.
090         */
091        public static boolean isXmlEncoded(String theMessage) {
092        //check for a number of expected strings 
093        String[] expected = { "<MSH.1", "<MSH.2", "</MSH>" };
094        for (int i = 0; i < expected.length; i++) {
095            if (theMessage.indexOf(expected[i]) < 0) {
096                return false;
097            }
098        }
099        
100        return true;
101        }
102
103        
104}