LaurelBridge.DCF.Examples.CharacterSetEncoding Namespace

public class Program
{
    private static readonly string _outputFilePath = "CharacterSetEncodingOutputText.txt";

    /// <summary>
    /// Main
    /// </summary>
    [SuppressMessage("ReSharper", "UnusedVariable")]
    public static void Main()
    {
        try
        {
            string inputFilename = "mr-knee.dcm";

            DicomDataSet dds;
            StringBuilder outputText = new StringBuilder();
            outputText.AppendFormat("Character Set Encoding Example:{0}", Environment.NewLine);
            using (DicomFileInput dfi = new DicomFileInput(inputFilename))
            {
                dds = dfi.ReadDataSet();
                dds.ExpandStreamingModeData(true);
            }

            // For the following examples, instead of throwing, replace any encoding or decoding with the 
            // hexadecimal representation of the characters that failed
            ElementOptions.Instance.EncoderFallbackStyle = EncodingFallbackStyle.XmlHex;
            ElementOptions.Instance.DecoderFallbackStyle = EncodingFallbackStyle.XmlHex;

            DicomDataSet isoIR6DataSet = InsertAsciiPersonNameToIsoIR6(outputText, dds);
            DicomDataSet japaneseDataSet = InsertJapanesePersonNameToIsoIR6(outputText, isoIR6DataSet);
            DicomDataSet mixedDataSet = InsertThaiPersonNameToJapanese(outputText, japaneseDataSet);
            DicomDataSet thaiHebrewDataSet = InsertThaiandHebrewPersonNameToJapanese(outputText, japaneseDataSet);

            WriteOutputToFile(_outputFilePath, outputText.ToString());

            Process.Start("notepad.exe", _outputFilePath);
        }
        catch (Exception e)
        {
            Console.WriteLine("Exception caught during execution: {0}", e);
        }

        if (Debugger.IsAttached)
        {
            Console.Write("Press any key to continue . . . ");
            Console.ReadKey();
        }
    }

    /// <summary>
    /// This method inserts an ASCII person name into the input ISO_IR 6 dataset. The resultant dataset does not need
    /// re-encoding, as made evident by the fact the recommended Specific Character Set to use matched the input.
    /// <para>
    /// NOTE: When the Specific Character Set is either missing or is the empty string, ISO_IR 6 is implied.
    /// </para>
    /// </summary>
    private static DicomDataSet InsertAsciiPersonNameToIsoIR6(StringBuilder outputText, DicomDataSet dds)
    {
        outputText.AppendFormat("{0}ISO_IR 6 to ISO_IR 6{0}==============================================={0}", Environment.NewLine);
        string origScs = !String.IsNullOrEmpty(dds.SpecificCharacterSet) ? dds.SpecificCharacterSet : "ISO_IR 6";
        outputText.AppendFormat("Initial Specific Character Set (0008,0005): \'{0}\'{1}", origScs, Environment.NewLine);

        // Before inserting the string element into the dataset, convert the dataset to unicode to make the insertion process trivial
        string isoIR6PersonName = "Doe^John";
        outputText.AppendFormat("Patient Name (0010,0010) to insert: {0}{1}", isoIR6PersonName, Environment.NewLine);
        dds.Insert(Tags.PatientName, isoIR6PersonName);

        // Determine the best Specific Character Set (0008,0005) to use for the updated Dicom dataset from the list of character sets.
        IList<string> isoir6Encodings = new List<string>() { null, "ISO_IR 100", "ISO_IR 166", "ISO_IR 192" };
        DicomDataSet result = EncodeDataSetWithBestScs(outputText, isoir6Encodings, dds);
        outputText.AppendFormat("Patient Name Re-encoded: {0}{1}",
            result.GetElement(Tags.PatientName).GetStringValueAt(0),
            Environment.NewLine);

        return result;
    }

    /// <summary>
    /// This method inserts a Japanese person name into the input ISO_IR 6 dataset by first converting the input dataset to ISO_IR 192 (Unicode). 
    /// The resultant dataset is than re-encoded using the recommended Specific Character Set (0008,0005) produced by analyzing each character set
    /// given in the list of character set encodings. The best specific character set value in this example was ISO 2022 IR 13\\ISO 2022 IR 87 and 
    /// was able to encode every character in the dataset properly.
    /// </summary>
    /// <para>
    /// NOTE: When the Specific Character Set is either missing or is the empty string \'\', ISO_IR 6 is implied.
    /// </para>
    private static DicomDataSet InsertJapanesePersonNameToIsoIR6(StringBuilder outputText, DicomDataSet dds)
    {
        outputText.AppendFormat("{0}ISO_IR 6 to Japanese{0}==============================================={0}", Environment.NewLine);
        string origScs = !String.IsNullOrEmpty(dds.SpecificCharacterSet) ? dds.SpecificCharacterSet : "ISO_IR 6";
        outputText.AppendFormat("Initial Specific Character Set (0008,0005): \'{0}\'{1}", origScs, Environment.NewLine);

        // Before inserting the string element into the dataset, convert the dataset to unicode to make the insertion process trivial
        string japanesePersonName = "ﾔﾏﾀﾞ^ﾀﾛｳ=山田^太郎=やまだ^たろう";
        outputText.AppendFormat("Patient Name (0010,0010) to insert: {0}{1}", japanesePersonName, Environment.NewLine);
        dds.Insert(Tags.PatientName, japanesePersonName);

        // Determine the best Specific Character Set (0008,0005) to use for the updated Dicom dataset from the list of character sets.
        IList<string> japaneseEncodings = new List<string>() { null, "\\ISO 2022 IR 87", "ISO 2022 IR 13\\ISO 2022 IR 87", "ISO_IR 192" };
        DicomDataSet result = EncodeDataSetWithBestScs(outputText, japaneseEncodings, dds);
        outputText.AppendFormat("Patient Name Re-encoded: {0}{1}",
            result.GetElement(Tags.PatientName).GetStringValueAt(0),
            Environment.NewLine);

        return result;
    }

    /// <summary>
    /// This method inserts a Thai person name into the input Japanese dataset by first converting the input dataset to ISO_IR 192 (Unicode). 
    /// The resultant dataset is than re-encoded using the recommended Specific Character Set (0008,0005) produced by analyzing each character set
    /// given in the list of character set encodings. The best Specific Character Set in this example turns out to be ISO_IR 192 because of the fact
    /// there was no other specific character set value that could properly encode all string elements, thus the need for unicode.
    /// </summary>
    /// <para>
    /// NOTE: When the Specific Character Set is either missing or is the empty string \'\', ISO_IR 6 is implied.
    /// </para>
    private static DicomDataSet InsertThaiPersonNameToJapanese(StringBuilder outputText, DicomDataSet dds)
    {
        outputText.AppendFormat("{0}Japanese to Mixed{0}==============================================={0}", Environment.NewLine);
        string origScs = !String.IsNullOrEmpty(dds.SpecificCharacterSet) ? dds.SpecificCharacterSet : "ISO_IR 6";
        outputText.AppendFormat("Initial Specific Character Set (0008,0005): \'{0}\'{1}", origScs, Environment.NewLine);

        // Before inserting the string element into the dataset, convert the dataset to unicode to make the insertion process trivial
        string thaiPersonName = "McIntai^Thongchai=แม็คอินไตย์^ธงไชย";
        outputText.AppendFormat("Performing Physician Name (0008,1050) to insert: {0}{1}", thaiPersonName, Environment.NewLine);
        dds.Insert(Tags.PerformingPhysicianName, thaiPersonName);

        // Determine the best Specific Character Set (0008,0005) to use for the updated Dicom dataset from the list of character sets.
        IList<string> mixedEncodings = new List<string>() { null, "\\ISO 2022 IR 87", "ISO 2022 IR 13\\ISO 2022 IR 87", "ISO_IR 192" };
        DicomDataSet result = EncodeDataSetWithBestScs(outputText, mixedEncodings, dds);
        outputText.AppendFormat("Patient Name re-encoded: {0}{1}",
            result.GetElement(Tags.PatientName).GetStringValueAt(0),
            Environment.NewLine);
        outputText.AppendFormat("Performing Physician Name re-encoded: {0}{1}",
            result.GetElement(Tags.PerformingPhysicianName).GetStringValueAt(0),
            Environment.NewLine);

        return result;
    }

    /// <summary>
    /// This method inserts a Thai and Hebrew person name into the input Japanese dataset by first converting the input dataset to ISO_IR 192 (Unicode). 
    /// The resultant dataset is than re-encoded using the recommended Specific Character Set (0008,0005) produced by analyzing each character set
    /// given in the list of character set encodings. In this case, there was no specific character set value that was able to encode every character
    /// in the dataset properly. Therefore, the best specific character set value was the value with the least number of encoding fallbacks(problems), 
    /// which turns out to be ISO_IR 166 for Thai. Note how the Hebrew string in this encoding was not decoded properly.
    /// <para>
    /// NOTE: When the Specific Character Set is either missing or is the empty string \'\', ISO_IR 6 is implied.
    /// </para>
    /// </summary>
    private static DicomDataSet InsertThaiandHebrewPersonNameToJapanese(StringBuilder outputText, DicomDataSet dds)
    {
        outputText.AppendFormat("{0}Mixed with No Unicode{0}==============================================={0}", Environment.NewLine);
        string origScs = !String.IsNullOrEmpty(dds.SpecificCharacterSet) ? dds.SpecificCharacterSet : "ISO_IR 6";
        outputText.AppendFormat("Initial Specific Character Set (0008,0005): \'{0}\'{1}", origScs, Environment.NewLine);

        // Before inserting the string element into the dataset, convert the dataset to unicode to make the insertion process trivial
        string hebrewPersonName = "Aleichem^Sholom==שלום^עליכם";
        string thaiPersonName = "McIntai^Thongchai=แม็คอินไตย์^ธงไชย";
        outputText.AppendFormat("Performing Physician Name (0008,1050) to insert: {0}{1}", hebrewPersonName, Environment.NewLine);
        dds.Insert(Tags.PatientName, hebrewPersonName);
        outputText.AppendFormat("Patient Name (0010,0010) to insert: {0}{1}", thaiPersonName, Environment.NewLine);
        dds.Insert(Tags.PerformingPhysicianName, thaiPersonName);

        // Determine the best Specific Character Set (0008,0005) to use for the updated Dicom dataset from the list of character sets.
        IList<string> mixedEncodings = new List<string>() { null, "ISO_IR 100", "ISO_IR 138", "ISO_IR 166" };
        DicomDataSet result = EncodeDataSetWithBestScs(outputText, mixedEncodings, dds);
        outputText.AppendFormat("Patient Name re-encoded: {0}{1}",
            result.GetElement(Tags.PatientName).GetStringValueAt(0),
            Environment.NewLine);
        outputText.AppendFormat("Performing Physician Name re-encoded: {0}{1}",
            result.GetElement(Tags.PerformingPhysicianName).GetStringValueAt(0),
            Environment.NewLine);

        return result;
    }

    /// <summary>
    /// This method analyzes each string element affected by the Specific Character Set (0008,0005) by encoding each string using the list of encodings.
    /// This analysis returns a score for each encoding, determining the best specific character set value based on the lowest number of fallback encodings.
    /// The unicode dataset is than re-encoded using this best specific character set value and returned.
    /// </summary>
    /// <param name="sb">Output string builder to keep track of results</param>
    /// <param name="encodings">The list of specific character set values to each test encoding the unicode dataset</param>
    /// <param name="dds">The unicode dataset to encode</param>
    /// <returns>The encoded dataset using the determined best specific character set value.</returns>
    private static DicomDataSet EncodeDataSetWithBestScs(StringBuilder sb, IList<string> encodings, DicomDataSet dds)
    {
        // Encode each string element affected by the specific character set using each of the encoding given in the list, keeping track of the 
        // number of fallbacks in the encoding that occur.
        EncodingResults analysisResults = EncodingUtils.AnalyzeEncodings(dds, encodings);

        // Output the results of the analysis of the encoding
        sb.AppendFormat("{0}Results from the encoding analysis:{0}", Environment.NewLine);
        foreach (EncodingScore score in analysisResults.Scores)
        {
            sb.AppendFormat("SCS Value: \'{0}\' Fallbacks: {1} Total Characters: {2}{3}", score.ScsValue, score.Fallbacks, score.TotalChars, Environment.NewLine);
        }

        sb.AppendFormat("{1}Recommended Specific Character Set (0008,0005): \'{0}\'{1}", analysisResults.Best.ScsValue, Environment.NewLine);
        string bestScsValue = analysisResults.Best.ScsValue != null ? analysisResults.Best.ScsValue : "ISO_IR 6";
        DicomDataSet reencodedDataSet = ReencodeDataSet(dds, bestScsValue);
        return reencodedDataSet;
    }

    /// <summary>
    /// Helper method that writes a given data set to the memory stream, returning the data set read from
    /// the memory stream. The purpose being to force the dataset to re-encode the necessary elements on write using 
    /// the given specific character set
    /// </summary>
    /// <param name="dds">The input data set that needs to be re-encoded</param>
    /// <param name="specificCharacterSet">The new specific character set to use to encode the dds with.</param>
    private static DicomDataSet ReencodeDataSet(DicomDataSet dds, string specificCharacterSet)
    {
        if (dds.SpecificCharacterSet != null && dds.SpecificCharacterSet.Equals(specificCharacterSet))
            return dds;

        // Clone the input dataset and change the specific character set in preparation for the re-encoding
        DicomDataSet clonedDataSet = (DicomDataSet)dds.Clone();
        clonedDataSet.Insert(Tags.SpecificCharacterSet, specificCharacterSet);

        DicomDataSet recodedDataSet;

        MemoryStream ms = new MemoryStream();
        DicomStreamWriter dsw = new DicomStreamWriter(ms, new DicomSessionSettings());
        using (DicomFileOutput dfo = new DicomFileOutput(dsw, Uids.ELE, null, null))
        {
            dfo.CreateChapter10Format = false;
            dfo.WriteDataSet(clonedDataSet);
        }

        ms = new MemoryStream(ms.ToArray());
        DicomStreamReader dsr = new DicomStreamReader(ms, new DicomSessionSettings());
        using (DicomFileInput dfi = new DicomFileInput(dsr, Uids.ELE, new DicomSessionSettings()))
        {
            recodedDataSet = dfi.ReadDataSet();
            recodedDataSet.ExpandStreamingModeData(true);
        }

        return recodedDataSet;
    }

    /// <summary>
    /// Write the given output text to disk in UTF8.
    /// </summary>
    /// <param name="outputFile">The output file path</param>
    /// <param name="outputText">The text to write</param>
    private static void WriteOutputToFile(string outputFile, string outputText)
    {
        using (StreamWriter writer = new StreamWriter(outputFile, false, Encoding.UTF8))
        {
            writer.Write(outputText);
        }
    }