Working With Binary String Data Examples

// Calculate a histogram of the amino acids found
// in the human SARS-CoV-2 spike protein.
Function covidSpikeAminoAcidHistogram()
    String url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=protein&id=QWK65230&rettype=fasta&retmode=text"
    URLRequest url=url
    if (V_responseCode != 200)
        print "Failed to successfully download protein sequence."
        return 0
    endif
    String response = S_serverResponse
    
    // The first line in the response is a description of the
    // sequence. The sequence starts after the first line feed character.
    Variable sequenceStart = strsearch(response, "\n", 0)
    if (sequenceStart <= 0)
        print "Could not find start of sequence."
        return 0
    endif
    
    String sequence = response[sequenceStart+1, inf]
    // Remove any line endings in the sequence
    sequence = ReplaceString("\n", sequence, "")
    sequence = TrimString(sequence)
    
    // Convert the sequence into a byte wave
    WAVE/B/U seqWave = StringToUnsignedByteWave(sequence)
    
    // Calculate the histogram with 26 bins (one for each letter).
    // Start the bins at the numeric value 65, which corresponds to "A".
    Histogram/C/B={char2num("A"),1,26}/DEST=seqHistWave seqWave
    
    // Create a text wave that contains the amino acid abbreviations.
    Make/O/N=26/T aminoAcidLabels
    aminoAcidLabels = num2char(char2num("A") + p)
    
    // Some letters do not correspond to an actual amino acid. So
    // delete those points from both waves.
    DeletePoints char2num("Z") - char2num("A"), 1, seqHistWave, aminoAcidLabels
    DeletePoints char2num("X") - char2num("A"), 1, seqHistWave, aminoAcidLabels
    // U is Selenocysteine. It is rare.
//  DeletePoints char2num("U") - char2num("A"), 1, seqHistWave, aminoAcidLabels
    // O is pyrrolysine. It is rare.
//  DeletePoints char2num("O") - char2num("A"), 1, seqHistWave, aminoAcidLabels
    DeletePoints char2num("J") - char2num("A"), 1, seqHistWave, aminoAcidLabels
    DeletePoints char2num("B") - char2num("A"), 1, seqHistWave, aminoAcidLabels
    
    // Sort the histogram wave to increasing size. Also sort
    // the amino acid labels wave in the same order.
    Sort seqHistWave, seqHistWave, aminoAcidLabels
    
    // Display the histogram.
    Display seqHistWave vs aminoAcidLabels
End

// Returns a ROT13 encoded string.
// See https://en.wikipedia.org/wiki/ROT13 for more information.
Function/S ROT13(String inStr)
    if (!strlen(inStr) > 0) // null or empty string
        return inStr
    endif
    
    Variable la = char2num("a")     // 97
    Variable lz = char2num("z")     // 122
    Variable bA = char2num("A")     // 65
    Variable bZ = char2num("Z")     // 90
    
    // Get the bytes
    WAVE/B/U bytes = StringToUnsignedByteWave(inStr)
    
    // encode uppercase letters
    bytes = (bytes[p] >= bA && bytes[p] <= bZ) ? mod(bytes[p] - bA + 13, 26) + bA : bytes[p]
    
    // encode lowercase letters
    bytes = (bytes[p] >= lA && bytes[p] <= lZ) ? mod(bytes[p] - lA + 13, 26) + lA : bytes[p]
    
    // convert back to a string
    String outStr = WaveDataToString(bytes)
    
    return outStr
End

•print rot13("AbC+z")
  NoP+m
•print rot13("NoP+m")
  AbC+z 

// Returns a random printable ascii character.
// "Printable" characters include the space, tab, line feed,
// and carriage return character.
ThreadSafe Function RandomPrintableChar()
    Variable c
    do
        c = trunc(abs(enoise(126)))
        if ((c >= 32 && c <= 126) || c == 9 || c == 10 || c == 13)
            break
        endif
    while (1)
    return c
End
 
// Generates length bytes of random ASCII text.
Function/S RandomPrintableText(Variable length)
    Make/FREE/B/U/N=(length) chars
    MultiThread chars = RandomPrintableChar()
    String theText = WaveDataToString(chars)
    return theText
End

•print RandomPrintableText(10)
  YI2XcCsPR9
•print RandomPrintableText(10)
  18'Gf[C\O%