trjhtr

I'm writing this as a follow-up for my previous question posted here:

I've successfully decoded a large histogram into a byte array, which is written to a file. I'm now focusing on returning the byte array back to the token-based String. Details on how the tokens work are in the previous example.

I've created a method, below, which takes the byte array as read from the file, and outputs a char array. Due to the unknown size of the output as this point, i'm using a StringBuilder to append the result of the byte array. The DecodingResult class is just a simple POJO with the output String as a char and the size of the histogram as an int.

 /** Decodes the raw byte into a decoding result object.
 * @param bytes bytes to decode
 * @return decodingResult object
 */
public static DecodingResult decodeBinarySPECtoRAW(byte bytes) 
 StringBuilder sb = new StringBuilder();

 int height = 0;
 int length = 0;
 int val;
 int histogramLength = 0;
 for (int i = 0; i < bytes.length; i++) 
 char token = (char) bytes[i];

 sb.append(token);
 boolean nonSpecial = false;
 for (Token t : Token.values()) 
 if (token == t.name().charAt(0)) 
 nonSpecial = true;
 height = t.getHeight();
 length = t.getLength();
 
 

 if (nonSpecial) 
 //length
 if (length != 0 && length != 1) 
 if (length == 8) 
 //1 byte
 sb.append(getPaddedString(String.valueOf(bytes[i + 1] & 0xFF), 3));
 histogramLength += bytes[i + 1] & 0xFF;
 i++;
 else if (length == 16) 
 //2 bytes
 val = Tools.convertFromByteArray2(bytes[i + 1], bytes[i + 2]);
 histogramLength += val;
 sb.append(getPaddedString(String.valueOf(val), 5));
 i += 2;
 else 
 //4 bytes
 val = Tools.convertFromByteArray4(bytes[i + 1], bytes[i + 2], bytes[i + 3], bytes[i + 4]);
 histogramLength += val;
 sb.append(getPaddedString(String.valueOf(val), 10));

 i += 4;
 
 else 
 histogramLength++;
 

 //height
 if (height != 0 && height != 1) 
 if (height == 8) 
 //1 byte
 sb.append(getPaddedString(String.valueOf(bytes[i + 1] & 0xFF), 3));
 i++;
 else if (height == 16) 
 //2 bytes
 val = Tools.convertFromByteArray2(bytes[i + 1], bytes[i + 2]);
 sb.append(getPaddedString(String.valueOf(val), 5));
 i += 2;
 else 
 //4 bytes
 val = Tools.convertFromByteArray4(bytes[i + 1], bytes[i + 2], bytes[i + 3], bytes[i + 4]);
 sb.append(getPaddedString(String.valueOf(val), 10));
 i += 4;
 
 
 else 
 switch (token) 
 case 'R': 
 int numReads = (int) bytes[i + 1] & 0xFF;
 i++;
 sb.append(getPaddedString(String.valueOf(numReads), 3));
 for (int j = 0; j < numReads; j++) 
 int nextNum = bytes[i + 1] & 0xFF;
 sb.append(getPaddedString(String.valueOf(nextNum), 3));
 histogramLength++;
 i++;
 
 break;
 
 case 'S': 
 int numReads = (int) bytes[i + 1] & 0xFF;
 i++;
 sb.append(getPaddedString(String.valueOf(numReads), 3));
 for (int j = 0; j < numReads; j++) 
 histogramLength++;

 sb.append(getPaddedString(String.valueOf(Tools.convertFromByteArray2(bytes[i + 1], bytes[i + 2])), 5));
 i += 2;

 
 break;
 
 case 'T': 
 sb.append(getPaddedString(String.valueOf(Tools.convertFromByteArray4(bytes[i + 1], bytes[i + 2], bytes[i + 3], bytes[i + 4])), 10));
 i += 4;
 sb.append(getPaddedString(String.valueOf(Tools.convertFromByteArray4(bytes[i + 1], bytes[i + 2], bytes[i + 3], bytes[i + 4])), 10));
 i += 4;
 break;
 
 case 'U': 
 sb.append(getPaddedString(String.valueOf(Tools.convertFromByteArray4(bytes[i + 1], bytes[i + 2], bytes[i + 3], bytes[i + 4])), 10));
 i += 4;
 break;
 
 case 'V': 
 List<Byte> VBytes = new ArrayList<>();
 boolean escapeFound = false;
 while (!escapeFound) 
 if (i + 1 < bytes.length) 
 if (bytes[i + 1] == 0) escapeFound = true;
 else 
 VBytes.add(bytes[i + 1]);
 i += 1;
 
 
 
 for (byte b : VBytes) 
 sb.append((char) b);
 
 sb.append(getPaddedString(String.valueOf(bytes[i + 1] & 0xFF), 3));
 i += 1;
 break;
 
 case 'W': 
 for (int j = 0; j < 6; j++) 
 sb.append("000");
 i += 1;
 
 sb.append(getPaddedString(String.valueOf(Tools.convertFromByteArray4(bytes[i + 1], bytes[i + 2], bytes[i + 3], bytes[i + 4])), 10));
 i += 4;
 break;
 
 case 'X': 
 sb.append(getPaddedString(String.valueOf(bytes[i + 1] & 0xFF), 3));
 i += 1;
 //get length of the statement
 int statementLength = bytes[i + 1] & 0xFF;
 sb.append(getPaddedString(String.valueOf(statementLength), 3));
 i += 1;
 for (int j = i + 1; j < i + 1 + statementLength; j++) 
 sb.append((char) bytes[j]);
 
 i += statementLength;
 sb.append(getPaddedString(String.valueOf(Tools.convertFromByteArray2(bytes[i + 1], bytes[i + 2])), 5));
 i += 2;
 //endseq
 int endLength = bytes[i + 1];
 sb.append(getPaddedString(String.valueOf(endLength), 3));
 i += 1;
 if (endLength != 0) 
 for (int j = i + 1; j < i + 1 + endLength; j++) 
 sb.append((char) bytes[j]);
 
 i += endLength;
 

 //flankseq
 int flankLength = bytes[i + 1];
 sb.append(getPaddedString(String.valueOf(flankLength), 3));
 i += 1;
 if (flankLength != 0) 
 for (int j = i + 1; j < i + 1 + flankLength; j++) 
 sb.append((char) bytes[j]);
 
 i += flankLength;
 
 break;
 
 case 'Y': 
 //must be Y
 sb.append(getPaddedString(String.valueOf(Tools.convertFromByteArray4(bytes[i + 1], bytes[i + 2], bytes[i + 3], bytes[i + 4])), 10));
 i += 4;
 break;
 
 
 

 

 return new DecodingResult(sb.toString().toCharArray(), histogramLength);



public static String getPaddedString(String s, int max)
 StringBuilder b = new StringBuilder(max);
 for(int i = 0; i < max - s.length(); i++)
 b.append('0');
 
 b.append(s);
 return b.toString();

The token code, just so no one has to go back and forth to the last post:

/** All lengths and heights in bits.
 * All 1's are to be ignored in writing
 * i.e 1 - 0 is transcoded as A.
 * 1 -1 is transcoded as E
 * 1 - 209 is transcoded as I209
 * 1 - 2 is transcoded as I002
 * 1 - 40000 is transcoded as M40000
 * 1 - 290 is transcoded as M00290
 */
 public enum Token 

A (1, 0),
B (8, 0),
I (1 ,8),
E (1, 1),
F (8, 1),
J (8, 8),
N (8,16),
M (1,16),
C (16,0),
D (32,0),
G (16,1),
H (32,1),
K (16,8),
L (32,8),
O (16,16),
P (32,16),
Q (16,32),
Z (1,32);


private final int length;
private final int height;


Token(int length, int height) 
 this.length = length;
 this.height = height;


public int getLength() 
 return length;


public int getHeight() 
 return height;

Also the convertFromByteArray code.

public static int convertFromByteArray2(byte byte1, byte byte2) (byte1 & 0xFF));


public static int convertFromByteArray4(byte byte1, byte byte2, byte byte3, byte byte4)
 return byte1 << 24 

There are two processes here that are repeated, and are taking a lot of time but i'm not sure if there's a better way of doing it. The first is the byte -> string process. I have created a padding method to remove the use of String.format

Secondly, It's having to loop through every Token in the list to find the corresponding correct one.

The loop can simply be replaced with a lookup map which you prepare once before the process runs:

Map<Character, Token> tokenLookup = EnumSet.allOf(Token.class).stream()
 .collect(Collectors.toMap(tok -> tok.name().charAt(0), Function.identity()));

Then, instead of the loop just:

Token t = tokenLookup.get(token);
if(t != null) 
 nonSpecial = true;
 height = t.getHeight();
 length = t.getLength();

Regarding the getPaddedString() method: you could at least eliminate the repeated call to s.length() for every loop operation:

for(int i = max - s.length(); i > 0; i--)
 ...