/**
* Joins array elements to string.
*
* @param arr Array.
* @return String.
*/
@Nullable
public static String compactArray(Object[] arr) {
if (arr == null || arr.length == 0) return null;
String sep = ", ";
StringBuilder sb = new StringBuilder();
for (Object s : arr) sb.append(s).append(sep);
if (sb.length() > 0) sb.setLength(sb.length() - sep.length());
return U.compact(sb.toString());
}
// pretty print Matrix(2D array of doubles)
public static String pprint(double[][] arr,DecimalFormat dformat) {
int colDim = 0;
for( double[] line : arr )
colDim = Math.max(colDim, line.length);
StringBuilder sb = new StringBuilder();
int max_width = 0;
int[] ilengths = new int[colDim];
Arrays.fill(ilengths, -1);
for( double[] line : arr ) {
for( int c = 0; c < line.length; ++c ) {
double d = line[c];
String dStr = dformat.format(d);
if( dStr.indexOf('.') == -1 ) dStr += ".0";
ilengths[c] = Math.max(ilengths[c], dStr.indexOf('.'));
int prefix = (d >= 0 ? 1 : 2);
max_width = Math.max(dStr.length() + prefix, max_width);
}
}
for( double[] line : arr ) {
for( int c = 0; c < line.length; ++c ) {
double d = line[c];
String dStr = dformat.format(d);
if( dStr.indexOf('.') == -1 ) dStr += ".0";
for( int x = dStr.indexOf('.'); x < ilengths[c] + 1; ++x )
sb.append(' ');
sb.append(dStr);
if( dStr.indexOf('.') == -1 ) sb.append('.');
for( int i = dStr.length() - Math.max(0, dStr.indexOf('.')); i <= 5; ++i )
sb.append('0');
}
sb.append("\n");
}
return sb.toString();
}
/**
* Returns compact class host.
*
* @param obj Object to compact.
* @return String.
*/
@Nullable
public static Object compactObject(Object obj) {
if (obj == null) return null;
if (obj instanceof Enum) return obj.toString();
if (obj instanceof String || obj instanceof Boolean || obj instanceof Number) return obj;
if (obj instanceof Collection) {
Collection col = (Collection) obj;
Object[] res = new Object[col.size()];
int i = 0;
for (Object elm : col) res[i++] = compactObject(elm);
return res;
}
if (obj.getClass().isArray()) {
Class<?> arrType = obj.getClass().getComponentType();
if (arrType.isPrimitive()) {
if (obj instanceof boolean[]) return Arrays.toString((boolean[]) obj);
if (obj instanceof byte[]) return Arrays.toString((byte[]) obj);
if (obj instanceof short[]) return Arrays.toString((short[]) obj);
if (obj instanceof int[]) return Arrays.toString((int[]) obj);
if (obj instanceof long[]) return Arrays.toString((long[]) obj);
if (obj instanceof float[]) return Arrays.toString((float[]) obj);
if (obj instanceof double[]) return Arrays.toString((double[]) obj);
}
Object[] arr = (Object[]) obj;
int iMax = arr.length - 1;
StringBuilder sb = new StringBuilder("[");
for (int i = 0; i <= iMax; i++) {
sb.append(compactObject(arr[i]));
if (i != iMax) sb.append(", ");
}
sb.append("]");
return sb.toString();
}
return U.compact(obj.getClass().getName());
}
public String getClasspath() {
final StringBuilder sb = new StringBuilder();
boolean firstPass = true;
final Enumeration<File> componentEnum = this.pathComponents.elements();
while (componentEnum.hasMoreElements()) {
if (!firstPass) {
sb.append(System.getProperty("path.separator"));
} else {
firstPass = false;
}
sb.append(componentEnum.nextElement().getAbsolutePath());
}
return sb.toString();
}
/** Prints entry information. */
void printEntry(ZipEntry e) throws IOException {
if (vflag) {
StringBuilder sb = new StringBuilder();
String s = Long.toString(e.getSize());
for (int i = 6 - s.length(); i > 0; --i) {
sb.append(' ');
}
sb.append(s).append(' ').append(new Date(e.getTime()).toString());
sb.append(' ').append(e.getName());
output(sb.toString());
} else {
output(e.getName());
}
}
public static String calculateCrc32(String source) {
CRC32 crc32 = new CRC32();
Adler32 adler32 = new Adler32();
adler32.update(source.getBytes());
System.out.println(adler32.getValue());
crc32.update(source.getBytes());
StringBuilder builder = new StringBuilder(8);
System.out.println(crc32.getValue());
System.out.println(Long.toHexString(crc32.getValue()));
builder.append(Long.toHexString(crc32.getValue()));
if (builder.length() < 8) {
builder.append(CHAR_TEMPLATE, 0, 8 - builder.length());
}
System.out.println(builder.toString());
return builder.toString();
}
public BSONTest() {
for (int x = 8; x < 2048; x *= 2) {
StringBuilder buf = new StringBuilder();
while (buf.length() < x) buf.append(x);
_data.add(buf.toString());
}
}
public static String sampleToString(int[] val, int max) {
if (val == null || val.length < max) return Arrays.toString(val);
StringBuilder b = new StringBuilder();
b.append('[');
max -= 10;
int valMax = val.length -1;
for (int i = 0; ; i++) {
b.append(val[i]);
if (i == max) {
b.append(", ...");
i = val.length - 10;
}
if ( i == valMax) {
return b.append(']').toString();
}
b.append(", ");
}
}
@Test
public void testOBBig1() {
BasicOutputBuffer a = new BasicOutputBuffer();
StringBuilder b = new StringBuilder();
for (String x : _data) {
a.write(x.getBytes());
b.append(x);
}
assertEquals(a.asString(), b.toString());
}
public static String getNextName(String base) {
StringBuilder sb = new StringBuilder();
sb.append(base);
sb.append(nextEntryNumber++);
return sb.toString();
}
/* -------------------------------------------------------------------------------------------------------
This method:
This method:
-- Takes in three paramters:
1. array - this is the byte array that actually holds the document contents
2. md5Hases - holds the entire hash values of the document
3. Divisor1/Divisor2/divisor3... - main and back up divisors
5. The remainder we are looking for
6/7. min/max boundaries
-- We will start running the karb rabin algorithm
-- We will find the boundaries using mod values and once they equal the mod value we have stored
-- we also have the divsor2/3 .. which are backup divisors. If we don't find a boundary by the divisor1 once we hit the maxBoundary
-- we will see if we have one with divisor2, if not, then we will see if we have one with divisor3 and so on
-- We will hash everything in that hash boundary and store it
-------------------------------------------------------------------------------------------------------- */
private static void runTddd(
byte[] array,
ArrayList<Long> md5Hashes,
long divisor1,
long divisor2,
long divisor3,
long remainder,
long minBoundary,
long maxBoundary) {
int documentStart = 0; // used to keep track of where the boundaries are
boolean match = false; // used to ck if we encountered a match
int backUpBreakPoint = -1; // used to store the backup breakpoint
int secondBackUpBreakPoint = -1; // used with the divisor3
StringBuilder builder = new StringBuilder();
int i = documentStart + (int) minBoundary - 1; // so we start at the minimum
// loop through all the values in the document
for (; i < md5Hashes.size() - 1; ++i) {
// if ((i - documentStart + 1) < minBoundary) // if the size of this boundary is less than
// the min, continue looping
// continue;
/*-----------------------------------------------------------------
- If the mod of this equals the modvalue we defined, then
- this is a boundary
------------------------------------------------------------------*/
if ((md5Hashes.get(i - 1) + md5Hashes.get(i) + md5Hashes.get(i + 1)) % divisor1
== remainder) // ck if this equals the mod value
{
// Hash all the values in the range (documentStart,current(i))
// Remember we only want to hash the original VALUES from the array that contains the
// original
// content of the file. Not the hash values in the md5Hash Array
for (int j = documentStart; j <= i; ++j) {
builder.append(array[j]); // store everything upto the current value
}
String original = builder.toString();
// if the string is a perfect match ( hash and original string)
if (HashClass.is_string_match(original, table)) // iinsert the hash in the table)
coverage += i - documentStart + 1; // this is the amount of bytes we saved
documentStart = i + 1; // set this as the beginning of the new boundary
backUpBreakPoint = -1; // reset this
secondBackUpBreakPoint = -1;
numOfPieces++; // increment the num of pieces
i = i + (int) minBoundary - 1; // skip all the way here
builder.setLength(0); // reset the stringBuilder for the next round
} else if ((md5Hashes.get(i - 1) + md5Hashes.get(i) + md5Hashes.get(i + 1)) % divisor2
== remainder) { // check if this is the backup point
backUpBreakPoint = i; // this is the backup breakpoint
} else if ((md5Hashes.get(i - 1) + md5Hashes.get(i) + md5Hashes.get(i + 1)) % divisor2
== remainder) {
secondBackUpBreakPoint = i; // set the second backup point
}
if ((i - documentStart + 1) >= maxBoundary) { // we have reached the maximum
// ck if we have a backUpbreakpoint
int point;
if (backUpBreakPoint != -1) // if we do, set this as the boundary
point = backUpBreakPoint;
else if (secondBackUpBreakPoint != -1) {
point = secondBackUpBreakPoint; // if we don't have a first break point, find the second
} else point = i; // else this current value of i is the breakpoint
// Hash all the values in the range (documentStart,current(i))
// Remember we only want to hash the original VALUES from the array that contains the
// original
// content of the file. Not the hash values in the md5Hash Array
for (int j = documentStart; j <= point; ++j) {
builder.append(array[j]); // store everything upto the current value
}
String original = builder.toString();
if (HashClass.is_string_match(original, table))
coverage += point - documentStart + 1; // this is the amount of bytes we saved
numOfPieces++; // increment the num of pieces
documentStart = point + 1; // set this as the beginning of the new boundary
backUpBreakPoint = -1; // reset this
secondBackUpBreakPoint = -1; // reset the secondBackUp point
i = point + (int) minBoundary - 1; // skip all the way here ;
builder.setLength(0); // reset the stringBuilder for the next round
}
} // end of the for loop
// -------------------------------------------------------------------------------------------
// we are missing the last boundary, so hash that last value
// We will also check against our values of the strings we already have, and if we encountered
// this
// already, then we will simply increment the counter, otherwise we will insert it in the
// hashtable
// and increase our miss counter
// ----------------------------------------------------------------------------------------------
for (int j = documentStart; j < array.length; ++j) {
builder.append(array[j]);
}
// only compute hash and insert into our hashtable only if the string buffer isn't empty
String original = builder.toString();
if (HashClass.is_string_match(original, table))
coverage += array.length - documentStart; // this is the amount of bytes we saved
numOfPieces++; // increment the num of pieces
} // end of the method