/**
* Returns the position of the first occurrence of substr in current string from the specified
* position (0-based index).
*
* @param v the string to be searched
* @param start the start position of the current string for searching
* @return the position of the first occurrence of substr, if not found, -1 returned.
*/
public int indexOf(UTF8String v, int start) {
if (v.numBytes() == 0) {
return 0;
}
// locate to the start position.
int i = 0; // position in byte
int c = 0; // position in character
while (i < numBytes && c < start) {
i += numBytesForFirstByte(getByte(i));
c += 1;
}
do {
if (i + v.numBytes > numBytes) {
return -1;
}
if (ByteArrayMethods.arrayEquals(base, offset + i, v.base, v.offset, v.numBytes)) {
return c;
}
i += numBytesForFirstByte(getByte(i));
c += 1;
} while (i < numBytes);
return -1;
}
/** Find the `str` from right to left. */
private int rfind(UTF8String str, int start) {
assert (str.numBytes > 0);
while (start >= 0) {
if (ByteArrayMethods.arrayEquals(base, offset + start, str.base, str.offset, str.numBytes)) {
return start;
}
start -= 1;
}
return -1;
}
@Override
public boolean equals(Object other) {
if (other instanceof UnsafeRow) {
UnsafeRow o = (UnsafeRow) other;
return (sizeInBytes == o.sizeInBytes)
&& ByteArrayMethods.arrayEquals(
baseObject, baseOffset, o.baseObject, o.baseOffset, sizeInBytes);
}
return false;
}
@Override
public boolean equals(final Object other) {
if (other instanceof UTF8String) {
UTF8String o = (UTF8String) other;
if (numBytes != o.numBytes) {
return false;
}
return ByteArrayMethods.arrayEquals(base, offset, o.base, o.offset, numBytes);
} else {
return false;
}
}
/*
* Returns the index of the string `match` in this String. This string has to be a comma separated
* list. If `match` contains a comma 0 will be returned. If the `match` isn't part of this String,
* 0 will be returned, else the index of match (1-based index)
*/
public int findInSet(UTF8String match) {
if (match.contains(COMMA_UTF8)) {
return 0;
}
int n = 1, lastComma = -1;
for (int i = 0; i < numBytes; i++) {
if (getByte(i) == (byte) ',') {
if (i - (lastComma + 1) == match.numBytes
&& ByteArrayMethods.arrayEquals(
base, offset + (lastComma + 1), match.base, match.offset, match.numBytes)) {
return n;
}
lastComma = i;
n++;
}
}
if (numBytes - (lastComma + 1) == match.numBytes
&& ByteArrayMethods.arrayEquals(
base, offset + (lastComma + 1), match.base, match.offset, match.numBytes)) {
return n;
}
return 0;
}
/**
* Levenshtein distance is a metric for measuring the distance of two strings. The distance is
* defined by the minimum number of single-character edits (i.e. insertions, deletions or
* substitutions) that are required to change one of the strings into the other.
*/
public int levenshteinDistance(UTF8String other) {
// Implementation adopted from org.apache.common.lang3.StringUtils.getLevenshteinDistance
int n = numChars();
int m = other.numChars();
if (n == 0) {
return m;
} else if (m == 0) {
return n;
}
UTF8String s, t;
if (n <= m) {
s = this;
t = other;
} else {
s = other;
t = this;
int swap;
swap = n;
n = m;
m = swap;
}
int[] p = new int[n + 1];
int[] d = new int[n + 1];
int[] swap;
int i, i_bytes, j, j_bytes, num_bytes_j, cost;
for (i = 0; i <= n; i++) {
p[i] = i;
}
for (j = 0, j_bytes = 0; j < m; j_bytes += num_bytes_j, j++) {
num_bytes_j = numBytesForFirstByte(t.getByte(j_bytes));
d[0] = j + 1;
for (i = 0, i_bytes = 0; i < n; i_bytes += numBytesForFirstByte(s.getByte(i_bytes)), i++) {
if (s.getByte(i_bytes) != t.getByte(j_bytes)
|| num_bytes_j != numBytesForFirstByte(s.getByte(i_bytes))) {
cost = 1;
} else {
cost =
(ByteArrayMethods.arrayEquals(
t.base, t.offset + j_bytes, s.base, s.offset + i_bytes, num_bytes_j))
? 0
: 1;
}
d[i + 1] = Math.min(Math.min(d[i] + 1, p[i + 1] + 1), p[i] + cost);
}
swap = p;
p = d;
d = swap;
}
return p[n];
}
private boolean matchAt(final UTF8String s, int pos) {
if (s.numBytes + pos > numBytes || pos < 0) {
return false;
}
return ByteArrayMethods.arrayEquals(base, offset + pos, s.base, s.offset, s.numBytes);
}