/**
* {@code findAllUTF8Submatch} is the <a href='#all'>All</a> version of {@link #findUTF8Submatch};
* it returns a list of up to {@code n} successive matches of the expression, as defined by the <a
* href='#all'>All</a> description above.
*
* <p>
* A return value of null indicates no match.
*/
// This is visible for testing.
public List <byte[][]> findAllUTF8Submatch(byte[] b, int n)
{
List <byte[][]> result = new List <byte[][]>();
allMatches(
MachineInput.fromUTF8(b),
n,
(int[] match) => {
byte[][] slice = new byte[match.Length / 2][];
for (int j = 0; j < slice.Length; ++j)
{
if (match[2 * j] >= 0)
{
slice[j] = Utils.subarray(b, match[2 * j], match[2 * j + 1]);
}
}
result.Add(slice);
});
if (!result.Any())
{
return(null);
}
return(result);
}
/**
* Returns a two-element array of integers defining the location of the leftmost match in
* {@code b} of this regular expression. The match itself is at {@code b[loc[0]...loc[1]]}.
*
* <p>
* A return value of null indicates no match.
*/
// This is visible for testing.
public int[] findUTF8Index(byte[] b)
{
int[] a = doExecute(MachineInput.fromUTF8(b), 0, UNANCHORED, 2);
if (a == null)
{
return(null);
}
return(Utils.subarray(a, 0, 2));
}
/**
* {@code findAllUTF8SubmatchIndex} is the <a href='#all'>All</a> version of
* {@link #findUTF8SubmatchIndex}; it returns a list of up to {@code n} successive matches of the
* expression, as defined by the <a href='#all'>All</a> description above.
*
* <p>
* A return value of null indicates no match.
*/
// This is visible for testing.
public List <int[]> findAllUTF8SubmatchIndex(byte[] b, int n)
{
List <int[]> result = new List <int[]>();
allMatches(
MachineInput.fromUTF8(b),
n,
(int[] match) => {
result.Add(match);
});
if (!result.Any())
{
return(null);
}
return(result);
}
/**
* {@code findAllUTF8()} is the <a href='#all'>All</a> version of {@link #findUTF8}; it returns a
* list of up to {@code n} successive matches of the expression, as defined by the <a
* href='#all'>All</a> description above.
*
* <p>
* A return value of null indicates no match.
*
* TODO(adonovan): think about defining a byte slice view class, like a read-only Go slice backed
* by |b|.
*/
// This is visible for testing.
public List <byte[]> findAllUTF8(byte[] b, int n)
{
List <byte[]> result = new List <byte[]>();
allMatches(
MachineInput.fromUTF8(b),
n,
(int[] match) => {
result.Add(Utils.subarray(b, match[0], match[1]));
});
if (!result.Any())
{
return(null);
}
return(result);
}
/**
* Returns an array of arrays the text of the leftmost match of the regular expression in
* {@code b} and the matches, if any, of its subexpressions, as defined by the <a
* href='#submatch'>Submatch</a> description above.
*
* <p>
* A return value of null indicates no match.
*/
// This is visible for testing.
public byte[][] findUTF8Submatch(byte[] b)
{
int[] a = doExecute(MachineInput.fromUTF8(b), 0, UNANCHORED, prog.numCap);
if (a == null)
{
return(null);
}
byte[][] ret = new byte[1 + numSubexp][];
for (int i = 0; i < ret.Length; i++)
{
if (2 * i < a.Length && a[2 * i] >= 0)
{
ret[i] = Utils.subarray(b, a[2 * i], a[2 * i + 1]);
}
}
return(ret);
}
/**
* Returns an array holding the index pairs identifying the leftmost match of this regular
* expression in {@code b} and the matches, if any, of its subexpressions, as defined by the the
* <a href='#submatch'>Submatch</a> and <a href='#index'>Index</a> descriptions above.
*
* <p>
* A return value of null indicates no match.
*/
// This is visible for testing.
public int[] findUTF8SubmatchIndex(byte[] b)
{
return(pad(doExecute(MachineInput.fromUTF8(b), 0, UNANCHORED, prog.numCap)));
}
/**
* Returns true iff this regexp matches the UTF-8 byte array {@code b}.
*/
// This is visible for testing.
bool matchUTF8(byte[] b)
{
return(doExecute(MachineInput.fromUTF8(b), 0, UNANCHORED, 0) != null);
}