/**
* {@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);
}
/**
* Matches the regular expression against input starting at position start and ending at position
* end, with the given anchoring. Records the submatch boundaries in group, which is [start, end)
* pairs of byte offsets. The number of boundaries needed is inferred from the size of the group
* array. It is most efficient not to ask for submatch boundaries.
*
* @param input the input byte array
* @param start the beginning position in the input
* @param end the end position in the input
* @param anchor the anchoring flag (UNANCHORED, ANCHOR_START, ANCHOR_BOTH)
* @param group the array to fill with submatch positions
* @param ngroup the number of array pairs to fill in
* @return true if a match was found
*/
public bool match(string input, int start, int end, int anchor, int[] group, int ngroup)
{
if (start >= end) // strings in Java and C# indexed from zero. But, java doesn't crash if over, c# crashes.
{
return(false);
}
// TODO(afrozm): We suspect that the correct code should look something
// like the following:
// doExecute(MachineInput.fromUTF16(input), start, anchor, 2*ngroup);
//
// In Russ' own words:
// That is, I believe doExecute needs to know the bounds of the whole input
// as well as the bounds of the subpiece that is being searched.
int[] groupMatch = doExecute(MachineInput.fromUTF16(input, 0, end), start, anchor, 2 * ngroup);
if (groupMatch == null)
{
return(false);
}
if (group != null)
{
System.Array.Copy(groupMatch, 0, group, 0, groupMatch.Length);
}
return(true);
}
/**
* {@code findAllSubmatch} is the <a href='#all'>All</a> version of {@link #findSubmatch}; 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 <String[]> findAllSubmatch(String s, int n)
{
List <String[]> result = new List <String[]>();
allMatches(
MachineInput.fromUTF16(s),
n,
(int[] match) => {
String[] slice = new String[match.Length / 2];
for (int j = 0; j < slice.Length; ++j)
{
if (match[2 * j] >= 0)
{
slice[j] = s.Substring(match[2 * j], match[2 * j + 1] - match[2 * j]);
}
}
result.Add(slice);
});
if (!result.Any())
{
return(null);
}
return(result);
}
// doExecute() finds the leftmost match in the input and returns
// the position of its subexpressions.
// Derived from exec.go.
public int[] doExecute(MachineInput @in, int pos, int anchor, int ncap)
{
Machine m = get();
m.init(ncap);
int[] cap = m.match(@in, pos, anchor) ? m.submatches() : null;
put(m);
return(cap);
}
/**
* Returns a two-element array of integers defining the location of the leftmost match in
* {@code s} of this regular expression. The match itself is at
* {@code s.substring(loc[0], loc[1])}.
*
* <p>
* A return value of null indicates no match.
*/
// This is visible for testing.
public int[] findIndex(String s)
{
int[] a = doExecute(MachineInput.fromUTF16(s), 0, UNANCHORED, 2);
if (a == null)
{
return(null);
}
return(a);
}
/**
* Returns a string holding the text of the leftmost match in {@code s} of this regular
* expression.
*
* <p>
* If there is no match, the return value is an empty string, but it will also be empty if the
* regular expression successfully matches an empty string. Use {@link #findIndex} or
* {@link #findSubmatch} if it is necessary to distinguish these cases.
*/
// This is visible for testing.
public String find(String s)
{
int[] a = doExecute(MachineInput.fromUTF16(s), 0, UNANCHORED, 2);
if (a == null)
{
return("");
}
return(s.Substring(a[0], a[1] - a[0]));
}
/**
* 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));
}
// Find matches in input.
private void allMatches(MachineInput input, int n, DeliverFunc deliver)
{
int end = input.endPos();
if (n < 0)
{
n = end + 1;
}
for (int pos = 0, i = 0, prevMatchEnd = -1; i < n && pos <= end;)
{
int[] matches = doExecute(input, pos, UNANCHORED, prog.numCap);
if (matches == null || matches.Length == 0)
{
break;
}
bool accept = true;
if (matches[1] == pos)
{
// We've found an empty match.
if (matches[0] == prevMatchEnd)
{
// We don't allow an empty match right
// after a previous match, so ignore it.
accept = false;
}
int r = input.step(pos);
if (r < 0)
{
// EOF
pos = end + 1;
}
else
{
pos += r & 0x7;
}
}
else
{
pos = matches[1];
}
prevMatchEnd = matches[1];
if (accept)
{
deliver(pad(matches));
i++;
}
}
}
/**
* {@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 findAll} is the <a href='#all'>All</a> version of {@link #find}; 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 <String> findAll(String s, int n)
{
List <String> result = new List <String>();
allMatches(
MachineInput.fromUTF16(s),
n,
(int[] match) => {
result.Add(s.Substring(match[0], match[1] - match[0]));
});
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);
}
/**
* {@code findAllSubmatchIndex} is the <a href='#all'>All</a> version of
* {@link #findSubmatchIndex}; 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[]> findAllSubmatchIndex(String s, int n)
{
List <int[]> result = new List <int[]>();
allMatches(
MachineInput.fromUTF16(s),
n,
(int[] match) => {
result.Add(match);
});
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 of strings holding the text of the leftmost match of the regular expression in
* {@code s} 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 string[] findSubmatch(String s)
{
int[] a = doExecute(MachineInput.fromUTF16(s), 0, UNANCHORED, prog.numCap);
if (a == null)
{
return(null);
}
string[] ret = new string[1 + numSubexp];
for (int i = 0; i < ret.Length; i++)
{
if (2 * i < a.Length && a[2 * i] >= 0)
{
ret[i] = s.Substring(a[2 * i], a[2 * i + 1] - a[2 * i]);
}
}
return(ret);
}
/**
* 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);
}
/**
* Returns an array holding the index pairs identifying the leftmost match of this regular
* expression in {@code s} 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 int[] findSubmatchIndex(String s)
{
return(pad(doExecute(MachineInput.fromUTF16(s), 0, UNANCHORED, prog.numCap)));
}
/**
* Returns true iff this regexp matches the string {@code s}.
*/
public bool match(string s)
{
return(doExecute(MachineInput.fromUTF16(s), 0, UNANCHORED, 0) != null);
}
/**
* Returns a copy of {@code src} in which at most {@code maxReplaces} matches for this regexp have
* been replaced by the return value of of function {@code repl} (whose first argument is the
* matched string). No support is provided for expressions (e.g. {@code \1} or {@code $1}) in the
* replacement string.
*/
// This is visible for testing.
public string replaceAllFunc(string src, ReplaceFunc repl, int maxReplaces)
{
int lastMatchEnd = 0; // end position of the most recent match
int searchPos = 0; // position where we next look for a match
StringBuilder buf = new StringBuilder();
MachineInput input = MachineInput.fromUTF16(src);
int numReplaces = 0;
while (searchPos <= src.Length)
{
int[] a = doExecute(input, searchPos, UNANCHORED, 2);
if (a == null || a.Length == 0)
{
break; // no more matches
}
// Copy the unmatched characters before this match.
buf.Append(src.Substring(lastMatchEnd, a[0]));
// Now insert a copy of the replacement string, but not for a
// match of the empty string immediately after another match.
// (Otherwise, we get double replacement for patterns that
// match both empty and nonempty strings.)
// FIXME(adonovan), FIXME(afrozm) - JDK seems to be doing exactly this
// put a replacement for a pattern that also matches empty and non-empty
// strings. The fix would not just be a[1] >= lastMatchEnd, there are a
// few corner cases in that as well, and there are tests which will fail
// when that case is touched (happens only at the end of the input string
// though).
if (a[1] > lastMatchEnd || a[0] == 0)
{
buf.Append(repl(src.Substring(a[0], a[1])));
// Increment the replace count.
++numReplaces;
}
lastMatchEnd = a[1];
// Advance past this match; always advance at least one character.
int width = input.step(searchPos) & 0x7;
if (searchPos + width > a[1])
{
searchPos += width;
}
else if (searchPos + 1 > a[1])
{
// This clause is only needed at the end of the input
// string. In that case, DecodeRuneInString returns width=0.
searchPos++;
}
else
{
searchPos = a[1];
}
if (numReplaces >= maxReplaces)
{
// Should never be greater though.
break;
}
}
// Copy the unmatched characters after the last match.
buf.Append(src.Substring(lastMatchEnd));
return(buf.ToString());
}
// match() runs the machine over the input |in| starting at |pos| with the
// RE2 Anchor |anchor|.
// It reports whether a match was found.
// If so, matchcap holds the submatch information.
public bool match(MachineInput @in, int pos, int anchor)
{
int startCond = re2.cond;
if (startCond == Utils.EMPTY_ALL)
{
// impossible
return(false);
}
if ((anchor == RE2.ANCHOR_START || anchor == RE2.ANCHOR_BOTH) && pos != 0)
{
return(false);
}
matched = false;
for (int jj = 0; jj < prog.numCap; ++jj)
{
matchcap[jj] = -1;
}
Queue runq = q0, nextq = q1;
int r = @in.step(pos);
int rune = r >> 3;
int width = r & 7;
int rune1 = -1;
int width1 = 0;
if (r != MachineInput.EOF)
{
r = @in.step(pos + width);
rune1 = r >> 3;
width1 = r & 7;
}
int flag; // bitmask of EMPTY_* flags
if (pos == 0)
{
flag = Utils.emptyOpContext(-1, rune);
}
else
{
flag = @in.context(pos);
}
for (;;)
{
if (runq.isEmpty())
{
if ((startCond & Utils.EMPTY_BEGIN_TEXT) != 0 && pos != 0)
{
// Anchored match, past beginning of text.
break;
}
if (matched)
{
// Have match; finished exploring alternatives.
break;
}
if (re2.prefix.Length != 0 && rune1 != re2.prefixRune && @in.canCheckPrefix())
{
// Match requires literal prefix; fast search for it.
int advance = @in.index(re2, pos);
if (advance < 0)
{
break;
}
pos += advance;
r = @in.step(pos);
rune = r >> 3;
width = r & 7;
r = @in.step(pos + width);
rune1 = r >> 3;
width1 = r & 7;
}
}
if (!matched && (pos == 0 || anchor == RE2.UNANCHORED))
{
// If we are anchoring at begin then only add threads that begin
// at |pos| = 0.
if (ncap > 0)
{
matchcap[0] = pos;
}
add(runq, prog.start, pos, matchcap, flag, null);
}
flag = Utils.emptyOpContext(rune, rune1);
step(runq, nextq, pos, pos + width, rune, flag, anchor, pos == @in.endPos());
if (width == 0)
{
// EOF
break;
}
if (ncap == 0 && matched)
{
// Found a match and not paying attention
// to where it is, so any match will do.
break;
}
pos += width;
rune = rune1;
width = width1;
if (rune != -1)
{
r = @in.step(pos + width);
rune1 = r >> 3;
width1 = r & 7;
}
Queue tmpq = runq;
runq = nextq;
nextq = tmpq;
}
free(nextq);
return(matched);
}
/**
* 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)));
}
