Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

code simplification in automatontermsenum 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1067969 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Robert Muir 2011-02-07 15:34:06 +00:00
parent 52c2eb7c77
commit 05552c705a
1 changed files with 18 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
lucene/src/java/org/apache/lucene/search/AutomatonTermsEnum.java
View File

@ -111,9 +111,9 @@ public class AutomatonTermsEnum extends FilteredTermsEnum {
@Override
protected BytesRef nextSeekTerm(final BytesRef term) throws IOException {
if (term == null) {
seekBytesRef.copy("");
assert seekBytesRef.length == 0;
// return the empty term, as its valid
if (runAutomaton.run(seekBytesRef.bytes, seekBytesRef.offset, seekBytesRef.length)) {
if (runAutomaton.isAccept(runAutomaton.getInitialState())) {
return seekBytesRef;
}
} else {
@ -122,25 +122,20 @@ public class AutomatonTermsEnum extends FilteredTermsEnum {
// seek to the next possible string;
if (nextString()) {
// reposition
if (linear)
setLinear(infinitePosition);
return seekBytesRef;
return seekBytesRef; // reposition
} else {
return null; // no more possible strings can match
}
// no more possible strings can match
return null;
}
// this instance prevents unicode conversion during backtracking,
// we can just call setLinear once at the end.
int infinitePosition;
/**
* Sets the enum to operate in linear fashion, as we have found
* a looping transition at position
* a looping transition at position: we set an upper bound and
* act like a TermRangeQuery for this portion of the term space.
*/
private void setLinear(int position) {
assert linear == false;
int state = runAutomaton.getInitialState();
int maxInterval = 0xff;
for (int i = 0; i < position; i++) {
@ -164,6 +159,8 @@ public class AutomatonTermsEnum extends FilteredTermsEnum {
System.arraycopy(seekBytesRef.bytes, 0, linearUpperBound.bytes, 0, position);
linearUpperBound.bytes[position] = (byte) maxInterval;
linearUpperBound.length = length;
linear = true;
}
private final IntsRef savedStates = new IntsRef(10);
@ -197,8 +194,7 @@ public class AutomatonTermsEnum extends FilteredTermsEnum {
states[pos+1] = nextState;
// we found a loop, record it for faster enumeration
if (!finite && !linear && visited[nextState] == curGen) {
linear = true;
infinitePosition = pos;
setLinear(pos);
}
state = nextState;
}
@ -284,15 +280,16 @@ public class AutomatonTermsEnum extends FilteredTermsEnum {
*/
transition = allTransitions[state][0];
state = transition.getDest().getNumber();
// we found a loop, record it for faster enumeration
if (!finite && !linear && visited[state] == curGen) {
linear = true;
infinitePosition = seekBytesRef.length;
}
// append the minimum transition
seekBytesRef.grow(seekBytesRef.length + 1);
seekBytesRef.length++;
seekBytesRef.bytes[seekBytesRef.length - 1] = (byte) transition.getMin();
// we found a loop, record it for faster enumeration
if (!finite && !linear && visited[state] == curGen) {
setLinear(seekBytesRef.length-1);
}
}
return true;
}