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

fix silly minor performance bug in CompiledAutomaton/Terms.intersect implementations 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1669639 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Michael McCandless 2015-03-27 18:06:56 +00:00
parent e0ff3a6b0c
commit f49f2b2af6
2 changed files with 11 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
lucene/core/src/java/org/apache/lucene/util/automaton/CompiledAutomaton.java
View File

@ -78,7 +78,8 @@ public class CompiledAutomaton {
/**
* Shared common suffix accepted by the automaton. Only valid
* for {@link AUTOMATON_TYPE#NORMAL}, and only when the
* automaton accepts an infinite language.
* automaton accepts an infinite language. This will be null
* if the common prefix is length 0.
*/
public final BytesRef commonSuffixRef;
@ -202,7 +203,12 @@ public class CompiledAutomaton {
commonSuffixRef = null;
} else {
// NOTE: this is a very costly operation! We should test if it's really warranted in practice...
commonSuffixRef = Operations.getCommonSuffixBytesRef(binary, maxDeterminizedStates);
BytesRef suffix = Operations.getCommonSuffixBytesRef(binary, maxDeterminizedStates);
if (suffix.length == 0) {
commonSuffixRef = null;
} else {
commonSuffixRef = suffix;
}
}
// This will determinize the binary automaton for us:

6
lucene/core/src/java/org/apache/lucene/util/automaton/Operations.java
View File

@ -1063,7 +1063,7 @@ final public class Operations {
* Returns the longest string that is a prefix of all accepted strings and
* visits each state at most once. The automaton must be deterministic.
*
* @return common prefix
* @return common prefix, which can be an empty (length 0) String (never null)
*/
public static String getCommonPrefix(Automaton a) {
if (a.isDeterministic() == false) {
@ -1097,7 +1097,7 @@ final public class Operations {
* Returns the longest BytesRef that is a prefix of all accepted strings and
* visits each state at most once. The automaton must be deterministic.
*
* @return common prefix
* @return common prefix, which can be an empty (length 0) BytesRef (never null)
*/
public static BytesRef getCommonPrefixBytesRef(Automaton a) {
BytesRefBuilder builder = new BytesRefBuilder();
@ -1159,7 +1159,7 @@ final public class Operations {
* @param maxDeterminizedStates maximum number of states determinizing the
* automaton can result in. Set higher to allow more complex queries and
* lower to prevent memory exhaustion.
* @return common suffix
* @return common suffix, which can be an empty (length 0) BytesRef (never null)
*/
public static BytesRef getCommonSuffixBytesRef(Automaton a, int maxDeterminizedStates) {
// reverse the language of the automaton, then reverse its common prefix.