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

Adding more JavaDoc to FST Builder because the arguments are rather cryptic right now. 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1130976 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Dawid Weiss 2011-06-03 10:39:33 +00:00
parent c7b59aec0b
commit 9e4a656592
1 changed files with 37 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
lucene/src/java/org/apache/lucene/util/fst/Builder.java
View File

@ -21,6 +21,7 @@ import org.apache.lucene.util.ArrayUtil;
import org.apache.lucene.util.RamUsageEstimator;
import org.apache.lucene.util.BytesRef;
import org.apache.lucene.util.IntsRef;
import org.apache.lucene.util.fst.FST.INPUT_TYPE;
import java.io.IOException;
@ -69,6 +70,42 @@ public class Builder<T> {
// current "frontier"
private UnCompiledNode<T>[] frontier;
/**
* Instantiates an FST/FSA builder without any pruning. A shortcut
* to {@link #Builder(INPUT_TYPE, int, int, boolean, Outputs)} with
* pruning options turned off.
*/
public Builder(FST.INPUT_TYPE inputType, Outputs<T> outputs)
{
this(inputType, 0, 0, true, outputs);
}
/**
* Instantiates an FST/FSA builder with all the possible tuning and construction
* tweaks. Read parameter documentation carefully.
*
* @param inputType
* The input type (transition labels). Can be anything from {@link INPUT_TYPE}
* enumeration. Shorter types will consume less memory. Strings (character sequences) are
* represented as {@link INPUT_TYPE#BYTE4} (full unicode codepoints).
*
* @param minSuffixCount1
* If pruning the input graph during construction, this threshold is used for telling
* if a node is kept or pruned. If transition_count(node) &gt;= minSuffixCount1, the node
* is kept.
*
* @param minSuffixCount2
* (Note: only Mike McCandless knows what this one is really doing...)
*
* @param doMinSuffix
* If <code>true</code>, the shared suffixes will be compacted into unique paths.
* This requires an additional hash map for lookups in memory. Setting this parameter to
* <code>false</code> creates a single path for all input sequences. This will result in a larger
* graph, but may require less memory and will speed up construction.
* @param outputs The output type for each input sequence. Applies only if building an FST. For
* FSA, use {@link NoOutputs#getSingleton()} and {@link NoOutputs#getNoOutput()} as the
* singleton output object.
*/
public Builder(FST.INPUT_TYPE inputType, int minSuffixCount1, int minSuffixCount2, boolean doMinSuffix, Outputs<T> outputs) {
this.minSuffixCount1 = minSuffixCount1;
this.minSuffixCount2 = minSuffixCount2;