public HyphenationTree()
{
stoplist = new Hashtable(23); // usually a small table
classmap = new TernaryTree();
vspace = new ByteVector();
vspace.Alloc(1); // this reserves index 0, which we don't use
}
public Iterator(TernaryTree parent)
{
this.parent = parent;
cur = -1;
ns = new Stack();
ks = new StringBuilder();
Rewind();
}
public Object Clone()
{
TernaryTree t = new TernaryTree();
t.lo = (char[])this.lo.Clone();
t.hi = (char[])this.hi.Clone();
t.eq = (char[])this.eq.Clone();
t.sc = (char[])this.sc.Clone();
t.kv = (CharVector)this.kv.Clone();
t.root = this.root;
t.freenode = this.freenode;
t.length = this.length;
return(t);
}
public void LoadSimplePatterns(Stream stream)
{
SimplePatternParser pp = new SimplePatternParser();
ivalues = new TernaryTree();
pp.Parse(stream, this);
// patterns/values should be now in the tree
// let's optimize a bit
TrimToSize();
vspace.TrimToSize();
classmap.TrimToSize();
// get rid of the auxiliary map
ivalues = null;
}
/**
* Each node stores a character (splitchar) which is part of
* some Key(s). In a compressed branch (one that only contain
* a single string key) the trailer of the key which is not
* already in nodes is stored externally in the kv array.
* As items are inserted, key substrings decrease.
* Some substrings may completely disappear when the whole
* branch is totally decompressed.
* The tree is traversed to find the key substrings actually
* used. In addition, duplicate substrings are removed using
* a map (implemented with a TernaryTree!).
*
*/
public void TrimToSize()
{
// first balance the tree for best performance
Balance();
// redimension the node arrays
RedimNodeArrays(freenode);
// ok, compact kv array
CharVector kx = new CharVector();
kx.Alloc(1);
TernaryTree map = new TernaryTree();
Compact(kx, map, root);
kv = kx;
kv.TrimToSize();
}
public Iterator(TernaryTree parent)
{
this.parent = parent;
cur = -1;
ns = new Stack();
ks = new StringBuilder();
Rewind();
}
private void Compact(CharVector kx, TernaryTree map, char p)
{
int k;
if (p == 0)
return;
if (sc[p] == 0xFFFF) {
k = map.Find(kv.Arr, lo[p]);
if (k < 0) {
k = kx.Alloc(Strlen(kv.Arr, lo[p]) + 1);
Strcpy(kx.Arr, k, kv.Arr, lo[p]);
map.Insert(kx.Arr, k, (char)k);
}
lo[p] = (char)k;
} else {
Compact(kx, map, lo[p]);
if (sc[p] != 0)
Compact(kx, map, eq[p]);
Compact(kx, map, hi[p]);
}
}
/**
* Each node stores a character (splitchar) which is part of
* some Key(s). In a compressed branch (one that only contain
* a single string key) the trailer of the key which is not
* already in nodes is stored externally in the kv array.
* As items are inserted, key substrings decrease.
* Some substrings may completely disappear when the whole
* branch is totally decompressed.
* The tree is traversed to find the key substrings actually
* used. In addition, duplicate substrings are removed using
* a map (implemented with a TernaryTree!).
*
*/
public void TrimToSize()
{
// first balance the tree for best performance
Balance();
// redimension the node arrays
RedimNodeArrays(freenode);
// ok, compact kv array
CharVector kx = new CharVector();
kx.Alloc(1);
TernaryTree map = new TernaryTree();
Compact(kx, map, root);
kv = kx;
kv.TrimToSize();
}
public Object Clone()
{
TernaryTree t = new TernaryTree();
t.lo = (char[])this.lo.Clone();
t.hi = (char[])this.hi.Clone();
t.eq = (char[])this.eq.Clone();
t.sc = (char[])this.sc.Clone();
t.kv = (CharVector)this.kv.Clone();
t.root = this.root;
t.freenode = this.freenode;
t.length = this.length;
return t;
}
public void LoadSimplePatterns(Stream stream)
{
SimplePatternParser pp = new SimplePatternParser();
ivalues = new TernaryTree();
pp.Parse(stream, this);
// patterns/values should be now in the tree
// let's optimize a bit
TrimToSize();
vspace.TrimToSize();
classmap.TrimToSize();
// get rid of the auxiliary map
ivalues = null;
}
