trie: one node per rune, children in rune order, and the last path kept

The trie walked a key byte by byte, so a Hangul syllable cost three
nodes and every lookup first spelled its key back into UTF-8.  It walks
runes now: a third of the nodes for Korean data, and no buffer in the
lookup.  Children are kept in rune order, so both the search and the
insert stop early, and a trie remembers the path of the last key put,
which a file sorted by key — hanja.dict is one — walks straight down.

dat.h

@@ -74,7 +74,7 @@ struct Tnode
 	int	vlen;
 	int	child;
 	int	sibling;
-	char	c;
+	Rune	c;
 };
 
 typedef struct Trie Trie;
@@ -83,6 +83,9 @@ struct Trie
 	Tnode	*nodes;
 	int	n;
 	int	cap;
+	/* the last key put and its path, so a sorted file walks it once */
+	Str	last;
+	int	path[Maxrunes];
 };
 
 enum

dict.c

@@ -24,7 +24,7 @@ words(Tnode *nd, Str *out, int n, int max)
 	return n;
 }
 
-/* The entries at and below a node, in the dictionary's order. */
+/* The entries at and below a node, the shortest keys first. */
 static int
 below(Trie *t, int ni, Str *out, int n, int max)
 {

trie.c

@@ -3,9 +3,9 @@
 #include "fn.h"
 
 /*
- * A byte trie over UTF-8 keys.  Maps need prefix matches while composing;
- * dictionaries need exact matches; both are small enough for one structure.
- * Node 0 is the root.
+ * A trie over the runes of a key.  Maps need prefix matches while
+ * composing; dictionaries need exact matches; both are small enough for
+ * one structure.  Node 0 is the root.
  */
 
 static int
@@ -24,32 +24,37 @@ newnode(Trie *t)
 	return i;
 }
 
+/* The children of a node are kept in rune order, so both end early. */
 static int
-find(Trie *t, int ni, char c)
+find(Trie *t, int ni, Rune c)
 {
 	int pi;
 
-	for(pi = t->nodes[ni].child; pi >= 0; pi = t->nodes[pi].sibling)
+	for(pi = t->nodes[ni].child; pi >= 0; pi = t->nodes[pi].sibling){
 		if(t->nodes[pi].c == c)
 			return pi;
+		if(t->nodes[pi].c > c)
+			break;
+	}
 	return -1;
 }
 
-/* Appends, so that a walk of the children keeps the file's order. */
 static int
-add(Trie *t, int ni, char c)
+add(Trie *t, int ni, Rune c)
 {
-	int last, pi;
+	int next, pi, prev;
 
-	last = -1;
-	for(pi = t->nodes[ni].child; pi >= 0; pi = t->nodes[pi].sibling)
-		last = pi;
+	prev = -1;
+	for(next = t->nodes[ni].child; next >= 0 && t->nodes[next].c < c;
+	    next = t->nodes[next].sibling)
+		prev = next;
 	pi = newnode(t);
 	t->nodes[pi].c = c;
-	if(last < 0)
+	t->nodes[pi].sibling = next;
+	if(prev < 0)
 		t->nodes[ni].child = pi;
 	else
-		t->nodes[last].sibling = pi;
+		t->nodes[prev].sibling = pi;
 	return pi;
 }
 
@@ -69,15 +74,26 @@ trienew(void)
 void
 trieput(Trie *t, char *key, int klen, char *val, int vlen)
 {
-	int ni, ci, i;
+	Str k;
+	int ci, i, ni, same;
 
+	if(!sinit(&k, key, klen))
+		return;
 	ni = 0;
-	for(i = 0; i < klen; i++){
-		ci = find(t, ni, key[i]);
-		if(ci < 0)
-			ci = add(t, ni, key[i]);
-		ni = ci;
+	same = 1;
+	for(i = 0; i < k.n; i++){
+		if(same && i < t->last.n && t->last.r[i] == k.r[i]){
+			ni = t->path[i];
+			continue;
 		}
+		same = 0;
+		ci = find(t, ni, k.r[i]);
+		if(ci < 0)
+			ci = add(t, ni, k.r[i]);
+		ni = ci;
+		t->path[i] = ni;
+	}
+	t->last = k;
 	free(t->nodes[ni].val);
 	t->nodes[ni].val = emalloc(vlen + 1);
 	memmove(t->nodes[ni].val, val, vlen);
@@ -163,15 +179,13 @@ trieclose(Trie *t)
 int
 trienode(Trie *t, Str *key)
 {
-	char buf[Maxutf];
-	int i, klen, ni;
+	int i, ni;
 
 	if(t == nil)
 		return -1;
-	klen = stoutf(key, buf, sizeof buf);
 	ni = 0;
-	for(i = 0; i < klen && ni >= 0; i++)
-		ni = find(t, ni, buf[i]);
+	for(i = 0; i < key->n && ni >= 0; i++)
+		ni = find(t, ni, key->r[i]);
 	return ni;
 }