Hojun-Cho/strans
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

data: one trie for maps and dictionaries, one loader

Browse Source 
The hash map served a single exact-match lookup that the trie already
answers, at the price of a second container, a second file loader with
its own drift, and a Str-to-UTF-8 conversion on every chain probe. The
files are small (kanji.dict is 7.5k lines), so the trie holds both.
trieopen validates keys and each space-separated value word against Str
and reports path:line; trielookup takes the Str every caller holds and
treats a nil trie as an unloaded map; trienew/trieput exist for tests.
The overflow guards on growth, Trie.root (always 0) and the per-language
init loop written twice are gone.
This commit is contained in:
Hojun-Cho
2026-08-16 15:56:32 +09:00
parent eb0f88f764
commit c7718ece52
15 changed files with 206 additions and 609 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
tests/trie_test.c
View File

@@ -5,26 +5,26 @@ trie_exact_prefix_and_duplicate(struct ct *t)
{
static const struct {
char *key;
int klen;
int match;
char *want;
} cases[] = {
{ "a", 1, TrieExact, "alpha" },
{ "dupli", 5, TriePrefix, nil },
{ "duplicate", 9, TrieExact, "second" },
{ "missing", 7, TrieMiss, nil },
{ nil, 1, TrieMiss, nil },
{ "a", -1, TrieMiss, nil },
{ "a", TrieExact, "alpha" },
{ "ab", TrieExact, "beta" },
{ "한", TrieExact, "값" },
{ "dupli", TriePrefix, nil },
{ "duplicate", TrieExact, "second" },
{ "missing", TrieMiss, nil },
{ "", TriePrefix, nil },
};
char *v;
Trie *trie;
Str key;
int i, match, n;
trie = trieopen("data/trie.map");
for(i = 0; i < nelem(cases); i++){
v = "unchanged";
n = 77;
match = trielookup(trie, cases[i].key, cases[i].klen, &v, &n);
key = mkstr(cases[i].key);
match = trielookup(trie, &key, &v, &n);
if(match != cases[i].match){
CT_ERRORF(t, "case %d: want match %d, got %d",
i, cases[i].match, match);
@@ -42,22 +42,28 @@ trie_exact_prefix_and_duplicate(struct ct *t)
}
void
trie_optional_outputs_and_invalid_lengths(struct ct *t)
trie_put_and_unloaded(struct ct *t)
{
char *v;
Trie *trie;
Str key;
int n;
trie = trieopen("data/trie.map");
CT_EQ_INT(t, TrieExact, trielookup(trie, "a", 1, &v, nil));
CT_CHECK(t, v != nil);
CT_EQ_INT(t, TrieExact, trielookup(trie, "a", 1, nil, &n));
CT_EQ_INT(t, 5, n);
CT_EQ_INT(t, TriePrefix,
trielookup(trie, "dupli", 5, nil, nil));
CT_EQ_INT(t, TriePrefix, trielookup(trie, nil, 0, &v, &n));
CT_EQ_PTR(t, nil, v);
CT_EQ_INT(t, 0, n);
key = mkstr("k");
CT_EQ_INT(t, TrieMiss, trielookup(nil, &key, &v, &n));
trie = trienew();
CT_EQ_INT(t, TrieMiss, trielookup(trie, &key, &v, &n));
trieput(trie, "k", 1, "one two", 7);
trieput(trie, "ka", 2, "", 0);
if(CT_EQ_INT(t, TrieExact, trielookup(trie, &key, &v, &n)))
CT_EQ_MEM(t, "one two", v, 7);
key = mkstr("ka");
if(CT_EQ_INT(t, TrieExact, trielookup(trie, &key, &v, &n)))
CT_EQ_INT(t, 0, n);
trieput(trie, "k", 1, "three", 5);
key = mkstr("k");
if(CT_EQ_INT(t, TrieExact, trielookup(trie, &key, &v, &n)))
CT_EQ_MEM(t, "three", v, 5);
trieclose(trie);
}