Skip to content

fix(extract): populate body_tokens before MinHash gate; add OS/TS identifier node types #1060

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
isc-tdyar wants to merge 1 commit into
base: main
Choose a base branch
from
+30 −5
Open

fix(extract): populate body_tokens before MinHash gate; add OS/TS identifier node types #1060

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 10 additions & 5 deletions internal/cbm/extract_defs.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,7 +82,7 @@ static bool try_append_ident(const char *source, uint32_t s, int len, uint32_t *
/* Walk AST body, collect unique identifier text as space-separated string.
* Returns arena-allocated string or NULL. */
static char *extract_body_ident_tokens(CBMExtractCtx *ctx, TSNode body) {
enum { BT_STACK = 512, BT_BUF = 512, BT_MAX_IDENTS = 40, BT_SEEN = 128, BT_SEEN_MASK = 127 };
enum { BT_STACK = 512, BT_BUF = 2048, BT_MAX_IDENTS = 128, BT_SEEN = 256, BT_SEEN_MASK = 255 };
TSNode bt_stack[BT_STACK];
int bt_top = 0;
bt_stack[bt_top++] = body;
Expand All @@ -98,7 +98,11 @@ static char *extract_body_ident_tokens(CBMExtractCtx *ctx, TSNode body) {
if (nc == 0) {
const char *k = ts_node_type(nd);
if (strcmp(k, "identifier") == 0 || strcmp(k, "field_identifier") == 0 ||
strcmp(k, "property_identifier") == 0) {
strcmp(k, "property_identifier") == 0 || strcmp(k, "type_identifier") == 0 ||
strcmp(k, "objectscript_identifier_special") == 0 ||
strcmp(k, "identifier_segment_immediate_special") == 0 ||
strcmp(k, "class_name") == 0 || strcmp(k, "method_name") == 0 ||
strcmp(k, "routine_name") == 0 || strcmp(k, "quote_permitting_identifier") == 0) {
uint32_t s = ts_node_start_byte(nd);
int len = (int)(ts_node_end_byte(nd) - s);
if (len > 0 && len < CBM_SZ_64 && s < (uint32_t)ctx->source_len) {
Expand Down Expand Up @@ -128,6 +132,10 @@ static void compute_fingerprint(CBMExtractCtx *ctx, CBMDefinition *def, TSNode f
if (ts_node_is_null(body)) {
body = func_node;
}
/* Extract raw identifier tokens from body for semantic search — before MinHash gate
* so short functions still get body_tokens even without a fingerprint. */
def->body_tokens = extract_body_ident_tokens(ctx, body);

cbm_minhash_t result;
if (!cbm_minhash_compute(body, ctx->source, (int)ctx->language, &result)) {
return; /* Too short or empty — no fingerprint */
Expand Down Expand Up @@ -155,9 +163,6 @@ static void compute_fingerprint(CBMExtractCtx *ctx, CBMDefinition *def, TSNode f
cbm_ast_profile_to_str(&profile, sp_buf, sizeof(sp_buf));
def->structural_profile = cbm_arena_strdup(ctx->arena, sp_buf);
}

/* Extract raw identifier tokens from body for semantic search */
def->body_tokens = extract_body_ident_tokens(ctx, body);
}

// Tree-sitter row is 0-based; lines are 1-based.
Expand Down
20 changes: 20 additions & 0 deletions tests/test_extraction.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -802,6 +802,25 @@ TEST(ts_class) {
PASS();
}

TEST(body_tokens_type_identifier) {
CBMFileResult *r = extract("function serialize(obj: MyModel): SerializedResult {\n"
" const result: SerializedResult = new SerializedResult();\n"
" return result;\n"
"}\n",
CBM_LANG_TYPESCRIPT, "t", "serial.ts");
ASSERT_NOT_NULL(r);
ASSERT_FALSE(r->has_error);
for (int i = 0; i < r->defs.count; i++) {
if (strcmp(r->defs.items[i].name, "serialize") == 0) {
ASSERT_NOT_NULL(r->defs.items[i].body_tokens);
ASSERT(strstr(r->defs.items[i].body_tokens, "SerializedResult") != NULL);
break;
}
}
cbm_free_result(r);
PASS();
}

/* --- Lua --- */
TEST(lua_function) {
CBMFileResult *r = extract(
Expand Down Expand Up @@ -3683,6 +3702,7 @@ SUITE(extraction) {
RUN_TEST(js_class);
RUN_TEST(ts_function);
RUN_TEST(ts_class);
RUN_TEST(body_tokens_type_identifier);
RUN_TEST(lua_function);
RUN_TEST(bash_function);
RUN_TEST(perl_function);
Expand Down
Loading