mirror of
https://github.com/sourcebot-dev/sourcebot.git
synced 2025-12-12 12:25:22 +00:00
f3a8fa3dab
Some checks failed
Publish to ghcr / build (linux/amd64, blacksmith-4vcpu-ubuntu-2404) (push) Has been cancelled
Publish to ghcr / build (linux/arm64, blacksmith-8vcpu-ubuntu-2204-arm) (push) Has been cancelled
Update Roadmap Released / update (push) Has been cancelled
Publish to ghcr / merge (push) Has been cancelled
* generate protobuf types * stream poc over SSE * wip: make stream search api follow existing schema. Modify UI to support streaming * fix scrolling issue * Dockerfile * wip on lezer parser grammar for query language * add lezer tree -> grpc transformer * remove spammy log message * fix syntax highlighting by adding a module resolution for @lezer/common * further wip on query language * Add case sensitivity and regexp toggles * Improved type safety / cleanup for query lang * support search contexts * update Dockerfile with query langauge package * fix filter * Add skeletons to filter panel when search is streaming * add client side caching * improved cancelation handling * add isSearchExausted flag for flagging when a search captured all results * Add back posthog search_finished event * remove zoekt tenant enforcement * migrate blocking search over to grpc. Centralize everything in searchApi * branch handling * plumb file weburl * add repo_sets filter for repositories a user has access to * refactor a bunch of stuff + add support for passing in Query IR to search api * refactor * dev README * wip on better error handling * error handling for stream path * update mcp * changelog wip * type fix * style * Support rev:* wildcard * changelog * changelog nit * feedback * fix build * update docs and remove uneeded test file
59 lines
1.7 KiB
TypeScript
59 lines
1.7 KiB
TypeScript
import { ExternalTokenizer } from "@lezer/lr";
|
|
import { negate } from "./parser.terms";
|
|
|
|
// External tokenizer for negation
|
|
// Only tokenizes `-` as negate when followed by a prefix keyword or `(`
|
|
export const negateToken = new ExternalTokenizer((input) => {
|
|
if (input.next !== 45 /* '-' */) return; // Not a dash
|
|
|
|
const startPos = input.pos;
|
|
|
|
// Look ahead to see what follows the dash
|
|
input.advance();
|
|
|
|
// Skip whitespace
|
|
let ch = input.next;
|
|
while (ch === 32 || ch === 9 || ch === 10) {
|
|
input.advance();
|
|
ch = input.next;
|
|
}
|
|
|
|
// Check if followed by opening paren
|
|
if (ch === 40 /* '(' */) {
|
|
input.acceptToken(negate, -input.pos + startPos + 1); // Accept just the dash
|
|
return;
|
|
}
|
|
|
|
// Check if followed by a prefix keyword (by checking for keyword followed by colon)
|
|
// Look ahead until we hit a delimiter or colon
|
|
const checkPos = input.pos;
|
|
let foundColon = false;
|
|
|
|
// Look ahead until we hit a delimiter or colon
|
|
while (ch >= 0) {
|
|
if (ch === 58 /* ':' */) {
|
|
foundColon = true;
|
|
break;
|
|
}
|
|
// Hit a delimiter (whitespace, paren, or quote) - not a prefix keyword
|
|
if (ch === 32 || ch === 9 || ch === 10 || ch === 40 || ch === 41 || ch === 34) {
|
|
break;
|
|
}
|
|
input.advance();
|
|
ch = input.next;
|
|
}
|
|
|
|
// Reset position
|
|
while (input.pos > checkPos) {
|
|
input.advance(-1);
|
|
}
|
|
|
|
if (foundColon) {
|
|
// It's a prefix keyword, accept as negate
|
|
input.acceptToken(negate, -input.pos + startPos + 1);
|
|
return;
|
|
}
|
|
|
|
// Otherwise, don't tokenize as negate (let word handle it)
|
|
});
|
|
|