Function scorePathRelevance

src/search/query-utils.ts:221–275

(
  filePath: string,
  query: string,
  projectNameTokens?: Set<string>,
)

 * Higher score = more relevant path
 */
export function scorePathRelevance(
  filePath: string,
  query: string,
  projectNameTokens?: Set<string>,
): number {
  const pathLower = filePath.toLowerCase();
  const fileName = path.basename(filePath).toLowerCase();
  const dirName = path.dirname(filePath).toLowerCase();
  let score = 0;

  // Score per original query WORD, not per sub-token. A single PascalCase word
  // splits into many sub-tokens (a project name "SuperBizAgent" →
  // superbizagent / super / biz / agent) that all match the SAME path segment,
  // so summing per sub-token boosted that path 4× for one concept — enough to
  // bury the rest of the query's stack (#720). A word matches a path level if
  // ANY of its sub-tokens do, and counts ONCE; distinct words still each add.
  // Split the ORIGINAL-case query into words; extractSearchTerms does the
  // camelCase/snake split per word (so `getUserName` still matches a
  // `get_user_name` path) — we just attribute each word's matches once.
  const allWords = query.split(/\s+/).filter((w) => w.length > 0);
  if (allWords.length === 0) return 0;

  // A query word that just names the PROJECT (its go.mod / package.json / repo
  // name) carries no discriminative path signal — drop it so the rest of the
  // query decides the ranking, instead of every file under a `<ProjectName>…/`
  // tree winning on the project name alone (#720). Only when OTHER words remain,
  // so a bare project-name query still scores on its path.
  const words =
    projectNameTokens && projectNameTokens.size > 0
      ? allWords.filter((w) => !projectNameTokens.has(normalizeNameToken(w)))
      : allWords;
  const scored = words.length > 0 ? words : allWords;

  for (const word of scored) {
    // Use base terms only — stem variants inflate path scores by generating
    // many near-duplicate terms that all match the same path segments.
    const subtokens = extractSearchTerms(word, { stems: false });
    if (subtokens.length === 0) continue;
    // Exact filename match (strongest)
    if (subtokens.some((t) => fileName.includes(t))) score += 10;
    // Directory match
    if (subtokens.some((t) => dirName.includes(t))) score += 5;
    // General path match
    else if (subtokens.some((t) => pathLower.includes(t))) score += 3;
  }

  // Deprioritize test files unless the query is explicitly about tests
  const queryLower = query.toLowerCase();
  const isTestQuery = queryLower.includes('test') || queryLower.includes('spec');
  if (!isTestQuery && isTestFile(filePath)) {
    score -= 15;
  }

  return score;
}

/**
 * Check if a file path looks like a test file