reverse-engineering-anything/src/domain/analysisSearch.ts

import { z } from "zod";

import { analysisSearchInput } from "../contracts/analysisSearchContract.js";
import { AnalysisInputError } from "./analysisErrorCore.js";

/** Parsed `search_procedures`/`search_strings` query shared by providers that match in REA. */
export const analysisSearchQuerySchema = z.object(analysisSearchInput);

export type AnalysisSearchQuery = z.infer<typeof analysisSearchQuerySchema>;

/**
 * Match a literal substring. With case ignored, ECMAScript Unicode RegExp
 * matching applies simple case folding character-by-character
 * ([Canonicalize](https://tc39.es/ecma262/2023/multipage/text-processing.html#sec-runtime-semantics-canonicalize));
 * it is locale-independent and does not expand characters into sequences.
 */
export const literalSubstringPredicate = (
  pattern: string,
  caseSensitive: boolean,
): ((value: string) => boolean) => {
  if (caseSensitive) return (value) => value.includes(pattern);
  const escaped = pattern.replace(/[.*+?^${}()|[\]\\]/gu, "\\$&");
  const regex = new RegExp(escaped, "iu");
  return (value) => regex.test(value);
};

/**
 * Match names the way the search contract describes: a literal substring by
 * default, or a Unicode regular expression, case-insensitive unless requested.
 * An invalid pattern is the caller's input error.
 */
export const analysisSearchPredicate = (
  query: AnalysisSearchQuery,
): ((value: string) => boolean) => {
  if (query.mode === "regex") {
    let regex: RegExp;
    try {
      regex = new RegExp(query.pattern, query.case_sensitive ? "u" : "iu");
    } catch (cause: unknown) {
      throw new AnalysisInputError("search", { cause });
    }
    return (value) => regex.test(value);
  }
  return literalSubstringPredicate(query.pattern, query.case_sensitive);
};