mirror of
https://github.com/morluto/rea
synced 2026-10-27 06:33:32 -04:00
fix(reference): report sloppy scripts, PHP, C# and enclosing Git facts (#1770)
* fix(reference): report sloppy scripts, PHP, C# and enclosing Git facts Importing the source/ subtree of a legacy PHP and C# checkout produced four wrong or missing facts: - Babel's unambiguous mode parses a module first and keeps its strict-mode recovery errors after falling back to a script, so a valid sloppy-mode `delete messages;` was reported as a parse failure and the semantic IR marked the file as parser-recovered. Parsing now goes through one owner that re-parses such a script as a script. - .php and .cs files had no language; they are now detected as PHP and C# (detection only, no parsing). - A root without its own .git was reported as having no version control even inside a checkout. The adapter now resolves the nearest enclosing repository, as Git does, and reports `none` only when no ancestor has one. - The CLI recorded importer_version as null although the package version is known. * fix(reference): keep module strictness and classify C# and PHP as source Review follow-up. `.mjs` and `.mts` files are modules by extension, but the script fallback re-parsed them in sloppy mode and erased real strict-mode errors. The parser boundary now owns the extension rule, parses explicit modules as modules and applies the fallback only when the mode is ambiguous; the require-binding analysis uses the same rule. `.cs` and `.php` received a language but stayed classified as unknown, so source-to-bundle comparison dropped them. Both are now source extensions, like the other detected languages. * fix(reference): honor package module scope and keep unknown-mode strict errors Review follow-up. A `.js` file under a package.json with `"type": "module"` is an ES module, but it went through the script fallback that erases strict-mode errors. The import now reads each in-inventory package.json and parses `.js` files in a module scope as modules. Other `.js` and `.ts` sources keep an unknown mode, because bundlers treat them as modules without that field: they are no longer forced to script, and errors that only the module parse reports are kept as an entry limitation. * fix(reference): bound package scopes and keep application parsing unchanged Review follow-up. - `.cjs` files parse as scripts, so module-only strict errors no longer become limitations on CommonJS trees. `.cts` keeps an unknown mode because TypeScript compiles ES import syntax there. - An unreadable or linked package.json now bounds the module scope with an unknown type instead of letting an outer `"type": "module"` apply. - The application pipeline parses as on main again. Its module-only strict errors keep a source partial; package-mode handling stays in the reference importer. * refactor(reference): keep unmarked module modes unknown instead of resolving package scope Review follow-up. Resolving Node package scope for `.js` kept pulling in more of Node's lookup semantics (require bindings, excluded or directory-named manifests). Only extensions now select a mode: `.mjs` and `.mts` parse as modules and `.cjs` as scripts. Every other source keeps an unknown mode, so module-only strict errors stay visible as an entry limitation instead of being dropped or asserted. This matches the require-binding analysis, which also treats unmarked paths as unknown.
This commit is contained in:
@@ -1,4 +1,4 @@
|
||||
import { parse, type ParserPlugin } from "@babel/parser";
|
||||
import { parse, type ParserOptions, type ParserPlugin } from "@babel/parser";
|
||||
|
||||
/** Babel AST produced by REA's inert JavaScript parser boundary. */
|
||||
export type ParsedJavaScriptSource = ReturnType<typeof parse>;
|
||||
@@ -37,6 +37,67 @@ export const parserPluginsForPath = (sourcePath?: string): ParserPlugin[] => {
|
||||
: ["decorators-legacy", typescript];
|
||||
};
|
||||
|
||||
/** `.mjs` and `.mts` are modules by extension; other paths leave the mode to syntax. */
|
||||
export const isExplicitModuleSourcePath = (path?: string): boolean =>
|
||||
/\.m[jt]s$/iu.test(path ?? "");
|
||||
|
||||
export interface RecoveredJavaScriptParse {
|
||||
readonly file: ParsedJavaScriptSource;
|
||||
/** Errors that apply only if a source of unknown mode is an ES module. */
|
||||
readonly moduleOnlyErrors: readonly string[];
|
||||
}
|
||||
|
||||
/**
|
||||
* Parse a module or script with recovery. Babel tries module mode first and
|
||||
* keeps its strict-mode errors after falling back to a script, so a script
|
||||
* with errors is parsed again as a script. Strict errors that only the module
|
||||
* parse reports stay visible because the source may still be a module.
|
||||
*/
|
||||
export const parseRecoveredJavaScript = (
|
||||
source: string,
|
||||
sourcePath: string | undefined,
|
||||
options: Omit<ParserOptions, "sourceType" | "errorRecovery">,
|
||||
): RecoveredJavaScriptParse => {
|
||||
// `.cjs` is CommonJS by extension, so module-only errors cannot apply.
|
||||
if (/\.cjs$/iu.test(sourcePath ?? ""))
|
||||
return {
|
||||
file: parse(source, {
|
||||
...options,
|
||||
sourceType: "script",
|
||||
errorRecovery: true,
|
||||
}),
|
||||
moduleOnlyErrors: [],
|
||||
};
|
||||
if (isExplicitModuleSourcePath(sourcePath))
|
||||
return {
|
||||
file: parse(source, {
|
||||
...options,
|
||||
sourceType: "module",
|
||||
errorRecovery: true,
|
||||
}),
|
||||
moduleOnlyErrors: [],
|
||||
};
|
||||
const file = parse(source, {
|
||||
...options,
|
||||
sourceType: "unambiguous",
|
||||
errorRecovery: true,
|
||||
});
|
||||
if (file.program.sourceType !== "script" || file.errors.length === 0)
|
||||
return { file, moduleOnlyErrors: [] };
|
||||
const script = parse(source, {
|
||||
...options,
|
||||
sourceType: "script",
|
||||
errorRecovery: true,
|
||||
});
|
||||
const scriptErrors = new Set(script.errors.map((error) => error.message));
|
||||
return {
|
||||
file: script,
|
||||
moduleOnlyErrors: file.errors
|
||||
.map((error) => error.message)
|
||||
.filter((message) => !scriptErrors.has(message)),
|
||||
};
|
||||
};
|
||||
|
||||
/** Parse JavaScript or TypeScript once without attaching comments to AST nodes. */
|
||||
export const parseJavaScriptSource = (
|
||||
source: string,
|
||||
|
||||
Reference in New Issue
Block a user