@appthreat/atom-parsetools 1.3.0 → 1.5.0

package/README.md

@@ -4,7 +4,7 @@ This package hosts a collection of parsing tools that complement the `@appthreat
 
 - astgen - Generates AST for JavaScript and TypeScript projects in JSON format
 - phpastgen - Generates AST for PHP projects using `php-parse` command from `nikic/php-parser`
-- rbastgen - Generates AST for Ruby projects using the AppThreat's `ruby_ast_gen` gem
+- rbastgen - Generates AST for Ruby projects using AppThreat's [`ruby_ast_gen`](https://github.com/AppThreat/ruby_ast_gen) gem (2.0.1)
 - scalasem - Generates a custom semantics slice for Scala Projects by utilising scalac command.
 
 ## Runtime support
@@ -31,13 +31,13 @@ Options:
 
 #### Environment variables
 
-| Variable                    | Default   | Purpose                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
-| --------------------------- | --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `ASTGEN_TYPE_WORKERS`       | `1` (off) | Number of worker threads for the TypeScript type-generation phase, or `auto` to derive it from the available CPUs. The TypeScript checker is single-threaded, so parallelism comes from sharding files across workers, each building its own program. **Opt-in:** sharding changes TypeScript's internal type-id ordering, which reorders the members of a small number of inferred union types (e.g. `A \| B` → `B \| A`; semantically identical). Leave unset for byte-identical output; set it (e.g. `auto` or `8`) to trade that cosmetic reordering for a large speedup on big projects. |
-| `ASTGEN_INCLUDE_TEST_FILES` | `false`   | When `true`, do not exclude test files (`*.poku.js`, `*.test.*`, `*.spec.*`, `*.e2e.*`, `__tests__/`, `__mocks__/`) from AST and type generation. They are excluded by default because they are typically the heaviest, lowest-value inputs for type generation.                                                                                                                                                                                                                                                                                                                              |
-| `ASTGEN_CONCURRENCY`        | `10`      | Chunk size for the in-thread file loop (bounds peak memory between `gc()` passes).                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
-| `ASTGEN_INCLUDE_NODE_MODULES_BUNDLES` | `false` | When `true`, also parse bundled entrypoints inside `node_modules` (files matching `*.(bundle\|dist\|index\|min\|app).(js\|cjs\|mjs)`). Off by default; `node_modules` is otherwise skipped entirely.                                                                                                                                                                                                                                                       |
-| `ASTGEN_IGNORE_DIRS`        | unset     | Comma/space-separated list of directories to ignore. As a side effect, when it is set and does **not** contain `node_modules`, the `node_modules` bundle entrypoints above are included (equivalent to `ASTGEN_INCLUDE_NODE_MODULES_BUNDLES=true`).                                                                                                                                                                                                        |
+| Variable                              | Default   | Purpose                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
+| ------------------------------------- | --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `ASTGEN_TYPE_WORKERS`                 | `1` (off) | Number of worker threads for the TypeScript type-generation phase, or `auto` to derive it from the available CPUs. The TypeScript checker is single-threaded, so parallelism comes from sharding files across workers, each building its own program. **Opt-in:** sharding changes TypeScript's internal type-id ordering, which reorders the members of a small number of inferred union types (e.g. `A \| B` → `B \| A`; semantically identical). Leave unset for byte-identical output; set it (e.g. `auto` or `8`) to trade that cosmetic reordering for a large speedup on big projects. |
+| `ASTGEN_INCLUDE_TEST_FILES`           | `false`   | When `true`, do not exclude test files (`*.poku.js`, `*.test.*`, `*.spec.*`, `*.e2e.*`, `__tests__/`, `__mocks__/`) from AST and type generation. They are excluded by default because they are typically the heaviest, lowest-value inputs for type generation.                                                                                                                                                                                                                                                                                                                              |
+| `ASTGEN_CONCURRENCY`                  | `10`      | Chunk size for the in-thread file loop (bounds peak memory between `gc()` passes).                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
+| `ASTGEN_INCLUDE_NODE_MODULES_BUNDLES` | `false`   | When `true`, also parse bundled entrypoints inside `node_modules` (files matching `*.(bundle\|dist\|index\|min\|app).(js\|cjs\|mjs)`). Off by default; `node_modules` is otherwise skipped entirely.                                                                                                                                                                                                                                                                                                                                                                                          |
+| `ASTGEN_IGNORE_DIRS`                  | unset     | Comma/space-separated list of directories to ignore. As a side effect, when it is set and does **not** contain `node_modules`, the `node_modules` bundle entrypoints above are included (equivalent to `ASTGEN_INCLUDE_NODE_MODULES_BUNDLES=true`).                                                                                                                                                                                                                                                                                                                                           |
 
 ### phpastgen
 
@@ -64,17 +64,90 @@ Operations is a list of the following options (--dump by default):
 
 ### rbastgen
 
+Requires Ruby 3.4.x or 4.0.x on the `PATH`, or `ATOM_RUBY_HOME` pointing at an install. The gem and
+its pure-Ruby dependencies are bundled under `plugins/rubyastgen`, so nothing needs to be
+gem-installed, and one build of this package runs under every supported Ruby: the bundle is exposed
+to the interpreter through `GEM_PATH` rather than through bundler's standalone loader, which
+resolved its paths from the ABI of the Ruby that built it.
+
+`prism` and `racc` are deliberately **not** bundled. Both carry C extensions, which are built per
+ABI and per platform, and both are default gems in every supported Ruby, so the runtime's own copies
+are used. One consequence is visible: the newest grammar available follows the interpreter's prism,
+so Ruby 3.4 tops out lower than Ruby 4.0 (grammar 3.5 versus 4.1 at the time of writing). Installing
+a newer `prism` gem on the machine raises it, since the caller's `GEM_PATH` is preserved.
+
 ```text
 node rbastgen.js --help
 Usage:
-  -i, --input      The input file or directory (required)
-  -o, --output     The output directory (default: '.ast')
-  -e, --exclude    The exclusion regex (default: '^(tests?|vendor|spec)')
-  -d, --debug      Enable debug logging
-      --version    Print the version
-      --help       Print usage
+  -i, --input <path>       The input file or directory (required)
+  -o, --output <dir>       The output directory (default: '.ast')
+  -e, --exclude <regex>    The exclusion regex (default: '^(tests?|vendor|spec)')
+  -l, --log <level>        The logging level: debug, info, warn or error (default: info)
+  -d, --debug              Enable debug logging (same as --log debug)
+      --parser-target <x.y>
+                           Parse with a specific Ruby grammar (e.g. 3.4, 4.0) instead
+                           of the newest available
+      --max-depth <n>      Maximum AST depth before truncation (default: 250)
+      --threads <n>        Worker threads for a directory run (default: 10)
+      --fail-on-error      Exit non-zero when any input file failed to parse
+      --parser-info        Print parser/runtime capability information
+      --version            Print the version
+      --help               Print usage
+```
+
+Problems with individual files are reported and skipped, never fatal; only usage errors (a missing
+`-i`, an unusable `--exclude` regex, an invalid `--parser-target`) exit non-zero. Note that
+`rbastgen` does not propagate the generator's exit status, so `--fail-on-error` is reported in the
+log but the wrapper still exits 0 — call the gem directly if a CI job needs to fail on a parse
+error.
+
+#### What the bundled generator emits (ruby_ast_gen 2.0.1)
+
+- **Parsing is decoupled from the running Ruby.** When `prism` is available the newest grammar its
+  translation layer supports is used, so a 3.4 runtime parses Ruby 4.0/4.1 syntax. `--parser-target
+x.y` pins a grammar instead (down to 1.8 through the `parser` gem), and a file that fails under
+  the selected grammar is retried once with the newest one. Every JSON file records the backend
+  that produced it in `parser_backend`, alongside `generator_version` and `ruby_version`.
+- **Ruby DSL files are discovered, not just `.rb`.** `Rakefile`, `Gemfile`, `Capfile`,
+  `Vagrantfile`, `Fastfile` and friends are matched by basename, plus the `.gemspec`, `.rake`,
+  `.ru`, `.rbi`, `.thor`, `.jbuilder`, `.axlsx` and `.rabl` extensions. Vendor and tool
+  directories (`.git`, `.bundle`, `.venv`, …) are skipped.
+- **Non-UTF-8 sources survive.** `# coding:` magic comments are honoured and undecodable bytes are
+  scrubbed rather than dropping the file, marked with `encoding_scrubbed: true`.
+- **Deeply nested source is truncated, not dropped**, with `truncated: true` on the boundary node
+  and a `truncated_nodes` count at the top level (`--max-depth`).
+- **Semantic metadata for consumers**: a `magic_comments` array (Sorbet `typed:` levels,
+  `frozen_string_literal`, …), `call_operator`/`has_parentheses` on calls, `percent_array` and
+  regexp `options`, heredoc body offsets, and `has_sig: true` on a `def` preceded by a Sorbet `sig`
+  block.
+- **Two side-records per run, written inside the output directory**, both ending in `.jsonl` so a
+  consumer globbing `*.json` for ASTs never mistakes them for one:
+  `ruby_ast_gen_manifest.jsonl` (one object: input/output, backend, counts of parsed, failed,
+  skipped, excluded and truncated files, threads, max depth) and
+  `ruby_ast_gen_diagnostics.jsonl` (one object per failed file with message, line, column), the
+  latter written only when something failed and removed when a later run is clean.
+
+To check which backend a machine will use:
+
+```shell
+rbastgen --parser-info
 ```
 
+`Parser gem` and `Prism gem` name the versions actually loaded — the vendored `parser` and the
+runtime's `prism` — so they are the quickest way to tell which copy of each library a machine is
+parsing with. They read `unavailable` only when a library genuinely is not loaded.
+
+#### Environment variables
+
+| Variable                          | Default                | Purpose                                                                                                                                      |
+| --------------------------------- | ---------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- |
+| `ATOM_RUBY_HOME`                  | unset                  | Ruby install directory to use when a suitable `ruby` is not on the `PATH`; its `bin` is prepended to `PATH` for the child process.           |
+| `RUBY_CMD`                        | `ruby`                 | Ruby interpreter to invoke. Set this (or `ATOM_RUBY_HOME`) when the detected version is not 3.4.x/4.0.x.                                     |
+| `RUBY_ASTGEN_BIN`                 | bundled `ruby_ast_gen` | The generator script to run. Point it at a checkout's `exe/ruby_ast_gen` to test an unreleased `ruby_ast_gen` without touching this package. |
+| `ATOM_CWD`                        | `process.cwd()`        | Working directory for the generator, which is what relative `-i`/`-o` paths resolve against.                                                 |
+| `ATOM_TIMEOUT` / `ASTGEN_TIMEOUT` | unset (no timeout)     | Milliseconds before the generator process is killed. `ATOM_TIMEOUT` wins; a non-numeric value is ignored. Also honoured by `scalasem`.       |
+| `GEM_PATH`                        | unset                  | Preserved and appended to the vendored bundle, so gems installed on the machine (a newer `prism`, for instance) stay reachable.              |
+
 ### scalasem
 
 ```text
@@ -87,6 +160,30 @@ Example:
 scalasem $(pwd) slices.json
 ```
 
+## Testing
+
+`npm test` covers the JavaScript/TypeScript side and needs nothing but Node. The Ruby workflow tests
+run the `rbastgen` command end to end against `test-fixtures/projects/ruby-parsing`, so they need a
+built plugin bundle and a supported Ruby, and they skip themselves cleanly when either is missing:
+
+```shell
+bash build.sh --ruby-only
+npm run test:ruby
+```
+
+`ci/verify-packed-tarball.sh` is the release check: it packs the tarball, installs it into a scratch
+project and parses the fixture with the installed copy, asserting along the way that the Ruby bundle
+is present and free of compiled extensions. CI runs it, and it runs the same way locally.
+
+They assert what a consumer depends on rather than that the command ran: which files are discovered
+(including `Gemfile` and `Rakefile`, matched by basename), that `has_sig`, `magic_comments`,
+`percent_array` and regexp `options` are emitted, that the manifest's counts reconcile, that a
+failed file lands in the diagnostics record while the run still exits 0, that a clean run leaves no
+stale record behind, and that the bundle contains no compiled extension. CI runs them under both
+Ruby 3.4 and Ruby 4.0 against a bundle built with 3.4, and separately installs the packed tarball
+and parses with that, which is the check that catches a bundle usable only on the Ruby that built
+it.
+
 ## License
 
 MIT

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@appthreat/atom-parsetools",
-  "version": "1.3.0",
+  "version": "1.5.0",
   "description": "Parsing tools that complement the @appthreat/atom project.",
   "main": "./index.js",
   "type": "module",
@@ -8,6 +8,13 @@
     "pretty": "prettier --write *.js --trailing-comma=none",
     "test": "node test-fixtures/astgen-type-regression.js && node test-fixtures/astgen-json-regression.js && node test-fixtures/astgen-vue-regression.js && node test-fixtures/astgen-shape-snapshot.js && node test-fixtures/evaluate-astgen.js",
     "test:evaluate": "node test-fixtures/evaluate-astgen.js",
+    "test:ruby": "node test-fixtures/rbastgen-regression.js",
+    "test:php": "node test-fixtures/phpastgen-cli.js && node test-fixtures/phpastgen-parser-info.js && node test-fixtures/phpastgen-discovery.js && node test-fixtures/phpastgen-provenance.js && node test-fixtures/phpastgen-framework-facts.js && node test-fixtures/phpastgen-legacy-regression.js && node test-fixtures/phpastgen-concurrency.js && node test-fixtures/phpastgen-regression.js && node test-fixtures/phpastgen-contract-snapshot.js && npm run test:php:pbt",
+    "test:php:concurrency": "node test-fixtures/phpastgen-concurrency.js",
+    "test:php:contract": "node test-fixtures/phpastgen-contract-snapshot.js",
+    "test:php:contract:update": "UPDATE_PHP_CONTRACT_SNAPSHOT=1 node test-fixtures/phpastgen-contract-snapshot.js",
+    "test:php:cli": "node test-fixtures/phpastgen-cli.js",
+    "test:php:pbt": "node test-fixtures/phpastgen-encoding-pbt.js && node test-fixtures/phpastgen-truncation-pbt.js && node test-fixtures/phpastgen-failure-isolation-pbt.js && node test-fixtures/phpastgen-manifest-pbt.js && node test-fixtures/phpastgen-sidecar-naming-pbt.js && node test-fixtures/phpastgen-stale-diagnostics-pbt.js && node test-fixtures/phpastgen-framework-facts-pbt.js",
     "test:shape": "node test-fixtures/astgen-shape-snapshot.js",
     "test:shape:update": "UPDATE_SHAPE_SNAPSHOT=1 node test-fixtures/astgen-shape-snapshot.js",
     "test:json": "node test-fixtures/astgen-json-regression.js",