pyscriptc 0.1.0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- pyscriptc/__init__.py +3 -0
- pyscriptc/__main__.py +3 -0
- pyscriptc/_posthog_token.py +1 -0
- pyscriptc/builtins.py +156 -0
- pyscriptc/canonical.py +167 -0
- pyscriptc/check.py +49 -0
- pyscriptc/cli.py +271 -0
- pyscriptc/coverage.py +388 -0
- pyscriptc/debug.py +120 -0
- pyscriptc/diagnostics.py +179 -0
- pyscriptc/errors.py +56 -0
- pyscriptc/ir.py +365 -0
- pyscriptc/llvm.py +2129 -0
- pyscriptc/log.py +127 -0
- pyscriptc/lower/__init__.py +1071 -0
- pyscriptc/lower/_calls.py +1499 -0
- pyscriptc/lower/_classes.py +969 -0
- pyscriptc/lower/_core.py +301 -0
- pyscriptc/lower/_expr.py +886 -0
- pyscriptc/lower/_stdlib.py +491 -0
- pyscriptc/lower/_stdlib_shared.py +93 -0
- pyscriptc/lower/_stmt.py +1173 -0
- pyscriptc/package.py +249 -0
- pyscriptc/restlower.py +1008 -0
- pyscriptc/runtime/ps_argv.c +28 -0
- pyscriptc/runtime/ps_b64.c +168 -0
- pyscriptc/runtime/ps_coll.c +133 -0
- pyscriptc/runtime/ps_dt.c +388 -0
- pyscriptc/runtime/ps_hash.c +411 -0
- pyscriptc/runtime/ps_help.c +219 -0
- pyscriptc/runtime/ps_hmac.c +120 -0
- pyscriptc/runtime/ps_io.c +198 -0
- pyscriptc/runtime/ps_island.c +272 -0
- pyscriptc/runtime/ps_json.c +402 -0
- pyscriptc/runtime/ps_mix.c +47 -0
- pyscriptc/runtime/ps_more.c +1089 -0
- pyscriptc/runtime/ps_osmore.c +447 -0
- pyscriptc/runtime/ps_path.c +547 -0
- pyscriptc/runtime/ps_re.c +1102 -0
- pyscriptc/runtime/ps_rt.c +1175 -0
- pyscriptc/runtime/ps_rt.h +189 -0
- pyscriptc/runtime/ps_struct.c +291 -0
- pyscriptc/runtime/ps_time.c +207 -0
- pyscriptc/runtime/ps_unicode.c +1521 -0
- pyscriptc/runtime/ps_url.c +327 -0
- pyscriptc/stdlib_queue.py +191 -0
- pyscriptc/stdmore.py +1596 -0
- pyscriptc/telemetry.py +219 -0
- pyscriptc-0.1.0.dist-info/METADATA +187 -0
- pyscriptc-0.1.0.dist-info/RECORD +54 -0
- pyscriptc-0.1.0.dist-info/WHEEL +5 -0
- pyscriptc-0.1.0.dist-info/entry_points.txt +2 -0
- pyscriptc-0.1.0.dist-info/licenses/LICENSE +201 -0
- pyscriptc-0.1.0.dist-info/top_level.txt +1 -0
pyscriptc/telemetry.py
ADDED
|
@@ -0,0 +1,219 @@
|
|
|
1
|
+
"""Anonymous usage telemetry via PostHog.
|
|
2
|
+
|
|
3
|
+
What is sent: a short event payload (subcommand, version, python/platform, and
|
|
4
|
+
for `compile` a duration plus the first PSxxxx fence code when the lower fences
|
|
5
|
+
the file). Never sent: file names, paths, source text, or anything derived from
|
|
6
|
+
the compiled program.
|
|
7
|
+
|
|
8
|
+
Token flow. The PostHog project token is baked in at release time, not read
|
|
9
|
+
from the environment at run time: the release workflow writes
|
|
10
|
+
`src/pyscriptc/_posthog_token.py` (gitignored, `TOKEN = "..."`) from the
|
|
11
|
+
`POSTHOG_PROJECT_TOKEN` repo variable before `packaging/build.sh` and before
|
|
12
|
+
`uv build`. Dev checkouts and contributor installs have no such file, so
|
|
13
|
+
`_token()` returns "" and every telemetry call is a silent no-op. For local
|
|
14
|
+
testing set `PYSC_POSTHOG_TOKEN`; it wins over the baked-in file.
|
|
15
|
+
|
|
16
|
+
Opt-out, first match wins:
|
|
17
|
+
|
|
18
|
+
- `CI` env var set: telemetry is off and the first-use notice never prints.
|
|
19
|
+
- `PYSC_NO_TELEMETRY` set to any truthy value.
|
|
20
|
+
- `DO_NOT_TRACK` set to any truthy value.
|
|
21
|
+
- `pyscriptc telemetry disable` writes `telemetry = false` to the config file.
|
|
22
|
+
- No token (see above): silent no-op.
|
|
23
|
+
|
|
24
|
+
Config file: `$XDG_CONFIG_HOME/pyscriptc/config.toml` (default
|
|
25
|
+
`~/.config/pyscriptc/config.toml`). It is a flat `key = value` TOML file; the
|
|
26
|
+
two keys are `telemetry` (bool) and `notice_seen` (bool).
|
|
27
|
+
|
|
28
|
+
Sending is fire-and-forget: each `track()` posts the event on a daemon thread
|
|
29
|
+
with a 1.5 s socket timeout and swallows every failure. Nothing here can slow
|
|
30
|
+
down or break a compile.
|
|
31
|
+
"""
|
|
32
|
+
|
|
33
|
+
from __future__ import annotations
|
|
34
|
+
|
|
35
|
+
import hashlib
|
|
36
|
+
import json
|
|
37
|
+
import os
|
|
38
|
+
import platform
|
|
39
|
+
import socket
|
|
40
|
+
import sys
|
|
41
|
+
import threading
|
|
42
|
+
import urllib.request
|
|
43
|
+
import uuid
|
|
44
|
+
from pathlib import Path
|
|
45
|
+
|
|
46
|
+
POSTHOG_HOST = "https://eu.i.posthog.com"
|
|
47
|
+
|
|
48
|
+
_SALT = b"pyscriptc-v1"
|
|
49
|
+
_TIMEOUT_S = 1.5
|
|
50
|
+
|
|
51
|
+
try: # release builds stamp this file; see the module docstring
|
|
52
|
+
from pyscriptc._posthog_token import TOKEN as _BAKED_TOKEN
|
|
53
|
+
except ImportError:
|
|
54
|
+
_BAKED_TOKEN = ""
|
|
55
|
+
|
|
56
|
+
|
|
57
|
+
def _token() -> str:
|
|
58
|
+
return os.environ.get("PYSC_POSTHOG_TOKEN", "") or _BAKED_TOKEN
|
|
59
|
+
|
|
60
|
+
|
|
61
|
+
def _truthy(name: str) -> bool:
|
|
62
|
+
return os.environ.get(name, "").strip().lower() not in ("", "0", "false", "no", "off")
|
|
63
|
+
|
|
64
|
+
|
|
65
|
+
def _config_path() -> Path:
|
|
66
|
+
base = os.environ.get("XDG_CONFIG_HOME") or str(Path.home() / ".config")
|
|
67
|
+
return Path(base) / "pyscriptc" / "config.toml"
|
|
68
|
+
|
|
69
|
+
|
|
70
|
+
def _read_config() -> dict[str, str]:
|
|
71
|
+
"""Parse the flat `key = value` TOML file. Unknown lines are ignored."""
|
|
72
|
+
values: dict[str, str] = {}
|
|
73
|
+
try:
|
|
74
|
+
for line in _config_path().read_text(encoding="utf-8").splitlines():
|
|
75
|
+
line = line.split("#", 1)[0].strip()
|
|
76
|
+
if not line or "=" not in line:
|
|
77
|
+
continue
|
|
78
|
+
key, _, value = line.partition("=")
|
|
79
|
+
values[key.strip()] = value.strip().strip('"').strip("'")
|
|
80
|
+
except OSError:
|
|
81
|
+
pass
|
|
82
|
+
return values
|
|
83
|
+
|
|
84
|
+
|
|
85
|
+
def _write_config(values: dict[str, str]) -> None:
|
|
86
|
+
path = _config_path()
|
|
87
|
+
path.parent.mkdir(parents=True, exist_ok=True)
|
|
88
|
+
lines = [f"{key} = {_toml_value(value)}" for key, value in sorted(values.items())]
|
|
89
|
+
path.write_text("\n".join(lines) + "\n", encoding="utf-8")
|
|
90
|
+
|
|
91
|
+
|
|
92
|
+
def _toml_value(value: str) -> str:
|
|
93
|
+
if value in ("true", "false"):
|
|
94
|
+
return value
|
|
95
|
+
return json.dumps(value)
|
|
96
|
+
|
|
97
|
+
|
|
98
|
+
def _machine_id() -> str:
|
|
99
|
+
"""Stable anonymous machine hash. Not reversible, carries no raw identity."""
|
|
100
|
+
parts = [_SALT]
|
|
101
|
+
for candidate in ("/etc/machine-id", "/var/lib/dbus/machine-id"):
|
|
102
|
+
try:
|
|
103
|
+
parts.append(Path(candidate).read_bytes().strip())
|
|
104
|
+
break
|
|
105
|
+
except OSError:
|
|
106
|
+
continue
|
|
107
|
+
try:
|
|
108
|
+
parts.append(str(uuid.getnode()).encode())
|
|
109
|
+
except Exception:
|
|
110
|
+
pass
|
|
111
|
+
try:
|
|
112
|
+
parts.append(socket.gethostname().encode())
|
|
113
|
+
except Exception:
|
|
114
|
+
pass
|
|
115
|
+
return hashlib.sha256(b"|".join(parts)).hexdigest()
|
|
116
|
+
|
|
117
|
+
|
|
118
|
+
def ci() -> bool:
|
|
119
|
+
return bool(os.environ.get("CI"))
|
|
120
|
+
|
|
121
|
+
|
|
122
|
+
def enabled() -> bool:
|
|
123
|
+
if ci() or _truthy("PYSC_NO_TELEMETRY") or _truthy("DO_NOT_TRACK"):
|
|
124
|
+
return False
|
|
125
|
+
if _read_config().get("telemetry") == "false":
|
|
126
|
+
return False
|
|
127
|
+
return bool(_token())
|
|
128
|
+
|
|
129
|
+
|
|
130
|
+
def maybe_print_notice() -> None:
|
|
131
|
+
"""One stderr line on first non-CI, opted-in invocation; never twice."""
|
|
132
|
+
if not enabled():
|
|
133
|
+
return
|
|
134
|
+
config = _read_config()
|
|
135
|
+
if config.get("notice_seen") == "true":
|
|
136
|
+
return
|
|
137
|
+
print(
|
|
138
|
+
"pyscriptc collects anonymous usage metrics (no source/paths). "
|
|
139
|
+
"Disable: PYSC_NO_TELEMETRY=1 or `pyscriptc telemetry disable`",
|
|
140
|
+
file=sys.stderr,
|
|
141
|
+
)
|
|
142
|
+
config["notice_seen"] = "true"
|
|
143
|
+
try:
|
|
144
|
+
_write_config(config)
|
|
145
|
+
except OSError:
|
|
146
|
+
pass
|
|
147
|
+
|
|
148
|
+
|
|
149
|
+
def track(event: str, properties: dict | None = None) -> None:
|
|
150
|
+
"""Queue one event on a daemon thread. Every failure is swallowed."""
|
|
151
|
+
if not enabled():
|
|
152
|
+
return
|
|
153
|
+
payload = {
|
|
154
|
+
"api_key": _token(),
|
|
155
|
+
"event": event,
|
|
156
|
+
"distinct_id": _machine_id(),
|
|
157
|
+
"properties": properties or {},
|
|
158
|
+
}
|
|
159
|
+
thread = threading.Thread(target=_post, args=(payload,), daemon=True)
|
|
160
|
+
try:
|
|
161
|
+
thread.start()
|
|
162
|
+
except Exception:
|
|
163
|
+
pass
|
|
164
|
+
|
|
165
|
+
|
|
166
|
+
def _post(payload: dict) -> None:
|
|
167
|
+
try:
|
|
168
|
+
body = json.dumps(payload).encode()
|
|
169
|
+
request = urllib.request.Request(
|
|
170
|
+
f"{POSTHOG_HOST}/capture/",
|
|
171
|
+
data=body,
|
|
172
|
+
headers={"Content-Type": "application/json"},
|
|
173
|
+
)
|
|
174
|
+
with urllib.request.urlopen(request, timeout=_TIMEOUT_S):
|
|
175
|
+
pass
|
|
176
|
+
except Exception:
|
|
177
|
+
pass
|
|
178
|
+
|
|
179
|
+
|
|
180
|
+
def base_properties() -> dict:
|
|
181
|
+
from pyscriptc import __version__
|
|
182
|
+
|
|
183
|
+
return {
|
|
184
|
+
"pyscriptc_version": __version__,
|
|
185
|
+
"python_version": platform.python_version(),
|
|
186
|
+
"platform": sys.platform,
|
|
187
|
+
"ci": ci(),
|
|
188
|
+
}
|
|
189
|
+
|
|
190
|
+
|
|
191
|
+
def telemetry_cmd(action: str) -> int:
|
|
192
|
+
"""Implement `pyscriptc telemetry disable|enable|status`."""
|
|
193
|
+
if action == "status":
|
|
194
|
+
config = _read_config()
|
|
195
|
+
print(f"telemetry: {'on' if enabled() else 'off'}")
|
|
196
|
+
print(f"config: {_config_path()} ({'exists' if _config_path().exists() else 'absent'})")
|
|
197
|
+
if ci():
|
|
198
|
+
print("reason: CI env var set")
|
|
199
|
+
elif _truthy("PYSC_NO_TELEMETRY"):
|
|
200
|
+
print("reason: PYSC_NO_TELEMETRY set")
|
|
201
|
+
elif _truthy("DO_NOT_TRACK"):
|
|
202
|
+
print("reason: DO_NOT_TRACK set")
|
|
203
|
+
elif config.get("telemetry") == "false":
|
|
204
|
+
print("reason: telemetry = false in config")
|
|
205
|
+
elif not _token():
|
|
206
|
+
print("reason: no PostHog token (dev install)")
|
|
207
|
+
return 0
|
|
208
|
+
if action not in ("enable", "disable"):
|
|
209
|
+
print("usage: pyscriptc telemetry disable|enable|status", file=sys.stderr)
|
|
210
|
+
return 2
|
|
211
|
+
config = _read_config()
|
|
212
|
+
config["telemetry"] = "true" if action == "enable" else "false"
|
|
213
|
+
try:
|
|
214
|
+
_write_config(config)
|
|
215
|
+
except OSError as exc:
|
|
216
|
+
print(f"cannot write {_config_path()}: {exc}", file=sys.stderr)
|
|
217
|
+
return 1
|
|
218
|
+
print(f"telemetry {'enabled' if action == 'enable' else 'disabled'} in {_config_path()}")
|
|
219
|
+
return 0
|
|
@@ -0,0 +1,187 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: pyscriptc
|
|
3
|
+
Version: 0.1.0
|
|
4
|
+
Summary: Lower a typed subset of Python to LLVM, with CPython as the island.
|
|
5
|
+
Author: Joaquin Terrasa
|
|
6
|
+
License-Expression: Apache-2.0
|
|
7
|
+
Project-URL: Homepage, https://github.com/sigilco/pyscriptc
|
|
8
|
+
Project-URL: Repository, https://github.com/sigilco/pyscriptc
|
|
9
|
+
Project-URL: Issues, https://github.com/sigilco/pyscriptc/issues
|
|
10
|
+
Project-URL: Reference, https://github.com/vercel-labs/scriptc
|
|
11
|
+
Classifier: Development Status :: 3 - Alpha
|
|
12
|
+
Classifier: Intended Audience :: Developers
|
|
13
|
+
Classifier: Operating System :: OS Independent
|
|
14
|
+
Classifier: Programming Language :: Python :: 3
|
|
15
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
16
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
17
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
18
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
19
|
+
Classifier: Programming Language :: Python :: 3.14
|
|
20
|
+
Classifier: Topic :: Software Development :: Compilers
|
|
21
|
+
Requires-Python: >=3.10
|
|
22
|
+
Description-Content-Type: text/markdown
|
|
23
|
+
License-File: LICENSE
|
|
24
|
+
Requires-Dist: mypy>=2.4
|
|
25
|
+
Dynamic: license-file
|
|
26
|
+
|
|
27
|
+
<h1 align="center">pyscriptc</h1>
|
|
28
|
+
|
|
29
|
+
<p align="center">Compile annotated Python to a native binary. No CPython at runtime.</p>
|
|
30
|
+
|
|
31
|
+
<p align="center">
|
|
32
|
+
<a href="https://pypi.org/project/pyscriptc/"><img alt="PyPI" src="https://img.shields.io/pypi/v/pyscriptc"></a>
|
|
33
|
+
<a href="https://github.com/sigilco/pyscriptc/actions/workflows/ci.yml"><img alt="CI" src="https://github.com/sigilco/pyscriptc/actions/workflows/ci.yml/badge.svg"></a>
|
|
34
|
+
<a href="LICENSE"><img alt="License" src="https://img.shields.io/badge/license-Apache--2.0-blue"></a>
|
|
35
|
+
</p>
|
|
36
|
+
|
|
37
|
+
A compiler that lowers a small, annotated subset of Python to a typed IR and then to LLVM. Parsing is CPython’s own `ast` module. [mypy](https://mypy-lang.org/) is a preflight: its tree is not an input. Anything the subset does not prove is a fence, not a guess.
|
|
38
|
+
|
|
39
|
+
## Try it now
|
|
40
|
+
|
|
41
|
+
```bash
|
|
42
|
+
uv tool install pyscriptc # or: pipx install pyscriptc / pip install pyscriptc
|
|
43
|
+
pyscriptc compile examples/sum_squares.py --run --call sum_squares --args '[10]' -o /tmp/sum_squares
|
|
44
|
+
```
|
|
45
|
+
|
|
46
|
+
`sum_squares(10)` prints `285`, the same value CPython prints — from a native binary.
|
|
47
|
+
|
|
48
|
+
## Install it
|
|
49
|
+
|
|
50
|
+
```bash
|
|
51
|
+
uv tool install pyscriptc
|
|
52
|
+
```
|
|
53
|
+
|
|
54
|
+
Requirements: CPython 3.10 or later (the IR is stamped with the interpreter that lowered it) and a clang that can assemble textual LLVM IR. `pipx install pyscriptc` and `pip install pyscriptc` work the same way.
|
|
55
|
+
|
|
56
|
+
## What it does
|
|
57
|
+
|
|
58
|
+
- Lowers an annotated Python subset (strict `x: T` typing, checked by mypy) to typed IR, then LLVM IR, then a native binary via clang or `zig cc`.
|
|
59
|
+
- Anything the subset does not prove stops at a named `PSxxxx` fence with a hint — it never guesses at semantics.
|
|
60
|
+
- `int` is a Python int: `i64` only when the value fits, traps on overflow, refuses literals that would truncate. `//` is floor division.
|
|
61
|
+
- Island calls (`subprocess.check_output`, `socket.gethostname`, `threading`, `logging`) embed CPython on first use — and only binaries that call them link libpython.
|
|
62
|
+
- `--emit ir` / `--emit llvm` dump the intermediate forms; `--run` compiles and executes; `--target` + `--driver zig` cross-compiles.
|
|
63
|
+
|
|
64
|
+
## Stack
|
|
65
|
+
|
|
66
|
+
| Layer | What it is |
|
|
67
|
+
| --- | --- |
|
|
68
|
+
| Parser | CPython's own `ast` module |
|
|
69
|
+
| Checker | mypy preflight + the `PS1xxx`/`PS2xxx` fence tables |
|
|
70
|
+
| IR | typed JSON, stamped per-interpreter (`gates-v1`) |
|
|
71
|
+
| Backend | hand-emitted LLVM IR text → `clang` / `zig cc` |
|
|
72
|
+
| Island | optional embedded-CPython calls, CPython-linked only when used |
|
|
73
|
+
| Scoring | `benchmarks/` layout follows [scriptc](https://github.com/vercel-labs/scriptc) |
|
|
74
|
+
|
|
75
|
+
The design is in [ARCHITECTURE.md](ARCHITECTURE.md). How to compile a script is in [docs/](docs/README.md). Contributor notes are in [.agents/docs/](.agents/docs/README.md). Programs that compile today, including an invoice, an access-log gate, and a URL allow-list, are in [examples/](examples/README.md). The benchmark layout is scriptc’s `benchmarks/` directory; see [benchmarks/README.md](benchmarks/README.md).
|
|
76
|
+
|
|
77
|
+
Licensed under Apache 2.0. Copyright 2026 Joaquin Terrasa and contributors.
|
|
78
|
+
|
|
79
|
+
## Subset
|
|
80
|
+
|
|
81
|
+
The IR stamp is `gates-v1`. Lowered:
|
|
82
|
+
|
|
83
|
+
- Annotated functions whose parameters and return use `int`, `float`, `bool`, `str`, `bytes`, `list`, `dict`, or an annotated class
|
|
84
|
+
- `if`, `while`, `for` over a `list` or `range`, assignment, `return`
|
|
85
|
+
- `int` `+`, `-`, `*`, `//`, unary `-`, and comparisons
|
|
86
|
+
- `float` `+`, `-`, `*`, and comparisons (`NaN` follows Python: `nan != nan`)
|
|
87
|
+
- `str` and `bytes` concatenation, indexing, ordering, and `in`
|
|
88
|
+
- `len` on `str`, `bytes`, `list`, `dict`, and `collections.deque`
|
|
89
|
+
- `abs`, `min`, `max`, `sum`, `sorted`, `ord`, `chr`, `round`, `isinstance`, `getattr`, and `hasattr` (the attribute name is a string literal)
|
|
90
|
+
- `open` with a literal mode `r`, `w`, `rb`, `wb`, `a`, or `ab`
|
|
91
|
+
- `int(float)` (toward zero) and `float(int)`
|
|
92
|
+
- Latin-1 `str` and `bytes` methods: `strip`, `lstrip`, `rstrip`, `upper`, `lower`, `startswith`, `endswith`, `find`, `replace`, `split`, `join`, plus `encode()` and `decode()` with no extra arguments
|
|
93
|
+
- `list` and `dict` literals, indexing, and item assignment. Assignment shares the buffer
|
|
94
|
+
- `try` / `except` for `ValueError`, `IndexError`, `KeyError`, `OverflowError`, `ZeroDivisionError`, `RuntimeError`, `Exception`, and a user subclass of one of those
|
|
95
|
+
- `*args` of one element type, lowered as a `list` of that type. A `set` of `int` or `str`: construction, `add`, membership, `len`, and iteration
|
|
96
|
+
- Annotated classes: fields, `__init__`, methods, and a single base. Layout is the parent's fields, then the class's own fields. Method lookup walks the parent. `@property` (getter only), `@staticmethod`, and `@classmethod` on methods. A flat `@dataclass` generates `__init__` from annotations. `enum.IntEnum` and `enum.Enum` members are integer constants. A subclass of `Exception` (or another lowered exception) can be raised and caught as its own type and as the parent
|
|
97
|
+
- `import` / `from` against the closed table in `pyscriptc.stdlib_queue`. `math` is lowered (`sqrt`, `fabs`, `sin`, `cos`, `tan`, `exp`, `log`, `log2`, `log10`, `hypot`, `pow`, `floor`, `ceil`, `trunc`, `isnan`, `isinf`, and `pi`, `e`, `tau`, `inf`, `nan`). The codec wave is lowered too: `re` (`escape`, `findall`, `sub`, `split`, `compile`), `json` (`loads`, `dumps`), `urllib.parse` (`quote`, `quote_plus`, `unquote`, `unquote_plus`, `urlencode`, `parse_qs`, `urlsplit`), `base64` (`b64encode`, `b64decode`, and the standard and urlsafe pairs), `hashlib` (`md5`, `sha1`, `sha256`, `sha384`, `sha512`), and `struct` (`pack`, `unpack` of a literal format). The rest of the queue is lowered as a closed surface: `datetime`, `time`, `collections`, `functools`, `itertools`, `operator`, `contextlib`, `os`, `posixpath`, `pathlib`, `stat`, `fnmatch`, `warnings`, `io`, `string`, `bisect`, `errno`, and the island modules `sys`, `importlib`, `inspect`, `threading`, `logging`, `asyncio`, `subprocess`, `socket`, `ssl`, and `ctypes`. Also lowered, as closed names: `importlib.resources.files` / `as_file`, `hmac.digest` / `new` / `compare_digest` for a literal `sha256` / `sha384` / `sha512` (and `md5` / `sha1`), Latin-1 `unicodedata`, `tempfile.gettempdir` / `gettempprefix` / `mkdtemp`, `atexit.register` of a no-argument function, `shutil.copyfile` / `rmtree`, `enum.Enum` / `enum.IntEnum` as integer members, and `dataclasses.dataclass` as a flat `__init__`. Anything outside the table fences at the import (`PS2002`). A name added to the queue and left out of the lowered set would fence with `PS2101`
|
|
98
|
+
|
|
99
|
+
Fenced (no LLVM for that file):
|
|
100
|
+
|
|
101
|
+
- `and` / `or` across two types, f-string format specs, a slice step other than 1, `break`, `continue`, `finally`, `except as`, user decorators, `super()`, multiple inheritance, `**kwargs`, keyword-only and positional-only parameters, and starred calls
|
|
102
|
+
- String literals outside Latin-1
|
|
103
|
+
- `bool` arithmetic, `list[bool]`, and `dict` values of `bool`. `bool` is not promoted to `float`
|
|
104
|
+
- Calls such as `str.encode("ascii")`, `math.gcd`, `functools.partial`, `itertools.count`, `operator.itemgetter`, `importlib.import_module`, and `asyncio.run` that are outside the lowered surface
|
|
105
|
+
- `with` except `contextlib.suppress(Exc)`, `contextlib.nullcontext()`, `with open(...) as name`, and `with importlib.resources.as_file(...) as name`
|
|
106
|
+
- `itertools.repeat` and `itertools.chain` except as the iterator of a `for`
|
|
107
|
+
- `re.findall` with more than four capturing groups. A literal pattern of two to four groups returns a tuple of strings. A dynamic pattern with two or more groups raises `ValueError`
|
|
108
|
+
- Float JSON, JSON null, and non-ASCII JSON text
|
|
109
|
+
- `struct` format `@`, a format that is not a string literal, and `Q` values that do not fit in `i64`
|
|
110
|
+
- Keyword arguments, including `re` flags and `base64` `validate`
|
|
111
|
+
|
|
112
|
+
`//` is Python floor division, including negative operands. Division by zero and signed `i64` overflow abort the process. They do not wrap. `math.floor`, `math.ceil`, `math.trunc`, and `int(float)` raise `OverflowError` when the result does not fit in `i64`. An uncaught exception prints its name to stderr and exits 1.
|
|
113
|
+
|
|
114
|
+
A `for` target that is new in the function is stored as `0`, `0.0`, or `""` before the loop. After `for i in range(0)`, this subset reads `i` as `0`. CPython would raise `UnboundLocalError`. A target that already had a value keeps that value when the loop body never runs.
|
|
115
|
+
|
|
116
|
+
`in` on a list uses `==`. `math.nan in [math.nan]` is false here. CPython's list finds that same object by identity before it compares.
|
|
117
|
+
|
|
118
|
+
`typing` stays in mypy. It is not a runtime lowering. Island constants (`sys.platform`, `sys.version`, `sys.executable`, `sys.maxsize`, `socket.AF_INET`, `ssl.OPENSSL_VERSION`, `ssl.HAS_SNI`, `stat.S_IFREG`, `ctypes.sizeof`) are baked from the interpreter that lowers the file. `sys.exit` is libc `exit`. `subprocess.check_output` takes a `list[str]` and returns `bytes`. `os.getenv` raises `KeyError` when the variable is unset. `date` plus `timedelta` uses the normalized day count; `datetime` plus `timedelta` uses the whole delta.
|
|
119
|
+
|
|
120
|
+
## Requirements
|
|
121
|
+
|
|
122
|
+
- CPython 3.10 or later (the IR is stamped with the interpreter that lowered it)
|
|
123
|
+
- [uv](https://docs.astral.sh/uv/)
|
|
124
|
+
- Clang that can assemble textual LLVM IR
|
|
125
|
+
|
|
126
|
+
## Run
|
|
127
|
+
|
|
128
|
+
```bash
|
|
129
|
+
uv sync
|
|
130
|
+
uv run pyscriptc compile examples/sum_squares.py --run --call sum_squares --args '[10]' -o /tmp/sum_squares
|
|
131
|
+
```
|
|
132
|
+
|
|
133
|
+
`sum_squares(10)` prints `285`, the same value CPython prints. `--args` is a Python literal parsed with `ast.literal_eval`, so integers are not rounded through JSON.
|
|
134
|
+
|
|
135
|
+
Other corpus programs:
|
|
136
|
+
|
|
137
|
+
```bash
|
|
138
|
+
uv run pyscriptc compile examples/longer.py --run --call longer --args '["bb", "a"]' -o /tmp/longer
|
|
139
|
+
uv run pyscriptc compile examples/floor_div.py --run --call floor_div --args '[-3, 2]' -o /tmp/floor_div
|
|
140
|
+
uv run pyscriptc compile examples/gates_math.py --run --call floors -o /tmp/floors
|
|
141
|
+
uv run pyscriptc compile examples/gates_probe.py --run --call probe -o /tmp/probe
|
|
142
|
+
uv run pyscriptc compile examples/fence_method.py --emit llvm -o /tmp/fence.ll
|
|
143
|
+
```
|
|
144
|
+
|
|
145
|
+
`floors()` prints `3`. `probe()` prints `0`. The fence exits nonzero, names `encode`, and does not write LLVM. `examples/wave_probe.py` prints `0` when the codec wave matches CPython. `examples/rest_probe.py` prints `0` when the rest of the queue matches CPython. `examples/fence_pickle.py` exits nonzero with `PS2002` because `pickle` is outside the import table. `examples/invoice.py`, `examples/access_log.py`, `examples/request_id.py`, `examples/release_note.py`, `examples/blob_digest.py`, `examples/url_gate.py`, and `examples/hostname.py` are the scripts in [docs/examples.md](docs/examples.md). `examples/bad_annotation.py` fails in mypy before lowering. `examples/big_literal.py` lowers to IR, then LLVM emission refuses the integer because it does not fit in `i64`.
|
|
146
|
+
|
|
147
|
+
`re.compile` returns a `Pattern` with a `pattern` field. `findall`, `sub`, and `split` on that object use the field. `hashlib` returns an opaque `Hash`; `hexdigest` and `digest` are the methods that lower. `urlsplit` returns a `SplitResult` of five strings (`scheme`, `netloc`, `path`, `query`, `fragment`). `struct.unpack` is a list, so `[0]` is the first value. `json.loads` takes its type from the annotation it is assigned to, or from the return annotation. `parse_qs` splits on `&` only, which is what CPython 3.14 does. A pattern that can match empty forever, such as `()*`, stops with `RuntimeError` once the matcher spends its fuel. `re.error`, `struct.error`, and `binascii.Error` surface here as `ValueError`.
|
|
148
|
+
|
|
149
|
+
`--emit ir` writes the JSON IR. `--emit llvm` writes textual LLVM. The CPython version is a field on the module. Emitting LLVM from an IR stamped by a different version is an error: re-lower it and re-run the corpus.
|
|
150
|
+
|
|
151
|
+
## Benchmarks
|
|
152
|
+
|
|
153
|
+
```bash
|
|
154
|
+
uv run python -m benchmarks.baseline.run --check
|
|
155
|
+
uv run python -m benchmarks.runtime.run --runs=5
|
|
156
|
+
uv run python -m benchmarks.scaling.run
|
|
157
|
+
```
|
|
158
|
+
|
|
159
|
+
`benchmarks/baseline/reference.json` is the reference metric set: wall time and peak RSS for each lowered workload, against the same call under CPython. Printed figures are speedups, `Nx CPython`, the reciprocal of the stored pyscriptc/CPython ratio, so a larger number is a bigger gain. `--check` still compares the stored ratios: it fails when a time ratio grows past 2× that set, or an RSS ratio grows past 1.25×. A reference of 10.0x CPython therefore fails once the run prints less than 5.0x.
|
|
160
|
+
|
|
161
|
+
The kernel geomean is the original four loops. The stdlib rows time every module that has a lowered call, including the builtin helpers. `importlib.import_module` and `asyncio.run` are fences, so those calls are not timed. `importlib.resources`, `hmac`, and Latin-1 `unicodedata` have their own rows. Calls that embed CPython (`socket.gethostname`, `inspect.cleandoc`, `threading`, `logging`, `subprocess.check_output`) are the island group: they link libpython, and their speedup sits near 1x CPython. `benchmarks/adoption` records why pyperformance, click, typer, pip, and black are not compiled suites yet.
|
|
162
|
+
|
|
163
|
+
## Telemetry
|
|
164
|
+
|
|
165
|
+
Release builds collect anonymous usage metrics with PostHog (EU host): the subcommand you ran, pyscriptc/python versions, platform, compile duration, and the first `PSxxxx` fence code when a file fails to lower. Never sent: file names, paths, or source text. The machine id is a salted sha256 that is not reversible.
|
|
166
|
+
|
|
167
|
+
Telemetry is off in CI and a no-op in dev checkouts (no baked-in token). One stderr line announces it on first use. Disable it with any of:
|
|
168
|
+
|
|
169
|
+
```bash
|
|
170
|
+
pyscriptc telemetry disable # writes ~/.config/pyscriptc/config.toml
|
|
171
|
+
export PYSC_NO_TELEMETRY=1
|
|
172
|
+
export DO_NOT_TRACK=1
|
|
173
|
+
```
|
|
174
|
+
|
|
175
|
+
`pyscriptc telemetry status` shows the effective state and why.
|
|
176
|
+
|
|
177
|
+
## Checks
|
|
178
|
+
|
|
179
|
+
```bash
|
|
180
|
+
uv run ruff check .
|
|
181
|
+
uv run ruff format --check .
|
|
182
|
+
uv run pytest
|
|
183
|
+
```
|
|
184
|
+
|
|
185
|
+
## What this does not prove
|
|
186
|
+
|
|
187
|
+
A new CPython release is not supported yet in the product sense. The stamp and the fences are the hooks that make that possible later: unknown syntax fails closed, and the backend will not silently compile IR from an interpreter it has not been run against. Island calls embed that same interpreter, and only the binary that actually calls them links libpython.
|
|
@@ -0,0 +1,54 @@
|
|
|
1
|
+
pyscriptc/__init__.py,sha256=chqxwWgRDbtqL9f-NvcRi19VyxeoeA4PnkPhkMgQq5c,87
|
|
2
|
+
pyscriptc/__main__.py,sha256=4vCzPwJUIKd51IfGCMR5OIat-NjaEge3JxXT02U-NVQ,57
|
|
3
|
+
pyscriptc/_posthog_token.py,sha256=JPgt6HkDBOvRiGEiedZoVYG0Zd0d-HKD8yEhJ5xHMYE,59
|
|
4
|
+
pyscriptc/builtins.py,sha256=ABof65cmVFoiLVQpf28kGqvBR4aIbpmvhJExxQWjgng,6117
|
|
5
|
+
pyscriptc/canonical.py,sha256=fU7dhy0E0rChEl9pcdULpdS6jSQxEzzuUjbgnhx1PuU,6485
|
|
6
|
+
pyscriptc/check.py,sha256=SoWfgSWOypvE_dqfrYj1USovFTjuSXeU700G2oPwQxY,1441
|
|
7
|
+
pyscriptc/cli.py,sha256=QE0ViPBzvXM8fhevq257kkhKiSDXycL3uY1FN8Mx9z8,10205
|
|
8
|
+
pyscriptc/coverage.py,sha256=hrfqDw3Kc97QA_4RwGwI2jY9utzJCIVUj5k0Lx-RYhM,16119
|
|
9
|
+
pyscriptc/debug.py,sha256=IzvWQOa0FhWcsSneUgC0A7zUNRumtDvsXJk88VbVgfI,4914
|
|
10
|
+
pyscriptc/diagnostics.py,sha256=xaV1JxIShcimuPzxsbVVg0JbGu4PypYe6F1mv9DrR0E,6354
|
|
11
|
+
pyscriptc/errors.py,sha256=ALE4mab7BWsucVlaxUX3bOExOeRYcQKOjfs4hhtr3hE,1627
|
|
12
|
+
pyscriptc/ir.py,sha256=E82FaVwlGGI8bz0BJOM0WBEbP03WYmcMwLu_Ys8QR9w,15212
|
|
13
|
+
pyscriptc/llvm.py,sha256=cCO2QnMJoVQ_83n7sBYqXoo-LEHuTwfXKo_Gr0gKsbc,91601
|
|
14
|
+
pyscriptc/log.py,sha256=8p0c66QMkYvGnA5gBEZ1P18DS5MGL1J6ZkQDnKo3pME,3884
|
|
15
|
+
pyscriptc/package.py,sha256=S_i67i-WAcWV0LjC64VPZhHZNrFoO4O6GzuSWUy6jM8,9557
|
|
16
|
+
pyscriptc/restlower.py,sha256=159OJXNwsEAvK1obcsKLhCnR5T5prTxb63JGZ3GxrDk,40526
|
|
17
|
+
pyscriptc/stdlib_queue.py,sha256=POmLTIfVEA6-tpiOq9ATPO2gITij2ThyYEvazHnM5U8,6081
|
|
18
|
+
pyscriptc/stdmore.py,sha256=NcYVNSGIeweuSF4EzmCGOGEv7ALKAEY94TKNRQfRGN8,44069
|
|
19
|
+
pyscriptc/telemetry.py,sha256=cpt-951K5ok-g85Lwf6tvyC84nE8mHfbGjrC4JPenZc,7007
|
|
20
|
+
pyscriptc/lower/__init__.py,sha256=fuVv6PrNmCdx9uHonthkzqrMKVy1X4D2myGpVP-q5QQ,47054
|
|
21
|
+
pyscriptc/lower/_calls.py,sha256=6cvqhRHX5BFCB1wh5Da1PeoHrnTknViTpBBudWpGVJ4,70672
|
|
22
|
+
pyscriptc/lower/_classes.py,sha256=4SbeDCVby03QWBIBSH3nuGGpJoy_EWw054og8H8N6mY,45159
|
|
23
|
+
pyscriptc/lower/_core.py,sha256=rxS6aL7T24-ZIRgd6JaroRcwn0mmWRMWj59IUFsgkgY,9397
|
|
24
|
+
pyscriptc/lower/_expr.py,sha256=rUOMGERL2f-UrLTLgM6x3h793Z9ACKAa75JNWXS8wPo,42941
|
|
25
|
+
pyscriptc/lower/_stdlib.py,sha256=t0x9Bi04Jz2Wtj3XIEge9KeGQiY-Zu7xiXQqahL4w1U,21997
|
|
26
|
+
pyscriptc/lower/_stdlib_shared.py,sha256=3CoUqv9iWBU0R8giZ3nzHxIlxe6wi1G4HJcWtmzxS7Y,3130
|
|
27
|
+
pyscriptc/lower/_stmt.py,sha256=-Cbb1uKMWq9ft353_EOXYiNnkEw3FpFqRW-YRcedfL4,51796
|
|
28
|
+
pyscriptc/runtime/ps_argv.c,sha256=jQm8ba29rkMSL6ykC1oIAo_VQUmdJ3sfC30Vrbp5rHY,781
|
|
29
|
+
pyscriptc/runtime/ps_b64.c,sha256=sN3vMYYQDc4ergNLTR6gyrRRJrbK2eqNzaD97_dG8NI,5124
|
|
30
|
+
pyscriptc/runtime/ps_coll.c,sha256=pj8s3PQZkpWTCT1gN3oFod4J6DKgLKQV8-16WEOJtSU,2998
|
|
31
|
+
pyscriptc/runtime/ps_dt.c,sha256=KV_jiSwgH5Inzm6CQmmhi32nCvfGWQYfseOKjUcknGk,11031
|
|
32
|
+
pyscriptc/runtime/ps_hash.c,sha256=UdpeGlre7xJX_QM2mUspJLbCQv8jOUMemp-5x8X0n54,14261
|
|
33
|
+
pyscriptc/runtime/ps_help.c,sha256=_lu7957yNF93Bwo_MNTJbDqi7lIhyhdFPhcKNLgFoEs,5668
|
|
34
|
+
pyscriptc/runtime/ps_hmac.c,sha256=O1Bmh54KhaSHC9rwLVXGZLNoozXB-M47JYj_cS7-43U,3248
|
|
35
|
+
pyscriptc/runtime/ps_io.c,sha256=d22sEqSqCf02iDLjsx4z9h1pl8QdV6gIKpYsexCiJN4,4758
|
|
36
|
+
pyscriptc/runtime/ps_island.c,sha256=3CtwH1apF9UxPd8GtdcTzJ3fOMJAJCfFjKTvVJcAnyk,7151
|
|
37
|
+
pyscriptc/runtime/ps_json.c,sha256=1tNQ9p_lUokPyA8nfZzcbavrIBIaoErZGbvIkykpgtc,11587
|
|
38
|
+
pyscriptc/runtime/ps_mix.c,sha256=GJX11vWLg1MeNKiTrme5eNiWQ_JchsP4tDxT5gn90e0,1446
|
|
39
|
+
pyscriptc/runtime/ps_more.c,sha256=AFwDR_y1cqnUqvlkCjqHW3WB2SyonlmM1bwQN3EBSGY,30647
|
|
40
|
+
pyscriptc/runtime/ps_osmore.c,sha256=47ThjGqjOTLutL-G6KLm1HcuijWUZBs7RDy2zIDGuaI,12284
|
|
41
|
+
pyscriptc/runtime/ps_path.c,sha256=yH4KXm0dwsrrntRNWzETnTG9zB_8THUFlpVudtGP6no,14443
|
|
42
|
+
pyscriptc/runtime/ps_re.c,sha256=_JjaFkgt3YAwXX3fkqkmqipzaNJkUec6sZw99eoeLG0,27518
|
|
43
|
+
pyscriptc/runtime/ps_rt.c,sha256=S2huTAEBxmk55VqISSDM1yyFeOwBae6-arhuuzlkdNw,30620
|
|
44
|
+
pyscriptc/runtime/ps_rt.h,sha256=ylfv1ANMO12pe1LfurRd1R2aLTPpNpFcEF71Az6aCso,6577
|
|
45
|
+
pyscriptc/runtime/ps_struct.c,sha256=YQCgX95nEUqL6EZQpgO_9dTG1KdW21UBXGc-lj5V2B0,9025
|
|
46
|
+
pyscriptc/runtime/ps_time.c,sha256=WjFhx2Qzhz1qNVazE3MHSIjkzknTS4yh5KrdocWZfXE,5419
|
|
47
|
+
pyscriptc/runtime/ps_unicode.c,sha256=AG4Vtybdx0E0Ls4W7TUiIy8Vhxxin0o9N4VElukZDHU,80823
|
|
48
|
+
pyscriptc/runtime/ps_url.c,sha256=0hnuXzgykla6f2-hIdd_dzG7LcZac7NbMEzKre4UQmM,9394
|
|
49
|
+
pyscriptc-0.1.0.dist-info/licenses/LICENSE,sha256=nsEoTHAXYOICwFfkx-wyZ0_iOkysThv0FOzfcY47www,11362
|
|
50
|
+
pyscriptc-0.1.0.dist-info/METADATA,sha256=Yg4JDWOfhlirMcPK7j7l80bvh_t-Mih-UWZF5TvWgk0,15171
|
|
51
|
+
pyscriptc-0.1.0.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
|
|
52
|
+
pyscriptc-0.1.0.dist-info/entry_points.txt,sha256=nD2UuZMF268ZZV_rC1zbBbj0QMCq4RZoYi3Ky15oYIs,49
|
|
53
|
+
pyscriptc-0.1.0.dist-info/top_level.txt,sha256=Ako6qEZO1JlY8_lWibH_8rhbWk4mKu2vjdiC9retqIw,10
|
|
54
|
+
pyscriptc-0.1.0.dist-info/RECORD,,
|