python · encukou · Mar 8, 2022 · Feb 1, 2022 · Feb 1, 2022 · Feb 1, 2022
diff --git a/.github/CODEOWNERS b/.github/CODEOWNERS
@@ -147,6 +147,8 @@ Lib/ast.py                    @isidentical
 **/*cgi*                      @ethanfurman
 **/*tarfile*                  @ethanfurman
 
+**/*tomllib*                  @encukou
+
 # macOS
 /Mac/                         @python/macos-team
 **/*osx_support*              @python/macos-team
diff --git a/Doc/library/fileformats.rst b/Doc/library/fileformats.rst
@@ -12,6 +12,7 @@ that aren't markup languages and are not related to e-mail.
 
    csv.rst
    configparser.rst
+   tomllib.rst
    netrc.rst
    xdrlib.rst
    plistlib.rst
@@ -0,0 +1,117 @@
+:mod:`tomllib` --- Parse TOML files
+===================================
+
+.. module:: tomllib
+   :synopsis: Parse TOML files.
+
+.. versionadded:: 3.11
+
+.. moduleauthor:: Taneli Hukkinen
+.. sectionauthor:: Taneli Hukkinen
+
+**Source code:** :source:`Lib/tomllib`
+
+--------------
+
+This module provides an interface for parsing TOML (Tom's Obvious Minimal
+Language, `https://toml.io <https://toml.io/en/>`_). This module does not
+support writing TOML.
+
+.. seealso::
+
+    The `Tomli-W package <https://pypi.org/project/tomli-w/>`__
+    is a TOML writer that can be used in conjunction with this module,
+    providing a write API familiar to users of the standard library
+    :mod:`marshal` and :mod:`pickle` modules.
+
+.. seealso::
+
+    The `TOML Kit package <https://pypi.org/project/tomlkit/>`__
+    is a style-preserving TOML library with both read and write capability.
+    It is a recommended replacement for this module for editing already
+    existing TOML files.
+
+
+This module defines the following functions:
+
+.. function:: load(fp, /, *, parse_float=float)
+
+   Read a TOML file. The first argument should be a readable and binary file object.
+   Return a :class:`dict`. Convert TOML types to Python using this
+   :ref:`conversion table <toml-to-py-table>`.
+
+   *parse_float* will be called with the string of every TOML
+   float to be decoded.  By default, this is equivalent to ``float(num_str)``.
+   This can be used to use another datatype or parser for TOML floats
+   (e.g. :class:`decimal.Decimal`). The callable must not return a
+   :class:`dict` or a :class:`list`, else a :exc:`ValueError` is raised.
+
+   A :exc:`TOMLDecodeError` will be raised on an invalid TOML document.
+
+
+.. function:: loads(s, /, *, parse_float=float)
+
+   Load TOML from a :class:`str` object. Return a :class:`dict`. Convert TOML
+   types to Python using this :ref:`conversion table <toml-to-py-table>`. The
+   *parse_float* argument has the same meaning as in :func:`load`.
+
+   A :exc:`TOMLDecodeError` will be raised on an invalid TOML document.
+
+
+The following exceptions are available:
+
+.. exception:: TOMLDecodeError
+
+   Subclass of :exc:`ValueError`.
+
+
+Examples
+--------
+
+Parsing a TOML file::
+
+    import tomllib
+
+    with open("pyproject.toml", "rb") as f:
+        data = tomllib.load(f)
+
+Parsing a TOML string::
+
+    import tomllib
+
+    toml_str = """
+    python-version = "3.11.0"
+    python-implementation = "CPython"
+    """
+
+    data = tomllib.loads(toml_str)
+
+
+Conversion Table
+----------------
+
+.. _toml-to-py-table:
+
++------------------+--------------------------------------------------------------------------------------+
+| TOML             | Python                                                                               |
++==================+======================================================================================+
+| table            | dict                                                                                 |
++------------------+--------------------------------------------------------------------------------------+
+| string           | str                                                                                  |
++------------------+--------------------------------------------------------------------------------------+
+| integer          | int                                                                                  |
++------------------+--------------------------------------------------------------------------------------+
+| float            | float (configurable with *parse_float*)                                              |
++------------------+--------------------------------------------------------------------------------------+
+| boolean          | bool                                                                                 |
++------------------+--------------------------------------------------------------------------------------+
+| offset date-time | datetime.datetime (``tzinfo`` attribute set to an instance of ``datetime.timezone``) |
++------------------+--------------------------------------------------------------------------------------+
+| local date-time  | datetime.datetime (``tzinfo`` attribute set to ``None``)                             |
++------------------+--------------------------------------------------------------------------------------+
+| local date       | datetime.date                                                                        |
++------------------+--------------------------------------------------------------------------------------+
+| local time       | datetime.time                                                                        |
++------------------+--------------------------------------------------------------------------------------+
+| array            | list                                                                                 |
++------------------+--------------------------------------------------------------------------------------+
diff --git a/Doc/whatsnew/3.11.rst b/Doc/whatsnew/3.11.rst
@@ -209,7 +209,8 @@ Other CPython Implementation Changes
 New Modules
 ===========
 
-* None yet.
+* A new module, :mod:`tomllib`, was added for parsing TOML.
+  (Contributed by Taneli Hukkinen in :issue:`40059`.)
 
 
 Improved Modules

@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: MIT
+# SPDX-FileCopyrightText: 2021 Taneli Hukkinen
+# Licensed to PSF under a Contributor Agreement.
+
+__all__ = ("tomllib",)
+
+# By changing this one line, we can run the tests against
+# a different module name.
+import tomllib
+
+import os
+from test.support import load_package_tests
+
+def load_tests(*args):
+    return load_package_tests(os.path.dirname(__file__), *args)
@@ -0,0 +1,6 @@
+import unittest
+
+from . import load_tests
+
+
+unittest.main()
@@ -0,0 +1,120 @@
+# SPDX-License-Identifier: MIT
+# SPDX-FileCopyrightText: 2021 Taneli Hukkinen
+# Licensed to PSF under a Contributor Agreement.
+
+"""Utilities for tests that are in the "burntsushi" format."""
+
+import datetime
+from typing import Any
+
+# Aliases for converting TOML compliance format [1] to BurntSushi format [2]
+# [1] https://github.com/toml-lang/compliance/blob/db7c3211fda30ff9ddb10292f4aeda7e2e10abc4/docs/json-encoding.md  # noqa: E501
+# [2] https://github.com/BurntSushi/toml-test/blob/4634fdf3a6ecd6aaea5f4cdcd98b2733c2694993/README.md  # noqa: E501
+_aliases = {
+    "boolean": "bool",
+    "offset datetime": "datetime",
+    "local datetime": "datetime-local",
+    "local date": "date-local",
+    "local time": "time-local",
+}
+
+
+def convert(obj):  # noqa: C901
+    if isinstance(obj, str):
+        return {"type": "string", "value": obj}
+    elif isinstance(obj, bool):
+        return {"type": "bool", "value": str(obj).lower()}
+    elif isinstance(obj, int):
+        return {"type": "integer", "value": str(obj)}
+    elif isinstance(obj, float):
+        return {"type": "float", "value": _normalize_float_str(str(obj))}
+    elif isinstance(obj, datetime.datetime):
+        val = _normalize_datetime_str(obj.isoformat())
+        if obj.tzinfo:
+            return {"type": "datetime", "value": val}
+        return {"type": "datetime-local", "value": val}
+    elif isinstance(obj, datetime.time):
+        return {
+            "type": "time-local",
+            "value": _normalize_localtime_str(str(obj)),
+        }
+    elif isinstance(obj, datetime.date):
+        return {
+            "type": "date-local",
+            "value": str(obj),
+        }
+    elif isinstance(obj, list):
+        return [convert(i) for i in obj]
+    elif isinstance(obj, dict):
+        return {k: convert(v) for k, v in obj.items()}
+    raise Exception("unsupported type")
+
+
+def normalize(obj: Any) -> Any:
+    """Normalize test objects.
+
+    This normalizes primitive values (e.g. floats), and also converts from
+    TOML compliance format [1] to BurntSushi format [2].
+
+    [1] https://github.com/toml-lang/compliance/blob/db7c3211fda30ff9ddb10292f4aeda7e2e10abc4/docs/json-encoding.md  # noqa: E501
+    [2] https://github.com/BurntSushi/toml-test/blob/4634fdf3a6ecd6aaea5f4cdcd98b2733c2694993/README.md  # noqa: E501
+    """
+    if isinstance(obj, list):
+        return [normalize(item) for item in obj]
+    if isinstance(obj, dict):
+        if "type" in obj and "value" in obj:
+            type_ = obj["type"]
+            norm_type = _aliases.get(type_, type_)
+            value = obj["value"]
+            if norm_type == "float":
+                norm_value = _normalize_float_str(value)
+            elif norm_type in {"datetime", "datetime-local"}:
+                norm_value = _normalize_datetime_str(value)
+            elif norm_type == "time-local":
+                norm_value = _normalize_localtime_str(value)
+            else:
+                norm_value = value
+
+            if norm_type == "array":
+                return [normalize(item) for item in value]
+            return {"type": norm_type, "value": norm_value}
+        return {k: normalize(v) for k, v in obj.items()}
+    raise AssertionError("Burntsushi fixtures should be dicts/lists only")
+
+
+def _normalize_datetime_str(dt_str: str) -> str:
+    if dt_str[-1].lower() == "z":
+        dt_str = dt_str[:-1] + "+00:00"
+
+    date = dt_str[:10]
+    rest = dt_str[11:]
+
+    if "+" in rest:
+        sign = "+"
+    elif "-" in rest:
+        sign = "-"
+    else:
+        sign = ""
+
+    if sign:
+        time, _, offset = rest.partition(sign)
+    else:
+        time = rest
+        offset = ""
+
+    time = time.rstrip("0") if "." in time else time
+    return date + "T" + time + sign + offset
+
+
+def _normalize_localtime_str(lt_str: str) -> str:
+    return lt_str.rstrip("0") if "." in lt_str else lt_str
+
+
+def _normalize_float_str(float_str: str) -> str:
+    as_float = float(float_str)
+
+    # Normalize "-0.0" and "+0.0"
+    if as_float == 0:
+        return "0"
+
+    return str(as_float)
@@ -0,0 +1 @@
+arrr = [true false]
@@ -0,0 +1,4 @@
+[[parent-table.arr]]
+[parent-table]
+not-arr = 1
+arr = 2
@@ -0,0 +1,2 @@
+a=true
+[[a]]
@@ -0,0 +1 @@
+a=[1
@@ -0,0 +1 @@
+v=[1,
@@ -0,0 +1 @@
+v=[
@@ -0,0 +1 @@
+"backslash is the last char\
@@ -0,0 +1 @@
+val=falsE
@@ -0,0 +1 @@
+val=trUe
@@ -0,0 +1 @@
+"only 28 or 29 days in february" = 1988-02-30
@@ -0,0 +1,2 @@
+a = false
+a.b = true
@@ -0,0 +1,3 @@
+[[tab.arr]]
+[tab]
+arr.val1=1
@@ -0,0 +1,4 @@
+[a.b.c.d]
+  z = 9
+[a]
+  b.c.d.k.t = 8
@@ -0,0 +1,4 @@
+[a.b.c]
+  z = 9
+[a]
+  b.c.t = 9
@@ -0,0 +1 @@
+arrr = { comma-missing = true valid-toml = false }
@@ -0,0 +1 @@
+table1 = { table2.dupe = 1, table2.dupe = 2 }
@@ -0,0 +1 @@
+table = { dupe = 1, dupe = 2 }
@@ -0,0 +1 @@
+a={b=1
@@ -0,0 +1,2 @@
+a = { b = 1 }
+a.b = 2
@@ -0,0 +1,5 @@
+[tab.nested]
+inline-t = { nest = {} }
+
+[tab]
+nested.inline-t.nest = 2
@@ -0,0 +1,3 @@
+inline-t = { nest = {} }
+
+[[inline-t.nest]]
@@ -0,0 +1,3 @@
+inline-t = { nest = {} }
+
+[inline-t.nest]
@@ -0,0 +1 @@
+a = { b = 1, b.c = 2 }
@@ -0,0 +1 @@
+tab = { inner.table = [{}], inner.table.val = "bad" }
@@ -0,0 +1 @@
+tab = { inner = { dog = "best" }, inner.cat = "worst" }
@@ -0,0 +1 @@
+a={
@@ -0,0 +1 @@
+# form feed () not allowed in comments
@@ -0,0 +1 @@
+escaped-unicode = "\uabag"
@@ -0,0 +1 @@
+hex = 0xgabba00f1
@@ -0,0 +1 @@
+[fwfw.wafw
@@ -0,0 +1 @@
+fs.fw
@@ -0,0 +1 @@
+why-no-value=
@@ -0,0 +1 @@
+fs.
@@ -0,0 +1,2 @@
+a=1
+[a.b.c.d]