From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 4EF3743F7C; Thu, 9 May 2024 13:27:05 +0200 (CEST) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 97ABF40A70; Thu, 9 May 2024 13:26:52 +0200 (CEST) Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by mails.dpdk.org (Postfix) with ESMTP id 939DE406BC for ; Thu, 9 May 2024 13:26:50 +0200 (CEST) Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 656CE12FC; Thu, 9 May 2024 04:27:15 -0700 (PDT) Received: from localhost.localdomain (unknown [10.1.194.74]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 3E4B43F6A8; Thu, 9 May 2024 04:26:49 -0700 (PDT) From: Luca Vizzarro To: dev@dpdk.org Cc: =?UTF-8?q?Juraj=20Linke=C5=A1?= , Jeremy Spewock , Luca Vizzarro , Paul Szczepanek Subject: [PATCH v2 3/5] dts: add parsing utility module Date: Thu, 9 May 2024 12:26:33 +0100 Message-Id: <20240509112635.1170557-4-luca.vizzarro@arm.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240509112635.1170557-1-luca.vizzarro@arm.com> References: <20240412111136.3470304-1-luca.vizzarro@arm.com> <20240509112635.1170557-1-luca.vizzarro@arm.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Adds parsing text into a custom dataclass. It provides a new `TextParser` dataclass to be inherited. This implements the `parse` method, which combined with the parser functions, it can automatically parse the value for each field. This new utility will facilitate and simplify the parsing of complex command outputs, while ensuring that the codebase does not get bloated and stays flexible. Signed-off-by: Luca Vizzarro Reviewed-by: Paul Szczepanek --- dts/framework/parser.py | 199 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 199 insertions(+) create mode 100644 dts/framework/parser.py diff --git a/dts/framework/parser.py b/dts/framework/parser.py new file mode 100644 index 0000000000..5b4acddead --- /dev/null +++ b/dts/framework/parser.py @@ -0,0 +1,199 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2024 Arm Limited + +r"""Parsing utility module. + +This module provides :class:`~TextParser` which can be used to model any dataclass to a block of +text. + +Usage example:: +..code:: python + + from dataclasses import dataclass, field + from enum import Enum + from framework.parser import TextParser + + class Colour(Enum): + BLACK = 1 + WHITE = 2 + + @classmethod + def from_str(cls, text: str): + match text: + case "black": + return cls.BLACK + case "white": + return cls.WHITE + case _: + return None # unsupported colour + + @classmethod + def make_parser(cls): + # make a parser function that finds a match and + # then makes it a Colour object through Colour.from_str + return TextParser.compose(cls.from_str, TextParser.find(r"is a (\w+)")) + + @dataclass + class Animal(TextParser): + kind: str = field(metadata=TextParser.find(r"is a \w+ (\w+)")) + name: str = field(metadata=TextParser.find(r"^(\w+)")) + colour: Colour = field(metadata=Colour.make_parser()) + age: int = field(metadata=TextParser.find_int(r"aged (\d+)")) + + steph = Animal.parse("Stephanie is a white cat aged 10") + print(steph) # Animal(kind='cat', name='Stephanie', colour=, age=10) +""" + +import re +from abc import ABC +from dataclasses import MISSING, dataclass, fields +from functools import partial +from typing import Any, Callable, TypedDict, cast + +from typing_extensions import Self + + +class ParserFn(TypedDict): + """Parser function in a dict compatible with the :func:`dataclasses.field` metadata param.""" + + #: + TextParser_fn: Callable[[str], Any] + + +@dataclass +class TextParser(ABC): + """Helper abstract dataclass that parses a text according to the fields' rules. + + This class provides a selection of parser functions and a function to compose generic functions + with parser functions. Parser functions are designed to be passed to the fields' metadata param + to enable parsing. + """ + + """============ BEGIN PARSER FUNCTIONS ============""" + + @staticmethod + def compose(f: Callable, parser_fn: ParserFn) -> ParserFn: + """Makes a composite parser function. + + The parser function is run and if a non-None value was returned, f is called with it. + Otherwise the function returns early with None. + + Metadata modifier for :func:`dataclasses.field`. + + Args: + f: the function to apply to the parser's result + parser_fn: the dictionary storing the parser function + """ + g = parser_fn["TextParser_fn"] + + def _composite_parser_fn(text: str) -> Any: + intermediate_value = g(text) + if intermediate_value is None: + return None + return f(intermediate_value) + + return ParserFn(TextParser_fn=_composite_parser_fn) + + @staticmethod + def find( + pattern: str | re.Pattern[str], + flags: re.RegexFlag = re.RegexFlag(0), + named: bool = False, + ) -> ParserFn: + """Makes a parser function that finds a regular expression match in the text. + + If the pattern has capturing groups, it returns None if no match was found. If the pattern + has only one capturing group and a match was found, its value is returned. If the pattern + has no capturing groups then either True or False is returned if the pattern had a match or + not. + + Metadata modifier for :func:`dataclasses.field`. + + Args: + pattern: the regular expression pattern + flags: the regular expression flags. Not used if the given pattern is already compiled + named: if set to True only the named capture groups will be returned as a dictionary + """ + if isinstance(pattern, str): + pattern = re.compile(pattern, flags) + + def _find(text: str) -> Any: + m = pattern.search(text) + if m is None: + return None if pattern.groups > 0 else False + + if pattern.groups == 0: + return True + + if named: + return m.groupdict() + + matches = m.groups() + if len(matches) == 1: + return matches[0] + + return matches + + return ParserFn(TextParser_fn=_find) + + @classmethod + def find_int( + cls, + pattern: str | re.Pattern[str], + flags: re.RegexFlag = re.RegexFlag(0), + int_base: int = 0, + ) -> ParserFn: + """Makes a parser function that converts the match of :meth:`~find` to int. + + This function is compatible only with a pattern containing one capturing group. + + Metadata modifier for :func:`dataclasses.field`. + + Args: + pattern: the regular expression pattern + flags: the regular expression flags + int_base: the base of the number to convert from + Raises: + RuntimeError: if the pattern does not have exactly one capturing group + """ + if isinstance(pattern, str): + pattern = re.compile(pattern, flags) + + if pattern.groups != 1: + raise RuntimeError("only one capturing group is allowed with this parser function") + + return cls.compose(partial(int, base=int_base), cls.find(pattern)) + + """============ END PARSER FUNCTIONS ============""" + + @classmethod + def parse(cls, text: str) -> Self: + """Creates a new instance of the class from the given text. + + A new class instance is created with all the fields that have a parser function in their + metadata. Fields without one are ignored and are expected to have a default value, otherwise + the class initialization will fail. + + A field is populated with the value returned by its corresponding parser function. + + Args: + text: the text to parse + Raises: + RuntimeError: if the parser did not find a match and the field does not have a default + value or default factory. + """ + fields_values = {} + for field in fields(cls): + parse = cast(ParserFn, field.metadata).get("TextParser_fn") + if parse is None: + continue + + value = parse(text) + if value is not None: + fields_values[field.name] = value + elif field.default is MISSING and field.default_factory is MISSING: + raise RuntimeError( + f"parser for field {field.name} returned None, but the field has no default" + ) + + return cls(**fields_values) -- 2.34.1