Master
943acbc573
Durcit la convention de nommage des projets (dérive constatée : 'Sliding Automation', 'code_versioning'... au lieu des formes canoniques). - trilium_api.py : projets_canoniques() lit le référentiel = valeurs du label projet sur les notes de type=projet (source unique, pas de constante en dur). Note-projet CodeVersioning créée (manquait). - mcp_server.py : _valider_projet() branché dans les 6 tools de création (add_decision/history/backlog, new_conversation, create_entite, add_skill). Refuse un projet non canonique (suggestion si faute) ou inconnu (renvoi au processus de création de projet). Ne verrouille pas si référentiel illisible. - lint_audit.py : VAL-nommage aligné sur le référentiel (attrape casse, espace ET snake_case ; l'ancien 'contient un espace' ratait code_versioning). - Données : 79 notes ré-étiquetées vers les 3 formes canoniques. Quality by design : l'erreur de nommage devient impossible à l'écriture, le Lint n'est plus que le filet de sécurité.
92 lines
3.1 KiB
Python
92 lines
3.1 KiB
Python
# Python Markdown
|
|
|
|
# A Python implementation of John Gruber's Markdown.
|
|
|
|
# Documentation: https://python-markdown.github.io/
|
|
# GitHub: https://github.com/Python-Markdown/markdown/
|
|
# PyPI: https://pypi.org/project/Markdown/
|
|
|
|
# Started by Manfred Stienstra (http://www.dwerg.net/).
|
|
# Maintained for a few years by Yuri Takhteyev (http://www.freewisdom.org).
|
|
# Currently maintained by Waylan Limberg (https://github.com/waylan),
|
|
# Dmitry Shachnev (https://github.com/mitya57) and Isaac Muse (https://github.com/facelessuser).
|
|
|
|
# Copyright 2007-2023 The Python Markdown Project (v. 1.7 and later)
|
|
# Copyright 2004, 2005, 2006 Yuri Takhteyev (v. 0.2-1.6b)
|
|
# Copyright 2004 Manfred Stienstra (the original version)
|
|
|
|
# License: BSD (see LICENSE.md for details).
|
|
|
|
"""
|
|
Preprocessors work on source text before it is broken down into its individual parts.
|
|
This is an excellent place to clean up bad characters or to extract portions for later
|
|
processing that the parser may otherwise choke on.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import TYPE_CHECKING, Any
|
|
from . import util
|
|
from .htmlparser import HTMLExtractor
|
|
import re
|
|
|
|
if TYPE_CHECKING: # pragma: no cover
|
|
from markdown import Markdown
|
|
|
|
|
|
def build_preprocessors(md: Markdown, **kwargs: Any) -> util.Registry[Preprocessor]:
|
|
""" Build and return the default set of preprocessors used by Markdown. """
|
|
preprocessors = util.Registry()
|
|
preprocessors.register(NormalizeWhitespace(md), 'normalize_whitespace', 30)
|
|
preprocessors.register(HtmlBlockPreprocessor(md), 'html_block', 20)
|
|
return preprocessors
|
|
|
|
|
|
class Preprocessor(util.Processor):
|
|
"""
|
|
Preprocessors are run after the text is broken into lines.
|
|
|
|
Each preprocessor implements a `run` method that takes a pointer to a
|
|
list of lines of the document, modifies it as necessary and returns
|
|
either the same pointer or a pointer to a new list.
|
|
|
|
Preprocessors must extend `Preprocessor`.
|
|
|
|
"""
|
|
def run(self, lines: list[str]) -> list[str]:
|
|
"""
|
|
Each subclass of `Preprocessor` should override the `run` method, which
|
|
takes the document as a list of strings split by newlines and returns
|
|
the (possibly modified) list of lines.
|
|
|
|
"""
|
|
pass # pragma: no cover
|
|
|
|
|
|
class NormalizeWhitespace(Preprocessor):
|
|
""" Normalize whitespace for consistent parsing. """
|
|
|
|
def run(self, lines: list[str]) -> list[str]:
|
|
source = '\n'.join(lines)
|
|
source = source.replace(util.STX, "").replace(util.ETX, "")
|
|
source = source.replace("\r\n", "\n").replace("\r", "\n") + "\n\n"
|
|
source = source.expandtabs(self.md.tab_length)
|
|
source = re.sub(r'(?<=\n) +\n', '\n', source)
|
|
return source.split('\n')
|
|
|
|
|
|
class HtmlBlockPreprocessor(Preprocessor):
|
|
"""
|
|
Remove html blocks from the text and store them for later retrieval.
|
|
|
|
The raw HTML is stored in the [`htmlStash`][markdown.util.HtmlStash] of the
|
|
[`Markdown`][markdown.Markdown] instance.
|
|
"""
|
|
|
|
def run(self, lines: list[str]) -> list[str]:
|
|
source = '\n'.join(lines)
|
|
parser = HTMLExtractor(self.md)
|
|
parser.feed(source)
|
|
parser.close()
|
|
return ''.join(parser.cleandoc).split('\n')
|