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.
117 lines
3.3 KiB
Python
117 lines
3.3 KiB
Python
import os
|
|
import re
|
|
|
|
from .compat.py313 import legacy_end_marker
|
|
|
|
_default_seps = os.sep + str(os.altsep) * bool(os.altsep)
|
|
|
|
|
|
class Translator:
|
|
"""
|
|
>>> Translator('xyz')
|
|
Traceback (most recent call last):
|
|
...
|
|
AssertionError: Invalid separators
|
|
|
|
>>> Translator('')
|
|
Traceback (most recent call last):
|
|
...
|
|
AssertionError: Invalid separators
|
|
"""
|
|
|
|
seps: str
|
|
|
|
def __init__(self, seps: str = _default_seps):
|
|
assert seps and set(seps) <= set(_default_seps), "Invalid separators"
|
|
self.seps = seps
|
|
|
|
def translate(self, pattern):
|
|
"""
|
|
Given a glob pattern, produce a regex that matches it.
|
|
"""
|
|
return self.extend(self.match_dirs(self.translate_core(pattern)))
|
|
|
|
@legacy_end_marker
|
|
def extend(self, pattern):
|
|
r"""
|
|
Extend regex for pattern-wide concerns.
|
|
|
|
Apply '(?s:)' to create a non-matching group that
|
|
matches newlines (valid on Unix).
|
|
|
|
Append '\z' to imply fullmatch even when match is used.
|
|
"""
|
|
return rf'(?s:{pattern})\z'
|
|
|
|
def match_dirs(self, pattern):
|
|
"""
|
|
Ensure that zipfile.Path directory names are matched.
|
|
|
|
zipfile.Path directory names always end in a slash.
|
|
"""
|
|
return rf'{pattern}[/]?'
|
|
|
|
def translate_core(self, pattern):
|
|
r"""
|
|
Given a glob pattern, produce a regex that matches it.
|
|
|
|
>>> t = Translator()
|
|
>>> t.translate_core('*.txt').replace('\\\\', '')
|
|
'[^/]*\\.txt'
|
|
>>> t.translate_core('a?txt')
|
|
'a[^/]txt'
|
|
>>> t.translate_core('**/*').replace('\\\\', '')
|
|
'.*/[^/][^/]*'
|
|
"""
|
|
self.restrict_rglob(pattern)
|
|
return ''.join(map(self.replace, separate(self.star_not_empty(pattern))))
|
|
|
|
def replace(self, match):
|
|
"""
|
|
Perform the replacements for a match from :func:`separate`.
|
|
"""
|
|
return match.group('set') or (
|
|
re.escape(match.group(0))
|
|
.replace('\\*\\*', r'.*')
|
|
.replace('\\*', rf'[^{re.escape(self.seps)}]*')
|
|
.replace('\\?', r'[^/]')
|
|
)
|
|
|
|
def restrict_rglob(self, pattern):
|
|
"""
|
|
Raise ValueError if ** appears in anything but a full path segment.
|
|
|
|
>>> Translator().translate('**foo')
|
|
Traceback (most recent call last):
|
|
...
|
|
ValueError: ** must appear alone in a path segment
|
|
"""
|
|
seps_pattern = rf'[{re.escape(self.seps)}]+'
|
|
segments = re.split(seps_pattern, pattern)
|
|
if any('**' in segment and segment != '**' for segment in segments):
|
|
raise ValueError("** must appear alone in a path segment")
|
|
|
|
def star_not_empty(self, pattern):
|
|
"""
|
|
Ensure that * will not match an empty segment.
|
|
"""
|
|
|
|
def handle_segment(match):
|
|
segment = match.group(0)
|
|
return '?*' if segment == '*' else segment
|
|
|
|
not_seps_pattern = rf'[^{re.escape(self.seps)}]+'
|
|
return re.sub(not_seps_pattern, handle_segment, pattern)
|
|
|
|
|
|
def separate(pattern):
|
|
"""
|
|
Separate out character sets to avoid translating their contents.
|
|
|
|
>>> [m.group(0) for m in separate('*.txt')]
|
|
['*.txt']
|
|
>>> [m.group(0) for m in separate('a[?]txt')]
|
|
['a', '[?]', 'txt']
|
|
"""
|
|
return re.finditer(r'([^\[]+)|(?P<set>[\[].*?[\]])|([\[][^\]]*$)', pattern)
|