mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-09-30 01:52:29 +00:00
041f957a7f
* refactor(components): extract shared component state into mixin - Introduce ComponentMixin class with shared state for components and steps - Move identity, config, and vault path functionality to ComponentMixin - Update BaseComponent to inherit from ComponentMixin - Update BaseStep to inherit from ComponentMixin - Consolidate vault path helper methods in ComponentMixin - Remove duplicate vault path implementations from BaseComponent and BaseStep - Add ComponentMixin to components module exports * refactor(file_io): implement path locks cache eviction mechanism - Add _PATH_LOCKS_MAX constant set to 1024 for cache size limit - Implement cache eviction logic when locks exceed maximum capacity - Remove half of unlocked entries when cache limit is reached - Use list comprehension to identify unlocked locks for removal - Maintain existing path normalization and locking behavior fix(edit): correct method call from public to private fail method - Change self.fail to self._fail for internal error handling - Maintain consistent private method usage within class fix(mcp_client): change pop to get for optional command and args - Replace kwargs.pop with kwargs.get to avoid removing keys - Preserve original kwargs dictionary contents - Maintain default empty string and list values feat(reme): add client backend validation with error raising - Check if client_cls is None before instantiation - Raise ValueError with descriptive message for unknown backends - Provide clear error feedback for invalid backend configurations * fix(components): move directory creation to start method - Moved component_metadata_path.mkdir call from __init__ to _start in base_keyword_index - Moved component_metadata_path.mkdir call from __init__ to _start in local_file_graph - Moved component_metadata_path.mkdir call from __init__ to _start in local_file_store - Ensures directory creation happens after component initialization - Prevents potential issues with path creation during object construction * fix(steps): replace assertions with runtime errors for app_context validation - Replace assert statements with explicit RuntimeError exceptions when app_context is None - Add descriptive error messages for better debugging when resolving components - Replace assert in resolve_component method with proper exception handling - Replace assert in get_file_parser method with proper exception handling - Maintain same functionality while improving error reporting clarity * refactor(file_io): split file IO utilities into modular components - Move daily note helpers to separate _daily_index module - Extract path validation and resolution to new _path module - Remove unused code and imports from _file_io module - Update import statements across affected modules - Introduce WikilinkHandler utility for link parsing - Replace regex-based link extraction with WikilinkHandler - Add integration JSONL files to gitignore - Consolidate file locking mechanism in _file_io module * style(formatter): fix spacing issues in file IO and chunked file parser - Fixed whitespace around colon in slice notation in file_io.py - Corrected spacing around colon in slice notation in chunked_file_parser.py - Applied consistent formatting for array slicing operations - Improved code readability by standardizing space placement in ranges * refactor(steps): replace property-based component resolution with Ref descriptor - Introduce Ref descriptor class for lazy component dependency resolution - Replace _resolve method and individual properties with Ref descriptors - Add as_llm, as_llm_formatter, as_token_counter, file_store, and embedding Ref attributes - Remove legacy property methods and resolve logic from BaseStep - Add cache clearing mechanism for Ref values during step calls - Update UpdateCatalogStep to use Ref instead of property-based resolution
96 lines
3 KiB
Python
96 lines
3 KiB
Python
"""Path resolution, validation, and filetype gating for CRUD steps."""
|
|
|
|
import re
|
|
from pathlib import Path
|
|
|
|
from ...utils import get_logger
|
|
|
|
logger = get_logger()
|
|
|
|
NON_MD_WARNING = (
|
|
"non-markdown file detected; CRUD operations are recommended on markdown files. "
|
|
"Operating in compatibility mode may carry risks of errors."
|
|
)
|
|
|
|
NON_IMAGE_WARNING = (
|
|
"non-image file detected; CRUD image operations are recommended on standard image formats. "
|
|
"Operating in compatibility mode may carry risks of errors."
|
|
)
|
|
|
|
IMAGE_MIME_BY_EXT: dict[str, str] = {
|
|
".png": "image/png",
|
|
".jpg": "image/jpeg",
|
|
".jpeg": "image/jpeg",
|
|
".webp": "image/webp",
|
|
".gif": "image/gif",
|
|
".bmp": "image/bmp",
|
|
".tiff": "image/tiff",
|
|
".heic": "image/heic",
|
|
}
|
|
|
|
_INVALID_CHARS = re.compile(r'[<>:"/\\|?*\x00-\x1f]')
|
|
_RESERVED_NAMES = {
|
|
"CON",
|
|
"PRN",
|
|
"AUX",
|
|
"NUL",
|
|
*(f"COM{i}" for i in range(1, 10)),
|
|
*(f"LPT{i}" for i in range(1, 10)),
|
|
}
|
|
|
|
|
|
def validate_filename_component(name: str, *, kind: str = "filename") -> str | None:
|
|
"""Return an error message, or ``None`` when ``name`` is a safe filename component."""
|
|
if not name:
|
|
return f"{kind} is required"
|
|
if name != name.strip():
|
|
return f"{kind} cannot have leading or trailing whitespace: {name!r}"
|
|
if _INVALID_CHARS.search(name):
|
|
return f'{kind} contains invalid characters (one of < > : " / \\ | ? * or a control char): {name!r}'
|
|
if name.endswith("."):
|
|
return f"{kind} cannot end with '.': {name!r}"
|
|
if name.split(".", 1)[0].upper() in _RESERVED_NAMES:
|
|
return f"{kind} is a Windows-reserved device name: {name!r}"
|
|
return None
|
|
|
|
|
|
def resolve_path(vault_path: Path, raw: str) -> tuple[Path | None, str | None]:
|
|
"""Resolve a `path=` argument against ``vault_path``.
|
|
|
|
Returns ``(abs_path, None)`` on success, or ``(None, error_message)`` on failure.
|
|
"""
|
|
if not raw or not str(raw).strip():
|
|
return None, "`path` is required"
|
|
s = str(raw).strip()
|
|
p = Path(s)
|
|
for part in p.parts:
|
|
if part == p.anchor:
|
|
continue
|
|
err = validate_filename_component(part, kind="path component")
|
|
if err:
|
|
return None, err
|
|
if p.is_absolute():
|
|
logger.info("absolute path detected, recommending relative paths")
|
|
return p, None
|
|
return vault_path / p, None
|
|
|
|
|
|
def gate_md(target: Path) -> tuple[Path, bool]:
|
|
"""Markdown gate with compatibility fallback.
|
|
|
|
Returns ``(path, is_md)``:
|
|
- No suffix -> auto-append `.md`, ``is_md=True``.
|
|
- `.md` suffix -> ``is_md=True``.
|
|
- Any other suffix -> ``is_md=False`` (caller handles degraded mode).
|
|
"""
|
|
if target.suffix == "":
|
|
return target.with_suffix(".md"), True
|
|
if target.suffix.lower() != ".md":
|
|
return target, False
|
|
return target, True
|
|
|
|
|
|
def gate_image(target: Path) -> tuple[Path, bool, str | None]:
|
|
"""Image gate with compatibility fallback. Returns ``(path, is_image, mime)``."""
|
|
mime = IMAGE_MIME_BY_EXT.get(target.suffix.lower())
|
|
return target, mime is not None, mime
|