mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-07-15 21:11:05 +02:00
703017e581
Replace the `...` bodies in DocumentParser / StorageEngine protocol methods with one-line docstrings: silences the CodeQL "statement has no effect" false positives on #272 (`...` is idiomatic for typing.Protocol, but docstrings document the contract and don't trip the analyzer) with no behavior change. Claude-Session: https://claude.ai/code/session_01Kx5DgKbhK1N8autqXH8SmS
31 lines
920 B
Python
31 lines
920 B
Python
from __future__ import annotations
|
|
from dataclasses import dataclass
|
|
from typing import Protocol, runtime_checkable
|
|
|
|
|
|
@dataclass
|
|
class ContentNode:
|
|
"""Universal content unit produced by parsers."""
|
|
content: str
|
|
tokens: int
|
|
title: str | None = None
|
|
index: int | None = None
|
|
level: int | None = None
|
|
images: list[dict] | None = None # [{"path": str, "width": int, "height": int}, ...]
|
|
|
|
|
|
@dataclass
|
|
class ParsedDocument:
|
|
"""Unified parser output. Always a flat list of ContentNode."""
|
|
doc_name: str
|
|
nodes: list[ContentNode]
|
|
metadata: dict | None = None
|
|
|
|
|
|
@runtime_checkable
|
|
class DocumentParser(Protocol):
|
|
def supported_extensions(self) -> list[str]:
|
|
"""Return the file extensions this parser handles (e.g. ['.pdf'])."""
|
|
|
|
def parse(self, file_path: str, **kwargs) -> ParsedDocument:
|
|
"""Parse a file into a ParsedDocument (a flat list of ContentNode)."""
|