mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-03-19 05:37:51 +08:00
## Summary This PR is the direct successor to the previous `docx` lazy-loading implementation. It addresses the technical debt intentionally left out in the last PR by fully migrating the `qa` and `manual` parsing strategies to the new lazy-loading model. Additionally, this PR comprehensively refactors the underlying `docx` parsing pipeline to eliminate significant code redundancy and introduces robust fallback mechanisms to handle completely corrupted image streams safely. ## What's Changed * **Centralized Abstraction (`docx_parser.py`)**: Moved the `get_picture` extraction logic up to the `RAGFlowDocxParser` base class. Previously, `naive`, `qa`, and `manual` parsers maintained separate, redundant copies of this method. All downstream strategies now natively gather raw blobs and return `LazyDocxImage` objects automatically. * **Robust Corrupted Image Fallback (`docx_parser.py`)**: Handled edge cases where `python-docx` encounters critically malformed magic headers. Implemented an explicit `try-except` structure that safely intercepts `UnrecognizedImageError` (and similar exceptions) and seamlessly falls back to retrieving the raw binary via `getattr(related_part, "blob", None)`, preventing parser crashes on damaged documents. * **Legacy Code & Redundancy Purge**: * Removed the duplicate `get_picture` methods from `naive.py`, `qa.py`, and `manual.py`. * Removed the standalone, immediate-decoding `concat_img` method in `manual.py`. It has been completely replaced by the globally unified, lazy-loading-compatible `rag.nlp.concat_img`. * Cleaned up unused legacy imports (e.g., `PIL.Image`, docx exception packages) across all updated strategy files. ## Scope To keep this PR focused, I have restricted these changes strictly to the unification of `docx` extraction logic and the lazy-load migration of `qa` and `manual`. ## Validation & Testing I've tested this to ensure no regressions and validated the fallback logic: * **Output Consistency**: Compared identical `.docx` inputs using `qa` and `manual` strategies before and after this branch: chunk counts, extracted text, table HTML, and attached images match perfectly. * **Memory Footprint Drop**: Confirmed a noticeable drop in peak memory usage when processing image-dense documents through the `qa` and `manual` pipelines, bringing them up to parity with the `naive` strategy's performance gains. ## Breaking Changes * None.
130 lines
3.3 KiB
Python
130 lines
3.3 KiB
Python
import logging
|
|
from io import BytesIO
|
|
|
|
from PIL import Image
|
|
|
|
from rag.nlp import concat_img
|
|
|
|
|
|
class LazyDocxImage:
|
|
def __init__(self, blobs, source=None):
|
|
self._blobs = [b for b in (blobs or []) if b]
|
|
self.source = source
|
|
self._pil = None
|
|
|
|
def __bool__(self):
|
|
return bool(self._blobs)
|
|
|
|
def to_pil(self):
|
|
if self._pil is not None:
|
|
try:
|
|
self._pil.load()
|
|
return self._pil
|
|
except Exception:
|
|
try:
|
|
self._pil.close()
|
|
except Exception:
|
|
pass
|
|
self._pil = None
|
|
res_img = None
|
|
for blob in self._blobs:
|
|
try:
|
|
image = Image.open(BytesIO(blob)).convert("RGB")
|
|
except Exception as e:
|
|
logging.info(f"LazyDocxImage: skip bad image blob: {e}")
|
|
continue
|
|
|
|
if res_img is None:
|
|
res_img = image
|
|
continue
|
|
|
|
new_img = concat_img(res_img, image)
|
|
if new_img is not res_img:
|
|
try:
|
|
res_img.close()
|
|
except Exception:
|
|
pass
|
|
try:
|
|
image.close()
|
|
except Exception:
|
|
pass
|
|
res_img = new_img
|
|
|
|
self._pil = res_img
|
|
return self._pil
|
|
|
|
def to_pil_detached(self):
|
|
pil = self.to_pil()
|
|
self._pil = None
|
|
return pil
|
|
|
|
def close(self):
|
|
if self._pil is not None:
|
|
try:
|
|
self._pil.close()
|
|
except Exception:
|
|
pass
|
|
self._pil = None
|
|
return None
|
|
|
|
def __getattr__(self, name):
|
|
pil = self.to_pil()
|
|
if pil is None:
|
|
raise AttributeError(name)
|
|
return getattr(pil, name)
|
|
|
|
def __array__(self, dtype=None):
|
|
import numpy as np
|
|
|
|
pil = self.to_pil()
|
|
if pil is None:
|
|
return np.array([], dtype=dtype)
|
|
return np.array(pil, dtype=dtype)
|
|
|
|
def __enter__(self):
|
|
return self.to_pil()
|
|
|
|
def __exit__(self, exc_type, exc, tb):
|
|
self.close()
|
|
return False
|
|
|
|
@staticmethod
|
|
def merge(a, b):
|
|
"""
|
|
Merge two LazyDocxImage instances by combining their blob lists.
|
|
"""
|
|
a_blobs = a._blobs if isinstance(a, LazyDocxImage) else []
|
|
b_blobs = b._blobs if isinstance(b, LazyDocxImage) else []
|
|
combined = a_blobs + b_blobs
|
|
if not combined:
|
|
return None
|
|
merged = LazyDocxImage(combined)
|
|
return merged
|
|
|
|
|
|
def ensure_pil_image(img):
|
|
if isinstance(img, Image.Image):
|
|
return img
|
|
if isinstance(img, LazyDocxImage):
|
|
return img.to_pil()
|
|
return None
|
|
|
|
|
|
def is_image_like(img):
|
|
return isinstance(img, Image.Image) or isinstance(img, LazyDocxImage)
|
|
|
|
|
|
def open_image_for_processing(img, *, allow_bytes=False):
|
|
if isinstance(img, Image.Image):
|
|
return img, False
|
|
if isinstance(img, LazyDocxImage):
|
|
return img.to_pil_detached(), True
|
|
if allow_bytes and isinstance(img, (bytes, bytearray)):
|
|
try:
|
|
pil = Image.open(BytesIO(img)).convert("RGB")
|
|
return pil, True
|
|
except Exception as e:
|
|
logging.info(f"open_image_for_processing: bad bytes: {e}")
|
|
return None, False
|
|
return img, False
|