marcel/familienarchiv
1
0
Fork 0
Code Issues 105 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

refactor(ocr): extract extract_page_blocks() from both OCR engines

Browse Source 
Enable per-page processing by extracting the inner loop body of
extract_blocks() into extract_page_blocks(image, page_idx, language).
The original extract_blocks() now delegates to the new function,
preserving backward compatibility for the batch path.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Marcel
2026-04-13 09:56:34 +02:00
parent d8dcba1a71
commit b7d5f71ef7
3 changed files with 231 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

90
ocr-service/engines/surya.py
View File

@@ -33,6 +33,54 @@ def load_models():
logger.info("Surya models loaded successfully")
def extract_page_blocks(image, page_idx: int, language: str = "de") -> list[dict]:
"""Run Surya OCR on a single PIL image and return block dicts for that page.
Coordinates are normalized to [0, 1].
"""
load_models()
page_w, page_h = image.size
blocks = []
predictions = _recognition_predictor([image], det_predictor=_detection_predictor)
page_pred = predictions[0]
for line in page_pred.text_lines:
bbox = line.bbox
x1, y1, x2, y2 = bbox
polygon = None
if hasattr(line, "polygon") and line.polygon and len(line.polygon) == 4:
polygon = [
[p[0] / page_w, p[1] / page_h]
for p in line.polygon
]
words = []
if hasattr(line, "words") and line.words:
for word in line.words:
words.append({
"text": word.text,
"confidence": word.confidence,
})
else:
words = [{"text": line.text, "confidence": getattr(line, "confidence", 1.0)}]
blocks.append({
"pageNumber": page_idx,
"x": x1 / page_w,
"y": y1 / page_h,
"width": (x2 - x1) / page_w,
"height": (y2 - y1) / page_h,
"polygon": polygon,
"text": line.text,
"words": words,
})
return blocks
def extract_blocks(images: list, language: str = "de") -> list[dict]:
"""Run Surya OCR on a list of PIL images (one per page).
@@ -40,50 +88,10 @@ def extract_blocks(images: list, language: str = "de") -> list[dict]:
Returns a flat list of block dicts with pageNumber, x, y, width, height,
polygon, text, words. Coordinates are normalized to [0, 1].
"""
load_models()
all_blocks = []
for page_idx, image in enumerate(images):
page_w, page_h = image.size
# Process single page to limit peak memory
predictions = _recognition_predictor([image], det_predictor=_detection_predictor)
page_pred = predictions[0]
for line in page_pred.text_lines:
bbox = line.bbox
x1, y1, x2, y2 = bbox
polygon = None
if hasattr(line, "polygon") and line.polygon and len(line.polygon) == 4:
polygon = [
[p[0] / page_w, p[1] / page_h]
for p in line.polygon
]
words = []
if hasattr(line, "words") and line.words:
for word in line.words:
words.append({
"text": word.text,
"confidence": word.confidence,
})
else:
words = [{"text": line.text, "confidence": getattr(line, "confidence", 1.0)}]
all_blocks.append({
"pageNumber": page_idx,
"x": x1 / page_w,
"y": y1 / page_h,
"width": (x2 - x1) / page_w,
"height": (y2 - y1) / page_h,
"polygon": polygon,
"text": line.text,
"words": words,
})
# Free page image after processing
all_blocks.extend(extract_page_blocks(image, page_idx, language))
del image
return all_blocks