egullickson/motovaultpro
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: UX design audit cleanup and receipt flow improvements #186

Merged
egullickson merged 25 commits from issue-162-ux-design-audit-cleanup into main 2026-02-14 03:50:23 +00:00
Conversation 0 Commits 25 Files Changed 51 +19 -15
2 changed files with 19 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 5e4515da7c - Show all commits

17
ocr/app/extractors/receipt_extractor.py
View File

@@ -162,15 +162,18 @@ class ReceiptExtractor(BaseExtractor):
def _extract_pdf_first_page(self, pdf_bytes: bytes) -> bytes:
"""Extract first page of PDF as PNG image for OCR processing."""
try:
from pdf2image import convert_from_bytes
import fitz # PyMuPDF
images = convert_from_bytes(pdf_bytes, first_page=1, last_page=1, dpi=300)
if images:
buffer = io.BytesIO()
images[0].save(buffer, format="PNG")
return buffer.getvalue()
doc = fitz.open(stream=pdf_bytes, filetype="pdf")
page = doc[0]
# Render at 300 DPI (default is 72, so scale factor = 300/72)
mat = fitz.Matrix(300 / 72, 300 / 72)
pix = page.get_pixmap(matrix=mat)
png_bytes = pix.tobytes("png")
doc.close()
return png_bytes
except ImportError:
logger.warning("pdf2image not available, PDF support limited")
logger.warning("PyMuPDF not available, PDF support limited")
except Exception as e:
logger.error(f"PDF first page extraction failed: {e}")

17
ocr/app/services/ocr_service.py
View File

@@ -141,16 +141,17 @@ class OcrService:
def _extract_pdf_first_page(self, pdf_bytes: bytes) -> bytes:
"""Extract first page of PDF as PNG image."""
try:
# Use pdf2image if available, otherwise return empty
from pdf2image import convert_from_bytes
import fitz # PyMuPDF
images = convert_from_bytes(pdf_bytes, first_page=1, last_page=1, dpi=300)
if images:
buffer = io.BytesIO()
images[0].save(buffer, format="PNG")
return buffer.getvalue()
doc = fitz.open(stream=pdf_bytes, filetype="pdf")
page = doc[0]
mat = fitz.Matrix(300 / 72, 300 / 72)
pix = page.get_pixmap(matrix=mat)
png_bytes = pix.tobytes("png")
doc.close()
return png_bytes
except ImportError:
logger.warning("pdf2image not available, PDF support limited")
logger.warning("PyMuPDF not available, PDF support limited")
except Exception as e:
logger.error(f"PDF extraction failed: {e}")