mcelwain
/
document-processor
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add document normalization metadata field

This commit is contained in:
Sean McElwain 2026-05-30 19:51:49 -05:00
parent 05c9b6964a
commit 18af01486c
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
app/models/document.py
View File

@ -1,6 +1,6 @@
from datetime import datetime
from sqlalchemy import Boolean, DateTime, Integer, String, Text
from sqlalchemy import Boolean, DateTime, Integer, String, Text, JSON
from sqlalchemy.orm import Mapped, mapped_column, relationship
from app.db.base import Base
@ -30,6 +30,10 @@ class Document(Base):
file_size: Mapped[int | None] = mapped_column(Integer, nullable=True)
page_count: Mapped[int | None] = mapped_column(Integer, nullable=True)
# Future-ready metadata for normalized sources, such as:
# image -> letter PDF, image -> A4 PDF, receipt roll normalization, etc.
normalization_json: Mapped[dict | None] = mapped_column(JSON, nullable=True)
sha256_original: Mapped[str | None] = mapped_column(String(64), nullable=True)
sha256_current: Mapped[str | None] = mapped_column(String(64), nullable=True)