lukaszett/Knack-Scraper
1
1
Fork 1
Code Issues Pull requests Projects Releases Packages Wiki Activity

Adds TransformNode to FuzzyFind Author Names

Browse source
This commit is contained in:
quorploop 2025-12-23 17:53:37 +01:00
parent 64df8fb328
commit 72765532d3
11 changed files with 696 additions and 58 deletions
Download patch file Download diff file Expand all files Collapse all files

25
transform/Dockerfile
View file

@ -1,7 +1,6 @@
FROM python:3.12-slim
RUN mkdir /app
RUN mkdir /data
RUN mkdir -p /app /data /models
# Install build dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
@ -11,9 +10,12 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
libopenblas-dev \
liblapack-dev \
pkg-config \
curl \
jq \
&& rm -rf /var/lib/apt/lists/*
#COPY /data/knack.sqlite /data
ENV GLINER_MODEL_ID=urchade/gliner_multi-v2.1
ENV GLINER_MODEL_PATH=/models/gliner_multi-v2.1
WORKDIR /app
COPY requirements.txt .
@ -24,18 +26,21 @@ COPY .env .
RUN apt update -y
RUN apt install -y cron locales
COPY *.py .
# Ensure GLiNER helper scripts are available
COPY ensure_gliner_model.sh /usr/local/bin/ensure_gliner_model.sh
COPY entrypoint.sh /usr/local/bin/entrypoint.sh
RUN chmod +x /usr/local/bin/ensure_gliner_model.sh /usr/local/bin/entrypoint.sh
ENV PYTHONUNBUFFERED=1
ENV LANG=de_DE.UTF-8
ENV LC_ALL=de_DE.UTF-8
COPY *.py .
# Create cron job that runs every weekend (Sunday at 3 AM) 0 3 * * 0
# Testing every 30 Minutes */30 * * * *
RUN echo "0 3 * * 0 cd /app && /usr/local/bin/python main.py >> /proc/1/fd/1 2>&1" > /etc/cron.d/knack-transform
RUN echo "*/30 * * * * cd /app && /usr/local/bin/python main.py >> /proc/1/fd/1 2>&1" > /etc/cron.d/knack-transform
RUN chmod 0644 /etc/cron.d/knack-transform
RUN crontab /etc/cron.d/knack-transform
# Start cron in foreground
CMD ["cron", "-f"]
# Persist models between container runs
VOLUME /models
CMD ["/usr/local/bin/entrypoint.sh"]
#CMD ["python", "main.py"]