feat: manually mirror opencoze's code from bytedance

Change-Id: I09a73aadda978ad9511264a756b2ce51f5761adf

backend/Dockerfile

@@ -0,0 +1,85 @@
+# Stage 1: Builder for Go application
+FROM golang:1.24-alpine AS builder
+
+WORKDIR /app
+
+# Install build dependencies for Go
+RUN apk add --no-cache git gcc libc-dev
+
+# Copy go.mod and go.sum first to leverage Docker cache
+COPY backend/go.mod backend/go.sum ./
+RUN go mod download
+
+
+COPY docker/proxy ./proxy
+
+# Build the proxy application
+RUN go build -ldflags="-s -w" -o /app/proxy_app ./proxy/proxy.go
+
+# Copy the entire backend source code
+COPY backend/ ./
+
+# Build the Go application
+RUN go build -ldflags="-s -w" -o /app/opencoze main.go
+
+
+
+# Stage 2: Final image
+FROM alpine:3.22.0
+
+WORKDIR /app
+
+# Install runtime dependencies for Go app and base for Python
+# pax-utils for scanelf, python3 for running Python, python3-dev for headers/shared libs
+# bind-tools for nslookup etc., file for debugging file types
+RUN apk add --no-cache pax-utils python3 python3-dev bind-tools file
+
+# Install Python build dependencies, create venv, install packages, then remove build deps
+RUN apk add --no-cache --virtual .python-build-deps build-base py3-pip git && \
+    python3 -m venv --copies --upgrade-deps /app/.venv && \
+    # Activate venv and install packages
+    . /app/.venv/bin/activate && \
+    # If you want to use other third-party libraries, you can install them here.
+    pip install git+https://gitcode.com/gh_mirrors/re/requests-async.git@master && \
+    pip install urllib3==1.26.16 && \
+    pip install --no-cache-dir pillow==11.2.1 pdfplumber==0.11.7 python-docx==1.2.0 numpy==2.3.1 && \
+    # Deactivate (optional, as RUN is a new shell)
+    # deactivate && \
+    # Remove build dependencies
+    apk del .python-build-deps
+
+# Copy the built Go binary from the builder stage
+COPY --from=builder /app/opencoze /app/opencoze
+COPY --from=builder /app/proxy_app /app/proxy
+
+# Copy Python application scripts
+COPY backend/infra/impl/document/parser/builtin/parse_pdf.py /app/parse_pdf.py
+COPY backend/infra/impl/document/parser/builtin/parse_docx.py /app/parse_docx.py
+
+
+# Copy static resources
+COPY backend/static /app/resources/static/
+COPY backend/conf /app/resources/conf/
+COPY docker/.env.example /app/.env
+# COPY docker/.env.ve /app/.env
+# COPY docker/cert.pem /app/cert.pem
+# COPY docker/key.pem /app/key.pem
+
+# Set PATH to prioritize venv's binaries
+ENV PATH="/app/.venv/bin:${PATH}"
+# ENV LD_LIBRARY_PATH="/usr/lib:${LD_LIBRARY_PATH}" # Keep commented for now
+
+# Ensure python scripts and venv executables are executable
+RUN chmod +x /app/parse_pdf.py /app/parse_docx.py  && \
+    find /app/.venv/bin -type f -exec chmod +x {} \;
+
+# Ensure Go binaries are executable
+RUN chmod +x /app/opencoze /app/proxy
+
+EXPOSE 8888
+
+# Use a script to start both applications
+COPY backend/script/bootstrap.sh /app/bootstrap.sh
+RUN chmod +x /app/bootstrap.sh
+
+CMD ["/app/bootstrap.sh"]