Merge branch 'main' into dev-guide

.github/workflows/docker-publish.yml

@@ -0,0 +1,73 @@
+name: Upload Docker Image
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+on:
+  push:
+    # Publish semver tags as releases.
+    tags: [ 'v*.*.*' ]
+
+env:
+  # Use docker.io for Docker Hub if empty
+  REGISTRY: docker.io
+  # github.repository as <account>/<repo>
+  IMAGE_NAME: byaidu/pdf2zh
+
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+      # This is used to complete the identity challenge
+      # with sigstore/fulcio when running outside of PRs.
+      id-token: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      # Install the cosign tool except on PR
+      # https://github.com/sigstore/cosign-installer
+
+      # Set up BuildKit Docker container builder to be able to build
+      # multi-platform images and export cache
+      # https://github.com/docker/setup-buildx-action
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@f95db51fddba0c2d1ec667646a06c2ce06100226 # v3.0.0
+
+      # Login against a Docker registry except on PR
+      # https://github.com/docker/login-action
+      - name: Log into registry ${{ env.REGISTRY }}
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@343f7c4344506bcbf9b4de18042ae17996df046d # v3.0.0
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      # Extract metadata (tags, labels) for Docker
+      # https://github.com/docker/metadata-action
+      - name: Extract Docker metadata
+        id: meta
+        uses: docker/metadata-action@96383f45573cb7f253c731d3b3ab81c87ef81934 # v5.0.0
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      # Build and push Docker image with Buildx (don't push on PR)
+      # https://github.com/docker/build-push-action
+      - name: Build and push Docker image
+        id: build-and-push
+        uses: docker/build-push-action@0565240e2d4ab88bba5387d719585280857ece09 # v5.0.0
+        with:
+          context: .
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

.github/workflows/python-publish.yml

@@ -0,0 +1,37 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python#publishing-to-package-registries
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+name: Upload Python Package
+
+on:
+  push:
+    # Publish semver tags as releases.
+    tags: [ 'v*.*.*' ]
+
+permissions:
+  contents: read
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install build
+    - name: Build package
+      run: python -m build
+    - name: Publish package
+      uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29

pdf2zh/gui.py

@@ -236,6 +236,7 @@ with gr.Blocks(
         background-color: #E8F3FF !important;
         transition: background-color 0.2s ease-in;
     }
+
     .progress-bar-wrap {
     border-radius: 8px !important;
     }

pdf2zh/high_level.py

@@ -164,7 +164,7 @@ def extract_text_to_fp(
         caching=not disable_caching,
     ), total=total_pages, position=0):
         pix = doc_en[page.pageno].get_pixmap()
-        image = np.fromstring(pix.samples, np.uint8).reshape(pix.height, pix.width, 3)
+        image = np.fromstring(pix.samples, np.uint8).reshape(pix.height, pix.width, 3)[:, :, ::-1]
         page_layout=model.predict(
             image,
             imgsz=int(pix.height/32)*32,