9f97f3abbe
CI - Python Bindings / sdist (push) Failing after 1s
CI - Python Bindings / Build x86_64-unknown-linux-musl (push) Failing after 1s
CI / fmt (push) Failing after 1s
E2E Output Validation / compare-outputs (push) Failing after 1s
Sync Docs to Developer Hub / sync-docs (push) Failing after 1s
CI - Python Bindings / Build x86_64-unknown-linux-gnu (push) Failing after 1s
CI - WASM Bindings / Build WASM (push) Failing after 0s
CI / clippy (push) Failing after 1s
CI / build-and-test (ubuntu-latest) (push) Failing after 0s
CI - WASM Bindings / Edge runtime PDF parse test (push) Has been skipped
CI - WASM Bindings / Browser PDF parse test (push) Has been skipped
Deploy Demo to GitHub Pages / deploy (push) Failing after 1s
CI / build-docker-image (push) Failing after 3s
CI - Node Bindings / Build darwin-x64 (push) Has been cancelled
CI - Node Bindings / Test win32-x64-msvc (push) Has been cancelled
CI - Node Bindings / Build linux-arm64-gnu (push) Has been cancelled
CI - Node Bindings / Build linux-x64-gnu (push) Has been cancelled
CI - Node Bindings / Build linux-x64-musl (push) Has been cancelled
CI - Node Bindings / Build win32-arm64-msvc (push) Has been cancelled
CI - Node Bindings / Build win32-x64-msvc (push) Has been cancelled
CI - Node Bindings / Test darwin-arm64 (push) Has been cancelled
CI - Node Bindings / Test darwin-x64 (push) Has been cancelled
CI - Node Bindings / Test linux-x64-gnu (push) Has been cancelled
CI - Node Bindings / Test linux-x64-musl (push) Has been cancelled
CI - Node Bindings / Test win32-arm64-msvc (push) Has been cancelled
CI - Python Bindings / Build aarch64-pc-windows-msvc (push) Has been cancelled
CI - Python Bindings / Build x86_64-pc-windows-msvc (push) Has been cancelled
CI - Python Bindings / Build x86_64-apple-darwin (push) Has been cancelled
CI - Python Bindings / Build aarch64-apple-darwin (push) Has been cancelled
CI - Python Bindings / Build aarch64-unknown-linux-gnu (push) Has been cancelled
CI - Node Bindings / Build darwin-arm64 (push) Has been cancelled
CI - Python Bindings / Test x86_64-apple-darwin (push) Has been cancelled
CI - Python Bindings / Test aarch64-apple-darwin (push) Has been cancelled
CI - Python Bindings / Test x86_64-unknown-linux-gnu (push) Has been cancelled
CI - Python Bindings / Test x86_64-unknown-linux-musl (push) Has been cancelled
CI - Python Bindings / Test aarch64-pc-windows-msvc (push) Has been cancelled
CI - Python Bindings / Test x86_64-pc-windows-msvc (push) Has been cancelled
CI / build-and-test (macos-26-intel) (push) Has been cancelled
CI / build-and-test (macos-latest) (push) Has been cancelled
CI / build-and-test (windows-11-arm) (push) Has been cancelled
CI / build-and-test (windows-latest) (push) Has been cancelled
E2E Output Validation / upload-dataset (push) Has been cancelled
149 lines
4.7 KiB
YAML
149 lines
4.7 KiB
YAML
name: E2E Output Validation
|
|
|
|
on:
|
|
pull_request:
|
|
branches: [main]
|
|
push:
|
|
branches: [main]
|
|
|
|
# For PRs, we need write permissions to add labels
|
|
permissions:
|
|
contents: read
|
|
pull-requests: write
|
|
|
|
jobs:
|
|
compare-outputs:
|
|
runs-on: ubuntu-latest
|
|
outputs:
|
|
has_changes: ${{ steps.compare.outputs.has_changes }}
|
|
|
|
steps:
|
|
- name: Checkout repository
|
|
uses: actions/checkout@v4
|
|
|
|
- name: Install system dependencies
|
|
run: |
|
|
sudo apt-get update
|
|
sudo apt-get install -y libtesseract-dev libleptonica-dev \
|
|
tesseract-ocr libreoffice imagemagick ghostscript
|
|
|
|
- uses: actions/cache@v4
|
|
with:
|
|
path: |
|
|
~/.cargo/registry
|
|
~/.cargo/git
|
|
~/.cache/pdfium-rs
|
|
target
|
|
key: ${{ runner.os }}-cargo-e2e-${{ hashFiles('**/Cargo.lock') }}
|
|
|
|
- name: Build
|
|
run: cargo build --release
|
|
|
|
- name: Download from HuggingFace
|
|
env:
|
|
HF_TOKEN: ${{ secrets.HF_TOKEN }}
|
|
run: |
|
|
pip install huggingface_hub
|
|
hf download 'llamaindex/liteparse_cicd_data' --local-dir expected-dataset --repo-type dataset
|
|
|
|
- name: Compare outputs
|
|
id: compare
|
|
run: ./scripts/compare-outputs.sh expected-dataset
|
|
|
|
- name: Upload comparison results
|
|
if: always()
|
|
uses: actions/upload-artifact@v4
|
|
with:
|
|
name: comparison-results
|
|
path: comparison-output.txt
|
|
|
|
- name: Add label for changed outputs (PR only)
|
|
if: github.event_name == 'pull_request' && steps.compare.outputs.has_changes == 'true'
|
|
uses: actions/github-script@v7
|
|
with:
|
|
script: |
|
|
github.rest.issues.addLabels({
|
|
owner: context.repo.owner,
|
|
repo: context.repo.repo,
|
|
issue_number: context.issue.number,
|
|
labels: ['output-changed']
|
|
})
|
|
|
|
- name: Check for approval label (PR only)
|
|
id: check-approved
|
|
if: github.event_name == 'pull_request' && steps.compare.outputs.has_changes == 'true'
|
|
uses: actions/github-script@v7
|
|
with:
|
|
script: |
|
|
const { data: labels } = await github.rest.issues.listLabelsOnIssue({
|
|
owner: context.repo.owner,
|
|
repo: context.repo.repo,
|
|
issue_number: context.issue.number
|
|
});
|
|
const hasApproval = labels.some(label => label.name === 'output-approved');
|
|
core.setOutput('has_approval', hasApproval.toString());
|
|
console.log(`Has output-approved label: ${hasApproval}`);
|
|
|
|
- name: Require approval for output changes
|
|
if: steps.compare.outputs.has_changes == 'true' && github.event_name == 'pull_request' && steps.check-approved.outputs.has_approval != 'true'
|
|
run: |
|
|
echo "::warning::This PR changes liteparse output. Please review the comparison results."
|
|
echo ""
|
|
echo "To approve these changes:"
|
|
echo "1. Review the comparison output in the artifacts"
|
|
echo "2. Add the 'output-approved' label to this PR"
|
|
echo "3. Re-run this workflow"
|
|
exit 1
|
|
|
|
# This job only runs on main branch after merge when outputs changed
|
|
upload-dataset:
|
|
runs-on: ubuntu-latest
|
|
needs: compare-outputs
|
|
if: github.event_name == 'push' && github.ref == 'refs/heads/main' && needs.compare-outputs.outputs.has_changes == 'true'
|
|
|
|
steps:
|
|
- name: Checkout repository
|
|
uses: actions/checkout@v4
|
|
|
|
- name: Install system dependencies
|
|
run: |
|
|
sudo apt-get update
|
|
sudo apt-get install -y libtesseract-dev libleptonica-dev \
|
|
tesseract-ocr libreoffice imagemagick ghostscript
|
|
|
|
- uses: actions/cache@v4
|
|
with:
|
|
path: |
|
|
~/.cargo/registry
|
|
~/.cargo/git
|
|
~/.cache/pdfium-rs
|
|
target
|
|
key: ${{ runner.os }}-cargo-e2e-${{ hashFiles('**/Cargo.lock') }}
|
|
|
|
- name: Build
|
|
run: cargo build --release
|
|
|
|
- name: Setup Python
|
|
uses: actions/setup-python@v5
|
|
with:
|
|
python-version: "3.11"
|
|
|
|
- name: Install dependencies
|
|
run: pip install huggingface_hub
|
|
|
|
- name: Download existing dataset from HuggingFace
|
|
env:
|
|
HF_TOKEN: ${{ secrets.HF_TOKEN }}
|
|
run: |
|
|
hf download 'llamaindex/liteparse_cicd_data' --local-dir expected-dataset --repo-type dataset
|
|
|
|
- name: Generate and upload dataset
|
|
env:
|
|
HF_TOKEN: ${{ secrets.HF_TOKEN }}
|
|
run: |
|
|
if [ -z "$HF_TOKEN" ]; then
|
|
echo "Warning: HF_TOKEN not set, skipping upload"
|
|
exit 0
|
|
fi
|
|
./scripts/upload-dataset.sh expected-dataset ${{ vars.HF_DATASET_REPO || 'llamaindex/liteparse_cicd_data' }}
|