feat: Edit Distance Wrapper Service (Text and Graphs)

.github/workflows/service-edit-distance-service.yml

@@ -0,0 +1,174 @@
+name: edit-distance-service
+
+on:
+  push:
+    branches: ["master"]
+    paths:
+      - "services/edit-distance-service/**"
+  pull_request:
+    branches: ["master"]
+    paths:
+      - "services/edit-distance-service/**"
+
+defaults:
+  run:
+    working-directory: services/edit-distance-service
+
+jobs:
+  lint:
+    name: Lint
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Cache dependencies
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('services/edit-distance-service/pyproject.toml') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-
+      - name: Install dependencies
+        run: |
+          pip install --upgrade pip
+          pip install -e ".[dev]"
+      - name: Ruff linting
+        run: make lint
+
+  test:
+    name: Test
+    runs-on: ubuntu-latest
+    needs: lint
+    steps:
+      - uses: actions/checkout@v4
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Cache dependencies
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('services/edit-distance-service/pyproject.toml') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-
+      - name: Install dependencies
+        run: |
+          pip install --upgrade pip
+          pip install -e ".[dev]"
+      - name: Run tests
+        run: pytest -v --tb=short
+      - name: Run smoke tests
+        run: |
+          set -e
+          # Start server in background
+          uvicorn src.main:app --host 0.0.0.0 --port 8000 &
+          SERVER_PID=$!
+
+          # Wait for server to be ready
+          for i in $(seq 1 30); do
+            if curl -s http://localhost:8000/health | grep -q '"status":"ok"'; then
+              echo "Server is ready"
+              break
+            fi
+            echo "Waiting for server... ($i/30)"
+            sleep 1
+          done
+
+          # Smoke test: health endpoint
+          echo "=== Health check ==="
+          curl -sf http://localhost:8000/health | python -c "import sys,json; d=json.load(sys.stdin); assert d['status']=='ok', f'Health failed: {d}'"
+          echo "Health: OK"
+
+          # Smoke test: text algorithms discovery
+          echo "=== Text algorithms ==="
+          curl -sf http://localhost:8000/v1/text/algorithms | python -c "import sys,json; d=json.load(sys.stdin); assert len(d)>0, 'No algorithms'; print(f'Found {len(d)} text algorithms')"
+
+          # Smoke test: GED algorithms discovery
+          echo "=== GED algorithms ==="
+          curl -sf http://localhost:8000/v1/graphs/algorithms | python -c "import sys,json; d=json.load(sys.stdin); assert len(d)>0, 'No GED algorithms'; print(f'Found {len(d)} GED algorithms')"
+
+          # Smoke test: Levenshtein compute
+          echo "=== Levenshtein compute ==="
+          curl -sf -X POST http://localhost:8000/v1/text/distance \
+            -H 'Content-Type: application/json' \
+            -d '{"algorithm":"levenshtein","params":{},"inputs":[{"id":"p1","a":"kitten","b":"sitting"}]}' \
+            | python -c "import sys,json; d=json.load(sys.stdin); assert d['algorithm']=='levenshtein'; assert len(d['results'])==1; print('Levenshtein: OK')"
+
+          # Smoke test: GED compute
+          echo "=== GED compute ==="
+          curl -sf -X POST http://localhost:8000/v1/graphs/distance \
+            -H 'Content-Type: application/json' \
+            -d '{"algorithm":"ged_astar","params":{"mode":"exact","timeout_ms":5000},"graphs":[{"id":"p1","g1":{"nodes":[{"id":"A"},{"id":"B"}],"edges":[{"source":"A","target":"B"}]},"g2":{"nodes":[{"id":"A"},{"id":"B"},{"id":"C"}],"edges":[{"source":"A","target":"B"},{"source":"B","target":"C"}]}}]}' \
+            | python -c "import sys,json; d=json.load(sys.stdin); assert d['algorithm']=='ged_astar'; assert len(d['results'])==1; print('GED compute: OK')"
+
+          echo "=== All smoke tests passed ==="
+
+          # Stop the server
+          kill $SERVER_PID 2>/dev/null || true
+          wait $SERVER_PID 2>/dev/null || true
+
+  generate-openapi:
+    name: Generate OpenAPI Spec
+    runs-on: ubuntu-latest
+    needs: test
+    steps:
+      - uses: actions/checkout@v4
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Cache dependencies
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('services/edit-distance-service/pyproject.toml') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-
+      - name: Install dependencies
+        run: |
+          pip install --upgrade pip
+          pip install -e ".[dev]"
+      - name: Generate OpenAPI spec
+        run: make generate-openapi
+      - name: Upload OpenAPI spec
+        uses: actions/upload-artifact@v4
+        with:
+          name: openapi-spec-edit-distance-service
+          path: services/edit-distance-service/edit-distance-service.openapi.json
+
+  build:
+    name: Build & Push Docker Image
+    runs-on: ubuntu-latest
+    needs: generate-openapi
+    if: github.event_name == 'push' && github.ref == 'refs/heads/master'
+    permissions:
+      contents: read
+      packages: write
+    steps:
+      - uses: actions/checkout@v4
+      - name: Log in to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Extract Docker metadata
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ghcr.io/${{ github.repository_owner }}/edit-distance-service
+          tags: |
+            type=sha,prefix=sha-
+            type=raw,value=latest
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          dockerfile: services/edit-distance-service/Dockerfile
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

services/edit-distance-service/.agent.md

@@ -0,0 +1,63 @@
+# Edit Distance Service
+
+## Location
+`/home/user/fernuni_job/ALADIN-Services/services/edit-distance-service/`
+
+## Architecture
+- **Language**: Python 3.11+ (FastAPI)
+- **Pattern**: Mirrors `noise-generation-service` (Rust/Axum) in Python
+- **Framework**: FastAPI with uvicorn
+- **CLI**: Click-based (src/cli.py) + run_cli() in main.py
+- **OpenAPI**: Auto-generated via FastAPI's get_openapi()
+
+## API Endpoints
+### Text ED (Part A)
+- `GET /v1/text/algorithms` — Discovery
+- `POST /v1/text/distance` — Compute (synchronous)
+
+### Graph ED (Part B)
+- `GET /v1/graphs/algorithms` — Discovery
+- `POST /v1/graphs/distance` — Compute (synchronous, returns 200 with result inline)
+	(Note: GET/DELETE by result id are not exposed; results are returned inline by POST.)
+
+## Libraries
+### Text ED (15 algorithm families)
+- **Tier 1** (87%): RapidFuzz + textdistance + jellyfish
+- **Tier 2** (100%): + edlib + diff-match-patch
+
+### Graph ED (10 algorithm families)
+- **Tier 1** (80%): NetworkX + GEDLIB (via gedlibpy)
+- **Tier 2** (100%): + GMatch4py
+
+## Key Files
+- `src/main.py` — FastAPI app with all routes
+- `src/models.py` — Pydantic models (request/response schemas):
+  - `InputPair(id, a, b)` / `InputPhonetic(id, text)` — text input types
+  - `GraphRef(nodes, edges, format, links, matrix, node_labels)` — graph input (3 formats)
+  - `GraphPair(id, g1, g2)` — a pair of GraphRefs
+  - `TextCompareRequest(inputs: list[InputPair | InputPhonetic], ...)` — typed union
+  - `GedComputeRequest(graphs: list[GraphPair], ...)` — typed GraphPair
+- `src/text/__init__.py` — Text ED implementations (dispatcher pattern)
+- `src/graph/__init__.py` — Graph ED implementations (dispatcher pattern); `_graph_ref_to_nx()` handles 3 formats: default (nodes+edges), `node_link` (networkx JSON), `adjacency_matrix`
+- `src/cli.py` — Click CLI (list, compare, serve, openapi commands)
+- `tests/test_text_compare.py` — Unit tests for text algorithms
+- `tests/test_graph_compare.py` — Unit tests for graph algorithms
+- `tests/test_integration.py` — FastAPI TestClient integration tests (incl. adjacency_matrix + node_link format tests)
+- `tests/test_smoke.sh` — Bash smoke test script
+
+## Build/Deploy
+- `make prep` — pip install -e ".[dev]"
+- `make test` — pytest -v
+- `make start` — uvicorn with --reload
+- `make generate-openapi` — generates edit-distance-service.openapi.json
+- `make docker-build` — multi-stage Docker build
+- `Dockerfile` — Multi-stage (builder + runtime)
+- `docker-compose.dev.yml` — Dev with volume mount
+- `docker-compose.prod.yml` — Production
+
+## Design Patterns
+- Discriminated union request body (algorithm field as discriminator)
+- Backend is explicit (different libs can produce different results)
+- Discovery endpoint exposes full catalog at runtime
+- Response is discriminated union on result_type
+- All compute endpoints accept arrays (batching)

services/edit-distance-service/.dockerignore

@@ -0,0 +1,23 @@
+# Git
+.git
+.gitignore
+
+# Docker
+docker-compose*.yml
+Dockerfile
+README.md
+
+# Build artifacts
+*.openapi.json
+
+# Python
+__pycache__/
+*.pyc
+*.pyo
+.venv
+venv
+*.egg-info/
+.pytest_cache/
+
+# Node (monorepo noise)
+node_modules/

services/edit-distance-service/.gitignore

@@ -0,0 +1,10 @@
+__pycache__/
+*.py[cod]
+*$py.class
+*.egg-info/
+.venv/
+venv/
+env/
+*.openapi.json
+dist/
+build/

services/edit-distance-service/Dockerfile

@@ -0,0 +1,53 @@
+# Stage 1: Build
+FROM python:3.12-slim AS builder
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    gcc \
+    g++ \
+    python3-dev \
+    libpython3.12-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+COPY services/edit-distance-service/pyproject.toml .
+COPY services/edit-distance-service/src/ src/
+
+# Install base dependencies and build wheel
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir build && \
+    python -m build --wheel && \
+    pip install --no-cache-dir dist/*.whl && \
+    rm -rf dist
+
+# Install optional GED library (gedlibpy) from monorepo third_party/
+# (not on PyPI — ships with the ALADIN monorepo)
+COPY third_party/gedlibpy/ /tmp/third_party/gedlibpy/
+RUN pip install --no-cache-dir Cython && \
+    cd /tmp/third_party/gedlibpy && \
+    python setup.py build_ext --inplace && \
+    pip install --no-cache-dir . && \
+    rm -rf /tmp/third_party
+
+# Install optional GED library (gmatch4py) from PyPI
+# (ged_hausdorff, ged_greedy, ged_heuristic backends)
+RUN pip install --no-cache-dir gmatch4py
+
+# Stage 2: Runtime
+FROM python:3.12-slim
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libssl3 \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+COPY --from=builder /usr/local/lib/python3.12/site-packages /usr/local/lib/python3.12/site-packages
+COPY --from=builder /usr/local/bin /usr/local/bin
+COPY services/edit-distance-service/src/ src/
+COPY services/edit-distance-service/pyproject.toml .
+
+# Set the user
+USER nobody
+
+# Start the service
+CMD ["uvicorn", "src.main:app", "--host", "0.0.0.0", "--port", "8000"]

services/edit-distance-service/Makefile

@@ -0,0 +1,34 @@
+.PHONY: prep build test lint start clean docker-build generate-openapi dev prod
+
+prep:
+	pip install -e ".[dev]"
+
+build:
+	pip install -e ".[dev]"
+
+test:
+	pytest -v
+
+lint:
+	ruff check src/
+	ruff format --check src/
+
+start:
+	uvicorn src.main:app --host 0.0.0.0 --port 8000 --reload
+
+clean:
+	rm -rf __pycache__ src/__pycache__ src/**/__pycache__
+	rm -rf .venv venv
+	rm -rf *.egg-info
+
+generate-openapi:
+	python -c "from src.main import app; import json; from fastapi.openapi.utils import get_openapi; spec = get_openapi(title=app.title, version=app.version, openapi_version=app.openapi_version, description=app.description, routes=app.routes); print(json.dumps(spec, indent=2))" > edit-distance-service.openapi.json
+
+docker-build:
+	docker build -f Dockerfile -t edit-distance-service ../..
+
+dev:
+	docker compose -f docker-compose.dev.yml up --build
+
+prod:
+	docker compose -f docker-compose.prod.yml up --build