mule-discovery 1.0.0__tar.gz

mule_discovery-1.0.0/.claude/settings.local.json

@@ -0,0 +1,18 @@
+{
+  "permissions": {
+    "allow": [
+      "Bash(python -m pytest --cov=mule_discovery --cov-report=term-missing --no-header -q)",
+      "Bash(/Users/stephen.brown/projects/sandbox-workspaces/mule-discovery-tools/mule-discovery/.venv/bin/python3 -m pytest --cov=mule_discovery --cov-report=term-missing --no-header -q)",
+      "Bash(.venv/bin/python -m pytest --co -q)",
+      "Bash(.venv/bin/python -m pytest --cov=mule_discovery --cov-report=term-missing --no-header -q 2>&1)",
+      "Bash(.venv/bin/python -m pytest --cov=mule_discovery --cov-report=term-missing:skip-covered --no-header -q)",
+      "Bash(find /Users/stephen.brown/projects/sandbox-workspaces/single-app-usecase/sys-sap-plants-maintenance-api -name *.wsdl -o -name *.raml -o -name *.swagger*)",
+      "Bash(find /Users/stephen.brown/projects/sandbox-workspaces/single-app-usecase/dfi-el-agama -name *.wsdl -o -name *.raml -o -name *.swagger*)",
+      "Bash(find /Users/stephen.brown/projects/sandbox-workspaces/single-app-usecase/dfi-el-agama/src/main/resources -type f -name *.dwl)",
+      "WebFetch(domain:github.com)",
+      "Bash(gh api:*)",
+      "Bash(make test:*)",
+      "Bash(uv sync:*)"
+    ]
+  }
+}

mule_discovery-1.0.0/.github/workflows/tests.yml

@@ -0,0 +1,27 @@
+name: Tests
+
+on:
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11", "3.12", "3.13"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+
+      - name: Set up Python ${{ matrix.python-version }}
+        run: uv python install ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: uv sync --extra dev
+
+      - name: Run tests
+        run: uv run --extra dev python -m pytest

mule_discovery-1.0.0/.gitignore

@@ -0,0 +1,35 @@
+# Python bytecode
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Distribution / packaging
+dist/
+build/
+*.egg-info/
+*.egg
+
+# Virtual environments
+.venv/
+venv/
+
+# Testing / coverage
+.pytest_cache/
+.coverage
+htmlcov/
+coverage.xml
+
+# IDEs
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+
+# OS files
+.DS_Store
+Thumbs.db
+
+# Environment variables
+.env
+.env.*

mule_discovery-1.0.0/Makefile

@@ -0,0 +1,52 @@
+.PHONY: test test-verbose test-cov test-quick install clean build publish publish-test
+
+## Install/sync dependencies
+install:
+	uv sync --extra dev
+
+## Run full test suite with coverage
+test:
+	uv run --extra dev python -m pytest
+
+## Run tests with verbose output
+test-verbose:
+	uv run --extra dev python -m pytest -v
+
+## Run tests without coverage (faster)
+test-quick:
+	uv run --extra dev python -m pytest --no-cov
+
+## Run tests and show detailed coverage report
+test-cov:
+	uv run --extra dev python -m pytest --cov-report=html
+	@echo "HTML report: htmlcov/index.html"
+
+## Run a specific test file (usage: make test-file F=tests/test_parsers/test_pom.py)
+test-file:
+	uv run --extra dev python -m pytest $(F) -v --no-cov
+
+## Run tests matching a keyword (usage: make test-k K=scoring)
+test-k:
+	uv run --extra dev python -m pytest -k "$(K)" -v --no-cov
+
+## Build distribution packages
+build: clean
+	uv build
+
+## Publish to PyPI
+publish: build
+	UV_PUBLISH_USERNAME=__token__ \
+	UV_PUBLISH_PASSWORD=$$(python3 -c "import configparser; c = configparser.ConfigParser(); c.read('$$HOME/.pypirc'); print(c['pypi']['password'])") \
+	uv publish
+
+## Publish to TestPyPI
+publish-test: build
+	UV_PUBLISH_USERNAME=__token__ \
+	UV_PUBLISH_PASSWORD=$$(python3 -c "import configparser; c = configparser.ConfigParser(); c.read('$$HOME/.pypirc'); print(c['testpypi']['password'])") \
+	uv publish --publish-url https://test.pypi.org/legacy/
+
+## Remove build artifacts and caches
+clean:
+	rm -rf dist build htmlcov .coverage .pytest_cache
+	find . -type d -name __pycache__ -exec rm -rf {} + 2>/dev/null || true
+	find . -type d -name "*.egg-info" -exec rm -rf {} + 2>/dev/null || true

mule_discovery-1.0.0/PKG-INFO

@@ -0,0 +1,236 @@
+Metadata-Version: 2.4
+Name: mule-discovery
+Version: 1.0.0
+Summary: Scan Mule applications for migration complexity assessment
+Project-URL: Homepage, https://github.com/KongHQ-CX/mule-discovery
+Author: Stephen Brown
+License-Expression: MIT
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.10
+Requires-Dist: pyyaml>=6.0
+Provides-Extra: anypoint
+Requires-Dist: anypoint-sdk>=0.2.0; extra == 'anypoint'
+Provides-Extra: dev
+Requires-Dist: pytest-cov>=4.0; extra == 'dev'
+Requires-Dist: pytest>=7.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# mule-discovery
+
+Scan Mule applications for migration complexity assessment.
+
+Parses Mule 4 (and 3) XML source files, POM dependencies, DataWeave scripts, and API specifications to produce a structured migration readiness report with complexity scoring.
+
+## Estate Analysis
+
+The output produced by `mule-discover` (JSON or YAML) can be fed into the [estate-analyzer](https://github.com/KongHQ-CX/kong-ps-agent-skills/tree/main/mule-analysis/estate-analyzer) agent skill to generate pre-sales migration reports. The estate-analyzer processes discovery output across your entire Mule application estate to produce complexity summaries, connector frequency analysis, PoC candidate recommendations, and migration sizing reports.
+
+## Quick Start (uv)
+
+No install required — just run from the project directory:
+
+```bash
+cd mule-discovery
+
+# Discover all Mule apps under a directory
+uv run mule-discover /path/to/apps --output-dir ./inventory
+
+# JSON output instead of YAML
+uv run mule-discover /path/to/apps --json --output-dir ./inventory
+```
+
+`uv run` reads `pyproject.toml`, resolves dependencies into an ephemeral environment, and runs the command. Nothing is installed globally.
+
+## Installation
+
+Install dependencies with uv:
+
+```bash
+uv sync
+```
+
+For development (adds pytest + coverage):
+
+```bash
+uv sync --extra dev
+```
+
+For Anypoint Platform integration (policy scanning):
+
+```bash
+uv sync --extra anypoint
+```
+
+Requires Python 3.10+.
+
+## CLI Tools
+
+### `mule-discover`
+
+Recursively find all Mule applications under a directory and produce migration complexity reports for each.
+
+```bash
+# Discover all apps, write YAML inventories (default) to ./inventory
+uv run mule-discover /path/to/apps --output-dir ./inventory
+
+# JSON output
+uv run mule-discover /path/to/apps --json --output-dir ./inventory
+
+# Suppress progress output
+uv run mule-discover /path/to/apps -o ./inventory -q
+
+# Custom complexity thresholds
+uv run mule-discover /path/to/apps --flow-low 8 --flow-medium 18 --flow-high 30
+```
+
+Each per-app report includes:
+- Flow inventory with complexity levels (LOW / MEDIUM / HIGH / VERY_HIGH)
+- DataWeave transformation analysis and classification
+- HTTP listener and scheduled job detection
+- Connector inventory with migration weights
+- API specification detection (OpenAPI, WSDL)
+- External dependency and out-of-scope item tracking
+- AWS service usage (SQS, S3, DynamoDB)
+- SOAP/WSDL service detection
+- Overall migration score (0–100) with recommendation (SIMPLE / MODERATE / COMPLEX / VERY_COMPLEX)
+
+### `mule-scan-policies`
+
+Scan Anypoint Platform for API policies on deployed applications. Requires the `anypoint` extra.
+
+```bash
+pip install -e ".[anypoint]"
+
+export ANYPOINT_CLIENT_ID=...
+export ANYPOINT_CLIENT_SECRET=...
+export ANYPOINT_ORG_ID=...
+export ANYPOINT_ENV_ID=...
+
+uv run mule-scan-policies
+uv run mule-scan-policies --format json
+```
+
+### `mule-download-policies`
+
+Download custom policies from Anypoint Exchange. Requires the `anypoint` extra.
+
+```bash
+export ANYPOINT_CLIENT_ID=...
+export ANYPOINT_CLIENT_SECRET=...
+export ANYPOINT_ORG_ID=...
+
+uv run mule-download-policies --output-dir ./custom_policies
+```
+
+## Complexity Scoring
+
+Each application receives a migration score from 0 to 100 (higher = simpler migration):
+
+| Score Range | Recommendation | Meaning |
+|---|---|---|
+| 75–100 | SMALL | Straightforward migration |
+| 50–74 | MEDIUM | Some complexity, manageable |
+| 25–49 | LARGE | Significant effort required |
+| 0–24 | XLARGE | Major rework needed |
+
+Deductions are applied across eight dimensions:
+
+| Dimension | Max Deduction |
+|---|---|
+| Flow complexity | 30 pts |
+| Transform complexity | 15 pts |
+| Risk / out-of-scope items | 20 pts |
+| Connector migration weight | 20 pts |
+| WSDL / SOAP services | 10 pts |
+| Scale (flow + component count) | 20 pts |
+| Pattern complexity (scatter-gather, choices, batch, parallel-foreach, retries) | 15 pts |
+| DataWeave volume | 15 pts |
+
+### Flow Complexity Thresholds
+
+Flows are classified by component count (configurable via CLI flags):
+
+| Components | Complexity |
+|---|---|
+| ≤ 6 | LOW |
+| 7–14 | MEDIUM |
+| 15–25 | HIGH |
+| > 25 | VERY_HIGH |
+
+### DataWeave Classification
+
+DataWeave transformations are classified by line count and function usage:
+
+| Classification | Criteria |
+|---|---|
+| simple_mapping | ≤ 5 lines, no complex functions |
+| field_level_logic | 6–20 lines, or uses routine functions (map, filter, pluck, etc.) |
+| business_logic | > 20 lines, or uses complex functions (reduce, groupBy, flatMap, etc.) |
+
+## Package Structure
+
+```
+src/mule_discovery/
+├── __init__.py                # Main discover_mule_app() orchestrator
+├── constants.py               # XML namespaces, element classifications, connector weights
+├── xml_helpers.py             # XML utility functions
+├── models/                    # Data models (dataclasses)
+│   ├── result.py              # DiscoveryResult (top-level container)
+│   ├── flows.py               # FlowInfo, BatchInfo, ChoiceInfo, ScatterGatherInfo, ...
+│   ├── connectors.py          # ConnectorInfo, SpringDependency
+│   ├── dataweave.py           # DataWeaveInfo
+│   ├── listeners.py           # HttpListenerInfo, ScheduledJobInfo
+│   ├── dependencies.py        # ExternalDependencyInfo, SourceFiles, OutOfScopeItem
+│   ├── schemas.py             # ApiSpecInfo (OpenAPI, WSDL)
+│   └── scoring.py             # ComplexityThresholds, ScoreResult
+├── parsers/                   # File IO → models
+│   ├── file_discovery.py      # find_mule_apps(), find_mule_xml_files()
+│   ├── mule_xml.py            # Mule XML parsing (flows, listeners, jobs)
+│   ├── pom.py                 # POM parsing (app name, version, connectors)
+│   ├── http_auth.py           # HTTP auth config extraction
+│   ├── dataweave.py           # DataWeave script parsing
+│   ├── soap.py                # SOAP/WSDL service detection
+│   ├── aws.py                 # AWS service detection (SQS, S3, DynamoDB)
+│   ├── openapi.py             # OpenAPI spec detection
+│   └── wsdl.py                # WSDL parsing utilities
+├── analysis/                  # Models → models (pure functions)
+│   ├── classification.py      # Flow type and source category constants
+│   ├── complexity.py          # Flow and DataWeave complexity assignment
+│   ├── patterns.py            # Pattern detection (async, scatter-gather, choice, ...)
+│   ├── scoring.py             # Migration score calculation (0–100)
+│   └── dependencies.py        # External dependency and out-of-scope extraction
+├── output/                    # Models → formatted strings
+│   ├── yaml_output.py         # YAML
+│   ├── json_output.py         # JSON
+│   └── text_output.py         # Human-readable text summary
+├── anypoint/                  # Anypoint Platform integration (optional)
+│   ├── policies.py            # Policy scanning
+│   └── exchange.py            # Custom policy download
+└── cli/                       # CLI entry points (thin wrappers)
+    ├── discover.py            # mule-discover
+    ├── scan_policies.py       # mule-scan-policies
+    └── download_policies.py   # mule-download-policies
+```
+
+### Design Principles
+
+- **No function does both IO and computation.** Parsers read files → return models. Analysis takes models → returns models. Output takes models → returns strings.
+- **All data models are plain dataclasses** with typed fields — no methods with side effects.
+- **All analysis functions are standalone** — no class methods, no inheritance.
+- **Each output format is a separate module.**
+
+## Testing
+
+```bash
+make test
+```
+
+Or directly:
+
+```bash
+uv run --extra dev python -m pytest
+```
+
+Coverage is enforced at 70% (branch coverage) via `pyproject.toml`.

mule_discovery-1.0.0/README.md

@@ -0,0 +1,217 @@
+# mule-discovery
+
+Scan Mule applications for migration complexity assessment.
+
+Parses Mule 4 (and 3) XML source files, POM dependencies, DataWeave scripts, and API specifications to produce a structured migration readiness report with complexity scoring.
+
+## Estate Analysis
+
+The output produced by `mule-discover` (JSON or YAML) can be fed into the [estate-analyzer](https://github.com/KongHQ-CX/kong-ps-agent-skills/tree/main/mule-analysis/estate-analyzer) agent skill to generate pre-sales migration reports. The estate-analyzer processes discovery output across your entire Mule application estate to produce complexity summaries, connector frequency analysis, PoC candidate recommendations, and migration sizing reports.
+
+## Quick Start (uv)
+
+No install required — just run from the project directory:
+
+```bash
+cd mule-discovery
+
+# Discover all Mule apps under a directory
+uv run mule-discover /path/to/apps --output-dir ./inventory
+
+# JSON output instead of YAML
+uv run mule-discover /path/to/apps --json --output-dir ./inventory
+```
+
+`uv run` reads `pyproject.toml`, resolves dependencies into an ephemeral environment, and runs the command. Nothing is installed globally.
+
+## Installation
+
+Install dependencies with uv:
+
+```bash
+uv sync
+```
+
+For development (adds pytest + coverage):
+
+```bash
+uv sync --extra dev
+```
+
+For Anypoint Platform integration (policy scanning):
+
+```bash
+uv sync --extra anypoint
+```
+
+Requires Python 3.10+.
+
+## CLI Tools
+
+### `mule-discover`
+
+Recursively find all Mule applications under a directory and produce migration complexity reports for each.
+
+```bash
+# Discover all apps, write YAML inventories (default) to ./inventory
+uv run mule-discover /path/to/apps --output-dir ./inventory
+
+# JSON output
+uv run mule-discover /path/to/apps --json --output-dir ./inventory
+
+# Suppress progress output
+uv run mule-discover /path/to/apps -o ./inventory -q
+
+# Custom complexity thresholds
+uv run mule-discover /path/to/apps --flow-low 8 --flow-medium 18 --flow-high 30
+```
+
+Each per-app report includes:
+- Flow inventory with complexity levels (LOW / MEDIUM / HIGH / VERY_HIGH)
+- DataWeave transformation analysis and classification
+- HTTP listener and scheduled job detection
+- Connector inventory with migration weights
+- API specification detection (OpenAPI, WSDL)
+- External dependency and out-of-scope item tracking
+- AWS service usage (SQS, S3, DynamoDB)
+- SOAP/WSDL service detection
+- Overall migration score (0–100) with recommendation (SIMPLE / MODERATE / COMPLEX / VERY_COMPLEX)
+
+### `mule-scan-policies`
+
+Scan Anypoint Platform for API policies on deployed applications. Requires the `anypoint` extra.
+
+```bash
+pip install -e ".[anypoint]"
+
+export ANYPOINT_CLIENT_ID=...
+export ANYPOINT_CLIENT_SECRET=...
+export ANYPOINT_ORG_ID=...
+export ANYPOINT_ENV_ID=...
+
+uv run mule-scan-policies
+uv run mule-scan-policies --format json
+```
+
+### `mule-download-policies`
+
+Download custom policies from Anypoint Exchange. Requires the `anypoint` extra.
+
+```bash
+export ANYPOINT_CLIENT_ID=...
+export ANYPOINT_CLIENT_SECRET=...
+export ANYPOINT_ORG_ID=...
+
+uv run mule-download-policies --output-dir ./custom_policies
+```
+
+## Complexity Scoring
+
+Each application receives a migration score from 0 to 100 (higher = simpler migration):
+
+| Score Range | Recommendation | Meaning |
+|---|---|---|
+| 75–100 | SMALL | Straightforward migration |
+| 50–74 | MEDIUM | Some complexity, manageable |
+| 25–49 | LARGE | Significant effort required |
+| 0–24 | XLARGE | Major rework needed |
+
+Deductions are applied across eight dimensions:
+
+| Dimension | Max Deduction |
+|---|---|
+| Flow complexity | 30 pts |
+| Transform complexity | 15 pts |
+| Risk / out-of-scope items | 20 pts |
+| Connector migration weight | 20 pts |
+| WSDL / SOAP services | 10 pts |
+| Scale (flow + component count) | 20 pts |
+| Pattern complexity (scatter-gather, choices, batch, parallel-foreach, retries) | 15 pts |
+| DataWeave volume | 15 pts |
+
+### Flow Complexity Thresholds
+
+Flows are classified by component count (configurable via CLI flags):
+
+| Components | Complexity |
+|---|---|
+| ≤ 6 | LOW |
+| 7–14 | MEDIUM |
+| 15–25 | HIGH |
+| > 25 | VERY_HIGH |
+
+### DataWeave Classification
+
+DataWeave transformations are classified by line count and function usage:
+
+| Classification | Criteria |
+|---|---|
+| simple_mapping | ≤ 5 lines, no complex functions |
+| field_level_logic | 6–20 lines, or uses routine functions (map, filter, pluck, etc.) |
+| business_logic | > 20 lines, or uses complex functions (reduce, groupBy, flatMap, etc.) |
+
+## Package Structure
+
+```
+src/mule_discovery/
+├── __init__.py                # Main discover_mule_app() orchestrator
+├── constants.py               # XML namespaces, element classifications, connector weights
+├── xml_helpers.py             # XML utility functions
+├── models/                    # Data models (dataclasses)
+│   ├── result.py              # DiscoveryResult (top-level container)
+│   ├── flows.py               # FlowInfo, BatchInfo, ChoiceInfo, ScatterGatherInfo, ...
+│   ├── connectors.py          # ConnectorInfo, SpringDependency
+│   ├── dataweave.py           # DataWeaveInfo
+│   ├── listeners.py           # HttpListenerInfo, ScheduledJobInfo
+│   ├── dependencies.py        # ExternalDependencyInfo, SourceFiles, OutOfScopeItem
+│   ├── schemas.py             # ApiSpecInfo (OpenAPI, WSDL)
+│   └── scoring.py             # ComplexityThresholds, ScoreResult
+├── parsers/                   # File IO → models
+│   ├── file_discovery.py      # find_mule_apps(), find_mule_xml_files()
+│   ├── mule_xml.py            # Mule XML parsing (flows, listeners, jobs)
+│   ├── pom.py                 # POM parsing (app name, version, connectors)
+│   ├── http_auth.py           # HTTP auth config extraction
+│   ├── dataweave.py           # DataWeave script parsing
+│   ├── soap.py                # SOAP/WSDL service detection
+│   ├── aws.py                 # AWS service detection (SQS, S3, DynamoDB)
+│   ├── openapi.py             # OpenAPI spec detection
+│   └── wsdl.py                # WSDL parsing utilities
+├── analysis/                  # Models → models (pure functions)
+│   ├── classification.py      # Flow type and source category constants
+│   ├── complexity.py          # Flow and DataWeave complexity assignment
+│   ├── patterns.py            # Pattern detection (async, scatter-gather, choice, ...)
+│   ├── scoring.py             # Migration score calculation (0–100)
+│   └── dependencies.py        # External dependency and out-of-scope extraction
+├── output/                    # Models → formatted strings
+│   ├── yaml_output.py         # YAML
+│   ├── json_output.py         # JSON
+│   └── text_output.py         # Human-readable text summary
+├── anypoint/                  # Anypoint Platform integration (optional)
+│   ├── policies.py            # Policy scanning
+│   └── exchange.py            # Custom policy download
+└── cli/                       # CLI entry points (thin wrappers)
+    ├── discover.py            # mule-discover
+    ├── scan_policies.py       # mule-scan-policies
+    └── download_policies.py   # mule-download-policies
+```
+
+### Design Principles
+
+- **No function does both IO and computation.** Parsers read files → return models. Analysis takes models → returns models. Output takes models → returns strings.
+- **All data models are plain dataclasses** with typed fields — no methods with side effects.
+- **All analysis functions are standalone** — no class methods, no inheritance.
+- **Each output format is a separate module.**
+
+## Testing
+
+```bash
+make test
+```
+
+Or directly:
+
+```bash
+uv run --extra dev python -m pytest
+```
+
+Coverage is enforced at 70% (branch coverage) via `pyproject.toml`.

mule_discovery-1.0.0/pyproject.toml

@@ -0,0 +1,53 @@
+[project]
+name = "mule-discovery"
+version = "1.0.0"
+description = "Scan Mule applications for migration complexity assessment"
+readme = "README.md"
+license = "MIT"
+requires-python = ">=3.10"
+authors = [{ name = "Stephen Brown" }]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    "pyyaml>=6.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/KongHQ-CX/mule-discovery"
+
+[project.optional-dependencies]
+anypoint = [
+    "anypoint-sdk>=0.2.0",
+]
+dev = [
+    "pytest>=7.0",
+    "pytest-cov>=4.0",
+]
+
+[project.scripts]
+mule-discover = "mule_discovery.cli.discover:main"
+mule-scan-policies = "mule_discovery.cli.scan_policies:main"
+mule-download-policies = "mule_discovery.cli.download_policies:main"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "--cov=mule_discovery --cov-report=term-missing --cov-fail-under=70"
+
+[tool.coverage.run]
+source = ["mule_discovery"]
+branch = true
+
+[tool.coverage.report]
+fail_under = 70
+show_missing = true
+exclude_lines = [
+    "if __name__ == .__main__.",
+    "pragma: no cover",
+]