Merge pull request #15 from eccenca/feature/allowBlacklistTypeIRIs-CMEM-6667

Blacklist type IRIs  + extend documentation

Author: seebi

.copier-answers.yml

@@ -1,5 +1,5 @@
 # Changes here will be overwritten by Copier
-_commit: v7.3.0-22-g87d8a9b
+_commit: v8.2.0
 _src_path: gh:eccenca/cmem-plugin-template
 author_mail: cmempy-developer@eccenca.com
 author_name: eccenca GmbH

.github/workflows/check.yml

@@ -22,6 +22,13 @@ jobs:
       - name: Check out repository
         uses: actions/checkout@v5
 
+      - name: Cache Trivy DB
+        id: cache-trivydb
+        uses: actions/cache@v4
+        with:
+          path: .trivycache
+          key: ${{ runner.os }}-trivydb
+
       - name: Install Task
         uses: arduino/setup-task@v2
 
@@ -61,9 +68,13 @@ jobs:
         run: |
           task check:deptry
 
-      - name: safety
+      - name: trivy
+        env:
+          TRIVY_NO_PROGRESS: "true"
+          TRIVY_CACHE_DIR: ".trivycache/"
+          TRIVY_DISABLE_VEX_NOTICE: "true"
         run: |
-          task check:safety
+          task check:trivy
 
       - name: Publish Test Report in Action
         uses: mikepenz/action-junit-report@v4

.gitlab-ci.yml

@@ -60,17 +60,24 @@ deptry:
   script:
     - task check:deptry
 
-safety:
+trivy:
   stage: test
+  variables:
+    TRIVY_NO_PROGRESS: "true"
+    TRIVY_CACHE_DIR: ".trivycache/"
+    TRIVY_DISABLE_VEX_NOTICE: "true"
   script:
-    - task check:safety
+    - task check:trivy
+  cache:
+    paths:
+      - .trivycache/
 
 build:
   stage: build
   needs:
     - mypy
     - pytest
-    - safety
+    - trivy
     - deptry
   script:
     - task build

.pre-commit-config.yaml

@@ -1,4 +1,7 @@
 ---
+default_language_version:
+  python: python3.13
+
 repos:
   - repo: local
     hooks:
@@ -36,3 +39,9 @@ repos:
         stages: [post-checkout, post-merge]
         always_run: true
 
+      - id: trivy
+        name: check:trivy
+        description: run trivy to scan for vulnerabilities
+        entry: task check:trivy
+        language: python
+        pass_filenames: false

.trivyignore

@@ -0,0 +1,4 @@
+# .trivyignore
+
+# ignore 51358 safety - dev dependency only
+CVE-2022-39280

CHANGELOG.md

@@ -4,6 +4,12 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](http://keepachangelog.com/) and this project adheres to [Semantic Versioning](https://semver.org/)
 
+## [Unreleased]
+
+### Added
+
+- Parameter to ignore specific type IRIs (blacklisting)
+
 ## [4.2.0] 2025-10-20
 
 ### Changed

Taskfile.yaml

@@ -112,7 +112,7 @@ tasks:
       - task: check:ruff
       - task: check:mypy
       - task: check:deptry
-      - task: check:safety
+      - task: check:trivy
 
   check:pytest:
     desc: Run unit and integration tests
@@ -154,12 +154,16 @@ tasks:
     vars:
       JUNIT_FILE: ./{{.DIST_DIR}}/junit-mypy.xml
 
-  check:safety:
-    desc: Complain about vulnerabilities in dependencies
+  check:trivy:
+    desc: Scan for vulnerabilities using Trivy
     <<: *preparation
     cmds:
-      # ignore 51358 safety - dev dependency only
-      - poetry run safety check -i 51358
+      - >
+        poetry run trivy fs
+        --include-dev-deps
+        --scanners vuln
+        --exit-code 1
+        .
 
   check:deptry:
     desc: Complain about unused or missing dependencies

cmem_plugin_shapes/doc/__init__.py

@@ -32,8 +32,6 @@
 from rdflib import DCTERMS, RDF, RDFS, SH, XSD, Graph, Literal, Namespace, URIRef
 from rdflib.namespace import split_uri
 
-from cmem_plugin_shapes.doc import SHAPES_DOC
-
 from . import __path__
 
 SHUI = Namespace("https://vocab.eccenca.com/shui/")
@@ -73,7 +71,65 @@ def str2bool(value: str) -> bool:
     label=PLUGIN_LABEL,
     icon=Icon(file_name="shapes.svg", package=__package__),
     description="Generate SHACL node and property shapes from a data graph",
-    documentation=SHAPES_DOC,
+    documentation="""This workflow task generates SHACL (Shapes Constraint Language)
+node and property shapes by analyzing instance data from a knowledge graph. The generated
+shapes describe the structure and properties of the classes used in the data graph.
+
+## Usage
+
+The plugin analyzes an input data graph and creates:
+
+- **Node shapes**: One for each class (`rdf:type`) used in the data graph
+- **Property shapes**: For all properties associated with each class, including:
+  - Regular object properties (subject → object relationships)
+  - Inverse object properties (object ← subject relationships, marked with ← prefix)
+  - Datatype properties (literal values)
+
+## Output
+
+The generated shapes are written to a shape catalog graph with:
+
+- Unique URIs based on UUIDs (UUID5 derived from class/property IRIs)
+- Human-readable labels and names (using namespace prefixes when available)
+- Metadata including source data graph reference and timestamps
+- Optional plugin provenance information (see advanced options)
+
+## Example
+
+Given a data graph with:
+
+``` turtle
+ex:Person123 a ex:Person ;
+    ex:name "John" ;
+    ex:knows ex:Person456 .
+```
+
+The plugin generates:
+
+- A node shape for `ex:Person` with `sh:targetClass ex:Person`
+
+``` turtle
+graph:90ee6e27-59b1-5ac8-9d7a-116c60c6791a a sh:NodeShape ;
+  rdfs:label "Person (ex:)"@en ;
+  sh:name "Person (ex:)"@en ;
+  sh:property
+    graph:0fcf371d-f99a-5eeb-ab50-6e6b5fbb0e06 ,
+    graph:dd5c6728-75a2-5215-8a5d-f9cd4077aaea ;
+  sh:targetClass ex:Person .
+```
+
+- Property shapes for `ex:name` (datatype property) and `ex:knows` (object property)
+
+``` turtle
+graph:0fcf371d-f99a-5eeb-ab50-6e6b5fbb0e06 a sh:PropertyShape ;
+  rdfs:label "knows (ex:)"@en ;
+  sh:name "knows (ex:)"@en ;
+  sh:nodeKind sh:IRI ;
+  sh:path ex:knows ;
+  shui:showAlways true .
+```
+
+""",
     parameters=[
         PluginParameter(
             param_type=GraphParameterType(allow_only_autocompleted_values=False),
@@ -135,6 +191,13 @@ def str2bool(value: str) -> bool:
             description="Provide the list of properties (as IRIs) to ignore.",
             advanced=True,
         ),
+        PluginParameter(
+            param_type=MultilineStringParameterType(),
+            name="ignore_types",
+            label="Types to ignore",
+            description="Provide the list of types (as IRIs) to ignore.",
+            advanced=True,
+        ),
         PluginParameter(
             param_type=BoolParameterType(),
             name="plugin_provenance",
@@ -156,6 +219,7 @@ def __init__(  # noqa: PLR0913
         import_shapes: bool = False,
         prefix_cc: bool = False,
         ignore_properties: str = "http://www.w3.org/1999/02/22-rdf-syntax-ns#type",
+        ignore_types: str = "",
         plugin_provenance: bool = False,
     ) -> None:
         if not validators.url(data_graph_iri):
@@ -191,6 +255,12 @@ def __init__(  # noqa: PLR0913
                 raise ValueError(f"Invalid property IRI ({_}) in parameter 'Properties to ignore'")
             self.ignore_properties.append(_)
 
+        self.ignore_types = []
+        for _ in filter(None, ignore_types.split("\n")):
+            if not validators.url(_):
+                raise ValueError(f"Invalid type IRI ({_}) in parameter 'Types to ignore'")
+            self.ignore_types.append(_)
+
         self.plugin_provenance = plugin_provenance
 
         self.shapes_count = 0
@@ -296,6 +366,7 @@ def get_class_dict(self) -> dict:
                 ?subject a ?class .
                 ?subject ?property ?object .
                 {self.iri_list_to_filter(self.ignore_properties)}
+                {self.iri_list_to_filter(self.ignore_types, name="class")}
                 BIND(isLiteral(?object) AS ?data)
                 BIND("false" AS ?inverse)
             }}
@@ -304,6 +375,7 @@ def get_class_dict(self) -> dict:
                 ?object a ?class .
                 ?subject ?property ?object .
                 {self.iri_list_to_filter(self.ignore_properties)}
+                {self.iri_list_to_filter(self.ignore_types, name="class")}
                 BIND("false" AS ?data)
                 BIND("true" AS ?inverse)
             }}