refactor: improve parsing of SHACL nodes

.github/workflows/testing.yaml

@@ -28,30 +28,29 @@ env:
     VENV_PATH: .venv
 
 jobs:
-    # TODO: refactor this using poetry
     # Verifies pep8, pyflakes and circular complexity
-    # flake8:
-    #     name: Lint Python Code (Flake8) (python ${{ matrix.python-version }})
-    #     runs-on: ubuntu-latest
-    #     strategy:
-    #         matrix:
-    #             python-version: ["3.11"]
-    #     steps:
-    #         # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
-    #         - uses: actions/checkout@v4
-    #         - name: Set up Python v${{ matrix.python-version }}
-    #           uses: actions/setup-python@v5
-    #           with:
-    #               python-version: ${{ matrix.python-version }}
-    #         - name: Install flake8
-    #           run: pip install flake8
-    #         - name: Run checks
-    #           run: flake8 -v .
+    flake8:
+        name: Lint Python Code (Flake8) (python ${{ matrix.python-version }})
+        runs-on: ubuntu-latest
+        strategy:
+            matrix:
+                python-version: ["3.11"]
+        steps:
+            # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+            - uses: actions/checkout@v4
+            - name: Set up Python v${{ matrix.python-version }}
+              uses: actions/setup-python@v5
+              with:
+                  python-version: ${{ matrix.python-version }}
+            - name: Install flake8
+              run: pip install flake8
+            - name: Run checks
+              run: flake8 -v rocrate_validator tests
 
     test:
         name: "Tests"
         runs-on: ubuntu-latest
-        # needs: [flake8]
+        needs: [flake8]
         steps:
             - name: Checkout
               uses: actions/checkout@v4

rocrate_validator/cli/commands/errors.py

@@ -50,7 +50,8 @@ def handle_error(e: Exception, console: Console) -> None:
         if logger.isEnabledFor(logging.DEBUG):
             console.print_exception()
         console.print(textwrap.indent("This error may be due to a bug.\n"
-                                      "Please report it to the issue tracker along with the following stack trace:\n", ' ' * 9))
+                                      "Please report it to the issue tracker "
+                                      "along with the following stack trace:\n", ' ' * 9))
         console.print_exception()
 
     console.print(f"\n\n[bold][[red]ERROR[/red]] {error_message}[/bold]\n", style="white")

rocrate_validator/cli/commands/profiles.py

@@ -263,7 +263,8 @@ def __verbose_describe_profile__(profile):
             # Uncomment the following lines to show the overridden checks
             # if check.overridden_by:
             #     severity_color = get_severity_color(check.overridden_by.severity)
-            #     override = f"[overridden by: [bold][magenta]{check.overridden_by.requirement.profile.identifier}[/magenta] "\
+            #     override = "[overridden by: " \
+            #         f"[bold][magenta]{check.overridden_by.requirement.profile.identifier}[/magenta] "\
             #         f"[{severity_color}]{check.overridden_by.relative_identifier}[/{severity_color}][/bold]]"
             if check.override:
                 severity_color = get_severity_color(check.override.severity)

rocrate_validator/cli/commands/validate.py

@@ -97,7 +97,7 @@ def get_single_char(console: Optional[Console] = None, end: str = "\n",
                 console.print(char, end=end if choices and char in choices else "")
         if choices and char not in choices:
             if console:
-                console.print(f" [bold red]INVALID CHOICE[/bold red]", end=end)
+                console.print(" [bold red]INVALID CHOICE[/bold red]", end=end)
     return char
 
 
@@ -275,11 +275,24 @@ def validate(ctx,
                 logger.info("Auto-detection of the profiles to use for validation is disabled")
 
             # Prompt the user to select the profile to use for validation if the interactive mode is enabled
-            # and no profile is autodetected or multiple profiles are detected
-            if interactive and (not candidate_profiles or len(candidate_profiles) == 0 or len(candidate_profiles) == len(available_profiles)):
+            # and no profile is auto-detected or multiple profiles are detected
+            if interactive and (
+                not candidate_profiles or
+                len(candidate_profiles) == 0 or
+                len(candidate_profiles) == len(available_profiles)
+            ):
                 # Define the list of choices
-                console.print(Padding(Rule("[bold yellow]WARNING: [/bold yellow]"
-                                           "[bold]Unable to automatically detect the profile to use for validation[/bold]\n", align="center", style="bold yellow"), (2, 2, 0, 2)))
+                console.print(
+                    Padding(
+                        Rule(
+                            "[bold yellow]WARNING: [/bold yellow]"
+                            "[bold]Unable to automatically detect the profile to use for validation[/bold]\n",
+                            align="center",
+                            style="bold yellow"
+                        ),
+                        (2, 2, 0, 2)
+                    )
+                )
                 selected_options = multiple_choice(console, available_profiles)
                 profile_identifier = [available_profiles[int(
                     selected_option)].identifier for selected_option in selected_options]
@@ -331,7 +344,10 @@ def validate(ctx,
                 verbose_choice = "n"
                 if interactive and not verbose and enable_pager:
                     verbose_choice = get_single_char(console, choices=['y', 'n'],
-                                                     message="[bold] > Do you want to see the validation details? ([magenta]y/n[/magenta]): [/bold]")
+                                                     message=(
+                                                         "[bold] > Do you want to see the validation details? "
+                                                         "([magenta]y/n[/magenta]): [/bold]"
+                                                     ))
                 if verbose_choice == "y" or verbose:
                     report_layout.show_validation_details(pager, enable_pager=enable_pager)
 
@@ -378,7 +394,6 @@ def multiple_choice(console: Console,
     ]
     console.print("\n")
     selected = prompt(question, style={"questionmark": "#ff9d00 bold",
-                                       "questionmark": "#e5c07b",
                                        "question": "bold",
                                        "checkbox": "magenta",
                                        "answer": "magenta"},
@@ -508,8 +523,11 @@ def __init_layout__(self):
         base_info_layout = Layout(
             Align(
                 f"\n[bold cyan]RO-Crate:[/bold cyan] [bold]{URI(settings['data_path']).uri}[/bold]"
-                f"\n[bold cyan]Target Profile:[/bold cyan][bold magenta] {settings['profile_identifier']}[/bold magenta] { '[italic](autodetected)[/italic]' if settings['profile_autodetected'] else ''}"
-                f"\n[bold cyan]Validation Severity:[/bold cyan] [bold {severity_color}]{settings['requirement_severity']}[/bold {severity_color}]",
+                "\n[bold cyan]Target Profile:[/bold cyan][bold magenta] "
+                f"{settings['profile_identifier']}[/bold magenta] "
+                f"{ '[italic](autodetected)[/italic]' if settings['profile_autodetected'] else ''}"
+                f"\n[bold cyan]Validation Severity:[/bold cyan] "
+                f"[bold {severity_color}]{settings['requirement_severity']}[/bold {severity_color}]",
                 style="white", align="left"),
             name="Base Info", size=5)
         #
@@ -557,12 +575,12 @@ def __init_layout__(self):
 
         # Create the main layout
         self.checks_stats_layout = Layout(
-            Panel(report_container_layout, title=f"[bold]- Validation Report -[/bold]",
+            Panel(report_container_layout, title="[bold]- Validation Report -[/bold]",
                   border_style="cyan", title_align="center", padding=(1, 2)))
 
         # Create the overall result layout
         self.overall_result = Layout(
-            Padding(Rule(f"\n[italic][cyan]Validating ROCrate...[/cyan][/italic]"), (1, 1)), size=3)
+            Padding(Rule("\n[italic][cyan]Validating ROCrate...[/cyan][/italic]"), (1, 1)), size=3)
 
         group_layout = Layout()
         group_layout.add_split(self.checks_stats_layout)
@@ -641,11 +659,13 @@ def set_overall_result(self, result: ValidationResult):
         self.result = result
         if result.passed():
             self.overall_result.update(
-                Padding(Rule(f"[bold][[green]OK[/green]] RO-Crate is a [green]valid[/green] [magenta]{result.context.target_profile.identifier}[/magenta] !!![/bold]\n\n",
+                Padding(Rule("[bold][[green]OK[/green]] RO-Crate is a [green]valid[/green] "
+                             f"[magenta]{result.context.target_profile.identifier}[/magenta] !!![/bold]\n\n",
                              style="bold green"), (1, 1)))
         else:
             self.overall_result.update(
-                Padding(Rule(f"[bold][[red]FAILED[/red]] RO-Crate is [red]not[/red] a [red]valid[/red] [magenta]{result.context.target_profile.identifier}[/magenta] !!![/bold]\n",
+                Padding(Rule("[bold][[red]FAILED[/red]] RO-Crate is [red]not[/red] a [red]valid[/red] "
+                             f"[magenta]{result.context.target_profile.identifier}[/magenta] !!![/bold]\n",
                              style="bold red"), (1, 1)))
 
     def show_validation_details(self, pager: Pager, enable_pager: bool = True):
@@ -674,7 +694,8 @@ def show_validation_details(self, pager: Pager, enable_pager: bool = True):
                           f"profile: [magenta bold]{requirement.profile.name }[/magenta bold]]", align="right")
                 )
                 console.print(
-                    f"  [bold][cyan][{requirement.order_number}] [u]{Markdown(requirement.name).markup}[/u][/cyan][/bold]",
+                    f"  [bold][cyan][{requirement.order_number}] "
+                    "[u]{Markdown(requirement.name).markup}[/u][/cyan][/bold]",
                     style="white",
                 )
                 console.print(Padding(Markdown(requirement.description), (1, 7)))
@@ -685,7 +706,10 @@ def show_validation_details(self, pager: Pager, enable_pager: bool = True):
                                     key=lambda x: (-x.severity.value, x)):
                     issue_color = get_severity_color(check.level.severity)
                     console.print(
-                        Padding(f"[bold][{issue_color}][{check.relative_identifier.center(16)}][/{issue_color}]  [magenta]{check.name}[/magenta][/bold]:", (0, 7)), style="white bold")
+                        Padding(
+                            f"[bold][{issue_color}][{check.relative_identifier.center(16)}][/{issue_color}]  "
+                            f"[magenta]{check.name}[/magenta][/bold]:", (0, 7)),
+                        style="white bold")
                     console.print(Padding(Markdown(check.description), (0, 27)))
                     console.print(Padding("[u] Detected issues [/u]", (0, 8)), style="white bold")
                     for issue in sorted(result.get_issues_by_check(check),
@@ -743,7 +767,8 @@ def __compute_profile_stats__(validation_settings: dict):
                 check_count_by_severity[severity] = 0
             if severity_validation <= severity:
                 num_checks = len(
-                    [_ for _ in requirement.get_checks_by_level(LevelCollection.get(severity.name)) if not _.overridden])
+                    [_ for _ in requirement.get_checks_by_level(LevelCollection.get(severity.name))
+                     if not _.overridden])
                 check_count_by_severity[severity] += num_checks
                 total_checks += num_checks
 

rocrate_validator/cli/main.py

@@ -86,7 +86,7 @@ def cli(ctx: click.Context, debug: bool, version: bool, disable_color: bool, no_
     except Exception as e:
         console.print(
             f"\n\n[bold][[red]FAILED[/red]] Unexpected error: {e} !!![/bold]\n", style="white")
-        console.print("""This error may be due to a bug. 
+        console.print("""This error may be due to a bug.
                       Please report it to the issue tracker
             along with the following stack trace:
             """)

rocrate_validator/errors.py

@@ -97,7 +97,7 @@ def __str__(self) -> str:
         return msg
 
     def __repr__(self):
-        return f"ProfileSpecificationNotFound()"
+        return "ProfileSpecificationNotFound()"
 
 
 class ProfileSpecificationError(ROCValidatorError):

rocrate_validator/models.py

@@ -150,8 +150,10 @@ def get(name: str) -> RequirementLevel:
 class Profile:
 
     # store the map of profiles: profile URI -> Profile instance
-    __profiles_map: MultiIndexMap = MultiIndexMap("uri",
-                                                  indexes=[MapIndex("name"), MapIndex("token", unique=False), MapIndex("identifier", unique=True)])
+    __profiles_map: MultiIndexMap = \
+        MultiIndexMap("uri", indexes=[
+            MapIndex("name"), MapIndex("token", unique=False), MapIndex("identifier", unique=True)
+        ])
 
     def __init__(self,
                  profiles_base_path: Path,
@@ -191,13 +193,17 @@ def __init__(self,
             self._token, self._version = self.__init_token_version__()
             # add the profile to the profiles map
             self.__profiles_map.add(
-                self._profile_node.toPython(), self, token=self.token, name=self.name, identifier=self.identifier)  # add the profile to the profiles map
+                self._profile_node.toPython(),
+                self, token=self.token,
+                name=self.name, identifier=self.identifier
+            )  # add the profile to the profiles map
         else:
             raise ProfileSpecificationError(
                 message=f"Profile specification file {spec_file} must contain exactly one profile")
 
-    def __get_specification_property__(self, property: str, namespace: Namespace,
-                                       pop_first: bool = True, as_Python_object: bool = True) -> Union[str, list[Union[str, URIRef]]]:
+    def __get_specification_property__(
+            self, property: str, namespace: Namespace,
+            pop_first: bool = True, as_Python_object: bool = True) -> Union[str, list[Union[str, URIRef]]]:
         assert self._profile_specification_graph is not None, "Profile specification graph not loaded"
         values = list(self._profile_specification_graph.objects(self._profile_node, namespace[property]))
         if values and as_Python_object:
@@ -306,15 +312,15 @@ def __get_nested_profiles__(cls, source: str) -> list[str]:
         queue = [source]
         while len(queue) > 0:
             p = queue.pop()
-            if not p in visited:
+            if p not in visited:
                 visited.append(p)
                 profile = cls.__profiles_map.get_by_key(p)
                 inherited_profiles = profile.is_profile_of
                 if inherited_profiles:
                     for p in sorted(inherited_profiles, reverse=True):
-                        if not p in visited:
+                        if p not in visited:
                             queue.append(p)
-                        if not p in result:
+                        if p not in result:
                             result.insert(0, p)
         return result
 
@@ -1234,7 +1240,8 @@ def parse(cls, settings: Union[dict, ValidationSettings]) -> ValidationSettings:
 
 
 class ValidationEvent(Event):
-    def __init__(self, event_type: EventType, validation_result: Optional[ValidationResult] = None, message: Optional[str] = None):
+    def __init__(self, event_type: EventType,
+                 validation_result: Optional[ValidationResult] = None, message: Optional[str] = None):
         super().__init__(event_type, message)
         self._validation_result = validation_result
 
@@ -1275,7 +1282,9 @@ def validation_result(self) -> Optional[bool]:
 
 
 class RequirementCheckValidationEvent(Event):
-    def __init__(self, event_type: EventType, requirement_check: RequirementCheck, validation_result: Optional[bool] = None, message: Optional[str] = None):
+    def __init__(self, event_type: EventType,
+                 requirement_check: RequirementCheck,
+                 validation_result: Optional[bool] = None, message: Optional[str] = None):
         assert event_type in (EventType.REQUIREMENT_CHECK_VALIDATION_START, EventType.REQUIREMENT_CHECK_VALIDATION_END)
         super().__init__(event_type, message)
         self._requirement_check = requirement_check
@@ -1545,8 +1554,9 @@ def __load_profiles__(self) -> list[Profile]:
                 # raised when the profile is not found
                 if logger.isEnabledFor(logging.DEBUG):
                     logger.exception(e)
-                raise ProfileNotFound(self.profile_identifier,
-                                      message=f"Profile '{self.profile_identifier}' not found in '{self.profiles_path}'") from e
+                raise ProfileNotFound(
+                    self.profile_identifier,
+                    message=f"Profile '{self.profile_identifier}' not found in '{self.profiles_path}'") from e
 
         # Set the profiles to validate against as the target profile and its inherited profiles
         profiles = profile.inherited_profiles + [profile]

rocrate_validator/profiles/ro-crate/should/5_web_data_entity_metadata.py

@@ -24,13 +24,14 @@
 @requirement(name="Web-based Data Entity: RECOMMENDED resource availability")
 class WebDataEntityRecommendedChecker(PyFunctionCheck):
     """
-    Web-based Data Entity instances SHOULD be available at the URIs specified in the `@id` property of the Web-based Data Entity.
+    Web-based Data Entity instances SHOULD be available
+    at the URIs specified in the `@id` property of the Web-based Data Entity.
     """
 
     @check(name="Web-based Data Entity: resource availability")
     def check_availability(self, context: ValidationContext) -> bool:
         """
-        Check if the Web-based Data Entity is directly downloadable 
+        Check if the Web-based Data Entity is directly downloadable
         by a simple retrieval (e.g. HTTP GET) permitting redirection and HTTP/HTTPS URIs
         """
         result = True
@@ -62,7 +63,8 @@ def check_content_size(self, context: ValidationContext) -> bool:
                 content_size = entity.get_property("contentSize")
                 if content_size and int(content_size) != context.ro_crate.get_external_file_size(entity.id):
                     context.result.add_check_issue(
-                        f'The property contentSize={content_size} of the Web-based Data Entity {entity.id} does not match the actual size of '
+                        f'The property contentSize={content_size} of the Web-based Data Entity '
+                        f'{entity.id} does not match the actual size of '
                         f'the downloadable content, i.e., {entity.content_size} (bytes)', self,
                         focusNode=entity.id, resultPath='contentSize', value=content_size)
                     result = False

rocrate_validator/profiles/workflow-ro-crate/may/1_main_workflow.py

@@ -33,7 +33,7 @@ def check_workflow_diagram(self, context: ValidationContext) -> bool:
             image = main_workflow.get_property("image")
             diagram_relpath = image.id if image else None
             if not diagram_relpath:
-                context.result.add_error(f"main workflow does not have an 'image' property", self)
+                context.result.add_error("main workflow does not have an 'image' property", self)
                 return False
             if not image.is_available():
                 context.result.add_error(f"Workflow diagram '{image.id}' not found in crate", self)