Merge pull request #3032 from mirpedrol/modules-yml-ontology

Modules meta.yml ontology

nf_core/__main__.py

@@ -1231,11 +1231,14 @@ def command_modules_test(ctx, tool, directory, no_prompts, update, once, profile
     is_flag=True,
     help="Fix the module version if a newer version is available",
 )
-def command_modules_lint(ctx, tool, directory, registry, key, all, fail_warned, local, passed, sort_by, fix_version):
+@click.option("--fix", is_flag=True, help="Fix all linting tests if possible.")
+def command_modules_lint(
+    ctx, tool, directory, registry, key, all, fail_warned, local, passed, sort_by, fix_version, fix
+):
     """
     Lint one or more modules in a directory.
     """
-    modules_lint(ctx, tool, directory, registry, key, all, fail_warned, local, passed, sort_by, fix_version)
+    modules_lint(ctx, tool, directory, registry, key, all, fail_warned, local, passed, sort_by, fix_version, fix)
 
 
 # nf-core modules info

nf_core/commands_modules.py

@@ -261,7 +261,7 @@ def modules_test(ctx, tool, directory, no_prompts, update, once, profile, migrat
         sys.exit(1)
 
 
-def modules_lint(ctx, tool, directory, registry, key, all, fail_warned, local, passed, sort_by, fix_version):
+def modules_lint(ctx, tool, directory, registry, key, all, fail_warned, local, passed, sort_by, fix_version, fix):
     """
     Lint one or more modules in a directory.
 
@@ -278,6 +278,7 @@ def modules_lint(ctx, tool, directory, registry, key, all, fail_warned, local, p
         module_lint = ModuleLint(
             directory,
             fail_warned=fail_warned,
+            fix=fix,
             registry=ctx.params["registry"],
             remote_url=ctx.obj["modules_repo_url"],
             branch=ctx.obj["modules_repo_branch"],

nf_core/components/components_utils.py

@@ -4,6 +4,7 @@
 from typing import TYPE_CHECKING, List, Optional, Tuple, Union
 
 import questionary
+import requests
 import rich.prompt
 
 if TYPE_CHECKING:
@@ -162,3 +163,29 @@ def get_components_to_install(subworkflow_dir: Union[str, Path]) -> Tuple[List[s
                 elif link.startswith("../"):
                     subworkflows.append(name.lower())
     return modules, subworkflows
+
+
+def get_biotools_id(tool_name) -> str:
+    """
+    Try to find a bio.tools ID for 'tool'
+    """
+    url = f"https://bio.tools/api/t/?q={tool_name}&format=json"
+    try:
+        # Send a GET request to the API
+        response = requests.get(url)
+        response.raise_for_status()  # Raise an error for bad status codes
+        # Parse the JSON response
+        data = response.json()
+
+        # Iterate through the tools in the response to find the tool name
+        for tool in data["list"]:
+            if tool["name"].lower() == tool_name:
+                return tool["biotoolsCURIE"]
+
+        # If the tool name was not found in the response
+        log.warning(f"Could not find a bio.tools ID for '{tool_name}'")
+        return ""
+
+    except requests.exceptions.RequestException as e:
+        log.warning(f"Could not find a bio.tools ID for '{tool_name}': {e}")
+        return ""

nf_core/components/create.py

@@ -21,6 +21,7 @@
 import nf_core
 import nf_core.utils
 from nf_core.components.components_command import ComponentCommand
+from nf_core.components.components_utils import get_biotools_id
 from nf_core.pipelines.lint_utils import run_prettier_on_file
 
 log = logging.getLogger(__name__)
@@ -61,6 +62,7 @@ def __init__(
         self.file_paths: Dict[str, Path] = {}
         self.not_empty_template = not empty_template
         self.migrate_pytest = migrate_pytest
+        self.tool_identifier = ""
 
     def create(self) -> bool:
         """
@@ -149,6 +151,8 @@ def create(self) -> bool:
             if self.component_type == "modules":
                 # Try to find a bioconda package for 'component'
                 self._get_bioconda_tool()
+                # Try to find a biotools entry for 'component'
+                self.tool_identifier = get_biotools_id(self.component)
 
             # Prompt for GitHub username
             self._get_username()

nf_core/components/lint/__init__.py

@@ -57,6 +57,7 @@ def __init__(
         component_type: str,
         directory: Union[str, Path],
         fail_warned: bool = False,
+        fix: bool = False,
         remote_url: Optional[str] = None,
         branch: Optional[str] = None,
         no_pull: bool = False,
@@ -73,6 +74,7 @@ def __init__(
         )
 
         self.fail_warned = fail_warned
+        self.fix = fix
         self.passed: List[LintResult] = []
         self.warned: List[LintResult] = []
         self.failed: List[LintResult] = []

nf_core/components/nfcore_component.py

@@ -49,7 +49,7 @@ def __init__(
         self.passed: List[Tuple[str, str, Path]] = []
         self.warned: List[Tuple[str, str, Path]] = []
         self.failed: List[Tuple[str, str, Path]] = []
-        self.inputs: List[str] = []
+        self.inputs: List[list[dict[str, dict[str, str]]]] = []
         self.outputs: List[str] = []
         self.has_meta: bool = False
         self.git_sha: Optional[str] = None
@@ -170,7 +170,7 @@ def _get_included_components_in_chained_tests(self, main_nf_test: Union[Path, st
 
     def get_inputs_from_main_nf(self) -> None:
         """Collect all inputs from the main.nf file."""
-        inputs: List[str] = []
+        inputs: list[list[dict[str, dict[str, str]]]] = []
         with open(self.main_nf) as f:
             data = f.read()
         # get input values from main.nf after "input:", which can be formatted as tuple val(foo) path(bar) or val foo or val bar or path bar or path foo
@@ -184,16 +184,22 @@ def get_inputs_from_main_nf(self) -> None:
         # don't match anything inside comments or after "output:"
         if "input:" not in data:
             log.debug(f"Could not find any inputs in {self.main_nf}")
+            return
         input_data = data.split("input:")[1].split("output:")[0]
-        regex = r"(val|path)\s*(\(([^)]+)\)|\s*([^)\s,]+))"
-        matches = re.finditer(regex, input_data, re.MULTILINE)
-        for _, match in enumerate(matches, start=1):
-            if match.group(3):
-                input_val = match.group(3).split(",")[0]  # handle `files, stageAs: "inputs/*"` cases
-                inputs.append(input_val)
-            elif match.group(4):
-                input_val = match.group(4).split(",")[0]  # handle `files, stageAs: "inputs/*"` cases
-                inputs.append(input_val)
+        for line in input_data.split("\n"):
+            channel_elements: list[dict[str, dict[str, str]]] = []
+            regex = r"(val|path)\s*(\(([^)]+)\)|\s*([^)\s,]+))"
+            matches = re.finditer(regex, line)
+            for _, match in enumerate(matches, start=1):
+                input_val = None
+                if match.group(3):
+                    input_val = match.group(3).split(",")[0]  # handle `files, stageAs: "inputs/*"` cases
+                elif match.group(4):
+                    input_val = match.group(4).split(",")[0]  # handle `files, stageAs: "inputs/*"` cases
+                if input_val:
+                    channel_elements.append({input_val: {}})
+            if len(channel_elements) > 0:
+                inputs.append(channel_elements)
         log.debug(f"Found {len(inputs)} inputs in {self.main_nf}")
         self.inputs = inputs
 
@@ -206,9 +212,23 @@ def get_outputs_from_main_nf(self):
             log.debug(f"Could not find any outputs in {self.main_nf}")
             return outputs
         output_data = data.split("output:")[1].split("when:")[0]
-        regex = r"emit:\s*([^)\s,]+)"
-        matches = re.finditer(regex, output_data, re.MULTILINE)
-        for _, match in enumerate(matches, start=1):
-            outputs.append(match.group(1))
+        regex_emit = r"emit:\s*([^)\s,]+)"
+        regex_elements = r"(val|path|env|stdout)\s*(\(([^)]+)\)|\s*([^)\s,]+))"
+        for line in output_data.split("\n"):
+            match_emit = re.search(regex_emit, line)
+            matches_elements = re.finditer(regex_elements, line)
+            if not match_emit:
+                continue
+            output_channel = {match_emit.group(1): []}
+            for _, match_element in enumerate(matches_elements, start=1):
+                output_val = None
+                if match_element.group(3):
+                    output_val = match_element.group(3)
+                elif match_element.group(4):
+                    output_val = match_element.group(4)
+                if output_val:
+                    output_val = output_val.strip("'").strip('"')  # remove quotes
+                    output_channel[match_emit.group(1)].append({output_val: {}})
+            outputs.append(output_channel)
         log.debug(f"Found {len(outputs)} outputs in {self.main_nf}")
         self.outputs = outputs

nf_core/module-template/meta.yml

@@ -20,48 +20,67 @@ tools:
       tool_dev_url: "{{ tool_dev_url }}"
       doi: ""
       licence: {{ tool_licence }}
+      identifier: {{ tool_identifier }}
 
 {% if not_empty_template -%}
 ## TODO nf-core: Add a description of all of the variables used as input
 {% endif -%}
 input:
   #{% if has_meta %} Only when we have meta
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. `[ id:'sample1', single_end:false ]`
+  - - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', single_end:false ]`
   {% endif %}
   {% if not_empty_template -%}
   ## TODO nf-core: Delete / customise this example input
   {%- endif %}
-  - {{ 'bam:' if not_empty_template else "input:" }}
-      type: file
-      description: {{ 'Sorted BAM/CRAM/SAM file' if not_empty_template else "" }}
-      pattern: {{ '"*.{bam,cram,sam}"' if not_empty_template else "" }}
+    - {{ 'bam:' if not_empty_template else "input:" }}
+        type: file
+        description: {{ 'Sorted BAM/CRAM/SAM file' if not_empty_template else "" }}
+        pattern: {{ '"*.{bam,cram,sam}"' if not_empty_template else "" }}
+        ontologies:
+          {% if not_empty_template -%}
+          - edam: "http://edamontology.org/format_25722"
+          - edam: "http://edamontology.org/format_2573"
+          - edam: "http://edamontology.org/format_3462"
+          {% else %}
+          - edam: ""
+          {%- endif %}
 
 {% if not_empty_template -%}
 ## TODO nf-core: Add a description of all of the variables used as output
 {% endif -%}
 output:
-  #{% if has_meta -%} Only when we have meta
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. `[ id:'sample1', single_end:false ]`
-  {% endif %}
   - versions:
-      type: file
-      description: File containing software versions
-      pattern: "versions.yml"
+    - "versions.yml":
+        type: file
+        description: File containing software versions
+        pattern: "versions.yml"
+  - {{ 'bam:' if not_empty_template else "output:" }}
+  #{% if has_meta -%} Only when we have meta
+    - meta:
+        type: map
+        description: |
+          Groovy Map containing sample information
+          e.g. `[ id:'sample1', single_end:false ]`
+  {%- endif %}
   {% if not_empty_template -%}
-  ## TODO nf-core: Delete / customise this example output
+    ## TODO nf-core: Delete / customise this example output
   {%- endif %}
-  - {{ 'bam:' if not_empty_template else "output:" }}
-      type: file
-      description: {{ 'Sorted BAM/CRAM/SAM file' if not_empty_template else "" }}
-      pattern: {{ '"*.{bam,cram,sam}"' if not_empty_template else "" }}
+    - {{ '"*.bam":' if not_empty_template else '"*":' }}
+        type: file
+        description: {{ 'Sorted BAM/CRAM/SAM file' if not_empty_template else "" }}
+        pattern: {{ '"*.{bam,cram,sam}"' if not_empty_template else "" }}
+        ontologies:
+          {% if not_empty_template -%}
+          - edam: "http://edamontology.org/format_25722"
+          - edam: "http://edamontology.org/format_2573"
+          - edam: "http://edamontology.org/format_3462"
+          {% else -%}
+          - edam: ""
+          {%- endif %}
 
 authors:
   - "{{ author }}"