Merge pull request #853 from juanjemdIos/master

running test in every PR with an action. Fixes #845

Author: dgarijo

.github/workflows/action-test-before-PR.yml

@@ -0,0 +1,34 @@
+name: Run SOMEF tests before PR
+
+on:
+  pull_request:
+    branches:
+      - dev #should be this branch or master?
+  workflow_dispatch:
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: "3.11"
+
+      - name: Install Poetry
+        run: curl -sSL https://install.python-poetry.org | python3 -
+
+      - name: Install dependencies
+        run: poetry install
+
+      - name: Download NLTK data
+        run: poetry run python -m nltk.downloader wordnet omw-1.4 punkt punkt_tab stopwords
+
+      - name: Configure SOMEF
+        run: poetry run somef configure -a
+        
+      - name: Run pytest
+        run: poetry run pytest -v src/somef/test

docs/pom.md

@@ -110,3 +110,5 @@ package_distribution': [{'result': {'value': 'http://127.0.0.1/websvn/my-project
 ```
 [{'value': 'Java: 1.8', 'name': 'Java', 'version': '1.8'}]
 ```
+
+

src/somef/extract_software_type.py

@@ -1,12 +1,14 @@
 import os
 from pathlib import Path
 import nbformat
+from nbformat.reader import NotJSONError
 from chardet import detect
 import re
 from .extract_workflows import is_file_workflow
 from .process_results import Result
 from .utils import constants
 from .extract_ontologies import is_file_ontology
+
 import pdb
 
 
@@ -301,14 +303,20 @@ def is_notebook_code(file_path):
     has_code = False
     num_code_cells = 0
     num_total_cells = 0
-    nb = nbformat.read(file_path, as_version=4)
-    for cell in nb['cells']:
-        if cell['cell_type'] == 'code':
-            num_total_cells += 1
-            if cell['source'].strip():
-                num_code_cells += 1
-                has_code = True
-    return has_code
+    try:
+        nb = nbformat.read(file_path, as_version=4)
+ 
+        for cell in nb['cells']:
+            if cell['cell_type'] == 'code':
+                num_total_cells += 1
+                if cell['source'].strip():
+                    num_code_cells += 1
+                    has_code = True
+        return has_code
+    except NotJSONError:
+        return False
+    except Exception:
+        return False
 
 
 def has_code_in_rmd(file_path):

src/somef/somef_cli.py

@@ -71,6 +71,7 @@ def cli_get_data(threshold, ignore_classifiers, repo_url=None, doc_src=None, loc
                 logging.info(f"{servidor} is GitLab.")
                 bGitLab = True
 
+            print(f"DEBUG: {servidor} is_gitlab = {bGitLab}")
             if bGitLab:
                 repo_type = constants.RepositoryType.GITLAB
             repository_metadata, owner, repo_name, def_branch = process_repository.load_online_repository_metadata(
@@ -80,6 +81,13 @@ def cli_get_data(threshold, ignore_classifiers, repo_url=None, doc_src=None, loc
                 repo_type,
                 authorization
             )
+            print("\n=== DEBUG GITLAB SELF-HOSTED ===")
+            print(f"repo_url: {repo_url}")
+            print(f"owner: {owner}")
+            print(f"repo_name: {repo_name}")
+            print(f"def_branch: {def_branch}")
+            print(f"repo_type: {repo_type}")
+            print("=================================\n")
 
             # download files and obtain path to download folder
             if readme_only: