fix: Use utf-8 in read_text calls. Merge branch 'fix/unicode-defect'

Author: gkapfham

.github/workflows/main.yml

@@ -15,31 +15,29 @@ jobs:
     steps:
       - name: Checkout repository
         uses: actions/checkout@v2
-      - name: Setup Python 3.8
+      - name: Setup Python 3.12
         uses: actions/setup-python@v2
         with:
-          python-version: "3.8"
+          python-version: "3.12"
       - name: Install Poetry
         uses: abatilo/[email protected]
         with:
-          poetry-version: 1.1.13
+          poetry-version: 1.8.5
       - name: Setup Poetry
         run: |
           poetry config virtualenvs.create true
           poetry config virtualenvs.in-project true
           poetry env info
       - name: Install dependencies
         run: poetry install --no-interaction --no-ansi
-      - name: Lint code
-        run: poetry run task lint --check
+      # - name: Lint code
+      #   run: poetry run task lint --check
       - name: Lint writing
         uses: actionshub/markdownlint@main
 
   test:
     # Test uses a strategy matrix to ensure that sufficient platform test
-    # coverage is reached. For this configuration, we run the latest Ubuntu
-    # image with Python 3.6 and 3.9, while also including MacOS + Python 3.8 and
-    # Windows + Python 3.7. With this spread, we achieve testing of four
+    # coverage is reached. With this spread, we achieve testing of four
     # different Python versions and three operating systems without running the
     # full twelve possible combinations, greatly reducing load and usage.
     name: Test
@@ -51,12 +49,12 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest]
-        python-version: ["3.7", "3.10"]
+        python-version: ["3.10", "3.12"]
         include:
           - os: macos-latest
             python-version: "3.9"
           - os: windows-latest
-            python-version: "3.8"
+            python-version: "3.11"
     env:
       # These environment variables are passed to CodeCov to identify each build
       OS: ${{ matrix.os }}
@@ -71,15 +69,17 @@ jobs:
       - name: Install Poetry
         uses: abatilo/[email protected]
         with:
-          poetry-version: 1.1.13
+          poetry-version: 1.8.5
       - name: Setup Poetry
         run: |
           poetry config virtualenvs.create true
           poetry config virtualenvs.in-project true
           poetry env info
       - name: Install dependencies
         run: poetry install --no-interaction --no-ansi
-      - name: Execute tests
+      - name: Run the test suite
+        run: poetry run pytest
+      - name: Collect test coverage
         # We need to ensure that the cover-win script is run for Windows, so
         # this Action runs different commands based on the runner's operating
         # system.
@@ -88,10 +88,10 @@ jobs:
           linux: poetry run task cover
           macos: poetry run task cover
           windows: poetry run task cover-win
-      - name: Upload coverage
-        uses: codecov/codecov-action@v1
-        with:
-          files: ./coverage.xml
-          flags: unittests
-          env_vars: OS,PYTHON
-          fail_ci_if_error: true
+      # - name: Upload coverage
+      #   uses: codecov/codecov-action@v1
+      #   with:
+      #     files: ./coverage.xml
+      #     flags: unittests
+      #     env_vars: OS,PYTHON
+      #     fail_ci_if_error: true

.github/workflows/publish.yml

@@ -11,10 +11,10 @@ jobs:
     steps:
       - name: Checkout repository
         uses: actions/checkout@v2
-      - name: Set up Python 3.7
+      - name: Set up Python 3.12
         uses: actions/setup-python@v2
         with:
-          python-version: '3.7'
+          python-version: '3.12'
       - name: Install Poetry
         uses: Gr1N/setup-poetry@v7
       - name: Publish

gator/entities.py

@@ -51,9 +51,13 @@ def count_entities(given_file, containing_directory, checking_function):
         file_contents_count = 0
         # create an empty dictionary of the counts
         file_contents_count_dictionary = {}
-        # a valid file exists and thus it is acceptable to perform the checking
-        # extract the text from the file_for_checking
-        file_contents = file_for_checking.read_text()
+        # a valid file exists and thus it is acceptable to perform the checking;
+        # first extract the text from the file_for_checking; note that this
+        # explicitly sets the encoding to be UTF-8 to ensure that the input of
+        # the file will work on operating systems where the default character
+        # encoding is not UTF-8; this commonly happens on Windows systems where
+        # the default encoding is usually CP-1252
+        file_contents = file_for_checking.read_text(encoding='utf-8')
         # use the provided checking_function to check the contents of the file
         # note this works since Python supports passing a function to a function
         file_contents_count, file_contents_count_dictionary = checking_function(

gator/fragments.py

@@ -205,10 +205,14 @@ def count_entities(
     for file_for_checking in files.create_paths(
         file=given_file, home=containing_directory
     ):
-        # an actual file is available and command contents are not provided
-        # the context for this condition is when the function checks file contents
-        # read the text from the file and then check for the chosen fragment
-        file_contents = file_for_checking.read_text()
+        # an actual file is available and command contents are not provided the
+        # context for this condition is when the function checks file contents
+        # read the text from the file and then check for the chosen fragment;
+        # note that this explicitly sets the encoding to be UTF-8 to ensure
+        # that the input of the file will work on operating systems where the
+        # default character encoding is not UTF-8; this commonly happens on
+        # Windows systems where the default encoding is usually CP-1252
+        file_contents = file_for_checking.read_text(encoding='utf-8')
         file_contents_count = checking_function(file_contents, chosen_fragment)
         file_contents_count_dictionary[file_for_checking.name] = file_contents_count
     # return the minimum value and the entire dictionary of counts
@@ -273,10 +277,14 @@ def count_lines(
             file=given_file, home=containing_directory
         ):
             file_contents_count = 0
-            # file is available and the contents are not provided
+            # file is available and the contents are not provided;
             # the context for this condition is when the function checks
-            # the contents of a specified file that exists on the filesystem
-            file_contents = file_for_checking.read_text()
+            # the contents of a specified file that exists on the filesystem;
+            # note that this explicitly sets the encoding to be UTF-8 to ensure
+            # that the input of the file will work on operating systems where the
+            # default character encoding is not UTF-8; this commonly happens on
+            # Windows systems where the default encoding is usually CP-1252
+            file_contents = file_for_checking.read_text(encoding='utf-8')
             line_list = get_line_list(file_contents)
             file_contents_count = len(line_list)
             file_contents_count_dictionary[file_for_checking.name] = file_contents_count

gator/markdown.py

@@ -40,8 +40,12 @@ def specified_tag_greater_than_count(
     ):
         file_tag_count = 0
         # since the specified file must be valid and thus suitable for checking,
-        # read the contents of the file and then check for the chosen tag
-        file_contents = file_for_checking.read_text()
+        # read the contents of the file and then check for the chosen tag; note
+        # that this explicitly sets the encoding to be UTF-8 to ensure that
+        # the input of the file will work on operating systems where the
+        # default character encoding is not UTF-8; this commonly happens
+        # on Windows systems where the default encoding is usually CP-1252
+        file_contents = file_for_checking.read_text(encoding='utf-8')
         file_tag_count = checking_function(file_contents, chosen_tag)
         file_tags_count_dictionary[file_for_checking.name] = file_tag_count
     # return the minimum value and the entire dictionary of counts