Update README, fix bugs from code review, switch to uv

.github/workflows/release.yml

@@ -15,28 +15,14 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v10.1.0
         with:
           python-version: ${{ matrix.python-version }}
-      - name: Install Poetry
-        uses: snok/install-poetry@v1
-        with:
-          virtualenvs-create: true
-          virtualenvs-in-project: true
-          installer-parallel: true
-      - name: Load cached venv
-        id: cached-poetry-venv
-        uses: actions/cache@v4
-        with:
-          path: .venv
-          key: venv-${{ matrix.python-version }}-${{ hashFiles('poetry.lock') }}
-      - name: Install dependencies
-        if: steps.cached-poetry-venv.outputs.cache-hit != 'true'
-        run: poetry install
+          enable-cache: true
       - name: Build
-        run: poetry build
+        run: uv build
       - name: Publish
-        run: |
-          poetry config pypi-token.pypi ${{ secrets.PYPI_TOKEN }}
-          poetry publish
+        run: uv publish
+        env:
+          UV_PUBLISH_TOKEN: ${{ secrets.PYPI_TOKEN }}

.github/workflows/test.yml

@@ -20,29 +20,15 @@ jobs:
     runs-on: ${{ matrix.os }}
     steps:
     - uses: actions/checkout@v4
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v4
+    - name: Install uv
+      uses: astral-sh/setup-uv@v10.1.0
       with:
         python-version: ${{ matrix.python-version }}
-    - name: Install Poetry
-      uses: snok/install-poetry@76e04a911780d5b312d89783f7b1cd627778900a
-      with:
-        virtualenvs-create: true
-        virtualenvs-in-project: true
-        installer-parallel: true
-    - name: Load cached venv
-      id: cached-poetry-venv
-      uses: actions/cache@v4
-      with:
-        path: .venv
-        key: venv-${{ matrix.python-version }}-${{ runner.os }}-${{ hashFiles('poetry.lock') }}
+        enable-cache: true
     - name: Install dependencies
-      if: steps.cached-poetry-venv.outputs.cache-hit != 'true'
-      run: poetry install --no-interaction
+      run: uv sync --locked
     - name: Run tests
-      run: |
-        source $VENV
-        poetry run pytest --cov --cov-report=xml --junitxml=tests.xml
+      run: uv run pytest --cov --cov-report=xml --junitxml=tests.xml
     - name: Test Report
       uses: dorny/test-reporter@v1
       if: success() || failure()
@@ -57,28 +43,16 @@ jobs:
         python-version: [ "3.12" ]
     runs-on: "ubuntu-latest"
     steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+      - uses: actions/checkout@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v10.1.0
         with:
           python-version: ${{ matrix.python-version }}
-      - name: Install Poetry
-        uses: snok/install-poetry@v1
-        with:
-          virtualenvs-create: true
-          virtualenvs-in-project: true
-          installer-parallel: true
-      - name: Load cached venv
-        id: cached-poetry-venv
-        uses: actions/cache@v4
-        with:
-          path: .venv
-          key: venv-${{ matrix.python-version }}-{{ runner.os }}-${{ hashFiles('poetry.lock') }}
+          enable-cache: true
       - name: Install dependencies
-        if: steps.cached-poetry-venv.outputs.cache-hit != 'true'
-        run: poetry install --no-interaction
+        run: uv sync --locked
       - name: Run tests
-        run: poetry run pytest --cov --cov-report=xml --junitxml=tests.xml
+        run: uv run pytest --cov --cov-report=xml --junitxml=tests.xml
       - name: Code Coverage Report
         uses: irongut/CodeCoverageSummary@v1.3.0
         with:
@@ -99,25 +73,13 @@ jobs:
         python-version: [ "3.12" ]
     runs-on: "ubuntu-latest"
     steps:
-      - uses: actions/checkout@v3
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+      - uses: actions/checkout@v4
+      - name: Install uv
+        uses: astral-sh/setup-uv@v10.1.0
         with:
           python-version: ${{ matrix.python-version }}
-      - name: Install Poetry
-        uses: snok/install-poetry@v1
-        with:
-          virtualenvs-create: true
-          virtualenvs-in-project: true
-          installer-parallel: true
-      - name: Load cached venv
-        id: cached-poetry-venv
-        uses: actions/cache@v3
-        with:
-          path: .venv
-          key: venv-${{ matrix.python-version }}-{{ runner.os }}-${{ hashFiles('poetry.lock') }}
+          enable-cache: true
       - name: Install dependencies
-        if: steps.cached-poetry-venv.outputs.cache-hit != 'true'
-        run: poetry install --no-interaction
+        run: uv sync --locked
       - name: Type checker
-        run: poetry run mypy codestripper
+        run: uv run mypy codestripper

README.md

@@ -27,13 +27,41 @@ CodeStripper can be used as a Python Module and as a command line tool. The comm
 | Flag | Long form | Description | Default value | Required |
 |----------|------|-------------|---------------|----------|
 | `<positional>` | None | files to include for code stripping (glob) | None | True |
-| -e | --exclude | files to exclude for code stripping (glob) | None | False |
-| -c | --comment | comment symbol(s) for the given language | // | False |
+| -x | --exclude | files to exclude for code stripping (glob), can be repeated | None | False |
+| -c | --comment | comment symbol(s) for a file extension, format `<extension>:<open>` or `<extension>:<open>:<close>` (e.g. `.java://`), the extension starts with a `.` and is case-insensitive, can be repeated | built-in mapping (see below) | False |
 | -o | --output | the output directory to store the stripped files | out | False |
 | -r | --recursive | do NOT use recursive globs for include/exclude | True | False |
-| -v | --verbosity | increase output verbosity | None | False |
-| -d | --dry | execute a dry run | False | False |
+| -v | --verbosity | increase output verbosity (can be repeated) | 0 | False |
+| -d | --dry-run | execute a dry run, prints the stripped files (with a `==> <file> <==` header) to stdout instead of writing them | False | False |
 | -w | --working-directory | set the working directory for include/exclude | pwd | False |
+| -e | --fail-on-error | do NOT fail if an error occurs during code stripping | fail on error | False |
+| -b | --binary | what to do if a binary file is matched: `fail`, `ignore` or `include` | fail | False |
+| -u | --unknown | what to do if a file with an unknown extension is matched: `fail`, `ignore` or `include` | fail | False |
+
+### Supported comment styles
+
+The comment symbol is chosen based on the file extension. The following extensions are supported by default:
+
+| Comment | Extensions |
+|---------|------------|
+| `//` | `.java`, `.cs`, `.js`, `.php`, `.swift` |
+| `#` | `.py`, `.r`, `.ps1`, `.rb`, `.yml`, `.yaml`, files without extension |
+| `%` | `.tex`, `.m` |
+| `--` | `.sql`, `.lua` |
+| `<!-- -->` | `.xml` |
+| `(* *)` | `.ml` |
+
+Use `-c` to add or override an extension, for example `-c .kt://` or `-c .html:'<!--':'-->'`.
+
+### Python module
+
+```python
+from codestripper.code_stripper import strip_files
+
+stripped = strip_files(["src/Test.java"], working_directory=".", output="out", dry_run=False)
+```
+
+`strip_files` returns the files that were stripped. Files that fail (e.g. an invalid tag) are logged and the other files are still processed, after which a `StripError` is raised. Pass `fail_on_error=False` to only log the errors, like the `-e` flag of the command line tool.
 
 ## Examples
 
@@ -150,7 +178,6 @@ classDiagram
     Tag <|-- RangeTag
 
     class Tag{
-        <<Abstract>>
         +offset: int
         +start: int
         +end: int
@@ -169,17 +196,18 @@ classDiagram
         +SingleTag(data: TagData)
     }
     class RangeOpenTag{
-        +RangeOpen(parent: Type, data: TagData)
+        +RangeOpenTag(parent: Type, data: TagData)
     }
     class RangeCloseTag{
-        +RangeOpen(parent: Type, data: TagData)
+        +RangeCloseTag(parent: Type, data: TagData)
     }
     class RangeTag{
         +inset: int
         +start: int
         +end: int
         +open_tag: RangeOpenTag
         +close_tag: RangeCloseTag
+        +tags: List[Tag]
         +RangeTag(open_tag: RangeOpenTag, close_tag: RangeCloseTag)
         +add_tags(tags: Iterable[Tag])
     }
@@ -212,7 +240,7 @@ class TestTag(SingleTag):
         # None means the line is removed
 
     def is_valid(self) -> bool:
-        # Return wether the tag is valid
+        # Return whether the tag is valid
 ```
 
   - RangeTag: Range needs a `RangeOpenTag`, `RangeCloseTag` and a `RangeTag`
@@ -228,7 +256,7 @@ class TestOpenTag(RangeOpenTag):
         # None means the line is removed
 
     def is_valid(self) -> bool:
-        # Return wether the tag is valid
+        # Return whether the tag is valid
 
 class TestCloseTag(RangeCloseTag):
     # Same as RangeOpenTag
@@ -242,15 +270,16 @@ class TestRangeTag(RangeTag):
     def execute(self, content: str) -> Union[str, None]:
         # Manipulate lines between the tags
 ```
-3. Add the new tag(s) to the `default_tags` in the `tokenizer`,
+3. Export the new tag(s) in `codestripper/tags/__init__.py`, import them in the `tokenizer` and add them to its `default_tags`,
 
 ```python
 default_tags: Set[Type[SingleTag]] = {
     IgnoreFileTag,
     RemoveOpenTag,
     ...,
     TestTag,
-    TestOpenTag
+    TestOpenTag,
+    TestCloseTag
 }
 ```
-> :warning: **Only the `SingleTag`(s) need to be added, not the `RangeTag`** 
+> :warning: **Only the `SingleTag`(s) (including `RangeOpenTag` and `RangeCloseTag`) need to be added, not the `RangeTag`** 

codestripper/__init__.py

@@ -1 +1,2 @@
 from codestripper.code_stripper import CodeStripper, strip_files
+from codestripper.errors import StripError

codestripper/__main__.py

@@ -1,4 +1,3 @@
-import sys
 
 from codestripper.cli import main
 

codestripper/cli.py

@@ -1,21 +1,30 @@
 import argparse
 import os
-from typing import List
 
 from codestripper.code_stripper import strip_files
 from codestripper.utils import FileUtils, set_logger_level, get_working_directory
+from codestripper.utils.comments import parse_comment
 from codestripper.utils.enums import UnexpectedInputOptions
 
 
+def comment_argument(value: str) -> str:
+    """Argparse type that validates a comment specification, the specification itself is parsed later"""
+    try:
+        parse_comment(value)
+    except ValueError as error:
+        raise argparse.ArgumentTypeError(str(error))
+    return value
+
+
 def add_commandline_arguments(parser: argparse.ArgumentParser) -> None:
     """Add command line arguments"""
     # Add positional arguments
     parser.add_argument("include", nargs="+", help="files to include for code stripping (multiple files or glob)")
     # Add optional arguments
     parser.add_argument("-x", "--exclude", action="append",
-                        help="files to include for code stripping (glob)", default=[])
-    parser.add_argument("-c", "--comment", action="append",
-                        help="comment symbol(s) for the given language, usage: <extension>:<comment> (e.g. .java://")
+                        help="files to exclude for code stripping (glob)", default=[])
+    parser.add_argument("-c", "--comment", action="append", type=comment_argument,
+                        help="comment symbol(s) for the given language, usage: <extension>:<open>[:<close>] (e.g. .java://)")
     parser.add_argument("-v", "--verbosity", action="count", help="increase output verbosity", default=0)
     parser.add_argument("-o", "--output", action="store",
                         help="output directory to store the stripped files", default="out")
@@ -27,9 +36,10 @@ def add_commandline_arguments(parser: argparse.ArgumentParser) -> None:
                         help="set the working directory for include/exclude", default=os.getcwd())
     parser.add_argument("-e", "--fail-on-error", action="store_false",
                         help="Fail if an error occurs during code stripping")
-    parser.add_argument("-b", "--binary", choices=list(UnexpectedInputOptions), default=UnexpectedInputOptions.FAIL,
+    unexpected_choices = [option.value for option in UnexpectedInputOptions]
+    parser.add_argument("-b", "--binary", choices=unexpected_choices, default=UnexpectedInputOptions.FAIL.value,
                         action="store", help="What to do if binary file is matched")
-    parser.add_argument("-u", "--unknown", choices=list(UnexpectedInputOptions), default=UnexpectedInputOptions.FAIL,
+    parser.add_argument("-u", "--unknown", choices=unexpected_choices, default=UnexpectedInputOptions.FAIL.value,
                         action="store", help="What to do if a file with unknown extension is matched")
 
 
@@ -46,9 +56,13 @@ def main() -> None:
     set_logger_level(logger_name, args.verbosity)
 
     # Find the files, based on the command line arguments
-    cwd = get_working_directory(args.working_directory)
+    try:
+        cwd = get_working_directory(args.working_directory)
+    except ValueError as error:
+        parser.error(str(error))
     files = FileUtils(args.include, args.exclude, cwd, args.recursive, logger_name).get_matching_files()
     # Strip all the files
 
     strip_files(files, cwd, comments=args.comment, output=args.output, dry_run=args.dry_run,
-                fail_on_error=args.fail_on_error)
+                fail_on_error=args.fail_on_error, binary=UnexpectedInputOptions(args.binary),
+                unknown_extension=UnexpectedInputOptions(args.unknown))