localizationkit 3.0.1__tar.gz → 4.0.0__tar.gz

localizationkit-4.0.0/.azure/publish.yml

@@ -0,0 +1,43 @@
+trigger:
+  tags:
+    include:
+      - "*"
+
+pool:
+  vmImage: "ubuntu-latest"
+
+jobs:
+  - job: "Publish"
+    pool:
+      vmImage: "ubuntu-latest"
+
+    steps:
+      - task: UsePythonVersion@0
+        inputs:
+          versionSpec: "3.x"
+
+      - script: |
+          curl -LsSf https://astral.sh/uv/install.sh | sh
+          echo "##vso[task.prependpath]$HOME/.local/bin"
+        displayName: "Install uv"
+
+      - script: |
+          # hatch-vcs derives the version from git tags, so full history is required.
+          git fetch --tags --unshallow || git fetch --tags
+        displayName: "Fetch tags"
+
+      - script: |
+          uv build
+        displayName: "Build"
+
+      - task: EsrpRelease@2
+        inputs:
+          ConnectedServiceName: "OM-ESRP-Release-Publishing"
+          Intent: "PackageDistribution"
+          ContentType: "PyPi"
+          PackageLocation: "dist"
+          Owners: "jizhen@microsoft.com"
+          Approvers: "jizhen@microsoft.com"
+          ServiceEndpointUrl: "https://api.esrp.microsoft.com"
+          MainPublisher: "OutlookMobileiOSESRPPublisher"
+          DomainTenantId: "72f988bf-86f1-41af-91ab-2d7cd011db47"

localizationkit-4.0.0/.github/dependabot.yml

@@ -0,0 +1,19 @@
+version: 2
+updates:
+  - package-ecosystem: "uv"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    groups:
+      python-dependencies:
+        patterns:
+          - "*"
+
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    groups:
+      github-actions:
+        patterns:
+          - "*"

localizationkit-4.0.0/.github/workflows/test.yml

@@ -0,0 +1,78 @@
+name: Test
+
+on:
+  push:
+    branches:
+      - master
+  pull_request:
+    branches:
+      - master
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+
+jobs:
+  test:
+    name: Test (Python ${{ matrix.python-version }})
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version:
+          - "3.11"
+          - "3.12"
+          - "3.13"
+          - "3.14"
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v8.2.0
+        with:
+          enable-cache: true
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: uv sync
+
+      - name: Lint
+        run: |
+          uv run ruff check localizationkit tests
+          uv run ruff format --check localizationkit tests
+
+      - name: Type Check
+        run: uv run mypy localizationkit/ tests/
+
+      - name: Test
+        run: uv run pytest tests --cov=localizationkit --cov-report xml --doctest-modules --junitxml=junit/test-results.xml
+
+      - name: Upload coverage report
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: coverage-${{ matrix.python-version }}
+          path: coverage.xml
+
+      - name: Upload test results
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: test-results-${{ matrix.python-version }}
+          path: junit/test-results.xml
+
+  test-result:
+    name: test-result
+    if: always()
+    needs: test
+    runs-on: ubuntu-latest
+    steps:
+      - name: Verify all matrix jobs passed
+        run: |
+          if [ "${{ needs.test.result }}" != "success" ]; then
+            echo "One or more test matrix jobs failed."
+            exit 1
+          fi
+          echo "All test matrix jobs passed."

localizationkit-4.0.0/.gitignore

@@ -0,0 +1,13 @@
+htmlcov
+junit
+__pycache__
+venv
+.coverage
+coverage.xml
+dist
+.env
+.venv
+.mypy_cache
+.pytest_cache
+.ruff_cache
+*.egg-info

localizationkit-4.0.0/.pre-commit-config.yaml

@@ -0,0 +1,26 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-toml
+      - id: check-merge-conflict
+      - id: check-added-large-files
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.15.20
+    hooks:
+      - id: ruff-check
+        args: [--fix]
+      - id: ruff-format
+
+  - repo: local
+    hooks:
+      - id: mypy
+        name: mypy
+        entry: uv run mypy localizationkit/ tests/
+        language: system
+        types: [python]
+        pass_filenames: false

localizationkit-4.0.0/.python-version

@@ -0,0 +1 @@
+3.13

localizationkit-4.0.0/.vscode/settings.json

@@ -0,0 +1,15 @@
+{
+    "python.testing.pytestArgs": [
+        "tests"
+    ],
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true,
+    "editor.formatOnSave": true,
+    "[python]": {
+        "editor.defaultFormatter": "charliermarsh.ruff",
+        "editor.codeActionsOnSave": {
+            "source.fixAll.ruff": "explicit",
+            "source.organizeImports.ruff": "explicit"
+        }
+    }
+}

localizationkit-4.0.0/CODE_OF_CONDUCT.md

@@ -0,0 +1,9 @@
+# Microsoft Open Source Code of Conduct
+
+This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
+
+Resources:
+
+- [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/)
+- [Microsoft Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/)
+- Contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with questions or concerns

{localizationkit-3.0.1 → localizationkit-4.0.0}/PKG-INFO

@@ -1,28 +1,24 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: localizationkit
-Version: 3.0.1
+Version: 4.0.0
 Summary: String localization tests
-Home-page: https://github.com/Microsoft/localizationkit
-License: MIT
+Project-URL: homepage, https://github.com/Microsoft/localizationkit
+Project-URL: repository, https://github.com/Microsoft/localizationkit
+Author-email: Dale Myers <dalemy@microsoft.com>
+License-Expression: MIT
+License-File: LICENSE
 Keywords: localization,strings,tests
-Author: Dale Myers
-Author-email: dalemy@microsoft.com
-Requires-Python: >=3.11,<4.0
-Classifier: Development Status :: 3 - Alpha
+Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.14
 Classifier: Topic :: Software Development
 Classifier: Topic :: Software Development :: Testing
 Classifier: Topic :: Utilities
-Requires-Dist: toml (>=0.10.2,<0.11.0)
-Project-URL: Repository, https://github.com/Microsoft/localizationkit
+Requires-Python: <4.0,>=3.11
 Description-Content-Type: text/markdown
 
 # localizationkit
@@ -238,6 +234,24 @@ Opt-In: `true`
 
 Checks that strings do not contain Swift style interpolation values since these cannot be localized.
 
+## Token Adjacency
+
+Identifier: `token_adjacency`
+Opt-In: `true`
+
+Checks that attempts for pluralization or other similar operations are not in place, e.g. `Open %@s in the app` doesn't translate well. 
+
+_Note: It is recommended that this is run on latin alphabet using languages only._
+
+<details>
+    <summary>Configuration</summary>
+
+| Parameter | Type | Acceptable Values | Default | Details | 
+| --- | --- | --- | --- | --- |
+| `only_check_language` | str or `None` | Language code | `None` | Set to only check a particular language. **Recommended** |
+
+</details>
+
 ## Token Matching
 
 Identifier: `token_matching`
@@ -281,4 +295,3 @@ provided by the bot. You will only need to do this once across all repos using o
 This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
 For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or
 contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.
-

{localizationkit-3.0.1 → localizationkit-4.0.0}/README.md

@@ -211,6 +211,24 @@ Opt-In: `true`
 
 Checks that strings do not contain Swift style interpolation values since these cannot be localized.
 
+## Token Adjacency
+
+Identifier: `token_adjacency`
+Opt-In: `true`
+
+Checks that attempts for pluralization or other similar operations are not in place, e.g. `Open %@s in the app` doesn't translate well. 
+
+_Note: It is recommended that this is run on latin alphabet using languages only._
+
+<details>
+    <summary>Configuration</summary>
+
+| Parameter | Type | Acceptable Values | Default | Details | 
+| --- | --- | --- | --- | --- |
+| `only_check_language` | str or `None` | Language code | `None` | Set to only check a particular language. **Recommended** |
+
+</details>
+
 ## Token Matching
 
 Identifier: `token_matching`

localizationkit-4.0.0/SECURITY.md

@@ -0,0 +1,35 @@
+<!-- BEGIN MICROSOFT SECURITY.MD V0.0.1 BLOCK -->
+
+## Security
+
+Microsoft takes the security of our software products and services seriously, which includes all source code repositories managed through our GitHub organizations, which include [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet), [Xamarin](https://github.com/xamarin), and [many more](https://opensource.microsoft.com/).
+
+If you believe you have found a security vulnerability in any Microsoft-owned repository that meets Microsoft's [definition](https://docs.microsoft.com/en-us/previous-versions/tn-archive/cc751383(v=technet.10)) of a security vulnerability, please report it to us as described below.
+
+## Reporting Security Issues
+
+**Please do not report security vulnerabilities through public GitHub issues.** Instead, please report them to the Microsoft Security Response Center at [secure@microsoft.com](mailto:secure@microsoft.com).  If possible, encrypt your message with our PGP key; please download it from the [Microsoft Security Response Center PGP Key page](https://technet.microsoft.com/en-us/security/dn606155).
+
+You should receive a response within 24 hours. If for some reason you do not, please follow up via email to ensure we received your original message. Additional information can be found at [microsoft.com/msrc](https://www.microsoft.com/msrc).
+
+Please include the requested information listed below (as much as you can provide) to help us better understand the nature and scope of the possible issue:
+
+  * Type of issue (e.g. buffer overflow, SQL injection, cross-site scripting, etc.)
+  * Full paths of source file(s) related to the manifestation of the issue
+  * The location of the affected source code (tag/branch/commit or direct URL)
+  * Any special configuration required to reproduce the issue
+  * Step-by-step instructions to reproduce the issue
+  * Proof-of-concept or exploit code (if possible)
+  * Impact of the issue, including how an attacker might exploit the issue
+
+This information will help us triage your report more quickly.
+
+## Preferred Languages
+
+We prefer all communications to be in English.
+
+## Policy
+
+Microsoft follows the principle of [Coordinated Vulnerability Disclosure](https://www.microsoft.com/en-us/msrc/cvd).
+
+<!-- END MICROSOFT SECURITY.MD BLOCK -->

localizationkit-4.0.0/SUPPORT.md

@@ -0,0 +1,12 @@
+# Support
+
+## How to file issues
+
+This project uses GitHub Issues to track bugs and feature requests. Please search the existing
+issues before filing new issues to avoid duplicates.  For new issues, file your bug or
+feature request as a new Issue.
+
+
+## Microsoft Support Policy
+
+Support for this tool is limited to the resources listed above.

{localizationkit-3.0.1 → localizationkit-4.0.0}/localizationkit/__init__.py

@@ -1,32 +1,36 @@
 """Toolkit for validation of localized strings."""
 
 import inspect
-from typing import Type
 
+from localizationkit import tests
 from localizationkit.configuration import Configuration
 from localizationkit.exceptions import LocalizationKitException
 from localizationkit.localization_types import LocalizedCollection, LocalizedString
-from localizationkit.utility_types import TestResult
 from localizationkit.tests.test_case import LocalizationTestCase
+from localizationkit.utility_types import TestResult
 
-from localizationkit import tests
+__all__ = [
+    "Configuration",
+    "LocalizationKitException",
+    "LocalizationTestCase",
+    "LocalizedCollection",
+    "LocalizedString",
+    "TestResult",
+    "run_tests",
+]
 
 
-def _find_tests() -> list[Type[LocalizationTestCase]]:
+def _find_tests() -> list[type[LocalizationTestCase]]:
     """Find all the tests."""
 
-    test_module_names = [
-        module_name for module_name in dir(tests) if not module_name.startswith("__")
-    ]
+    test_module_names = [module_name for module_name in dir(tests) if not module_name.startswith("__")]
     test_modules = [getattr(tests, name) for name in test_module_names]
 
     names_seen: set[str] = set()
-    test_classes: list[Type[LocalizationTestCase]] = []
+    test_classes: list[type[LocalizationTestCase]] = []
 
     for module in test_modules:
-
         for reference_name in dir(module):
-
             reference = getattr(module, reference_name)
 
             if not inspect.isclass(reference):
@@ -39,9 +43,7 @@ def _find_tests() -> list[Type[LocalizationTestCase]]:
                 continue
 
             if reference.__name__ in names_seen:
-                raise LocalizationKitException(
-                    "At least 2 classes exist with the same name: " + reference.__name__
-                )
+                raise LocalizationKitException("At least 2 classes exist with the same name: " + reference.__name__)
 
             test_classes.append(reference)
 

{localizationkit-3.0.1 → localizationkit-4.0.0}/localizationkit/configuration.py

@@ -1,8 +1,7 @@
 """Configuration for localization tests."""
 
-from typing import Any, cast
-
-import toml
+import tomllib
+from typing import Any
 
 
 class Configuration:
@@ -54,5 +53,5 @@ class Configuration:
         :returns: The parsed configuration object
         """
 
-        with open(file_path, encoding="utf-8") as config_file:
-            return Configuration(cast(dict[str, Any], toml.load(config_file)))
+        with open(file_path, "rb") as config_file:
+            return Configuration(tomllib.load(config_file))

{localizationkit-3.0.1 → localizationkit-4.0.0}/localizationkit/localization_types.py

@@ -1,7 +1,8 @@
 """Types for localization."""
 
 import re
-from typing import ClassVar, Pattern
+from re import Pattern
+from typing import ClassVar
 
 
 class LocalizedString:
@@ -13,9 +14,7 @@ class LocalizedString:
     :param language_code: The language code for the language the string is in
     """
 
-    _TOKEN_REGEX: ClassVar[str] = (
-        r"(%(?:[0-9]+\$)?[0-9]*\.?[0-9]*(?:h|hh|l|ll|q|L|z|t|j){0,2}[dDuUxXoOfFeEgGcCsSaAp@])"
-    )
+    _TOKEN_REGEX: ClassVar[str] = r"(%(?:[0-9]+\$)?[0-9]*\.?[0-9]*(?:h|hh|l|ll|q|L|z|t|j){0,2}[dDuUxXoOfFeEgGcCsSaAp@])"
     _TOKEN_PATTERN: ClassVar[Pattern] = re.compile(_TOKEN_REGEX, flags=re.DOTALL)
 
     key: str
@@ -36,6 +35,14 @@ class LocalizedString:
         """
         return LocalizedString._TOKEN_PATTERN.findall(self.value)
 
+    def tokens_with_positions(self) -> list[tuple[str, int, int]]:
+        """Find and return the tokens in the string with their start and end position.
+
+        :returns: The list of tuples containing the token, start, and end for each.
+        """
+        tokens = LocalizedString._TOKEN_PATTERN.finditer(self.value)
+        return [(match.group(0), match.start(), match.end()) for match in tokens]
+
     def comment_tokens(self) -> list[str]:
         """Find and return the tokens in the comment string.
 
@@ -84,9 +91,7 @@ class LocalizedCollection:
 
         :returns: The list of strings with the matching language code
         """
-        return [
-            string for string in self.localized_strings if string.language_code == language_code
-        ]
+        return [string for string in self.localized_strings if string.language_code == language_code]
 
     def languages(self) -> list[str]:
         """Return the list of languages in the collection.

{localizationkit-3.0.1 → localizationkit-4.0.0}/localizationkit/tests/comment_linebreaks.py

@@ -24,7 +24,6 @@ class CommentLinebreaks(LocalizationTestCase):
         violations = []
 
         for string in self.collection.strings_for_language(self.configuration.default_language()):
-
             if string.comment is None:
                 continue
 

{localizationkit-3.0.1 → localizationkit-4.0.0}/localizationkit/tests/duplicate_keys.py

@@ -22,17 +22,12 @@ class DuplicateKeys(LocalizationTestCase):
 
         all_languages = self.get_setting("all_languages")
 
-        if all_languages:
-            languages_to_check = self.collection.languages()
-        else:
-            languages_to_check = [self.configuration.default_language()]
+        languages_to_check = self.collection.languages() if all_languages else [self.configuration.default_language()]
 
         for language in languages_to_check:
-
             keys: set[str] = set()
 
             for string in self.collection.strings_for_language(language):
-
                 if string.key in keys:
                     violations.append(
                         (

{localizationkit-3.0.1 → localizationkit-4.0.0}/localizationkit/tests/has_comments.py

@@ -24,7 +24,6 @@ class HasComments(LocalizationTestCase):
         violations = []
 
         for string in self.collection.strings_for_language(self.configuration.default_language()):
-
             if string.comment is None:
                 violations.append((f"Comment was empty: {string}", string.language_code))
                 continue
@@ -38,10 +37,7 @@ class HasComments(LocalizationTestCase):
                 )
                 continue
 
-            if (
-                minimum_comment_words >= 0
-                and len(string.comment.split(" ")) < minimum_comment_words
-            ):
+            if minimum_comment_words >= 0 and len(string.comment.split(" ")) < minimum_comment_words:
                 violations.append(
                     (
                         f"Comment did not meet minimum word count of {minimum_comment_words}: {string}",

{localizationkit-3.0.1 → localizationkit-4.0.0}/localizationkit/tests/has_value.py

@@ -21,9 +21,7 @@ class HasValue(LocalizationTestCase):
         violations: list[tuple[str, str]] = []
 
         if self.get_setting("default_language_only"):
-            test_collection = self.collection.strings_for_language(
-                self.configuration.default_language()
-            )
+            test_collection = self.collection.strings_for_language(self.configuration.default_language())
         else:
             test_collection = self.collection.localized_strings
 

{localizationkit-3.0.1 → localizationkit-4.0.0}/localizationkit/tests/invalid_tokens.py

@@ -21,10 +21,17 @@ class InvalidTokens(LocalizationTestCase):
 
         violations = []
 
-        invalid_token_pattern = re.compile(r"(%[^@%\.a-zA-Z0-9 ]+)", flags=re.DOTALL)
+        # "%%" is the printf escape for a literal percent sign and is always
+        # valid, so consume it first in the alternation. The capturing group
+        # only matches a "%" that starts something which is *not* a valid
+        # conversion (i.e. is followed by a character other than a conversion
+        # flag/specifier, "@", "%", ".", alphanumeric, or space). Matching "%%"
+        # via the first branch leaves an empty capture group, which is filtered
+        # out below, so "50%%)" no longer trips on the trailing "%)".
+        invalid_token_pattern = re.compile(r"%%|(%[^@%\.a-zA-Z0-9 ]+)", flags=re.DOTALL)
 
         for string in self.collection.localized_strings:
-            matches = invalid_token_pattern.findall(string.value)
+            matches = [match for match in invalid_token_pattern.findall(string.value) if match]
 
             # Any matches are a bad thing
             if matches and len(matches) > 0:

{localizationkit-3.0.1 → localizationkit-4.0.0}/localizationkit/tests/key_length.py

@@ -28,7 +28,6 @@ class KeyLength(LocalizationTestCase):
             return violations
 
         for string in self.collection.strings_for_language(self.configuration.default_language()):
-
             key = string.key
 
             if key is None:

{localizationkit-3.0.1 → localizationkit-4.0.0}/localizationkit/tests/objectivec_alternative_tokens.py

@@ -33,7 +33,6 @@ class ObjectivecAlternativeTokens(LocalizationTestCase):
         pattern = re.compile(r"(%(?:[0-9]+)(?:\.[0-9]+)?[@a-z][a-z]?)", flags=re.DOTALL)
 
         for string in self.collection.localized_strings:
-
             if pattern.findall(string.value):
                 violations.append(
                     (

{localizationkit-3.0.1 → localizationkit-4.0.0}/localizationkit/tests/swift_interpolation.py

@@ -28,7 +28,6 @@ class SwiftInterpolation(LocalizationTestCase):
         pattern = re.compile(r'\\\([^\)"]*\)', flags=re.DOTALL)
 
         for string in self.collection.localized_strings:
-
             if pattern.findall(string.value):
                 violations.append(
                     (

{localizationkit-3.0.1 → localizationkit-4.0.0}/localizationkit/tests/test_case.py

@@ -81,9 +81,7 @@ class LocalizationTestCase(abc.ABC):
             violations = self.run_test()
 
             if violations is None:
-                raise LocalizationKitException(
-                    f"Failed to get exceptions from test: {self.__class__.name()}"
-                )
+                raise LocalizationKitException(f"Failed to get exceptions from test: {self.__class__.name()}")
 
             if len(violations):
                 return TestResult.failure(self.__class__.name(), violations)

localizationkit-4.0.0/localizationkit/tests/token_adjacency.py

@@ -0,0 +1,60 @@
+"""Token matching."""
+
+from typing import Any
+
+from localizationkit.tests.test_case import LocalizationTestCase
+
+
+class TokenAdjacency(LocalizationTestCase):
+    """Check that nothing is directly adjacent to a token. e.g. Don't allow `You have new %@s` for plurals."""
+
+    @classmethod
+    def name(cls) -> str:
+        return "token_adjacency"
+
+    @classmethod
+    def is_opt_in(cls) -> bool:
+        """Check if the test is opt in or not."""
+        return True
+
+    @classmethod
+    def default_settings(cls) -> dict[str, Any]:
+        return {"only_check_language": None}
+
+    def run_test(self) -> list[tuple[str, str]]:
+
+        violations = []
+
+        only_check_language = self.get_setting("only_check_language")
+
+        allowed_characters = '.\n\r\t,:;" '
+
+        for string in self.collection.localized_strings:
+            if only_check_language and string.language_code != only_check_language:
+                continue
+
+            tokens = string.tokens_with_positions()
+
+            if not tokens or len(tokens) == 0:
+                continue
+
+            for token, start, end in tokens:
+                preceding_char = string.value[start - 1] if start > 0 else None
+                if preceding_char and preceding_char not in allowed_characters:
+                    violations.append(
+                        (
+                            f"Token '{token}' is directly preceded by '{preceding_char}' in string: {string}",
+                            string.language_code,
+                        )
+                    )
+
+                succeeding_char = string.value[end] if end < len(string.value) else None
+                if succeeding_char and succeeding_char not in allowed_characters:
+                    violations.append(
+                        (
+                            f"Token '{token}' is directly followed by '{succeeding_char}' in string: {string}",
+                            string.language_code,
+                        )
+                    )
+
+        return violations