localizationkit 3.0.1__tar.gz → 3.1.0__tar.gz

{localizationkit-3.0.1 → localizationkit-3.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: localizationkit
-Version: 3.0.1
+Version: 3.1.0
 Summary: String localization tests
 Home-page: https://github.com/Microsoft/localizationkit
 License: MIT
@@ -238,6 +238,24 @@ 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-3.0.1 → localizationkit-3.1.0}/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-3.0.1 → localizationkit-3.1.0}/localizationkit/localization_types.py

@@ -36,6 +36,14 @@ 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.
 

localizationkit-3.1.0/localizationkit/tests/token_adjacency.py

@@ -0,0 +1,62 @@
+"""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:
+                    if 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:
+                    if 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

{localizationkit-3.0.1 → localizationkit-3.1.0}/pyproject.toml

@@ -1,13 +1,11 @@
 [tool.poetry]
 name = "localizationkit"
-version = "3.0.1"
+version = "3.1.0"
 description = "String localization tests"
 
 license = "MIT"
 
-authors = [
-    "Dale Myers <dalemy@microsoft.com>"
-]
+authors = ["Dale Myers <dalemy@microsoft.com>"]
 
 readme = 'README.md'
 
@@ -26,7 +24,7 @@ classifiers = [
     'Programming Language :: Python :: 3.11',
     'Topic :: Software Development',
     'Topic :: Software Development :: Testing',
-    'Topic :: Utilities'
+    'Topic :: Utilities',
 ]
 
 [tool.poetry.dependencies]