Change pre-commit hooks and add tests for convert_parse

Author: CoolCat467

.pre-commit-config.yaml

@@ -16,18 +16,17 @@ repos:
       - id: check-merge-conflict
       - id: mixed-line-ending
       - id: check-case-conflict
+      - id: check-added-large-files
       - id: sort-simple-yaml
         files: .pre-commit-config.yaml
-  - repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 25.1.0
-    hooks:
-      - id: black
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.12.2
+    rev: v0.12.7
     hooks:
-      - id: ruff
+      - id: ruff-format
+      - id: ruff-check
         types: [file]
         types_or: [python, pyi, toml]
+        args: ["--show-fixes"]
   - repo: https://github.com/CoolCat467/badgie
     rev: v0.9.6
     hooks:

README.md

@@ -5,8 +5,6 @@ Script for simplifying the process of translating Language (.lang) files
 
 [![pre-commit.ci status](https://results.pre-commit.ci/badge/github/CoolCat467/Localization-Translation-Utility/main.svg)](https://results.pre-commit.ci/latest/github/CoolCat467/Localization-Translation-Utility/main)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit)](https://github.com/pre-commit/pre-commit)
-[![code style: black](https://img.shields.io/badge/code_style-black-000000.svg)](https://github.com/psf/black)
-[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
 
 <!-- END BADGIE TIME -->
 

src/localization_translation/convert_parse.py

@@ -67,7 +67,7 @@ class IndentFormat(NamedTuple):
 
 def lang_to_dict(
     lang_data: str,
-) -> tuple[dict[str, Any], CommentData]:
+) -> tuple[dict[int | str, Any], CommentData]:
     """Return data and comments from lua table."""
     all_tokens: list[lua_parser.Token] = list(lua_parser.tokenize_cst(lang_data))
     parser = lua_parser.Parser([t for t in all_tokens if not isinstance(t, lua_parser.CSTToken)])
@@ -160,11 +160,12 @@ def cartrage_return() -> None:
 
     root = cast("dict[str | int, Any]", data)
     roots: list[dict[str | int, Any]] = []
-    last_key: str | int | None = None
+    last_key: str | int | float | None = None
 
     in_blocks = 0
     has_keys = False
     in_unmarked = False
+    just_did_list_entry = False
     unmarked_index = 1
     unmarked_groups: list[tuple[bool, int]] = []
 
@@ -189,22 +190,36 @@ def cartrage_return() -> None:
 
             # Handle case where it's just a list and no identifiers
             # recorded
-            if all(isinstance(key, int) and not isinstance(value, dict) for key, value in root.items()):
+            if root and all(isinstance(key, int) and not isinstance(value, dict) for key, value in root.items()):
+                just_did_list_entry = True
                 true_start = min(map(int, root))
                 start = max(true_start, 1)
                 end = max(map(int, root))
                 # print(f'{root = }')
                 # print(f'{start = } {end = }')
+                unbroken_chain = True
                 for index in range(start, end + 1):
                     # print(f'{index = }', end=" ")
-                    value = root[index]
-                    value = f'"{value}"' if isinstance(value, str) else repr(value)
+                    value = root.get(index)
+                    if value is None:
+                        unbroken_chain = False
+                        continue
+                    if isinstance(value, str):
+                        value = f'"{value}"'
+                    elif isinstance(value, int | bool):
+                        value = repr(value).lower()
+                    else:
+                        raise ValueError(f"Unhandled key {type(value) = }")
+                    if not unbroken_chain:
+                        line += f"[{index}] = "
                     line += value
                     # No comma if end and does not need other recorded value like 0
                     if index != end or start != true_start:
                         line += ","
-                    cartrage_return()
+                        cartrage_return()
                 # print()
+            else:
+                just_did_list_entry = False
         elif token.type_ == TokenType.EndBracket:
             in_blocks -= 1
             in_unmarked, unmarked_index = unmarked_groups.pop()
@@ -225,23 +240,26 @@ def cartrage_return() -> None:
             if in_blocks > 0:
                 line += ","
             cartrage_return()
+            just_did_list_entry = False
         elif token.type_ == TokenType.Newline:
             cartrage_return()
         elif token.type_ in {TokenType.Identifier, TokenType.Numeric}:
             has_keys = True
             last_key = token.text
             if token.type_ == TokenType.Numeric:
                 line += f"[{token.text}]"
-                last_key = int(last_key)
+                last_key = int(last_key) if "." not in last_key else float(last_key)
             else:
                 line += token.text
             line += " = "
             if comments.keys[idx + 1].type_ != TokenType.StartBracket:
+                if last_key not in root:
+                    continue
                 value = root[last_key]
-                assert isinstance(value, str | int | float), "should not unpack collections"
+                assert isinstance(value, str | int | float | bool), "should not unpack collections"
 
-                if isinstance(value, int | float):
-                    line += repr(value)
+                if isinstance(value, int | float | bool):
+                    line += repr(value).lower()
                 else:
                     line += f'"{value}"'
                 if comments.keys[idx + 1].type_ != TokenType.EndBracket:
@@ -251,6 +269,8 @@ def cartrage_return() -> None:
             line += token.text
             cartrage_return()
         elif token.type_ == TokenType.Whitespace:
+            if just_did_list_entry:
+                continue
             line += token.text
         ##elif isinstance(token, lua_parser.Separator):
         ##    line += token.text
@@ -259,7 +279,7 @@ def cartrage_return() -> None:
 
     ##    write_dict(comments.keys)
 
-    return "\n".join(lines)
+    return "\n".join(lines) or "{}"
 
 
 def run() -> None:

src/localization_translation/extricate.py

@@ -86,7 +86,7 @@ def read_block(data: Any) -> tuple[list[str], list[str]]:
                     intersect = set(str(key)) & (set(CHAR_TYPE) | {SEP})
                     if intersect:
                         raise ValueError(
-                            'Dict key contains CHAR_TYPE value(s) "' f"{''.join(intersect)}" + '"',
+                            f'Dict key contains CHAR_TYPE value(s) "{"".join(intersect)}' + '"',
                         )
 
                     key = wrap_quotes(key, TYPE_CHAR[type(key).__name__])

src/localization_translation/lua_parser.py

@@ -390,7 +390,7 @@ def expect_or(self, options: Collection[str]) -> Token:
         token = self.next()
         if token.text not in options:
             self.fail(
-                f"Expected {list_or([repr(x) for x in options])}, got {token.text!r} ({token.location()})",
+                f"Expected {list_or([repr(x) for x in sorted(options)])}, got {token.text!r} ({token.location()})",
             )
         return token
 

src/localization_translation/mineos_auto_trans.py

@@ -238,7 +238,7 @@ async def abstract_translate(
             if isinstance(entry, str) and entry.endswith("English.lang"):
                 search.add(section)
 
-    print(f'\nSections with English.lang files: {", ".join(search)}\n')
+    print(f"\nSections with English.lang files: {', '.join(search)}\n")
 
     new_files = 1