From 1749dbffc7912b78d0d1c748663b9123c90cd97d Mon Sep 17 00:00:00 2001
From: Paillat <me@paillat.dev>
Date: Sat, 3 May 2025 18:13:58 +0200
Subject: [PATCH] Refactor code structure and enhance documentation in main
 modules

- Updated `pyproject.toml` to include configuration for `ruff` linting tool.
- Improved `download_build.py` by adding a docstring to the `dowload` function.
- Refactored `__main__.py` for clarity and consistency in path handling.
- Enhanced `extract.py` with detailed docstrings for error classes and functions.
---
 pyproject.toml        | 27 +++++++++++++++++++++++++++
 src/__main__.py       |  9 ++++-----
 src/download_build.py |  6 +++++-
 src/extract.py        | 23 +++++++++++------------
 4 files changed, 47 insertions(+), 18 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index 25b6a61..a530a0e 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -14,6 +14,33 @@ dev = [
 ]
 
 [tool.basedpyright]
+pythonVersion = "3.13"
 typeCheckingMode = "all"
 reportUnusedCallResult = false
 reportAny = false
+
+[tool.ruff]
+target-version = "py313"
+line-length = 120
+indent-width = 4
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+skip-magic-trailing-comma = false
+line-ending = "auto"
+docstring-code-format = false
+docstring-code-line-length = "dynamic"
+
+[tool.ruff.lint]
+select = ["ALL"]
+extend-ignore = [
+    "D203",
+    "D213",
+    "COM812",
+    "EM101",
+    "TRY003",
+    "T201",
+    "D100",
+    "D400"
+]
\ No newline at end of file
diff --git a/src/__main__.py b/src/__main__.py
index 950dce7..dc98d15 100644
--- a/src/__main__.py
+++ b/src/__main__.py
@@ -1,20 +1,19 @@
 # Copyright (c) Paillat-dev
 # SPDX-License-Identifier: MIT
 
-import os
-import pathlib
 import hashlib
 import json
-
+import pathlib
 import sys
 from typing import Any
 
-from extract import extract_emojis_from_str
 from download_build import dowload
+from extract import extract_emojis_from_str
 
 
 def main() -> None:
-    build_path = pathlib.Path(os.getcwd()) / "build"
+    """Download the latest discord build and extract emojis."""
+    build_path = pathlib.Path.cwd() / "build"
     build_path.mkdir(exist_ok=True)
 
     out_path = build_path / "emojis.json"
diff --git a/src/download_build.py b/src/download_build.py
index 8ec3e22..f7a5330 100644
--- a/src/download_build.py
+++ b/src/download_build.py
@@ -7,7 +7,11 @@ URL = "https://raw.githubusercontent.com/Discord-Datamining/Discord-Datamining/r
 
 
 def dowload() -> str:
+    """Download the latest discord build from the datamining repository.
+
+    Returns the content of the file as a string.
+    """
     print("Downloading the latest discord build")
-    response = requests.get(URL)
+    response = requests.get(URL, timeout=10)
     response.raise_for_status()
     return response.text
diff --git a/src/extract.py b/src/extract.py
index 51251b4..7274674 100644
--- a/src/extract.py
+++ b/src/extract.py
@@ -3,11 +3,11 @@
 
 import json
 import re
-from warnings import warn
-import json5
-from typing import Any
 from collections.abc import Mapping, Sequence
+from typing import Any
+from warnings import warn
 
+import json5
 
 type AnyDict = dict[Any, Any]  # pyright: ignore[reportExplicitAny]
 type AnyList = list[Any]  # pyright: ignore[reportExplicitAny]
@@ -17,34 +17,32 @@ PATTERN = re.compile(r"""(?<=\(')(\{"emojis".*?\})(?='\))""")
 
 
 class ExtractError(Exception):
-    pass
+    """Base class for all extract errors."""
 
 
 class NotFoundError(ExtractError):
-    pass
+    """No matches found in the build."""
 
 
 class MultipleFoundError(ExtractError):
-    pass
+    """Multiple matches found in the build."""
 
 
 _SUR = re.compile(r"[\uD800-\uDFFF]")
 
 
 def report_surrogates(node: AnyDict | AnyList | AnyTuple | str, path: str = "") -> None:
-    """
-    Recursively walk *node* (dict / list / tuple / str) and print the location
-    and code-point of every UTF-16 surrogate half it encounters.
+    r"""Recursively walk *node* (dict / list / tuple / str) and print the location and code-point of every UTF-16 surrogate half it encounters.
 
     >>> data = {"a": "OK", "b": ["\\uD83D", {"c": "x\\uDE00y"}]}
     >>> report_surrogates(data)
     b[0] : U+D83D
     b[1].c : U+DE00
-    """
+    """  # noqa: E501
     if isinstance(node, str):
         for m in _SUR.finditer(node):
             cp = ord(m.group())
-            warn(f"Surrogate found at {path or '<root>'} : U+{cp:04X}")
+            warn(f"Surrogate found at {path or '<root>'} : U+{cp:04X}", SyntaxWarning, 2)
         return
 
     if isinstance(node, Mapping):
@@ -59,12 +57,13 @@ def report_surrogates(node: AnyDict | AnyList | AnyTuple | str, path: str = "")
 
 
 def extract_emojis_from_str(content: str) -> AnyDict:
+    """Extract emojis from a string containing the discord build."""
     print("Searching for emojis...")
     matches: list[str] = PATTERN.findall(content)
 
     if len(matches) == 0:
         raise NotFoundError("No matches found")
-    elif len(matches) > 1:
+    if len(matches) > 1:
         raise MultipleFoundError("Multiple matches found")
 
     match: str = matches[0]