Enable ruff, apply fixes

README.md

@@ -66,7 +66,7 @@ needles = [
 ]
 haystack_file_path = './addr_list.txt'
 
-addresses_found_list: List[str] = search_multiple_in_file(
+addresses_found_list: list[str] = search_multiple_in_file(
     haystack_file_path=haystack_file_path,
     needles=needled,
 )

pyproject.toml

@@ -42,3 +42,7 @@ used_addr_check = "used_addr_check.cli:main_cli"
 
 [tool.pyright]
 typeCheckingMode = "basic"
+
+[tool.ruff.lint]
+select = ["ALL"]
+ignore = ["D", "S", "TD", "FIX", "COM812"]

src/used_addr_check/__init__.py

@@ -1,17 +1,30 @@
 __VERSION__ = "0.1.6"
 __AUTHOR__ = "RecRanger"
 
-from .index_create import (  # noqa F401
-    load_or_generate_index,
+from .cli import main_cli
+from .index_create import (
     generate_index,
-    store_index_json,
     load_index_json,
-    store_index_parquet,
     load_index_parquet,
+    load_or_generate_index,
+    store_index_json,
+    store_index_parquet,
 )
-from .index_search import (  # noqa F401
+from .index_search import (
     search_in_file_with_index,
     search_multiple_in_file,  # <- main library function
 )
-from .index_types import IndexEntry  # noqa F401
-from .cli import main_cli  # noqa F401
+from .index_types import IndexEntry
+
+__all__ = [
+    "IndexEntry",
+    "generate_index",
+    "load_index_json",
+    "load_index_parquet",
+    "load_or_generate_index",
+    "main_cli",
+    "search_in_file_with_index",
+    "search_multiple_in_file",
+    "store_index_json",
+    "store_index_parquet",
+]

src/used_addr_check/cli.py

@@ -1,16 +1,16 @@
-# from used_addr_check.download_list import download_list, BITCOIN_LIST_URL
+import argparse
+import sys
+from pathlib import Path
+
 from used_addr_check import __VERSION__
+from used_addr_check.defaults import DEFAULT_INDEX_CHUNK_SIZE
+from used_addr_check.download_list import BITCOIN_LIST_URL, download_list
 from used_addr_check.index_create import load_or_generate_index
 from used_addr_check.index_search import search_multiple_in_file
 from used_addr_check.scan_file import scan_file_for_used_addresses
-from used_addr_check.defaults import DEFAULT_INDEX_CHUNK_SIZE
-
-import argparse
-import sys
-from pathlib import Path
 
 
-def main_cli():
+def main_cli() -> None:
     parser = argparse.ArgumentParser(
         description="CLI for file processing and searching"
     )
@@ -32,23 +32,21 @@ def main_cli():
     subparsers = parser.add_subparsers(dest="command")
 
     # # Subparser for the 'download' command
-    # download_parser = subparsers.add_parser(
-    #     "download", help="Download the file"
-    # )
-    # download_parser.add_argument(
-    #     "-o",
-    #     "--output",
-    #     dest="output_path",
-    #     required=True,
-    #     help="Output file path (should end in .gz)",
-    # )
-    # download_parser.add_argument(
-    #     "-u",
-    #     "--url",
-    #     dest="url",
-    #     default=BITCOIN_LIST_URL,
-    #     help="URL to download the file from",
-    # )
+    download_parser = subparsers.add_parser("download", help="Download the file")
+    download_parser.add_argument(
+        "-o",
+        "--output",
+        dest="output_path",
+        required=True,
+        help="Output file path (should end in .gz)",
+    )
+    download_parser.add_argument(
+        "-u",
+        "--url",
+        dest="url",
+        default=BITCOIN_LIST_URL,
+        help="URL to download the file from",
+    )
 
     # Subparser for the 'version' command (subparser not really used)
     subparsers.add_parser(
@@ -59,7 +57,10 @@ def main_cli():
     # Subparser for the 'index' command
     index_parser = subparsers.add_parser(
         "index",
-        help="Index a haystack 'used addresses' file, save it to orig_name.txt.index.json",  # noqa
+        help=(
+            "Index a haystack 'used addresses' file, "
+            "and save it to orig_name.txt.index.json"
+        ),
     )
     index_parser.add_argument(
         "-f",
@@ -90,7 +91,7 @@ def main_cli():
     # Subparser for the 'scan_file' command
     scan_file_parser = subparsers.add_parser(
         "scan_file",
-        help="Scan a file for bitcoin addresses, and see which ones have been used.",  # noqa
+        help="Scan a file for bitcoin addresses, and see which ones have been used.",
     )
     scan_file_parser.add_argument(
         "-f",
@@ -111,7 +112,7 @@ def main_cli():
     args = parser.parse_args()
 
     if args.command == "version" or args.version:
-        print(f"used_addr_scan version v{__VERSION__}")
+        print(f"used_addr_scan version v{__VERSION__}")  # noqa: T201
         sys.exit(0)
     elif args.command == "index":
         load_or_generate_index(
@@ -125,8 +126,8 @@ def main_cli():
             args.needles,
             index_chunk_size=args.index_chunk_size,
         )
-    # elif args.command == "download":
-    #     download_list(Path(args.output_path))
+    elif args.command == "download":
+        download_list(Path(args.output_path))
     elif args.command == "scan_file":
         scan_file_for_used_addresses(
             Path(args.haystack_file_path),

src/used_addr_check/download_list.py

@@ -1,16 +1,16 @@
 from pathlib import Path
 
 import backoff
-from loguru import logger
 import requests
+from loguru import logger
 
 # TODO: This download feature isn't really production-ready.
 # TODO: Make the downloader as fast as wget.
 # TODO: Create an extract function.
 
 
 BITCOIN_LIST_URL = (
-    "http://alladdresses.loyce.club/all_Bitcoin_addresses_ever_used_sorted.txt.gz"  # noqa
+    "http://alladdresses.loyce.club/all_Bitcoin_addresses_ever_used_sorted.txt.gz"
 )
 
 
@@ -31,6 +31,7 @@ def _get_remote_file_size(url: str) -> int:
 )
 def _download_file(url: str, dest: Path) -> Path:
     """Download a file from a URL to a local destination, resuming if possible.
+
     If the file already exists and is fully downloaded, do nothing.
     If the file is partially downloaded, resume the download.
     If the file does not exist, download it from scratch.
@@ -40,22 +41,16 @@ def _download_file(url: str, dest: Path) -> Path:
     """
     total_size = _get_remote_file_size(url)
 
-    if dest.is_dir():
-        destination = dest / Path(url).name
-    else:
-        destination = dest
+    destination = (dest / Path(url).name) if dest.is_dir() else dest
 
-    # Check how much of the file has already been downloaded
-    if destination.exists():
-        current_size = destination.stat().st_size
-    else:
-        current_size = 0
+    # Check how much of the file has already been downloaded.
+    current_size = destination.stat().st_size if destination.exists() else 0
 
     # If file is already fully downloaded
     if current_size == total_size:
         logger.info("File already downloaded.")
         return destination
-    elif current_size > total_size:
+    if current_size > total_size:
         logger.warning(
             f"File size mismatch. Current size: {current_size:,} bytes, "
             f"Total size: {total_size:,} bytes"
@@ -72,7 +67,7 @@ def _download_file(url: str, dest: Path) -> Path:
     with requests.get(url, headers=headers, stream=True) as r:
         r.raise_for_status()
         # Open the file in append mode, create if does not exist
-        with open(destination, "ab") as f:
+        with destination.open("ab") as f:
             for chunk in r.iter_content(chunk_size=8192):
                 if chunk:  # filter out keep-alive new chunks
                     f.write(chunk)

src/used_addr_check/index_create.py

@@ -1,18 +1,17 @@
 from pathlib import Path
-from typing import List
 
-from loguru import logger
 import orjson
 import polars as pl
+from loguru import logger
 from tqdm import tqdm
 
-from used_addr_check.index_types import IndexEntry
 from used_addr_check.defaults import DEFAULT_INDEX_CHUNK_SIZE
+from used_addr_check.index_types import IndexEntry
 
 
 def generate_index(
     haystack_file_path: Path, index_chunk_size: int = DEFAULT_INDEX_CHUNK_SIZE
-) -> List[IndexEntry]:
+) -> list[IndexEntry]:
     """
     Generates an index for a large sorted text file, storing every
     `index_chunk_size` lines.
@@ -25,7 +24,7 @@ def generate_index(
     - List[IndexEntry]: A list of tuples containing
             line text, byte offset, and line number.
     """
-    index: List[IndexEntry] = []
+    index: list[IndexEntry] = []
     haystack_file_size = haystack_file_path.stat().st_size
     with (
         tqdm(
@@ -35,7 +34,7 @@ def generate_index(
             total=haystack_file_size,
             desc="Indexing haystack file",
         ) as progress_bar,
-        open(haystack_file_path, "rb") as file,
+        haystack_file_path.open("rb") as file,
     ):
         offset = 0
         for line_number, line in enumerate(file):
@@ -56,7 +55,7 @@ def generate_index(
     return index
 
 
-def store_index_json(index: List[IndexEntry], index_json_file_path: Path) -> None:
+def store_index_json(index: list[IndexEntry], index_json_file_path: Path) -> None:
     """
     Stores the index in a file for later use.
 
@@ -65,11 +64,11 @@ def store_index_json(index: List[IndexEntry], index_json_file_path: Path) -> Non
     - index_file_path (Path): The path to store the index.
     """
 
-    with open(index_json_file_path, "wb") as file:
+    with index_json_file_path.open("wb") as file:
         file.write(orjson.dumps(index))
 
 
-def load_index_json(index_json_file_path: Path) -> List[IndexEntry]:
+def load_index_json(index_json_file_path: Path) -> list[IndexEntry]:
     """
     Loads an index from a JSON file.
 
@@ -79,12 +78,12 @@ def load_index_json(index_json_file_path: Path) -> List[IndexEntry]:
     Returns:
     - List[IndexEntry]: The loaded index.
     """
-    with open(index_json_file_path, "rb") as file:
-        raw_read: List[dict] = orjson.loads(file.read())
+    with index_json_file_path.open("rb") as file:
+        raw_read: list[dict] = orjson.loads(file.read())
     return [IndexEntry(**val) for val in raw_read]
 
 
-def store_index_parquet(index: List[IndexEntry], index_parquet_file_path: Path) -> None:
+def store_index_parquet(index: list[IndexEntry], index_parquet_file_path: Path) -> None:
     """
     Stores the index in a parquet file for later use.
 
@@ -97,7 +96,7 @@ def store_index_parquet(index: List[IndexEntry], index_parquet_file_path: Path)
     df.write_parquet(index_parquet_file_path)
 
 
-def load_index_parquet(index_parquet_file_path: Path) -> List[IndexEntry]:
+def load_index_parquet(index_parquet_file_path: Path) -> list[IndexEntry]:
     """
     Loads an index from a parquet file.
 
@@ -114,8 +113,9 @@ def load_index_parquet(index_parquet_file_path: Path) -> List[IndexEntry]:
 def load_or_generate_index(
     haystack_file_path: Path,
     index_chunk_size: int = DEFAULT_INDEX_CHUNK_SIZE,
+    *,
     force_recreate: bool = False,
-) -> List[IndexEntry]:
+) -> list[IndexEntry]:
     """Attempts to load an index from a file, or generates one if it doesn't,
     or if `force_recreate` is enabled.
 
@@ -153,4 +153,5 @@ def load_or_generate_index(
         logger.info(f"Index loaded with {len(index):,} entries")
         return index
 
-    raise Exception("This should be unreachable.")
+    msg = "This should be unreachable."
+    raise RuntimeError(msg)