First commmit
This commit is contained in:
0
packages/utils/README.md
Normal file
0
packages/utils/README.md
Normal file
17
packages/utils/pyproject.toml
Normal file
17
packages/utils/pyproject.toml
Normal file
@@ -0,0 +1,17 @@
|
||||
[project]
|
||||
name = "utils"
|
||||
version = "0.1.0"
|
||||
description = "Add your description here"
|
||||
readme = "README.md"
|
||||
authors = [
|
||||
{ name = "Anibal Angulo", email = "a8065384@banorte.com" }
|
||||
]
|
||||
requires-python = ">=3.12"
|
||||
dependencies = []
|
||||
|
||||
[project.scripts]
|
||||
normalize-filenames = "utils.normalize_filenames:app"
|
||||
|
||||
[build-system]
|
||||
requires = ["uv_build>=0.8.3,<0.9.0"]
|
||||
build-backend = "uv_build"
|
||||
2
packages/utils/src/utils/__init__.py
Normal file
2
packages/utils/src/utils/__init__.py
Normal file
@@ -0,0 +1,2 @@
|
||||
def hello() -> str:
|
||||
return "Hello from utils!"
|
||||
115
packages/utils/src/utils/normalize_filenames.py
Normal file
115
packages/utils/src/utils/normalize_filenames.py
Normal file
@@ -0,0 +1,115 @@
|
||||
"""Normalize filenames in a directory."""
|
||||
|
||||
import pathlib
|
||||
import re
|
||||
import unicodedata
|
||||
|
||||
import typer
|
||||
from rich.console import Console
|
||||
from rich.panel import Panel
|
||||
from rich.table import Table
|
||||
|
||||
app = typer.Typer()
|
||||
|
||||
|
||||
def normalize_string(s: str) -> str:
|
||||
"""Normalizes a string to be a valid filename."""
|
||||
# 1. Decompose Unicode characters into base characters and diacritics
|
||||
nfkd_form = unicodedata.normalize("NFKD", s)
|
||||
# 2. Keep only the base characters (non-diacritics)
|
||||
only_ascii = "".join([c for c in nfkd_form if not unicodedata.combining(c)])
|
||||
# 3. To lowercase
|
||||
only_ascii = only_ascii.lower()
|
||||
# 4. Replace spaces with underscores
|
||||
only_ascii = re.sub(r"\s+", "_", only_ascii)
|
||||
# 5. Remove any characters that are not alphanumeric, underscores, dots, or hyphens
|
||||
only_ascii = re.sub(r"[^a-z0-9_.-]", "", only_ascii)
|
||||
return only_ascii
|
||||
|
||||
|
||||
def truncate_string(s: str) -> str:
|
||||
"""given a string with /, return a string with only the text after the last /"""
|
||||
return pathlib.Path(s).name
|
||||
|
||||
|
||||
def remove_extension(s: str) -> str:
|
||||
"""Given a string, if it has a extension like .pdf, remove it and return the new string"""
|
||||
return str(pathlib.Path(s).with_suffix(""))
|
||||
|
||||
|
||||
def remove_duplicate_vowels(s: str) -> str:
|
||||
"""Removes consecutive duplicate vowels (a, e, i, o, u) from a string."""
|
||||
return re.sub(r"([aeiou])\1+", r"\1", s, flags=re.IGNORECASE)
|
||||
|
||||
|
||||
@app.callback(invoke_without_command=True)
|
||||
def normalize_filenames(
|
||||
directory: str = typer.Argument(
|
||||
..., help="The path to the directory containing files to normalize."
|
||||
),
|
||||
):
|
||||
"""Normalizes all filenames in a directory."""
|
||||
console = Console()
|
||||
console.print(
|
||||
Panel(
|
||||
f"Normalizing filenames in directory: [bold cyan]{directory}[/bold cyan]",
|
||||
title="[bold green]Filename Normalizer[/bold green]",
|
||||
expand=False,
|
||||
)
|
||||
)
|
||||
|
||||
source_path = pathlib.Path(directory)
|
||||
if not source_path.is_dir():
|
||||
console.print(f"[bold red]Error: Directory not found at {directory}[/bold red]")
|
||||
raise typer.Exit(code=1)
|
||||
|
||||
files_to_rename = [p for p in source_path.rglob("*") if p.is_file()]
|
||||
|
||||
if not files_to_rename:
|
||||
console.print(
|
||||
f"[bold yellow]No files found in {directory} to normalize.[/bold yellow]"
|
||||
)
|
||||
return
|
||||
|
||||
table = Table(title="File Renaming Summary")
|
||||
table.add_column("Original Name", style="cyan", no_wrap=True)
|
||||
table.add_column("New Name", style="magenta", no_wrap=True)
|
||||
table.add_column("Status", style="green")
|
||||
|
||||
for file_path in files_to_rename:
|
||||
original_name = file_path.name
|
||||
file_stem = file_path.stem
|
||||
file_suffix = file_path.suffix
|
||||
|
||||
normalized_stem = normalize_string(file_stem)
|
||||
new_name = f"{normalized_stem}{file_suffix}"
|
||||
|
||||
if new_name == original_name:
|
||||
table.add_row(
|
||||
original_name, new_name, "[yellow]Skipped (No change)[/yellow]"
|
||||
)
|
||||
continue
|
||||
|
||||
new_path = file_path.with_name(new_name)
|
||||
|
||||
# Handle potential name collisions
|
||||
counter = 1
|
||||
while new_path.exists():
|
||||
new_name = f"{normalized_stem}_{counter}{file_suffix}"
|
||||
new_path = file_path.with_name(new_name)
|
||||
counter += 1
|
||||
|
||||
try:
|
||||
file_path.rename(new_path)
|
||||
table.add_row(original_name, new_name, "[green]Renamed[/green]")
|
||||
except OSError as e:
|
||||
table.add_row(original_name, new_name, f"[bold red]Error: {e}[/bold red]")
|
||||
|
||||
console.print(table)
|
||||
console.print(
|
||||
Panel(
|
||||
f"[bold]Normalization complete.[/bold] Processed [bold blue]{len(files_to_rename)}[/bold blue] files.",
|
||||
title="[bold green]Complete[/bold green]",
|
||||
expand=False,
|
||||
)
|
||||
)
|
||||
0
packages/utils/src/utils/py.typed
Normal file
0
packages/utils/src/utils/py.typed
Normal file
Reference in New Issue
Block a user