Initial commit

.gitignore

@@ -0,0 +1,214 @@
+# File created using '.gitignore Generator' for Visual Studio Code: https://bit.ly/vscode-gig
+# Created by https://www.toptal.com/developers/gitignore/api/visualstudiocode,linux,python
+# Edit at https://www.toptal.com/developers/gitignore?templates=visualstudiocode,linux,python
+
+### Linux ###
+*~
+
+# temporary files which can be created if a process still has a handle open of a deleted file
+.fuse_hidden*
+
+# KDE directory preferences
+.directory
+
+# Linux trash folder which might appear on any partition or disk
+.Trash-*
+
+# .nfs files are created when an open file is removed but is still being accessed
+.nfs*
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+# End of https://www.toptal.com/developers/gitignore/api/visualstudiocode,linux,python
+
+# Custom rules (everything added below won't be overriden by 'Generate .gitignore File' if you use 'Update' option)
+

.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+    "python.formatting.provider": "black"
+}

README.md

@@ -0,0 +1,9 @@
+# renamebycsv
+
+A simple program that renames files by using a spreadsheet in CSV format as a dictionary for the files to be renamed.
+
+## Features
+
+ - Rename files recursively within a directory to a desired string
+ - Desired string is set by a CSV where one column is the original string, and another column is the string to replace the original string with
+ - Uses a REGEX capture group to select file and the portion of the filename to rename

renamebycsv.py

@@ -0,0 +1,133 @@
+#!/usr/bin/env python3
+
+import argparse
+import csv
+import os
+import re
+from typing import Iterable
+import logging
+
+
+def find_all_candidates(input_dir: str, regex: str, recursive: bool):
+    results = []
+    for subitem in os.listdir(input_dir):
+        subitem_path = os.path.join(input_dir, subitem)
+        match = re.match(regex, subitem)
+        if os.path.isdir(subitem_path) and recursive:
+            logging.debug(f'Checking directory "{subitem}"...')
+            results.extend(find_all_candidates(subitem_path, regex, recursive))
+        else:
+            if not match:
+                logging.debug(f'Ignoring "{subitem}"...')
+                continue
+            results.append((subitem_path, subitem, match))
+            logging.debug(f'Collecting "{subitem}"...')
+    return results
+
+
+def rename(
+    csv_path: str,
+    candidates: Iterable[tuple[str, str, re.Match]],
+    current: str,
+    become: str,
+    dry: bool,
+):
+    replacement_dict = {}
+    with open(csv_path, "r") as csv_fd:
+        reader = csv.reader(csv_fd)
+        current_col_ind = None
+        become_col_ind = None
+        for row in reader:
+            if current_col_ind is None and become_col_ind is None:
+                current_col_ind = row.index(current)
+                become_col_ind = row.index(become)
+                continue
+            if (
+                row[current_col_ind] in replacement_dict
+                and replacement_dict[row[current_col_ind]] != row[become_col_ind]
+            ):
+                raise Exception("Duplicate current key.")
+            replacement_dict[row[current_col_ind]] = row[become_col_ind]
+    for subitem_path, subitem, match in candidates:
+        original = subitem_path
+        objective = os.path.join(
+            os.path.dirname(subitem_path),
+            re.sub(match.re, replacement_dict[match.group(1)], subitem),
+        )
+        logging.info(f'Will rename "{original}" to "{os.path.basename(objective)}"')
+        if os.path.exists(objective):
+            logging.error(
+                f'Path at "{objective}" exists, not continuing. '
+                "Use -f to overwrite instead of stopping."
+            )
+            exit(1)
+        if not dry:
+            os.rename(original, objective)
+    if dry:
+        logging.info("No file names were modified.")
+
+
+def main():
+    program_name = "renamebycsv"
+    argparser = argparse.ArgumentParser(
+        program_name, "Rename all files by using a CSV as a dictionary."
+    )
+    argparser.add_argument(
+        "input_dir",
+        help="The directory containing the items that is to be renamed.",
+        metavar="I",
+    )
+    argparser.add_argument(
+        "regex",
+        help="The regex to apply to each file name. The first capture group is used to "
+        "perform the replacement.",
+        metavar="R",
+    )
+    argparser.add_argument(
+        "csv",
+        help="The CSV to use as the dictionary for the substitutions in file name.",
+        metavar="C",
+    )
+    argparser.add_argument(
+        "current",
+        help="The column header to look for the text matched by the regex.",
+        metavar="F",
+    )
+    argparser.add_argument(
+        "become", help="The column header to replace the regex match.", metavar="T"
+    )
+    argparser.add_argument(
+        "-r",
+        "--recursive",
+        help="Perform renaming action recursively",
+        action="store_true",
+    )
+    argparser.add_argument(
+        "-f",
+        "--force",
+        help="Overwrite files if file already exists",
+        action="store_true",
+    )
+    argparser.add_argument(
+        "-d", "--dry", help="Do not perform any renames", action="store_true"
+    )
+    argparser.add_argument(
+        "-V",
+        "--verbosity",
+        help="Set the logging verbosity",
+        required=False,
+        type=str,
+        default="INFO",
+    )
+
+    args = argparser.parse_args()
+    logging.basicConfig(
+        format="[%(filename)s %(asctime)s - %(levelname)s] %(message)s",
+        level=args.verbosity.upper(),
+    )
+    candidates = find_all_candidates(args.input_dir, args.regex, args.recursive)
+    rename(args.csv, candidates, args.current, args.become, args.dry)
+
+
+if __name__ == "__main__":
+    main()

tox.ini

@@ -0,0 +1,3 @@
+[flake8]
+max-line-length = 88
+extend-ignore = E203