cleanrbx 1.2__tar.gz

cleanrbx-1.2/PKG-INFO

@@ -0,0 +1,81 @@
+Metadata-Version: 2.4
+Name: cleanrbx
+Version: 1.2
+Summary: Delete files from a Rekordbox folder not present in exported Rekordbox XML.
+Author-email: Ádám Vincze <edboyww@gmail.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/edboyww/python-clean-rb-folder-by-xml
+Project-URL: Repository, https://github.com/edboyww/python-clean-rb-folder-by-xml
+Project-URL: Issues, https://github.com/edboyww/python-clean-rb-folder-by-xml/issues
+Keywords: rekordbox,xml,cleanup
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: End Users/Desktop
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Multimedia :: Sound/Audio
+Classifier: Topic :: Utilities
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: prompt-toolkit>=3.0
+
+# cleanrbx
+
+cleanrbx compares a Rekordbox XML export against a folder on disk and finds files that are no longer referenced by your Rekordbox library.
+
+## Features
+
+- Simulation mode by default (safe preview)
+- Optional deletion mode with confirmation
+- Path filtering with `--skip`
+- Detailed output on screen or in a file
+- XML path validation with `--check-xml`
+- Interactive folder selection when `--folder` is not provided
+
+## Installation
+
+```bash
+pip install cleanrbx
+```
+
+## Quick Start
+
+Simulate what would be removed:
+
+```bash
+cleanrbx rekordbox.xml
+```
+
+Clean a specific folder:
+
+```bash
+cleanrbx rekordbox.xml --folder "D:\\Music\\Rekordbox" --clean
+```
+
+Skip selected path fragments:
+
+```bash
+cleanrbx rekordbox.xml --skip backups,samples
+```
+
+Check XML paths that do not exist locally:
+
+```bash
+cleanrbx rekordbox.xml --check-xml
+```
+
+Show all options:
+
+```bash
+cleanrbx --help
+```
+
+## Notes
+
+- Streaming URLs in the XML are ignored.
+- `--clean` deletes files, so run without it first to review results.
+- Back up your library before using deletion mode.

cleanrbx-1.2/README.pypi.md

@@ -0,0 +1,56 @@
+# cleanrbx
+
+cleanrbx compares a Rekordbox XML export against a folder on disk and finds files that are no longer referenced by your Rekordbox library.
+
+## Features
+
+- Simulation mode by default (safe preview)
+- Optional deletion mode with confirmation
+- Path filtering with `--skip`
+- Detailed output on screen or in a file
+- XML path validation with `--check-xml`
+- Interactive folder selection when `--folder` is not provided
+
+## Installation
+
+```bash
+pip install cleanrbx
+```
+
+## Quick Start
+
+Simulate what would be removed:
+
+```bash
+cleanrbx rekordbox.xml
+```
+
+Clean a specific folder:
+
+```bash
+cleanrbx rekordbox.xml --folder "D:\\Music\\Rekordbox" --clean
+```
+
+Skip selected path fragments:
+
+```bash
+cleanrbx rekordbox.xml --skip backups,samples
+```
+
+Check XML paths that do not exist locally:
+
+```bash
+cleanrbx rekordbox.xml --check-xml
+```
+
+Show all options:
+
+```bash
+cleanrbx --help
+```
+
+## Notes
+
+- Streaming URLs in the XML are ignored.
+- `--clean` deletes files, so run without it first to review results.
+- Back up your library before using deletion mode.

cleanrbx-1.2/pyproject.toml

@@ -0,0 +1,46 @@
+[build-system]
+requires = ["setuptools>=69", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "cleanrbx"
+version = "1.2"
+description = "Delete files from a Rekordbox folder not present in exported Rekordbox XML."
+readme = {file ="README.pypi.md", content-type = "text/markdown"}
+requires-python = ">=3.10"
+dependencies = [
+  "prompt-toolkit>=3.0",
+]
+
+authors = [
+  { name = "Ádám Vincze", email = "edboyww@gmail.com" }
+]
+license = "MIT"
+keywords = ["rekordbox", "xml", "cleanup"]
+classifiers = [
+  "Development Status :: 4 - Beta",
+  "Intended Audience :: End Users/Desktop",
+  "Operating System :: OS Independent",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3 :: Only",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Topic :: Multimedia :: Sound/Audio",
+  "Topic :: Utilities",
+]
+
+[project.scripts]
+cleanrbx = "cleanrbx.cli:main"
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[project.urls]
+Homepage = "https://github.com/edboyww/python-clean-rb-folder-by-xml"
+Repository = "https://github.com/edboyww/python-clean-rb-folder-by-xml"
+Issues = "https://github.com/edboyww/python-clean-rb-folder-by-xml/issues"

cleanrbx-1.2/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

cleanrbx-1.2/src/cleanrbx/__init__.py

@@ -0,0 +1 @@
+__version__ = "1.2"

cleanrbx-1.2/src/cleanrbx/__main__.py

@@ -0,0 +1,4 @@
+from .cli import main
+
+if __name__ == "__main__":
+    raise SystemExit(main())

cleanrbx-1.2/src/cleanrbx/cli.py

@@ -0,0 +1,324 @@
+import argparse
+import os
+import xml.etree.ElementTree as ET
+from datetime import datetime
+from pathlib import Path
+from typing import List
+from urllib.parse import unquote
+
+import prompt_toolkit
+import prompt_toolkit.completion
+
+from . import __version__
+
+SEP = os.path.sep
+AutocompleteDict = dict[str, "AutocompleteDict | None"]
+
+
+def parse_args(argv: list[str] | None = None) -> argparse.Namespace:
+    parser = argparse.ArgumentParser(
+        prog="cleanrbx",
+        description=(
+            "Deletes files from your Rekordbox folder which are not in the library "
+            "based on an exported Rekordbox XML"
+        ),
+        add_help=True,
+    )
+    parser.add_argument(
+        "rekordbox_xml",
+        help="The file name of the XML file from Rekordbox",
+    )
+    parser.add_argument(
+        "-c", "--clean", action="store_true", help="do the cleaning", default=False
+    )
+    parser.add_argument(
+        "-s",
+        "--simulate",
+        action="store_true",
+        help="simulate the cleaning to see what would be deleted (default behaviour)",
+        default=True,
+    )
+    parser.add_argument(
+        "-f",
+        "--folder",
+        "--f",
+        dest="folder",
+        type=str,
+        action="store",
+        default=None,
+        help=(
+            "the folder to clean. If it is not given, the user will be able to set "
+            "the common folder based on the XML"
+        ),
+    )
+    parser.add_argument(
+        "--skip",
+        type=str,
+        action="store",
+        default=None,
+        help=(
+            "skip the cleaning for these strings in the folder paths, divided by ',' "
+            "(applies to both the local files and the paths in the XML file)"
+        ),
+    )
+    parser.add_argument(
+        "--details",
+        action="store_true",
+        help="show the detailed results (per file) on console instead of a summary",
+        default=False,
+    )
+    parser.add_argument(
+        "--details-file",
+        action="store_true",
+        help=(
+            "write the detailed results to a text file: either clean_results_<datetime>.txt "
+            "or simulate_results_<datetime>.txt"
+        ),
+        default=False,
+    )
+    parser.add_argument(
+        "--check-xml",
+        action="store_true",
+        help="check if the XML has any URLs which does not exist in the filesystem",
+        default=False,
+    )
+    parser.add_argument(
+        "-v", "--version", action="version", version=f"%(prog)s {__version__}"
+    )
+    return parser.parse_args(argv)
+
+
+def should_skip_path(input_arg: Path | str, skip_list: List[str] | None) -> bool:
+    try:
+        input_path = Path(input_arg)
+    except Exception:
+        return True
+
+    parent_str = str(input_path.parent).lower()
+    if not skip_list:
+        return False
+
+    for skip in skip_list:
+        if skip and skip.lower() in parent_str:
+            return True
+    return False
+
+
+def get_path_list_from_rekordbox_xml(xml_filename: str) -> List[str]:
+    try:
+        with open(xml_filename, "r", encoding="utf-8") as rxml:
+            xml_tree = ET.parse(rxml)
+    except FileNotFoundError:
+        print("XML file not found")
+        raise SystemExit(1)
+    except ET.ParseError:
+        print("Invalid XML file")
+        raise SystemExit(1)
+
+    xml_tracks = list(xml_tree.iter("TRACK"))
+    if not xml_tracks:
+        print("No TRACK elements found in the XML file")
+        raise SystemExit(1)
+
+    xml_paths: List[str] = []
+    for track in xml_tracks:
+        location = track.get("Location")
+        if location:
+            raw_path = unquote(location.replace("file://localhost/", ""))
+            if (
+                raw_path.startswith("tidal:")
+                or raw_path.startswith("soundcloud:")
+                or raw_path.startswith("itunes:")
+                or raw_path.startswith("beatsource:")
+                or raw_path.startswith("beatport:")
+            ):
+                continue
+            xml_paths.append(raw_path.replace("/", SEP))
+
+    return xml_paths
+
+
+def determine_common_path(paths: List[str]) -> str:
+    if not paths:
+        return ""
+    try:
+        return os.path.commonpath(paths)
+    except ValueError:
+        return ""
+
+
+def autocomplete_dict(path: Path) -> None | AutocompleteDict:
+    iter_dir = [item for item in path.iterdir() if item.is_dir()]
+    if len(iter_dir) == 0:
+        return None
+
+    folder_dict: AutocompleteDict = {}
+    for item in iter_dir:
+        try:
+            folder_dict[item.name + SEP] = autocomplete_dict(item)
+        except PermissionError:
+            folder_dict[item.name + SEP] = None
+    return folder_dict
+
+
+def main(argv: list[str] | None = None) -> int:
+    args = parse_args(argv)
+
+    xml_paths = get_path_list_from_rekordbox_xml(args.rekordbox_xml)
+    common_path = ""
+
+    if args.folder:
+        if not os.path.exists(args.folder):
+            print("Error: The given path does not exist. Please enter a valid path.\n")
+            return 1
+        in_xml = False
+        for path in xml_paths:
+            if args.folder in path:
+                common_path = args.folder
+                in_xml = True
+                break
+        if not in_xml:
+            print("Error: There are no files for the given path in the XML.\n")
+            return 1
+
+    if common_path == "":
+        initial_common_path = determine_common_path(xml_paths)
+        try:
+            autocomplete_data = autocomplete_dict(Path(initial_common_path))
+        except PermissionError:
+            print("ERROR: No permission to process common path in XML")
+            return 1
+        common_path = initial_common_path
+        if autocomplete_data is not None:
+            print(
+                "\nSet the folder you want to clean starting with the common folder for all "
+                "the files in the XML file. Press TAB to see the folders on a current level "
+                "and SPACE to get to the next level. You can set the path by pressing ENTER.\n"
+            )
+
+            completer = prompt_toolkit.completion.NestedCompleter.from_nested_dict(
+                autocomplete_data
+            )
+
+            while True:
+                print("SELECT THE PATH:")
+                input_raw = prompt_toolkit.prompt(initial_common_path, completer=completer)
+                input_path = input_raw.strip().replace(" ", "")
+                common_path = initial_common_path + input_path
+                if not os.path.exists(common_path):
+                    print("The path does not exist. Please enter a valid path.\n")
+                    continue
+                print(
+                    f"\nThe selected path is\n{common_path}\nIS THE PATH OKAY? (Y)es / (N)o:",
+                    end=" ",
+                )
+                inp = input().lower()
+                if inp not in ("y", "n"):
+                    print("Please enter 'Y' or 'N' to answer the question:", end=" ")
+                elif inp == "y":
+                    break
+
+    print(
+        f"\nStarting to {'clean' if args.clean else 'simulate cleaning'} from folder {common_path}"
+    )
+    file_postfix = ""
+    if args.details_file:
+        file_postfix = datetime.now().strftime("%Y%m%d_%H%M%S")
+        print(
+            "The details will be written to the following file: "
+            f"{'clean' if args.clean else 'simulate'}_details_{file_postfix}.txt"
+        )
+
+    if args.clean:
+        print(
+            "\nWE ARE ABOUT TO DELETE FILES FROM YOUR REKORDBOX LIBRARY! MAKE SURE YOUR LIBRARY "
+            "IS BACKED UP\nDo you want to proceed?\n\n(Y)es / (N)o"
+        )
+        while True:
+            inp = input().lower()
+            if inp not in ("y", "n"):
+                print("Please enter 'Y' or 'N' to answer the question")
+            else:
+                break
+        if inp == "n":
+            print("\nOk, bye!")
+            return 0
+
+    deleted_files = 0
+    deleted_details = (
+        "\n\nDeleted files:\n--------------\n"
+        if args.clean
+        else "\n\nFiles to be deleted:\n--------------------\n"
+    )
+    skipped_files = 0
+    skipped_details = "\n\n\nSkipped files:\n--------------\n"
+
+    skip_list: List[str] | None = None
+    if args.skip:
+        skip_list = [item.strip() for item in args.skip.split(",") if item.strip()]
+
+    for path in Path(common_path).rglob("*"):
+        if not path.is_file():
+            continue
+
+        resolved = str(path)
+        if should_skip_path(resolved, skip_list):
+            skipped_files += 1
+            skipped_details += f"\nS: {resolved.replace(common_path, '')}"
+            continue
+
+        if resolved not in xml_paths:
+            deleted_files += 1
+            rel = resolved.replace(common_path, "")
+            deleted_details += f"\nD: {rel}  (not listed in Rekordbox XML export)"
+            if args.clean:
+                path.unlink()
+
+    results = (
+        f"\nSUMMARY:\n========\n"
+        f"{'Deleted files' if args.clean else 'Files to be deleted'}: {deleted_files}\n"
+        f"Skipped files: {skipped_files}\n"
+    )
+
+    xml_paths_not_found: List[str] = []
+    xml_paths_not_found_details = ""
+    if args.check_xml:
+        for xml_path in xml_paths:
+            if not os.path.exists(xml_path):
+                xml_paths_not_found.append(xml_path)
+        if len(xml_paths_not_found) > 0:
+            results += f"Paths in XML not found: {len(xml_paths_not_found)}"
+            if args.details or args.details_file:
+                xml_paths_not_found_details += (
+                    "\n\n\nPaths in the XML file not found:\n"
+                    "---------------------------------\n"
+                )
+                for notfound in xml_paths_not_found:
+                    xml_paths_not_found_details += f"\nX: {notfound}"
+
+    print(results)
+
+    if args.details or args.details_file:
+        details = ""
+        if deleted_files:
+            details += deleted_details
+        if skipped_files:
+            details += skipped_details
+        if args.check_xml and xml_paths_not_found:
+            details += xml_paths_not_found_details
+        if args.details:
+            print(details)
+        if args.details_file:
+            results += details
+            with open(
+                f"{'clean' if args.clean else 'simulate'}_details_{file_postfix}.txt",
+                "w",
+                encoding="utf-8",
+            ) as details_file:
+                details_file.write(results)
+
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

cleanrbx-1.2/src/cleanrbx.egg-info/PKG-INFO

@@ -0,0 +1,81 @@
+Metadata-Version: 2.4
+Name: cleanrbx
+Version: 1.2
+Summary: Delete files from a Rekordbox folder not present in exported Rekordbox XML.
+Author-email: Ádám Vincze <edboyww@gmail.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/edboyww/python-clean-rb-folder-by-xml
+Project-URL: Repository, https://github.com/edboyww/python-clean-rb-folder-by-xml
+Project-URL: Issues, https://github.com/edboyww/python-clean-rb-folder-by-xml/issues
+Keywords: rekordbox,xml,cleanup
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: End Users/Desktop
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Multimedia :: Sound/Audio
+Classifier: Topic :: Utilities
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: prompt-toolkit>=3.0
+
+# cleanrbx
+
+cleanrbx compares a Rekordbox XML export against a folder on disk and finds files that are no longer referenced by your Rekordbox library.
+
+## Features
+
+- Simulation mode by default (safe preview)
+- Optional deletion mode with confirmation
+- Path filtering with `--skip`
+- Detailed output on screen or in a file
+- XML path validation with `--check-xml`
+- Interactive folder selection when `--folder` is not provided
+
+## Installation
+
+```bash
+pip install cleanrbx
+```
+
+## Quick Start
+
+Simulate what would be removed:
+
+```bash
+cleanrbx rekordbox.xml
+```
+
+Clean a specific folder:
+
+```bash
+cleanrbx rekordbox.xml --folder "D:\\Music\\Rekordbox" --clean
+```
+
+Skip selected path fragments:
+
+```bash
+cleanrbx rekordbox.xml --skip backups,samples
+```
+
+Check XML paths that do not exist locally:
+
+```bash
+cleanrbx rekordbox.xml --check-xml
+```
+
+Show all options:
+
+```bash
+cleanrbx --help
+```
+
+## Notes
+
+- Streaming URLs in the XML are ignored.
+- `--clean` deletes files, so run without it first to review results.
+- Back up your library before using deletion mode.

cleanrbx-1.2/src/cleanrbx.egg-info/SOURCES.txt

@@ -0,0 +1,11 @@
+README.pypi.md
+pyproject.toml
+src/cleanrbx/__init__.py
+src/cleanrbx/__main__.py
+src/cleanrbx/cli.py
+src/cleanrbx.egg-info/PKG-INFO
+src/cleanrbx.egg-info/SOURCES.txt
+src/cleanrbx.egg-info/dependency_links.txt
+src/cleanrbx.egg-info/entry_points.txt
+src/cleanrbx.egg-info/requires.txt
+src/cleanrbx.egg-info/top_level.txt

cleanrbx-1.2/src/cleanrbx.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

cleanrbx-1.2/src/cleanrbx.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+cleanrbx = cleanrbx.cli:main

cleanrbx-1.2/src/cleanrbx.egg-info/requires.txt

@@ -0,0 +1 @@
+prompt-toolkit>=3.0

cleanrbx-1.2/src/cleanrbx.egg-info/top_level.txt

@@ -0,0 +1 @@
+cleanrbx