debian-forge/osbuild/util/parsing.py

124 lines
3.6 KiB
Python

"""Helpers related to parsing"""
import os
import re
from typing import Dict, Tuple, Union
from urllib.parse import ParseResult, urlparse
def parse_size(s: str) -> Union[int, str]:
"""Parse a size string into a number or 'unlimited'.
Supported suffixes: kB, kiB, MB, MiB, GB, GiB, TB, TiB
"""
units = [
(r'^\s*(\d+)\s*kB$', 1000, 1),
(r'^\s*(\d+)\s*KiB$', 1024, 1),
(r'^\s*(\d+)\s*MB$', 1000, 2),
(r'^\s*(\d+)\s*MiB$', 1024, 2),
(r'^\s*(\d+)\s*GB$', 1000, 3),
(r'^\s*(\d+)\s*GiB$', 1024, 3),
(r'^\s*(\d+)\s*TB$', 1000, 4),
(r'^\s*(\d+)\s*TiB$', 1024, 4),
(r'^\s*(\d+)$', 1, 1),
(r'^unlimited$', "unlimited", 1),
]
for pat, base, power in units:
m = re.fullmatch(pat, s)
if m:
if isinstance(base, int):
return int(m.group(1)) * base ** power
if base == "unlimited":
return "unlimited"
raise TypeError(f"invalid size value: '{s}'")
def find_mount_root(url: ParseResult, args: Dict) -> os.PathLike:
"""
Parses the mount URL to extract the root path.
Parameters:
- url (ParseResult): The ParseResult object obtained from urlparse.
- args (Dict):A dictionary containing arguments including mounts and
path information as passed by osbuild.api.arguments()
"""
name = url.netloc
if name:
root = args["mounts"].get(name, {}).get("path")
if root is None:
raise ValueError(f"Unknown mount '{name}'")
else:
root = args["paths"]["mounts"]
return root
def parse_input(url: ParseResult, args: Dict) -> os.PathLike:
"""
Parses the input URL to extract the root path.
Parameters:
- url (ParseResult): The ParseResult object obtained from urlparse.
- args (Dict): A dictionary containing arguments including mounts and
path information as passed by osbuild.api.arguments()
"""
name = url.netloc
root = args["inputs"].get(name, {}).get("path")
if root is None:
raise ValueError(f"Unknown input '{name}'")
return root
def parse_location_into_parts(location: str, args: Dict) -> Tuple[str, str]:
"""
Parses the location URL to derive the corresponding root and url path.
Parameters:
- location (str): The location URL to be parsed. If the URL has no scheme,
then 'tree://' is implied
- args (Dict): A dictionary containing arguments including mounts and
path information as passed by osbuild.api.arguments()
"""
if "://" not in location:
location = f"tree://{location}"
url = urlparse(location)
scheme = url.scheme
if scheme == "tree":
root = args["tree"]
elif scheme == "mount":
root = find_mount_root(url, args)
elif scheme == "input":
root = parse_input(url, args)
else:
raise ValueError(f"Unsupported scheme '{scheme}'")
if not url.path.startswith("/"):
raise ValueError(f"url.path from location must start with '/', got: {url.path}")
return root, url.path
def parse_location(location: str, args: Dict) -> str:
"""
Parses the location URL to derive the corresponding file path.
Parameters:
- location (str): The location URL to be parsed.
- args (Dict): A dictionary containing arguments including mounts and
path information as passed by osbuild.api.arguments()
"""
root, urlpath = parse_location_into_parts(location, args)
path = os.path.relpath(urlpath, "/")
path = os.path.join(root, path)
path = os.path.normpath(path)
if urlpath.endswith("/"):
path = os.path.join(path, ".")
return path