impl/python/accepts_file.py
3,266 bytes · the Python implementation · view raw
from typing import List, Sequence
from .form_file_check_types import FileInfo
# ASCII whitespace only, so all three languages trim the same characters.
_SPACE = " \t\n\r\f\v"
_MIME_PUNCTUATION = "!#$&^_.+-"
def _lower(value: str) -> str:
return "".join(chr(ord(c) + 32) if "A" <= c <= "Z" else c for c in value)
def _upper(value: str) -> str:
return "".join(chr(ord(c) - 32) if "a" <= c <= "z" else c for c in value)
def _is_mime_name(value: str) -> bool:
# RFC 6838's restricted-name characters.
return value != "" and all(
"a" <= c <= "z" or "A" <= c <= "Z" or "0" <= c <= "9" or c in _MIME_PUNCTUATION for c in value
)
def accept_tokens(accept: str) -> List[str]:
"""The accept attribute's tokens, trimmed and lower-cased, empty ones
dropped. Anything that is not an extension, a MIME type or a type/*
wildcard raises."""
tokens: List[str] = []
for raw in accept.split(","):
token = _lower(raw.strip(_SPACE))
if token == "":
continue
ok = False
if token.startswith("."):
ext = token[1:]
ok = ext != "" and "/" not in ext and not any(c in _SPACE for c in ext)
else:
slash = token.find("/")
if slash > 0:
kind, subtype = token[:slash], token[slash + 1 :]
ok = _is_mime_name(kind) and (subtype == "*" or _is_mime_name(subtype))
if not ok:
raise ValueError(
'accept token "%s" is not an extension (.pdf), a MIME type (application/pdf) or a wildcard (image/*)'
% raw.strip(_SPACE)
)
tokens.append(token)
return tokens
def describe_accept(tokens: Sequence[str]) -> str:
"""What the accepted types are called in an error message: "a PDF",
"an image", "a PDF, JPG or PNG"."""
words: List[str] = []
for token in tokens:
if token.startswith("."):
word = _upper(token[1:])
elif token.endswith("/*"):
word = token[:-2]
else:
word = _upper(token[token.find("/") + 1 :])
if word not in words:
words.append(word)
listed = words[0] if len(words) == 1 else "%s or %s" % (", ".join(words[:-1]), words[-1])
first = words[0][0]
# A lower-case word is said as a word; an initialism letter by letter.
an = first in "aeiou" if "a" <= first <= "z" else first in "AEFHILMNORSX8"
return "%s %s" % ("an" if an else "a", listed)
def matches_accept(tokens: Sequence[str], file: FileInfo) -> bool:
if not tokens:
return True
name = _lower(file.name)
kind = _lower(file.mime_type)
for token in tokens:
if token.startswith("."):
if name.endswith(token):
return True
elif token.endswith("/*"):
if kind.startswith(token[:-1]):
return True
elif kind == token:
return True
return False
def accepts_file(accept: str, file: FileInfo) -> bool:
"""Whether a browser's file chooser would offer this file for an accept
attribute: by extension, exact MIME type or type/* wildcard, ignoring
case. An empty accept takes anything."""
return matches_accept(accept_tokens(accept), file)