1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243
|
import asyncio
import mimetypes
import os
import pathlib
import sys
from typing import ( # noqa
IO,
TYPE_CHECKING,
Any,
Awaitable,
Callable,
List,
Optional,
Union,
cast,
)
from . import hdrs
from .abc import AbstractStreamWriter
from .typedefs import LooseHeaders
from .web_exceptions import (
HTTPNotModified,
HTTPPartialContent,
HTTPPreconditionFailed,
HTTPRequestRangeNotSatisfiable,
)
from .web_response import StreamResponse
__all__ = ("FileResponse",)
if TYPE_CHECKING: # pragma: no cover
from .web_request import BaseRequest
_T_OnChunkSent = Optional[Callable[[bytes], Awaitable[None]]]
NOSENDFILE = bool(os.environ.get("AIOHTTP_NOSENDFILE"))
class FileResponse(StreamResponse):
"""A response object can be used to send files."""
def __init__(
self,
path: Union[str, pathlib.Path],
chunk_size: int = 256 * 1024,
status: int = 200,
reason: Optional[str] = None,
headers: Optional[LooseHeaders] = None,
) -> None:
super().__init__(status=status, reason=reason, headers=headers)
if isinstance(path, str):
path = pathlib.Path(path)
self._path = path
self._chunk_size = chunk_size
async def _sendfile_fallback(
self, writer: AbstractStreamWriter, fobj: IO[Any], offset: int, count: int
) -> AbstractStreamWriter:
# To keep memory usage low,fobj is transferred in chunks
# controlled by the constructor's chunk_size argument.
chunk_size = self._chunk_size
loop = asyncio.get_event_loop()
await loop.run_in_executor(None, fobj.seek, offset)
chunk = await loop.run_in_executor(None, fobj.read, chunk_size)
while chunk:
await writer.write(chunk)
count = count - chunk_size
if count <= 0:
break
chunk = await loop.run_in_executor(None, fobj.read, min(chunk_size, count))
await writer.drain()
return writer
async def _sendfile(
self, request: "BaseRequest", fobj: IO[Any], offset: int, count: int
) -> AbstractStreamWriter:
writer = await super().prepare(request)
assert writer is not None
if NOSENDFILE or sys.version_info < (3, 7) or self.compression:
return await self._sendfile_fallback(writer, fobj, offset, count)
loop = request._loop
transport = request.transport
assert transport is not None
try:
await loop.sendfile(transport, fobj, offset, count)
except NotImplementedError:
return await self._sendfile_fallback(writer, fobj, offset, count)
await super().write_eof()
return writer
async def prepare(self, request: "BaseRequest") -> Optional[AbstractStreamWriter]:
filepath = self._path
gzip = False
if "gzip" in request.headers.get(hdrs.ACCEPT_ENCODING, ""):
gzip_path = filepath.with_name(filepath.name + ".gz")
if gzip_path.is_file():
filepath = gzip_path
gzip = True
loop = asyncio.get_event_loop()
st = await loop.run_in_executor(None, filepath.stat)
modsince = request.if_modified_since
if modsince is not None and st.st_mtime <= modsince.timestamp():
self.set_status(HTTPNotModified.status_code)
self._length_check = False
# Delete any Content-Length headers provided by user. HTTP 304
# should always have empty response body
return await super().prepare(request)
unmodsince = request.if_unmodified_since
if unmodsince is not None and st.st_mtime > unmodsince.timestamp():
self.set_status(HTTPPreconditionFailed.status_code)
return await super().prepare(request)
if hdrs.CONTENT_TYPE not in self.headers:
ct, encoding = mimetypes.guess_type(str(filepath))
if not ct:
ct = "application/octet-stream"
should_set_ct = True
else:
encoding = "gzip" if gzip else None
should_set_ct = False
status = self._status
file_size = st.st_size
count = file_size
start = None
ifrange = request.if_range
if ifrange is None or st.st_mtime <= ifrange.timestamp():
# If-Range header check:
# condition = cached date >= last modification date
# return 206 if True else 200.
# if False:
# Range header would not be processed, return 200
# if True but Range header missing
# return 200
try:
rng = request.http_range
start = rng.start
end = rng.stop
except ValueError:
# https://tools.ietf.org/html/rfc7233:
# A server generating a 416 (Range Not Satisfiable) response to
# a byte-range request SHOULD send a Content-Range header field
# with an unsatisfied-range value.
# The complete-length in a 416 response indicates the current
# length of the selected representation.
#
# Will do the same below. Many servers ignore this and do not
# send a Content-Range header with HTTP 416
self.headers[hdrs.CONTENT_RANGE] = f"bytes */{file_size}"
self.set_status(HTTPRequestRangeNotSatisfiable.status_code)
return await super().prepare(request)
# If a range request has been made, convert start, end slice
# notation into file pointer offset and count
if start is not None or end is not None:
if start < 0 and end is None: # return tail of file
start += file_size
if start < 0:
# if Range:bytes=-1000 in request header but file size
# is only 200, there would be trouble without this
start = 0
count = file_size - start
else:
# rfc7233:If the last-byte-pos value is
# absent, or if the value is greater than or equal to
# the current length of the representation data,
# the byte range is interpreted as the remainder
# of the representation (i.e., the server replaces the
# value of last-byte-pos with a value that is one less than
# the current length of the selected representation).
count = (
min(end if end is not None else file_size, file_size) - start
)
if start >= file_size:
# HTTP 416 should be returned in this case.
#
# According to https://tools.ietf.org/html/rfc7233:
# If a valid byte-range-set includes at least one
# byte-range-spec with a first-byte-pos that is less than
# the current length of the representation, or at least one
# suffix-byte-range-spec with a non-zero suffix-length,
# then the byte-range-set is satisfiable. Otherwise, the
# byte-range-set is unsatisfiable.
self.headers[hdrs.CONTENT_RANGE] = f"bytes */{file_size}"
self.set_status(HTTPRequestRangeNotSatisfiable.status_code)
return await super().prepare(request)
status = HTTPPartialContent.status_code
# Even though you are sending the whole file, you should still
# return a HTTP 206 for a Range request.
self.set_status(status)
if should_set_ct:
self.content_type = ct # type: ignore
if encoding:
self.headers[hdrs.CONTENT_ENCODING] = encoding
if gzip:
self.headers[hdrs.VARY] = hdrs.ACCEPT_ENCODING
self.last_modified = st.st_mtime # type: ignore
self.content_length = count
self.headers[hdrs.ACCEPT_RANGES] = "bytes"
real_start = cast(int, start)
if status == HTTPPartialContent.status_code:
self.headers[hdrs.CONTENT_RANGE] = "bytes {}-{}/{}".format(
real_start, real_start + count - 1, file_size
)
if request.method == hdrs.METH_HEAD or self.status in [204, 304]:
return await super().prepare(request)
fobj = await loop.run_in_executor(None, filepath.open, "rb")
if start: # be aware that start could be None or int=0 here.
offset = start
else:
offset = 0
try:
return await self._sendfile(request, fobj, offset, count)
finally:
await loop.run_in_executor(None, fobj.close)
|