Rewrite media caching (old image provider)
- Doesn't use pyotherside's image provider feature, for more flexibility and simplicity - Suitable for supporting matrix media events and more later - Avoid a lot of duplicate files that the old cache created due to server not returning what we expect, mistakes in Python/QML code, etc - Changed file structure (e.g. thumbnails/32x32/<mxc id> instead of thumbnails/<mxc id>.32.32.crop) - Backend.wait_until_account_exist: start issuing warnings if the function runs for more than 10s, which means in most case a bad user ID was passed - New HMxcImage QML component, used in H(User/Room)Avatar
This commit is contained in:
miruka
@@ -38,12 +38,7 @@ class App:
|
||||
self.backend = Backend(app=self)
|
||||
self.debug = False
|
||||
|
||||
from .image_provider import ImageProvider
|
||||
self.image_provider = ImageProvider(self)
|
||||
pyotherside.set_image_provider(self.image_provider.get)
|
||||
|
||||
self.loop = asyncio.get_event_loop()
|
||||
|
||||
self.loop = asyncio.get_event_loop()
|
||||
self.loop_thread = Thread(target=self._loop_starter)
|
||||
self.loop_thread.start()
|
||||
|
||||
|
||||
@@ -109,6 +109,7 @@ class Backend:
|
||||
|
||||
|
||||
async def wait_until_client_exists(self, user_id: str = "") -> None:
|
||||
loops = 0
|
||||
while True:
|
||||
if user_id and user_id in self.clients:
|
||||
return
|
||||
@@ -116,7 +117,12 @@ class Backend:
|
||||
if not user_id and self.clients:
|
||||
return
|
||||
|
||||
if loops and loops % 100 == 0: # every 10s except first time
|
||||
log.warning("Waiting for account %s to exist, %ds passed",
|
||||
user_id, loops // 10)
|
||||
|
||||
await asyncio.sleep(0.1)
|
||||
loops += 1
|
||||
|
||||
|
||||
# General functions
|
||||
|
||||
@@ -1,183 +0,0 @@
|
||||
import asyncio
|
||||
import logging as log
|
||||
import random
|
||||
import re
|
||||
from dataclasses import dataclass, field
|
||||
from io import BytesIO
|
||||
from pathlib import Path
|
||||
from typing import Optional, Tuple
|
||||
from urllib.parse import urlparse
|
||||
|
||||
import aiofiles
|
||||
from PIL import Image as PILImage
|
||||
|
||||
import nio
|
||||
import pyotherside
|
||||
from nio.api import ResizingMethod
|
||||
|
||||
from . import utils
|
||||
|
||||
POSFormat = int
|
||||
Size = Tuple[int, int]
|
||||
ImageData = Tuple[bytearray, Size, int] # last int: pyotherside format enum
|
||||
|
||||
CONCURRENT_DOWNLOADS_LIMIT = asyncio.BoundedSemaphore(8)
|
||||
|
||||
with BytesIO() as img_out:
|
||||
PILImage.new("RGBA", (1, 1), (0, 0, 0, 0)).save(img_out, "PNG")
|
||||
TRANSPARENT_1X1_PNG = (img_out.getvalue(), pyotherside.format_data)
|
||||
|
||||
|
||||
@dataclass
|
||||
class Thumbnail:
|
||||
provider: "ImageProvider" = field()
|
||||
mxc: str = field()
|
||||
width: int = field()
|
||||
height: int = field()
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
self.mxc = re.sub(r"#auto$", "", self.mxc)
|
||||
|
||||
if not re.match(r"^mxc://.+/.+", self.mxc):
|
||||
raise ValueError(f"Invalid mxc URI: {self.mxc}")
|
||||
|
||||
|
||||
@property
|
||||
def server_size(self) -> Tuple[int, int]:
|
||||
# https://matrix.org/docs/spec/client_server/latest#thumbnails
|
||||
|
||||
if self.width > 640 or self.height > 480:
|
||||
return (800, 600)
|
||||
|
||||
if self.width > 320 or self.height > 240:
|
||||
return (640, 480)
|
||||
|
||||
if self.width > 96 or self.height > 96:
|
||||
return (320, 240)
|
||||
|
||||
if self.width > 32 or self.height > 32:
|
||||
return (96, 96)
|
||||
|
||||
return (32, 32)
|
||||
|
||||
|
||||
@property
|
||||
def resize_method(self) -> ResizingMethod:
|
||||
return ResizingMethod.scale \
|
||||
if self.width > 96 or self.height > 96 else ResizingMethod.crop
|
||||
|
||||
|
||||
@property
|
||||
def http(self) -> str:
|
||||
return nio.Api.mxc_to_http(self.mxc)
|
||||
|
||||
|
||||
@property
|
||||
def local_path(self) -> Path:
|
||||
parsed = urlparse(self.mxc)
|
||||
name = "%s.%03d.%03d.%s" % (
|
||||
parsed.path.lstrip("/"),
|
||||
self.server_size[0],
|
||||
self.server_size[1],
|
||||
self.resize_method.value,
|
||||
)
|
||||
return self.provider.cache / parsed.netloc / name
|
||||
|
||||
|
||||
async def read_data(self, data: bytes, mime: Optional[str],
|
||||
) -> Tuple[bytes, POSFormat]:
|
||||
if mime == "image/svg+xml":
|
||||
return (data, pyotherside.format_svg_data)
|
||||
|
||||
if mime in ("image/jpeg", "image/png"):
|
||||
return (data, pyotherside.format_data)
|
||||
|
||||
try:
|
||||
with BytesIO(data) as img_in:
|
||||
image = PILImage.open(img_in)
|
||||
|
||||
if image.mode == "RGB":
|
||||
return (data, pyotherside.format_rgb888)
|
||||
|
||||
if image.mode == "RGBA":
|
||||
return (data, pyotherside.format_argb32)
|
||||
|
||||
with BytesIO() as img_out:
|
||||
image.save(img_out, "PNG")
|
||||
return (img_out.getvalue(), pyotherside.format_data)
|
||||
|
||||
except OSError as err:
|
||||
log.warning("Unable to process image: %s - %r", self.http, err)
|
||||
return TRANSPARENT_1X1_PNG
|
||||
|
||||
|
||||
async def download(self) -> Tuple[bytes, POSFormat]:
|
||||
client = random.choice(
|
||||
tuple(self.provider.app.backend.clients.values()),
|
||||
)
|
||||
parsed = urlparse(self.mxc)
|
||||
|
||||
async with CONCURRENT_DOWNLOADS_LIMIT:
|
||||
resp = await client.thumbnail(
|
||||
server_name = parsed.netloc,
|
||||
media_id = parsed.path.lstrip("/"),
|
||||
width = self.server_size[0],
|
||||
height = self.server_size[1],
|
||||
method = self.resize_method,
|
||||
)
|
||||
|
||||
if isinstance(resp, nio.ThumbnailError):
|
||||
log.warning("Downloading thumbnail failed - %s", resp)
|
||||
return TRANSPARENT_1X1_PNG
|
||||
|
||||
body, pos_format = await self.read_data(resp.body, resp.content_type)
|
||||
|
||||
self.local_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
async with aiofiles.open(self.local_path, "wb") as file:
|
||||
# body might have been converted, always save the original image.
|
||||
await file.write(resp.body)
|
||||
|
||||
return (body, pos_format)
|
||||
|
||||
|
||||
async def local_read(self) -> Tuple[bytes, POSFormat]:
|
||||
data = self.local_path.read_bytes()
|
||||
with BytesIO(data) as data_io:
|
||||
return await self.read_data(data, utils.guess_mime(data_io))
|
||||
|
||||
|
||||
async def get_data(self) -> ImageData:
|
||||
try:
|
||||
data, pos_format = await self.local_read()
|
||||
except (OSError, IOError, FileNotFoundError):
|
||||
data, pos_format = await self.download()
|
||||
|
||||
with BytesIO(data) as img_in:
|
||||
real_size = PILImage.open(img_in).size
|
||||
|
||||
return (bytearray(data), real_size, pos_format)
|
||||
|
||||
|
||||
class ImageProvider:
|
||||
def __init__(self, app) -> None:
|
||||
self.app = app
|
||||
|
||||
self.cache = Path(self.app.appdirs.user_cache_dir) / "thumbnails"
|
||||
self.cache.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
|
||||
def get(self, image_id: str, requested_size: Size) -> ImageData:
|
||||
if requested_size[0] < 1 or requested_size[1] < 1:
|
||||
raise ValueError(f"width or height < 1: {requested_size!r}")
|
||||
|
||||
try:
|
||||
thumb = Thumbnail(self, image_id, *requested_size)
|
||||
except ValueError as err:
|
||||
log.warning(err)
|
||||
data, pos_format = TRANSPARENT_1X1_PNG
|
||||
return (bytearray(data), (1, 1), pos_format)
|
||||
|
||||
return asyncio.run_coroutine_threadsafe(
|
||||
thumb.get_data(), self.app.loop,
|
||||
).result()
|
||||
@@ -93,6 +93,10 @@ class MatrixClient(nio.AsyncClient):
|
||||
|
||||
self.skipped_events: DefaultDict[str, int] = DefaultDict(lambda: 0)
|
||||
|
||||
from .media_cache import MediaCache
|
||||
cache_dir = Path(self.backend.app.appdirs.user_cache_dir)
|
||||
self.media_cache = MediaCache(self, cache_dir)
|
||||
|
||||
self.connect_callbacks()
|
||||
|
||||
|
||||
|
||||
182
src/python/media_cache.py
Normal file
182
src/python/media_cache.py
Normal file
@@ -0,0 +1,182 @@
|
||||
import asyncio
|
||||
import io
|
||||
import re
|
||||
from dataclasses import dataclass, field
|
||||
from pathlib import Path
|
||||
from typing import DefaultDict, Optional, Tuple
|
||||
from urllib.parse import urlparse
|
||||
|
||||
import aiofiles
|
||||
import nio
|
||||
from PIL import Image as PILImage
|
||||
|
||||
from .matrix_client import MatrixClient
|
||||
|
||||
Size = Tuple[int, int]
|
||||
|
||||
CONCURRENT_DOWNLOADS_LIMIT = asyncio.BoundedSemaphore(8)
|
||||
ACCESS_LOCKS: DefaultDict[str, asyncio.Lock] = DefaultDict(asyncio.Lock)
|
||||
|
||||
|
||||
@dataclass
|
||||
class DownloadFailed(Exception):
|
||||
message: str = field()
|
||||
http_code: int = field()
|
||||
|
||||
|
||||
@dataclass
|
||||
class Media:
|
||||
cache: "MediaCache" = field()
|
||||
mxc: str = field()
|
||||
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
self.mxc = re.sub(r"#auto$", "", self.mxc)
|
||||
|
||||
if not re.match(r"^mxc://.+/.+", self.mxc):
|
||||
raise ValueError(f"Invalid mxc URI: {self.mxc}")
|
||||
|
||||
|
||||
@property
|
||||
def http(self) -> str:
|
||||
return nio.Api.mxc_to_http(self.mxc)
|
||||
|
||||
|
||||
@property
|
||||
def local_path(self) -> Path:
|
||||
parsed = urlparse(self.mxc)
|
||||
name = parsed.path.lstrip("/")
|
||||
return self.cache.downloads_dir / parsed.netloc / name
|
||||
|
||||
|
||||
async def get(self) -> Path:
|
||||
async with ACCESS_LOCKS[self.mxc]:
|
||||
try:
|
||||
return await self._get_local_existing_file()
|
||||
except FileNotFoundError:
|
||||
return await self._download()
|
||||
|
||||
|
||||
async def _get_local_existing_file(self) -> Path:
|
||||
if not self.local_path.exists():
|
||||
raise FileNotFoundError()
|
||||
|
||||
return self.local_path
|
||||
|
||||
|
||||
async def _download(self) -> Path:
|
||||
async with CONCURRENT_DOWNLOADS_LIMIT:
|
||||
body = await self._get_remote_data()
|
||||
|
||||
self.local_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
async with aiofiles.open(self.local_path, "wb") as file:
|
||||
await file.write(body)
|
||||
|
||||
return self.local_path
|
||||
|
||||
|
||||
async def _get_remote_data(self) -> bytes:
|
||||
raise NotImplementedError()
|
||||
|
||||
|
||||
@dataclass
|
||||
class Thumbnail(Media):
|
||||
cache: "MediaCache" = field()
|
||||
mxc: str = field()
|
||||
wanted_size: Size = field()
|
||||
|
||||
server_size: Optional[Size] = field(init=False, repr=False, default=None)
|
||||
|
||||
|
||||
@staticmethod
|
||||
def normalize_size(size: Size) -> Size:
|
||||
# https://matrix.org/docs/spec/client_server/latest#thumbnails
|
||||
|
||||
if size[0] > 640 or size[1] > 480:
|
||||
return (800, 600)
|
||||
|
||||
if size[0] > 320 or size[1] > 240:
|
||||
return (640, 480)
|
||||
|
||||
if size[0] > 96 or size[1] > 96:
|
||||
return (320, 240)
|
||||
|
||||
if size[0] > 32 or size[1] > 32:
|
||||
return (96, 96)
|
||||
|
||||
return (32, 32)
|
||||
|
||||
|
||||
@property
|
||||
def local_path(self) -> Path:
|
||||
# example: thumbnails/matrix.org/32x32/<mxc id>
|
||||
|
||||
parsed = urlparse(self.mxc)
|
||||
size = self.normalize_size(self.server_size or self.wanted_size)
|
||||
name = "%dx%d/%s" % (size[0], size[1], parsed.path.lstrip("/"))
|
||||
|
||||
return self.cache.thumbs_dir / parsed.netloc / name
|
||||
|
||||
|
||||
async def _get_local_existing_file(self) -> Path:
|
||||
if self.local_path.exists():
|
||||
return self.local_path
|
||||
|
||||
# If we have a bigger size thumbnail than the wanted_size for this pic,
|
||||
# return it instead of asking the server for a smaller thumbnail.
|
||||
|
||||
try_sizes = ((32, 32), (96, 96), (320, 240), (640, 480), (800, 600))
|
||||
parts = list(self.local_path.parts)
|
||||
size = self.normalize_size(self.server_size or self.wanted_size)
|
||||
|
||||
for width, height in try_sizes:
|
||||
if width < size[0] or height < size[1]:
|
||||
continue
|
||||
|
||||
parts[-2] = f"{width}x{height}"
|
||||
path = Path("/".join(parts))
|
||||
|
||||
if path.exists():
|
||||
return path
|
||||
|
||||
raise FileNotFoundError()
|
||||
|
||||
|
||||
|
||||
async def _get_remote_data(self) -> bytes:
|
||||
parsed = urlparse(self.mxc)
|
||||
|
||||
resp = await self.cache.client.thumbnail(
|
||||
server_name = parsed.netloc,
|
||||
media_id = parsed.path.lstrip("/"),
|
||||
width = self.wanted_size[0],
|
||||
height = self.wanted_size[1],
|
||||
)
|
||||
|
||||
with io.BytesIO(resp.body) as img:
|
||||
# The server may return a thumbnail bigger than what we asked for
|
||||
self.server_size = PILImage.open(img).size
|
||||
|
||||
if isinstance(resp, nio.ErrorResponse):
|
||||
raise DownloadFailed(resp.message, resp.status_code)
|
||||
|
||||
return resp.body
|
||||
|
||||
|
||||
@dataclass
|
||||
class MediaCache:
|
||||
client: MatrixClient = field()
|
||||
base_dir: Path = field()
|
||||
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
self.thumbs_dir = self.base_dir / "thumbnails"
|
||||
self.downloads_dir = self.base_dir / "downloads"
|
||||
|
||||
self.thumbs_dir.mkdir(parents=True, exist_ok=True)
|
||||
self.downloads_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
|
||||
async def thumbnail(self, mxc: str, width: int, height: int) -> str:
|
||||
return str(await Thumbnail(self, mxc, (width, height)).get())
|
||||
Reference in New Issue
Block a user