mirror of
https://github.com/lrnselfreliance/wrolpi.git
synced 2026-10-26 19:01:39 -04:00
* Fix API stalls: non-blocking switch worker, threaded searches, indexed Videos page Three response-time fixes found by benchmarking the read-only API endpoints hot and cold on real libraries: * `switch_worker` runs on the Sanic worker's event loop every 0.1s and called the blocking `multiprocessing.Event.wait(timeout=1)`. With no switch pending (the normal state) this froze the loop for a second at a time; about a third of all requests, including trivial ones, took ~1,000 ms. It now polls `is_set()` and returns immediately. * The search handlers (videos, files, archives, docs, zims) and `/api/statistics` ran synchronous SQLite queries on the event loop, so one slow search stalled every other request on that worker. They now run via `asyncio.to_thread`. * The unfiltered Videos page (`POST /api/videos/search` with only an order) used `mimetype LIKE 'video/%' OR ...` plus `COUNT(*) OVER()`, which visits every video's index entry before LIMIT applies: seconds cold on a large library on a spinning disk, and ~10 s hot for a deep page. It now seeks each exact mimetype on the (mimetype, effective_datetime) index for `limit + offset` rows and merges them, with the total from a separate count cached for 60 s. Results are identical to the generic query. Also adds `scripts/api_perf.py` (times every read-only endpoint against a host, optionally restarting the API over SSH for cold numbers) and `scripts/api_perf_compare.py` (merges per-host results). Host profiles live in a gitignored JSON file; an example is included. Measured on an 8-core docker host with a 10 GB library: median hot request 1,007 ms -> 22 ms; Videos page 1 hot 287 -> 108 ms, page 50 1,345 -> 120 ms. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Serve the video description from its own endpoint instead of Video.__json__ `Video.__json__` computed `description` as `c_text or get_video_description()`, where the fallback opens and parses the video's info json from disk. The list endpoints serialize every result with `__json__`, so any page containing videos without an indexed description (common: many videos have none) read their info json files on every request, cold, for a field the list never displays. The description is not part of search either: search runs against the FTS copy of `c_text`, so the fallback never fed the index. Drop `description` from `__json__` and serve it from `GET /api/videos/<id>/description`, like comments and captions. The endpoint returns the indexed `c_text`, falling back to the info json only there, for a row indexed before descriptions were stored. The player page fetches it through `useVideoExtras` alongside the comments. Tests assert the list and detail responses never touch the info json, and cover the endpoint's indexed, fallback, and not-found cases. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Address review: thread-local zim sessions, fast-path equivalence test, comments * Zim search, single-zim search, and search estimates run libzim off the event loop, each opening its own session inside the worker thread rather than passing the request's SQLAlchemy Session across threads. * The Videos fast-path test now runs the same requests through the generic query and asserts identical rows and paging for both date orders. The one intentional difference is documented: past the end, the fast path still reports the true total. * switch_worker returns before its try block so the empty path does not clear the event; its comment states the invariant only. The copied "synchronous SQLite" comments are reduced to one line in one place. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
285 lines
5.7 KiB
Python
285 lines
5.7 KiB
Python
from dataclasses import dataclass, field
|
|
from typing import List, Optional
|
|
|
|
from modules.videos.video.lib import DEFAULT_VIDEO_ORDER, VIDEO_QUERY_LIMIT
|
|
from wrolpi.errors import ValidationError
|
|
|
|
|
|
@dataclass
|
|
class ChannelPostRequest:
|
|
name: str
|
|
directory: str
|
|
calculate_duration: Optional[bool] = None
|
|
download_missing_data: Optional[bool] = True
|
|
generate_posters: Optional[bool] = None
|
|
source_id: Optional[str] = None
|
|
tag_name: Optional[str] = None
|
|
url: Optional[str] = None
|
|
|
|
def __post_init__(self):
|
|
self.name = self.name.strip() or None
|
|
self.directory = self.directory.strip() or None
|
|
self.url = self.url.strip() if self.url else None
|
|
self.source_id = self.source_id.strip() if self.source_id else None
|
|
|
|
|
|
@dataclass
|
|
class ChannelPutRequest:
|
|
calculate_duration: Optional[bool] = None
|
|
directory: Optional[str] = None
|
|
download_missing_data: Optional[bool] = True
|
|
generate_posters: Optional[bool] = None
|
|
mkdir: Optional[bool] = None
|
|
name: Optional[str] = None
|
|
url: Optional[str] = None
|
|
|
|
def __post_init__(self):
|
|
self.name = self.name.strip() or None
|
|
self.directory = self.directory.strip() or None
|
|
self.url = self.url.strip() if self.url else None
|
|
|
|
|
|
@dataclass
|
|
class ChannelTagRequest:
|
|
tag_name: Optional[str] = None
|
|
directory: Optional[str] = None
|
|
|
|
def __post_init__(self):
|
|
if self.directory and self.directory.startswith('/'):
|
|
raise ValidationError('Directory must be relative to media directory')
|
|
|
|
|
|
@dataclass
|
|
class ChannelTagInfoRequest:
|
|
channel_id: Optional[int] = None
|
|
tag_name: Optional[str] = None
|
|
|
|
|
|
@dataclass
|
|
class ChannelDownloadRequest:
|
|
url: str
|
|
frequency: int
|
|
settings: dict = field(default_factory=dict)
|
|
|
|
def __post_init__(self):
|
|
self.url = self.url.strip()
|
|
if not self.url:
|
|
raise ValidationError('url cannot be empty')
|
|
|
|
# Validate settings contents. Remove empty values.
|
|
from wrolpi.schema import DownloadSettings
|
|
self.settings = {k: v for k, v in DownloadSettings(**self.settings).__dict__.items() if v not in ([], None)}
|
|
|
|
|
|
@dataclass
|
|
class RefreshRequest:
|
|
channel_name: str
|
|
|
|
|
|
@dataclass
|
|
class ChannelModel:
|
|
id: int
|
|
url: str
|
|
name: str
|
|
directory: str
|
|
|
|
|
|
@dataclass
|
|
class ChannelResponse:
|
|
channel = ChannelModel
|
|
|
|
|
|
@dataclass
|
|
class ChannelPostResponse:
|
|
success: str
|
|
|
|
|
|
@dataclass
|
|
class ChannelsChannelModel:
|
|
id: int
|
|
name: str
|
|
|
|
|
|
@dataclass
|
|
class ChannelsResponse:
|
|
channels: List[ChannelsChannelModel]
|
|
|
|
|
|
@dataclass
|
|
class StreamResponse:
|
|
success: str
|
|
stream_url: str
|
|
|
|
|
|
@dataclass
|
|
class Video:
|
|
id: int
|
|
description_path: str
|
|
ext: str
|
|
poster_path: str
|
|
source_id: str
|
|
title: str
|
|
video_path: str
|
|
name: str
|
|
caption_path: str
|
|
idempotency: str
|
|
info_json_path: str
|
|
channel_id: int
|
|
|
|
|
|
@dataclass
|
|
class VideoWithChannel:
|
|
id: int
|
|
description_path: str
|
|
ext: str
|
|
poster_path: str
|
|
source_id: str
|
|
title: str
|
|
video_path: str
|
|
name: str
|
|
caption_path: str
|
|
idempotency: str
|
|
info_json_path: str
|
|
channel_id: int
|
|
|
|
channel = ChannelModel
|
|
|
|
|
|
@dataclass
|
|
class ExtendedVideo(Video):
|
|
info_json: dict
|
|
|
|
|
|
@dataclass
|
|
class VideoResponse:
|
|
file_group = ExtendedVideo
|
|
prev = ExtendedVideo
|
|
next = ExtendedVideo
|
|
|
|
|
|
@dataclass
|
|
class VideoCommentsResponse:
|
|
comments: list[dict]
|
|
|
|
|
|
@dataclass
|
|
class VideoCaptionsResponse:
|
|
captions: list
|
|
|
|
|
|
@dataclass
|
|
class VideoDescriptionResponse:
|
|
description: Optional[str]
|
|
|
|
|
|
@dataclass
|
|
class VideoSearchRequest:
|
|
search_str: Optional[str] = None
|
|
tags: List[str] = field(default_factory=list)
|
|
offset: Optional[int] = None
|
|
limit: Optional[int] = VIDEO_QUERY_LIMIT
|
|
order_by: Optional[str] = DEFAULT_VIDEO_ORDER
|
|
channel_id: Optional[int] = None
|
|
tag_names: List[str] = field(default_factory=list)
|
|
headline: bool = False
|
|
censored: bool = False
|
|
deep: bool = False # When True, search all text including captions (d_text)
|
|
|
|
|
|
@dataclass
|
|
class VideoSearchResponse:
|
|
videos: List[VideoWithChannel]
|
|
tsquery: str
|
|
|
|
|
|
@dataclass
|
|
class PaginationQuery:
|
|
offset: int
|
|
|
|
|
|
@dataclass
|
|
class TagRequest:
|
|
video_id: int
|
|
tag_name: str
|
|
|
|
|
|
@dataclass
|
|
class WROLModeRequest:
|
|
enabled: bool
|
|
|
|
|
|
@dataclass
|
|
class VideoStatistics:
|
|
videos: int
|
|
week: int
|
|
month: int
|
|
year: int
|
|
sum_duration: int
|
|
sum_size: int
|
|
max_size: int
|
|
have_comments: int
|
|
missing_comments: int
|
|
failed_comments: int
|
|
|
|
|
|
@dataclass
|
|
class ChannelStatistics:
|
|
channels: int
|
|
tagged_channels: int
|
|
|
|
|
|
@dataclass
|
|
class VideosStatisticsResponse:
|
|
videos = VideoStatistics
|
|
channels = ChannelStatistics
|
|
|
|
|
|
@dataclass
|
|
class CensoredVideoRequest:
|
|
limit: int
|
|
offset: int
|
|
|
|
|
|
@dataclass
|
|
class CensoredVideoResponse:
|
|
videos: List[VideoWithChannel]
|
|
|
|
|
|
@dataclass
|
|
class ChannelSearchRequest:
|
|
tag_names: List[str] = field(default_factory=list)
|
|
|
|
|
|
@dataclass
|
|
class VideoFileFormatRequest:
|
|
video_file_format: str
|
|
|
|
|
|
@dataclass
|
|
class CookiesUploadRequest:
|
|
"""Request to upload and encrypt cookies."""
|
|
cookies_content: str
|
|
password: str
|
|
|
|
def __post_init__(self):
|
|
if not self.cookies_content:
|
|
raise ValidationError('cookies_content cannot be empty')
|
|
if not self.password or len(self.password) < 8:
|
|
raise ValidationError('password must be at least 8 characters')
|
|
|
|
|
|
@dataclass
|
|
class CookiesUnlockRequest:
|
|
"""Request to unlock cookies with password."""
|
|
password: str
|
|
|
|
def __post_init__(self):
|
|
if not self.password:
|
|
raise ValidationError('password cannot be empty')
|
|
|
|
|
|
@dataclass
|
|
class CookiesStatusResponse:
|
|
"""Response with cookies status."""
|
|
cookies_exist: bool
|
|
cookies_unlocked: bool
|