justinzeus/scholarr
1
0
Fork 0
Code Issues 1 Pull requests 18 Projects Releases Packages Wiki Activity Actions

Initial release prep

Browse source
This commit is contained in:
Justin Visser 2026-02-27 10:46:05 +01:00
parent c9b9d892f4
commit 92395b2b4b
100 changed files with 405 additions and 401 deletions
Download patch file Download diff file Expand all files Collapse all files

4
app/services/arxiv/application.py
View file

@ -2,13 +2,13 @@ from __future__ import annotations
from typing import TYPE_CHECKING
from app.services.domains.arxiv.gateway import (
from app.services.arxiv.gateway import (
build_arxiv_query,
get_arxiv_gateway,
)
if TYPE_CHECKING:
from app.services.domains.publications.types import PublicationListItem, UnreadPublicationItem
from app.services.publications.types import PublicationListItem, UnreadPublicationItem
def _build_arxiv_query(title: str, author_surname: str | None) -> str | None:

4
app/services/arxiv/cache.py
View file

@ -12,8 +12,8 @@ from sqlalchemy import delete, func, select
from app.db.models import ArxivQueryCacheEntry
from app.db.session import get_session_factory
from app.services.domains.arxiv.constants import ARXIV_CACHE_FINGERPRINT_VERSION
from app.services.domains.arxiv.types import ArxivEntry, ArxivFeed, ArxivOpenSearchMeta
from app.services.arxiv.constants import ARXIV_CACHE_FINGERPRINT_VERSION
from app.services.arxiv.types import ArxivEntry, ArxivFeed, ArxivOpenSearchMeta
_INFLIGHT_LOCK = asyncio.Lock()
_INFLIGHT_FEEDS: dict[str, asyncio.Future[ArxivFeed]] = {}

12
app/services/arxiv/client.py
View file

@ -6,21 +6,21 @@ from collections.abc import Awaitable, Callable
import httpx
from app.logging_utils import structured_log
from app.services.domains.arxiv.cache import (
from app.services.arxiv.cache import (
build_query_fingerprint,
get_cached_feed,
run_with_inflight_dedupe,
set_cached_feed,
)
from app.services.domains.arxiv.constants import (
from app.services.arxiv.constants import (
ARXIV_SOURCE_PATH_LOOKUP_IDS,
ARXIV_SOURCE_PATH_SEARCH,
ARXIV_SOURCE_PATH_UNKNOWN,
)
from app.services.domains.arxiv.errors import ArxivClientValidationError, ArxivRateLimitError
from app.services.domains.arxiv.parser import parse_arxiv_feed
from app.services.domains.arxiv.rate_limit import get_arxiv_cooldown_status, run_with_global_arxiv_limit
from app.services.domains.arxiv.types import ArxivFeed
from app.services.arxiv.errors import ArxivClientValidationError, ArxivRateLimitError
from app.services.arxiv.parser import parse_arxiv_feed
from app.services.arxiv.rate_limit import get_arxiv_cooldown_status, run_with_global_arxiv_limit
from app.services.arxiv.types import ArxivFeed
from app.settings import settings
_ARXIV_API_URL = "https://export.arxiv.org/api/query"

8
app/services/arxiv/gateway.py
View file

@ -6,13 +6,13 @@ import unicodedata
from typing import TYPE_CHECKING, Protocol
from app.logging_utils import structured_log
from app.services.domains.arxiv.client import ArxivClient
from app.services.domains.arxiv.errors import ArxivRateLimitError
from app.services.domains.arxiv.types import ArxivFeed
from app.services.arxiv.client import ArxivClient
from app.services.arxiv.errors import ArxivRateLimitError
from app.services.arxiv.types import ArxivFeed
from app.settings import settings
if TYPE_CHECKING:
from app.services.domains.publications.types import PublicationListItem, UnreadPublicationItem
from app.services.publications.types import PublicationListItem, UnreadPublicationItem
logger = logging.getLogger(__name__)

8
app/services/arxiv/guards.py
View file

@ -3,17 +3,17 @@ from __future__ import annotations
import re
from typing import TYPE_CHECKING
from app.services.domains.arxiv.constants import (
from app.services.arxiv.constants import (
ARXIV_STRONG_IDENTIFIER_CONFIDENCE,
ARXIV_TITLE_MIN_ALPHA_TOKENS,
ARXIV_TITLE_MIN_TOKENS,
ARXIV_TITLE_TOKEN_MIN_LENGTH,
)
from app.services.domains.doi.normalize import normalize_doi
from app.services.domains.publication_identifiers.normalize import normalize_arxiv_id
from app.services.doi.normalize import normalize_doi
from app.services.publication_identifiers.normalize import normalize_arxiv_id
if TYPE_CHECKING:
from app.services.domains.publications.types import PublicationListItem, UnreadPublicationItem
from app.services.publications.types import PublicationListItem, UnreadPublicationItem
_TITLE_TOKEN_RE = re.compile(r"[a-z0-9]+")

6
app/services/arxiv/parser.py
View file

@ -2,9 +2,9 @@ from __future__ import annotations
import xml.etree.ElementTree as ET
from app.services.domains.arxiv.errors import ArxivParseError
from app.services.domains.arxiv.types import ArxivEntry, ArxivFeed, ArxivOpenSearchMeta
from app.services.domains.publication_identifiers.normalize import normalize_arxiv_id
from app.services.arxiv.errors import ArxivParseError
from app.services.arxiv.types import ArxivEntry, ArxivFeed, ArxivOpenSearchMeta
from app.services.publication_identifiers.normalize import normalize_arxiv_id
_NAMESPACES = {
"atom": "http://www.w3.org/2005/Atom",

4
app/services/arxiv/rate_limit.py
View file

@ -13,13 +13,13 @@ from sqlalchemy.ext.asyncio import AsyncSession
from app.db.models import ArxivRuntimeState
from app.db.session import get_session_factory
from app.logging_utils import structured_log
from app.services.domains.arxiv.constants import (
from app.services.arxiv.constants import (
ARXIV_RATE_LIMIT_LOCK_KEY,
ARXIV_RATE_LIMIT_LOCK_NAMESPACE,
ARXIV_RUNTIME_STATE_KEY,
ARXIV_SOURCE_PATH_UNKNOWN,
)
from app.services.domains.arxiv.errors import ArxivRateLimitError
from app.services.arxiv.errors import ArxivRateLimitError
from app.settings import settings
logger = logging.getLogger(__name__)