lib.itmens/catalog/book/models.py

303 lines
8.9 KiB
Python
Raw Normal View History

"""
Models for Book
Series -> Work -> Edition
Series is not fully implemented at the moment
Goodreads
Famous works have many editions
Google Books:
only has Edition level ("volume") data
Douban:
old editions has only CUBN(Chinese Unified Book Number)
2022-12-08 16:08:59 +00:00
work data seems asymmetric (a book links to a work, but may not listed in that work as one of its editions)
"""
2024-04-08 20:25:14 -04:00
from os.path import exists
2023-01-05 03:06:13 -05:00
from django.core.validators import MaxValueValidator, MinValueValidator
from django.db import models
from django.utils.translation import gettext_lazy as _
2024-04-08 21:27:36 -04:00
from loguru import logger as _logger
2023-08-11 01:43:19 -04:00
from catalog.common import (
BaseSchema,
ExternalResource,
IdType,
Item,
ItemCategory,
ItemInSchema,
ItemSchema,
ItemType,
PrimaryLookupIdDescriptor,
jsondata,
)
from .utils import *
2023-02-15 15:45:57 -05:00
class EditionInSchema(ItemInSchema):
subtitle: str | None = None
orig_title: str | None = None
author: list[str]
translator: list[str]
language: str | None = None
pub_house: str | None = None
pub_year: int | None = None
pub_month: int | None = None
binding: str | None = None
price: str | None = None
2023-11-18 20:30:48 -05:00
pages: int | str | None = None
2023-02-15 15:45:57 -05:00
series: str | None = None
imprint: str | None = None
class EditionSchema(EditionInSchema, BaseSchema):
2023-02-15 16:22:32 -05:00
isbn: str | None = None
2023-02-15 15:45:57 -05:00
pass
class Edition(Item):
2022-12-11 23:20:28 +00:00
category = ItemCategory.Book
2022-12-29 23:57:02 -05:00
url_path = "book"
2022-12-15 17:29:35 -05:00
isbn = PrimaryLookupIdDescriptor(IdType.ISBN)
asin = PrimaryLookupIdDescriptor(IdType.ASIN)
cubn = PrimaryLookupIdDescriptor(IdType.CUBN)
# douban_book = LookupIdDescriptor(IdType.DoubanBook)
# goodreads = LookupIdDescriptor(IdType.Goodreads)
METADATA_COPY_LIST = [
2022-12-29 23:57:02 -05:00
"title",
"subtitle",
"author",
"pub_house",
"pub_year",
"pub_month",
"language",
"orig_title",
"translator",
"series",
2023-01-05 03:06:13 -05:00
"imprint",
2022-12-29 23:57:02 -05:00
"binding",
"pages",
2023-01-05 03:06:13 -05:00
"price",
"brief",
"contents",
]
2023-01-05 03:06:13 -05:00
subtitle = jsondata.CharField(
2024-03-10 20:55:50 -04:00
_("subtitle"), null=True, blank=True, default=None, max_length=500
2023-01-05 03:06:13 -05:00
)
orig_title = jsondata.CharField(
2024-03-10 20:55:50 -04:00
_("original title"), null=True, blank=True, default=None, max_length=500
2023-01-05 03:06:13 -05:00
)
author = jsondata.ArrayField(
2024-03-10 20:55:50 -04:00
verbose_name=_("author"),
2023-01-05 03:06:13 -05:00
base_field=models.CharField(max_length=500),
null=False,
blank=False,
default=list,
)
translator = jsondata.ArrayField(
2024-03-10 20:55:50 -04:00
verbose_name=_("translator"),
2023-01-05 03:06:13 -05:00
base_field=models.CharField(max_length=500),
null=True,
blank=True,
default=list,
)
2023-01-09 09:21:53 -05:00
language = jsondata.CharField(
2024-03-10 20:55:50 -04:00
_("language"), null=True, blank=True, default=None, max_length=500
2023-01-09 09:21:53 -05:00
)
2023-01-05 03:06:13 -05:00
pub_house = jsondata.CharField(
2024-03-10 20:55:50 -04:00
_("publisher"), null=True, blank=False, default=None, max_length=500
2023-01-05 03:06:13 -05:00
)
pub_year = jsondata.IntegerField(
2024-03-10 20:55:50 -04:00
_("publication year"),
2023-01-05 03:06:13 -05:00
null=True,
blank=False,
validators=[MinValueValidator(1), MaxValueValidator(2999)],
)
pub_month = jsondata.IntegerField(
2024-03-10 20:55:50 -04:00
_("publication month"),
2023-01-05 03:06:13 -05:00
null=True,
blank=True,
2023-01-05 03:06:13 -05:00
validators=[MinValueValidator(1), MaxValueValidator(12)],
)
binding = jsondata.CharField(
2024-03-10 20:55:50 -04:00
_("binding"), null=True, blank=True, default=None, max_length=500
2023-01-05 03:06:13 -05:00
)
2024-03-10 20:55:50 -04:00
pages = jsondata.IntegerField(_("pages"), blank=True, default=None)
2023-01-05 03:06:13 -05:00
series = jsondata.CharField(
2024-03-10 20:55:50 -04:00
_("series"), null=True, blank=True, default=None, max_length=500
2023-01-05 03:06:13 -05:00
)
2024-03-10 20:55:50 -04:00
contents = jsondata.TextField(_("contents"), null=True, blank=True, default=None)
price = jsondata.CharField(_("price"), null=True, blank=True, max_length=500)
imprint = jsondata.CharField(_("imprint"), null=True, blank=True, max_length=500)
@property
def isbn10(self):
return isbn_13_to_10(self.isbn)
@isbn10.setter
def isbn10(self, value):
self.isbn = isbn_10_to_13(value)
2023-01-05 03:06:13 -05:00
@classmethod
def lookup_id_type_choices(cls):
id_types = [
IdType.ISBN,
IdType.ASIN,
IdType.CUBN,
IdType.DoubanBook,
IdType.Goodreads,
IdType.GoogleBooks,
]
return [(i.value, i.label) for i in id_types]
@classmethod
def lookup_id_cleanup(cls, lookup_id_type, lookup_id_value):
if lookup_id_type in [IdType.ASIN.value, IdType.ISBN.value]:
return detect_isbn_asin(lookup_id_value)
return super().lookup_id_cleanup(lookup_id_type, lookup_id_value)
2024-04-08 21:27:36 -04:00
def merge_to(self, to_item):
super().merge_to(to_item)
for work in self.works.all():
to_item.works.add(work)
self.works.clear()
def delete(self, using=None, soft=True, *args, **kwargs):
if soft:
self.works.clear()
return super().delete(using, soft, *args, **kwargs)
2022-12-08 16:08:59 +00:00
def update_linked_items_from_external_resource(self, resource):
"""add Work from resource.metadata['work'] if not yet"""
links = resource.required_resources + resource.related_resources
for w in links:
2023-07-20 21:59:49 -04:00
if w.get("model") == "Work":
2024-04-08 21:27:36 -04:00
work_res = ExternalResource.objects.filter(
id_type=w["id_type"], id_value=w["id_value"]
2022-12-29 23:57:02 -05:00
).first()
2024-04-08 21:27:36 -04:00
if work_res:
work = work_res.item
if not work:
_logger.warning(f"Unable to find work for {work_res}")
else:
_logger.warning(
f'Unable to find resource for {w["id_type"]}:{w["id_value"]}'
)
work = Work.objects.filter(
primary_lookup_id_type=w["id_type"],
primary_lookup_id_value=w["id_value"],
).first()
if work and work not in self.works.all():
self.works.add(work)
def get_related_books(self):
2023-02-13 00:52:24 -05:00
works = list(self.works.all())
return (
Edition.objects.filter(works__in=works)
2023-06-08 18:05:19 -04:00
.distinct()
2023-02-13 00:52:24 -05:00
.exclude(pk=self.pk)
.exclude(is_deleted=True)
.exclude(merged_to_item__isnull=False)
.order_by("title")
2023-02-13 00:52:24 -05:00
)
2024-04-08 20:25:14 -04:00
def has_related_books(self):
works = list(self.works.all())
if not works:
return False
return Edition.objects.filter(works__in=works).exclude(pk=self.pk).exists()
def link_to_related_book(self, target: "Edition") -> bool:
if target == self or target.is_deleted or target.merged_to_item:
return False
if target.works.all().exists():
for work in target.works.all():
self.works.add(work)
elif self.works.all().exists():
for work in self.works.all():
target.works.add(work)
else:
Work.objects.create(title=self.title).editions.add(self, target)
return True
def unlink_from_all_works(self):
self.works.clear()
def has_works(self):
return self.works.all().exists()
class Work(Item):
2022-12-11 23:20:28 +00:00
category = ItemCategory.Book
2022-12-29 23:57:02 -05:00
url_path = "book/work"
2022-12-11 23:20:28 +00:00
douban_work = PrimaryLookupIdDescriptor(IdType.DoubanBook_Work)
goodreads_work = PrimaryLookupIdDescriptor(IdType.Goodreads_Work)
2022-12-29 23:57:02 -05:00
editions = models.ManyToManyField(Edition, related_name="works")
2024-04-09 15:47:27 -04:00
author = jsondata.ArrayField(
verbose_name=_("author"),
base_field=models.CharField(max_length=500),
null=True,
blank=True,
default=list,
)
other_title = jsondata.ArrayField(
verbose_name=_("other title"),
base_field=models.CharField(blank=True, default="", max_length=200),
null=True,
blank=True,
default=list,
)
METADATA_COPY_LIST = [
"title",
"other_title",
"author",
"brief",
]
2023-06-08 18:05:19 -04:00
# TODO: we have many duplicates due to 302
# a lazy fix is to remove smaller DoubanBook_Work ids
# but ideally deal with 302 in scrape().
2024-04-09 00:45:40 -04:00
@classmethod
def lookup_id_type_choices(cls):
id_types = [
2024-04-09 15:47:27 -04:00
IdType.WikiData,
2024-04-09 00:45:40 -04:00
IdType.DoubanBook_Work,
IdType.Goodreads_Work,
]
return [(i.value, i.label) for i in id_types]
2024-04-08 21:27:36 -04:00
def merge_to(self, to_item):
2024-04-09 15:47:27 -04:00
if (
to_item
and self.title != to_item.title
and self.title not in to_item.other_title
):
to_item.other_title += [self.title]
2024-04-08 21:27:36 -04:00
super().merge_to(to_item)
for edition in self.editions.all():
to_item.editions.add(edition)
self.editions.clear()
def delete(self, using=None, soft=True, *args, **kwargs):
if soft:
self.editions.clear()
return super().delete(using, soft, *args, **kwargs)
class Series(Item):
2022-12-11 23:20:28 +00:00
category = ItemCategory.Book
2022-12-29 23:57:02 -05:00
url_path = "book/series"
# douban_serie = LookupIdDescriptor(IdType.DoubanBook_Serie)
# goodreads_serie = LookupIdDescriptor(IdType.Goodreads_Serie)
class Meta:
proxy = True