diff --git a/bookwyrm/isbn/isbn.py b/bookwyrm/isbn/isbn.py
index e07d2100d..4cc7f47dd 100644
--- a/bookwyrm/isbn/isbn.py
+++ b/bookwyrm/isbn/isbn.py
@@ -1,11 +1,20 @@
""" Use the range message from isbn-international to hyphenate ISBNs """
import os
+from typing import Optional
from xml.etree import ElementTree
+from xml.etree.ElementTree import Element
+
import requests
from bookwyrm import settings
+def _get_rules(element: Element) -> list[Element]:
+ if (rules_el := element.find("Rules")) is not None:
+ return rules_el.findall("Rule")
+ return []
+
+
class IsbnHyphenator:
"""Class to manage the range message xml file and use it to hyphenate ISBNs"""
@@ -15,58 +24,94 @@ class IsbnHyphenator:
)
__element_tree = None
- def update_range_message(self):
+ def update_range_message(self) -> None:
"""Download the range message xml file and save it locally"""
response = requests.get(self.__range_message_url)
with open(self.__range_file_path, "w", encoding="utf-8") as file:
file.write(response.text)
self.__element_tree = None
- def hyphenate(self, isbn_13):
+ def hyphenate(self, isbn_13: Optional[str]) -> Optional[str]:
"""hyphenate the given ISBN-13 number using the range message"""
if isbn_13 is None:
return None
+
if self.__element_tree is None:
self.__element_tree = ElementTree.parse(self.__range_file_path)
+
gs1_prefix = isbn_13[:3]
reg_group = self.__find_reg_group(isbn_13, gs1_prefix)
if reg_group is None:
return isbn_13 # failed to hyphenate
+
registrant = self.__find_registrant(isbn_13, gs1_prefix, reg_group)
if registrant is None:
return isbn_13 # failed to hyphenate
+
publication = isbn_13[len(gs1_prefix) + len(reg_group) + len(registrant) : -1]
check_digit = isbn_13[-1:]
return "-".join((gs1_prefix, reg_group, registrant, publication, check_digit))
- def __find_reg_group(self, isbn_13, gs1_prefix):
- for ean_ucc_el in self.__element_tree.find("EAN.UCCPrefixes").findall(
- "EAN.UCC"
- ):
- if ean_ucc_el.find("Prefix").text == gs1_prefix:
- for rule_el in ean_ucc_el.find("Rules").findall("Rule"):
- length = int(rule_el.find("Length").text)
+ def __find_reg_group(self, isbn_13: str, gs1_prefix: str) -> Optional[str]:
+ if self.__element_tree is None:
+ self.__element_tree = ElementTree.parse(self.__range_file_path)
+
+ ucc_prefixes_el = self.__element_tree.find("EAN.UCCPrefixes")
+ if ucc_prefixes_el is None:
+ return None
+
+ for ean_ucc_el in ucc_prefixes_el.findall("EAN.UCC"):
+ if (
+ prefix_el := ean_ucc_el.find("Prefix")
+ ) is not None and prefix_el.text == gs1_prefix:
+ for rule_el in _get_rules(ean_ucc_el):
+ length_el = rule_el.find("Length")
+ if length_el is None:
+ continue
+ length = int(text) if (text := length_el.text) else 0
if length == 0:
continue
- reg_grp_range = [
- int(x[:length]) for x in rule_el.find("Range").text.split("-")
- ]
+
+ range_el = rule_el.find("Range")
+ if range_el is None or range_el.text is None:
+ continue
+
+ reg_grp_range = [int(x[:length]) for x in range_el.text.split("-")]
reg_group = isbn_13[len(gs1_prefix) : len(gs1_prefix) + length]
if reg_grp_range[0] <= int(reg_group) <= reg_grp_range[1]:
return reg_group
return None
return None
- def __find_registrant(self, isbn_13, gs1_prefix, reg_group):
+ def __find_registrant(
+ self, isbn_13: str, gs1_prefix: str, reg_group: str
+ ) -> Optional[str]:
from_ind = len(gs1_prefix) + len(reg_group)
- for group_el in self.__element_tree.find("RegistrationGroups").findall("Group"):
- if group_el.find("Prefix").text == "-".join((gs1_prefix, reg_group)):
- for rule_el in group_el.find("Rules").findall("Rule"):
- length = int(rule_el.find("Length").text)
+
+ if self.__element_tree is None:
+ self.__element_tree = ElementTree.parse(self.__range_file_path)
+
+ reg_groups_el = self.__element_tree.find("RegistrationGroups")
+ if reg_groups_el is None:
+ return None
+
+ for group_el in reg_groups_el.findall("Group"):
+ if (
+ prefix_el := group_el.find("Prefix")
+ ) is not None and prefix_el.text == "-".join((gs1_prefix, reg_group)):
+ for rule_el in _get_rules(group_el):
+ length_el = rule_el.find("Length")
+ if length_el is None:
+ continue
+ length = int(text) if (text := length_el.text) else 0
if length == 0:
continue
+
+ range_el = rule_el.find("Range")
+ if range_el is None or range_el.text is None:
+ continue
registrant_range = [
- int(x[:length]) for x in rule_el.find("Range").text.split("-")
+ int(x[:length]) for x in range_el.text.split("-")
]
registrant = isbn_13[from_ind : from_ind + length]
if registrant_range[0] <= int(registrant) <= registrant_range[1]:
diff --git a/bookwyrm/models/book.py b/bookwyrm/models/book.py
index 8cb47e5c8..d0c3c7fd3 100644
--- a/bookwyrm/models/book.py
+++ b/bookwyrm/models/book.py
@@ -217,6 +217,13 @@ class Book(BookDataModel):
"""editions and works both use "book" instead of model_name"""
return f"https://{DOMAIN}/book/{self.id}"
+ def guess_sort_title(self):
+ """Get a best-guess sort title for the current book"""
+ articles = chain(
+ *(LANGUAGE_ARTICLES.get(language, ()) for language in tuple(self.languages))
+ )
+ return re.sub(f'^{" |^".join(articles)} ', "", str(self.title).lower())
+
def __repr__(self):
# pylint: disable=consider-using-f-string
return "<{} key={!r} title={!r}>".format(
@@ -374,16 +381,7 @@ class Edition(Book):
# Create sort title by removing articles from title
if self.sort_title in [None, ""]:
- if self.sort_title in [None, ""]:
- articles = chain(
- *(
- LANGUAGE_ARTICLES.get(language, ())
- for language in tuple(self.languages)
- )
- )
- self.sort_title = re.sub(
- f'^{" |^".join(articles)} ', "", str(self.title).lower()
- )
+ self.sort_title = self.guess_sort_title()
return super().save(*args, **kwargs)
diff --git a/bookwyrm/models/status.py b/bookwyrm/models/status.py
index e51f2ba07..5d6109468 100644
--- a/bookwyrm/models/status.py
+++ b/bookwyrm/models/status.py
@@ -1,5 +1,6 @@
""" models for storing different kinds of Activities """
from dataclasses import MISSING
+from typing import Optional
import re
from django.apps import apps
@@ -269,7 +270,7 @@ class GeneratedNote(Status):
"""indicate the book in question for mastodon (or w/e) users"""
message = self.content
books = ", ".join(
- f'"{book.title}"'
+ f'{book.title}'
for book in self.mention_books.all()
)
return f"{self.user.display_name} {message} {books}"
@@ -320,17 +321,14 @@ class Comment(BookStatus):
@property
def pure_content(self):
"""indicate the book in question for mastodon (or w/e) users"""
- if self.progress_mode == "PG" and self.progress and (self.progress > 0):
- return_value = (
- f'{self.content}
'
- )
- return return_value
+ progress = self.progress or 0
+ citation = (
+ f'comment on '
+ f"{self.book.title}"
+ )
+ if self.progress_mode == "PG" and progress > 0:
+ citation += f", p. {progress}"
+ return f"{self.content}
({citation})
"
activity_serializer = activitypub.Comment
@@ -354,22 +352,24 @@ class Quotation(BookStatus):
blank=True,
)
+ def _format_position(self) -> Optional[str]:
+ """serialize page position"""
+ beg = self.position
+ end = self.endposition or 0
+ if self.position_mode != "PG" or not beg:
+ return None
+ return f"pp. {beg}-{end}" if end > beg else f"p. {beg}"
+
@property
def pure_content(self):
"""indicate the book in question for mastodon (or w/e) users"""
quote = re.sub(r"^
", '
"', self.quote)
quote = re.sub(r"
$", '"', quote)
- if self.position_mode == "PG" and self.position and (self.position > 0):
- return_value = (
- f'{quote}