Simplify summary and word count implementations

website/common/models.py

@@ -11,7 +11,7 @@ from django.http.response import Http404, HttpResponse, HttpResponseBadRequest
 from django.shortcuts import redirect
 from django.template.defaultfilters import pluralize
 from django.utils.functional import cached_property, classproperty
-from django.utils.text import slugify
+from django.utils.text import Truncator, slugify
 from wagtail.admin.panels import FieldPanel, MultiFieldPanel
 from wagtail.contrib.routable_page.models import RoutablePageMixin, route
 from wagtail.contrib.settings.models import BaseGenericSetting, register_setting
@@ -31,12 +31,10 @@ from .serializers import PaginationSerializer
 from .streamfield import add_heading_anchors, get_blocks, get_content_html
 from .utils import (
     TocEntry,
-    count_words,
     extract_text,
     get_site_title,
     get_table_of_contents,
     get_url_mime_type,
-    truncate_string,
 )
 
 
@@ -141,16 +139,11 @@ class BaseContentPage(BasePage, MetadataMixin):
 
     @cached_property
     def word_count(self) -> int:
-        return count_words(self.plain_text)
+        return len(self.plain_text.split())
 
     @cached_property
     def summary(self) -> str:
-        summary = truncate_string(self.plain_text, 50)
-
-        if summary and summary != self.plain_text and not summary.endswith("."):
-            summary += "…"
-
-        return summary
+        return Truncator(self.plain_text).words(50)
 
     @cached_property
     def body_html(self) -> str:

website/common/tests/test_utils.py

@@ -3,7 +3,6 @@ from django.test import SimpleTestCase
 from wagtail.rich_text import features as richtext_feature_registry
 
 from website.common.utils import (
-    count_words,
     extract_text,
     get_table_of_contents,
     heading_id,
@@ -97,13 +96,6 @@ class ExtractTextTestCase(SimpleTestCase):
         self.assertEqual(extract_text("Hello there!"), "Hello there!")
 
 
-class CountWordsTestCase(SimpleTestCase):
-    def test_counts_words(self) -> None:
-        self.assertEqual(count_words("a b c"), 3)
-        self.assertEqual(count_words("Correct Horse Battery Staple"), 4)
-        self.assertEqual(count_words("Hello there! How are you?"), 5)
-
-
 class RichTextFeaturesTestCase(SimpleTestCase):
     def test_features_exist(self) -> None:
         for editor, editor_config in settings.WAGTAILADMIN_RICH_TEXT_EDITORS.items():

website/common/utils.py

@@ -1,13 +1,13 @@
 from dataclasses import dataclass
-from itertools import islice, pairwise
-from typing import Iterable, Optional, Type
+from itertools import pairwise
+from typing import Optional, Type
 
 import requests
 from bs4 import BeautifulSoup, SoupStrainer
 from django.conf import settings
 from django.db import models
 from django.http.request import HttpRequest
-from django.utils.text import re_words, slugify
+from django.utils.text import slugify
 from django_cache_decorator import django_cache_decorator
 from wagtail.models import Page, Site
 from wagtail.models import get_page_models as get_wagtail_page_models
@@ -69,19 +69,6 @@ def show_toolbar_callback(request: HttpRequest) -> bool:
     return settings.DEBUG
 
 
-def split_words(text: str) -> Iterable[str]:
-    for word in re_words.split(text):
-        if word and word.strip():
-            yield word.strip()
-
-
-def count_words(text: str) -> int:
-    """
-    Count the number of words in the text, without duplicating the item in memory
-    """
-    return len(list(split_words(text)))
-
-
 def extract_text(html: str) -> str:
     """
     Get the plain text of some HTML.
@@ -91,10 +78,6 @@ def extract_text(html: str) -> str:
     )
 
 
-def truncate_string(text: str, words: int) -> str:
-    return " ".join(islice(split_words(text), words))
-
-
 def heading_id(heading: str) -> str:
     """
     Convert a heading into an identifier which is valid for a HTML id attribute