From 299a6342cc4b5fecde84059e437ed9aab72474d0 Mon Sep 17 00:00:00 2001
From: Jake Howard <git@theorangeone.net>
Date: Sun, 26 Jun 2022 19:25:30 +0100
Subject: [PATCH] Add basic word count and reading time

---
 website/common/models.py      | 10 +++++++---
 website/common/streamfield.py | 23 +++++++++++++++++++++--
 2 files changed, 28 insertions(+), 5 deletions(-)

diff --git a/website/common/models.py b/website/common/models.py
index f4e50b4..a6deb52 100644
--- a/website/common/models.py
+++ b/website/common/models.py
@@ -1,3 +1,4 @@
+import math
 from typing import Any
 
 from django.db import models
@@ -8,7 +9,7 @@ from wagtail.fields import StreamField
 from wagtail.images import get_image_model_string
 from wagtail.models import Page
 
-from .streamfield import get_blocks
+from .streamfield import get_blocks, get_word_count
 from .utils import TocEntry, get_table_of_contents
 
 
@@ -53,11 +54,14 @@ class BaseContentMixin(models.Model):
 
     @cached_property
     def reading_time(self) -> int:
-        return 4
+        """
+        https://help.medium.com/hc/en-us/articles/214991667-Read-time
+        """
+        return int(math.ceil(self.word_count / 265))
 
     @cached_property
     def word_count(self) -> int:
-        return 1600
+        return get_word_count(self.body)
 
 
 class ContentPage(BasePage, BaseContentMixin):  # type: ignore[misc]
diff --git a/website/common/streamfield.py b/website/common/streamfield.py
index 13f65e7..0b91bc6 100644
--- a/website/common/streamfield.py
+++ b/website/common/streamfield.py
@@ -1,13 +1,18 @@
+from typing import Iterator
+
 from django.utils import lorem_ipsum
-from django.utils.html import format_html_join
+from django.utils.html import format_html_join, strip_tags
+from django.utils.text import smart_split
 from wagtail import blocks
 from wagtail.embeds.blocks import EmbedBlock
 
+IGNORE_WORDCOUNT_BLOCKS = (blocks.RawHTMLBlock, EmbedBlock)
+
 
 class LoremBlock(blocks.StructBlock):
     paragraphs = blocks.IntegerBlock(min_value=1)
 
-    def render(self, value: dict, context: dict) -> str:
+    def render(self, value: dict, context: dict | None = None) -> str:
         return format_html_join(
             "\n\n",
             "<p>{}</p>",
@@ -26,3 +31,17 @@ def get_blocks() -> list[tuple[str, blocks.BaseBlock]]:
         ("lorem", LoremBlock()),
         ("html", blocks.RawHTMLBlock()),
     ]
+
+
+def get_plain_text(value: blocks.StreamValue) -> Iterator[str]:
+    for block in value:
+        if isinstance(block.block_type, IGNORE_WORDCOUNT_BLOCKS):
+            continue
+        yield strip_tags(str(block))
+
+
+def get_word_count(value: blocks.StreamValue) -> int:
+    count = 0
+    for chunk in get_plain_text(value):
+        count += len(list(smart_split(chunk)))
+    return count