Cool_Tools/mkdocs-material
1
0
Fork 0
mirror of https://github.com/squidfunk/mkdocs-material.git synced 2024-11-12 01:50:52 +01:00
Code Issues Releases Wiki Activity

Fixed blog readtime calculation to ignore non-content text (#7370)

Browse Source
This commit is contained in:
Sigurd Spieckermann 2024-07-16 15:49:13 +02:00 committed by GitHub
parent 4f8081c268
commit 6b13c560f5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 64 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
material/plugins/blog/readtime/parser.py
View File

@ -20,6 +20,10 @@
from html.parser import HTMLParser
# TODO: Refactor the `void` set into a common module and import it from there
# and not from the search plugin.
from material.plugins.search.plugin import void
# -----------------------------------------------------------------------------
# Classes
# -----------------------------------------------------------------------------
@ -31,15 +35,40 @@ class ReadtimeParser(HTMLParser):
def __init__(self):
super().__init__(convert_charrefs = True)
# Tags to skip
self.skip = set([
"object", # Objects
"script", # Scripts
"style", # Styles
"svg" # SVGs
])
# Current context
self.context = []
# Keep track of text and images
self.text = []
self.images = 0
# Collect images
# Called at the start of every HTML tag
def handle_starttag(self, tag, attrs):
# Collect images
if tag == "img":
self.images += 1
# Collect text
# Ignore self-closing tags
if tag not in void:
# Add tag to context
self.context.append(tag)
# Called for the text contents of each tag
def handle_data(self, data):
self.text.append(data)
# Collect text if not inside skip context
if not self.skip.intersection(self.context):
self.text.append(data)
# Called at the end of every HTML tag
def handle_endtag(self, tag):
if self.context and self.context[-1] == tag:
# Remove tag from context
self.context.pop()

35
src/plugins/blog/readtime/parser.py
View File

@ -20,6 +20,10 @@
from html.parser import HTMLParser
# TODO: Refactor the `void` set into a common module and import it from there
# and not from the search plugin.
from material.plugins.search.plugin import void
# -----------------------------------------------------------------------------
# Classes
# -----------------------------------------------------------------------------
@ -31,15 +35,40 @@ class ReadtimeParser(HTMLParser):
def __init__(self):
super().__init__(convert_charrefs = True)
# Tags to skip
self.skip = set([
"object", # Objects
"script", # Scripts
"style", # Styles
"svg" # SVGs
])
# Current context
self.context = []
# Keep track of text and images
self.text = []
self.images = 0
# Collect images
# Called at the start of every HTML tag
def handle_starttag(self, tag, attrs):
# Collect images
if tag == "img":
self.images += 1
# Collect text
# Ignore self-closing tags
if tag not in void:
# Add tag to context
self.context.append(tag)
# Called for the text contents of each tag
def handle_data(self, data):
self.text.append(data)
# Collect text if not inside skip context
if not self.skip.intersection(self.context):
self.text.append(data)
# Called at the end of every HTML tag
def handle_endtag(self, tag):
if self.context and self.context[-1] == tag:
# Remove tag from context
self.context.pop()