Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

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

Merged
merged 1 commit into from
Jul 16, 2024
Merged

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

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 32 additions & 3 deletions material/plugins/blog/readtime/parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
# -----------------------------------------------------------------------------
Expand All @@ -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 changes: 32 additions & 3 deletions src/plugins/blog/readtime/parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
# -----------------------------------------------------------------------------
Expand All @@ -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()