mirror of
https://github.com/python/cpython.git
synced 2025-10-30 21:21:22 +00:00
[3.13] gh-129873: IDLE: Improve help.py's method of parsing HTML (GH-129859) (#129884)
gh-129873: IDLE: Improve help.py's method of parsing HTML (GH-129859)
In `help.copy_strip`, only copy the text `<section>`. In `help.HelpParser.handle_starttag` and elsewhere, remove code to skip the no longer present html. Add a reminder at the top of idle.rst to run copy_strip after changes.
---------
(cherry picked from commit 6fbf15f98e)
Co-authored-by: Stan Ulbrych <89152624+StanFromIreland@users.noreply.github.com>
Co-authored-by: Terry Jan Reedy <tjreedy@udel.edu>
This commit is contained in:
Miss Islington (bot)
GitHub
parent
c28eed3c27
commit
f7d885a8ff
5 changed files with 30 additions and 416 deletions
|
|
@ -20,7 +20,7 @@
|
|||
|
||||
HelpWindow - Display HelpFrame in a standalone window.
|
||||
|
||||
copy_strip - Copy idle.html to help.html, rstripping each line.
|
||||
copy_strip - Copy the text part of idle.html to help.html while rstripping each line.
|
||||
|
||||
show_idlehelp - Create HelpWindow. Called in EditorWindow.help_dialog.
|
||||
"""
|
||||
|
|
@ -54,7 +54,6 @@ def __init__(self, text):
|
|||
self.text = text # Text widget we're rendering into.
|
||||
self.tags = '' # Current block level text tags to apply.
|
||||
self.chartags = '' # Current character level text tags.
|
||||
self.show = False # Exclude html page navigation.
|
||||
self.hdrlink = False # Exclude html header links.
|
||||
self.level = 0 # Track indentation level.
|
||||
self.pre = False # Displaying preformatted text?
|
||||
|
|
@ -77,11 +76,7 @@ def handle_starttag(self, tag, attrs):
|
|||
if a == 'class':
|
||||
class_ = v
|
||||
s = ''
|
||||
if tag == 'section' and attrs == [('id', 'idle')]:
|
||||
self.show = True # Start main content.
|
||||
elif tag == 'div' and class_ == 'clearer':
|
||||
self.show = False # End main content.
|
||||
elif tag == 'p' and self.prevtag and not self.prevtag[0]:
|
||||
if tag == 'p' and self.prevtag and not self.prevtag[0]:
|
||||
# Begin a new block for <p> tags after a closed tag.
|
||||
# Avoid extra lines, e.g. after <pre> tags.
|
||||
lastline = self.text.get('end-1c linestart', 'end-1c')
|
||||
|
|
@ -112,31 +107,27 @@ def handle_starttag(self, tag, attrs):
|
|||
s = '\n'
|
||||
elif tag == 'pre':
|
||||
self.pre = True
|
||||
if self.show:
|
||||
self.text.insert('end', '\n\n')
|
||||
self.text.insert('end', '\n\n')
|
||||
self.tags = 'preblock'
|
||||
elif tag == 'a' and class_ == 'headerlink':
|
||||
self.hdrlink = True
|
||||
elif tag == 'h1':
|
||||
self.tags = tag
|
||||
elif tag in ['h2', 'h3']:
|
||||
if self.show:
|
||||
self.header = ''
|
||||
self.text.insert('end', '\n\n')
|
||||
self.header = ''
|
||||
self.text.insert('end', '\n\n')
|
||||
self.tags = tag
|
||||
if self.show:
|
||||
self.text.insert('end', s, (self.tags, self.chartags))
|
||||
self.text.insert('end', s, (self.tags, self.chartags))
|
||||
self.prevtag = (True, tag)
|
||||
|
||||
def handle_endtag(self, tag):
|
||||
"Handle endtags in help.html."
|
||||
if tag in ['h1', 'h2', 'h3']:
|
||||
assert self.level == 0
|
||||
if self.show:
|
||||
indent = (' ' if tag == 'h3' else
|
||||
' ' if tag == 'h2' else
|
||||
'')
|
||||
self.toc.append((indent+self.header, self.text.index('insert')))
|
||||
indent = (' ' if tag == 'h3' else
|
||||
' ' if tag == 'h2' else
|
||||
'')
|
||||
self.toc.append((indent+self.header, self.text.index('insert')))
|
||||
self.tags = ''
|
||||
elif tag in ['span', 'em']:
|
||||
self.chartags = ''
|
||||
|
|
@ -151,7 +142,7 @@ def handle_endtag(self, tag):
|
|||
|
||||
def handle_data(self, data):
|
||||
"Handle date segments in help.html."
|
||||
if self.show and not self.hdrlink:
|
||||
if not self.hdrlink:
|
||||
d = data if self.pre else data.replace('\n', ' ')
|
||||
if self.tags == 'h1':
|
||||
try:
|
||||
|
|
@ -253,7 +244,7 @@ def __init__(self, parent, filename, title):
|
|||
|
||||
|
||||
def copy_strip(): # pragma: no cover
|
||||
"""Copy idle.html to idlelib/help.html, stripping trailing whitespace.
|
||||
"""Copy the text part of idle.html to idlelib/help.html while stripping trailing whitespace.
|
||||
|
||||
Files with trailing whitespace cannot be pushed to the git cpython
|
||||
repository. For 3.x (on Windows), help.html is generated, after
|
||||
|
|
@ -265,7 +256,7 @@ def copy_strip(): # pragma: no cover
|
|||
|
||||
It can be worthwhile to occasionally generate help.html without
|
||||
touching idle.rst. Changes to the master version and to the doc
|
||||
build system may result in changes that should not changed
|
||||
build system may result in changes that should not change
|
||||
the displayed text, but might break HelpParser.
|
||||
|
||||
As long as master and maintenance versions of idle.rst remain the
|
||||
|
|
@ -278,10 +269,14 @@ def copy_strip(): # pragma: no cover
|
|||
src = join(abspath(dirname(dirname(dirname(__file__)))),
|
||||
'Doc', 'build', 'html', 'library', 'idle.html')
|
||||
dst = join(abspath(dirname(__file__)), 'help.html')
|
||||
with open(src, 'rb') as inn,\
|
||||
open(dst, 'wb') as out:
|
||||
|
||||
with open(src, 'r', encoding="utf-8") as inn, open(dst, 'w', encoding="utf-8") as out:
|
||||
copy = False
|
||||
for line in inn:
|
||||
out.write(line.rstrip() + b'\n')
|
||||
if '<section id="idle">' in line: copy = True
|
||||
if '<div class="clearer">' in line: break
|
||||
if copy: out.write(line.strip() + '\n')
|
||||
|
||||
print(f'{src} copied to {dst}')
|
||||
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue