Autres/audacity
1
0
Fork 0
mirror of https://github.com/cookiengineer/audacity synced 2025-06-15 15:49:36 +02:00
Code Issues Releases Wiki Activity

Script to pull manual no longer includes the translations.

Browse Source
This commit is contained in:
james.k.crook@gmail.com 2011-04-29 14:45:28 +00:00
parent 793f52aeab
commit 79309f6df4
1 changed files with 25 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
scripts/mw2html_audacity/mw2html.py
View File

@ -250,6 +250,8 @@ def pre_html_transform(doc, url):
if config.remove_history:
doc = html_remove_image_history(doc)
doc = html_remove_translation_links(doc)
return doc
def pos_html_transform(doc, url):
@ -335,6 +337,16 @@ def html_remove_image_history(doc):
doc = re.sub(r'<h2>Image links</h2>[\s\S]+?</ul>', r'', doc)
return doc
def html_remove_translation_links(doc):
"""
Remove translation links (the international flags).
We identify them by the pattern for a 2 letter language code, /[\s\S][\s\S][/"]
in the URL.
"""
doc = re.sub(r'<a href="[^"]+/[\s\S][\s\S][/"][\s\S]+?</a>', r'<!--Removed Translation Flag-->', doc)
doc = re.sub(r'<a href="[^"]+/[\s\S][\s\S]_[\s\S][\s\S][/"][\s\S]+?</a>', r'<!--Removed Translation Flag2-->', doc)
return doc
def monobook_hack_skin_html(doc):
"""
Hacks Monobook HTML output: use CSS ids for hacked skin.
@ -625,6 +637,10 @@ def url_to_filename(url):
L[4] = L[4][len('title='):]
L[2] = L[2][:-len('index.php')]
if lpath[-1]=='man':
L[2] += '/' + INDEX_HTML
L[2] = L[2].strip('/')
#don't sanitize / for path
@ -933,15 +949,8 @@ def run(out=sys.stdout):
elif filename.endswith('.css'):
(doc, new_urls) = parse_css(doc, url)
# Enqueue URLs that we haven't yet spidered.
for u in new_urls:
if normalize_url(u) not in complete:
# Strip off any #section link.
if '#' in u:
u = u[:u.index('#')]
pending.add(u)
# Save document changes to disk
# The unmodified file already exists on disk.
update = False
text_ext = ('txt', 'html', 'rtf', 'css', 'sgml', 'xml')
for ext in text_ext:
@ -958,6 +967,14 @@ def run(out=sys.stdout):
out.write(url + '\n => ' + filename + '\n\n')
n += 1
# Enqueue URLs that we haven't yet spidered.
for u in new_urls:
if normalize_url(u) not in complete:
# Strip off any #section link.
if '#' in u:
u = u[:u.index('#')]
pending.add(u)
conn.close()
print "connection to", domain, "closed."
out.write(str(n) + ' files saved\n')