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

Some more fixes #4

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Some more fixes #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
353dc5f
Some fixes + info text at the end
fxthomas Mar 5, 2012
e393984
Added new docset creation script
fxthomas Mar 14, 2012
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
111 changes: 58 additions & 53 deletions PythonDocs2DocSet/create_docset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -90,6 +90,7 @@ def find_existing_file(possible):
modindex_path = find_existing_file([
"modindex.html",
"py-modindex.html",
"np-modindex.html"
])

genindex_path = find_existing_file([
Expand Down Expand Up @@ -170,24 +171,21 @@ def find_existing_file(possible):
apple_ref = "//apple_ref/cpp/cat/%s" % name
pages[href].append(apple_ref)


## Collect pages from the general index
with codecs.open(os.path.join(source_folder, genindex_path), 'r', encoding="utf-8") as f:
for line in f:
for search in re.finditer("(<dt>|, )<a href=\"([^#]+).*?\">", line):
href = search.group(2)
if not href in pages:
pages[href] = []


## Collect pages from the library index
if os.path.exists(os.path.join(source_folder, "library/index.html")):
with codecs.open(os.path.join(source_folder, "library/index.html"), 'r', encoding="utf-8") as f:
for line in f:
for search in re.finditer("<a class=\"reference external\" href=\"([^#\"]+).*?\">", line):
href = "library/" + search.group(1)
if not ("http://" in href or "https://" in href or href in pages):
pages[href] = []
## Collect remaning HTML pages
for path,_,files in os.walk ("."):
# Clean up path (remove "./")
cleanPath = re.sub (r"^./", "", path)
if cleanPath == ".":
cleanPath = ""
if os.path.samefile (path, dest_folder):
continue

# Walk through HTML files
for f in files:
if re.match (r".*\.html$", f):
href = os.path.join (cleanPath, f)
if not href in pages:
pages[href] = []

with codecs.open(token_path, "w", encoding="utf-8" ) as tokens:
## Start of the tokens file
Expand Down Expand Up @@ -222,41 +220,45 @@ def find_existing_file(possible):

## This adds some hidden tags that makes Dash display this page's
## TOC on the left side of the screen, just like with iOS and OSX docs
toc = soup.find('div', 'sphinxsidebarwrapper').findAll("a", "reference")
if len(toc) > 0:
toc_tag = soup.new_tag("div", style="display:none;")
soup.body.append(toc_tag)
a_tag = soup.new_tag("a")
a_tag["name"] = "#"
toc_tag.append(a_tag)
h3_tag = soup.new_tag("h3")
h3_tag["class"] = "tasks"
h3_tag.append("TOC")
toc_tag.append(h3_tag)
ul_tag = soup.new_tag("ul")
ul_tag["class"] = "tooltip"
toc_tag.append(ul_tag)

for t in toc:
li_tag = soup.new_tag("li")
li_tag["class"] = "tooltip"
ul_tag.append(li_tag)
a_tag = soup.new_tag("a")
a_tag["href"] = t['href']
a_tag.append(t.text)
li_tag.append(a_tag)

if len(names) > 0:
tokens.write("<File path=\"%s\">\n" % href)
for name in names:
tokens.write("\t<Token><TokenIdentifier>%s</TokenIdentifier><Anchor>%s</Anchor></Token>\n" % (name, name))
tokens.write("</File>\n")

newFilePath = os.path.join(dest_folder, href)
if not os.path.exists(os.path.dirname(newFilePath)):
os.makedirs(os.path.dirname(newFilePath)) # might be a bug...if given something/test.html, it creates test.html as a directory!
with codecs.open(newFilePath, "w", encoding="utf-8") as newFile:
newFile.write(unicode(soup))
tocdiv = soup.find('div', 'sphinxsidebarwrapper')
if tocdiv is None:
tocdiv = soup.find('div', 'sphinxsidebar')

if tocdiv is not None:
toc = tocdiv.findAll("a", "reference")
if len(toc) > 0:
toc_tag = soup.new_tag("div", style="display:none;")
soup.body.append(toc_tag)
a_tag = soup.new_tag("a")
a_tag["name"] = "#"
toc_tag.append(a_tag)
h3_tag = soup.new_tag("h3")
h3_tag["class"] = "tasks"
h3_tag.append("TOC")
toc_tag.append(h3_tag)
ul_tag = soup.new_tag("ul")
ul_tag["class"] = "tooltip"
toc_tag.append(ul_tag)

for t in toc:
li_tag = soup.new_tag("li")
li_tag["class"] = "tooltip"
ul_tag.append(li_tag)
a_tag = soup.new_tag("a")
a_tag["href"] = t['href']
a_tag.append(t.text)
li_tag.append(a_tag)

tokens.write("<File path=\"%s\">\n" % href)
for name in names:
tokens.write("\t<Token><TokenIdentifier>%s</TokenIdentifier><Anchor>%s</Anchor></Token>\n" % (name, name))
tokens.write("</File>\n")

newFilePath = os.path.join(dest_folder, href)
if not os.path.exists(os.path.dirname(newFilePath)):
os.makedirs(os.path.dirname(newFilePath)) # might be a bug...if given something/test.html, it creates test.html as a directory!
with codecs.open(newFilePath, "w", encoding="utf-8") as newFile:
newFile.write(unicode(soup))

tokens.write("</Tokens>")

Expand All @@ -274,3 +276,6 @@ def find_existing_file(possible):
os.remove(os.path.join(docset_folder, "Contents/Resources/Tokens.xml"))

print("done")
print("")
print("You might have to manually add missing references (images, ...) as they are not automatically detected.")
print("It is also a good practice to remove additional elements, such as headers, sidebars, and so on.")
Loading