latex/onpoint
6
0
Fork 0
Code Issues 2 Pull Requests Releases 1 Wiki Activity

Add more specific fragment tag identification

Browse Source
This commit is contained in:
Knoch 2020-06-11 10:52:07 +02:00
parent 9b05df056f
commit 4ce0b0dcd6
1 changed files with 14 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
fragments.py
View File

@ -10,9 +10,19 @@ FRAGMENT_CLASS = "fragment"
# Search and delete the FRAGMENT_TAG anywhere in the given HTML
# while adding the FRAGMENT_CLASS as an attribute
# @returns the HTML with all FRAGMENT_TAG instances shifted to an attribute
def defragmentize(html):
dom = etree.fromstring(html)
fragments = dom.xpath("//*[contains(text(), '%s')]" % FRAGMENT_TAG)
query = "|".join([
# FRAGMENT_TAG between two spaces
"//*[contains(text(), ' %s ')]" % FRAGMENT_TAG,
# FRAGMENT_TAG as first element followed by a space
"//*[starts-with(text(), '%s ')]" % FRAGMENT_TAG,
# FRAGMENT_TAG after a tab, followed by a space
"//*[contains(text(), '\t%s ')]" % FRAGMENT_TAG
])
fragments = dom.xpath(query)
for fragment in fragments:
class_list = fragment.get('class')
@ -22,7 +32,8 @@ def defragmentize(html):
class_list += " %s" % FRAGMENT_CLASS
fragment.set('class', class_list)
fragment.text = re.sub(r"\s*%s\s*" % re.escape(FRAGMENT_TAG), '', fragment.text)
fragment.text = re.sub(r"\s*%s\s*" %
re.escape(FRAGMENT_TAG), '', fragment.text)
return etree.tostring(dom, method='html', encoding='utf-8',
pretty_print=True).decode('utf-8')
pretty_print=True).decode('utf-8')