github/pelican
1
0
Fork 1
mirror of https://github.com/getpelican/pelican.git synced 2025-10-15 20:28:56 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #1813 from andreacorbellini/faster-truncation

Browse source 
When truncating, stop parsing the document immediately after finding the last word
This commit is contained in:
Justin Mayer 2015-09-23 08:58:55 -07:00
commit b152aba6c6
1 changed files with 18 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

23
pelican/utils.py
View file

@ -414,6 +414,13 @@ class _HTMLWordTruncator(HTMLParser):
_singlets = ('br', 'col', 'link', 'base', 'img', 'param', 'area', _singlets = ('br', 'col', 'link', 'base', 'img', 'param', 'area',
'hr', 'input') 'hr', 'input')
class TruncationCompleted(Exception):
def __init__(self, truncate_at):
super(_HTMLWordTruncator.TruncationCompleted, self).__init__(
truncate_at)
self.truncate_at = truncate_at
def __init__(self, max_words): def __init__(self, max_words):
# In Python 2, HTMLParser is not a new-style class, # In Python 2, HTMLParser is not a new-style class,
# hence super() cannot be used. # hence super() cannot be used.
@ -425,6 +432,16 @@ class _HTMLWordTruncator(HTMLParser):
self.last_word_end = None self.last_word_end = None
self.truncate_at = None self.truncate_at = None
def feed(self, *args, **kwargs):
try:
# With Python 2, super() cannot be used.
# See the comment for __init__().
HTMLParser.feed(self, *args, **kwargs)
except self.TruncationCompleted as exc:
self.truncate_at = exc.truncate_at
else:
self.truncate_at = None
def getoffset(self): def getoffset(self):
line_start = 0 line_start = 0
lineno, line_offset = self.getpos() lineno, line_offset = self.getpos()
@ -436,22 +453,18 @@ class _HTMLWordTruncator(HTMLParser):
self.words_found += 1 self.words_found += 1
self.last_word_end = None self.last_word_end = None
if self.words_found == self.max_words: if self.words_found == self.max_words:
self.truncate_at = word_end raise self.TruncationCompleted(word_end)
def add_last_word(self): def add_last_word(self):
if self.last_word_end is not None: if self.last_word_end is not None:
self.add_word(self.last_word_end) self.add_word(self.last_word_end)
def handle_starttag(self, tag, attrs): def handle_starttag(self, tag, attrs):
if self.truncate_at is not None:
return
self.add_last_word() self.add_last_word()
if tag not in self._singlets: if tag not in self._singlets:
self.open_tags.insert(0, tag) self.open_tags.insert(0, tag)
def handle_endtag(self, tag): def handle_endtag(self, tag):
if self.truncate_at is not None:
return
self.add_last_word() self.add_last_word()
try: try:
i = self.open_tags.index(tag) i = self.open_tags.index(tag)