def shorten_excerpt(content, terms):
"""
Iterates over the words in the excerpt and attempts to
"close the gap" between matched terms in an overly long excerpt.
Naive implementation.
"""
flattened_excerpt_words = []
last_term_appearence = 0
skipping_words = False
terms = compile_terms(terms)
for i, word in enumerate(content.split()):
# Spotted a matched term, set our state flag to false and update
# the "time" of our last term appearance
for term in terms:
if term.match(word):
last_term_appearence = i
skipping_words = False
# If it's been too long since our last match, start dropping words
if i - last_term_appearence > EXCERPT_MATCH_WINDOW_SIZE:
# Only want to add '...' once between terms,
# so check our state flag first
if not skipping_words:
flattened_excerpt_words.append('...')
skipping_words = True
continue
flattened_excerpt_words.append(word)
return ' '.join(flattened_excerpt_words)
def highlight(content, terms):
"""
Highlight the HTML with BeautifulSoup.
"""
index = 1
update_content = False
soup = BeautifulSoup(content)
terms = compile_terms(terms)
for term in terms:
for text in soup.find_all(text=term):
if text.parent.name in PROTECTED_MARKUPS:
continue
def highlight(match):
match_term = match.group(0)
return HIGHLIGHTING_PATTERN % {
'index': index, 'term': match_term}
new_text = term.sub(highlight, text)
text.replace_with(BeautifulSoup(new_text))
update_content = True
# Reload the entire soup, because substituion
# doesn't rebuild the document tree
soup = BeautifulSoup(str(soup))
index += 1
if update_content:
return str(soup)
return content
def generate_term_positions(splitted_content, terms):
"""
Iterates over the words in the corpus and stores the locations of
each matched query term. This data is structured as a list of lists,
where each sub-list contains all of the positions for a matched query
term.
"""
positions = [[] for i in range(len(terms))]
terms = compile_terms(sorted(terms))
for i, word in enumerate(splitted_content):
for term in terms:
if term.match(word):
positions[terms.index(term)].append(i)
break
return [x for x in positions if x]
def test_compile_terms(self):
terms = compile_terms(['toto', 'titi'])
self.assertTrue(terms[0].match('TOTO'))
def test_compile_terms(self):
terms = compile_terms(['toto', 'titi'])
self.assertTrue(terms[0].match('TOTO'))
