def zsite2keyword(z):
r = []
t = defaultdict(int)
id = z.id
name = z.name
if name:
for word in seg_title_search(name):
t[word] += 2
url = url_by_id(id)
if url:
t[url] += 2
if z.cid == CID_SITE:
for word in seg_title_search(motto_get(id)):
t[word] += 1
elif z.cid == CID_USER:
mail = mail_by_user_id(id)
if mail:
t[mail] += 2
t[mail.split('@', 1)[0]] += 2
txt = txt_get(id)
if txt:
man_txt_len = len(txt)
for word in seg_txt_search(txt):
t[word] += 1
for seq, career in enumerate(career_list_all(id)):
if seq:
add = 1
else:
add = 2
unit = career.unit
title = career.title
txt = career.txt
if unit:
for word in seg_title_search(unit):
t[word] += add
if title:
for word in seg_title_search(title):
t[word] += add
if txt:
for word in seg_txt_search(txt):
t[word] += add
return t
def zsite2keyword(z):
r = []
t = defaultdict(int)
id = z.id
name = z.name
if name:
for word in seg_title_search(name):
t[word] += 2
url = url_by_id(id)
if url:
t[url] += 2
if z.cid == CID_SITE:
for word in seg_title_search(motto_get(id)):
t[word] += 1
elif z.cid == CID_USER:
mail = mail_by_user_id(id)
if mail:
t[mail] += 2
t[mail.split('@', 1)[0]] += 2
txt = txt_get(id)
if txt:
man_txt_len = len(txt)
for word in seg_txt_search(txt):
t[word] += 1
for seq, career in enumerate(career_list_all(id)):
if seq:
add = 1
else:
add = 2
unit = career.unit
title = career.title
txt = career.txt
if unit:
for word in seg_title_search(unit):
t[word] += add
if title:
for word in seg_title_search(title):
t[word] += add
if txt:
for word in seg_txt_search(txt):
t[word] += add
return t
def split_words(text):
"""docstring for split_words"""
words = []
for i in seg_txt_search(text):
words.append(i)
return words
def split_words(text):
"""docstring for split_words"""
words = []
for i in seg_txt_search(text):
words.append(i)
return words
def guess_keywords(querystring, known_prefix=None):
stem = xapian.Stem('en')
words = set()
contains_chinese = 0
for piece in querystring.split():
prefix = None
if known_prefix and ':' in piece:
qprefix, other = piece.split(':', 1)
if qprefix in known_prefix:
prefix = known_prefix[qprefix]
piece = other
for word in seg_txt_search(piece):
if ord(word[0]) <= 127: # english
word = stem(word)
else:
contains_chinese = 1
if prefix:
words.add(prefix + word)
else:
words.add(word)
return contains_chinese, list(words)
def guess_keywords(querystring, known_prefix=None):
stem = xapian.Stem('en')
words = set()
contains_chinese = 0
for piece in querystring.split():
prefix = None
if known_prefix and ':' in piece:
qprefix, other = piece.split(':', 1)
if qprefix in known_prefix:
prefix = known_prefix[qprefix]
piece = other
for word in seg_txt_search(piece):
if ord(word[0]) <= 127: # english
word = stem(word)
else:
contains_chinese = 1
if prefix:
words.add(prefix + word)
else:
words.add(word)
return contains_chinese, list(words)
def split_words(text):
"""docstring for split_words"""
return [i for i in seg_txt_search(text)]
