def _pinyin_search(request, search_string):
# CLEAN UP THE INCOMING PINYIN
clean_string = _normalize_pinyin(search_string)
ascii_string = _pinyin_to_ascii(search_string)
key = settings.PINYIN_WORD_KEY % ascii_string
suggested = []
words = []
r_server = _get_redis()
try:
for o in json.loads(r_server.get(key)):
word = ChineseWord(chars=o)
for i in word.meanings:
# IF THE CLEANED SEARCH STRING AND THE CONVERTED PINYIN MATCH
if _normalize_pinyin(i['pinyin']) == clean_string:
words.append(word)
# IF THERE'S NO NUMBERS IN THE CLEANED_STRING, ADD IT
elif not any(ext in clean_string for ext in ['1', '2', '3', '4', '5']):
words.append(word)
else:
suggested.append(word)
except TypeError:
pass
return _render(request, 'website/wordlist.html', locals())
def handle_noargs(self, **options):
# 一事無成 一事无成 [yi1 shi4 wu2 cheng2] /to have achieved nothing/to be a total failure/to get nowhere/
# EMPTY ALL ZH + PY KEYS
self._del_keys('ZH:*')
self._del_keys('PY:*')
# NOW LETS START
file = open(settings.DICT_FILE_LOCATION)
item_count = 0
for line in file:
if line.startswith("#"):
pass
else:
# OPEN REDIS CONNECTION NOW
r_server = _get_redis()
# GATHER ALL THE MAIN VARIABLES
new = line.split()
numbered_pinyin = line[(line.index('[')+1):(line.index(']'))]
f = ReadingFactory()
tonal_pinyin = f.convert(numbered_pinyin, 'Pinyin', 'Pinyin',
sourceOptions={'toneMarkType': 'numbers', 'yVowel': 'v',
'missingToneMark': 'fifth'})
meanings = line[(line.index('/')+1):(line.rindex('/'))]
characters = new[1]
# REMOVE ALL THE UGLY CHARACTERS
if '，' in characters:
characters = characters.replace('，', '')
# GET AND CLEAN THE MEASURE WORD
mws = None
if "CL:" in meanings:
new_meanings = meanings.split('/')
for idx, val in enumerate(new_meanings):
if "CL:" in val:
mws = []
for x in val.replace('CL:', '').split(','):
x = x[:(x.index('['))]
if '|' in x:
x = x[(x.index('|')+1):]
# ADD THE MEAASURE WORDS ENTRY
# ----------------------------
mws_key = settings.MEASURE_WORD_KEY % x
if r_server.exists(mws_key):
values = json.loads(_search_redis(mws_key))
values['chars'].append(characters)
else:
values = {'chars': [characters,]}
r_server.set(mws_key, json.dumps(values))
mws.append(x)
new_meanings.pop(idx)
meanings = "/".join(new_meanings)
char_key = settings.CHINESE_WORD_KEY % ((len((characters))/3), characters)
# CREATE THE PRONUNCIATION/MEANING PAIR
pair = {}
pair['pinyin'] = tonal_pinyin
pair['pinyin_numbered'] = _normalize_pinyin(numbered_pinyin)
pair['meaning'] = meanings
pair['measure_words'] = mws
# ADD THE PINYIN ENTRY
# --------------------
py_key = settings.PINYIN_WORD_KEY % _pinyin_to_ascii(numbered_pinyin)
if r_server.exists(py_key):
values = json.loads(_search_redis(py_key))
if smart_unicode(characters) not in values:
values.append(characters)
else:
values = [characters,]
r_server.set(py_key, json.dumps(values))
# ADD THE CHINESE CHARACTER ENTRY
# -------------------------------
if r_server.exists(char_key):
values = json.loads(_search_redis(char_key))
values['meanings'].append(pair)
else:
values = {
'chars': characters,
'meanings': [pair,],
}
r_server.set(char_key, json.dumps(values))
item_count += 1
print item_count
print "%s Chinese items added" % item_count
file.close()
