def msgindex(self): self.fwd_lookup = {} self.words = collections.Counter() self.msgtok = {} for mid, value in self.msgs.items(): src, text, date, fwd_src, fwd_date, reply_id, media = value self.fwd_lookup[(src, date)] = mid tok = self.msgtok[mid] = tuple(self.msgpreprocess(zhconv.convert(self.tc.truecase(re_url.sub('', stripreaction(text))), 'zh-hans'))) for w in frozenset(t.lower() for t in tok): self.words[w] += 1 self.words = dict(self.words)
def cmd_ime(expr, chatid, replyid, msg): '''/ime [pinyin] Simple Pinyin IME.''' tinput = '' if 'reply_to_message' in msg: tinput = msg['reply_to_message'].get('text', '') tinput = (expr or tinput).strip() if len(tinput) > 200: tinput = tinput[:200] + '…' if not tinput: sendmsg('Syntax error. Usage: ' + cmd_ime.__doc__, chatid, replyid) return res = zhconv.convert(simpleime.pinyininput(tinput), 'zh-hans') sendmsg(res, chatid, replyid)
def getsayingbytext(text='', mode='r'): global SAY_P with SAY_LCK: text = (mode + ' '.join(mosesproxy.cut(zhconv.convert(text, 'zh-hans'), HMM=False)[:60]).strip()).encode('utf-8') + b'\n' try: SAY_P.stdin.write(text) SAY_P.stdin.flush() say = SAY_P.stdout.readline().strip().decode('utf-8') except BrokenPipeError: SAY_P = subprocess.Popen(SAY_CMD, stdin=subprocess.PIPE, stdout=subprocess.PIPE, cwd='vendor') SAY_P.stdin.write(text) SAY_P.stdin.flush() say = SAY_P.stdout.readline().strip().decode('utf-8') return say
def msgindex(self): self.fwd_lookup = {} self.words = collections.Counter() self.msgtok = {} for mid, value in self.msgs.items(): src, text, date, fwd_src, fwd_date, reply_id, media = value self.fwd_lookup[(src, date)] = mid tok = self.msgtok[mid] = tuple( self.msgpreprocess( zhconv.convert( self.tc.truecase(re_url.sub('', stripreaction(text))), 'zh-hans'))) for w in frozenset(t.lower() for t in tok): self.words[w] += 1 self.words = dict(self.words)
def cmd_cc(expr): if zhconv.issimp(expr): return zhconv.convert(expr, 'zh-hant') else: return zhconv.convert(expr, 'zh-hans')
def cmd_ime(expr): return zhconv.convert(simpleime.pinyininput(expr.lower()), 'zh-hans')