def search_mdx_entry(self):
result_list = self.mdx.look_up(self.query)
self.result_list = result_list
# result_list 0:start,1:end,2:r_p1,3:r_p2:4:entry,5:record
self.f_pk = self.dic.pk
r_list = []
for rt in result_list:
self.f_p1 = rt[2]
self.f_p2 = rt[3]
self.cmp.clear()
record = self.substitute_record(rt[5])
if record != '':
# 这里self.f_p2应该是不正确的，可能需要将自身的r_p1,r_p2也写入rsult_list中
r_list.append(
mdxentry(self.dic_name, rt[4], record, self.prior,
self.dic.pk, self.f_pk, self.f_p1, self.f_p2))
for i in range(len(r_list) - 1, -1, -1):
if r_list[i].mdx_record.find(
'@@@LINK') == 0 or r_list[i].mdx_record == '':
del r_list[i]
# 英文维基part3查back substitution结果是@@@LINK=Triangular matrixForward and back substitution，
# 但是指向的词条不存在，因此返回为空。
return r_list
def lemmatize_func(query, record_list, is_en):
# 设置成自定义功能，全局启用原形推测，仅在查询无结果时启用原形推测，关闭原形推测，推荐第二种设置。
words_list = []
if is_en:
words_list = lemmatize_word(query)
words_list_len = len(words_list)
mdict = []
if words_list_len > 0:
mdict.append('<div>' + query + '原形推测：</div>')
for w in words_list:
mdict.append('<div><span class="badge badge-pill badge-light">' +
w[1] + '</span><a href="entry://' + w[0] + '">' +
w[0] + '</a></div>')
# if len(record_list) == 0:
record_list.append(
mdxentry(builtin_dic_name, '', ''.join(mdict), 0, -1, -1, -1, -1))
# else:
# if record_list[len(record_list) - 1].mdx_name == builtin_dic_name:
# b = record_list[len(record_list) - 1]
#
# txt = b.mdx_record
# txt += '<hr />'
# txt += ''.join(mdict)
# b.mdx_record = txt
# del record_list[len(record_list) - 1]
# record_list.append(b)
# else:
# record_list.append(mdxentry(builtin_dic_name, '', ''.join(mdict), builtin_dic_pror, -1, -1, -1, -1))
return record_list
def extract_bultin_dic_all(r_list):
mdict = []
mdx_entry = []
r_list_len = len(r_list)
mdict.append(builtin_dic_prefix)
i = 1
for r in r_list:
mdx_entry.append(r.mdict_entry + '/') # 将显示的词条名用斜杠分隔开
mdict_content = get_mdict_content(r)
if 1 <= i < r_list_len:
mdict_content.append('<hr />')
i += 1
mdict.append(''.join(mdict_content))
if r_list_len > 0:
entry_t = ''.join(mdx_entry)
entry_t = entry_t[:len(entry_t) - 1] # 去掉entry后面的最后一个斜杠
return mdxentry(builtin_dic_name, entry_t, ''.join(mdict), 0, -1, -1,
-1, -1)
else:
return None
def key_spellcheck(query, record_list, is_en):
# 拼写检查
# 对只含字母，短横杠、撇号和空格的单词进行拼写检查
if is_en:
# 这里设置成自定义配置，是否开启拼写检查，始终开启拼写检查，仅当查询无结果时开启拼写检查，关闭拼写检查，推荐第二种设置。
'''
if len(record_list) > 0 and record_list[0].mdx_name == builtin_dic_name:
c_list = spellcheck(query)
for i in range(len(c_list) - 1, -1, -1):
if c_list[i] == query.lower():
del c_list[i]
if len(c_list) > 0:
if len(c_list) > 9:
c_list = c_list[:9]
mdxentry_t = record_list[0]
mdict_content = list(mdxentry_t.mdx_record)
mdict_content.append('<hr /><div>' + query + '拼写检查：</div>')
for c in c_list:
mdict_content.append('<div><a href="entry://' + c + '">' + c + '</a></div>')
mdxentry_t.mdx_record = ''.join(mdict_content)
record_list.pop(0)
record_list.append(mdxentry_t)
'''
c_list = spellcheck(query)
for i in range(len(c_list) - 1, -1, -1):
if c_list[i] == query.lower():
del c_list[i]
if len(c_list) > 0:
if len(c_list) > 9:
c_list = c_list[:9]
mdict_content = ['<div>' + query + '拼写检查：</div>']
for c in c_list:
mdict_content.append('<div><a href="entry://' + c + '">' + c +
'</a></div>')
# record_list.insert(0, mdxentry(builtin_dic_name, query, ''.join(mdict_content), 20, -1, -1, -1))
record_list.append(
mdxentry(builtin_dic_name, query, ''.join(mdict_content), 20,
-1, -1, -1, -1))
return record_list
def merge_record(query, record_list):
# 多于4个的词条进行合并，主要是处理国家教育研究院双语词汇双向词典，该词典查variation有27个词条。
# 长度小于500才合并，原因是英和中词典的a词条都合并起来，特别特别长，iframe展开时，台式机要卡住好长时间才能显示
merge_entry_num = get_config_con('merge_entry_num')
merge_entry_max_length = get_config_con('merge_entry_max_length')
dic_dict = {}
for i in range(len(record_list)):
mdx_name = record_list[i].mdx_name
mdx_record = record_list[i].mdx_record
if len(mdx_record) < merge_entry_max_length: # 这里暂时性的判断
if mdx_name in dic_dict:
dic_dict[mdx_name] += 1
else:
dic_dict[mdx_name] = 1
dic_list = []
for k, v in dic_dict.items():
if v >= merge_entry_num:
dic_list.append(k)
t_list = []
for dic in dic_list:
record = ''
pror = 1
for i in range(len(record_list) - 1, -1, -1):
mdx = record_list[i]
if mdx.mdx_name == dic:
record = mdx.mdx_record + record
pror = mdx.mdx_pror
del record_list[i]
t_list.append(mdxentry(dic, query, record, pror, -1, -1, -1, -1))
record_list.extend(t_list)
return record_list