In [1]:

    

from pystardict import Dictionary
from pathlib import Path
import re
from ipywidgets import interact


    

In [2]:

    

# ---------- output string format ----------
indexword_out_str = '{0}'
pos_out_str = ' {0}{1}'
pos_cn_out_str = ' {0}{1}'
phon_out_str = ' {0}'
misc_out_str = ' {0}'
dict_name_out_str = ' {0}'

# regular expressions
pos_reg = re.compile('(a|v|n|ad|adj|adv|vt|vi)\.')
pos_cn_reg = re.compile('【.*】')
phon_reg = re.compile('\*?\[.*\]')
pinyin_bug = re.compile('([a-z]\?.*){2,}')
jap_bug = re.compile('\$')


    

In [3]:

    

# ---------- loading all the dictionaries ----------
dictionaries = []
dict_book_names = []
dict_path_prefix = Path.home().joinpath('.stardict')
for i_dir in dict_path_prefix.glob('*'):
    dict_path = dict_path_prefix.joinpath(i_dir)
    dict_dir_name = str(dict_path) + '/'
    for dict_name in dict_path.glob('*'):
        if dict_name.match('*.ifo'):
            info_name = dict_name.stem
            with open(str(dict_name), 'r') as dict_info_file:
                for line in dict_info_file:
                    if line.startswith('bookname'):
                        words = line.strip().split('=')
                        dict_book_names.append(words[-1])
        if dict_name.match('*.idx'):
            indx_name = dict_name.stem
        if dict_name.match('*.dict') or dict_name.match('*.dict.dz'):
            data_name = dict_name.stem.split('.')[0]
    if not info_name == indx_name == data_name:
        print('Error: Dictionary name should be same for .ifo .idx and .dict (.dict.dz) files.')
    else:
        dict_name = dict_dir_name + data_name
        dict1 = Dictionary(dict_name, True)
        dictionaries.append(dict1)


    

In [4]:

    

def sdcv(request, dict_sel_opt):
    dict_local = dictionaries
    dnames_loc = dict_book_names
    try:
        d_tmp = dict_local[dict_sel_opt]
        dict_local = [d_tmp]
        name_tmp = dnames_loc[dict_sel_opt]
        dnames_loc = [name_tmp]
    except Exception:
        print(' Using all the dictionaries: ')

    for i, d in enumerate(dict_local):
        dict_key_list = d.keys()
        for dict_word in dict_key_list:
            if request == dict_word:
                translation = d[dict_word]
                print('--------------------------------------------------')
                print(dict_name_out_str.format(dnames_loc[i]))
                print(indexword_out_str.format(dict_word))
                for transline in translation.split('\n'):
                    m_pos = re.match(pos_reg, transline)
                    m_pos_cn = re.search(pos_cn_reg, transline)
                    if m_pos:
                        print(pos_out_str.format(transline[:m_pos.end()], transline[m_pos.end():]))
                    elif m_pos_cn:
                        print(pos_cn_out_str.format(transline[:m_pos_cn.end()], transline[m_pos_cn.end():]))
                    elif re.match(phon_reg, transline):
                        print(phon_out_str.format(transline))
                    elif transline.startswith('词形') or transline.startswith('例句') or transline.startswith('相关'):
                        print('~~~~~~~~~~~~~~~~~~~~')
                        print(misc_out_str.format(transline))
                    elif re.match(pinyin_bug, transline):
                        pass
                    elif jap_bug.match(transline):
                        print('  ', transline[1:])
                    else:
                        print(' ', transline)


    

In [5]:

    

dictionary_bookname_dict = {}
for i, bname in enumerate(dict_book_names):
    dictionary_bookname_dict[bname] = i
dictionary_bookname_dict["All"] = len(dict_book_names) + 1


    

In [6]:

    

interact(sdcv, dict_sel_opt=dictionary_bookname_dict, request='')


    

    




 Using all the dictionaries: