-
Notifications
You must be signed in to change notification settings - Fork 0
/
mdict_query.py
350 lines (315 loc) · 12.1 KB
/
mdict_query.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
# -*- coding: utf-8 -*-
from readmdict import MDX, MDD
from struct import pack, unpack
from io import BytesIO
import re
import sys
import os
import sqlite3
import json
# zlib compression is used for engine version >=2.0
import zlib
# LZO compression is used for engine version < 2.0
try:
import lzo
except ImportError:
lzo = None
#print("LZO compression support is not available")
# 2x3 compatible
if sys.hexversion >= 0x03000000:
unicode = str
version = '1.1'
class IndexBuilder(object):
#todo: enable history
def __init__(self, fname, encoding = "", passcode = None, force_rebuild = False, enable_history = False, sql_index = True, check = False):
self._mdx_file = fname
self._mdd_file = ""
self._encoding = ''
self._stylesheet = {}
self._title = ''
self._version = ''
self._description = ''
self._sql_index = sql_index
self._check = check
_filename, _file_extension = os.path.splitext(fname)
assert(_file_extension == '.mdx')
assert(os.path.isfile(fname))
self._mdx_db = _filename + ".mdx.db"
# make index anyway
if force_rebuild:
self._make_mdx_index(self._mdx_db)
if os.path.isfile(_filename + '.mdd'):
self._mdd_file = _filename + ".mdd"
self._mdd_db = _filename + ".mdd.db"
self._make_mdd_index(self._mdd_db)
if os.path.isfile(self._mdx_db):
#read from META table
conn = sqlite3.connect(self._mdx_db)
#cursor = conn.execute("SELECT * FROM META")
cursor = conn.execute("SELECT * FROM META WHERE key = \"version\"")
#判断有无版本号
for cc in cursor:
self._version = cc[1]
################# if not version in fo #############
if not self._version:
print("version info not found")
conn.close()
self._make_mdx_index(self._mdx_db)
print("mdx.db rebuilt!")
if os.path.isfile(_filename + '.mdd'):
self._mdd_file = _filename + ".mdd"
self._mdd_db = _filename + ".mdd.db"
self._make_mdd_index(self._mdd_db)
print("mdd.db rebuilt!")
return None
cursor = conn.execute("SELECT * FROM META WHERE key = \"encoding\"")
for cc in cursor:
self._encoding = cc[1]
cursor = conn.execute("SELECT * FROM META WHERE key = \"stylesheet\"")
for cc in cursor:
self._stylesheet = json.loads(cc[1])
cursor = conn.execute("SELECT * FROM META WHERE key = \"title\"")
for cc in cursor:
self._title = cc[1]
cursor = conn.execute("SELECT * FROM META WHERE key = \"description\"")
for cc in cursor:
self._description = cc[1]
#for cc in cursor:
# if cc[0] == 'encoding':
# self._encoding = cc[1]
# continue
# if cc[0] == 'stylesheet':
# self._stylesheet = json.loads(cc[1])
# continue
# if cc[0] == 'title':
# self._title = cc[1]
# continue
# if cc[0] == 'title':
# self._description = cc[1]
else:
self._make_mdx_index(self._mdx_db)
if os.path.isfile(_filename + ".mdd"):
self._mdd_file = _filename + ".mdd"
self._mdd_db = _filename + ".mdd.db"
if not os.path.isfile(self._mdd_db):
self._make_mdd_index(self._mdd_db)
pass
def _replace_stylesheet(self, txt):
# substitute stylesheet definition
txt_list = re.split('`\d+`', txt)
txt_tag = re.findall('`\d+`', txt)
txt_styled = txt_list[0]
for j, p in enumerate(txt_list[1:]):
style = self._stylesheet[txt_tag[j][1:-1]]
if p and p[-1] == '\n':
txt_styled = txt_styled + style[0] + p.rstrip() + style[1] + '\r\n'
else:
txt_styled = txt_styled + style[0] + p + style[1]
return txt_styled
def _make_mdx_index(self, db_name):
if os.path.exists(db_name):
os.remove(db_name)
mdx = MDX(self._mdx_file)
self._mdx_db = db_name
returned_index = mdx.get_index(check_block = self._check)
index_list = returned_index['index_dict_list']
conn = sqlite3.connect(db_name)
c = conn.cursor()
c.execute(
''' CREATE TABLE MDX_INDEX
(key_text text not null,
file_pos integer,
compressed_size integer,
decompressed_size integer,
record_block_type integer,
record_start integer,
record_end integer,
offset integer
)'''
)
tuple_list = [
(item['key_text'],
item['file_pos'],
item['compressed_size'],
item['decompressed_size'],
item['record_block_type'],
item['record_start'],
item['record_end'],
item['offset']
)
for item in index_list
]
c.executemany('INSERT INTO MDX_INDEX VALUES (?,?,?,?,?,?,?,?)',
tuple_list)
# build the metadata table
meta = returned_index['meta']
c.execute(
'''CREATE TABLE META
(key text,
value text
)''')
#for k,v in meta:
# c.execute(
# 'INSERT INTO META VALUES (?,?)',
# (k, v)
# )
c.executemany(
'INSERT INTO META VALUES (?,?)',
[('encoding', meta['encoding']),
('stylesheet', meta['stylesheet']),
('title', meta['title']),
('description', meta['description']),
('version', version)
]
)
if self._sql_index:
c.execute(
'''
CREATE INDEX key_index ON MDX_INDEX (key_text)
'''
)
conn.commit()
conn.close()
#set class member
self._encoding = meta['encoding']
self._stylesheet = json.loads(meta['stylesheet'])
self._title = meta['title']
self._description = meta['description']
def _make_mdd_index(self, db_name):
if os.path.exists(db_name):
os.remove(db_name)
mdd = MDD(self._mdd_file)
self._mdd_db = db_name
index_list = mdd.get_index(check_block = self._check)
conn = sqlite3.connect(db_name)
c = conn.cursor()
c.execute(
''' CREATE TABLE MDX_INDEX
(key_text text not null unique,
file_pos integer,
compressed_size integer,
decompressed_size integer,
record_block_type integer,
record_start integer,
record_end integer,
offset integer
)'''
)
tuple_list = [
(item['key_text'],
item['file_pos'],
item['compressed_size'],
item['decompressed_size'],
item['record_block_type'],
item['record_start'],
item['record_end'],
item['offset']
)
for item in index_list
]
c.executemany('INSERT INTO MDX_INDEX VALUES (?,?,?,?,?,?,?,?)',
tuple_list)
if self._sql_index:
c.execute(
'''
CREATE UNIQUE INDEX key_index ON MDX_INDEX (key_text)
'''
)
conn.commit()
conn.close()
@staticmethod
def get_data_by_index(fmdx, index):
fmdx.seek(index['file_pos'])
record_block_compressed = fmdx.read(index['compressed_size'])
record_block_type = record_block_compressed[:4]
record_block_type = index['record_block_type']
decompressed_size = index['decompressed_size']
#adler32 = unpack('>I', record_block_compressed[4:8])[0]
if record_block_type == 0:
_record_block = record_block_compressed[8:]
# lzo compression
elif record_block_type == 1:
if lzo is None:
print("LZO compression is not supported")
# decompress
header = b'\xf0' + pack('>I', index['decompressed_size'])
_record_block = lzo.decompress(record_block_compressed[8:], initSize = decompressed_size, blockSize=1308672)
# zlib compression
elif record_block_type == 2:
# decompress
_record_block = zlib.decompress(record_block_compressed[8:])
data = _record_block[index['record_start'] - index['offset']:index['record_end'] - index['offset']]
return data
def get_mdx_by_index(self, fmdx, index):
data = self.get_data_by_index(fmdx,index)
record = data.decode(self._encoding, errors='ignore').strip(u'\x00').encode('utf-8')
if self._stylesheet:
record = self._replace_stylesheet(record)
record = record.decode('utf-8')
return record
def get_mdd_by_index(self, fmdx, index):
return self.get_data_by_index(fmdx,index)
@staticmethod
def lookup_indexes(db,keyword,ignorecase=None):
indexes = []
if ignorecase:
sql = 'SELECT * FROM MDX_INDEX WHERE lower(key_text) = lower("{}")'.format(keyword)
else:
sql = 'SELECT * FROM MDX_INDEX WHERE key_text = "{}"'.format(keyword)
with sqlite3.connect(db) as conn:
cursor = conn.execute(sql)
for result in cursor:
index = {}
index['file_pos'] = result[1]
index['compressed_size'] = result[2]
index['decompressed_size'] = result[3]
index['record_block_type'] = result[4]
index['record_start'] = result[5]
index['record_end'] = result[6]
index['offset'] = result[7]
indexes.append(index)
return indexes
def mdx_lookup(self, keyword,ignorecase=None):
lookup_result_list = []
indexes = self.lookup_indexes(self._mdx_db,keyword,ignorecase)
with open(self._mdx_file,'rb') as mdx_file:
for index in indexes:
lookup_result_list.append(self.get_mdx_by_index(mdx_file, index))
return lookup_result_list
def mdd_lookup(self, keyword,ignorecase=None):
lookup_result_list = []
indexes = self.lookup_indexes(self._mdd_db,keyword,ignorecase)
with open(self._mdd_file,'rb') as mdd_file:
for index in indexes:
lookup_result_list.append(self.get_mdd_by_index(mdd_file, index))
return lookup_result_list
@staticmethod
def get_keys(db,query = ''):
if not db:
return []
if query:
if '*' in query:
query = query.replace('*','%')
else:
query = query + '%'
sql = 'SELECT key_text FROM MDX_INDEX WHERE key_text LIKE \"' + query + '\"'
else:
sql = 'SELECT key_text FROM MDX_INDEX'
with sqlite3.connect(db) as conn:
cursor = conn.execute(sql)
keys = [item[0] for item in cursor]
return keys
def get_mdd_keys(self, query = ''):
return self.get_keys(self._mdd_db,query)
def get_mdx_keys(self, query = ''):
return self.get_keys(self._mdx_db,query)
if __name__ == '__main__':
mdx_builder = IndexBuilder("OALD7.mdx")
text = mdx_builder.mdx_lookup('xes')
print(text)
# keys = mdx_builder.get_mdx_keys()
# keys1 = mdx_builder.get_mdx_keys('abstrac')
# keys2 = mdx_builder.get_mdx_keys('*tion')
# for key in keys2:
# text = mdx_builder.mdx_lookup(key)[0]
# pass