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
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
|
from __future__ import absolute_import, print_function, division
import operator
from petl.compat import text_type
from petl.errors import DuplicateKeyError
from petl.util.base import Table, asindices, asdict, Record, rowgetter
def _setup_lookup(table, key, value):
# obtain iterator and header row
it = iter(table)
try:
hdr = next(it)
except StopIteration:
hdr = []
# prepare key getter
keyindices = asindices(hdr, key)
assert len(keyindices) > 0, 'no key selected'
getkey = operator.itemgetter(*keyindices)
# prepare value getter
if value is None:
# default value is complete row
getvalue = rowgetter(*range(len(hdr)))
else:
valueindices = asindices(hdr, value)
assert len(valueindices) > 0, 'no value selected'
getvalue = operator.itemgetter(*valueindices)
return it, getkey, getvalue
def lookup(table, key, value=None, dictionary=None):
"""
Load a dictionary with data from the given table. E.g.::
>>> import petl as etl
>>> table1 = [['foo', 'bar'],
... ['a', 1],
... ['b', 2],
... ['b', 3]]
>>> lkp = etl.lookup(table1, 'foo', 'bar')
>>> lkp['a']
[1]
>>> lkp['b']
[2, 3]
>>> # if no value argument is given, defaults to the whole
... # row (as a tuple)
... lkp = etl.lookup(table1, 'foo')
>>> lkp['a']
[('a', 1)]
>>> lkp['b']
[('b', 2), ('b', 3)]
>>> # compound keys are supported
... table2 = [['foo', 'bar', 'baz'],
... ['a', 1, True],
... ['b', 2, False],
... ['b', 3, True],
... ['b', 3, False]]
>>> lkp = etl.lookup(table2, ('foo', 'bar'), 'baz')
>>> lkp[('a', 1)]
[True]
>>> lkp[('b', 2)]
[False]
>>> lkp[('b', 3)]
[True, False]
>>> # data can be loaded into an existing dictionary-like
... # object, including persistent dictionaries created via the
... # shelve module
... import shelve
>>> lkp = shelve.open('example1.dat', flag='n')
>>> lkp = etl.lookup(table1, 'foo', 'bar', lkp)
>>> lkp.close()
>>> lkp = shelve.open('example1.dat', flag='r')
>>> lkp['a']
[1]
>>> lkp['b']
[2, 3]
"""
if dictionary is None:
dictionary = dict()
# setup
it, getkey, getvalue = _setup_lookup(table, key, value)
# build lookup dictionary
for row in it:
k = getkey(row)
v = getvalue(row)
if k in dictionary:
# work properly with shelve
l = dictionary[k]
l.append(v)
dictionary[k] = l
else:
dictionary[k] = [v]
return dictionary
Table.lookup = lookup
def lookupone(table, key, value=None, dictionary=None, strict=False):
"""
Load a dictionary with data from the given table, assuming there is
at most one value for each key. E.g.::
>>> import petl as etl
>>> table1 = [['foo', 'bar'],
... ['a', 1],
... ['b', 2],
... ['b', 3]]
>>> # if the specified key is not unique and strict=False (default),
... # the first value wins
... lkp = etl.lookupone(table1, 'foo', 'bar')
>>> lkp['a']
1
>>> lkp['b']
2
>>> # if the specified key is not unique and strict=True, will raise
... # DuplicateKeyError
... try:
... lkp = etl.lookupone(table1, 'foo', strict=True)
... except etl.errors.DuplicateKeyError as e:
... print(e)
...
duplicate key: 'b'
>>> # compound keys are supported
... table2 = [['foo', 'bar', 'baz'],
... ['a', 1, True],
... ['b', 2, False],
... ['b', 3, True],
... ['b', 3, False]]
>>> lkp = etl.lookupone(table2, ('foo', 'bar'), 'baz')
>>> lkp[('a', 1)]
True
>>> lkp[('b', 2)]
False
>>> lkp[('b', 3)]
True
>>> # data can be loaded into an existing dictionary-like
... # object, including persistent dictionaries created via the
... # shelve module
... import shelve
>>> lkp = shelve.open('example2.dat', flag='n')
>>> lkp = etl.lookupone(table1, 'foo', 'bar', lkp)
>>> lkp.close()
>>> lkp = shelve.open('example2.dat', flag='r')
>>> lkp['a']
1
>>> lkp['b']
2
"""
if dictionary is None:
dictionary = dict()
# setup
it, getkey, getvalue = _setup_lookup(table, key, value)
# build lookup dictionary
for row in it:
k = getkey(row)
if strict and k in dictionary:
raise DuplicateKeyError(k)
elif k not in dictionary:
v = getvalue(row)
dictionary[k] = v
return dictionary
Table.lookupone = lookupone
def dictlookup(table, key, dictionary=None):
"""
Load a dictionary with data from the given table, mapping to dicts. E.g.::
>>> import petl as etl
>>> table1 = [['foo', 'bar'],
... ['a', 1],
... ['b', 2],
... ['b', 3]]
>>> lkp = etl.dictlookup(table1, 'foo')
>>> lkp['a']
[{'foo': 'a', 'bar': 1}]
>>> lkp['b']
[{'foo': 'b', 'bar': 2}, {'foo': 'b', 'bar': 3}]
>>> # compound keys are supported
... table2 = [['foo', 'bar', 'baz'],
... ['a', 1, True],
... ['b', 2, False],
... ['b', 3, True],
... ['b', 3, False]]
>>> lkp = etl.dictlookup(table2, ('foo', 'bar'))
>>> lkp[('a', 1)]
[{'foo': 'a', 'bar': 1, 'baz': True}]
>>> lkp[('b', 2)]
[{'foo': 'b', 'bar': 2, 'baz': False}]
>>> lkp[('b', 3)]
[{'foo': 'b', 'bar': 3, 'baz': True}, {'foo': 'b', 'bar': 3, 'baz': False}]
>>> # data can be loaded into an existing dictionary-like
... # object, including persistent dictionaries created via the
... # shelve module
... import shelve
>>> lok = shelve.open('example3.dat', flag='n')
>>> lok = etl.dictlookup(table1, 'foo', lok)
>>> lok.close()
>>> lup = shelve.open('example3.dat', flag='r')
>>> lup['a']
[{'foo': 'a', 'bar': 1}]
>>> lup['b']
[{'foo': 'b', 'bar': 2}, {'foo': 'b', 'bar': 3}]
"""
if dictionary is None:
dictionary = dict()
it = iter(table)
try:
hdr = next(it)
except StopIteration:
hdr = []
flds = list(map(text_type, hdr))
keyindices = asindices(hdr, key)
assert len(keyindices) > 0, 'no key selected'
getkey = operator.itemgetter(*keyindices)
for row in it:
k = getkey(row)
rec = asdict(flds, row)
if k in dictionary:
# work properly with shelve
l = dictionary[k]
l.append(rec)
dictionary[k] = l
else:
dictionary[k] = [rec]
return dictionary
Table.dictlookup = dictlookup
def dictlookupone(table, key, dictionary=None, strict=False):
"""
Load a dictionary with data from the given table, mapping to dicts,
assuming there is at most one row for each key. E.g.::
>>> import petl as etl
>>> table1 = [['foo', 'bar'],
... ['a', 1],
... ['b', 2],
... ['b', 3]]
>>> # if the specified key is not unique and strict=False (default),
... # the first value wins
... lkp = etl.dictlookupone(table1, 'foo')
>>> lkp['a']
{'foo': 'a', 'bar': 1}
>>> lkp['b']
{'foo': 'b', 'bar': 2}
>>> # if the specified key is not unique and strict=True, will raise
... # DuplicateKeyError
... try:
... lkp = etl.dictlookupone(table1, 'foo', strict=True)
... except etl.errors.DuplicateKeyError as e:
... print(e)
...
duplicate key: 'b'
>>> # compound keys are supported
... table2 = [['foo', 'bar', 'baz'],
... ['a', 1, True],
... ['b', 2, False],
... ['b', 3, True],
... ['b', 3, False]]
>>> lkp = etl.dictlookupone(table2, ('foo', 'bar'))
>>> lkp[('a', 1)]
{'foo': 'a', 'bar': 1, 'baz': True}
>>> lkp[('b', 2)]
{'foo': 'b', 'bar': 2, 'baz': False}
>>> lkp[('b', 3)]
{'foo': 'b', 'bar': 3, 'baz': True}
>>> # data can be loaded into an existing dictionary-like
... # object, including persistent dictionaries created via the
... # shelve module
... import shelve
>>> lkp = shelve.open('example4.dat', flag='n')
>>> lkp = etl.dictlookupone(table1, 'foo', lkp)
>>> lkp.close()
>>> lkp = shelve.open('example4.dat', flag='r')
>>> lkp['a']
{'foo': 'a', 'bar': 1}
>>> lkp['b']
{'foo': 'b', 'bar': 2}
"""
if dictionary is None:
dictionary = dict()
it = iter(table)
try:
hdr = next(it)
except StopIteration:
hdr = []
flds = list(map(text_type, hdr))
keyindices = asindices(hdr, key)
assert len(keyindices) > 0, 'no key selected'
getkey = operator.itemgetter(*keyindices)
for row in it:
k = getkey(row)
if strict and k in dictionary:
raise DuplicateKeyError(k)
elif k not in dictionary:
d = asdict(flds, row)
dictionary[k] = d
return dictionary
Table.dictlookupone = dictlookupone
def recordlookup(table, key, dictionary=None):
"""
Load a dictionary with data from the given table, mapping to record objects.
"""
if dictionary is None:
dictionary = dict()
it = iter(table)
try:
hdr = next(it)
except StopIteration:
hdr = []
flds = list(map(text_type, hdr))
keyindices = asindices(hdr, key)
assert len(keyindices) > 0, 'no key selected'
getkey = operator.itemgetter(*keyindices)
for row in it:
k = getkey(row)
rec = Record(row, flds)
if k in dictionary:
# work properly with shelve
l = dictionary[k]
l.append(rec)
dictionary[k] = l
else:
dictionary[k] = [rec]
return dictionary
Table.recordlookup = recordlookup
def recordlookupone(table, key, dictionary=None, strict=False):
"""
Load a dictionary with data from the given table, mapping to record objects,
assuming there is at most one row for each key.
"""
if dictionary is None:
dictionary = dict()
it = iter(table)
try:
hdr = next(it)
except StopIteration:
hdr = []
flds = list(map(text_type, hdr))
keyindices = asindices(hdr, key)
assert len(keyindices) > 0, 'no key selected'
getkey = operator.itemgetter(*keyindices)
for row in it:
k = getkey(row)
if strict and k in dictionary:
raise DuplicateKeyError(k)
elif k not in dictionary:
d = Record(row, flds)
dictionary[k] = d
return dictionary
Table.recordlookupone = recordlookupone
|
