imw 0.2.7 → 0.2.8

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (93) hide show
  1. data/Gemfile +23 -0
  2. data/Gemfile.lock +47 -0
  3. data/LICENSE +20 -674
  4. data/README.rdoc +3 -4
  5. data/VERSION +1 -1
  6. data/lib/imw.rb +64 -35
  7. data/lib/imw/dataset.rb +12 -2
  8. data/lib/imw/formats.rb +4 -2
  9. data/lib/imw/formats/delimited.rb +96 -36
  10. data/lib/imw/formats/excel.rb +69 -101
  11. data/lib/imw/formats/json.rb +3 -5
  12. data/lib/imw/formats/pdf.rb +71 -0
  13. data/lib/imw/formats/yaml.rb +3 -5
  14. data/lib/imw/metadata.rb +66 -0
  15. data/lib/imw/metadata/contains_metadata.rb +44 -0
  16. data/lib/imw/metadata/dsl.rb +111 -0
  17. data/lib/imw/metadata/field.rb +65 -0
  18. data/lib/imw/metadata/schema.rb +227 -0
  19. data/lib/imw/metadata/schematized.rb +27 -0
  20. data/lib/imw/parsers.rb +1 -0
  21. data/lib/imw/parsers/flat.rb +44 -0
  22. data/lib/imw/resource.rb +36 -224
  23. data/lib/imw/schemes.rb +3 -1
  24. data/lib/imw/schemes/hdfs.rb +12 -1
  25. data/lib/imw/schemes/http.rb +1 -2
  26. data/lib/imw/schemes/local.rb +139 -16
  27. data/lib/imw/schemes/remote.rb +14 -9
  28. data/lib/imw/schemes/s3.rb +12 -0
  29. data/lib/imw/schemes/sql.rb +117 -0
  30. data/lib/imw/tools.rb +5 -3
  31. data/lib/imw/tools/downloader.rb +63 -0
  32. data/lib/imw/tools/summarizer.rb +21 -10
  33. data/lib/imw/utils.rb +10 -0
  34. data/lib/imw/utils/dynamically_extendable.rb +137 -0
  35. data/lib/imw/utils/error.rb +3 -0
  36. data/lib/imw/utils/extensions.rb +0 -4
  37. data/lib/imw/utils/extensions/array.rb +6 -7
  38. data/lib/imw/utils/extensions/hash.rb +3 -5
  39. data/lib/imw/utils/extensions/string.rb +3 -3
  40. data/lib/imw/utils/has_uri.rb +114 -0
  41. data/spec/data/{sample.csv → formats/delimited/sample.csv} +1 -1
  42. data/spec/data/{sample.tsv → formats/delimited/sample.tsv} +0 -0
  43. data/spec/data/formats/delimited/with_schema/ace-hardware-locations.tsv +11 -0
  44. data/spec/data/formats/delimited/with_schema/all-countries-ip-address-to-geolocation-data.tsv +16 -0
  45. data/spec/data/formats/delimited/with_schema/complete-list-of-starbucks-locations.tsv +11 -0
  46. data/spec/data/formats/delimited/with_schema/myspace-user-activity-stream-cumulative-word-count-from-from-dec.tsv +22 -0
  47. data/spec/data/formats/delimited/with_schema/myspace-user-activity-stream-myspace-application-adds-by-zip-cod.tsv +22 -0
  48. data/spec/data/formats/delimited/with_schema/myspace-user-activity-stream-myspace-application-counts.tsv +12 -0
  49. data/spec/data/formats/delimited/with_schema/myspace-user-activity-stream-user-count-by-latlong.tsv +13 -0
  50. data/spec/data/formats/delimited/with_schema/myspace-user-activity-stream-user-count-by-zip-code.tsv +22 -0
  51. data/spec/data/formats/delimited/with_schema/myspace-user-activity-stream-word-count-by-day-from-december-200.tsv +22 -0
  52. data/spec/data/formats/delimited/without_schema/ace-hardware-locations.tsv +10 -0
  53. data/spec/data/formats/delimited/without_schema/all-countries-ip-address-to-geolocation-data.tsv +15 -0
  54. data/spec/data/formats/delimited/without_schema/complete-list-of-starbucks-locations.tsv +10 -0
  55. data/spec/data/formats/delimited/without_schema/myspace-user-activity-stream-cumulative-word-count-from-from-dec.tsv +21 -0
  56. data/spec/data/formats/delimited/without_schema/myspace-user-activity-stream-myspace-application-adds-by-zip-cod.tsv +21 -0
  57. data/spec/data/formats/delimited/without_schema/myspace-user-activity-stream-myspace-application-counts.tsv +11 -0
  58. data/spec/data/formats/delimited/without_schema/myspace-user-activity-stream-user-count-by-latlong.tsv +12 -0
  59. data/spec/data/formats/delimited/without_schema/myspace-user-activity-stream-user-count-by-zip-code.tsv +21 -0
  60. data/spec/data/formats/delimited/without_schema/myspace-user-activity-stream-word-count-by-day-from-december-200.tsv +21 -0
  61. data/spec/data/formats/excel/sample.xls +0 -0
  62. data/spec/data/formats/json/sample.json +1 -0
  63. data/spec/data/formats/none/sample +650 -0
  64. data/spec/data/formats/sgml/sample.xml +617 -0
  65. data/spec/data/formats/text/sample.txt +650 -0
  66. data/spec/data/formats/yaml/sample.yaml +410 -0
  67. data/spec/data/schema-tabular.yaml +11 -0
  68. data/spec/imw/formats/delimited_spec.rb +34 -2
  69. data/spec/imw/formats/excel_spec.rb +55 -0
  70. data/spec/imw/formats/json_spec.rb +3 -3
  71. data/spec/imw/formats/sgml_spec.rb +4 -4
  72. data/spec/imw/formats/yaml_spec.rb +3 -3
  73. data/spec/imw/metadata/field_spec.rb +26 -0
  74. data/spec/imw/metadata/schema_spec.rb +27 -0
  75. data/spec/imw/metadata_spec.rb +39 -0
  76. data/spec/imw/parsers/line_parser_spec.rb +1 -1
  77. data/spec/imw/resource_spec.rb +0 -100
  78. data/spec/imw/schemes/hdfs_spec.rb +19 -13
  79. data/spec/imw/schemes/local_spec.rb +59 -3
  80. data/spec/imw/schemes/s3_spec.rb +4 -0
  81. data/spec/imw/utils/dynamically_extendable_spec.rb +69 -0
  82. data/spec/imw/utils/has_uri_spec.rb +55 -0
  83. data/spec/spec_helper.rb +1 -2
  84. data/spec/support/random.rb +4 -4
  85. metadata +58 -17
  86. data/CHANGELOG +0 -0
  87. data/TODO +0 -18
  88. data/spec/data/sample.json +0 -782
  89. data/spec/data/sample.txt +0 -131
  90. data/spec/data/sample.xml +0 -653
  91. data/spec/data/sample.yaml +0 -651
  92. data/spec/spec.opts +0 -4
  93. data/spec/support/extensions.rb +0 -18
@@ -1,651 +0,0 @@
1
- ---
2
-
3
- - id: 001
4
- name: Gray-bellied Night Monkey
5
- genus: Aotus
6
- species: lemurinus
7
-
8
- - id: 002
9
- name: Panamanian Night Monkey
10
- genus: Aotus
11
- species: zonalis
12
-
13
- - id: 003
14
- name: Hernández-Camacho's Night Monkey
15
- genus: Aotus
16
- species: jorgehernandezi
17
-
18
- - id: 004
19
- name: Gray-handed Night Monkey
20
- genus: Aotus
21
- species: griseimembra
22
-
23
- - id: 005
24
- name: Hershkovitz's Night Monkey
25
- genus: Aotus
26
- species: hershkovitzi
27
-
28
- - id: 006
29
- name: Brumback's Night Monkey
30
- genus: Aotus
31
- species: brumbacki
32
-
33
- - id: 007
34
- name: Three-striped Night Monkey
35
- genus: Aotus
36
- species: trivirgatus
37
-
38
- - id: 008
39
- name: Spix's Night Monkey
40
- genus: Aotus
41
- species: vociferans
42
-
43
- - id: 009
44
- name: Malaysian Lar Gibbon
45
- genus: Hylobates
46
- species: lar lar
47
-
48
- - id: 010
49
- name: Carpenter's Lar Gibbon
50
- genus: Hylobates
51
- species: lar carpenteri
52
-
53
- - id: 011
54
- name: Central Lar Gibbon
55
- genus: Hylobates
56
- species: lar entelloides
57
-
58
- - id: 012
59
- name: Sumatran Lar Gibbon
60
- genus: Hylobates
61
- species: lar vestitus
62
-
63
- - id: 013
64
- name: Yunnan Lar Gibbon
65
- genus: Hylobates
66
- species: lar yunnanensis
67
-
68
- - id: 014
69
- name: Mountain Agile Gibbon
70
- genus: Hylobates
71
- species: agilis agilis
72
-
73
- - id: 015
74
- name: Bornean White-bearded Gibbon
75
- genus: Hylobates
76
- species: agilis albibarbis
77
-
78
- - id: 016
79
- name: Lowland Agile Gibbon
80
- genus: Hylobates
81
- species: agilis unko
82
-
83
- - id: 017
84
- name: Müller's Gray Gibbon
85
- genus: Hylobates
86
- species: muelleri muelleri
87
-
88
- - id: 018
89
- name: Abbott's Gray Gibbon
90
- genus: Hylobates
91
- species: muelleri abbotti
92
-
93
- - id: 019
94
- name: Northern Gray Gibbon
95
- genus: Hylobates
96
- species: muelleri funereus
97
-
98
- - id: 020
99
- name: Black Tamarin
100
- genus: Saguinas
101
- species: niger
102
-
103
- - id: 021
104
- name: Black-mantled Tamarin
105
- genus: Saguinas
106
- species: nigricollis
107
-
108
- - id: 022
109
- name: Brown-mantled Tamarin
110
- genus: Saguinas
111
- species: fuscicollis
112
-
113
- - id: 023
114
- name: Cottontop Tamarin or Pinché Tamarin
115
- genus: Saguinas
116
- species: oedipus
117
-
118
- - id: 024
119
- name: Emperor Tamarin
120
- genus: Saguinas
121
- species: imperator
122
-
123
- - id: 025
124
- name: Geoffroy's Tamarin
125
- genus: Saguinas
126
- species: geoffroyi
127
-
128
- - id: 026
129
- name: Golden-mantled Tamarin
130
- genus: Saguinas
131
- species: tripartitus
132
-
133
- - id: 027
134
- name: Graells's Tamarin
135
- genus: Saguinas
136
- species: graellsi
137
-
138
- - id: 028
139
- name: Martins's Tamarin
140
- genus: Saguinas
141
- species: martinsi
142
-
143
- - id: 029
144
- name: Mottle-faced Tamarin
145
- genus: Saguinas
146
- species: inustus
147
-
148
- - id: 030
149
- name: Moustached Tamarin
150
- genus: Saguinas
151
- species: mystax
152
-
153
- - id: 031
154
- name: Pied Tamarin
155
- genus: Saguinas
156
- species: bicolor
157
-
158
- - id: 032
159
- name: Red-capped Tamarin
160
- genus: Saguinas
161
- species: pileatus
162
-
163
- - id: 033
164
- name: Red-handed Tamarin
165
- genus: Saguinas
166
- species: midas
167
-
168
- - id: 034
169
- name: White-footed Tamarin
170
- genus: Saguinas
171
- species: leucopus
172
-
173
- - id: 035
174
- name: White-lipped Tamarin
175
- genus: Saguinas
176
- species: labiatus
177
-
178
- - id: 036
179
- name: White-mantled Tamarin
180
- genus: Saguinas
181
- species: melanoleucus
182
-
183
- - id: 037
184
- name: Allen's Swamp Monkey
185
- genus: Allenopithecus
186
- species: nigroviridis
187
-
188
- - id: 038
189
- name: Angolan Talapoin
190
- genus: Miopithecus
191
- species: talapoin
192
-
193
- - id: 039
194
- name: Gabon Talapoin
195
- genus: Miopithecus
196
- species: ogouensis
197
-
198
- - id: 040
199
- name: Patas Monkey
200
- genus: Erythrocebus
201
- species: patas
202
-
203
- - id: 041
204
- name: Green Monkey
205
- genus: Chlorocebus
206
- species: sabaeus
207
-
208
- - id: 042
209
- name: Grivet
210
- genus: Chlorocebus
211
- species: aethiops
212
-
213
- - id: 043
214
- name: Bale Mountains Vervet
215
- genus: Chlorocebus
216
- species: djamdjamensis
217
-
218
- - id: 044
219
- name: Tantalus Monkey
220
- genus: Chlorocebus
221
- species: tantalus
222
-
223
- - id: 045
224
- name: Vervet Monkey
225
- genus: Chlorocebus
226
- species: pygerythrus
227
-
228
- - id: 046
229
- name: Malbrouck
230
- genus: Chlorocebus
231
- species: cynosuros
232
-
233
- - id: 047
234
- name: Dryas Monkey or Salongo Monkey
235
- genus: Cercopithecus
236
- species: dryas
237
-
238
- - id: 048
239
- name: Diana Monkey
240
- genus: Cercopithecus
241
- species: diana
242
-
243
- - id: 049
244
- name: Roloway Monkey
245
- genus: Cercopithecus
246
- species: roloway
247
-
248
- - id: 050
249
- name: Greater Spot-nosed Monkey
250
- genus: Cercopithecus
251
- species: nictitans
252
-
253
- - id: 051
254
- name: Blue Monkey
255
- genus: Cercopithecus
256
- species: mitis
257
-
258
- - id: 052
259
- name: Silver Monkey
260
- genus: Cercopithecus
261
- species: doggetti
262
-
263
- - id: 053
264
- name: Golden Monkey
265
- genus: Cercopithecus
266
- species: kandti
267
-
268
- - id: 054
269
- name: Sykes's Monkey
270
- genus: Cercopithecus
271
- species: albogularis
272
-
273
- - id: 055
274
- name: Mona Monkey
275
- genus: Cercopithecus
276
- species: mona
277
-
278
- - id: 056
279
- name: Campbell's Mona Monkey
280
- genus: Cercopithecus
281
- species: campbelli
282
-
283
- - id: 057
284
- name: Lowe's Mona Monkey
285
- genus: Cercopithecus
286
- species: lowei
287
-
288
- - id: 058
289
- name: Crested Mona Monkey
290
- genus: Cercopithecus
291
- species: pogonias
292
-
293
- - id: 059
294
- name: Wolf's Mona Monkey
295
- genus: Cercopithecus
296
- species: wolfi
297
-
298
- - id: 060
299
- name: Dent's Mona Monkey
300
- genus: Cercopithecus
301
- species: denti
302
-
303
- - id: 061
304
- name: Lesser Spot-nosed Monkey
305
- genus: Cercopithecus
306
- species: petaurista
307
-
308
- - id: 062
309
- name: White-throated Guenon
310
- genus: Cercopithecus
311
- species: erythrogaster
312
-
313
- - id: 063
314
- name: Sclater's Guenon
315
- genus: Cercopithecus
316
- species: sclateri
317
-
318
- - id: 064
319
- name: Red-eared Guenon
320
- genus: Cercopithecus
321
- species: erythrotis
322
-
323
- - id: 065
324
- name: Moustached Guenon
325
- genus: Cercopithecus
326
- species: cephus
327
-
328
- - id: 066
329
- name: Red-tailed Monkey
330
- genus: Cercopithecus
331
- species: ascanius
332
-
333
- - id: 067
334
- name: L'Hoest's Monkey
335
- genus: Cercopithecus
336
- species: lhoesti
337
-
338
- - id: 068
339
- name: Preuss's Monkey
340
- genus: Cercopithecus
341
- species: preussi
342
-
343
- - id: 069
344
- name: Sun-tailed Monkey
345
- genus: Cercopithecus
346
- species: solatus
347
-
348
- - id: 070
349
- name: Hamlyn's Monkey
350
- genus: Cercopithecus
351
- species: hamlyni
352
-
353
- - id: 071
354
- name: De Brazza's Monkey
355
- genus: Cercopithecus
356
- species: neglectus
357
-
358
- - id: 072
359
- name: Barbary Macaque
360
- genus: Macaca
361
- species: sylvanus
362
-
363
- - id: 073
364
- name: Lion-tailed Macaque
365
- genus: Macaca
366
- species: silenus
367
-
368
- - id: 074
369
- name: Southern Pig-tailed Macaque or Beruk
370
- genus: Macaca
371
- species: nemestrina
372
-
373
- - id: 075
374
- name: Northern Pig-tailed Macaque
375
- genus: Macaca
376
- species: leonina
377
-
378
- - id: 076
379
- name: Pagai Island Macaque or Bokkoi
380
- genus: Macaca
381
- species: pagensis
382
-
383
- - id: 077
384
- name: Siberut Macaque
385
- genus: Macaca
386
- species: siberu
387
-
388
- - id: 078
389
- name: Moor Macaque
390
- genus: Macaca
391
- species: maura
392
-
393
- - id: 079
394
- name: Booted Macaque
395
- genus: Macaca
396
- species: ochreata
397
-
398
- - id: 080
399
- name: Tonkean Macaque
400
- genus: Macaca
401
- species: tonkeana
402
-
403
- - id: 081
404
- name: Heck's Macaque
405
- genus: Macaca
406
- species: hecki
407
-
408
- - id: 082
409
- name: Gorontalo Macaque
410
- genus: Macaca
411
- species: nigrescens
412
-
413
- - id: 083
414
- name: Celebes Crested Macaque or Black Ape
415
- genus: Macaca
416
- species: nigra
417
-
418
- - id: 084
419
- name: Crab-eating Macaque or Long-tailed Macaque or Kera
420
- genus: Macaca
421
- species: fascicularis
422
-
423
- - id: 085
424
- name: Stump-tailed Macaque or Bear Macaque
425
- genus: Macaca
426
- species: arctoides
427
-
428
- - id: 086
429
- name: Rhesus Macaque
430
- genus: Macaca
431
- species: mulatta
432
-
433
- - id: 087
434
- name: Formosan Rock Macaque
435
- genus: Macaca
436
- species: cyclopis
437
-
438
- - id: 088
439
- name: Japanese Macaque
440
- genus: Macaca
441
- species: fuscata
442
-
443
- - id: 089
444
- name: Toque Macaque
445
- genus: Macaca
446
- species: sinica
447
-
448
- - id: 090
449
- name: Bonnet Macaque
450
- genus: Macaca
451
- species: radiata
452
-
453
- - id: 091
454
- name: Assam Macaque
455
- genus: Macaca
456
- species: assamensis
457
-
458
- - id: 092
459
- name: Tibetan Macaque or Milne-Edwards' Macaque
460
- genus: Macaca
461
- species: thibetana
462
-
463
- - id: 093
464
- name: Arunachal Macaque or Munzala
465
- genus: Macaca
466
- species: munzala
467
-
468
- - id: 094
469
- name: Grey-cheeked Mangabey
470
- genus: Lophocebus
471
- species: albigena
472
-
473
- - id: 095
474
- name: Black Crested Mangabey
475
- genus: Lophocebus
476
- species: aterrimus
477
-
478
- - id: 096
479
- name: Opdenbosch's Mangabey
480
- genus: Lophocebus
481
- species: opdenboschi
482
-
483
- - id: 097
484
- name: Uganda Mangabey
485
- genus: Lophocebus
486
- species: ugandae
487
-
488
- - id: 098
489
- name: Johnston's Mangabey
490
- genus: Lophocebus
491
- species: johnstoni
492
-
493
- - id: 099
494
- name: Osman Hill's Mangabey
495
- genus: Lophocebus
496
- species: osmani
497
-
498
- - id: 100
499
- name: Kipunji
500
- genus: Rungwecebus
501
- species: kipunji
502
-
503
- - id: 101
504
- name: Hamadryas Baboon
505
- genus: Papio
506
- species: hamadryas
507
-
508
- - id: 102
509
- name: Guinea Baboon
510
- genus: Papio
511
- species: papio
512
-
513
- - id: 103
514
- name: Olive Baboon
515
- genus: Papio
516
- species: anubis
517
-
518
- - id: 104
519
- name: Yellow Baboon
520
- genus: Papio
521
- species: cynocephalus
522
-
523
- - id: 105
524
- name: Chacma Baboon
525
- genus: Papio
526
- species: ursinus
527
-
528
- - id: 106
529
- name: Gelada
530
- genus: Theropithecus
531
- species: gelada
532
-
533
- - id: 107
534
- name: Sooty Mangabey
535
- genus: Cercocebus
536
- species: atys
537
-
538
- - id: 108
539
- name: Collared Mangabey
540
- genus: Cercocebus
541
- species: torquatus
542
-
543
- - id: 109
544
- name: Agile Mangabey
545
- genus: Cercocebus
546
- species: agilis
547
-
548
- - id: 110
549
- name: Golden-bellied Mangabey
550
- genus: Cercocebus
551
- species: chrysogaster
552
-
553
- - id: 111
554
- name: Tana River Mangabey
555
- genus: Cercocebus
556
- species: galeritus
557
-
558
- - id: 112
559
- name: Sanje Mangabey
560
- genus: Cercocebus
561
- species: sanjei
562
-
563
- - id: 113
564
- name: Mandrill
565
- genus: Mandrillus
566
- species: sphinx
567
-
568
- - id: 114
569
- name: Drill
570
- genus: Mandrillus
571
- species: leucophaeus
572
-
573
- - id: 115
574
- name: Black Colobus
575
- genus: Colobus
576
- species: satanas
577
-
578
- - id: 116
579
- name: Angola Colobus
580
- genus: Colobus
581
- species: angolensis
582
-
583
- - id: 117
584
- name: King Colobus
585
- genus: Colobus
586
- species: polykomos
587
-
588
- - id: 118
589
- name: Ursine Colobus
590
- genus: Colobus
591
- species: vellerosus
592
-
593
- - id: 119
594
- name: Mantled Guereza
595
- genus: Colobus
596
- species: guereza
597
-
598
- - id: 120
599
- name: Western Red Colobus
600
- genus: Piliocolobus
601
- species: badius
602
-
603
- - id: 121
604
- name: Pennant's Colobus
605
- genus: Piliocolobus
606
- species: pennantii
607
-
608
- - id: 122
609
- name: Preuss's Red Colobus
610
- genus: Piliocolobus
611
- species: preussi
612
-
613
- - id: 123
614
- name: Thollon's Red Colobus
615
- genus: Piliocolobus
616
- species: tholloni
617
-
618
- - id: 124
619
- name: Central African Red Colobus
620
- genus: Piliocolobus
621
- species: foai
622
-
623
- - id: 125
624
- name: Ugandan Red Colobus
625
- genus: Piliocolobus
626
- species: tephrosceles
627
-
628
- - id: 126
629
- name: Uzungwa Red Colobus
630
- genus: Piliocolobus
631
- species: gordonorum
632
-
633
- - id: 127
634
- name: Zanzibar Red Colobus
635
- genus: Piliocolobus
636
- species: kirkii
637
-
638
- - id: 128
639
- name: Tana River Red Colobus
640
- genus: Piliocolobus
641
- species: rufomitratus
642
-
643
- - id: 129
644
- name: Olive Colobus
645
- genus: Procolobus
646
- species: verus
647
-
648
- - id: 130
649
- name: Maroon Leaf Monkey
650
- genus: Presbytis
651
- species: rubicunda