pennmarc 0.0.1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (59) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +6 -0
  3. data/.rspec +2 -0
  4. data/.ruby-version +1 -0
  5. data/Gemfile +23 -0
  6. data/Gemfile.lock +119 -0
  7. data/README.md +82 -0
  8. data/legacy/indexer.rb +568 -0
  9. data/legacy/marc.rb +2964 -0
  10. data/legacy/test_file_output.json +49 -0
  11. data/lib/pennmarc/encoding_level.rb +43 -0
  12. data/lib/pennmarc/enriched_marc.rb +36 -0
  13. data/lib/pennmarc/heading_control.rb +11 -0
  14. data/lib/pennmarc/helpers/citation.rb +31 -0
  15. data/lib/pennmarc/helpers/creator.rb +237 -0
  16. data/lib/pennmarc/helpers/database.rb +89 -0
  17. data/lib/pennmarc/helpers/date.rb +85 -0
  18. data/lib/pennmarc/helpers/edition.rb +90 -0
  19. data/lib/pennmarc/helpers/format.rb +312 -0
  20. data/lib/pennmarc/helpers/genre.rb +71 -0
  21. data/lib/pennmarc/helpers/helper.rb +11 -0
  22. data/lib/pennmarc/helpers/identifier.rb +134 -0
  23. data/lib/pennmarc/helpers/language.rb +37 -0
  24. data/lib/pennmarc/helpers/link.rb +12 -0
  25. data/lib/pennmarc/helpers/location.rb +97 -0
  26. data/lib/pennmarc/helpers/note.rb +132 -0
  27. data/lib/pennmarc/helpers/production.rb +131 -0
  28. data/lib/pennmarc/helpers/relation.rb +135 -0
  29. data/lib/pennmarc/helpers/series.rb +118 -0
  30. data/lib/pennmarc/helpers/subject.rb +304 -0
  31. data/lib/pennmarc/helpers/title.rb +197 -0
  32. data/lib/pennmarc/mappings/language.yml +516 -0
  33. data/lib/pennmarc/mappings/locations.yml +1801 -0
  34. data/lib/pennmarc/mappings/relator.yml +263 -0
  35. data/lib/pennmarc/parser.rb +177 -0
  36. data/lib/pennmarc/util.rb +240 -0
  37. data/lib/pennmarc.rb +6 -0
  38. data/pennmarc.gemspec +22 -0
  39. data/spec/fixtures/marcxml/test.xml +167 -0
  40. data/spec/lib/pennmarc/helpers/citation_spec.rb +27 -0
  41. data/spec/lib/pennmarc/helpers/creator_spec.rb +183 -0
  42. data/spec/lib/pennmarc/helpers/database_spec.rb +60 -0
  43. data/spec/lib/pennmarc/helpers/date_spec.rb +105 -0
  44. data/spec/lib/pennmarc/helpers/edition_spec.rb +38 -0
  45. data/spec/lib/pennmarc/helpers/format_spec.rb +200 -0
  46. data/spec/lib/pennmarc/helpers/genre_spec.rb +89 -0
  47. data/spec/lib/pennmarc/helpers/identifer_spec.rb +105 -0
  48. data/spec/lib/pennmarc/helpers/language_spec.rb +30 -0
  49. data/spec/lib/pennmarc/helpers/location_spec.rb +70 -0
  50. data/spec/lib/pennmarc/helpers/note_spec.rb +233 -0
  51. data/spec/lib/pennmarc/helpers/production_spec.rb +193 -0
  52. data/spec/lib/pennmarc/helpers/relation_spec.rb +120 -0
  53. data/spec/lib/pennmarc/helpers/subject_spec.rb +262 -0
  54. data/spec/lib/pennmarc/helpers/title_spec.rb +169 -0
  55. data/spec/lib/pennmarc/marc_util_spec.rb +206 -0
  56. data/spec/lib/pennmarc/parser_spec.rb +13 -0
  57. data/spec/spec_helper.rb +104 -0
  58. data/spec/support/marc_spec_helpers.rb +84 -0
  59. metadata +171 -0
@@ -0,0 +1,516 @@
1
+ aar: Afar
2
+ abk: Abkhaz
3
+ ace: Achinese
4
+ ach: Acoli
5
+ ada: Adangme
6
+ ady: Adygei
7
+ afa: Afroasiatic (Other)
8
+ afh: Afrihili (Artificial language)
9
+ afr: Afrikaans
10
+ ain: Ainu
11
+ ajm: Aljamía
12
+ aka: Akan
13
+ akk: Akkadian
14
+ alb: Albanian
15
+ ale: Aleut
16
+ alg: Algonquian (Other)
17
+ alt: Altai
18
+ amh: Amharic
19
+ ang: English, Old (ca. 450-1100)
20
+ anp: Angika
21
+ apa: Apache languages
22
+ ara: Arabic
23
+ arc: Aramaic
24
+ arg: Aragonese
25
+ arm: Armenian
26
+ arn: Mapuche
27
+ arp: Arapaho
28
+ art: Artificial (Other)
29
+ arw: Arawak
30
+ asm: Assamese
31
+ ast: Bable
32
+ ath: Athapascan (Other)
33
+ aus: Australian languages
34
+ ava: Avaric
35
+ ave: Avestan
36
+ awa: Awadhi
37
+ aym: Aymara
38
+ aze: Azerbaijani
39
+ bad: Banda languages
40
+ bai: Bamileke languages
41
+ bak: Bashkir
42
+ bal: Baluchi
43
+ bam: Bambara
44
+ ban: Balinese
45
+ baq: Basque
46
+ bas: Basa
47
+ bat: Baltic (Other)
48
+ bej: Beja
49
+ bel: Belarusian
50
+ bem: Bemba
51
+ ben: Bengali
52
+ ber: Berber (Other)
53
+ bho: Bhojpuri
54
+ bih: Bihari (Other)
55
+ bik: Bikol
56
+ bin: Edo
57
+ bis: Bislama
58
+ bla: Siksika
59
+ bnt: Bantu (Other)
60
+ bos: Bosnian
61
+ bra: Braj
62
+ bre: Breton
63
+ btk: Batak
64
+ bua: Buriat
65
+ bug: Bugis
66
+ bul: Bulgarian
67
+ bur: Burmese
68
+ byn: Bilin
69
+ cad: Caddo
70
+ cai: Central American Indian (Other)
71
+ cam: Khmer
72
+ car: Carib
73
+ cat: Catalan
74
+ cau: Caucasian (Other)
75
+ ceb: Cebuano
76
+ cel: Celtic (Other)
77
+ cha: Chamorro
78
+ chb: Chibcha
79
+ che: Chechen
80
+ chg: Chagatai
81
+ chi: Chinese
82
+ chk: Chuukese
83
+ chm: Mari
84
+ chn: Chinook jargon
85
+ cho: Choctaw
86
+ chp: Chipewyan
87
+ chr: Cherokee
88
+ chu: Church Slavic
89
+ chv: Chuvash
90
+ chy: Cheyenne
91
+ cmc: Chamic languages
92
+ cop: Coptic
93
+ cor: Cornish
94
+ cos: Corsican
95
+ cpe: Creoles and Pidgins, English-based (Other)
96
+ cpf: Creoles and Pidgins, French-based (Other)
97
+ cpp: Creoles and Pidgins, Portuguese-based (Other)
98
+ cre: Cree
99
+ crh: Crimean Tatar
100
+ crp: Creoles and Pidgins (Other)
101
+ csb: Kashubian
102
+ cus: Cushitic (Other)
103
+ cze: Czech
104
+ dak: Dakota
105
+ dan: Danish
106
+ dar: Dargwa
107
+ day: Dayak
108
+ del: Delaware
109
+ den: Slavey
110
+ dgr: Dogrib
111
+ din: Dinka
112
+ div: Divehi
113
+ doi: Dogri
114
+ dra: Dravidian (Other)
115
+ dsb: Lower Sorbian
116
+ dua: Duala
117
+ dum: Dutch, Middle (ca. 1050-1350)
118
+ dut: Dutch
119
+ dyu: Dyula
120
+ dzo: Dzongkha
121
+ efi: Efik
122
+ egy: Egyptian
123
+ eka: Ekajuk
124
+ elx: Elamite
125
+ eng: English
126
+ enm: English, Middle (1100-1500)
127
+ epo: Esperanto
128
+ esk: Eskimo languages
129
+ esp: Esperanto
130
+ est: Estonian
131
+ eth: Ethiopic
132
+ ewe: Ewe
133
+ ewo: Ewondo
134
+ fan: Fang
135
+ fao: Faroese
136
+ far: Faroese
137
+ fat: Fanti
138
+ fij: Fijian
139
+ fil: Filipino
140
+ fin: Finnish
141
+ fiu: Finno-Ugrian (Other)
142
+ fon: Fon
143
+ fre: French
144
+ fri: Frisian
145
+ frm: French, Middle (ca. 1300-1600)
146
+ fro: French, Old (ca. 842-1300)
147
+ frr: North Frisian
148
+ frs: East Frisian
149
+ fry: Frisian
150
+ ful: Fula
151
+ fur: Friulian
152
+ gaa: Gã
153
+ gae: Scottish Gaelix
154
+ gag: Galician
155
+ gal: Oromo
156
+ gay: Gayo
157
+ gba: Gbaya
158
+ gem: Germanic (Other)
159
+ geo: Georgian
160
+ ger: German
161
+ gez: Ethiopic
162
+ gil: Gilbertese
163
+ gla: Scottish Gaelic
164
+ gle: Irish
165
+ glg: Galician
166
+ glv: Manx
167
+ gmh: German, Middle High (ca. 1050-1500)
168
+ goh: German, Old High (ca. 750-1050)
169
+ gon: Gondi
170
+ gor: Gorontalo
171
+ got: Gothic
172
+ grb: Grebo
173
+ grc: Greek, Ancient (to 1453)
174
+ gre: Greek, Modern (1453-)
175
+ grn: Guarani
176
+ gsw: Swiss German
177
+ gua: Guarani
178
+ guj: Gujarati
179
+ gwi: Gwich'in
180
+ hai: Haida
181
+ hat: Haitian French Creole
182
+ hau: Hausa
183
+ haw: Hawaiian
184
+ heb: Hebrew
185
+ her: Herero
186
+ hil: Hiligaynon
187
+ him: Western Pahari languages
188
+ hin: Hindi
189
+ hit: Hittite
190
+ hmn: Hmong
191
+ hmo: Hiri Motu
192
+ hrv: Croatian
193
+ hsb: Upper Sorbian
194
+ hun: Hungarian
195
+ hup: Hupa
196
+ iba: Iban
197
+ ibo: Igbo
198
+ ice: Icelandic
199
+ ido: Ido
200
+ iii: Sichuan Yi
201
+ ijo: Ijo
202
+ iku: Inuktitut
203
+ ile: Interlingue
204
+ ilo: Iloko
205
+ ina: Interlingua (International Auxiliary Language Association)
206
+ inc: Indic (Other)
207
+ ind: Indonesian
208
+ ine: Indo-European (Other)
209
+ inh: Ingush
210
+ int: Interlingua (International Auxiliary Language Association)
211
+ ipk: Inupiaq
212
+ ira: Iranian (Other)
213
+ iri: Irish
214
+ iro: Iroquoian (Other)
215
+ ita: Italian
216
+ jav: Javanese
217
+ jbo: Lojban (Artificial language)
218
+ jpn: Japanese
219
+ jpr: Judeo-Persian
220
+ jrb: Judeo-Arabic
221
+ kaa: Kara-Kalpak
222
+ kab: Kabyle
223
+ kac: Kachin
224
+ kal: Kalâtdlisut
225
+ kam: Kamba
226
+ kan: Kannada
227
+ kar: Karen languages
228
+ kas: Kashmiri
229
+ kau: Kanuri
230
+ kaw: Kawi
231
+ kaz: Kazakh
232
+ kbd: Kabardian
233
+ kha: Khasi
234
+ khi: Khoisan (Other)
235
+ khm: Khmer
236
+ kho: Khotanese
237
+ kik: Kikuyu
238
+ kin: Kinyarwanda
239
+ kir: Kyrgyz
240
+ kmb: Kimbundu
241
+ kok: Konkani
242
+ kom: Komi
243
+ kon: Kongo
244
+ kor: Korean
245
+ kos: Kosraean
246
+ kpe: Kpelle
247
+ krc: Karachay-Balkar
248
+ krl: Karelian
249
+ kro: Kru (Other)
250
+ kru: Kurukh
251
+ kua: Kuanyama
252
+ kum: Kumyk
253
+ kur: Kurdish
254
+ kus: Kusaie
255
+ kut: Kootenai
256
+ lad: Ladino
257
+ lah: Lahndā
258
+ lam: Lamba (Zambia and Congo)
259
+ lan: Occitan (post 1500)
260
+ lao: Lao
261
+ lap: Sami
262
+ lat: Latin
263
+ lav: Latvian
264
+ lez: Lezgian
265
+ lim: Limburgish
266
+ lin: Lingala
267
+ lit: Lithuanian
268
+ lol: Mongo-Nkundu
269
+ loz: Lozi
270
+ ltz: Luxembourgish
271
+ lua: Luba-Lulua
272
+ lub: Luba-Katanga
273
+ lug: Ganda
274
+ lui: Luiseño
275
+ lun: Lunda
276
+ luo: Luo (Kenya and Tanzania)
277
+ lus: Lushai
278
+ mac: Macedonian
279
+ mad: Madurese
280
+ mag: Magahi
281
+ mah: Marshallese
282
+ mai: Maithili
283
+ mak: Makasar
284
+ mal: Malayalam
285
+ man: Mandingo
286
+ mao: Maori
287
+ map: Austronesian (Other)
288
+ mar: Marathi
289
+ mas: Maasai
290
+ max: Manx
291
+ may: Malay
292
+ mdf: Moksha
293
+ mdr: Mandar
294
+ men: Mende
295
+ mga: Irish, Middle (ca. 1100-1550)
296
+ mic: Micmac
297
+ min: Minangkabau
298
+ mis: Miscellaneous languages
299
+ mkh: Mon-Khmer (Other)
300
+ mla: Malagasy
301
+ mlg: Malagasy
302
+ mlt: Maltese
303
+ mnc: Manchu
304
+ mni: Manipuri
305
+ mno: Manobo languages
306
+ moh: Mohawk
307
+ mol: Moldavian
308
+ mon: Mongolian
309
+ mos: Mooré
310
+ mul: Multiple languages
311
+ mun: Munda (Other)
312
+ mus: Creek
313
+ mwl: Mirandese
314
+ mwr: Marwari
315
+ myn: Mayan languages
316
+ myv: Erzya
317
+ nah: Nahuatl
318
+ nai: North American Indian (Other)
319
+ nap: Neapolitan Italian
320
+ nau: Nauru
321
+ nav: Navajo
322
+ nbl: Ndebele (South Africa)
323
+ nde: Ndebele (Zimbabwe)
324
+ ndo: Ndonga
325
+ nds: Low German
326
+ nep: Nepali
327
+ new: Newari
328
+ nia: Nias
329
+ nic: Niger-Kordofanian (Other)
330
+ niu: Niuean
331
+ nno: Norwegian (Nynorsk)
332
+ nob: Norwegian (Bokmål)
333
+ nog: Nogai
334
+ non: Old Norse
335
+ nor: Norwegian
336
+ nqo: N'Ko
337
+ nso: Northern Sotho
338
+ nub: Nubian languages
339
+ nwc: Newari, Old
340
+ nya: Nyanja
341
+ nym: Nyamwezi
342
+ nyn: Nyankole
343
+ nyo: Nyoro
344
+ nzi: Nzima
345
+ oci: Occitan (post-1500)
346
+ oji: Ojibwa
347
+ ori: Oriya
348
+ orm: Oromo
349
+ osa: Osage
350
+ oss: Ossetic
351
+ ota: Turkish, Ottoman
352
+ oto: Otomian languages
353
+ paa: Papuan (Other)
354
+ pag: Pangasinan
355
+ pal: Pahlavi
356
+ pam: Pampanga
357
+ pan: Panjabi
358
+ pap: Papiamento
359
+ pau: Palauan
360
+ peo: Old Persian (ca. 600-400 B.C.)
361
+ per: Persian
362
+ phi: Philippine (Other)
363
+ phn: Phoenician
364
+ pli: Pali
365
+ pol: Polish
366
+ pon: Pohnpeian
367
+ por: Portuguese
368
+ pra: Prakrit languages
369
+ pro: Provençal (to 1500)
370
+ pus: Pushto
371
+ que: Quechua
372
+ raj: Rajasthani
373
+ rap: Rapanui
374
+ rar: Rarotongan
375
+ roa: Romance (Other)
376
+ roh: Raeto-Romance
377
+ rom: Romani
378
+ rum: Romanian
379
+ run: Rundi
380
+ rup: Aromanian
381
+ rus: Russian
382
+ sad: Sandawe
383
+ sag: Sango (Ubangi Creole)
384
+ sah: Yakut
385
+ sai: South American Indian (Other)
386
+ sal: Salishan languages
387
+ sam: Samaritan Aramaic
388
+ san: Sanskrit
389
+ sao: Samoan
390
+ sas: Sasak
391
+ sat: Santali
392
+ scc: Serbian
393
+ scn: Sicilian Italian
394
+ sco: Scots
395
+ scr: Croatian
396
+ sel: Selkup
397
+ sem: Semitic (Other)
398
+ sga: Irish, Old (to 1100)
399
+ sgn: Sign languages
400
+ shn: Shan
401
+ sho: Shona
402
+ sid: Sidamo
403
+ sin: Sinhalese
404
+ sio: Siouan (Other)
405
+ sit: Sino-Tibetan (Other)
406
+ sla: Slavic (Other)
407
+ slo: Slovak
408
+ slv: Slovenian
409
+ sma: Southern Sami
410
+ sme: Northern Sami
411
+ smi: Sami
412
+ smj: Lule Sami
413
+ smn: Inari Sami
414
+ smo: Samoan
415
+ sms: Skolt Sami
416
+ sna: Shona
417
+ snd: Sindhi
418
+ snh: Sinhalese
419
+ snk: Soninke
420
+ sog: Sogdian
421
+ som: Somali
422
+ son: Songhai
423
+ sot: Sotho
424
+ spa: Spanish
425
+ srd: Sardinian
426
+ srn: Sranan
427
+ srp: Serbian
428
+ srr: Serer
429
+ ssa: Nilo-Saharan (Other)
430
+ sso: Sotho
431
+ ssw: Swazi
432
+ suk: Sukuma
433
+ sun: Sundanese
434
+ sus: Susu
435
+ sux: Sumerian
436
+ swa: Swahili
437
+ swe: Swedish
438
+ swz: Swazi
439
+ syc: Syriac
440
+ syr: Syriac, Modern
441
+ tag: Tagalog
442
+ tah: Tahitian
443
+ tai: Tai (Other)
444
+ taj: Tajik
445
+ tam: Tamil
446
+ tar: Tatar
447
+ tat: Tatar
448
+ tel: Telugu
449
+ tem: Temne
450
+ ter: Terena
451
+ tet: Tetum
452
+ tgk: Tajik
453
+ tgl: Tagalog
454
+ tha: Thai
455
+ tib: Tibetan
456
+ tig: Tigré
457
+ tir: Tigrinya
458
+ tiv: Tiv
459
+ tkl: Tokelauan
460
+ tlh: Klingon (Artificial language)
461
+ tli: Tlingit
462
+ tmh: Tamashek
463
+ tog: Tonga (Nyasa)
464
+ ton: Tongan
465
+ tpi: Tok Pisin
466
+ tru: Truk
467
+ tsi: Tsimshian
468
+ tsn: Tswana
469
+ tso: Tsonga
470
+ tsw: Tswana
471
+ tuk: Turkmen
472
+ tum: Tumbuka
473
+ tup: Tupi languages
474
+ tur: Turkish
475
+ tut: Altaic (Other)
476
+ tvl: Tuvaluan
477
+ twi: Twi
478
+ tyv: Tuvinian
479
+ udm: Udmurt
480
+ uga: Ugaritic
481
+ uig: Uighur
482
+ ukr: Ukrainian
483
+ umb: Umbundu
484
+ und: Undetermined
485
+ urd: Urdu
486
+ uzb: Uzbek
487
+ vai: Vai
488
+ ven: Venda
489
+ vie: Vietnamese
490
+ vol: Volapük
491
+ vot: Votic
492
+ wak: Wakashan languages
493
+ wal: Wolayta
494
+ war: Waray
495
+ was: Washoe
496
+ wel: Welsh
497
+ wen: Sorbian (Other)
498
+ wln: Walloon
499
+ wol: Wolof
500
+ xal: Oirat
501
+ xho: Xhosa
502
+ yao: Yao (Africa)
503
+ yap: Yapese
504
+ yid: Yiddish
505
+ yor: Yoruba
506
+ ypk: Yupik languages
507
+ zap: Zapotec
508
+ zbl: Blissymbolics
509
+ zen: Zenaga
510
+ zha: Zhuang
511
+ znd: Zande languages
512
+ zul: Zulu
513
+ zun: Zuni
514
+ zxx: No linguistic content
515
+ zza: Zaza
516
+ ___: No linguistic content provided