annotate importFromOpenMind/importer/filterISMI.py @ 2:e55656794c82

create and use separate export directory.
author root@ismi.rz-berlin.mpg.de
date Tue, 02 Jun 2015 11:09:16 +0200
parents 124ef8f3b22d
children 0ae6145e7c80
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
1 '''
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
2 Created on 22.04.2014
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
3
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
4 @author: dwinter
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
5 '''
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
6
2
e55656794c82 create and use separate export directory.
root@ismi.rz-berlin.mpg.de
parents: 0
diff changeset
7 import os
0
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
8 import json
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
9 import urllib.request
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
10
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
11 class Importer:
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
12
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
13 def loadJSON(self,url):
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
14
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
15
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
16 response = urllib.request.urlopen(url)
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
17 str_response = response.readall().decode('utf-8')
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
18
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
19 self.data = json.loads(str_response)
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
20
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
21
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
22 def loadJSONFromFile(self,fn):
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
23
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
24
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
25 self.data = json.load(open(fn+".json",'r', encoding="utf-8"),encoding="utf-8")
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
26
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
27
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
28 def getEntIdsMentioned(self,kind="tar",filterOC=[]):
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
29 """ holt alle Id entweder als src_id """
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
30
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
31 ents = self.data.get("ents")
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
32
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
33
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
34
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
35 ret=set()
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
36 rels=[]
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
37 if kind=="tar":
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
38 rel_type="tar_rels"
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
39 id_type="src_id"
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
40 oc_type="src_oc"
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
41 else:
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
42 rel_type="src_rels"
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
43 id_type="tar_id"
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
44 oc_type="tar_oc"
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
45
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
46 for ent in ents:
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
47 tar_rels = ent.get(rel_type)
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
48
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
49
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
50
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
51 for tar_rel in tar_rels:
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
52
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
53
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
54 if not tar_rel.get(oc_type) in filterOC:
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
55
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
56
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
57 ret.add(str(tar_rel.get(id_type)))
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
58
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
59
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
60 rels.append(tar_rel)
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
61
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
62
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
63
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
64 return ret,rels
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
65
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
66
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
67 def loadallEnts(self,kind="tar",filterOC=[]):
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
68
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
69 ids,rels = self.getEntIdsMentioned(kind=kind,filterOC=filterOC)
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
70
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
71
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
72 baseUrl="http://openmind-ismi-dev.mpiwg-berlin.mpg.de/om4-ismi/jsonInterface?include_content=true&include_romanization=true&method=get_ents"
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
73
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
74 lenId = len(ids)
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
75
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
76 portions = int(lenId / 500)
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
77
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
78 ents = []
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
79 for p in range(portions+1):
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
80
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
81
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
82 start = p * 500
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
83 end = min(lenId,(p+1)*500)
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
84
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
85 idsFrak = list(ids)[start:end]
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
86 idsString = ",".join(idsFrak)
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
87
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
88
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
89 qs = baseUrl+"&ids="+idsString
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
90 print (qs)
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
91 response = urllib.request.urlopen(qs)
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
92 entsJ = json.loads(response.readall().decode('utf-8'));
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
93 ents += entsJ.get("ents")
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
94 #str_response += response.readall().decode('utf-8')
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
95
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
96
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
97 str_response = json.dumps({"ents":ents});
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
98 return str_response,rels
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
99
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
100 def saveallEnts(self,filename,kind="tar",filterOC=[]):
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
101
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
102 ents,rels = self.loadallEnts(kind=kind,filterOC=filterOC)
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
103 of = open(filename+".json","wb")
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
104 of.write(ents.encode('utf-8'))
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
105 of.close()
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
106
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
107 of = open(filename+"_rels.json","w")
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
108 json.dump({'rels':rels},of);
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
109 of.close()
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
110
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
111
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
112
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
113 if __name__ == '__main__':
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
114 imp = Importer()
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
115
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
116 # url = """http://openmind-ismi-dev.mpiwg-berlin.mpg.de/om4-ismi/jsonInterface?method=get_ents&ids=27543,36745,58453,87298,259646,35093,22863,34870,36882,101488,36696,31794,37240,35014,35583,37025,35960,172492,98286,165721,260111,90980,36316,260120,36241,260129,260138,38860,176694,72545,36185,36575,260146,31672,37739,89861,176778,180743,86328,260150,90658,58423,181058,105948,35526,74078,260158,181096,31606,31568,27872,36938,4836,34668,76866,102230,76888,74070,73757,182685,260162,260170,1102,172888,260174,34806,28088,36713,37323,34551,35943,98095,260178,260182,182770,260186,260190,260194,36114,85003,31630,157290,37153,37213,172952,86871,64406,102590,82615,58245,179791,179550,12419,95861,36429,36099,74237,36065,74822,87549,83765,36733,19259,260198,34986,88041,260202,36550,260206,37228,39880,36318,36597,35035,58328,80831,58354,74277,36529,36380,69450,200246,260222,81178,260226,199952,262557,87212,99059,64270,81811,65785,36645
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
117 # """
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
118 #
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
119
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
120 url = """http://openmind-ismi-dev.mpiwg-berlin.mpg.de/om4-ismi/jsonInterface?method=get_public_codices"""
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
121
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
122
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
123 imp.loadJSON(url)
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
124
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
125 #ids= imp.getEntIdsMentioned()
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
126
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
127
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
128 #loadall = imp.loadallEnts()
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
129 #print(loadall.encode('utf-8'))
2
e55656794c82 create and use separate export directory.
root@ismi.rz-berlin.mpg.de
parents: 0
diff changeset
130
e55656794c82 create and use separate export directory.
root@ismi.rz-berlin.mpg.de
parents: 0
diff changeset
131 exportDir = '/tmp/ismi_data'
e55656794c82 create and use separate export directory.
root@ismi.rz-berlin.mpg.de
parents: 0
diff changeset
132 if not os.access(exportDir, os.R_OK):
e55656794c82 create and use separate export directory.
root@ismi.rz-berlin.mpg.de
parents: 0
diff changeset
133 # dir doesn't exist -> create
e55656794c82 create and use separate export directory.
root@ismi.rz-berlin.mpg.de
parents: 0
diff changeset
134 os.makedirs(exportDir)
0
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
135
2
e55656794c82 create and use separate export directory.
root@ismi.rz-berlin.mpg.de
parents: 0
diff changeset
136 imp.saveallEnts(exportDir+"/witnesses",kind="tar")
0
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
137
2
e55656794c82 create and use separate export directory.
root@ismi.rz-berlin.mpg.de
parents: 0
diff changeset
138 imp.saveallEnts(exportDir+"/codex_src",kind="src",filterOC=['CODEX','WITNESS'])
0
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
139
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
140 #hole jetzt alle relationen an den witnessen
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
141
2
e55656794c82 create and use separate export directory.
root@ismi.rz-berlin.mpg.de
parents: 0
diff changeset
142 imp.loadJSONFromFile(exportDir+"/witnesses")
0
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
143
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
144 #ids= imp.getEntIdsMentioned(kind="src")
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
145
2
e55656794c82 create and use separate export directory.
root@ismi.rz-berlin.mpg.de
parents: 0
diff changeset
146 imp.saveallEnts(exportDir+"/texts",kind="src",filterOC=['CODEX','WITNESS','PERSON'])
0
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
147
2
e55656794c82 create and use separate export directory.
root@ismi.rz-berlin.mpg.de
parents: 0
diff changeset
148 imp.loadJSONFromFile(exportDir+"/texts")
0
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
149
2
e55656794c82 create and use separate export directory.
root@ismi.rz-berlin.mpg.de
parents: 0
diff changeset
150 imp.saveallEnts(exportDir+"/authors_subjects_src",kind="src",filterOC=['CODEX','WITNESS','TEXT'])
0
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
151
2
e55656794c82 create and use separate export directory.
root@ismi.rz-berlin.mpg.de
parents: 0
diff changeset
152 imp.saveallEnts(exportDir+"/authors_subjects_tar",kind="tar",filterOC=['CODEX','WITNESS','TEXT'])
0
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
153
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
154
2
e55656794c82 create and use separate export directory.
root@ismi.rz-berlin.mpg.de
parents: 0
diff changeset
155 imp.loadJSONFromFile(exportDir+"/authors_subjects_src")
0
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
156
2
e55656794c82 create and use separate export directory.
root@ismi.rz-berlin.mpg.de
parents: 0
diff changeset
157 imp.saveallEnts(exportDir+"/subjects_places",kind="src",filterOC=['CODEX','WITNESS','TEXT','PERSON'])
e55656794c82 create and use separate export directory.
root@ismi.rz-berlin.mpg.de
parents: 0
diff changeset
158 imp.saveallEnts(exportDir+"/references_places",kind="tar",filterOC=['CODEX','WITNESS','TEXT','PERSON'])
0
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
159
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
160
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
161
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
162
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
163
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
164
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
165
124ef8f3b22d initial
Dirk Wintergruen <dwinter@mpiwg-berlin.mpg.de>
parents:
diff changeset
166