-
Notifications
You must be signed in to change notification settings - Fork 2
/
mappings.py
249 lines (244 loc) · 6.83 KB
/
mappings.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
AUTHOR_MAP = {
'Tonya Dewey': 'Tonya Kim Dewey-Findell',
'Maria Reina Bastardas': 'Maria-Reina Bastardas',
'Ganesh Gupta': '',
'Henrik Liljegren': '',
'Simone Loi': '',
'Ulrich Geupel': '',
'Shervin Farridnejad': '',
'Adam Benkato': '',
'Mandar Purandare': '',
'Sam Mersch': '',
'Borana Lushaj': '',
'Asfar Ali Khan': '',
'Patrycja Markus': '',
'Nicholas Sims-Williams': '',
'Paul Videsott': '',
'Paul Versloot': '',
'Charalambos Christodoulou': '',
'Guto Rhys': '',
'Annemarie Verkerk': '',
'Mojtaba Gheitasi': '',
'Harald Hammarstr\xf6m': '',
'Giorgio Cadorini': '',
'Lo\xefc Cheveau': '',
'Arash Zeini': '',
'J\xe9r\xe9mie Delorme': '',
'Lars Steensland': '',
'Manuel Widmer': '',
'Stephen Dworkin': '',
'Esther Baiwir': '',
'Khawaja Rehman': '',
'Sabine Tittel': '',
'Heather Pagan': '',
}
"""
clade
id
cladeName
hexColor
shortName
export
exportDate
taxonsetName
atMost
atLeast
distribution
uniformUpper # always empty
uniformLower # always empty
cladeLevel0
cladeLevel1
cladeLevel2
cladeLevel3
level0Name
level1Name
level2Name
level3Name
languagelist
id
name
description
languageclade
id
cladesOrder
clade_id
language_id
romanisedsymbol
id
symbol
sndcomp
id
lgSetName
lv0
lv1
lv2
lv3
cladeLevel0
cladeLevel1
cladeLevel2
cladeLevel3
meaninglist
id
name
description
languagelistorder
id
language_id
language_list_id
order
"""
FIELD_MAP = {
'author':
{
"id": "ID",
"surname": "Last_Name",
"firstNames": "First_Name",
"email": "",
"website": "URL",
"initials": "initials",
"user_id": "",
},
'lexeme': # -> forms.csv
{
"id": "ID",
"language_id": "Language_ID",
"meaning_id": "Parameter_ID",
"romanised": "Form",
"phon_form": "phon_form",
"gloss": "Gloss",
"notes": "Comment",
"_order": "",
"dubious": "",
"not_swadesh_term": "not_swadesh_term",
"phoneMic": "Phonemic",
"rfcWebLookup1": "url",
"rfcWebLookup2": "", # all empty
"nativeScript": "native_script",
},
'language': # -> languages.csv
{
"id": "ID", # -> id
"iso_code": "ISO639P3code", # -> iso639P3code
"ascii_name": "ascii_name",
"utf8_name": "Name", # -> Name
"description": "Description",
"earliestTimeDepthBound": "",
"latestTimeDepthBound": "",
"progress": "",
"author": "Authors",
"foss_stat": "fossil",
"glottocode": "Glottocode", # -> glottocode
"level0": "level0",
"level1": "level1",
"level2": "level2",
"level3": "level3",
"low_stat": "", # always False
"representative": "representative",
"reviewer": "",
"rfcWebPath1": "url",
"rfcWebPath2": "", # all empty
"soundcompcode": "",
"variety": "Variety",
"sortRankInClade": "sortRankInClade",
"sndCompLevel0": "",
"sndCompLevel1": "",
"sndCompLevel2": "",
"sndCompLevel3": "",
"entryTimeframe": "",
"originalAsciiName": "",
"historical": "historical",
"notInExport": "notInExport",
"distribution": "distribution",
"logNormalMean": "logNormalMean",
"logNormalOffset": "logNormalOffset",
"logNormalStDev": "logNormalStDev",
"normalMean": "normalMean",
"normalStDev": "normalStDev",
"uniformLower": "",
"uniformUpper": "",
"latitude": "Latitude", # -> Latitude
"longitude": "Longitude", # -> Longitude
"exampleLanguage": "exampleLanguage",
"fragmentary": "",
"loc_justification": "loc_justification",
},
'meaning': # -> parameters.csv
{
"id": "ID",
"gloss": "Name",
"description": "", # always empty!
"notes": "", # always empty!
"percent_coded": "",
"doubleCheck": "",
"exclude": "",
"meaningSetIx": "",
"tooltip": "Description",
"meaningSetMember": "",
"exampleContext": "exampleContext",
"ixElicitation": "",
"concepticon_id": "Concepticon_ID",
},
'cognatejudgement': # -> cognates.csv
{
"id": "ID",
"lexeme_id": "Form_ID",
"cognate_class_id": "Cognateset_ID",
},
'cognateclass':
{
"id": "ID",
"root_form": "Root_Form",
"gloss_in_root_lang": "Root_Gloss",
"root_language": "Root_Language",
# alias
"notes": "Comment",
"justificationDiscussion": "Justification",
# name - always empty
"loan_notes": "loan_notes",
"loan_source": "loan_source", # pretty variable languoid names
"loanword": "loanword",
# loanEventTimeDepthBP
"loanSourceCognateClass_id": "loanSourceCognateClass_id",
"sourceFormInLoanLanguage": "sourceFormInLoanLanguage",
# should be put in forms.csv!? (only 509, though)
"parallelLoanEvent": "parallelLoanEvent",
# -> if True, split into individual borrowings!
# notProtoIndoEuropean
"dubiousSet": "dubiousSet",
"parallelDerivation": "parallelDerivation",
"revisedBy": "revised_by",
# revisedYet
"ideophonic": "Ideophonic",
"proposedAsCognateTo_id": "proposedAsCognateTo_pk",
"proposedAsCognateToScale": "proposedAsCognateToScale",
"supersetid": "supersetid",
},
'clade': # -> clades.csv
{
"id": "ID",
"cladeName": "clade_name",
"hexColor": "color",
"shortName": "short_name",
"taxonsetName": "taxonsetName",
"export": "export",
"atMost": "",
"atLeast": "",
"cladeLevel0": "clade_level0",
"cladeLevel1": "clade_level1",
"cladeLevel2": "clade_level2",
"cladeLevel3": "clade_level3",
"level0Name": "level0_name",
"level1Name": "level1_name",
"level2Name": "level2_name",
"level3Name": "level3_name"
}
}
"""
meaninglistorder
id
meaning_id
meaning_list_id
order
*citation
reliability A|B|C|X
"""