Skip to content

Commit 3c1fe1e

Browse files
Update 030-match-ds-to-wikidata-entities.json
1 parent 736e87b commit 3c1fe1e

1 file changed

Lines changed: 108 additions & 15 deletions

File tree

‎instructions/wikidata-upload/030-match-ds-to-wikidata-entities.json‎

Lines changed: 108 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -101,6 +101,34 @@
101101
"maxColumns": 0,
102102
"description": "Split column placeWikidata by separator"
103103
},
104+
{
105+
"op": "core/column-addition",
106+
"engineConfig": {
107+
"facets": [],
108+
"mode": "row-based"
109+
},
110+
"baseColumnName": "scriptNotes",
111+
"expression": "grel:cell.cross(\"scripts ds aat wikidata csv\",\"script_note_as_recorded\").cells[\"wikidata_qid\"].value[0]",
112+
"onError": "set-to-blank",
113+
"newColumnName": "scriptWikidata",
114+
"columnInsertIndex": 14,
115+
"description": "Create column scriptWikidata at index 14 based on column scriptNotes using expression grel:cell.cross(\"scripts ds aat wikidata csv\",\"script_note_as_recorded\").cells[\"wikidata_qid\"].value[0]"
116+
},
117+
{
118+
"op": "core/column-split",
119+
"engineConfig": {
120+
"facets": [],
121+
"mode": "row-based"
122+
},
123+
"columnName": "scriptWikidata",
124+
"guessCellType": true,
125+
"removeOriginalColumn": true,
126+
"mode": "separator",
127+
"separator": "|",
128+
"regex": false,
129+
"maxColumns": 0,
130+
"description": "Split column scriptWikidata by separator"
131+
},
104132
{
105133
"op": "core/multivalued-cell-split",
106134
"columnName": "centuryDS",
@@ -269,31 +297,96 @@
269297
"description": "Remove column 2millennium"
270298
},
271299
{
272-
"op": "core/column-addition",
300+
"op": "core/multivalued-cell-split",
301+
"columnName": "centuryWikidata",
302+
"keyColumnName": "signature",
303+
"mode": "separator",
304+
"separator": "|",
305+
"regex": false,
306+
"description": "Split multi-valued cells in column centuryWikidata"
307+
},
308+
{
309+
"op": "core/recon-use-values-as-identifiers",
273310
"engineConfig": {
274311
"facets": [],
275312
"mode": "row-based"
276313
},
277-
"baseColumnName": "scriptNotes",
278-
"expression": "grel:cell.cross(\"scripts ds aat wikidata csv\",\"script_note_as_recorded\").cells[\"wikidata_qid\"].value[0]",
279-
"onError": "set-to-blank",
280-
"newColumnName": "scriptWikidata",
281-
"columnInsertIndex": 14,
282-
"description": "Create column scriptWikidata at index 14 based on column scriptNotes using expression grel:cell.cross(\"scripts ds aat wikidata csv\",\"script_note_as_recorded\").cells[\"wikidata_qid\"].value[0]"
314+
"columnName": "centuryWikidata",
315+
"service": "https://wikidata.reconci.link/en/api",
316+
"identifierSpace": "http://www.wikidata.org/entity/",
317+
"schemaSpace": "http://www.wikidata.org/prop/direct/",
318+
"description": "Use values as reconciliation identifiers in column centuryWikidata"
283319
},
284320
{
285-
"op": "core/column-split",
321+
"op": "core/extend-reconciled-data",
286322
"engineConfig": {
287323
"facets": [],
288324
"mode": "row-based"
289325
},
290-
"columnName": "scriptWikidata",
291-
"guessCellType": true,
292-
"removeOriginalColumn": true,
293-
"mode": "separator",
326+
"baseColumnName": "centuryWikidata",
327+
"endpoint": "https://wikidata.reconci.link/en/api",
328+
"identifierSpace": "http://www.wikidata.org/entity/",
329+
"schemaSpace": "http://www.wikidata.org/prop/direct/",
330+
"extension": {
331+
"properties": [
332+
{
333+
"id": "Len",
334+
"name": "SPARQL: Len"
335+
}
336+
]
337+
},
338+
"columnInsertIndex": 8,
339+
"description": "Extend data at index 8 based on column centuryWikidata"
340+
},
341+
{
342+
"op": "core/text-transform",
343+
"engineConfig": {
344+
"facets": [],
345+
"mode": "row-based"
346+
},
347+
"columnName": "Len",
348+
"expression": "grel:value.replace(\"th \",\"\").replace(\"st \",\"\").replace(\"nd \",\"\")",
349+
"onError": "keep-original",
350+
"repeat": false,
351+
"repeatCount": 10,
352+
"description": "Text transform on cells in column Len using expression grel:value.replace(\"th \",\"\").replace(\"st \",\"\").replace(\"nd \",\"\")"
353+
},
354+
{
355+
"op": "core/text-transform",
356+
"engineConfig": {
357+
"facets": [],
358+
"mode": "row-based"
359+
},
360+
"columnName": "Len",
361+
"expression": "grel:value.replace(\"century\",\"00C\").replace(\"millennium\",\"000M\")",
362+
"onError": "keep-original",
363+
"repeat": false,
364+
"repeatCount": 10,
365+
"description": "Text transform on cells in column Len using expression grel:value.replace(\"century\",\"00C\").replace(\"millennium\",\"000M\")"
366+
},
367+
{
368+
"op": "core/column-rename",
369+
"oldColumnName": "Len",
370+
"newColumnName": "century",
371+
"description": "Rename column Len to century"
372+
},
373+
{
374+
"op": "core/multivalued-cell-join",
375+
"columnName": "centuryWikidata",
376+
"keyColumnName": "signature",
294377
"separator": "|",
295-
"regex": false,
296-
"maxColumns": 0,
297-
"description": "Split column scriptWikidata by separator"
378+
"description": "Join multi-valued cells in column centuryWikidata"
379+
},
380+
{
381+
"op": "core/multivalued-cell-join",
382+
"columnName": "century",
383+
"keyColumnName": "signature",
384+
"separator": "|",
385+
"description": "Join multi-valued cells in column century"
386+
},
387+
{
388+
"op": "core/column-removal",
389+
"columnName": "centuryWikidata",
390+
"description": "Remove column centuryWikidata"
298391
}
299392
]

0 commit comments

Comments
 (0)