opencultureconsulting
/
ba-sachsen-pica
mirror of https://github.com/opencultureconsulting/ba-sachsen-pica
2
0
Fork 0
Code Issues Releases Wiki Activity
ba-sachsen-pica/tasks/02-bibliotheca-main.sh

1967 lines
47 KiB
Bash
Raw Normal View History

Refactoring mit task runner
2020-08-01 02:04:39 +02:00
#!/bin/bash
Initial commit
2020-07-13 12:42:14 +02:00
# Bibliotheca Hauptverarbeitung
# - Datenbereinigungen
Export in PICA+ ausgelagert
2020-07-22 11:00:38 +02:00
# - Mapping auf PICA3
Refactoring mit task runner
2020-08-01 02:04:39 +02:00
# - PICA3 als CSV (via Template) exportieren
Initial commit
2020-07-13 12:42:14 +02:00
Refactoring mit task runner
2020-08-01 02:04:39 +02:00
# =============================== ENVIRONMENT ================================ #
Initial commit
2020-07-13 12:42:14 +02:00
Refactoring mit task runner
2020-08-01 02:04:39 +02:00
# source the main script
source "${BASH_SOURCE%/*}/../bash-refine.sh" || exit 1
# read input
if [[ $1 ]]; then
inputdir="$(readlink -e "$1")"
else
echo 1>&2 "Please provide path to directory with input file(s)"; exit 1
fi
Initial commit
2020-07-13 12:42:14 +02:00
Refactoring mit task runner
2020-08-01 02:04:39 +02:00
# check requirements, set trap, create workdir and tee to logfile
init
Initial commit
2020-07-13 12:42:14 +02:00
# ================================= STARTUP ================================== #
Refactoring mit task runner
2020-08-01 02:04:39 +02:00
checkpoint "Startup"; echo
# start OpenRefine server
Initial commit
2020-07-13 12:42:14 +02:00
refine_start; echo
# ================================== IMPORT ================================== #
Refactoring mit task runner
2020-08-01 02:04:39 +02:00
checkpoint "Import"; echo
Initial commit
2020-07-13 12:42:14 +02:00
Refactoring mit task runner
2020-08-01 02:04:39 +02:00
# TSV-Exporte aller Einzelprojekte in ein Zip-Archiv packen
zip -j "${workdir}/bibliotheca.zip" "${inputdir}"/*.tsv
projects["bibliotheca"]="${workdir}/bibliotheca.zip"
# Neues Projekt erstellen aus Zip-Archiv
Initial commit
2020-07-13 12:42:14 +02:00
p="bibliotheca"
echo "import file" "${projects[$p]}" "..."
if curl -fs --write-out "%{redirect_url}\n" \
--form project-file="@${projects[$p]}" \
--form project-name="${p}" \
--form format="text/line-based/*sv" \
--form options='{
"encoding": "UTF-8",
"includeFileSources": "true",
"separator": "\t"
}' \
"${endpoint}/command/core/create-project-from-upload$(refine_csrf)" \
Refactoring mit task runner
2020-08-01 02:04:39 +02:00
> "${workdir}/${p}.id"
Initial commit
2020-07-13 12:42:14 +02:00
then
log "imported ${projects[$p]} as ${p}"
else
error "import of ${projects[$p]} failed!"
fi
Refactoring mit task runner
2020-08-01 02:04:39 +02:00
refine_store "${p}" "${workdir}/${p}.id" || error "import of ${p} failed!"
Initial commit
2020-07-13 12:42:14 +02:00
echo
# ================================ TRANSFORM ================================= #
Refactoring mit task runner
2020-08-01 02:04:39 +02:00
checkpoint "Transform"; echo
Nummerierung im Quellcode entfernt um Neusortierung zu erleichtern und Diffs aussagekräftiger zu machen
2020-08-13 15:25:31 +02:00
# ----------------------------- Spalten sortieren ---------------------------- #
Initial commit
2020-07-13 12:42:14 +02:00
# damit Records-Mode erhalten bleibt
Schönheitskorrekturen
2020-07-22 18:11:54 +02:00
echo "Spalten sortieren: Beginnen mit 1. M|MEDNR, 2. E|EXNR, 3. File..."
Initial commit
2020-07-13 12:42:14 +02:00
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/column-move",
"columnName": "File",
Korrektur spec_Z_03 und neu spec_B_E16
2020-10-20 17:53:08 +02:00
"index": 0
Zwischenformat PICA3
2020-07-21 23:09:58 +02:00
},
{
"op": "core/column-move",
"columnName": "E|EXNR",
Korrektur spec_Z_03 und neu spec_B_E16
2020-10-20 17:53:08 +02:00
"index": 0
Zwischenformat PICA3
2020-07-21 23:09:58 +02:00
},
{
"op": "core/column-move",
"columnName": "M|MEDNR",
Korrektur spec_Z_03 und neu spec_B_E16
2020-10-20 17:53:08 +02:00
"index": 0
Initial commit
2020-07-13 12:42:14 +02:00
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
Nummerierung im Quellcode entfernt um Neusortierung zu erleichtern und Diffs aussagekräftiger zu machen
2020-08-13 15:25:31 +02:00
# ------------------------- E-Books löschen (Bautzen) ------------------------ #
Initial commit
2020-07-13 12:42:14 +02:00
Spezifikationscodes ergänzt
2020-07-13 13:41:34 +02:00
# spec_Z_01
Initial commit
2020-07-13 12:42:14 +02:00
# - M|MEDGR > Facet > Text facet > eBook
# -- show as: records
# --- All > Edit rows > Remove all matching rows
echo "E-Books löschen (Bautzen)..."
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/row-removal",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "M|MEDGR",
"expression": "value",
"columnName": "M|MEDGR",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "eBook",
"l": "eBook"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "record-based"
}
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
Nummerierung im Quellcode entfernt um Neusortierung zu erleichtern und Diffs aussagekräftiger zu machen
2020-08-13 15:25:31 +02:00
# --------------- Zeitschriften löschen (Breitenbrunn, Dresden) -------------- #
Initial commit
2020-07-13 12:42:14 +02:00
Spezifikationscodes ergänzt
2020-07-13 13:41:34 +02:00
# spec_Z_02
Initial commit
2020-07-13 12:42:14 +02:00
# - M|ART > Facet > Text facet > "Z" und "GH"
# -- show as: records
# --- All > Edit rows > Remove all matching rows
echo "Zeitschriften löschen (Breitenbrunn, Dresden)..."
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/row-removal",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "M|ART",
"expression": "value",
"columnName": "M|ART",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "GH",
"l": "GH"
}
},
{
"v": {
"v": "Z",
"l": "Z"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "record-based"
}
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
Nummerierung im Quellcode entfernt um Neusortierung zu erleichtern und Diffs aussagekräftiger zu machen
2020-08-13 15:25:31 +02:00
# ------------------------- Makulierte Medien löschen ------------------------ #
Initial commit
2020-07-13 12:42:14 +02:00
Spezifikationscodes ergänzt
2020-07-13 13:41:34 +02:00
# spec_Z_03
Korrektur spec_Z_03 und neu spec_B_E16
2020-10-20 17:53:08 +02:00
# löscht alle Titel+Exemplare, die ausschließlich makulierte Ex. enthalten
Initial commit
2020-07-13 12:42:14 +02:00
echo "Makulierte Medien löschen..."
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/row-removal",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "E|EXSTA",
Korrektur spec_Z_03 und neu spec_B_E16
2020-10-20 17:53:08 +02:00
"expression": "grel:row.record.cells[columnName].value.uniques().join(',') == 'M'",
Initial commit
2020-07-13 12:42:14 +02:00
"columnName": "E|EXSTA",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
Korrektur spec_Z_03 und neu spec_B_E16
2020-10-20 17:53:08 +02:00
"v": true,
"l": "true"
Initial commit
2020-07-13 12:42:14 +02:00
}
}
],
"selectBlank": false,
"selectError": false
}
],
Korrektur spec_Z_03 und neu spec_B_E16
2020-10-20 17:53:08 +02:00
"mode": "record-based"
Initial commit
2020-07-13 12:42:14 +02:00
}
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
Nummerierung im Quellcode entfernt um Neusortierung zu erleichtern und Diffs aussagekräftiger zu machen
2020-08-13 15:25:31 +02:00
# ------------------------------------ File ---------------------------------- #
Bibliothekskürzel aus Importdateiname, ISBN ergänzt, Korrektur Standort, Template vereinfacht
2020-07-22 17:42:00 +02:00
echo "Bibliothekskürzel aus Import-Dateiname..."
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/text-transform",
"engineConfig": {
"facets": [],
"mode": "row-based"
},
"columnName": "File",
"expression": "grel:with([ ['bautzen.tsv','BZ'], ['breitenbrunn.tsv','BB'], ['dresden.tsv','DD'], ['glauchau.tsv','GC'], ['plauen.tsv','PL'] ], mapping, forEach(mapping, m, if(value == m[0], m[1], '')).join(''))",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
Nummerierung im Quellcode entfernt um Neusortierung zu erleichtern und Diffs aussagekräftiger zu machen
2020-08-13 15:25:31 +02:00
# ------------------------------------ 0100 ---------------------------------- #
Initial commit
2020-07-13 12:42:14 +02:00
Zwischenformat PICA3
2020-07-21 23:09:58 +02:00
# spec_B_T_01
# TODO: Aufteilung in 0100 / 0110 nach Nummernkreisen
# TODO: Korrekturen für <9 und >10-stellige
echo "K10plus-PPNs in 0100..."
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/column-addition",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "M|IDNR",
"expression": "grel:value.length()",
"columnName": "M|IDNR",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": 9,
"l": "9"
}
},
{
"v": {
"v": 10,
"l": "10"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"baseColumnName": "M|IDNR",
"expression": "grel:value",
"onError": "set-to-blank",
"newColumnName": "0100",
"columnInsertIndex": 3
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
Nummerierung im Quellcode entfernt um Neusortierung zu erleichtern und Diffs aussagekräftiger zu machen
2020-08-13 15:25:31 +02:00
# ------------------------------------ 2199 ---------------------------------- #
Zwischenformat PICA3
2020-07-21 23:09:58 +02:00
# spec_B_T_49
echo "Nummern aus Datenkonversion 2199..."
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/column-addition",
"engineConfig": {
"facets": [],
"mode": "row-based"
},
"baseColumnName": "M|MEDNR",
Bibliothekskürzel aus Importdateiname, ISBN ergänzt, Korrektur Standort, Template vereinfacht
2020-07-22 17:42:00 +02:00
"expression": "grel:'BA' + cells['File'].value + value",
Zwischenformat PICA3
2020-07-21 23:09:58 +02:00
"onError": "set-to-blank",
"newColumnName": "2199",
"columnInsertIndex": 3
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
CBS-Exemplardaten Bibliotheca v50
2020-10-19 15:09:01 +02:00
# ----------------------------------- 7100j ---------------------------------- #
Zwischenformat PICA3
2020-07-21 23:09:58 +02:00
# spec_B_E_15
CBS-Exemplardaten Bibliotheca v50
2020-10-19 15:09:01 +02:00
echo "Abteilungsnummer 7100j..."
Initial commit
2020-07-13 12:42:14 +02:00
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/column-addition",
"engineConfig": {
"facets": [],
"mode": "row-based"
},
Kürzel aus Dateiname und für Dresden nachrangig aus E|ZWGST
2020-08-10 15:47:03 +02:00
"baseColumnName": "File",
CBS-Exemplardaten Bibliotheca v50
2020-10-19 15:09:01 +02:00
"expression": "grel:with(if(value=='DD',forNonBlank(cells['E|ZWGST'].value,v,v,value),value),x,x.replace('BB','0002').replace('BZ','0001').replace('DD','0003').replace('EH','0008').replace('GC','0004').replace('PL','0007'))",
Initial commit
2020-07-13 12:42:14 +02:00
"onError": "set-to-blank",
CBS-Exemplardaten Bibliotheca v50
2020-10-19 15:09:01 +02:00
"newColumnName": "7100j",
Zwischenformat PICA3
2020-07-21 23:09:58 +02:00
"columnInsertIndex": 3
Initial commit
2020-07-13 12:42:14 +02:00
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
Nummerierung im Quellcode entfernt um Neusortierung zu erleichtern und Diffs aussagekräftiger zu machen
2020-08-13 15:25:31 +02:00
# ----------------------------------- 7100f ---------------------------------- #
Export in PICA+ ausgelagert
2020-07-22 11:00:38 +02:00
Korrektur spec_Z_03 und neu spec_B_E16
2020-10-20 17:53:08 +02:00
# spec_B_E_13, spec_Z_03
echo "Zweigstelle 7100f"
Export in PICA+ ausgelagert
2020-07-22 11:00:38 +02:00
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/column-addition",
"engineConfig": {
"facets": [],
"mode": "row-based"
},
Kürzel aus Dateiname und für Dresden nachrangig aus E|ZWGST
2020-08-10 15:47:03 +02:00
"baseColumnName": "File",
"expression": "grel:if(value=='DD',forNonBlank(cells['E|ZWGST'].value,v,v,value),value)",
Export in PICA+ ausgelagert
2020-07-22 11:00:38 +02:00
"onError": "set-to-blank",
"newColumnName": "7100f",
"columnInsertIndex": 3
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
Initial commit
2020-07-13 12:42:14 +02:00
Nummerierung im Quellcode entfernt um Neusortierung zu erleichtern und Diffs aussagekräftiger zu machen
2020-08-13 15:25:31 +02:00
# ----------------------------------- 7100a ---------------------------------- #
Initial commit
2020-07-13 12:42:14 +02:00
Export in PICA+ ausgelagert
2020-07-22 11:00:38 +02:00
# spec_B_E_07
Bibliothekskürzel aus Importdateiname, ISBN ergänzt, Korrektur Standort, Template vereinfacht
2020-07-22 17:42:00 +02:00
echo "Standort 7100a..."
Initial commit
2020-07-13 12:42:14 +02:00
if curl -fs \
--data project="${projects[$p]}" \
Export in PICA+ ausgelagert
2020-07-22 11:00:38 +02:00
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/column-addition",
"engineConfig": {
"facets": [],
"mode": "row-based"
},
"baseColumnName": "E|STA1",
Mehrfache Leerzeichen in 7100a entfernen
2020-10-20 11:44:31 +02:00
"expression": "grel:value.replace('␟',' ').replace(/ +/,' ')",
Export in PICA+ ausgelagert
2020-07-22 11:00:38 +02:00
"onError": "set-to-blank",
Bibliothekskürzel aus Importdateiname, ISBN ergänzt, Korrektur Standort, Template vereinfacht
2020-07-22 17:42:00 +02:00
"newColumnName": "7100a",
Export in PICA+ ausgelagert
2020-07-22 11:00:38 +02:00
"columnInsertIndex": 3
}
]
JSON
Initial commit
2020-07-13 12:42:14 +02:00
then
Export in PICA+ ausgelagert
2020-07-22 11:00:38 +02:00
log "transformed ${p} (${projects[$p]})"
Initial commit
2020-07-13 12:42:14 +02:00
else
Export in PICA+ ausgelagert
2020-07-22 11:00:38 +02:00
error "transform ${p} (${projects[$p]}) failed!"
Initial commit
2020-07-13 12:42:14 +02:00
fi
echo
Nummerierung im Quellcode entfernt um Neusortierung zu erleichtern und Diffs aussagekräftiger zu machen
2020-08-13 15:25:31 +02:00
# ----------------------------------- 2000 ----------------------------------- #
Bibliothekskürzel aus Importdateiname, ISBN ergänzt, Korrektur Standort, Template vereinfacht
2020-07-22 17:42:00 +02:00
# TODO: ISMN in 2020
# spec_B_T_04, spec_B_T_05
echo "ISBN 2000..."
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/column-addition",
"engineConfig": {
"facets": [],
"mode": "record-based"
},
"baseColumnName": "M|ISBN",
2000: Prüfziffer in ISBN immer als Großbuchstabe (x -> X)
2020-08-25 23:17:08 +02:00
"expression": "grel:[ forNonBlank(cells['M|ISBN'].value,v,if(isNumeric(v[0]),v,null),null), forNonBlank(cells['M|ISBN2'].value,v,if(isNumeric(v[0]),v,null),null) ].uniques().join('␟').replace('-','').toUppercase()",
Bibliothekskürzel aus Importdateiname, ISBN ergänzt, Korrektur Standort, Template vereinfacht
2020-07-22 17:42:00 +02:00
"onError": "set-to-blank",
"newColumnName": "2000",
Schönheitskorrekturen
2020-07-22 18:11:54 +02:00
"columnInsertIndex": 3
Bibliothekskürzel aus Importdateiname, ISBN ergänzt, Korrektur Standort, Template vereinfacht
2020-07-22 17:42:00 +02:00
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
Nummerierung im Quellcode entfernt um Neusortierung zu erleichtern und Diffs aussagekräftiger zu machen
2020-08-13 15:25:31 +02:00
# ----------------------------------- E0XX ----------------------------------- #
Zugangsdatum und Selektionsschlüssel
2020-07-22 23:38:39 +02:00
# spec_B_E_10
echo "Zugangsdatum E0XX..."
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/column-addition",
"engineConfig": {
Korrektur temporäre Löschregel für Titel ohne Exemplare
2020-08-18 17:40:07 +02:00
"facets": [
{
"type": "list",
"name": "E|EXNR",
"expression": "isBlank(value)",
"columnName": "E|EXNR",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": false,
"l": "false"
}
}
],
"selectBlank": false,
"selectError": false
}
],
Zugangsdatum und Selektionsschlüssel
2020-07-22 23:38:39 +02:00
"mode": "row-based"
},
"baseColumnName": "E|ZUDAT",
"expression": "grel:forNonBlank(value,v,v[0,2] + '-' + v[3,5] + '-' + v[8,10],'22-07-20')",
"onError": "set-to-blank",
"newColumnName": "E0XX",
"columnInsertIndex": 3
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
Nummerierung im Quellcode entfernt um Neusortierung zu erleichtern und Diffs aussagekräftiger zu machen
2020-08-13 15:25:31 +02:00
# ----------------------------------- E0XXb ---------------------------------- #
Zugangsdatum und Selektionsschlüssel
2020-07-22 23:38:39 +02:00
Korrektur spec_Z_03 und neu spec_B_E16
2020-10-20 17:53:08 +02:00
# spec_B_E_14, spec_Z_03, spec_B_E16
# leer für Exemplare, die nicht konvertiert werden sollen:
# - makulierte Exemplare
# - ACQ-Datensätze
Zugangsdatum und Selektionsschlüssel
2020-07-22 23:38:39 +02:00
echo "Selektionsschlüssel E0XXb..."
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
Korrektur spec_Z_03 und neu spec_B_E16
2020-10-20 17:53:08 +02:00
[
{
"op": "core/column-addition",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "E|EXNR",
"expression": "isBlank(value)",
"columnName": "E|EXNR",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": false,
"l": "false"
Korrektur temporäre Löschregel für Titel ohne Exemplare
2020-08-18 17:40:07 +02:00
}
Korrektur spec_Z_03 und neu spec_B_E16
2020-10-20 17:53:08 +02:00
}
],
"selectBlank": false,
"selectError": false
},
{
"type": "list",
"name": "E|EXSTA",
"expression": "value",
"columnName": "E|EXSTA",
"invert": true,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "M",
"l": "M"
}
}
],
"selectBlank": false,
"selectError": false
},
{
"type": "list",
"name": "E|MEKZ",
"expression": "value",
"columnName": "E|MEKZ",
"invert": true,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "ACQ",
"l": "ACQ"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"baseColumnName": "File",
"expression": "grel:with(if(value=='DD',forNonBlank(cells['E|ZWGST'].value,v,v,value),value),x,'n'+x.toLowercase())",
"onError": "set-to-blank",
"newColumnName": "E0XXb",
"columnInsertIndex": 3
}
]
Zugangsdatum und Selektionsschlüssel
2020-07-22 23:38:39 +02:00
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
Nummerierung im Quellcode entfernt um Neusortierung zu erleichtern und Diffs aussagekräftiger zu machen
2020-08-13 15:25:31 +02:00
# ----------------------------------- 0500 ----------------------------------- #
0500 spec_B_T_56
2020-08-11 17:36:22 +02:00
# spec_B_T_56
# TODO: Differenzierung nach MEDGR
echo "Gattung und Status 0500..."
read -r -d '' expression << EXPRESSION
if(
1140 Veröffentlichungsart aus ART
2020-08-13 15:46:22 +02:00
or(
value == 'M',
value == 'L'
),
0500 spec_B_T_56
2020-08-11 17:36:22 +02:00
'Aan',
1140 Veröffentlichungsart aus ART
2020-08-13 15:46:22 +02:00
if(
value == 'U',
'Asn',
if(
or(
value == 'A',
value == 'V'
),
'Ban',
if(
and(
value == 'P',
forNonBlank(cells['M|MEDGR'].value,v,if(v == 'SPIEL', true, false),false)
),
Korrektur 0500 ART=P Spiel -> Van
2020-10-20 18:10:01 +02:00
'Van',
1140 Veröffentlichungsart aus ART
2020-08-13 15:46:22 +02:00
if(
value == 'P',
'Lax',
if(
value == 'G',
'Acn',
if(
value == 'S',
'AFn',
if(
value == 'Z',
'Abn',
null
))))))))
0500 spec_B_T_56
2020-08-11 17:36:22 +02:00
EXPRESSION
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< JSON
[
{
"op": "core/column-addition",
"engineConfig": {
"facets": [],
"mode": "row-based"
},
"baseColumnName": "M|ART",
fix 0500
2020-08-12 17:11:38 +02:00
"expression": $(echo "grel:${expression}" | ${jq} -s -R '.'),
0500 spec_B_T_56
2020-08-11 17:36:22 +02:00
"onError": "set-to-blank",
"newColumnName": "0500",
"columnInsertIndex": 3
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
1140 Veröffentlichungsart aus ART
2020-08-13 15:46:22 +02:00
# ----------------------------------- 1140 ----------------------------------- #
# spec_B_T_53
# TODO: Differenzierung nach MEDGR
echo "Veröffentlichungsart 1140..."
read -r -d '' expression << EXPRESSION
if(
value == 'A',
'muto',
if(
value == 'V',
'vide',
if(
value == 'L',
'lo',
null
)))
EXPRESSION
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< JSON
[
{
"op": "core/column-addition",
"engineConfig": {
"facets": [],
"mode": "row-based"
},
"baseColumnName": "M|ART",
"expression": $(echo "grel:${expression}" | ${jq} -s -R '.'),
"onError": "set-to-blank",
"newColumnName": "1140",
"columnInsertIndex": 3
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
Nummerierung im Quellcode entfernt um Neusortierung zu erleichtern und Diffs aussagekräftiger zu machen
2020-08-13 15:25:31 +02:00
# ----------------------------------- 4000 ----------------------------------- #
Haupttitel 4000 aus HST
2020-08-12 16:12:22 +02:00
# spec_B_T_17
echo "Haupttitel 4000..."
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/column-addition",
"engineConfig": {
fix 4000 und 8200
2020-08-12 17:52:44 +02:00
"facets": [],
"mode": "record-based"
Haupttitel 4000 aus HST
2020-08-12 16:12:22 +02:00
},
"baseColumnName": "M|HST",
fix 4000 und 8200
2020-08-12 17:52:44 +02:00
"expression": "grel:if(value.contains('¬'),with(value.split('¬'), v, v[0].trim() + ' @' + v[1].trim()),value)",
Haupttitel 4000 aus HST
2020-08-12 16:12:22 +02:00
"onError": "set-to-blank",
"newColumnName": "4000",
"columnInsertIndex": 3
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
Verbuchungsnummer 8200 aus BARCO und Präfix
2020-08-12 16:31:36 +02:00
fi
echo
Nummerierung im Quellcode entfernt um Neusortierung zu erleichtern und Diffs aussagekräftiger zu machen
2020-08-13 15:25:31 +02:00
# ----------------------------------- 8200 ----------------------------------- #
Verbuchungsnummer 8200 aus BARCO und Präfix
2020-08-12 16:31:36 +02:00
# spec_B_E_02
echo "Verbuchungsnummer 4000..."
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/column-addition",
"engineConfig": {
fix 4000 und 8200
2020-08-12 17:52:44 +02:00
"facets": [],
Verbuchungsnummer 8200 aus BARCO und Präfix
2020-08-12 16:31:36 +02:00
"mode": "row-based"
},
"baseColumnName": "E|BARCO",
"expression": "grel:cells['File'].value + value",
"onError": "set-to-blank",
"newColumnName": "8200",
"columnInsertIndex": 3
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
Haupttitel 4000 aus HST
2020-08-12 16:12:22 +02:00
fi
echo
1100 Jahr spec_B_T_02
2020-08-18 12:07:32 +02:00
# ----------------------------------- 1100 ----------------------------------- #
# spec_B_T_02
# 1100a normiert mit zahlreichen Ersetzungen
echo "Jahresangaben 1100a und 1100n..."
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/column-addition",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "M|MEDNR",
"expression": "isBlank(value)",
"columnName": "M|MEDNR",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": false,
"l": "false"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"baseColumnName": "M|JAHR",
"expression": "grel:value",
"onError": "set-to-blank",
"newColumnName": "1100n",
"columnInsertIndex": 3
},
{
"op": "core/column-addition",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "M|MEDNR",
"expression": "isBlank(value)",
"columnName": "M|MEDNR",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": false,
"l": "false"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"baseColumnName": "M|JAHR",
"expression": "grel:with(with(with(value.replace('[','').replace(']','').replace('(','').replace(')','').replace(' ','').replace('?','').replace('.','').replace('ca','').replace('c','').replace('ff',''),x,forNonBlank(x.split('/')[1],v,v,x)),y,y.split('-')[0]),z,if(and(z.length()==4,isNumeric(z)),z,if(z=='19XX','19XX',null))))",
"onError": "set-to-blank",
"newColumnName": "1100a",
"columnInsertIndex": 3
},
{
"op": "core/text-transform",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "M|MEDNR",
"expression": "isBlank(value)",
"columnName": "M|MEDNR",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": false,
"l": "false"
}
}
],
"selectBlank": false,
"selectError": false
},
{
"type": "list",
"name": "1100a",
"expression": "isBlank(value)",
"columnName": "1100a",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": true,
"l": "true"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"columnName": "1100a",
"expression": "grel:if(cells['M|JAHR'].value.contains('19'),'19XX','20XX')",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
Exemplardaten Bibliotheca 7100d 8011 8100 8515
2020-10-06 23:30:58 +02:00
# ----------------------------------- 8515 ----------------------------------- #
# spec_B_E_01
CBS-Exemplardaten Bibliotheca v50
2020-10-19 15:09:01 +02:00
# nur für Bautzen
Exemplardaten Bibliotheca 7100d 8011 8100 8515
2020-10-06 23:30:58 +02:00
echo "Ausleihhinweis 8515..."
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/column-addition",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "File",
"expression": "value",
"columnName": "File",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "BZ",
"l": "BZ"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"baseColumnName": "E|AUHIN",
"expression": "grel:value",
"onError": "set-to-blank",
"newColumnName": "8515",
"columnInsertIndex": 3
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
# ----------------------------------- 7100d ---------------------------------- #
# spec_B_E_04 und spec_B_E_05
echo "Exemplarstatus 7100d..."
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/column-addition",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "E|EXSTA",
"expression": "value",
"columnName": "E|EXSTA",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "H",
"l": "H"
}
},
{
"v": {
"v": "I",
"l": "I"
}
},
{
"v": {
"v": "T",
"l": "T"
}
},
{
"v": {
"v": "U",
"l": "U"
}
},
{
"v": {
"v": "V",
"l": "V"
}
},
{
"v": {
"v": "v",
"l": "v"
}
},
{
"v": {
"v": "Z",
"l": "Z"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"baseColumnName": "E|EXSTA",
"expression": "grel:'u'",
"onError": "set-to-blank",
"newColumnName": "7100d",
"columnInsertIndex": 3
},
{
"op": "core/text-transform",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "E|EXSTA",
"expression": "value",
"columnName": "E|EXSTA",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "A",
"l": "A"
}
}
],
"selectBlank": false,
"selectError": false
},
{
"type": "list",
"name": "File",
"expression": "value",
"columnName": "File",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "PL",
"l": "PL"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"columnName": "7100d",
"expression": "grel:'z'",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
},
{
"op": "core/text-transform",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "E|EXSTA",
"expression": "value",
"columnName": "E|EXSTA",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "A",
"l": "A"
}
}
],
"selectBlank": false,
"selectError": false
},
{
"type": "list",
"name": "File",
"expression": "value",
"columnName": "File",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "DD",
"l": "DD"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"columnName": "7100d",
"expression": "grel:'a'",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
},
{
"op": "core/text-transform",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "E|EXSTA",
"expression": "value",
"columnName": "E|EXSTA",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "B",
"l": "B"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"columnName": "7100d",
"expression": "grel:'a'",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
},
{
"op": "core/text-transform",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "E|EXSTA",
"expression": "value",
"columnName": "E|EXSTA",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "G",
"l": "G"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"columnName": "7100d",
"expression": "grel:'g'",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
},
{
"op": "core/text-transform",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "E|EXSTA",
"expression": "value",
"columnName": "E|EXSTA",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "K",
"l": "K"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"columnName": "7100d",
"expression": "grel:'i'",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
},
{
"op": "core/text-transform",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "E|EXSTA",
"expression": "value",
"columnName": "E|EXSTA",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "N",
"l": "N"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"columnName": "7100d",
"expression": "grel:'u'",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
},
{
"op": "core/text-transform",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "E|EXSTA",
"expression": "value",
"columnName": "E|EXSTA",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "P",
"l": "P"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"columnName": "7100d",
"expression": "grel:'i'",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
},
{
"op": "core/text-transform",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "E|EXSTA",
"expression": "value",
"columnName": "E|EXSTA",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "W",
"l": "W"
}
}
],
"selectBlank": false,
"selectError": false
},
{
"type": "list",
"name": "File",
"expression": "value",
"columnName": "File",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "PL",
"l": "PL"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"columnName": "7100d",
"expression": "grel:'c'",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
},
{
"op": "core/text-transform",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "E|EXSTA",
"expression": "value",
"columnName": "E|EXSTA",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "W",
"l": "W"
}
}
],
"selectBlank": false,
"selectError": false
},
{
"type": "list",
"name": "File",
"expression": "value",
"columnName": "File",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "DD",
"l": "DD"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"columnName": "7100d",
"expression": "grel:'z'",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
},
{
"op": "core/text-transform",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "E|EXSTA",
"expression": "value",
"columnName": "E|EXSTA",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "W",
"l": "W"
}
}
],
"selectBlank": false,
"selectError": false
},
{
"type": "list",
"name": "File",
"expression": "value",
"columnName": "File",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "BB",
"l": "BB"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"columnName": "7100d",
"expression": "grel:'z'",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
},
{
"op": "core/text-transform",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "E|EXSTA",
"expression": "value",
"columnName": "E|EXSTA",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "w",
"l": "w"
}
}
],
"selectBlank": false,
"selectError": false
},
{
"type": "list",
"name": "File",
"expression": "value",
"columnName": "File",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "BB",
"l": "BB"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"columnName": "7100d",
"expression": "grel:'z'",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
},
{
"op": "core/text-transform",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "E|EXSTA",
"expression": "value",
"columnName": "E|EXSTA",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "E",
"l": "E"
}
}
],
"selectBlank": false,
"selectError": false
},
{
"type": "list",
"name": "E|ESORG",
"expression": "value",
"columnName": "E|ESORG",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "P",
"l": "P"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"columnName": "7100d",
"expression": "grel:'i'",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
},
{
"op": "core/text-transform",
"engineConfig": {
7100d EXSTA E und ESORG K -> AUI u
2020-10-26 12:45:40 +01:00
"facets": [
{
"type": "list",
"name": "E|EXSTA",
"expression": "value",
"columnName": "E|EXSTA",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "E",
"l": "E"
}
}
],
"selectBlank": false,
"selectError": false
},
{
"type": "list",
"name": "E|ESORG",
"expression": "value",
"columnName": "E|ESORG",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "K",
"l": "K"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"columnName": "7100d",
"expression": "grel:'u'",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
},
{
"op": "core/text-transform",
"engineConfig": {
Exemplardaten Bibliotheca 7100d 8011 8100 8515
2020-10-06 23:30:58 +02:00
"facets": [
{
"type": "list",
"name": "E|EXSTA",
"expression": "value",
"columnName": "E|EXSTA",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "E",
"l": "E"
}
}
],
"selectBlank": false,
"selectError": false
},
{
"type": "list",
"name": "E|ESORG",
"expression": "value",
"columnName": "E|ESORG",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "W",
"l": "W"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"columnName": "7100d",
"expression": "grel:'c'",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
},
{
"op": "core/text-transform",
"engineConfig": {
"facets": [
{
"type": "list",
"name": "E|EXSTA",
"expression": "value",
"columnName": "E|EXSTA",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": "E",
"l": "E"
}
}
],
"selectBlank": false,
"selectError": false
},
{
"type": "list",
"name": "7100d",
"expression": "isBlank(value)",
"columnName": "7100d",
"invert": false,
"omitBlank": false,
"omitError": false,
"selection": [
{
"v": {
"v": true,
"l": "true"
}
}
],
"selectBlank": false,
"selectError": false
}
],
"mode": "row-based"
},
"columnName": "7100d",
"expression": "grel:'u'",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
# ----------------------------------- 8011 ----------------------------------- #
# spec_B_E_06
echo "Mediengruppe 8011..."
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/column-addition",
"engineConfig": {
"facets": [],
"mode": "row-based"
},
"baseColumnName": "E|MEDGR",
"expression": "grel:'MEDGR: ' + value",
"onError": "set-to-blank",
"newColumnName": "8011",
"columnInsertIndex": 3
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
# ----------------------------------- 8100 ----------------------------------- #
# spec_B_E_11 und spec_B_E_12
echo "Zugangsnummer 8100..."
if curl -fs \
--data project="${projects[$p]}" \
--data-urlencode "operations@-" \
"${endpoint}/command/core/apply-operations$(refine_csrf)" > /dev/null \
<< "JSON"
[
{
"op": "core/column-addition",
"engineConfig": {
"facets": [],
"mode": "row-based"
},
"baseColumnName": "E|ZUNR",
"expression": "grel:cells['File'].value + ' ' + value.replace('-','/')",
"onError": "set-to-blank",
"newColumnName": "8100",
"columnInsertIndex": 3
},
{
"op": "core/text-transform",
"engineConfig": {
"facets": [
{
"type": "text",
"name": "E|ZUS",
"columnName": "E|ZUS",
"query": "Notation",
"mode": "text",
"caseSensitive": false,
"invert": false
}
],
"mode": "row-based"
},
"columnName": "8100",
"expression": "grel:value + ' ' + cells['E|ZUS'].value.replace('Notation||','')",
"onError": "keep-original",
"repeat": false,
"repeatCount": 10
}
]
JSON
then
log "transformed ${p} (${projects[$p]})"
else
error "transform ${p} (${projects[$p]}) failed!"
fi
echo
Export in PICA+ ausgelagert
2020-07-22 11:00:38 +02:00
# ================================== EXPORT ================================== #
Initial commit
2020-07-13 12:42:14 +02:00
Refactoring mit task runner
2020-08-01 02:04:39 +02:00
checkpoint "Export"; echo
Export OpenRefine-Projekt für Debugging
2020-08-12 17:01:26 +02:00
# Export des OpenRefine-Projekts für Tests
format="openrefine.tar.gz"
echo "export ${p} to ${format} file..."
if curl -fs \
--data project="${projects[$p]}" \
"${endpoint}/command/core/export-project" \
> "${workdir}/${p}.${format}"
then
log "exported ${p} (${projects[$p]}) to ${workdir}/${p}.${format}"
else
error "export of ${p} (${projects[$p]}) failed!"
fi
echo
Export in PICA+ ausgelagert
2020-07-22 11:00:38 +02:00
# Export der PICA3-Spalten als CSV
0500 spec_B_T_56
2020-08-11 17:36:22 +02:00
# Spalte 2199 muss vorne stehen, weil später für Sortierung benötigt
Export in PICA+ ausgelagert
2020-07-22 11:00:38 +02:00
format="csv"
echo "export ${p} to ${format} file using template..."
Initial commit
2020-07-13 12:42:14 +02:00
IFS= read -r -d '' template << "TEMPLATE"
{{
Export in PICA+ ausgelagert
2020-07-22 11:00:38 +02:00
with(
[
'2199',
'0100',
0500 spec_B_T_56
2020-08-11 17:36:22 +02:00
'0500',
1100 Jahr spec_B_T_02
2020-08-18 12:07:32 +02:00
'1100a',
'1100n',
1140 Veröffentlichungsart aus ART
2020-08-13 15:46:22 +02:00
'1140',
Bibliothekskürzel aus Importdateiname, ISBN ergänzt, Korrektur Standort, Template vereinfacht
2020-07-22 17:42:00 +02:00
'2000',
Haupttitel 4000 aus HST
2020-08-12 16:12:22 +02:00
'4000',
CBS-Exemplardaten Bibliotheca v50
2020-10-19 15:09:01 +02:00
'7100j',
Export in PICA+ ausgelagert
2020-07-22 11:00:38 +02:00
'7100f',
Zugangsdatum und Selektionsschlüssel
2020-07-22 23:38:39 +02:00
'7100a',
Exemplardaten Bibliotheca 7100d 8011 8100 8515
2020-10-06 23:30:58 +02:00
'7100d',
'8011',
'8100',
fix 8200
2020-08-12 18:13:40 +02:00
'8200',
Exemplardaten Bibliotheca 7100d 8011 8100 8515
2020-10-06 23:30:58 +02:00
'8515',
Zugangsdatum und Selektionsschlüssel
2020-07-22 23:38:39 +02:00
'E0XX',
'E0XXb'
Export in PICA+ ausgelagert
2020-07-22 11:00:38 +02:00
],
columns,
if(
row.index == 0,
forEach(
columns,
cn,
cn.escape('csv')
).join(',')
+ '\n'
+ with(
forEach(
columns,
cn,
forNonBlank(
cells[cn].value,
v,
v.escape('csv'),
'␀'
)
).join(',').replace('␀',''),
r,
if(
isNonBlank(r.split(',').join(',')),
r + '\n',
''
)
),
with(
forEach(
columns,
cn,
forNonBlank(
cells[cn].value,
v,
v.escape('csv'),
'␀'
)
).join(',').replace('␀',''),
r,
if(
isNonBlank(r.split(',').join(',')),
r + '\n',
''
)
)
)
)
Initial commit
2020-07-13 12:42:14 +02:00
}}
TEMPLATE
if echo "${template}" | head -c -2 | curl -fs \
--data project="${projects[$p]}" \
--data format="template" \
--data prefix="" \
--data suffix="" \
--data separator="" \
--data engine='{"facets":[],"mode":"row-based"}' \
--data-urlencode template@- \
"${endpoint}/command/core/export-rows" \
Refactoring mit task runner
2020-08-01 02:04:39 +02:00
> "${workdir}/${p}.${format}"
Initial commit
2020-07-13 12:42:14 +02:00
then
Refactoring mit task runner
2020-08-01 02:04:39 +02:00
log "exported ${p} (${projects[$p]}) to ${workdir}/${p}.${format}"
Initial commit
2020-07-13 12:42:14 +02:00
else
error "export of ${p} (${projects[$p]}) failed!"
fi
echo
# ================================== FINISH ================================== #
Refactoring mit task runner
2020-08-01 02:04:39 +02:00
checkpoint "Finish"; echo
# stop OpenRefine server
Initial commit
2020-07-13 12:42:14 +02:00
refine_stop; echo
Refactoring mit task runner
2020-08-01 02:04:39 +02:00
# calculate run time based on checkpoints
checkpoint_stats; echo
# word count on all files in workdir
count_output