scripts/get_qid_from_property.sh

   1 #!/bin/bash
   2
   3 # get_equivalent.sh - Search equivalent element on Wikidata.
   4 # Copyright (C) 2022  Pierre Choffet
   5 #
   6 # This program is free software: you can redistribute it and/or modify
   7 # it under the terms of version 3 of the GNU General Public License as
   8 # published by the Free Software Foundation.
   9 #
  10 # This program is distributed in the hope that it will be useful,
  11 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  13 # GNU General Public License for more details.
  14 #
  15 # You should have received a copy of the GNU General Public License
  16 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
  17
  18 source "$(dirname "$0")/query.sh"
  19
  20 set -euo pipefail
  21
  22 function buildQuery() {
  23         local -r pid="${1}"
  24         shift
  25         local -r values=( "${@}" )
  26
  27         echo 'SELECT DISTINCT ?element WHERE {'
  28
  29         for index in ${!values[@]}
  30         do
  31                 if [ "${index}" -ne 0 ]
  32                 then
  33                         echo 'UNION'
  34                 fi
  35                 echo "{ ?element p:${pid} ?id${index}. ?id${index} (ps:${pid}) ${values[$index]@Q}. }"
  36         done
  37
  38         echo '} LIMIT 2'
  39 }
  40
  41 function usage() {
  42         cat << EOF
  43 USAGE: get_qid_from_property.sh <wdef_path> <element_id> <element_pid>
  44
  45 This script will get Wikidata's equivalent element to an entry in a wdef. If
  46 uniqueness can be ensured from a literal value (typically an external identifier),
  47 it's an easy way to merge your wdef with Wikidata.
  48 EOF
  49 }
  50
  51 if [ "$#" -ne 3 ]
  52 then
  53         usage >&2
  54         exit 1
  55 fi
  56
  57 readonly WDEF_PATH="${1}"
  58 readonly ELEMENT_ID="${2}"
  59 readonly ELEMENT_PID="${3}"
  60
  61 # Get wdef
  62 readarray -t VALUES<<<$(xmlstarlet sel -t -m "/wdef:knowledge/wdef:element[@wdef:id = \"${ELEMENT_ID}\"]/wdef:property[@wdef:pid = \"${ELEMENT_PID}\"]/wdef:value/wdef:literal" -v '.' -n "${WDEF_PATH}")
  63
  64 # Build query
  65 readonly QUERY_PATH=$(mktemp)
  66 buildQuery "${ELEMENT_PID}" ${VALUES[@]} > "${QUERY_PATH}"
  67 readonly RESULT_PATH=$(query "${QUERY_PATH}")
  68
  69 # Cleanup
  70 rm "${QUERY_PATH}"
  71
  72 # Print potential result in stdout, cleanup, exit
  73 readonly QID=$(xmlstarlet sel -t -m '/_:sparql/_:results[count(_:result) = 1]' -v '_:result/_:binding[@name = "element"]/_:uri' "${RESULT_PATH}")
  74
  75 if [ "${QID}" != '' ]
  76 then
  77         echo "${QID##*/}"
  78 else
  79         exit 1
  80 fi