1 #!/bin/bash

     2 

     3 # Relational pipes

     4 # Copyright © 2020 František Kučera (Frantovo.cz, GlobalCode.info)

     5 # 

     6 # This program is free software: you can redistribute it and/or modify

     7 # it under the terms of the GNU General Public License as published by

     8 # the Free Software Foundation, version 3 of the License.

     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 relpipe_in_sparql_help() {

    19 	cat <<-EOF

    20 		SPARQL query is expected on the STDIN. Exapmple:

    21 		  echo 'SELECT * WHERE { ?subject ?predicate ?object . } LIMIT 3' \

    22 | relpipe-in-sparql | relpipe-out-tabular

    23 		

    24 		Namespace prefixes are part of the query.

    25 		But because they are usually constant, they can be set as the 

    26 		RELPIPE_IN_SPARQL_PREFIXES environmental variable.

    27 		Then they are prepended to the query.

    28 		

    29 		SPARQL endpoint can be set ad-hoc by the --endpoint option.

    30 		

    31 		To configure default SPARQL endpoint, add something like this to your environment:

    32 		  export RELPIPE_IN_SPARQL_ENDPOINT="https://query.wikidata.org/sparql"

    33 		  export RELPIPE_IN_SPARQL_ENDPOINT="https://dbpedia.org/sparql"

    34 		  export RELPIPE_IN_SPARQL_ENDPOINT="https://data.gov.cz/sparql"

    35 		  export RELPIPE_IN_SPARQL_ENDPOINT="https://data.cssz.cz/sparql"

    36 

    37 		The relation name defaults to "rdf". Custom name can be set using the --relation option.

    38 EOF

    39 }

    40 

    41 relation="rdf";

    42 endpoint="${RELPIPE_IN_SPARQL_ENDPOINT:-https://dbpedia.org/sparql}";

    43 

    44 while [[ $# -gt 0 ]]; do

    45 	argument="$1";

    46 	case "$argument" in

    47 		"--relation") relation="$2"; shift; shift; ;;

    48 		"--endpoint") endpoint="$2"; shift; shift; ;;

    49 		"--help") relpipe_in_sparql_help; exit; ;;

    50 	esac

    51 done

    52 

    53 [[ -n "$RELPIPE_IN_SPARQL_PREFIXES" ]] && query="$RELPIPE_IN_SPARQL_PREFIXES"; query+=$'\n\n';

    54 

    55 query+="$(</dev/stdin)";

    56 

    57 

    58 # Simple implementation that utilizes the CSV output of the SPARQL endpoint.

    59 relpipe_in_sparql_implementation_csv() {

    60 	curl \

    61 		--header "Accept: text/csv" \

    62 		--data-urlencode query="$query" \

    63 		--fail \

    64 		--silent \

    65 		--show-error \

    66 		"$endpoint" \

    67 		| relpipe-in-csv "$relation"

    68 }

    69 

    70 # More powerful implementation based on XML.

    71 # Can be customized through XSLT.

    72 # But: has more dependencies and avoids streaming.

    73 relpipe_in_sparql_implementation_xml() {

    74 	DIR="$(dirname $(realpath "$0"))";

    75 	curl \

    76 		--header "Accept: application/sparql-results+xml" \

    77 		--data-urlencode query="$query" \

    78 		--fail \

    79 		--silent \

    80 		--show-error \

    81 		"$endpoint" \

    82 		| xsltproc --stringparam "relation" "$relation" "$DIR/relpipe-in-sparql.xsl" - \

    83 		| relpipe-in-xml

    84 }

    85 

    86 relpipe_in_sparql_implementation_${RELPIPE_IN_SPARQL_IMPLEMENTATION:-csv}