Map local authority records to libris URI:s

hydrate.groovy

@Grab('com.github.albaker:GroovySparql:0.9.0')
import groovy.sparql.*

@Grab('commons-lang#commons-lang;2.4')
import org.apache.commons.lang.WordUtils

import groovy.json.StringEscapeUtils

// Tab separated file with ids and names to look up in Libris.
// Example line format:
// 20384204  Strindberg, August, 1849-1912
//
fname = 'cleaned.txt'

// Libris sparql endpoint
spep = new Sparql(endpoint:"http://libris.kb.se/sparql")


/**
 * Tries to find a related libris URI.
 *
 * @param name Name to look for e.g. "Strindberg, August, 1849-1912"
 * @return a list of matching URI:s
 */
def lookup(name) {
  result = []
  name = StringEscapeUtils.escapeJavaScript(WordUtils.capitalizeFully(name))

  query = """
  PREFIX owl: <http://www.w3.org/2002/07/owl#>
  PREFIX foaf: <http://xmlns.com/foaf/0.1/>
  PREFIX dbpedia: <http://dbpedia.org/ontology/>
  PREFIX rdfs: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>

  select ?s {
    ?s a foaf:Person .
      ?s foaf:name "${name}" .
  }
  """

  spep.each query, {
    result << "${s}"
  }

  return result
}



File csv = new File(fname)
lineno = 1
skipped = 0

csv.withReader { reader ->
    while ((line = reader.readLine())!=null) {
      l = line.split("\t")

      if (l[1].size() < 50 && !l[1].contains("/") && !l[1].contains("\"")) {
        librisUri = lookup(l[1])
        if (librisUri != []) {
          println "${l[0]}\t${l[1]}\t${librisUri[0]}"
        }
      } else {
        skipped++
      }

      lineno++
    }
}

//println "Checked ${lineno} names."
//println "Skipped ${skipped} lines."
//println "Matched ${lineno-skipped} lines."