Reputation:

Getting RDF parsed per Node.js The Right Way book example

In the book Node.js The Right Way there is an example of getting an RDF file parsed. I cannot get this example working as described in the book.

The RDF parser is this:

"use strict";
const fs      = require("fs");
const cheerio = require("cheerio");

module.exports = function(filename, callback) {
    fs.readFile(filename, function(err, data) {
        if (err) {
            return callback(err);
        }
        let $ = cheerio.load(data.toString());
        let collect = function(index, elem) {
            return $(elem).text();
        };
        callback(null, {
            _id: $('pgterms\\:ebook').attr('rdf:about').replace('ebooks/', ''),
            title: $('dcterms\\:title').text(),
            authors: $('pgterms\\:agent pgterms\\:name').map(collect),
            subjects: $('[rdf\\:resource$="/LCSH"] ~ rdf\\:value').map(collect)
        });
    });
};

The input RDF file is this:

<rdf:RDF>
  <pgterms:ebook rdf:about="ebooks/132">
    <dcterms:subject>
      <rdf:Description>
        <dcam:memberOf rdf:resource="http://purl.org/dc/terms/LCSH"/>
        <rdf:value>Military art and science -- Early works to 1800</rdf:value>
        <rdf:value>War -- Early works to 1800</rdf:value>
      </rdf:Description>
    </dcterms:subject>
    <dcterms:title>The Art of War</dcterms:title>
  </pgterms:ebook>
  <pgterms:agent rdf:about="2009/agents/4349">
    <pgterms:name>Sunzi (6th cent. BC)</pgterms:name>
  </pgterms:agent>
  <pgterms:agent rdf:about="2009/agents/5101">
    <pgterms:name>Giles, Lionel</pgterms:name>
  </pgterms:agent>
</rdf:RDF>

And I believe the output of the parser should look like this:

{
  "_id": "132",
  "title": "The Art of War", 
  "authors": [
    "Sunzi (6th cent. BC)",
    "Giles, Lionel"
  ],
  "subjects": [
    "Military art and science -- Early works to 1800",
    "War -- Early works to 1800"
  ] 
}

The code does run and parse the RDF file, but has a lot of extra "stuff" I'm not familiar with. I cannot tell whether I'm not using the example code right or whether there is a bug in the book's source code.

The command I use to run the parser is this:

node -e 'require("./lib/rdf-parser.js")("test/pg132.rdf", console.log)'

And I get the following output instead of the expected output above:

null { _id: '132',
  title: 'The Art of War',
  authors:
   { '0': 'Sunzi (6th cent. BC)',
     '1': 'Giles, Lionel',
     options:
      { withDomLvl1: true,
        normalizeWhitespace: false,
        xmlMode: false,
        decodeEntities: true },
     _root: { '0': [Object], options: [Object], length: 1, _root: [Circular] },
     length: 2,
     prevObject:
      { '0': [Object],
        '1': [Object],
        options: [Object],
        _root: [Object],
        length: 2,
        prevObject: [Object] } },
  subjects:
   { options:
      { withDomLvl1: true,
        normalizeWhitespace: false,
        xmlMode: false,
        decodeEntities: true },
     _root: { '0': [Object], options: [Object], length: 1, _root: [Circular] },
     length: 0,
     prevObject:
      { options: [Object],
        _root: [Object],
        length: 0,
        prevObject: [Object] } } }

What is the problem?

Upvotes: 0

Answers (3)

Seth Landsman Ph.D.

Reputation: 11

The new code for rdf-parser.js's last two lines should read:

authors: $('pgterms\\:agent pgterms\\:name').map(collect).get(),
subjects : $('[rdf\\:resource$="/LCSH"]').siblings('rdf\\:value').map(collect).toArray()

Also, as per the author at https://forums.pragprog.com/forums/301/topics/12439, the new example JSON file should read (note the change in the subjects section):

{
 "id": "132",
 "title": "",
 "authors": [
   "Sunzi, active 6th century B.C.",
   "Giles, Lionel"
 ],
 "subjects": [
     "Military art and science -- Early works to 1800"
 ]

}

Upvotes: 0