rdf2json 0.0.1 → 0.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 5b7bc9157133dd33407d3807be8d4e2ae8361424
-  data.tar.gz: 4f22bddd6f50b8708d289f6699eaee564d7a0afe
+  metadata.gz: 229b623b98cb1edf2917e919f28cedaaa40d4405
+  data.tar.gz: e8b2debf2eceff26846ff3e9e1b549f3c188e1b9
 SHA512:
-  metadata.gz: 4c0697837463e626dfc077ba4a0cd27ee7240fe6c3fcfdde29a3708edbf83689901e25f92ae266a8fe9a840fe34f6839c4363502b647fe207ef0fa2042908bb0
-  data.tar.gz: ece185939cd4925b52632ca346653486905b91f185852845e5081dab6ca670de61df858795c2cbad5683bd2ebfaac23f845842185ac323412966ab8afb918b91
+  metadata.gz: fa6329cafa516402423d0f2f4eaef39f0021951951cb4ec8db4034b03338b5e9c4967499fb75aa9068c82b32aae95fb73f82777c738cf702dc3255800e918613
+  data.tar.gz: 74b64a2375e9274e24da1c8b3560fcaffb9b0264b4218ed688f14b095ad948642c9ca92f6e87124d09bc0d1873741598e6b95a38646c75fde2b2e696ffe0681c

data/README.md

@@ -8,6 +8,20 @@ output file.
 
 Usage: `rdf2json [options] --input filename.nt --output filename.json`
 
+#### Preliminaries
+
+RDF N-Triples/N-Quads need to be sorted by subject, so that
+it is possible to output JSON/JSON-LD documents on-the-fly,
+without holding the entire input in memory or falling back to
+time consuming file-pointer seek operations.
+
+Both RDF formats can be sorted on Mac OS X and Linux using the
+following shell command:
+
+```sh
+sort -k 1,1 UNSORTED.EXT > SORTED.EXT
+```
+
 #### Required options
 
 *  `-i`, `--input FILE`: Input file for the conversion; either RDF N-Triples or N-Quads.
@@ -25,6 +39,16 @@ Usage: `rdf2json [options] --input filename.nt --output filename.json`
 
 *  `-h`, `--help`: Show this message.
 
+#### JSON output (`--minimize` option)
+
+*  replaces "@id" keys with an alternative name if the `--namespace` option is present
+*  keys that start with the prefix of `--prefix` are shortened (prefix is removed)
+*  array contents are "lifted up", i.e. for each entry of the array:
+   *  hashes with a "@value" key are replaced by the value of "@value", or else
+   *  hashes with a "@id" key are replaced by the value of "@id", or else
+   *  the array value is left unchanged
+*  removes all "@type" key/value pairs
+
 ## Installation
 
 ```sh

data/VERSION

@@ -1 +1 @@
-0.0.1
+0.0.2

data/lib/rdf2json/rdf2json.rb

@@ -5,8 +5,13 @@ require 'rdf/nquads'
 require 'json/ld'
 require 'optparse'
 
+# Module that contains a class for transforming RDF N-Triples/N-Quads into
+# JSON/JSON-LD as well as a command line interface implementation for user
+# interactions.
 module RDF2JSON
 
+# Command line interface; reads parameters, outputs help, or proceeds with the
+# transformation of RDF N-Triples/N-Quads into JSON/JSON-LD.
 def self.cli
   options = {}
 
@@ -18,6 +23,13 @@ def self.cli
     opts.separator '             append a JSON/JSON-LD document per line in a designated'
     opts.separator '             output file.'
     opts.separator ''
+    opts.separator 'Notes:'
+    opts.separator '             Sorting on Mac OS X & Linux:'
+    opts.separator '               sort -k 1,1 UNSORTED.EXT > SORTED.EXT'
+    opts.separator ''
+    opts.separator '             More information on the --minimize parameter:'
+    opts.separator '               https://github.com/joejimbo/rdf2json'
+    opts.separator ''
     opts.separator 'Required:'
 
     opts.on('-i', '--input FILE', 'Input file for the conversion; either RDF N-Triples or N-Quads.') { |file|
@@ -118,8 +130,19 @@ def self.cli
   end
 end
 
+# Class that takes an input file (RDF N-Triples/N-Quads) and appends JSON/JSON-LD to
+# a possible pre-existing output file. A namespace and prefix can be given that handle
+# `--namespace` and `--prefix` parameters in conjunction with the `--minimize` parameter.
 class Converter
 
+  # Initializes a new converter instance.
+  #
+  # +input_filename+:: path/filename of the input file in RDF N-Triples/N-Quads
+  # +output_filename+:: path/filename of the output file to which JSON/JSON-LD is being appended
+  # +input_format+:: format of the input file (:ntriples or :nquads)
+  # +output_format+:: format of the output (:json or jsonld)
+  # +namespace+:: a possible namespace for replacing "@id" keys (may be nil)
+  # +prefix+:: a possible prefix for shortening keys (may be nil)
   def initialize(input_filename, output_filename, input_format, output_format, namespace, prefix)
     @input_file = File.open(input_filename, 'r')
     @output_file = File.open(output_filename, 'a')
@@ -129,6 +152,12 @@ class Converter
     @prefix = prefix
   end
 
+  # Convert the input file by appending the newly formatted data to the output file.
+  #
+  # At the end of the conversion a short statistic is output. It tells the number of
+  # lines read from the input file, the number of errors in the N-Triples/N-Quads file,
+  # the number of JSON/JSON-LD documents appended to the output file (equiv. to number
+  # of lines appended).
   def convert
     no_of_lines = 0
     no_of_statements = 0
@@ -163,6 +192,9 @@ class Converter
     puts "JSON/JSON-LD documents output                : #{no_of_statements}"
   end
 
+  # Minimize a JSON-LD hash to JSON.
+  #
+  # +jsonld_hash+:: a JSON-LD hash that should be rewritten to plain JSON
   def minify(jsonld_hash)
     jsonld_hash.keys.each { |key|
       if key == '@type' then
@@ -187,9 +219,14 @@ class Converter
     }
   end
 
+  # Takes a block of RDF statements that share the same subject and creates
+  # a JSON/JSON-LD document from them, which is appended to the output file.
+  #
+  # +block+:: one or more lines that share the same subject in RDF N-Triples/N-Quads
   def write_graph(block)
     return { :read_errors => 0, :no_of_statements => 0 } unless block and not block.empty?
 
+    # Virtuoso output error-handling:
     block.gsub!("\\'", "'")
 
     read_errors = 0

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rdf2json
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors:
 - Joachim Baran
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-05-20 00:00:00.000000000 Z
+date: 2014-05-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rdf
@@ -117,14 +117,12 @@ extensions: []
 extra_rdoc_files:
 - LICENSE.txt
 - README.md
-- README.rdoc
 files:
 - .document
 - .travis.yml
 - Gemfile
 - LICENSE.txt
 - README.md
-- README.rdoc
 - Rakefile
 - VERSION
 - lib/rdf2json.rb

data/README.rdoc

@@ -1,48 +0,0 @@
-= bio-rdf2json
-
-{<img
-src="https://secure.travis-ci.org/joejimbo/bioruby-rdf2json.png"
-/>}[http://travis-ci.org/#!/joejimbo/bioruby-rdf2json]
-
-Full description goes here
-
-Note: this software is under active development!
-
-== Installation
-
-        gem install bio-rdf2json
-
-== Usage
-
-== Developers
-
-To use the library 
-
-        require 'bio-rdf2json'
-
-The API doc is online. For more code examples see also the test files in
-the source tree.
-        
-== Project home page
-
-Information on the source tree, documentation, issues and how to contribute, see
-
-  http://github.com/joejimbo/bioruby-rdf2json
-
-The BioRuby community is on IRC server: irc.freenode.org, channel: #bioruby.
-
-== Cite
-
-  If you use this software, please cite one of
- 
-* [BioRuby: bioinformatics software for the Ruby programming language](http://dx.doi.org/10.1093/bioinformatics/btq475)
-* [Biogem: an effective tool-based approach for scaling up open source software development in bioinformatics](http://dx.doi.org/10.1093/bioinformatics/bts080)
-
-== Biogems.info
-
-This Biogem is published at http://biogems.info/index.html#bio-rdf2json
-
-== Copyright
-
-Copyright (c) 2014 Joachim Baran. See LICENSE.txt for further details.
-