Purée

Metadata extraction from the Pure Research Information System.

Status

Installation

Add this line to your application's Gemfile:

gem 'puree'

And then execute:

$ bundle

Or install it yourself as:

$ gem install puree

Configuration

# For Extractor and REST modules.
config = {
  url:      'https://YOUR_HOST/ws/api/59',
  username: 'YOUR_USERNAME',
  password: 'YOUR_PASSWORD',
  api_key:  'YOUR_API_KEY'
}

Extractor module

Find a resource by identifier and get Ruby objects.

# Configure an extractor
extractor = Puree::Extractor::Dataset.new config

# Fetch the metadata for a resource with a particular identifier
dataset = extractor.find 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx'
#=> #<Puree::Model::Dataset:0x00c0ffee>

# Access specific metadata e.g. an internal person's name
dataset.persons_internal[0].name
#=> #<Puree::Model::PersonName:0x00c0ffee @first="Foo", @last="Bar">

# Select a formatting style for a person's name
dataset.persons_internal[0].name.last_initial
#=> "Bar, F."

XMLExtractor module

Get Ruby objects from Pure XML.

Single resource

xml = '<project> ... </project>'

# Configure an XML extractor
xml_extractor = Puree::XMLExtractor::Project.new xml

# Get a single piece of metadata
xml_extractor.title
#=> "An interesting project title"

# Get all the metadata together
xml_extractor.model
#=> #<Puree::Model::Project:0x00c0ffee>

Homogeneous resource collection

xml = '<result>
        <dataSet> ... </dataSet>
        <dataSet> ... </dataSet>
        ...
      </result>'

# Get an array of datasets
Puree::XMLExtractor::Collection.datasets xml
#=> [#<Puree::Model::Dataset:0x00c0ffee>, ...]

Heterogeneous resource collection

xml = '<result>
        <contributionToJournal> ... </contributionToJournal>
        <contributionToConference> ... </contributionToConference>
        ...
      </result>'

# Get a hash of research outputs
Puree::XMLExtractor::Collection.research_outputs xml
#=> {
#     journal_articles: [#<Puree::Model::JournalArticle:0x00c0ffee>, ...],
#     conference_papers: [#<Puree::Model::ConferencePaper:0x00c0ffee>, ...],
#     theses: [#<Puree::Model::Thesis:0x00c0ffee>, ...],
#     other: [#<Puree::Model::ResearchOutput:0x00c0ffee>, ...]
#   }

REST module

Query the Pure REST API.

Client

# Configure a client
client = Puree::REST::Client.new config

# Find a person
client.persons.find id: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx'
#=> #<HTTP::Response:0x00c0ffee>

# Find a person, limit the metadata to ORCID and employee start date
client.persons.find id: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx',
                    params: {fields: ['orcid', 'employeeStartDate']}
#=> #<HTTP::Response:0x00c0ffee>

# Find five people, response body as JSON
client.persons.all params: {size: 5}, accept: :json
#=> #<HTTP::Response:0x00c0ffee>

# Find research outputs for a person
client.persons.research_outputs id: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx'
#=> #<HTTP::Response:0x00c0ffee>

Resource

# Configure a resource
persons = Puree::REST::Person.new config

# Find a person
persons.find id: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx'
#=> #<HTTP::Response:0x00c0ffee>

REST module with XMLExtractor module

Query the Pure REST API and get Ruby objects from Pure XML.

# Configure a client
client = Puree::REST::Client.new config

# Find projects for a person
response = client.persons.projects id: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx'

# Extract metadata from XML
Puree::XMLExtractor::Collection.projects response.to_s
#=> [#<Puree::Model::Project:0x00c0ffee>, ...]