bergamasco 0.1.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 1397e1d71f822e2ba31fb055cae298505fe60d92
+  data.tar.gz: 1928b970eed69989858bf680b6290151ec42539d
+SHA512:
+  metadata.gz: 2604ab9dcd36d6e2670ec41392fe27aa308252a93ddaaad7faed930591dd5be15c4e52dd6a156f826a78846f6aed24a93dcdb56b301ab94a227cdb01e4396b91
+  data.tar.gz: 677df10181be5b8a3b47fc4a78c2d5f768640c7339b7d52f6696d692b51bc37fefecf5c81c6b8ce9f0142f3c413d8c3702bdee12014a6620e29cddd367459d04

data/.gitignore

@@ -0,0 +1,50 @@
+*.gem
+*.rbc
+/.config
+/coverage/
+/InstalledFiles
+/pkg/
+/spec/reports/
+/spec/examples.txt
+/test/tmp/
+/test/version_tmp/
+/tmp/
+
+# Used by dotenv library to load environment variables.
+# .env
+
+## Specific to RubyMotion:
+.dat*
+.repl_history
+build/
+*.bridgesupport
+build-iPhoneOS/
+build-iPhoneSimulator/
+
+## Specific to RubyMotion (use of CocoaPods):
+#
+# We recommend against adding the Pods directory to your .gitignore. However
+# you should judge for yourself, the pros and cons are mentioned at:
+# https://guides.cocoapods.org/using/using-cocoapods.html#should-i-check-the-pods-directory-into-source-control
+#
+# vendor/Pods/
+
+## Documentation cache and generated files:
+/.yardoc/
+/_yardoc/
+/doc/
+/rdoc/
+
+## Environment normalization:
+/.bundle/
+/vendor/bundle
+/lib/bundler/man/
+
+# for a library or gem, you might want to ignore these files since the code is
+# intended to run in multiple environments; otherwise, check them in:
+# Gemfile.lock
+# .ruby-version
+# .ruby-gemset
+
+# unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
+.rvmrc

data/.travis.yml

@@ -0,0 +1,26 @@
+language: ruby
+rvm:
+- 2.3.1
+
+before_install:
+  - sudo add-apt-repository ppa:kalakris/cmake -y
+  - sudo apt-get update -q
+  - sudo apt-get install cmake -y
+
+install:
+- travis_retry bundle install
+
+script: bundle exec rspec
+
+notifications:
+  slack: "$SLACK_TOKEN"
+  email: false
+
+deploy:
+  provider: rubygems
+  api_key:
+    secure: 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
+  gem: bergamasco
+  on:
+    tags: true
+    repo: datacite/bergamasco

data/Gemfile

@@ -0,0 +1,3 @@
+source 'https://rubygems.org'
+
+gemspec

data/Gemfile.lock

@@ -0,0 +1,80 @@
+PATH
+  remote: .
+  specs:
+    bergamasco (0.1.1)
+      activesupport (~> 4.2, >= 4.2.5)
+      builder (~> 3.2, >= 3.2.2)
+      commonmarker (~> 0.14.0)
+      loofah (~> 2.0, >= 2.0.3)
+      multi_json (~> 1.11.2)
+      nokogiri (~> 1.6.7)
+      oj (~> 2.13.1)
+      pandoc-ruby (~> 2.0, >= 2.0.0)
+      safe_yaml (~> 1.0, >= 1.0.4)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    activesupport (4.2.7.1)
+      i18n (~> 0.7)
+      json (~> 1.7, >= 1.7.7)
+      minitest (~> 5.1)
+      thread_safe (~> 0.3, >= 0.3.4)
+      tzinfo (~> 1.1)
+    builder (3.2.2)
+    codeclimate-test-reporter (1.0.3)
+      simplecov
+    commonmarker (0.14.0)
+      ruby-enum (~> 0.4)
+    diff-lcs (1.2.5)
+    docile (1.1.5)
+    i18n (0.7.0)
+    json (1.8.3)
+    loofah (2.0.3)
+      nokogiri (>= 1.5.9)
+    mini_portile2 (2.1.0)
+    minitest (5.10.1)
+    multi_json (1.11.3)
+    nokogiri (1.6.8.1)
+      mini_portile2 (~> 2.1.0)
+    oj (2.13.1)
+    pandoc-ruby (2.0.1)
+    rake (12.0.0)
+    rspec (3.5.0)
+      rspec-core (~> 3.5.0)
+      rspec-expectations (~> 3.5.0)
+      rspec-mocks (~> 3.5.0)
+    rspec-core (3.5.4)
+      rspec-support (~> 3.5.0)
+    rspec-expectations (3.5.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.5.0)
+    rspec-mocks (3.5.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.5.0)
+    rspec-support (3.5.0)
+    ruby-enum (0.6.0)
+      i18n
+    safe_yaml (1.0.4)
+    simplecov (0.12.0)
+      docile (~> 1.1.0)
+      json (>= 1.8, < 3)
+      simplecov-html (~> 0.10.0)
+    simplecov-html (0.10.0)
+    thread_safe (0.3.5)
+    tzinfo (1.2.2)
+      thread_safe (~> 0.1)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bergamasco!
+  bundler (~> 1.0)
+  codeclimate-test-reporter (~> 1.0.0)
+  rake
+  rspec (~> 3.4)
+  simplecov
+
+BUNDLED WITH
+   1.13.6

data/LICENSE.md

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2016 DataCite
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

data/README.md

@@ -0,0 +1,32 @@
+# Bergamasco
+
+[![Gem Version](https://badge.fury.io/rb/bergamasco.svg)](https://badge.fury.io/rb/bergamasco)
+[![Build Status](https://travis-ci.org/datacite/bergamasco.svg?branch=master)](https://travis-ci.org/datacite/bergamasco)
+[![Test Coverage](https://codeclimate.com/github/datacite/bergamasco/badges/coverage.svg)](https://codeclimate.com/github/datacite/bergamasco/coverage)
+[![Code Climate](https://codeclimate.com/github/datacite/bergamasco/badges/gpa.svg)](https://codeclimate.com/github/datacite/bergamasco)
+
+Text utilities for common cleanup and reformatting tasks when working with scholarly metadata.
+
+## Installation
+
+The usual way with Bundler: add the following to your `Gemfile` to install the current version of the gem:
+
+```ruby
+gem 'bergamasco'
+```
+
+Then run `bundle install` to install into your environment.
+
+You can also install the gem system-wide in the usual way:
+
+```bash
+gem install bergamasco
+```
+
+## Usage
+
+TBD.
+
+## License
+
+[MIT](license.md)

data/Rakefile

@@ -0,0 +1,5 @@
+#!/usr/bin/env rake
+
+# Get useful helper tasks from Bundler
+require "bundler/gem_tasks"
+

data/bergamasco.gemspec

@@ -0,0 +1,35 @@
+require "date"
+require File.expand_path("../lib/bergamasco/version", __FILE__)
+
+Gem::Specification.new do |s|
+  s.authors       = "Martin Fenner"
+  s.email         = "mfenner@datacite.org"
+  s.name          = "bergamasco"
+  s.homepage      = "https://github.com/datacite/bergamasco"
+  s.summary       = "Text utilities for working with scholarly metadata"
+  s.date          = Date.today
+  s.description   = "Text utilities for common cleanup and reformatting tasks when working with scholarly metadata"
+  s.require_paths = ["lib"]
+  s.version       = Bergamasco::VERSION
+  s.extra_rdoc_files = ["README.md"]
+  s.license       = 'MIT'
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.require_paths = ["lib"]
+
+  s.add_dependency 'nokogiri', '~> 1.6.7'
+  s.add_dependency 'loofah', '~> 2.0', '>= 2.0.3'
+  s.add_dependency "pandoc-ruby", '~> 2.0', '>= 2.0.0'
+  s.add_dependency 'builder', '~> 3.2', '>= 3.2.2'
+  s.add_dependency 'multi_json', '~> 1.11.2'
+  s.add_dependency 'oj', '~> 2.13.1'
+  s.add_dependency 'activesupport', '~> 4.2', '>= 4.2.5'
+  s.add_dependency 'safe_yaml', '~> 1.0', '>= 1.0.4'
+  s.add_dependency 'commonmarker', '~> 0.14.0'
+  s.add_development_dependency 'bundler', '~> 1.0'
+  s.add_development_dependency 'rspec', '~> 3.4'
+  s.add_development_dependency 'rake'
+  s.add_development_dependency 'codeclimate-test-reporter', "~> 1.0.0"
+  s.add_development_dependency 'simplecov'
+end

data/lib/bergamasco.rb

@@ -0,0 +1,12 @@
+require 'active_support/all'
+require 'json'
+require 'nokogiri'
+require 'yaml'
+require 'safe_yaml/load'
+require 'loofah'
+require 'commonmarker'
+
+require "bergamasco/summarize"
+require "bergamasco/sanitize"
+require "bergamasco/markdown"
+require "bergamasco/whitelist_scrubber"

data/lib/bergamasco/markdown.rb

@@ -0,0 +1,32 @@
+module Bergamasco
+  module Markdown
+    # split file into YAML frontmatter and content
+    YAML_FRONT_MATTER_REGEXP = /\A(---\s*\n.*?\n?)^((---|\.\.\.)\s*$\n?)/m
+
+    def self.split_yaml_frontmatter(file)
+      metadata = SafeYAML.load(file)
+      content = YAML_FRONT_MATTER_REGEXP.match(file).post_match
+      [metadata, content]
+    end
+
+    def self.update_yaml_frontmatter(metadata, new_metadata)
+      metadata.merge(new_metadata).compact
+    end
+
+    def self.join_yaml_frontmatter(metadata, content)
+      metadata.to_yaml + "---\n" + content
+    end
+
+    def self.update_file(file, new_metadata)
+      metadata, content = split_yaml_frontmatter(file)
+      metadata = update_yaml_frontmatter(metadata, new_metadata)
+      join_yaml_frontmatter(metadata, content)
+    end
+
+    def self.render_html(text, options={})
+      text = split_yaml_frontmatter(text).last if options[:skip_yaml_header]
+
+      CommonMarker.render_html(text, :default)
+    end
+  end
+end

data/lib/bergamasco/sanitize.rb

@@ -0,0 +1,12 @@
+module Bergamasco
+  module Sanitize
+    ALLOWED_TAGS = Set.new(%w(strong em b i code pre sub sup br))
+
+    def self.sanitize(text, options={})
+      options[:tags] ||= ALLOWED_TAGS
+      custom_scrubber = Bergamasco::WhitelistScrubber.new(options)
+
+      Loofah.scrub_fragment(text, custom_scrubber).to_s
+    end
+  end
+end

data/lib/bergamasco/summarize.rb

@@ -0,0 +1,75 @@
+module Bergamasco
+  module Summarize
+    # based on from https://github.com/middleman/middleman-blog/blob/master/lib/middleman-blog/blog_article.rb
+    def self.summary(text, options={})
+      if options[:separator]
+        truncate_at_separator(text, options[:separator])
+      else
+        max_length = options[:length] || 250
+        ellipsis = options[:ellipsis] || "..."
+        truncate_at_length(text, max_length, ellipsis)
+      end
+    end
+
+    # from https://github.com/middleman/middleman-blog/blob/master/lib/middleman-blog/truncate_html.rb
+    def self.truncate_at_separator(text, separator)
+      text = text.encode('UTF-8') if text.respond_to?(:encode)
+      doc = Nokogiri::HTML::DocumentFragment.parse text.split(separator).first
+      doc.inner_html
+    end
+
+    # from https://github.com/middleman/middleman-blog/blob/master/lib/middleman-blog/truncate_html.rb
+    def self.truncate_at_length(text, max_length, ellipsis = "...")
+      ellipsis_length = ellipsis.length
+      text = text.encode('UTF-8') if text.respond_to?(:encode)
+      doc = Nokogiri::HTML::DocumentFragment.parse text
+      content_length = doc.inner_text.length
+      actual_length = max_length - ellipsis_length
+      if content_length > actual_length
+        doc.truncate(actual_length, ellipsis).inner_html
+      else
+        text
+      end
+    end
+  end
+end
+
+# from https://github.com/middleman/middleman-blog/blob/master/lib/middleman-blog/truncate_html.rb
+module NokogiriTruncator
+  module NodeWithChildren
+    def truncate(max_length, ellipsis)
+      return self if inner_text.length <= max_length
+      truncated_node = self.dup
+      truncated_node.children.remove
+
+      self.children.each do |node|
+        remaining_length = max_length - truncated_node.inner_text.length
+        break if remaining_length <= 0
+        truncated_node.add_child node.truncate(remaining_length, ellipsis)
+      end
+      truncated_node
+    end
+  end
+
+  module TextNode
+    def truncate(max_length, ellipsis)
+      # Don't break in the middle of a word
+      trimmed_content = content.match(/(.{1,#{max_length}}[\w]*)/m).to_s
+      trimmed_content << ellipsis if trimmed_content.length < content.length
+
+      Nokogiri::XML::Text.new(trimmed_content, parent)
+    end
+  end
+
+  module CommentNode
+    def truncate(*args)
+      # Don't truncate comments, since they aren't visible
+      self
+    end
+  end
+end
+
+Nokogiri::HTML::DocumentFragment.send(:include, NokogiriTruncator::NodeWithChildren)
+Nokogiri::XML::Element.send(:include, NokogiriTruncator::NodeWithChildren)
+Nokogiri::XML::Text.send(:include, NokogiriTruncator::TextNode)
+Nokogiri::XML::Comment.send(:include, NokogiriTruncator::CommentNode)

data/lib/bergamasco/version.rb

@@ -0,0 +1,3 @@
+module Bergamasco
+  VERSION = "0.1.1"
+end

data/lib/bergamasco/whitelist_scrubber.rb

@@ -0,0 +1,45 @@
+# modified from https://gist.github.com/ivan-kolmychek/ee2fdc53f3e2c637271d
+
+module Bergamasco
+  class WhitelistScrubber < Loofah::Scrubber
+    def initialize(options={})
+      @direction = :bottom_up
+      @tags = options[:tags]
+      @attributes = options[:attributes]
+    end
+
+    def scrub(node)
+      scrub_node_attributes(node) and return CONTINUE if node_allowed?(node)
+      node.before node.children
+      node.remove
+    end
+
+    private
+
+    def scrub_node_attributes(node)
+      fallback_scrub_node_attributes(node) and return true unless @attributes.present? && @attributes.respond_to?(:include?)
+      node.attribute_nodes.each do |attr_node|
+        attr_node.remove unless @attributes.include?(attr_node.name)
+      end
+    end
+
+    def allowed_not_element_node_types
+      [ Nokogiri::XML::Node::TEXT_NODE, Nokogiri::XML::Node::CDATA_SECTION_NODE ]
+    end
+
+    def fallback_scrub_node_attributes(node)
+      Loofah::HTML5::Scrub.scrub_attributes(node)
+    end
+
+    def fallback_allowed_element_detection(node)
+      Loofah::HTML5::Scrub.allowed_element?(node.name)
+    end
+
+    def node_allowed?(node)
+      return fallback_allowed_element_detection(node) unless @tags.present? && @tags.respond_to?(:include?)
+      return true if allowed_not_element_node_types.include?(node.type)
+      return false unless node.type == Nokogiri::XML::Node::ELEMENT_NODE
+      @tags.include? node.name
+    end
+  end
+end

data/spec/fixtures/abstract.tex

@@ -0,0 +1 @@
+CERN-LHC. A first measurement is presented of the top quark mass using the decay channel $\text{t}\to(\text{W}\to\ell\nu)\,(\text{b}\to\text{J}/\psi+\text{X}\to\mu^+\mu^-+\text{X})$, in events selected in proton-proton collisions and recorded with the CMS detector at the LHC at a center-of-mass energy of 8 TeV. The data correspond to an integrated luminosity of 19.7 /fb, with 666 $\text{t}\bar{\text{t}}$ and single top quark candidate events containing a reconstructed J/$\psi$ candidate decaying into an oppositely-charged muon pair. The top quark mass is extracted from an unbinned maximum-likelihood fit to the invariant mass of the (J/$\psi$+$\ell$) system, where $\ell$ is an electron or a muon from W boson decay. The resulting top quark mass measurement is 173.5 $\pm$ 3.0(stat) $\pm$ 0.9(syst) GeV. Even though the results are statistically limited, the dominant systematic uncertainties are different from those of the most precise direct reconstruction methods. As the sensitivity to jet-related uncertainties is negligible, this allows the possibility to contribute significantly in combination with other top quark mass measurements. Furthermore, with the larger data set expected in the next runs of the LHC, the method described in this paper will provide a result which will be more competitive with those obtained from the conventional reconstruction techniques.

data/spec/fixtures/cool-dois-without-yml.md

@@ -0,0 +1,87 @@
+In 1998 Tim Berners-Lee coined the term cool URIs [-@https://www.w3.org/Provider/Style/URI], that is URIs that don’t change. We know that URLs referenced in the scholarly literature are often not cool, leading to link rot [@https://doi.org/10.1371/journal.pone.0115253] and making it hard or impossible to find the referenced resource.READMORE
+
+Cool URIs are, of course, a fundamental principle behind DOIs, with the two important concepts [*resolution*](https://www.doi.org/doi_handbook/3_Resolution.html) (it is very hard to maintain a URL directly pointing at a resource) and [*policies*](https://www.doi.org/doi_handbook/6_Policies.html) (that all DOI registration agencies and organizations minting DOIs agree to maintain the redirection). The third essential element for DOIs, their [*data model*](https://www.doi.org/doi_handbook/4_Data_Model.html), is not directly about persistent linking, but about the discoverability of the linked resources via standard metadata in a central index.
+
+All DOIs, expressed as HTTP URI, are therefore cool URIs. So what is a cool DOI? And, furthermore, how to create and use them? To understand what a cool DOI is, we have to explain the three parts that make up a DOI:
+
+![](/images/2016/12/doi-parts.png)
+
+### Proxy
+
+The proxy is not part of the DOI specification, but almost all scholarly DOIs that users encounter today will be expressed as HTTP URLs. DataCite recommends that all DOIs are displayed as permanent URLs, consistent with the recommendations of other DOI registration agencies, e.g. the [Crossref DOI display guidelines](http://www.crossref.org/02publishers/doi_display_guidelines.html). When the DOI system was originally designed, it was thought that the DOI protocol would become widely used, but that clearly has not happened and displaying DOIs as **doi:10.5281/ZENODO.31780** is therefore not recommended.
+
+The DOI proxy enables the functionality of expressing DOIs as HTTP URIs. Users should also be aware of two these two recommendations:
+
+* Use [doi.org](https://www.doi.org/doi_proxy/proxy_policies.html) instead of dx.doi.org as DNS name
+* Use the HTTPS protocol instead of HTTP protocol
+
+Ed Pentz from Crossref makes the case for HTTPS in a [September blog post](http://blog.crossref.org/2016/09/new-crossref-doi-display-guidelines.html). The web, and therefore also the scholarly web, is moving to HTTPS as the default. It is important that the DOI proxy redirects to HTTPS URLs, and it will take some time until all DataCite data centers use HTTPS for the landing pages their DOIs redirects to.
+
+What many users don’t know is that doi.org is not the only proxy server for DOIs. DOIs use the handle system and any handle server will resolve a DOI, just as doi.org will resolve any handle. This means that [https://hdl.handle.net/10.5281/ZENODO.31780](https://hdl.handle.net/10.5281/ZENODO.31780) will resolve to the landing page for that DOI and that [http://doi.org/10273/BGRB5054RX05201](http://doi.org/10273/BGRB5054RX05201) is a handle (for a [IGSN](http://www.igsn.org/)) and not a DOI.
+
+### Prefix
+
+The DOI prefix is used as a namespace so that DOIs are globally unique without requiring global coordination for every new identifier. Prefixes in the handle system and therefore for DOIs are numbers without any semantic meaning. One lesson learned with persistent identifiers is that adding meaning to the identifier (e.g. by using a prefix with the name of the data repository) is always dangerous, because – despite best intentions – all names can change over time.
+
+Since the DOI prefix is a namespace to keep DOIs globally unique, there is usually no need for multiple prefixes for one organization managing DOI assignment. The tricky part is that these responsibilities can change, e.g. when an organization manages multiple repositories and one of them is migrated to another organization. It therefore makes sense to assign one prefix per list of resources that always stays together, e.g. one repository. It is possible that one prefix is managed by multiple organizations (as long as they use the same DOI registration agency), but that makes DOI management more complex.
+
+### Suffix
+
+The suffix for a DOI can be (almost) any string. Which is both a feature and a curse. It is a feature because it gives maximal flexibility, for example when migrating existing identifiers to the DOI system. And it is a curse because it not always works well in the web context, as the list of characters allowed in a URL is limited. A good example of this are SICIs ([Serial Item and Contribution Identifier](https://en.wikipedia.org/wiki/Serial_Item_and_Contribution_Identifier)), they were defined in 1996 before the DOI system was implemented, and could then be migrated to DOIs. Unfortunately they can contain many characters that are problematic in a URL or make it difficult to validate the DOI, as in [https://doi.org/10.1002/(sici)1099-1409(199908/10)3:6/7<672::aid-jpp192>3.0.co;2-8](https://doi.org/10.1002/(sici)1099-1409(199908/10)3:6/7<672::aid-jpp192>3.0.co;2-8). A Crossref [blog post](http://blog.crossref.org/2015/08/doi-regular-expressions.html) by Andrew Gilmartin gives a good overview about the characters found in DOIs and suggests the following regular expression to check for valid DOIs:
+
+```
+/^10.\d{4,9}/[-._;()/:A-Z0-9]+$/i
+```
+
+SICIs demonstrate two other pitfalls:
+
+* they contain semantic information (ISSN, volume, number, etc.) that may change over time, and
+* they are long, difficult to transcribe, with characters not allowed in URLs, and not very human-readable.
+
+Semantic information might also lead users to expect certain functionalities. A common pattern that we see at DataCite is to include information about the version or parent in the suffix, e.g. [https://doi.org/10.6084/M9.FIGSHARE.3501629.V1](https://doi.org/10.6084/M9.FIGSHARE.3501629.V1) or [https://doi.org/10.5061/DRYAD.0SN63/7](https://doi.org/10.5061/DRYAD.0SN63/7). While the decision on what to put into the suffix is up to each data center, we should make sure users don't think that these are functionalities of the DOI system (e.g. that adding **.V2** to any DOI name will resolve to version 2 of that resource).
+
+Another issue to keep in mind when assigning suffixes is that DOIs – in contrast to HTTP URIs – are case-insensitive, [https://doi.org/10.5281/ZENODO.31780](https://doi.org/10.5281/ZENODO.31780) and [https://doi.org/10.5281/zenodo.31780](https://doi.org/10.5281/zenodo.31780) are the same DOI. All DOIs are [converted to upper case](https://www.doi.org/doi_handbook/2_Numbering.html#2.4) upon registration and DOI resolution, but DOIs are not consistently displayed in such a way.
+
+### Generating cool DOIs
+
+With all that, what should the ideal DOI look like? Its suffix should be:
+
+* opaque without semantic information
+* work well in a web environment, avoiding characters problematic in URLs
+* short and human-readable
+* Resistant to transcription errors
+* easy to generate
+
+On Tuesday DataCite released a tool that helps generating such a suffix, an open source command line tool called [cirneco](https://github.com/datacite/cirneco) (a lot of our open source software uses Italian dog breed names). Cirneco is a Ruby gem that can be installed via
+
+```
+gem install cirneco
+```
+
+Cirneco uses base32 encoding, as [described](http://www.crockford.com/wrmg/base32.html) by Douglas Crockford. The encoding starts with a randomly generated number to guarantee uniqueness of the identifier, and then encodes the number into a string that uses all numbers and uppercase letters. It avoids the letters I, O and L as they can be confused with the letter 1 and 0, using 32 characters (and 5 checksum characters) in total. The last character is a checksum. The resulting string from cirneco always has a length of 8 characters, in groups of 4 separated by a hyphen to help with readability. The advantage of base32 encoding over using only numbers (as for example ORCID is doing) is that the resulting string becomes much more compact, the available 7 characters (plus one for the checksum) can encode 34,359,738,367 strings, compared to 10 million when only using numbers. This number is large enough that the resulting suffix will not only be unique for a given prefix, but also unique for all DOIs (there is a very small chance to get the same random number twice, but this will be rejected when trying to register the DOI).
+
+Another common way to generate random strings would have been universally unique identifiers ([UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier)), but they are long and not very human-readable, e.g. [https://doi.org/10.4233/UUID:6D192FE2-DE18-4556-873A-D3CD56AB96A6](https://doi.org/10.4233/UUID:6D192FE2-DE18-4556-873A-D3CD56AB96A6).
+
+An example DOI generated by cirneco would be
+
+```
+cirneco doi generate --prefix 10.5555
+10.5555/KVTD-VPWM
+```
+
+The generated DOI is short enough that it should work well in places where space is limited, providing an alternative to the [ShortDOI](http://shortdoi.org/) service which shortens existing DOIs, but does this by adding another layer on top of the DOI proxy.
+
+Another cirneco command checks that this is a valid bas32 string using the checksum
+
+```
+cirneco doi check 10.5555/KVTD-VPWM
+Checksum for 10.5555/KVTD-VPWM is valid
+```
+
+This can be used to quickly verify a DOI, e.g. in a web form or API. The Ruby base32 encoding library used by cirneco is open source ([https://github.com/datacite/base32](https://github.com/datacite/base32). I added the checksum to the existing library), and implementations of the Crockford base32 encoding pattern are available in many other languages, including [Python](https://github.com/jbittel/base32-crockford), [PHP](https://github.com/dflydev/dflydev-base32-crockford), [Javascript](https://www.npmjs.com/package/base32-crockford), [Java](http://stackoverflow.com/questions/22385467/crockford-base32-encoding-for-large-number-java-implementation), [Go](https://github.com/richardlehane/crock32) and [.NET](https://crockfordbase32.codeplex.com/).
+
+To answer the question raised at the beginning: a cool DOI is a DOI expressed as HTTPS URI using the doi.org proxy and using a base32-encoded suffix, for example **https://doi.org/10.5555/KVTD-VPWM**. This DOI works well in a web environment, is human readable, easy to parse and detect (e.g. in text mining), and can be generated using an algorithm that is well understood and supported.
+
+![](/images/2016/12/cool-dois.png)
+
+### References

data/spec/fixtures/cool-dois.html.md

@@ -0,0 +1,97 @@
+---
+layout: post
+title: Cool DOI's
+author: mfenner
+date: 2016-12-15
+tags:
+- doi
+- featured
+image: https://blog.datacite.org/images/2016/12/cool-dois.png
+---
+In 1998 Tim Berners-Lee coined the term cool URIs [-@https://www.w3.org/Provider/Style/URI], that is URIs that don’t change. We know that URLs referenced in the scholarly literature are often not cool, leading to link rot [@https://doi.org/10.1371/journal.pone.0115253] and making it hard or impossible to find the referenced resource.READMORE
+
+Cool URIs are, of course, a fundamental principle behind DOIs, with the two important concepts [*resolution*](https://www.doi.org/doi_handbook/3_Resolution.html) (it is very hard to maintain a URL directly pointing at a resource) and [*policies*](https://www.doi.org/doi_handbook/6_Policies.html) (that all DOI registration agencies and organizations minting DOIs agree to maintain the redirection). The third essential element for DOIs, their [*data model*](https://www.doi.org/doi_handbook/4_Data_Model.html), is not directly about persistent linking, but about the discoverability of the linked resources via standard metadata in a central index.
+
+All DOIs, expressed as HTTP URI, are therefore cool URIs. So what is a cool DOI? And, furthermore, how to create and use them? To understand what a cool DOI is, we have to explain the three parts that make up a DOI:
+
+![](/images/2016/12/doi-parts.png)
+
+### Proxy
+
+The proxy is not part of the DOI specification, but almost all scholarly DOIs that users encounter today will be expressed as HTTP URLs. DataCite recommends that all DOIs are displayed as permanent URLs, consistent with the recommendations of other DOI registration agencies, e.g. the [Crossref DOI display guidelines](http://www.crossref.org/02publishers/doi_display_guidelines.html). When the DOI system was originally designed, it was thought that the DOI protocol would become widely used, but that clearly has not happened and displaying DOIs as **doi:10.5281/ZENODO.31780** is therefore not recommended.
+
+The DOI proxy enables the functionality of expressing DOIs as HTTP URIs. Users should also be aware of two these two recommendations:
+
+* Use [doi.org](https://www.doi.org/doi_proxy/proxy_policies.html) instead of dx.doi.org as DNS name
+* Use the HTTPS protocol instead of HTTP protocol
+
+Ed Pentz from Crossref makes the case for HTTPS in a [September blog post](http://blog.crossref.org/2016/09/new-crossref-doi-display-guidelines.html). The web, and therefore also the scholarly web, is moving to HTTPS as the default. It is important that the DOI proxy redirects to HTTPS URLs, and it will take some time until all DataCite data centers use HTTPS for the landing pages their DOIs redirects to.
+
+What many users don’t know is that doi.org is not the only proxy server for DOIs. DOIs use the handle system and any handle server will resolve a DOI, just as doi.org will resolve any handle. This means that [https://hdl.handle.net/10.5281/ZENODO.31780](https://hdl.handle.net/10.5281/ZENODO.31780) will resolve to the landing page for that DOI and that [http://doi.org/10273/BGRB5054RX05201](http://doi.org/10273/BGRB5054RX05201) is a handle (for a [IGSN](http://www.igsn.org/)) and not a DOI.
+
+### Prefix
+
+The DOI prefix is used as a namespace so that DOIs are globally unique without requiring global coordination for every new identifier. Prefixes in the handle system and therefore for DOIs are numbers without any semantic meaning. One lesson learned with persistent identifiers is that adding meaning to the identifier (e.g. by using a prefix with the name of the data repository) is always dangerous, because – despite best intentions – all names can change over time.
+
+Since the DOI prefix is a namespace to keep DOIs globally unique, there is usually no need for multiple prefixes for one organization managing DOI assignment. The tricky part is that these responsibilities can change, e.g. when an organization manages multiple repositories and one of them is migrated to another organization. It therefore makes sense to assign one prefix per list of resources that always stays together, e.g. one repository. It is possible that one prefix is managed by multiple organizations (as long as they use the same DOI registration agency), but that makes DOI management more complex.
+
+### Suffix
+
+The suffix for a DOI can be (almost) any string. Which is both a feature and a curse. It is a feature because it gives maximal flexibility, for example when migrating existing identifiers to the DOI system. And it is a curse because it not always works well in the web context, as the list of characters allowed in a URL is limited. A good example of this are SICIs ([Serial Item and Contribution Identifier](https://en.wikipedia.org/wiki/Serial_Item_and_Contribution_Identifier)), they were defined in 1996 before the DOI system was implemented, and could then be migrated to DOIs. Unfortunately they can contain many characters that are problematic in a URL or make it difficult to validate the DOI, as in [https://doi.org/10.1002/(sici)1099-1409(199908/10)3:6/7<672::aid-jpp192>3.0.co;2-8](https://doi.org/10.1002/(sici)1099-1409(199908/10)3:6/7<672::aid-jpp192>3.0.co;2-8). A Crossref [blog post](http://blog.crossref.org/2015/08/doi-regular-expressions.html) by Andrew Gilmartin gives a good overview about the characters found in DOIs and suggests the following regular expression to check for valid DOIs:
+
+```
+/^10.\d{4,9}/[-._;()/:A-Z0-9]+$/i
+```
+
+SICIs demonstrate two other pitfalls:
+
+* they contain semantic information (ISSN, volume, number, etc.) that may change over time, and
+* they are long, difficult to transcribe, with characters not allowed in URLs, and not very human-readable.
+
+Semantic information might also lead users to expect certain functionalities. A common pattern that we see at DataCite is to include information about the version or parent in the suffix, e.g. [https://doi.org/10.6084/M9.FIGSHARE.3501629.V1](https://doi.org/10.6084/M9.FIGSHARE.3501629.V1) or [https://doi.org/10.5061/DRYAD.0SN63/7](https://doi.org/10.5061/DRYAD.0SN63/7). While the decision on what to put into the suffix is up to each data center, we should make sure users don't think that these are functionalities of the DOI system (e.g. that adding **.V2** to any DOI name will resolve to version 2 of that resource).
+
+Another issue to keep in mind when assigning suffixes is that DOIs – in contrast to HTTP URIs – are case-insensitive, [https://doi.org/10.5281/ZENODO.31780](https://doi.org/10.5281/ZENODO.31780) and [https://doi.org/10.5281/zenodo.31780](https://doi.org/10.5281/zenodo.31780) are the same DOI. All DOIs are [converted to upper case](https://www.doi.org/doi_handbook/2_Numbering.html#2.4) upon registration and DOI resolution, but DOIs are not consistently displayed in such a way.
+
+### Generating cool DOIs
+
+With all that, what should the ideal DOI look like? Its suffix should be:
+
+* opaque without semantic information
+* work well in a web environment, avoiding characters problematic in URLs
+* short and human-readable
+* Resistant to transcription errors
+* easy to generate
+
+On Tuesday DataCite released a tool that helps generating such a suffix, an open source command line tool called [cirneco](https://github.com/datacite/cirneco) (a lot of our open source software uses Italian dog breed names). Cirneco is a Ruby gem that can be installed via
+
+```
+gem install cirneco
+```
+
+Cirneco uses base32 encoding, as [described](http://www.crockford.com/wrmg/base32.html) by Douglas Crockford. The encoding starts with a randomly generated number to guarantee uniqueness of the identifier, and then encodes the number into a string that uses all numbers and uppercase letters. It avoids the letters I, O and L as they can be confused with the letter 1 and 0, using 32 characters (and 5 checksum characters) in total. The last character is a checksum. The resulting string from cirneco always has a length of 8 characters, in groups of 4 separated by a hyphen to help with readability. The advantage of base32 encoding over using only numbers (as for example ORCID is doing) is that the resulting string becomes much more compact, the available 7 characters (plus one for the checksum) can encode 34,359,738,367 strings, compared to 10 million when only using numbers. This number is large enough that the resulting suffix will not only be unique for a given prefix, but also unique for all DOIs (there is a very small chance to get the same random number twice, but this will be rejected when trying to register the DOI).
+
+Another common way to generate random strings would have been universally unique identifiers ([UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier)), but they are long and not very human-readable, e.g. [https://doi.org/10.4233/UUID:6D192FE2-DE18-4556-873A-D3CD56AB96A6](https://doi.org/10.4233/UUID:6D192FE2-DE18-4556-873A-D3CD56AB96A6).
+
+An example DOI generated by cirneco would be
+
+```
+cirneco doi generate --prefix 10.5555
+10.5555/KVTD-VPWM
+```
+
+The generated DOI is short enough that it should work well in places where space is limited, providing an alternative to the [ShortDOI](http://shortdoi.org/) service which shortens existing DOIs, but does this by adding another layer on top of the DOI proxy.
+
+Another cirneco command checks that this is a valid bas32 string using the checksum
+
+```
+cirneco doi check 10.5555/KVTD-VPWM
+Checksum for 10.5555/KVTD-VPWM is valid
+```
+
+This can be used to quickly verify a DOI, e.g. in a web form or API. The Ruby base32 encoding library used by cirneco is open source ([https://github.com/datacite/base32](https://github.com/datacite/base32). I added the checksum to the existing library), and implementations of the Crockford base32 encoding pattern are available in many other languages, including [Python](https://github.com/jbittel/base32-crockford), [PHP](https://github.com/dflydev/dflydev-base32-crockford), [Javascript](https://www.npmjs.com/package/base32-crockford), [Java](http://stackoverflow.com/questions/22385467/crockford-base32-encoding-for-large-number-java-implementation), [Go](https://github.com/richardlehane/crock32) and [.NET](https://crockfordbase32.codeplex.com/).
+
+To answer the question raised at the beginning: a cool DOI is a DOI expressed as HTTPS URI using the doi.org proxy and using a base32-encoded suffix, for example **https://doi.org/10.5555/KVTD-VPWM**. This DOI works well in a web environment, is human readable, easy to parse and detect (e.g. in text mining), and can be generated using an algorithm that is well understood and supported.
+
+![](/images/2016/12/cool-dois.png)
+
+### References

data/spec/fixtures/cool-dois.yml

@@ -0,0 +1,8 @@
+layout: post
+title: Cool DOI's
+author: mfenner
+date: 2016-12-15
+tags:
+- doi
+- featured
+image: https://blog.datacite.org/images/2016/12/cool-dois.png

data/spec/markdown_spec.rb

@@ -0,0 +1,54 @@
+require 'spec_helper'
+
+describe Bergamasco::Markdown do
+  subject { Bergamasco::Markdown }
+
+  it 'should split yaml frontmatter' do
+    filepath = fixture_path + 'cool-dois.html.md'
+    file = IO.read(filepath)
+    metadata, content = subject.split_yaml_frontmatter(file)
+    expect(metadata).to have_key("title")
+    expect(content).to start_with("In 1998 Tim Berners-Lee coined")
+  end
+
+  it 'should update yaml frontmatter' do
+    filepath = fixture_path + 'cool-dois.html.md'
+    file = IO.read(filepath)
+    new_metadata = { "doi" => "10.23725/0000-03VC"}
+    metadata, content = subject.split_yaml_frontmatter(file)
+    metadata = subject.update_yaml_frontmatter(metadata, new_metadata)
+    expect(metadata["doi"]).to eq("10.23725/0000-03VC")
+  end
+
+  it 'should update yaml frontmatter remove attribute' do
+    filepath = fixture_path + 'cool-dois.html.md'
+    file = IO.read(filepath)
+    new_metadata = { "title" => nil }
+    metadata, content = subject.split_yaml_frontmatter(file)
+    metadata = subject.update_yaml_frontmatter(metadata, new_metadata)
+    expect(metadata["title"]).to be nil
+  end
+
+  it 'should join yaml frontmatter' do
+    filepath = fixture_path + 'cool-dois.html.md'
+    file = IO.read(filepath)
+    metadata, content = subject.split_yaml_frontmatter(file)
+    updated_file = subject.join_yaml_frontmatter(metadata, content)
+    expect(updated_file).to eq(file)
+  end
+
+  it 'should update file' do
+    filepath = fixture_path + 'cool-dois.html.md'
+    file = IO.read(filepath)
+    new_metadata = { "doi" => "10.23725/0000-03VC"}
+    updated_file = subject.update_file(file, new_metadata)
+    expect(updated_file).to include("\ndoi: 10.23725/0000-03VC\n")
+  end
+
+  it 'should convert markdown' do
+    filepath = fixture_path + 'cool-dois.html.md'
+    file = IO.read(filepath)
+    html = subject.render_html(file, skip_yaml_header: true)
+    expect(html).to start_with("<p>In 1998 Tim Berners-Lee coined")
+  end
+end

data/spec/sanitize_spec.rb

@@ -0,0 +1,17 @@
+require 'spec_helper'
+
+describe Bergamasco::Sanitize do
+  subject { Bergamasco::Sanitize }
+
+  it 'should remove a tags' do
+    text = "In 1998 <strong>Tim Berners-Lee</strong> coined the term <a href=\"https://www.w3.org/Provider/Style/URI\">cool URIs</a>"
+    content = subject.sanitize(text)
+    expect(content).to eq("In 1998 <strong>Tim Berners-Lee</strong> coined the term cool URIs")
+  end
+
+  it 'should only keep specific tags' do
+    text = "In 1998 <strong>Tim Berners-Lee</strong> coined the term <a href=\"https://www.w3.org/Provider/Style/URI\">cool URIs</a>"
+    content = subject.sanitize(text, tags: ["a"])
+    expect(content).to eq("In 1998 Tim Berners-Lee coined the term <a href=\"https://www.w3.org/Provider/Style/URI\">cool URIs</a>")
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,18 @@
+require 'bundler/setup'
+Bundler.setup
+
+require 'simplecov'
+SimpleCov.start
+
+require 'bergamasco'
+require 'rspec'
+
+RSpec.configure do |config|
+  config.expect_with :rspec do |c|
+    c.syntax = :expect
+  end
+end
+
+def fixture_path
+  File.expand_path("../fixtures", __FILE__) + '/'
+end

data/spec/summarize_spec.rb

@@ -0,0 +1,30 @@
+require 'spec_helper'
+
+describe Bergamasco::Summarize do
+  subject { Bergamasco::Summarize }
+
+  it 'should truncate after 250 characters' do
+    filepath = fixture_path + 'cool-dois-without-yml.md'
+    file = IO.read(filepath)
+    content = subject.summary(file)
+    expect(content.length).to eq(250)
+    expect(content).to start_with("In 1998 Tim Berners-Lee coined")
+  end
+
+  it 'should truncate after 75 characters' do
+    filepath = fixture_path + 'cool-dois-without-yml.md'
+    file = IO.read(filepath)
+    content = subject.summary(file, length: 75)
+    expect(content.length).to eq(83)
+    expect(content).to start_with("In 1998 Tim Berners-Lee coined")
+  end
+
+  it 'should truncate at separator' do
+    filepath = fixture_path + 'cool-dois-without-yml.md'
+    file = IO.read(filepath)
+    separator = "READMORE"
+    content = subject.summary(file, separator: separator)
+    expect(content).to start_with("In 1998 Tim Berners-Lee coined")
+    expect(content).to end_with("the referenced resource.")
+  end
+end

metadata

@@ -0,0 +1,293 @@
+--- !ruby/object:Gem::Specification
+name: bergamasco
+version: !ruby/object:Gem::Version
+  version: 0.1.1
+platform: ruby
+authors:
+- Martin Fenner
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2016-12-16 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.6.7
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.6.7
+- !ruby/object:Gem::Dependency
+  name: loofah
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.0.3
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.0.3
+- !ruby/object:Gem::Dependency
+  name: pandoc-ruby
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.0.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.0.0
+- !ruby/object:Gem::Dependency
+  name: builder
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 3.2.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.2'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 3.2.2
+- !ruby/object:Gem::Dependency
+  name: multi_json
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.11.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.11.2
+- !ruby/object:Gem::Dependency
+  name: oj
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.13.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.13.1
+- !ruby/object:Gem::Dependency
+  name: activesupport
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.2'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 4.2.5
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '4.2'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 4.2.5
+- !ruby/object:Gem::Dependency
+  name: safe_yaml
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.4
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.4
+- !ruby/object:Gem::Dependency
+  name: commonmarker
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.14.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.14.0
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.4'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.4'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: codeclimate-test-reporter
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.0.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.0.0
+- !ruby/object:Gem::Dependency
+  name: simplecov
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Text utilities for common cleanup and reformatting tasks when working
+  with scholarly metadata
+email: mfenner@datacite.org
+executables: []
+extensions: []
+extra_rdoc_files:
+- README.md
+files:
+- ".gitignore"
+- ".travis.yml"
+- Gemfile
+- Gemfile.lock
+- LICENSE.md
+- README.md
+- Rakefile
+- bergamasco.gemspec
+- lib/bergamasco.rb
+- lib/bergamasco/markdown.rb
+- lib/bergamasco/sanitize.rb
+- lib/bergamasco/summarize.rb
+- lib/bergamasco/version.rb
+- lib/bergamasco/whitelist_scrubber.rb
+- spec/fixtures/abstract.tex
+- spec/fixtures/cool-dois-without-yml.md
+- spec/fixtures/cool-dois.html.md
+- spec/fixtures/cool-dois.yml
+- spec/markdown_spec.rb
+- spec/sanitize_spec.rb
+- spec/spec_helper.rb
+- spec/summarize_spec.rb
+homepage: https://github.com/datacite/bergamasco
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.8
+signing_key: 
+specification_version: 4
+summary: Text utilities for working with scholarly metadata
+test_files: []