ojxv 0.0.2 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 518bbd33a429a3ece2825afaeabe463a393f5bcb3161f9ab59bcc3042949b2a5
-  data.tar.gz: a562dbbe85156da40b63506b96dc89ab36c97948796712aafa6967064b48fd5d
+  metadata.gz: 575fd6a87c9df03bee0e507a16780e893ca18e3a75403a6a6e70db32ccb9efc2
+  data.tar.gz: 747bedc6a2a62da393ede7b0398bfe04152b1c500eb64050ebc4a3361332aa90
 SHA512:
-  metadata.gz: 21f2b1fffca14aafb2c2843d0ab003debce15e07a369faabb6ce530cf750b12e2e0eb51062f9fd04ac5ce5ad230e0df8104ad1ead83101357846a14291c255a8
-  data.tar.gz: 8676d1fcefb2bb2ed314c951e4ba4e4259b07b1ed18912defc20ac255a577ee303236373230008d9f79ec171dabb6c67ed1989fe3f68bd739f7db0184ce111d6
+  metadata.gz: 5ac7fc2b9ec288fe7b60c5bde35a3bed389f3e975c404039e567a1694f1bd60c7b57129aadb87f3531ac04c474e05794821909de711c43eee462dae982662deb
+  data.tar.gz: 5101c69c5e0c0f7f046ce3aaa02124b83a85d7f45d3581cfc82b35a2275a03b60b33982a872219445cdcb7e01ae4647b34fee24ce4072a55cbaca14730cfd9d9

data/README.md

@@ -1,2 +1,77 @@
-# OJXV
-Open Journals XML Validator
+# OJXV: Open Journals XML Validator
+
+OJXV validates Open Journals' publishing pipeline XML outputs (JATS and Crossref).
+
+## Installation
+
+```
+gem install ojxv
+```
+
+## Usage
+
+OJXV can be used to validate JATS and Crossref XML files against the following schema versions:
+
+- JATS:
+  - 1.1
+  - 1.1d1
+  - 1.1d2
+  - 1.1d3
+  - 1.2
+  - 1.2d1
+  - 1.2d2
+  - 1.3d1
+  - 1.3
+- Crossref:
+  - 4.8.0
+  - 4.8.1
+  - 5.1.0
+  - 5.2.0
+  - 5.3.0
+  - 5.3.1
+
+### Validating JATS files
+
+Use the `OJXV::JatsFile` class:
+
+```ruby
+require "ojxv"
+
+jats_file_path = "example/paper.jats"
+
+jats_file = OJXV::JatsFile.new(jats_file_path)
+
+# By default validation is performed against JATS v1.3
+jats_file.valid_jats? #=> true / false
+
+# Validating against a specific schema version:
+jats_file.valid_jats?("1.2") #=> true / false
+
+# After validating, errors can be queried:
+jats_file.errors #=> [] / ["Error: missing element article", "Error: invalid namespace", ...]
+```
+
+### Validating Crossref XML files
+
+Use the `OJXV::CrossrefMetadataFile` class:
+
+```ruby
+require "ojxv"
+
+crossref_file_path = "example/paper.crossref"
+
+crossref_file = OJXV::CrossrefMetadataFile.new(crossref_file_path)
+
+# By default validation is performed against Crossref 5.3.1
+crossref_file.valid_crossref? #=> true / false
+
+# Validating against a specific schema version:
+crossref_file.valid_crossref?("4.8.0") #=> true / false
+
+# After validating, errors can be queried:
+crossref_file.errors #=> [] / ["Error: missing element article", "Error: invalid namespace", ...]
+```
+
+## License
+
+Released under a [MIT License](./LICENSE) - © Juanjo Bazán

data/lib/ojxv/crossref_metadata_file.rb

@@ -0,0 +1,49 @@
+require 'nokogiri'
+
+module OJXV
+  # VALIDATING CROSSREF against the XSD
+  # Crossref bundle v0.3.1 from https://gitlab.com/crossref/schema/-/releases
+  class CrossrefMetadataFile
+
+    attr_accessor :errors
+    attr_accessor :file
+
+    def initialize(filepath)
+      @errors = nil
+      if File.exist?(filepath)
+        @file = File.open(filepath)
+      else
+        raise ::OJXV::FileNotFound, "Can't find file: #{filepath}"
+      end
+    end
+
+    def valid_crossref?(crossref_version="5.3.1")
+      @errors = nil
+
+      xsd = Nokogiri::XML::Schema(schema(crossref_version))
+      doc = Nokogiri::XML(file.read)
+
+      @errors = xsd.validate(doc)
+      @errors.empty?
+
+    rescue Nokogiri::XML::SyntaxError => e
+      raise ::OJXV::XMLParsingError, e.message
+    end
+
+    def self.supported_schema_versions
+      ["4.8.0", "4.8.1", "5.1.0", "5.2.0", "5.3.0", "5.3.1"]
+    end
+
+    private
+
+      def schema(crossref_version)
+        schema_path = File.join(File.dirname(__FILE__), "schemas", "crossref", "crossref#{crossref_version}.xsd")
+
+        unless File.exist?(schema_path) && CrossrefMetadataFile.supported_schema_versions.include?(crossref_version)
+          raise ::OJXV::UnsupportedCrossrefSchemaVersion, "Unsupported Crossref schema version: #{crossref_version}"
+        end
+
+        File.open(schema_path)
+      end
+  end
+end

data/lib/ojxv/jats_file.rb

@@ -0,0 +1,64 @@
+require 'nokogiri'
+require 'securerandom'
+
+module OJXV
+  # VALIDATING JATS against DTD
+  # DTD schemas from https://jats.nlm.nih.gov/archiving/1.3/dtd.html
+  class JatsFile
+
+    attr_accessor :errors
+    attr_reader :filepath
+
+    def initialize(path)
+      @errors = nil
+      raise ::OJXV::FileNotFound, "Can't find file: #{path}" unless File.exist?(path)
+      @filepath = path
+    end
+
+    def valid_jats?(schema_version="1.3")
+      @errors = nil
+      FileUtils.mkdir_p(local_path)
+
+      FileUtils.cp_r schema_files_path(schema_version), local_path
+      FileUtils.cp @filepath, local_path
+
+      new_filepath = File.join(local_path, File.basename(@filepath))
+
+      doc = Nokogiri::XML(File.open(new_filepath)) do |config|
+        config.dtdload.dtdvalid
+      end
+
+      raise(NoDTD, "File has no DTD declaration") if doc.external_subset.nil?
+
+      @errors = doc.external_subset.validate(doc)
+      @errors.empty?
+
+    rescue Nokogiri::XML::SyntaxError => e
+      raise ::OJXV::XMLParsingError, e.message
+    ensure
+      cleanup
+    end
+
+    def self.supported_schema_versions
+      ["1.1", "1.1d1", "1.1d2", "1.1d3", "1.2", "1.2d1", "1.2d2", "1.3d1", "1.3"]
+    end
+
+    private
+
+      def schema_files_path(schema_version)
+        unless JatsFile.supported_schema_versions.include?(schema_version)
+          raise ::OJXV::UnsupportedJATSSchemaVersion, "Unsupported JATS schema version: #{schema_version}"
+        end
+
+        File.join(File.dirname(__FILE__), "schemas", "jats", schema_version.to_s, ".")
+      end
+
+      def local_path
+        @local_path ||= "tmp-ojxv-jats-#{SecureRandom.hex(3)}"
+      end
+
+      def cleanup
+        FileUtils.rm_rf(local_path) if Dir.exist?(local_path)
+      end
+  end
+end

data/lib/ojxv/schemas/crossref/AccessIndicators.xsd

@@ -0,0 +1,64 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
+    targetNamespace="http://www.crossref.org/AccessIndicators.xsd"
+    xmlns="http://www.crossref.org/AccessIndicators.xsd">
+    
+    <xsd:annotation>
+        <xsd:documentation> Version: 1.1 This is CrossRef's schema for defining the applicable
+            licenses for a given item. This schema was available and in use prior to the completion
+            of the NISO working group Access and License Indicators
+            (http://www.niso.org/publications/rp/rp-22-2015). That effort produced a schema
+            (http://www.niso.org/schemas/ali/1.0/ali.xsd) that extended the CrossRef definition but
+            at the same time omitted necessary CrossRef features. This schema will continue as the
+            basis for CrossRef metadata deposits, but will incorporate the NISO work where possible.
+            Change history: 2/23/15 CSK added Niso free_to_read element 
+                            4/21/15 CSK added start and end attributes to the free-to-read element as in the Niso ALI schema
+                                        but will make both attributes optional.
+        </xsd:documentation>
+    </xsd:annotation>
+
+    <xsd:element name="program">
+        <xsd:annotation>
+            <xsd:documentation>Accommodates deposit of license metadata. The license_ref value will
+                be a URL. Values for the "applies_to" attribute are vor (version of record),am
+                (accepted manuscript), and tdm (text and data mining).</xsd:documentation>
+        </xsd:annotation>
+        <xsd:complexType>
+            <xsd:sequence>
+                <xsd:element ref="free_to_read" minOccurs="0"/>
+                <xsd:element ref="license_ref" minOccurs="0" maxOccurs="unbounded"/>
+            </xsd:sequence>
+            <xsd:attribute name="name" type="xsd:string" fixed="AccessIndicators"/>
+        </xsd:complexType>
+    </xsd:element>
+    <xsd:element name="license_ref">
+        <xsd:complexType>
+            <xsd:simpleContent>
+                <xsd:extension base="license_ref_t">
+                    <xsd:attribute name="start_date" type="xsd:date" use="optional"/>
+                    <xsd:attribute name="applies_to" use="optional">
+                        <xsd:simpleType>
+                            <xsd:restriction base="xsd:NMTOKEN">
+                                <xsd:enumeration value="vor"/>
+                                <xsd:enumeration value="am"/>
+                                <xsd:enumeration value="tdm"/>
+                            </xsd:restriction>
+                        </xsd:simpleType>
+                    </xsd:attribute>
+                </xsd:extension>
+            </xsd:simpleContent>
+        </xsd:complexType>
+    </xsd:element>
+    <xsd:simpleType name="license_ref_t">
+        <xsd:restriction base="xsd:anyURI">
+            <xsd:minLength value="10"/>
+            <xsd:pattern value="([hH][tT][tT][pP]|[hH][tT][tT][pP][sS]|[fF][tT][pP])://.*"/>
+        </xsd:restriction>
+    </xsd:simpleType>
+    <xsd:element name="free_to_read">
+        <xsd:complexType>
+            <xsd:attribute name="end_date" use="optional" type="xsd:date"/>
+            <xsd:attribute name="start_date" use="optional" type="xsd:date"/>
+        </xsd:complexType>
+    </xsd:element>
+</xsd:schema>