dcc 0.2.0

data/lib/dcc/schema/resources/xmldsig/xmldsig-core-schema.xsd

@@ -0,0 +1,312 @@
+<?xml version="1.0" encoding="utf-8"?>
+
+<!-- Schema for XML Signatures
+    http://www.w3.org/2000/09/xmldsig#
+    $Revision: 1.2 $ on $Date: 2013-04-16 12:48:49 $ by $Author: denis $
+
+    Copyright 2001 The Internet Society and W3C (Massachusetts Institute
+    of Technology, Institut National de Recherche en Informatique et en
+    Automatique, Keio University). All Rights Reserved.
+    http://www.w3.org/Consortium/Legal/
+
+    This document is governed by the W3C Software License [1] as described
+    in the FAQ [2].
+
+    [1] http://www.w3.org/Consortium/Legal/copyright-software-19980720
+    [2] http://www.w3.org/Consortium/Legal/IPR-FAQ-20000620.html#DTD
+
+    Modification by PTB:
+    - Removed lines 2 to 10 from W3C XMLDSig-Core scheme to avoid the use of DTD due to security risk.
+-->
+
+
+<schema xmlns="http://www.w3.org/2001/XMLSchema"
+        xmlns:ds="http://www.w3.org/2000/09/xmldsig#"
+        targetNamespace="http://www.w3.org/2000/09/xmldsig#"
+        version="0.1" elementFormDefault="qualified"> 
+
+<!-- Basic Types Defined for Signatures -->
+
+<simpleType name="CryptoBinary">
+  <restriction base="base64Binary">
+  </restriction>
+</simpleType>
+
+<!-- Start Signature -->
+
+<element name="Signature" type="ds:SignatureType"/>
+<complexType name="SignatureType">
+  <sequence> 
+    <element ref="ds:SignedInfo"/> 
+    <element ref="ds:SignatureValue"/> 
+    <element ref="ds:KeyInfo" minOccurs="0"/> 
+    <element ref="ds:Object" minOccurs="0" maxOccurs="unbounded"/> 
+  </sequence>  
+  <attribute name="Id" type="ID" use="optional"/>
+</complexType>
+
+  <element name="SignatureValue" type="ds:SignatureValueType"/> 
+  <complexType name="SignatureValueType">
+    <simpleContent>
+      <extension base="base64Binary">
+        <attribute name="Id" type="ID" use="optional"/>
+      </extension>
+    </simpleContent>
+  </complexType>
+
+<!-- Start SignedInfo -->
+
+<element name="SignedInfo" type="ds:SignedInfoType"/>
+<complexType name="SignedInfoType">
+  <sequence> 
+    <element ref="ds:CanonicalizationMethod"/> 
+    <element ref="ds:SignatureMethod"/> 
+    <element ref="ds:Reference" maxOccurs="unbounded"/> 
+  </sequence>  
+  <attribute name="Id" type="ID" use="optional"/> 
+</complexType>
+
+  <element name="CanonicalizationMethod" type="ds:CanonicalizationMethodType"/> 
+  <complexType name="CanonicalizationMethodType" mixed="true">
+    <sequence>
+      <any namespace="##any" minOccurs="0" maxOccurs="unbounded"/>
+      <!-- (0,unbounded) elements from (1,1) namespace -->
+    </sequence>
+    <attribute name="Algorithm" type="anyURI" use="required"/> 
+  </complexType>
+
+  <element name="SignatureMethod" type="ds:SignatureMethodType"/>
+  <complexType name="SignatureMethodType" mixed="true">
+    <sequence>
+      <element name="HMACOutputLength" minOccurs="0" type="ds:HMACOutputLengthType"/>
+      <any namespace="##other" minOccurs="0" maxOccurs="unbounded"/>
+      <!-- (0,unbounded) elements from (1,1) external namespace -->
+    </sequence>
+    <attribute name="Algorithm" type="anyURI" use="required"/> 
+  </complexType>
+
+<!-- Start Reference -->
+
+<element name="Reference" type="ds:ReferenceType"/>
+<complexType name="ReferenceType">
+  <sequence> 
+    <element ref="ds:Transforms" minOccurs="0"/> 
+    <element ref="ds:DigestMethod"/> 
+    <element ref="ds:DigestValue"/> 
+  </sequence>
+  <attribute name="Id" type="ID" use="optional"/> 
+  <attribute name="URI" type="anyURI" use="optional"/> 
+  <attribute name="Type" type="anyURI" use="optional"/> 
+</complexType>
+
+  <element name="Transforms" type="ds:TransformsType"/>
+  <complexType name="TransformsType">
+    <sequence>
+      <element ref="ds:Transform" maxOccurs="unbounded"/>  
+    </sequence>
+  </complexType>
+
+  <element name="Transform" type="ds:TransformType"/>
+  <complexType name="TransformType" mixed="true">
+    <choice minOccurs="0" maxOccurs="unbounded"> 
+      <any namespace="##other" processContents="lax"/>
+      <!-- (1,1) elements from (0,unbounded) namespaces -->
+      <element name="XPath" type="string"/> 
+    </choice>
+    <attribute name="Algorithm" type="anyURI" use="required"/> 
+  </complexType>
+
+<!-- End Reference -->
+
+<element name="DigestMethod" type="ds:DigestMethodType"/>
+<complexType name="DigestMethodType" mixed="true"> 
+  <sequence>
+    <any namespace="##other" processContents="lax" minOccurs="0" maxOccurs="unbounded"/>
+  </sequence>    
+  <attribute name="Algorithm" type="anyURI" use="required"/> 
+</complexType>
+
+<element name="DigestValue" type="ds:DigestValueType"/>
+<simpleType name="DigestValueType">
+  <restriction base="base64Binary"/>
+</simpleType>
+
+<!-- End SignedInfo -->
+
+<!-- Start KeyInfo -->
+
+<element name="KeyInfo" type="ds:KeyInfoType"/> 
+<complexType name="KeyInfoType" mixed="true">
+  <choice maxOccurs="unbounded">     
+    <element ref="ds:KeyName"/> 
+    <element ref="ds:KeyValue"/> 
+    <element ref="ds:RetrievalMethod"/> 
+    <element ref="ds:X509Data"/> 
+    <element ref="ds:PGPData"/> 
+    <element ref="ds:SPKIData"/>
+    <element ref="ds:MgmtData"/>
+    <any processContents="lax" namespace="##other"/>
+    <!-- (1,1) elements from (0,unbounded) namespaces -->
+  </choice>
+  <attribute name="Id" type="ID" use="optional"/> 
+</complexType>
+
+  <element name="KeyName" type="string"/>
+  <element name="MgmtData" type="string"/>
+
+  <element name="KeyValue" type="ds:KeyValueType"/> 
+  <complexType name="KeyValueType" mixed="true">
+   <choice>
+     <element ref="ds:DSAKeyValue"/>
+     <element ref="ds:RSAKeyValue"/>
+     <any namespace="##other" processContents="lax"/>
+   </choice>
+  </complexType>
+
+  <element name="RetrievalMethod" type="ds:RetrievalMethodType"/> 
+  <complexType name="RetrievalMethodType">
+    <sequence>
+      <element ref="ds:Transforms" minOccurs="0"/> 
+    </sequence>  
+    <attribute name="URI" type="anyURI"/>
+    <attribute name="Type" type="anyURI" use="optional"/>
+  </complexType>
+
+<!-- Start X509Data -->
+
+<element name="X509Data" type="ds:X509DataType"/> 
+<complexType name="X509DataType">
+  <sequence maxOccurs="unbounded">
+    <choice>
+      <element name="X509IssuerSerial" type="ds:X509IssuerSerialType"/>
+      <element name="X509SKI" type="base64Binary"/>
+      <element name="X509SubjectName" type="string"/>
+      <element name="X509Certificate" type="base64Binary"/>
+      <element name="X509CRL" type="base64Binary"/>
+      <any namespace="##other" processContents="lax"/>
+    </choice>
+  </sequence>
+</complexType>
+
+<complexType name="X509IssuerSerialType"> 
+  <sequence> 
+    <element name="X509IssuerName" type="string"/> 
+    <element name="X509SerialNumber" type="integer"/> 
+  </sequence>
+</complexType>
+
+<!-- End X509Data -->
+
+<!-- Begin PGPData -->
+
+<element name="PGPData" type="ds:PGPDataType"/> 
+<complexType name="PGPDataType"> 
+  <choice>
+    <sequence>
+      <element name="PGPKeyID" type="base64Binary"/> 
+      <element name="PGPKeyPacket" type="base64Binary" minOccurs="0"/> 
+      <any namespace="##other" processContents="lax" minOccurs="0"
+       maxOccurs="unbounded"/>
+    </sequence>
+    <sequence>
+      <element name="PGPKeyPacket" type="base64Binary"/> 
+      <any namespace="##other" processContents="lax" minOccurs="0"
+       maxOccurs="unbounded"/>
+    </sequence>
+  </choice>
+</complexType>
+
+<!-- End PGPData -->
+
+<!-- Begin SPKIData -->
+
+<element name="SPKIData" type="ds:SPKIDataType"/> 
+<complexType name="SPKIDataType">
+  <sequence maxOccurs="unbounded">
+    <element name="SPKISexp" type="base64Binary"/>
+    <any namespace="##other" processContents="lax" minOccurs="0"/>
+  </sequence>
+</complexType> 
+
+<!-- End SPKIData -->
+
+<!-- End KeyInfo -->
+
+<!-- Start Object (Manifest, SignatureProperty) -->
+
+<element name="Object" type="ds:ObjectType"/> 
+<complexType name="ObjectType" mixed="true">
+  <sequence minOccurs="0" maxOccurs="unbounded">
+    <any namespace="##any" processContents="lax"/>
+  </sequence>
+  <attribute name="Id" type="ID" use="optional"/> 
+  <attribute name="MimeType" type="string" use="optional"/> <!-- add a grep facet -->
+  <attribute name="Encoding" type="anyURI" use="optional"/> 
+</complexType>
+
+<element name="Manifest" type="ds:ManifestType"/> 
+<complexType name="ManifestType">
+  <sequence>
+    <element ref="ds:Reference" maxOccurs="unbounded"/> 
+  </sequence>
+  <attribute name="Id" type="ID" use="optional"/> 
+</complexType>
+
+<element name="SignatureProperties" type="ds:SignaturePropertiesType"/> 
+<complexType name="SignaturePropertiesType">
+  <sequence>
+    <element ref="ds:SignatureProperty" maxOccurs="unbounded"/> 
+  </sequence>
+  <attribute name="Id" type="ID" use="optional"/> 
+</complexType>
+
+   <element name="SignatureProperty" type="ds:SignaturePropertyType"/> 
+   <complexType name="SignaturePropertyType" mixed="true">
+     <choice maxOccurs="unbounded">
+       <any namespace="##other" processContents="lax"/>
+       <!-- (1,1) elements from (1,unbounded) namespaces -->
+     </choice>
+     <attribute name="Target" type="anyURI" use="required"/> 
+     <attribute name="Id" type="ID" use="optional"/> 
+   </complexType>
+
+<!-- End Object (Manifest, SignatureProperty) -->
+
+<!-- Start Algorithm Parameters -->
+
+<simpleType name="HMACOutputLengthType">
+  <restriction base="integer"/>
+</simpleType>
+
+<!-- Start KeyValue Element-types -->
+
+<element name="DSAKeyValue" type="ds:DSAKeyValueType"/>
+<complexType name="DSAKeyValueType">
+  <sequence>
+    <sequence minOccurs="0">
+      <element name="P" type="ds:CryptoBinary"/>
+      <element name="Q" type="ds:CryptoBinary"/>
+    </sequence>
+    <element name="G" type="ds:CryptoBinary" minOccurs="0"/>
+    <element name="Y" type="ds:CryptoBinary"/>
+    <element name="J" type="ds:CryptoBinary" minOccurs="0"/>
+    <sequence minOccurs="0">
+      <element name="Seed" type="ds:CryptoBinary"/>
+      <element name="PgenCounter" type="ds:CryptoBinary"/>
+    </sequence>
+  </sequence>
+</complexType>
+
+<element name="RSAKeyValue" type="ds:RSAKeyValueType"/>
+<complexType name="RSAKeyValueType">
+  <sequence>
+    <element name="Modulus" type="ds:CryptoBinary"/> 
+    <element name="Exponent" type="ds:CryptoBinary"/> 
+  </sequence>
+</complexType> 
+
+<!-- End KeyValue Element-types -->
+
+<!-- End Signature -->
+
+</schema>

data/lib/dcc/schema/version.rb

@@ -0,0 +1,94 @@
+# frozen_string_literal: true
+
+# `Dcc::Schema::Version` enumerates the bundled DCC and D-SI schema versions
+# and provides lookup helpers. Versions are stored as Strings in semver form
+# (e.g. `"3.3.0"`) with an optional `"v"` prefix tolerated on input.
+module Dcc
+  module Schema
+    module Version
+      DCC_ALL = %w[
+        2.1.0 2.1.1 2.2.0 2.3.0 2.4.0
+        3.0.0 3.1.0 3.1.1 3.1.2 3.2.0 3.2.1 3.3.0
+      ].freeze
+
+      DCC_LATEST = "3.3.0"
+      DCC_DEFAULT = DCC_LATEST
+
+      DSI_ALL = %w[
+        1.0.1 1.3.0 1.3.1 2.0.0 2.1.0 2.2.1
+      ].freeze
+
+      DSI_LATEST = "2.2.1"
+      DSI_DEFAULT = DSI_LATEST
+
+      QUDT_VERSION = "2.2.1"
+
+      class << self
+        # Normalize a version input to a bare `"X.Y.Z"` String.
+        # @param v [String, Symbol] e.g. `:v3_3_0`, `"3.3.0"`, `"v3.3.0"`.
+        # @return [String, nil]
+        def normalize(v)
+          return nil if v.nil?
+
+          s = v.to_s.sub(/\Av/, "").gsub(/_/, ".")
+          s.empty? ? nil : s
+        end
+
+        # @param v [String, Symbol] candidate version.
+        # @return [Boolean] whether the version is a known DCC release.
+        def dcc?(v)
+          DCC_ALL.include?(normalize(v))
+        end
+
+        # @param v [String, Symbol] candidate version.
+        # @return [Boolean] whether the version is a known D-SI release.
+        def dsi?(v)
+          DSI_ALL.include?(normalize(v))
+        end
+
+        # Major version of a semver string (`"3.3.0"` → `3`).
+        def major(v)
+          Integer(normalize(v).split(".").first)
+        end
+
+        # Resolve `:auto`, `nil`, `"latest"`, or a specific version string to
+        # a concrete DCC version. The `:auto` strategy reads `schemaVersion`
+        # from the XML body.
+        def resolve_dcc(version, xml: nil)
+          v = normalize(version)
+          return detect_from_xml(xml) if v.nil? || v == "auto"
+          return DCC_LATEST if v == "latest"
+
+          unless dcc?(v)
+            raise ::Dcc::UnknownVersionError,
+                  "Unknown DCC schema version: #{version.inspect}"
+          end
+
+          v
+        end
+
+        def resolve_dsi(version, xml: nil)
+          v = normalize(version)
+          return DSI_LATEST if v.nil? || v == "auto" || v == "latest"
+
+          unless dsi?(v)
+            raise ::Dcc::UnknownVersionError,
+                  "Unknown D-SI schema version: #{version.inspect}"
+          end
+
+          v
+        end
+
+        # Extract the `schemaVersion` attribute from an XML string.
+        # @return [String, nil]
+        def detect_from_xml(xml)
+          return nil unless xml
+
+          str = ::Dcc.read_input(xml)
+          match = str.match(/schemaVersion\s*=\s*["']([^"']+)["']/)
+          match && match[1]
+        end
+      end
+    end
+  end
+end

data/lib/dcc/schema.rb

@@ -0,0 +1,35 @@
+# frozen_string_literal: true
+
+# `Dcc::Schema` provides access to the bundled XSD, Schematron, and QUDT
+# resources that ship with the gem under `lib/dcc/schema/resources/`.
+#
+# Use `Dcc::Schema.path("dcc/v3.3.0/dcc.xsd")` to get the absolute filesystem
+# path of a bundled resource. Use `Dcc::Schema::Version` for the canonical
+# list of supported versions.
+module Dcc
+  module Schema
+    RESOURCES_DIR = File.expand_path("schema/resources", __dir__).freeze
+
+    autoload :Version, "dcc/schema/version"
+
+    class << self
+      # @param relative_path [String, Array<String>] resource path relative to
+      #   `lib/dcc/schema/resources/`, e.g. `"dcc/v3.3.0/dcc.xsd"`.
+      # @return [String] absolute filesystem path.
+      def path(relative_path)
+        File.join(RESOURCES_DIR, *Array(relative_path))
+      end
+
+      # @return [Boolean] whether the bundled resource exists.
+      def exists?(relative_path)
+        File.file?(path(relative_path))
+      end
+
+      # Read a bundled resource's contents.
+      # @return [String]
+      def read(relative_path)
+        File.read(path(relative_path))
+      end
+    end
+  end
+end

data/lib/dcc/server/app.rb

@@ -0,0 +1,133 @@
+# frozen_string_literal: true
+
+# Loads Sinatra lazily so the gem works without it installed.
+begin
+  require "sinatra/base"
+  SINATRA_AVAILABLE = true
+rescue ::LoadError
+  SINATRA_AVAILABLE = false
+end
+
+module Dcc
+  module Server
+    # Sinatra application exposing the DCC REST API. Mirrors PTB dcclib's
+    # endpoints: POST /dccs, GET /dccs/:id, DELETE /dccs/:id,
+    # POST /dccs/:id/validate/{xsd,schematron}, /convert/json,
+    # /extract/{files,formulae}, /signature, /transform/xslt.
+    #
+    # Run via:
+    #   require "dcc/server"
+    #   Dcc::Server::App.run!
+    class App < ::Sinatra::Base
+      before do
+        content_type :json
+      end
+
+      # Storage instance — override in config.ru for production swaps.
+      set :storage, ::Dcc::Server::Storage::Memory.new
+
+      get "/" do
+        {
+          title: "dcc gem REST API",
+          version: ::Dcc::VERSION,
+          endpoints: [
+            "POST /dccs",
+            "GET /dccs/:id",
+            "DELETE /dccs/:id",
+            "POST /dccs/:id/validate/xsd",
+            "POST /dccs/:id/validate/schematron",
+            "POST /dccs/:id/convert/json",
+            "GET /dccs/:id/extract/files",
+            "POST /dccs/:id/transform/xslt",
+          ],
+        }.to_json
+      end
+
+      post "/dccs" do
+        ensure_loaded!
+        body = JSON.parse(request.body.read)
+        xml = body.fetch("xml")
+        entry = settings.storage.put(xml)
+        status 201
+        { id: entry.id, expires: entry.expires_at }.to_json
+      rescue ::KeyError
+        status 400
+        { error: "missing 'xml' in request body" }.to_json
+      end
+
+      get "/dccs/:id" do
+        entry = settings.storage.get(params[:id])
+        halt 404, { error: "not found" }.to_json unless entry
+
+        { id: entry.id, xml: entry.xml, expires: entry.expires_at }.to_json
+      end
+
+      delete "/dccs/:id" do
+        deleted = settings.storage.delete(params[:id])
+        halt 404, { error: "not found" }.to_json unless deleted
+
+        status 204
+      end
+
+      post "/dccs/:id/validate/xsd" do
+        result = with_dcc(params[:id]) { |xml| ::Dcc::Validate::Xsd.call(xml) }
+        result.to_json
+      end
+
+      post "/dccs/:id/validate/schematron" do
+        result = with_dcc(params[:id]) { |xml| ::Dcc::Validate::Schematron.call(::Dcc.parse(xml)) }
+        result.to_json
+      end
+
+      post "/dccs/:id/convert/json" do
+        with_dcc(params[:id]) do |xml|
+          ::Dcc::Convert::Json.call(::Dcc.parse(xml)).payload
+        end
+      end
+
+      get "/dccs/:id/extract/files" do
+        with_dcc(params[:id]) do |xml|
+          files = ::Dcc::Extract::File.each(::Dcc.parse(xml))
+          {
+            files: files.map do |f|
+              {
+                name: f.name, file_name: f.file_name,
+                mime_type: f.mime_type, ring: f.ring.to_s,
+                data_base64: ::Base64.strict_encode64(f.data),
+              }
+            end,
+          }.to_json
+        end
+      end
+
+      post "/dccs/:id/transform/xslt" do
+        body = JSON.parse(request.body.read)
+        xslt = body.fetch("xslt")
+        with_dcc(params[:id]) do |xml|
+          ::Dcc::Transform::Xslt.call(xml, xslt).payload
+        end
+      end
+
+      private
+
+      def ensure_loaded!
+        return if @loaded
+
+        ::Dcc.load_all!
+        @loaded = true
+      end
+
+      def with_dcc(id)
+        entry = settings.storage.get(id)
+        halt 404, { error: "not found" }.to_json unless entry
+
+        ensure_loaded!
+        result = yield(entry.xml)
+        result.is_a?(::String) ? result : result.to_json
+      end
+    end
+  end
+end
+
+require "base64"
+require "json"

data/lib/dcc/server/storage/entry.rb

@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+
+module Dcc
+  module Server
+    module Storage
+      # Value object for a stored DCC entry. Carries the SHA-256 id, XML
+      # payload, and expiry timestamp.
+      Entry = ::Struct.new(:id, :xml, :expires_at, keyword_init: true) do
+        def expired?
+          expires_at && Time.now > expires_at
+        end
+      end
+    end
+  end
+end

data/lib/dcc/server/storage/memory.rb

@@ -0,0 +1,57 @@
+# frozen_string_literal: true
+
+require "digest"
+
+module Dcc
+  module Server
+    module Storage
+      # In-memory storage with SHA-256-keyed entries and TTL eviction.
+      # Not thread-safe without external synchronization — wrap in a
+      # Mutex for concurrent deployments.
+      class Memory
+        attr_reader :ttl_seconds
+
+        def initialize(ttl_seconds: 300)
+          @store = {}
+          @ttl_seconds = ttl_seconds
+        end
+
+        # @param xml [String]
+        # @return [Dcc::Server::Storage::Entry]
+        def put(xml)
+          id = ::Digest::SHA256.hexdigest(xml)
+          entry = Entry.new(id: id, xml: xml, expires_at: Time.now + ttl_seconds)
+          @store[id] = entry
+          entry
+        end
+
+        # @param id [String] SHA-256 hex.
+        # @return [Dcc::Server::Storage::Entry, nil]
+        def get(id)
+          entry = @store[id]
+          return nil unless entry
+
+          if entry.expired?
+            @store.delete(id)
+            return nil
+          end
+          entry
+        end
+
+        # @param id [String]
+        # @return [Boolean]
+        def delete(id)
+          !!@store.delete(id)
+        end
+
+        def clear
+          @store.clear
+        end
+
+        def size
+          @store.size
+        end
+      end
+    end
+  end
+end

data/lib/dcc/server/storage.rb

@@ -0,0 +1,13 @@
+# frozen_string_literal: true
+
+module Dcc
+  module Server
+    # Pluggable storage for uploaded DCC XML documents. The default
+    # `Memory` implementation keeps documents in-process; production
+    # deployments can swap in a disk or Redis-backed implementation.
+    module Storage
+      autoload :Memory, "dcc/server/storage/memory"
+      autoload :Entry, "dcc/server/storage/entry"
+    end
+  end
+end