kataba 1.0.0 → 1.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: fd9fd6f5ee1170b5552d4345a4c23fab923efcaa
-  data.tar.gz: e78ca648b702ecd40a576263eb6aaab7d4fd4d13
+SHA256:
+  metadata.gz: 97107593bef37bc5a20d934c683ca45c5c1142d301bc705067a20b3e94a07d58
+  data.tar.gz: fee7e5c92557a7f85170a395a97de0055b447d978d822575aadf8a6fe301b391
 SHA512:
-  metadata.gz: 13ed9bbd4e28ee1e7e8e955f6ea9084b52e94da83458d395fb776a75b40094079e640bdb82c7424eca93dc27b1063968b3fb96791723d1a9d432a29837a18362
-  data.tar.gz: 46f8e1813d56ecdd4cd689bd5ee2354d250861f1b627cd0812fed4ed36b4ccab8aa8313a779416e0ee69e12fb08c048c7f4bd109d2f626af1e20ac49c426ac5c
+  metadata.gz: 28c18ab1818719194b5f9ae1a512bfad8716caf430fac3ce4509dad455e4796cf9634bf33fec4b0e51501cea3dc70b1908945dfd4c80d71316d61bac2fa68293
+  data.tar.gz: d7d05f52acc72e4f6ed031d255304b7d37984f07e89d24bf76c74e9e6be40bf06e1dab08a07f9eb8e7b2d8633c39b6d93ea10df503752189672ea0689e397dc0

data/lib/kataba.rb

@@ -2,12 +2,17 @@ require 'nokogiri'
 require 'tmpdir'
 require 'digest/md5'
 require 'open-uri'
+require 'fileutils'
+require 'yaml'
 
 module Kataba
 
-  class << self
-    attr_accessor :configuration
-  end
+  # Allows for configuration by block
+  #
+  # Example:
+  #  MegaLotto.configure do |config|
+  #   config.drawing_count = 10
+  #  end
 
   def self.configure
     yield(configuration) if block_given?
@@ -17,35 +22,71 @@ module Kataba
     @configuration ||=  Configuration.new
   end
 
+  # Undoes any configuration - this method was built for testing purposes
+  #
+  # Example:
+  #   Kataba.reset
+
   def self.reset
     @configuration = Configuration.new
   end
 
   class Configuration
+    # Offline storage is "#{Dir.tmpdir}/kataba" by default.
+    # This attribute allows the user to change that default value.
+    #
+    # Example:
+    #   Kataba.configuration.offline_storage = "/tmp/kataba"
     attr_accessor :offline_storage
+    # The user can optionally provide a mirror list to reduce stress on primary XSD providers.
+    # This attribute allows the user to configure Kataba to use a YAML file with key/value pairs of
+    # original/mirror values. Sample YAML file can be found at https://github.com/dgcliff/kataba/blob/master/test/fixtures/mirror.yml
+    #
+    # Example:
+    #   Kataba.configuration.mirror_list = File.join(Rails.root, 'config', 'mirror.yml')
     attr_accessor :mirror_list
 
+    # Default configuration values
     def initialize
       @offline_storage = "#{Dir.tmpdir}/kataba"
     end
   end
 
+  # If already downloaded, uses offline version. If not, downloads from the URI provided.
+  # If mirror list is configured, searches for mirrored URI instead.
+  #
+  # Example:
+  #   Kataba.fetch_schema("http://www.loc.gov/standards/mods/v3/mods-3-5.xsd")
+  #
+  # Arguments:
+  #   xsd_uri: (String)
+
   def self.fetch_schema(xsd_uri)
     uri_md5 = Digest::MD5.hexdigest(xsd_uri)
     dir_path = "#{self.configuration.offline_storage}"
     xsd_path = "#{dir_path}/#{uri_md5}.xsd"
 
-    # Does the offline version exist already?
-    if !(File.exists?(xsd_path))
-      # If not, go download
-      xsd_array = []
-      xsd_array << xsd_uri
-      download_xsd(xsd_array)
-    end
+    attempts = 0
+    begin
+      # Does the offline version exist already?
+      if !(File.exist?(xsd_path))
+        # If not, go download
+        xsd_array = []
+        xsd_array << xsd_uri
+        download_xsd(xsd_array)
+      end
 
-    # Validate and return Nokogiri schema
-    Dir.chdir(dir_path) do
-      return Nokogiri::XML::Schema(IO.read(xsd_path))
+      # Validate and return Nokogiri schema
+      Dir.chdir(dir_path) do
+        return Nokogiri::XML::Schema(IO.read(xsd_path))
+      end
+    rescue Nokogiri::XML::SyntaxError
+      # Poisoned cache (e.g. a pre-fix install that stored a bad fetch).
+      # Evict the offending file and refetch once.
+      File.delete(xsd_path) if File.exist?(xsd_path)
+      attempts += 1
+      retry if attempts < 2
+      raise
     end
   end
 
@@ -67,23 +108,37 @@ module Kataba
         end
 
         file_path = "#{dir_name}/#{uri_md5}.xsd"
-
-        file_paths << file_path
-
-        open(file_path, "wb+") do |file|
+        tmp_path  = "#{file_path}.part"
+
+        # Write to a .part file first; only rename to the final cache path
+        # after we've confirmed the bytes parse as XML. Without this, a
+        # malformed response (HTML error page, truncated TCP stream, captive
+        # portal stub) would land at the canonical cache path and poison
+        # every subsequent fetch.
+        File.open(tmp_path, "wb+") do |file|
           if !self.configuration.mirror_list.to_s.empty?
             mirror_list = YAML.load_file(self.configuration.mirror_list)
             mirror = mirror_list[xsd_uri]
             if mirror.to_s.empty?
               # No mirror for that uri
-              file.write(open(xsd_uri).read)
+              file.write(URI.open(xsd_uri).read)
             else
-              file.write(open(mirror).read)
+              file.write(URI.open(mirror).read)
             end
           else
-            file.write(open(xsd_uri).read)
+            file.write(URI.open(xsd_uri).read)
           end
         end
+
+        begin
+          Nokogiri::XML(File.read(tmp_path)) { |c| c.strict }
+        rescue Nokogiri::XML::SyntaxError
+          File.delete(tmp_path)
+          raise
+        end
+
+        File.rename(tmp_path, file_path)
+        file_paths << file_path
       end
 
       # Search inside for other schemaLocations

metadata

@@ -1,31 +1,73 @@
 --- !ruby/object:Gem::Specification
 name: kataba
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.0.3
 platform: ruby
 authors:
 - David Cliff
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2016-10-02 00:00:00.000000000 Z
+date: 2026-05-15 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'
+        version: '1.19'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '1.6'
-description: A simple gem that allows for the functionality that an XML catalog would
-  provide
+        version: '1.19'
+- !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: minitest
+  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: webmock
+  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: Kataba allows for mirroring and offline storage of XSD files, to enhance
+  Nokogiri
 email: d.cliff@northeastern.edu
 executables: []
 extensions: []
@@ -36,24 +78,23 @@ homepage: http://rubygems.org/gems/kataba
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ~>
+  - - ">="
     - !ruby/object:Gem::Version
-      version: '2.0'
+      version: '3.2'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.2.2
-signing_key: 
+rubygems_version: 3.4.10
+signing_key:
 specification_version: 4
 summary: XML Schema Definition (XSD) mirroring and offline validation for Nokogiri
 test_files: []