kataba 1.1.0 → 1.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1849ebd6214469739d5a16981525a9c5ab23d0ca7ddb91ad028064a43e63dad0
-  data.tar.gz: 46da3306e49890c4801362c7c5af2c8e7cbf68cf2d3a8b9604e4d69f9d3f7887
+  metadata.gz: 3e2048c2adaac9976b8feb4fcea1da32d937a7d39955152a579f18d81e9fe3f2
+  data.tar.gz: 806c80fff00c2a8dd637b42e1df485787e041a514ecc6372df5cb4902db8889e
 SHA512:
-  metadata.gz: 7d26265f3e4b30fbc11c82f12bec40860b56f3910d8a7aefccc9150bf6cd24d61a543da9fb33eb11111a8410386e1c632df6c02f56e2f91a8681515e4f2e5548
-  data.tar.gz: e35b99af877e7b660838d9b58943806c35084861c8295ea93e4a456d66e20943fb987261ee5adf795a0c858c26fa8a7c4cd41212d9012d26d5ba14cab80d51bc
+  metadata.gz: 15b1a25d1ed46d7510f829f4a6b51ca6516ed29edfa011b4a8395cee0bc36092e37d4ecb925e24791da6d4790435896059cabd8fb375b17278c724dff61540c9
+  data.tar.gz: 64fa54356f4d0c0387a9c52898795462524363b6fccf6632259b635adb7d2c19544760c2e0b91256cf1e22b50a3e3836868ce5581c73499bda3184f32838b086

data/lib/kataba/fetcher.rb

@@ -12,6 +12,12 @@ module Kataba
   #     consumer already trusted this host by putting it in their
   #     schemaLocation. Cross-origin downgrades stay refused — that's
   #     the actual DNS-redirect attack vector.
+  #   - /mods/xml.xsd: rewrite to /standards/mods/xml.xsd before the
+  #     first request. The /mods/xml.xsd path is what every mods-3-N.xsd
+  #     embeds in its xs:import, but LoC only serves the file from
+  #     /standards/mods/xml.xsd today — the embedded path bounces
+  #     HTTPS->HTTP and 503s. Applied here so transitive xs:import
+  #     resolution benefits, not just top-level fetch_schema calls.
   #
   # mirror_list remains the consumer's backstop for URI-identity
   # changes (path renames, host moves) that no delivery heuristic
@@ -19,6 +25,13 @@ module Kataba
   class Fetcher
     MAX_REDIRECTS = 5
 
+    # Map from a path that's embedded in published schemas but no longer
+    # serves the file, to the path that does. xml.xsd: every mods-3-N.xsd
+    # imports /mods/xml.xsd, but only /standards/mods/xml.xsd serves it.
+    PATH_REWRITES = {
+      '/mods/xml.xsd' => '/standards/mods/xml.xsd',
+    }.freeze
+
     class FetchError < StandardError; end
 
     def initialize(uri)
@@ -26,11 +39,19 @@ module Kataba
     end
 
     def fetch
-      attempt(@original_uri, alt_scheme_retry: true)
+      attempt(normalize(@original_uri), alt_scheme_retry: true)
     end
 
     private
 
+    def normalize(uri)
+      PATH_REWRITES.each do |from, to|
+        rewritten = uri.sub(%r{(\Ahttps?://[^/]+)#{Regexp.escape(from)}\z}i, "\\1#{to}")
+        return rewritten unless rewritten == uri
+      end
+      uri
+    end
+
     def attempt(uri, alt_scheme_retry:)
       response = request_with_redirects(uri, redirect_depth: 0)
 

data/lib/kataba.rb

@@ -61,6 +61,14 @@ module Kataba
   # Arguments:
   #   xsd_uri: (String)
 
+  # Dir.chdir is process-wide state, not thread-local: if two threads each
+  # have a chdir block open at once, Ruby raises "conflicting chdir during
+  # another chdir block" rather than let one thread's cwd stomp on the
+  # other's. A shared Mutex serializes just that step across threads in one
+  # process — cheap, since by this point it's a local file read + a Nokogiri
+  # parse, not the network fetch (which stays outside the lock).
+  CHDIR_MUTEX = Mutex.new
+
   def self.fetch_schema(xsd_uri)
     uri_md5 = Digest::MD5.hexdigest(xsd_uri)
     dir_path = "#{self.configuration.offline_storage}"
@@ -77,8 +85,10 @@ module Kataba
       end
 
       # Validate and return Nokogiri schema
-      Dir.chdir(dir_path) do
-        return Nokogiri::XML::Schema(IO.read(xsd_path))
+      CHDIR_MUTEX.synchronize do
+        Dir.chdir(dir_path) do
+          return Nokogiri::XML::Schema(IO.read(xsd_path))
+        end
       end
     rescue Nokogiri::XML::SyntaxError
       # Poisoned cache (e.g. a pre-fix install that stored a bad fetch).
@@ -115,7 +125,9 @@ module Kataba
         # orphaned 0-byte .part on disk — the file simply isn't created.
         fetch_uri = xsd_uri
         if !self.configuration.mirror_list.to_s.empty?
-          mirror_list = YAML.load_file(self.configuration.mirror_list)
+          # YAML.load_file returns nil for a comments-only or empty file.
+          # Treat that as "no mirror configured" rather than NoMethodError.
+          mirror_list = YAML.load_file(self.configuration.mirror_list) || {}
           mirror = mirror_list[xsd_uri]
           fetch_uri = mirror unless mirror.to_s.empty?
         end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: kataba
 version: !ruby/object:Gem::Version
-  version: 1.1.0
+  version: 1.1.2
 platform: ruby
 authors:
 - David Cliff
@@ -14,56 +14,56 @@ dependencies:
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         version: '1.19'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '>='
+    - - ">="
       - !ruby/object:Gem::Version
         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
@@ -85,16 +85,16 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '3.2'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.9
+rubygems_version: 3.2.33
 signing_key:
 specification_version: 4
 summary: XML Schema Definition (XSD) mirroring and offline validation for Nokogiri