moxml 0.5.170 → 0.5.172

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 68f6b7acd8107269dc0e15246d3990ef57d3afaa0516896c43fa2db3acfc4cc5
-  data.tar.gz: b6511730c2af6f71b66b1a07b118260fc76c6069bd000be29539beb7462522b5
+  metadata.gz: f8719e57bb76ceb63baa171d151028d8aff538fc351be7397b6ec5a492c8bdf1
+  data.tar.gz: 8fa85d23570f0588da0eb5d4ce5f83d59fb28e325d587f7210d3380a8afd5e33
 SHA512:
-  metadata.gz: b3c3f675bc7ecc526414d7cf045e33dbbcd14ff4b52794552a7ccd4d69b6efab0e3bf14cf5d56e05e3b48e7852795a6a9181ac15c98504233dac324c0c54a6ec
-  data.tar.gz: 47fdcc6d4e46766f75bf4927b89ae95931d8920e0fc5f8213a48167b2f5b19ded9f1807bbf13c2351e8735e71e3210f7829f913a7bbb2a82781ca88a68405729
+  metadata.gz: b93fc457a9d7435e2a55cb4fb5e3320d37b5949e77b184c640dd65a8b21954aab9987f204c8916411d9bfe6e11f7f0e358faa78f1ee9cfe3477f52b2d209e857
+  data.tar.gz: 78c66d6b3bdbb800b8cf23dde851235ab3a621bbb30fd0c413db06f9f856ba245b56f9a2c4a4d8220ca313b3bb2ef447d5737733387052bd82f2151cfd7bcdc5

data/README.adoc

@@ -95,7 +95,8 @@ adapter refuses to load below its floor.
 
 |Ox
 |>= 2.14
-|Tested against the 2.14 line.
+|DEPRECATED (#491) — warned at configuration; use :leptris (primary)
+or :nokogiri. Removal after the deprecation cycle.
 
 |Oga
 |3.4 / 3.5
@@ -105,8 +106,9 @@ moxml's customized generator and decoder overrides.
 
 |LibXML (libxml-ruby)
 |>= 5.0
-|6.x works and is the installed default on Ruby >= 3.2 (libxml-ruby
-6.0 itself requires Ruby >= 3.2); Ruby 3.1 resolves 5.x.
+|DEPRECATED (#491) — warned at configuration; use :nokogiri (the
+same libxml2 engine, governed by the consistency suite). Removal
+after the deprecation cycle.
 
 |Leptris (leptris-ruby)
 |>= 1.9.194.1
@@ -114,10 +116,7 @@ moxml's customized generator and decoder overrides.
 Raised from 1.9.32 (2026-09-20): every known consumer resolves a
 modern binding, and the sub-1.9.194 accommodation paths are deleted.
 Newer bindings unlock more native surface automatically:
-1.9.163.7+ single-result XPath seams, 1.9.174.4+ C-minted identity
-wrappers, 1.9.174.6+ one-dispatch subtree walks, 1.9.177+ first-class
-entity references (`entity_mode: :keep`), 1.9.193.4+ native plan rows
-(`Moxml::Plan`), 1.9.194.1+ hot-read aliases, 1.9.201.1+ the C struct
+1.9.194.1+ hot-read aliases, 1.9.201.1+ the C struct
 executor (`Moxml::StructPlan`; the floor is the varargs-mint fix),
 1.9.204+ native document-level parts (created DOCTYPEs as native
 nodes, document-PI removal, declaration clear), 1.9.240+ the bulk

data/Rakefile

@@ -350,4 +350,27 @@ namespace :docs do
   end
 end
 
+namespace :conformance do
+  desc "Export the cross-language conformance dataset to JSON (#496)"
+  task :export do
+    require "json"
+    require_relative "lib/moxml"
+    dataset = Moxml::XSD::BuiltinLexical::CONFORMANCE_CASES
+    payload = {
+      schema: 1,
+      generator: "moxml #{Moxml::VERSION}",
+      cases: {
+        "builtin_lexical" => dataset.map do |type, lexical, expected|
+          { "type" => type, "lexical" => lexical, "valid" => expected }
+        end,
+      },
+    }
+    dir = File.expand_path("conformance", __dir__)
+    FileUtils.mkdir_p(dir)
+    target = File.join(dir, "moxml-conformance.json")
+    File.write(target, "#{JSON.pretty_generate(payload)}\n")
+    puts "conformance: exported #{dataset.size} cases to #{target}"
+  end
+end
+
 task default: :spec

data/conformance/moxml-conformance.json

@@ -0,0 +1,413 @@
+{
+  "schema": 1,
+  "generator": "moxml 0.5.171",
+  "cases": {
+    "builtin_lexical": [
+      {
+        "type": "xs:token",
+        "lexical": "a  b",
+        "valid": true
+      },
+      {
+        "type": "xs:ID",
+        "lexical": " id ",
+        "valid": true
+      },
+      {
+        "type": "xs:NMTOKEN",
+        "lexical": "\tx ",
+        "valid": true
+      },
+      {
+        "type": "xs:ID",
+        "lexical": "1d",
+        "valid": false
+      },
+      {
+        "type": "xs:integer",
+        "lexical": "11111111111111111111111111111",
+        "valid": true
+      },
+      {
+        "type": "xs:positiveInteger",
+        "lexical": "11111111111111111111111111111",
+        "valid": true
+      },
+      {
+        "type": "xs:nonNegativeInteger",
+        "lexical": "11111111111111111111111111111",
+        "valid": true
+      },
+      {
+        "type": "xs:negativeInteger",
+        "lexical": "-100000000000000000000",
+        "valid": true
+      },
+      {
+        "type": "xs:nonPositiveInteger",
+        "lexical": "0",
+        "valid": true
+      },
+      {
+        "type": "xs:nonPositiveInteger",
+        "lexical": "-0",
+        "valid": true
+      },
+      {
+        "type": "xs:long",
+        "lexical": "9223372036854775807",
+        "valid": true
+      },
+      {
+        "type": "xs:long",
+        "lexical": "9223372036854775808",
+        "valid": false
+      },
+      {
+        "type": "xs:unsignedLong",
+        "lexical": "18446744073709551615",
+        "valid": true
+      },
+      {
+        "type": "xs:unsignedLong",
+        "lexical": "18446744073709551616",
+        "valid": false
+      },
+      {
+        "type": "xs:byte",
+        "lexical": "128",
+        "valid": false
+      },
+      {
+        "type": "xs:unsignedByte",
+        "lexical": "256",
+        "valid": false
+      },
+      {
+        "type": "xs:float",
+        "lexical": "+INF",
+        "valid": true
+      },
+      {
+        "type": "xs:double",
+        "lexical": "-INF",
+        "valid": true
+      },
+      {
+        "type": "xs:float",
+        "lexical": "NaN",
+        "valid": true
+      },
+      {
+        "type": "xs:float",
+        "lexical": "1.5E-3",
+        "valid": true
+      },
+      {
+        "type": "xs:decimal",
+        "lexical": "5.",
+        "valid": true
+      },
+      {
+        "type": "xs:decimal",
+        "lexical": ".5",
+        "valid": true
+      },
+      {
+        "type": "xs:decimal",
+        "lexical": "1e3",
+        "valid": false
+      },
+      {
+        "type": "xs:date",
+        "lexical": "2024-02-29",
+        "valid": true
+      },
+      {
+        "type": "xs:date",
+        "lexical": "1999-02-29",
+        "valid": false
+      },
+      {
+        "type": "xs:date",
+        "lexical": "2024-04-31",
+        "valid": false
+      },
+      {
+        "type": "xs:date",
+        "lexical": "2024-13-01",
+        "valid": false
+      },
+      {
+        "type": "xs:date",
+        "lexical": "not-a-date",
+        "valid": false
+      },
+      {
+        "type": "xs:dateTime",
+        "lexical": "2024-02-29T23:59:59Z",
+        "valid": true
+      },
+      {
+        "type": "xs:dateTime",
+        "lexical": "1999-02-29T00:00:00",
+        "valid": false
+      },
+      {
+        "type": "xs:dateTime",
+        "lexical": "not-a-date",
+        "valid": false
+      },
+      {
+        "type": "xs:dateTimeStamp",
+        "lexical": "2024-02-29T00:00:00Z",
+        "valid": true
+      },
+      {
+        "type": "xs:dateTimeStamp",
+        "lexical": "2024-02-29T00:00:00",
+        "valid": false
+      },
+      {
+        "type": "xs:time",
+        "lexical": "23:59:59.999+05:30",
+        "valid": true
+      },
+      {
+        "type": "xs:time",
+        "lexical": "24:00:00",
+        "valid": false
+      },
+      {
+        "type": "xs:time",
+        "lexical": "25:20:00",
+        "valid": false
+      },
+      {
+        "type": "xs:time",
+        "lexical": "13:20:60",
+        "valid": false
+      },
+      {
+        "type": "xs:gYearMonth",
+        "lexical": "2024-02Z",
+        "valid": true
+      },
+      {
+        "type": "xs:gYearMonth",
+        "lexical": "2024-13",
+        "valid": false
+      },
+      {
+        "type": "xs:gMonthDay",
+        "lexical": "--02-29",
+        "valid": true
+      },
+      {
+        "type": "xs:gMonthDay",
+        "lexical": "--02-30",
+        "valid": false
+      },
+      {
+        "type": "xs:gDay",
+        "lexical": "---31",
+        "valid": true
+      },
+      {
+        "type": "xs:gDay",
+        "lexical": "---32",
+        "valid": false
+      },
+      {
+        "type": "xs:duration",
+        "lexical": "P1Y2M3DT4H5M6.5S",
+        "valid": true
+      },
+      {
+        "type": "xs:duration",
+        "lexical": "PT0S",
+        "valid": true
+      },
+      {
+        "type": "xs:duration",
+        "lexical": "-P1D",
+        "valid": true
+      },
+      {
+        "type": "xs:duration",
+        "lexical": "P",
+        "valid": false
+      },
+      {
+        "type": "xs:duration",
+        "lexical": "PT",
+        "valid": false
+      },
+      {
+        "type": "xs:duration",
+        "lexical": "P1Y2MT",
+        "valid": false
+      },
+      {
+        "type": "xs:duration",
+        "lexical": "P200.5Y",
+        "valid": false
+      },
+      {
+        "type": "xs:dayTimeDuration",
+        "lexical": "P1DT2H",
+        "valid": true
+      },
+      {
+        "type": "xs:dayTimeDuration",
+        "lexical": "P1Y",
+        "valid": false
+      },
+      {
+        "type": "xs:yearMonthDuration",
+        "lexical": "P1Y2M",
+        "valid": true
+      },
+      {
+        "type": "xs:yearMonthDuration",
+        "lexical": "P1D",
+        "valid": false
+      },
+      {
+        "type": "xs:yearMonthDuration",
+        "lexical": "P1YT1H",
+        "valid": false
+      },
+      {
+        "type": "xs:base64Binary",
+        "lexical": "aGVsbG8=",
+        "valid": true
+      },
+      {
+        "type": "xs:base64Binary",
+        "lexical": "abcd",
+        "valid": true
+      },
+      {
+        "type": "xs:base64Binary",
+        "lexical": "abcde",
+        "valid": false
+      },
+      {
+        "type": "xs:base64Binary",
+        "lexical": "a b",
+        "valid": false
+      },
+      {
+        "type": "xs:hexBinary",
+        "lexical": "0A",
+        "valid": true
+      },
+      {
+        "type": "xs:hexBinary",
+        "lexical": "0AB",
+        "valid": false
+      },
+      {
+        "type": "xs:QName",
+        "lexical": "foo",
+        "valid": true
+      },
+      {
+        "type": "xs:QName",
+        "lexical": "ns:foo",
+        "valid": true
+      },
+      {
+        "type": "xs:QName",
+        "lexical": "xmlns:xsi",
+        "valid": false
+      },
+      {
+        "type": "xs:QName",
+        "lexical": ":foo",
+        "valid": false
+      },
+      {
+        "type": "xs:QName",
+        "lexical": "a:b:c",
+        "valid": false
+      },
+      {
+        "type": "xs:NOTATION",
+        "lexical": "foo",
+        "valid": true
+      },
+      {
+        "type": "xs:IDREFS",
+        "lexical": "a b",
+        "valid": true
+      },
+      {
+        "type": "xs:IDREFS",
+        "lexical": "a",
+        "valid": true
+      },
+      {
+        "type": "xs:IDREFS",
+        "lexical": "",
+        "valid": false
+      },
+      {
+        "type": "xs:NMTOKENS",
+        "lexical": "a.b-c:d e",
+        "valid": true
+      },
+      {
+        "type": "xs:ENTITIES",
+        "lexical": "a 1",
+        "valid": false
+      },
+      {
+        "type": "xs:string",
+        "lexical": "anything <>&",
+        "valid": true
+      },
+      {
+        "type": "xs:anyURI",
+        "lexical": "http://example.com/a b",
+        "valid": true
+      },
+      {
+        "type": "xs:boolean",
+        "lexical": "true",
+        "valid": true
+      },
+      {
+        "type": "xs:boolean",
+        "lexical": "0",
+        "valid": true
+      },
+      {
+        "type": "xs:boolean",
+        "lexical": "TRUE",
+        "valid": false
+      },
+      {
+        "type": "xs:language",
+        "lexical": "en-US",
+        "valid": true
+      },
+      {
+        "type": "xs:language",
+        "lexical": "en_US",
+        "valid": false
+      },
+      {
+        "type": "xs:Name",
+        "lexical": "a:b",
+        "valid": true
+      },
+      {
+        "type": "xs:NCName",
+        "lexical": "a:b",
+        "valid": false
+      }
+    ]
+  }
+}

data/lib/moxml/adapter/customized_leptris/declaration.rb

@@ -1,5 +1,14 @@
 # frozen_string_literal: true
 
+# Wrapper for an XML declaration.
+#
+# Lifecycle record: libleptris models the declaration as document-state
+# flags — setters shipped (leptris#1094) and clear shipped
+# (leptris#1229, binding 1.9.204.0) — but there is still no first-class
+# declaration NODE, so the facade keeps this mutable, removable value
+# object as the node stand-in. Dissolves when libleptris exposes
+# declaration node identity (leptris#1904's successor surface).
+
 module Moxml
   module Adapter
     module CustomizedLeptris

data/lib/moxml/adapter/customized_leptris/doctype.rb

@@ -1,5 +1,13 @@
 # frozen_string_literal: true
 
+# Wrapper for a programmatic DOCTYPE.
+#
+# Lifecycle record: set shipped (leptris#212, binding 1.9.176) and unset
+# shipped (leptris#1229, binding 1.9.204.0 remove_doctype), but there is
+# still no first-class DOCTYPE NODE — the facade keeps this value object
+# as the node stand-in in the document's attachments. Dissolves with
+# declaration node identity (see customized_leptris/declaration.rb).
+
 module Moxml
   module Adapter
     module CustomizedLeptris

data/lib/moxml/adapter/customized_leptris/entity_reference.rb

@@ -1,5 +1,13 @@
 # frozen_string_literal: true
 
+# Parse-path face: libleptris expands the five built-in entities at
+# parse time and has no custom ones, so parsed references are carried
+# as Moxml::Entity::Reference values over marker-bearing text.
+# Programmatic creation is native (NATIVE_ENTITY_REFS, binding >= 1.9.177).
+#
+# Lifecycle record: dissolves when parse-time entity reference retention
+# ships — leptris#1904 (references as nodes or bulk positions).
+
 module Moxml
   module Adapter
     module CustomizedLeptris

data/lib/moxml/adapter/customized_leptris/text_segment.rb

@@ -1,5 +1,13 @@
 # frozen_string_literal: true
 
+# A text run split out of a native text node that carried entity
+# markers. Value object: the moxml contract exposes text nodes as
+# separate children around entity references, while libleptris stores
+# them as one marker-bearing text node.
+#
+# Lifecycle record: dissolves with entity reference retention —
+# leptris#1904 (see customized_leptris/entity_reference.rb).
+
 module Moxml
   module Adapter
     module CustomizedLeptris

data/lib/moxml/adapter/customized_leptris.rb

@@ -7,6 +7,11 @@ module Moxml
     # and document-level processing instructions.
     # The adapter stores them via NativeAttachment and serializes them
     # from #to_xml.
+    #
+    # Lifecycle record (#495): a tracked shim, not an adapter-fate
+    # case — the parse-time entity-retention gap is the last engine
+    # ask of the #275 mutation-completion round; when the engine ships
+    # native retention these classes dissolve into Base.
     module CustomizedLeptris
       autoload :Declaration, "moxml/adapter/customized_leptris/declaration"
       autoload :Doctype, "moxml/adapter/customized_leptris/doctype"

data/lib/moxml/adapter/customized_libxml/cdata.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+# Lifecycle record: the :libxml adapter is deprecated (#491); this wrapper dies with it.
+
 module Moxml
   module Adapter
     module CustomizedLibxml

data/lib/moxml/adapter/customized_libxml/comment.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+# Lifecycle record: the :libxml adapter is deprecated (#491); this wrapper dies with it.
+
 module Moxml
   module Adapter
     module CustomizedLibxml

data/lib/moxml/adapter/customized_libxml/declaration.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+# Lifecycle record: the :libxml adapter is deprecated (#491); this wrapper dies with it.
+
 module Moxml
   module Adapter
     module CustomizedLibxml

data/lib/moxml/adapter/customized_libxml/element.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+# Lifecycle record: the :libxml adapter is deprecated (#491); this wrapper dies with it.
+
 module Moxml
   module Adapter
     module CustomizedLibxml

data/lib/moxml/adapter/customized_libxml/entity_reference.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+# Lifecycle record: the :libxml adapter is deprecated (#491); this wrapper dies with it.
+
 module Moxml
   module Adapter
     module CustomizedLibxml

data/lib/moxml/adapter/customized_libxml/node.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+# Lifecycle record: the :libxml adapter is deprecated (#491); this wrapper dies with it.
+
 module Moxml
   module Adapter
     module CustomizedLibxml

data/lib/moxml/adapter/customized_libxml/processing_instruction.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+# Lifecycle record: the :libxml adapter is deprecated (#491); this wrapper dies with it.
+
 module Moxml
   module Adapter
     module CustomizedLibxml

data/lib/moxml/adapter/customized_libxml/text.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+# Lifecycle record: the :libxml adapter is deprecated (#491); this wrapper dies with it.
+
 module Moxml
   module Adapter
     module CustomizedLibxml

data/lib/moxml/adapter/customized_libxml.rb

@@ -2,6 +2,9 @@
 
 module Moxml
   module Adapter
+    # Lifecycle record (#495): engine-gap shims for the :libxml
+    # adapter, deprecated in moxml#491 -- removed with it after the
+    # cycle. No separate upstream ask; the adapter's fate governs.
     module CustomizedLibxml
       autoload :Cdata, "moxml/adapter/customized_libxml/cdata"
       autoload :Comment, "moxml/adapter/customized_libxml/comment"

data/lib/moxml/adapter/customized_oga/entity_decoder.rb

@@ -1,5 +1,13 @@
 # frozen_string_literal: true
 
+# Override Oga::EntityDecoder.decode for XML inputs.
+#
+# Engine gap (upstream oga): Oga 3.4's stock Oga::XML::Entities.decode
+# runs multiple passes, turning the well-formed "&" into "&"
+# rather than the correct "&". Upstream tracker:
+# https://github.com/yorickpeterse/oga — the override stays until oga
+# fixes the decoder or the adapter is retired.
+
 require "oga"
 
 module Moxml

data/lib/moxml/adapter/customized_oga/raw_value_override.rb

@@ -1,5 +1,13 @@
 # frozen_string_literal: true
 
+# Bypass Oga's lazy decoder for user-authored values.
+#
+# Engine gap (upstream oga): Oga::XML::Attribute#value and
+# Oga::XML::Text#text decode @value/@text on first read via
+# Oga::EntityDecoder; EntityDecoderOverride (this directory) must hold
+# user-authored raw values. Upstream tracker:
+# https://github.com/yorickpeterse/oga
+
 require "oga"
 
 module Moxml

data/lib/moxml/adapter/customized_oga/xml_declaration.rb

@@ -1,5 +1,13 @@
 # frozen_string_literal: true
 
+# Stand-in XML declaration node.
+#
+# Engine gap (upstream oga): Oga::XML::XmlDeclaration is not writable —
+# version/encoding/standalone cannot be set on an instance the way the
+# facade contract requires, so this subclass owns the state and renders
+# the declaration itself. Upstream tracker:
+# https://github.com/yorickpeterse/oga
+
 require "oga"
 
 module Moxml