lutaml-model 0.8.36 → 0.8.38

data/lib/lutaml/xml/html_entities.rb

@@ -0,0 +1,290 @@
+# frozen_string_literal: true
+
+# lutaml-model#154: HTML 4.01 named entity table (plus apos) for opt-in
+# decoding of HTML entities in XML text (MathML and friends rely on
+# them although XML itself defines none beyond the predefined five).
+
+module Lutaml
+  module Xml
+    module HtmlEntities
+      # The table is the data: a gem dependency or data file for a static
+      # W3C list would cost more than the frozen literal itself.
+      # The table is the data: a gem dependency or data file for a static
+      # W3C list would cost more than the frozen literal itself.
+      NAMED_TO_CODEPOINT = { # rubocop:disable Metrics/CollectionLiteralLength
+        "AElig" => 198,
+        "Aacute" => 193,
+        "Acirc" => 194,
+        "Agrave" => 192,
+        "Alpha" => 913,
+        "Aring" => 197,
+        "Atilde" => 195,
+        "Auml" => 196,
+        "Beta" => 914,
+        "Ccedil" => 199,
+        "Chi" => 935,
+        "Dagger" => 8225,
+        "Delta" => 916,
+        "ETH" => 208,
+        "Eacute" => 201,
+        "Ecirc" => 202,
+        "Egrave" => 200,
+        "Epsilon" => 917,
+        "Eta" => 919,
+        "Euml" => 203,
+        "Gamma" => 915,
+        "Iacute" => 205,
+        "Icirc" => 206,
+        "Igrave" => 204,
+        "Iota" => 921,
+        "Iuml" => 207,
+        "Kappa" => 922,
+        "Lambda" => 923,
+        "Mu" => 924,
+        "Ntilde" => 209,
+        "Nu" => 925,
+        "OElig" => 338,
+        "Oacute" => 211,
+        "Ocirc" => 212,
+        "Ograve" => 210,
+        "Omega" => 937,
+        "Omicron" => 927,
+        "Oslash" => 216,
+        "Otilde" => 213,
+        "Ouml" => 214,
+        "Phi" => 934,
+        "Pi" => 928,
+        "Prime" => 8243,
+        "Psi" => 936,
+        "Rho" => 929,
+        "Scaron" => 352,
+        "Sigma" => 931,
+        "THORN" => 222,
+        "Tau" => 932,
+        "Theta" => 920,
+        "Uacute" => 218,
+        "Ucirc" => 219,
+        "Ugrave" => 217,
+        "Upsilon" => 933,
+        "Uuml" => 220,
+        "Xi" => 926,
+        "Yacute" => 221,
+        "Yuml" => 376,
+        "Zeta" => 918,
+        "aacute" => 225,
+        "acirc" => 226,
+        "acute" => 180,
+        "aelig" => 230,
+        "agrave" => 224,
+        "alefsym" => 8501,
+        "alpha" => 945,
+        "amp" => 38,
+        "and" => 8743,
+        "ang" => 8736,
+        "apos" => 39,
+        "aring" => 229,
+        "asymp" => 8776,
+        "atilde" => 227,
+        "auml" => 228,
+        "bdquo" => 8222,
+        "beta" => 946,
+        "brvbar" => 166,
+        "bull" => 8226,
+        "cap" => 8745,
+        "ccedil" => 231,
+        "cedil" => 184,
+        "cent" => 162,
+        "chi" => 967,
+        "circ" => 710,
+        "clubs" => 9827,
+        "cong" => 8773,
+        "copy" => 169,
+        "crarr" => 8629,
+        "cup" => 8746,
+        "curren" => 164,
+        "dArr" => 8659,
+        "dagger" => 8224,
+        "darr" => 8595,
+        "deg" => 176,
+        "delta" => 948,
+        "diams" => 9830,
+        "divide" => 247,
+        "eacute" => 233,
+        "ecirc" => 234,
+        "egrave" => 232,
+        "empty" => 8709,
+        "emsp" => 8195,
+        "ensp" => 8194,
+        "epsilon" => 949,
+        "equiv" => 8801,
+        "eta" => 951,
+        "eth" => 240,
+        "euml" => 235,
+        "euro" => 8364,
+        "exist" => 8707,
+        "fnof" => 402,
+        "forall" => 8704,
+        "frac12" => 189,
+        "frac14" => 188,
+        "frac34" => 190,
+        "frasl" => 8260,
+        "gamma" => 947,
+        "ge" => 8805,
+        "gt" => 62,
+        "hArr" => 8660,
+        "harr" => 8596,
+        "hearts" => 9829,
+        "hellip" => 8230,
+        "iacute" => 237,
+        "icirc" => 238,
+        "iexcl" => 161,
+        "igrave" => 236,
+        "image" => 8465,
+        "infin" => 8734,
+        "int" => 8747,
+        "iota" => 953,
+        "iquest" => 191,
+        "isin" => 8712,
+        "iuml" => 239,
+        "kappa" => 954,
+        "lArr" => 8656,
+        "lambda" => 955,
+        "lang" => 9001,
+        "laquo" => 171,
+        "larr" => 8592,
+        "lceil" => 8968,
+        "ldquo" => 8220,
+        "le" => 8804,
+        "lfloor" => 8970,
+        "lowast" => 8727,
+        "loz" => 9674,
+        "lrm" => 8206,
+        "lsaquo" => 8249,
+        "lsquo" => 8216,
+        "lt" => 60,
+        "macr" => 175,
+        "mdash" => 8212,
+        "micro" => 181,
+        "middot" => 183,
+        "minus" => 8722,
+        "mu" => 956,
+        "nabla" => 8711,
+        "nbsp" => 160,
+        "ndash" => 8211,
+        "ne" => 8800,
+        "ni" => 8715,
+        "not" => 172,
+        "notin" => 8713,
+        "nsub" => 8836,
+        "ntilde" => 241,
+        "nu" => 957,
+        "oacute" => 243,
+        "ocirc" => 244,
+        "oelig" => 339,
+        "ograve" => 242,
+        "oline" => 8254,
+        "omega" => 969,
+        "omicron" => 959,
+        "oplus" => 8853,
+        "or" => 8744,
+        "ordf" => 170,
+        "ordm" => 186,
+        "oslash" => 248,
+        "otilde" => 245,
+        "otimes" => 8855,
+        "ouml" => 246,
+        "para" => 182,
+        "part" => 8706,
+        "permil" => 8240,
+        "perp" => 8869,
+        "phi" => 966,
+        "pi" => 960,
+        "piv" => 982,
+        "plusmn" => 177,
+        "pound" => 163,
+        "prime" => 8242,
+        "prod" => 8719,
+        "prop" => 8733,
+        "psi" => 968,
+        "quot" => 34,
+        "rArr" => 8658,
+        "radic" => 8730,
+        "rang" => 9002,
+        "raquo" => 187,
+        "rarr" => 8594,
+        "rceil" => 8969,
+        "rdquo" => 8221,
+        "real" => 8476,
+        "reg" => 174,
+        "rfloor" => 8971,
+        "rho" => 961,
+        "rlm" => 8207,
+        "rsaquo" => 8250,
+        "rsquo" => 8217,
+        "sbquo" => 8218,
+        "scaron" => 353,
+        "sdot" => 8901,
+        "sect" => 167,
+        "shy" => 173,
+        "sigma" => 963,
+        "sigmaf" => 962,
+        "sim" => 8764,
+        "spades" => 9824,
+        "sub" => 8834,
+        "sube" => 8838,
+        "sum" => 8721,
+        "sup" => 8835,
+        "sup1" => 185,
+        "sup2" => 178,
+        "sup3" => 179,
+        "supe" => 8839,
+        "szlig" => 223,
+        "tau" => 964,
+        "there4" => 8756,
+        "theta" => 952,
+        "thetasym" => 977,
+        "thinsp" => 8201,
+        "thorn" => 254,
+        "tilde" => 732,
+        "times" => 215,
+        "trade" => 8482,
+        "uArr" => 8657,
+        "uacute" => 250,
+        "uarr" => 8593,
+        "ucirc" => 251,
+        "ugrave" => 249,
+        "uml" => 168,
+        "upsih" => 978,
+        "upsilon" => 965,
+        "uuml" => 252,
+        "weierp" => 8472,
+        "xi" => 958,
+        "yacute" => 253,
+        "yen" => 165,
+        "yuml" => 255,
+        "zeta" => 950,
+        "zwj" => 8205,
+        "zwnj" => 8204,
+      }.freeze
+
+      NAME_PATTERN = /&(#x?[0-9A-Fa-f]+|[A-Za-z][A-Za-z0-9]*);/
+
+      module_function
+
+      def decode(value)
+        value.gsub(NAME_PATTERN) do |match|
+          body = match[1..-2]
+          case body[0]
+          when "x", "X"
+            body[1..].to_i(16).chr(Encoding::UTF_8)
+          when "#"
+            body[1..].to_i.chr(Encoding::UTF_8)
+          else
+            codepoint = NAMED_TO_CODEPOINT[body]
+            codepoint ? codepoint.chr(Encoding::UTF_8) : match
+          end
+        end
+      end
+    end
+  end
+end

data/lib/lutaml/xml/mapping.rb

@@ -84,6 +84,7 @@ module Lutaml
         @cached_elements = {}
         @cached_attributes = {}
         @cached_mappings = {}
+        @cached_attribute_name_counts = {}
         @finalized = false
       end
 
@@ -98,6 +99,17 @@ module Lutaml
         # Resolve any deferred mapping imports before finalizing
         ensure_mappings_imported!
 
+        # lutaml-model#687: nested sequence choices tag their target
+        # model attributes now that the mapper class is known.
+        @element_sequence.each do |seq|
+          seq.bind_choice_compositors!(mapper_class)
+        end
+
+        # lutaml-model#296: a mapped rule whose attribute type can never
+        # accept the serialization shape fails here, with the attribute
+        # and type named, instead of surfacing mid-parse as a cast oddity.
+        validate_mapped_attribute_types!(mapper_class)
+
         # Validate mixed content requires collection attribute for content mapping
         validate_mixed_content_collection!(mapper_class)
 
@@ -108,9 +120,17 @@ module Lutaml
         @cached_elements.clear
         @cached_attributes.clear
         @cached_mappings.clear
+        @cached_attribute_name_counts.clear
+        @rule_records_version = (@rule_records_version || 0) + 1
         @finalized = true
       end
 
+      # Bumped at finalize; ModelTransform's compiled rule records are
+      # keyed on it so late mapping changes rebuild instead of going stale.
+      def rule_records_version
+        @rule_records_version ||= 0
+      end
+
       def finalized?
         @finalized
       end
@@ -1028,6 +1048,26 @@ module Lutaml
         end
       end
 
+      # Fire InvalidAttributeTypeError at definition time for mapped
+      # rules whose target attribute type is neither a Type::Value nor
+      # Serializable (lutaml-model#296). Undeclared types are left to
+      # deferred-import resolution.
+      def validate_mapped_attribute_types!(mapper_class)
+        (elements + attributes).each do |rule|
+          target = mapper_class.attributes[rule.to]
+          next unless target
+
+          begin
+            resolved = target.type(Lutaml::Model::Config.default_register)
+          rescue Lutaml::Model::UnknownTypeError
+            next
+          end
+          next unless resolved.is_a?(Class)
+
+          target.validate_attr_type!(resolved)
+        end
+      end
+
       def elements(register_id = nil)
         reg_key = register_id || :default
         cached = @cached_elements[reg_key]
@@ -1060,6 +1100,26 @@ module Lutaml
         @raw_mapping
       end
 
+      # lutaml-model#790/#791: whether `rule` is the only attribute rule
+      # claiming its exact name spelling. The answer is a property of the
+      # mapping, not the document, so it is counted once per register
+      # (rules sharing a spelling make each other non-sole).
+      def sole_local_attribute_claimant?(rule, register_id = nil)
+        reg_key = register_id || :default
+        counts = @cached_attribute_name_counts[reg_key]
+        unless counts
+          counts = {}
+          attributes(register_id).each do |r|
+            key = r.name_strings
+            counts[key] = (counts[key] || 0) + 1
+          end
+          counts.freeze if @finalized
+          @cached_attribute_name_counts[reg_key] = counts
+        end
+
+        (counts[rule.name_strings] || 1) == 1
+      end
+
       def mappings(register_id = nil)
         reg_key = register_id || :default
         cached = @cached_mappings[reg_key]
@@ -1281,6 +1341,18 @@ module Lutaml
         !@namespace_class.nil?
       end
 
+      # lutaml-model#154: opt-in decoding of HTML named/numeric entities
+      # (e.g. ©, —) in mapped text and attribute values. XML
+      # documents are otherwise kept byte-faithful: HTML entities are not
+      # defined in XML without a DTD.
+      def html_entities(enabled: true)
+        @decode_html_entities = enabled
+      end
+
+      def decode_html_entities?
+        !!@decode_html_entities
+      end
+
       # Whether namespace was explicitly set via DSL
       def namespace_set?
         !!@namespace_set