moxml 0.5.12 → 0.5.14

data/lib/moxml/adapter/leptris.rb

@@ -27,12 +27,38 @@ module Moxml
       # DTD ATTLIST defaults, matching libxml2/Nokogiri semantics;
       # ParseOptions::DTDATTR opts in (leptris/leptris#606).
       DTDATTR_SUPPORTED = ::Leptris::XML::ParseOptions.const_defined?(:DTDATTR)
-      # leptris-ruby 1.9.32 (#89): traverse is subtree-bounded again —
-      # earlier 1.9.x walks followed the document chain and swept
-      # following siblings, so element materialize had to fall back
-      # to the generic wrapper walk.
-      TRAVERSE_SUBTREE_BOUNDED =
-        Gem::Version.new(::Leptris::VERSION) >= Gem::Version.new("1.9.32")
+
+      # The raw field-read surface for the bulk materializer (issue
+      # #143). Bindings without the full set fall back to the generic
+      # wrapper walk.
+      BULK_FIELD_READS = %i[
+        leptris_node_children leptris_node_get_type
+        leptris_element_name leptris_element_prefix leptris_element_namespace
+        leptris_element_namespace_count leptris_element_namespace_decl_prefix
+        leptris_element_namespace_decl_uri leptris_element_first_attribute
+        leptris_attribute_get_name leptris_attribute_get_value
+        leptris_attribute_next leptris_attribute_namespace_uri
+        leptris_text_node_get_content leptris_cdata_node_get_content
+        leptris_comment_node_get_content leptris_pi_node_get_target
+        leptris_pi_node_get_data
+      ].all? { |fn| ::Leptris::XML::FFI.respond_to?(fn) }
+
+      NO_PARSE_ERRORS = [].freeze
+      private_constant :NO_PARSE_ERRORS
+
+      # Cohesive clusters extracted from this class — the adapter
+      # protocol surface is unchanged; the modules hold the document
+      # parts assembly, the entity-marker pipeline, and the bulk
+      # materializer respectively.
+      autoload :DocumentParts, "moxml/adapter/leptris/document_parts"
+      autoload :Markers, "moxml/adapter/leptris/markers"
+      autoload :Materialize, "moxml/adapter/leptris/materialize"
+      autoload :Serialize, "moxml/adapter/leptris/serialize"
+      autoload :LeptrisSAXBridge, "moxml/adapter/leptris/sax_bridge"
+      extend Serialize
+      extend DocumentParts
+      extend Markers
+      extend Materialize
 
       class << self
         def attachments
@@ -63,9 +89,12 @@ module Moxml
           rescue ::Leptris::XML::ParseError => e
             # libleptris has no recovery mode that survives unclosed
             # tags; non-strict callers get an empty document, matching
-            # the Libxml adapter's non-strict behavior.
+            # the Libxml adapter's non-strict behavior. The fatal
+            # error rides the document as parse diagnostics (issue
+            # #147) — otherwise nothing says why it came back empty.
             raise Moxml::ParseError.new(e.message) if options[:strict]
 
+            recover_errors = [e.message]
             create_document
           end
           ctx = _context || Context.new(:leptris)
@@ -73,6 +102,7 @@ module Moxml
 
           record_source_declaration(native_doc, processed)
           attachments.set(native_doc, :entity_markers, entity_markers)
+          attachments.set(native_doc, :parse_errors, recover_errors) if recover_errors
 
           doc
         end
@@ -85,20 +115,8 @@ module Moxml
           ::Leptris::XML::ParseOptions.dtdattr
         end
 
-        # Issue #134: deterministic release of the C tree. The binding
-        # clears its wrapper cache and raises UseAfterFreeError on
-        # later access; moxml-side attachments for the document are
-        # swept too (the context wrapper identity map self-cleans via
-        # its size valve).
-        DOCUMENT_ATTACHMENT_KEYS = %i[
-          entity_markers doc_pi_nodes declaration doctype
-          had_source_declaration document_text
-        ].freeze
-
-        def free_document(native)
-          DOCUMENT_ATTACHMENT_KEYS.each { |key| attachments.delete(native, key) }
-          native.free
-          nil
+        def parse_errors(native_doc)
+          attachments.get(native_doc, :parse_errors) || NO_PARSE_ERRORS
         end
 
         def create_document(_native_doc = nil)
@@ -258,136 +276,6 @@ module Moxml
           node.target
         end
 
-        # Marker presence is a document-level fact: parse records it,
-        # the ER builder path flips it, and the split/restore scans
-        # consult it. Customized natives only exist as split products
-        # of marker-bearing text, so they always report true.
-        def entity_bearing?(native)
-          case native
-          when CustomizedLeptris::Declaration, CustomizedLeptris::Doctype,
-               CustomizedLeptris::EntityReference, CustomizedLeptris::TextSegment,
-               CustomizedLeptris::DocumentPI
-            true
-          else
-            doc = native.document
-            doc.nil? || attachments.get(doc, :entity_markers) != false
-          end
-        end
-
-        # Bulk materialization (issue #132): leptris_node_traverse
-        # walks the subtree with one FFI call; the only per-node cost
-        # is the C->Ruby callback and the property reads below. No
-        # Moxml::Node or Attribute wrapper is allocated.
-        def bulk_materialize?
-          true
-        end
-
-        def materialize_records(native, &block)
-          doc = native.is_a?(::Leptris::XML::Document) ? native : native.document
-          # Marker-bearing text needs the split pipeline (children-level
-          # ER expansion); the bulk path has no marker handling.
-          return nil if doc.nil? || attachments.get(doc, :entity_markers)
-
-          # On bindings whose traverse follows the document chain
-          # (leptris 1.9.28–1.9.31), element materialize falls back to
-          # the generic wrapper walk — only document materialization
-          # can filter safely there (issue #140).
-          root = if native.is_a?(::Leptris::XML::Document)
-                   doc.root
-                 else
-                   return nil unless TRAVERSE_SUBTREE_BOUNDED
-
-                   native
-                 end
-          return nil if root.nil?
-
-          depth_memo = {}.compare_by_identity
-          root.traverse do |node|
-            depth = material_depth_in_subtree(node, root, depth_memo)
-            next if depth.nil?
-
-            record = case node
-                     when ::Leptris::XML::Element
-                       element_material_record(node, depth)
-                     when ::Leptris::XML::CDATA
-                       # CDATA < Text in the binding: this arm must come
-                       # first or CDATA content reports as text.
-                       text_material_record(:cdata, node.content, depth)
-                     when ::Leptris::XML::Text
-                       text_material_record(:text, node.content, depth)
-                     when ::Leptris::XML::Comment
-                       text_material_record(:comment, node.content, depth)
-                     when ::Leptris::XML::ProcessingInstruction
-                       text_material_record(:processing_instruction, node.content, depth)
-                         .merge(qname: node.target)
-                     end
-            yield(record) if record
-          end
-          true
-        end
-
-        def element_material_record(node, depth)
-          attributes = node.each_attribute.map do |attr|
-            # Local name + separate prefix, matching the generic
-            # path's resolver semantics (moxml's canonical shape).
-            name = attr.name
-            prefix = attr.prefix
-            name = name.split(":", 2)[1] || name if prefix
-            [name, attr.value, attr.namespace_uri, prefix]
-          end
-          ns = node.namespace
-          {
-            kind: :element,
-            qname: node.name,
-            prefix: node.prefix,
-            namespace_uri: ns&.href,
-            # Own declarations only — same shape as the generic
-            # path's Element#declared_namespaces (issue #138).
-            namespaces: begin
-              decls = node.namespace_definitions.map { |d| [d.prefix, d.href] }
-              decls.empty? ? Materializer::EMPTY_ATTRIBUTES : decls
-            end,
-            attributes: attributes,
-            text: nil,
-            depth: depth,
-          }
-        end
-
-        def text_material_record(kind, text, depth)
-          {
-            kind: kind,
-            qname: nil,
-            prefix: nil,
-            namespace_uri: nil,
-            namespaces: Materializer::EMPTY_ATTRIBUTES,
-            attributes: Materializer::EMPTY_ATTRIBUTES,
-            text: text,
-            depth: depth,
-          }
-        end
-
-        # Depth relative to the subtree root, or nil when the node
-        # lies outside it (traverse follows the document chain since
-        # leptris 1.9.28, so epilog siblings can appear in the
-        # stream). Binding wrappers are address-stable and #parent is
-        # memoized, so each edge resolves once through the
-        # identity-keyed memo.
-        def material_depth_in_subtree(node, root, memo)
-          memo[node] ||= if node.equal?(root)
-                           0
-                         else
-                           parent = node.parent
-                           if parent.nil? || parent.is_a?(::Leptris::XML::Document)
-                             nil
-                           else
-
-                             parent_depth = material_depth_in_subtree(parent, root, memo)
-                             parent_depth.nil? ? nil : parent_depth + 1
-
-                           end
-                         end
-        end
-
         def node_type(node)
           # Frequency-ordered: elements and text dominate every real
           # document, and Node.wrap dispatches here once per cold
@@ -465,32 +353,6 @@ module Moxml
           end
         end
 
-        # Expand marker-bearing text nodes into the child sequence the
-        # moxml contract exposes: text, EntityReference, text, ...
-        def split_entity_markers(natives, parent)
-          result = []
-          natives.each do |child|
-            # FFI Text#content returns a fresh unfrozen BINARY string:
-            # retag in place (dup would be a throwaway allocation), but
-            # before include? — BINARY.include? with the UTF-8 marker raises
-            if child.is_a?(::Leptris::XML::Text)
-              content = child.content
-              content.force_encoding("UTF-8")
-            end
-            if content&.include?(Entity::MARKER)
-              content.scan(/([^#{Entity::MARKER}]*)(?:#{Entity::MARKER}([\w.:-]+);)?/o) do
-                text_part = Regexp.last_match(1)
-                name = Regexp.last_match(2)
-                result << CustomizedLeptris::TextSegment.new(text_part, parent) unless text_part.empty?
-                result << CustomizedLeptris::EntityReference.new(name) if name
-              end
-            else
-              result << child
-            end
-          end
-          result
-        end
-
         def parent(node)
           case node
           when ::Leptris::XML::Document then nil
@@ -843,6 +705,7 @@ module Moxml
             ast = XPath::Parser.parse_with_cache(expression)
             next false if ast_contains_type?(ast, :variable)
             next false if uses_xmlns_prefix?(ast)
+            next false if prefixed_attribute_test?(ast)
 
             !selects_attribute_results?(ast)
           end
@@ -882,6 +745,24 @@ module Moxml
           end
         end
 
+        # Some released native engines do not match prefixed attribute
+        # tests inside predicates (@p:kind='a'); the Ruby engine does.
+        # An attribute test is a :test whose parent axis is
+        # "attribute"; bare ones (namespace nil) stay native.
+        def prefixed_attribute_test?(ast, parent_axis = nil)
+          if ast.type == :test && parent_axis == "attribute"
+            ns = ast.value[:namespace]
+            return true if ns && !ns.empty? && ns != "xmlns"
+          end
+
+          axis = ast.children.first if ast.type == :axis
+
+          ast.children.any? do |child|
+            child.is_a?(XPath::AST::Node) &&
+              prefixed_attribute_test?(child, axis || (child.type == :axis ? nil : parent_axis))
+          end
+        end
+
         def engine_xpath(node, expression, namespaces = {})
           unless node.is_a?(Moxml::Node)
             node = Moxml::Node.wrap(node, Context.new(:leptris))
@@ -909,191 +790,6 @@ module Moxml
           end
         end
 
-        def serialize(node, options = {})
-          # Entity restoration belongs to the wrapper layer
-          # (Node#to_xml runs adapter.restore_entities for every
-          # adapter); doing it here scanned the output a second time.
-          normalize_serialization(raw_serialize(node, options), options)
-        end
-
-        def raw_serialize(node, options)
-          # CDATA must precede Text in this chain: CDATA < Text in the
-          # binding, so a Text branch first would swallow CDATA nodes.
-          case node
-          when CustomizedLeptris::Declaration, CustomizedLeptris::Doctype,
-               CustomizedLeptris::EntityReference, CustomizedLeptris::DocumentPI
-            return node.to_xml
-          when ::Leptris::XML::CDATA
-            return XmlEmitter.cdata(node.content)
-          when ::Leptris::XML::Comment
-            return "<!--#{node.content}-->"
-          when ::Leptris::XML::ProcessingInstruction
-            content = node.content.to_s
-            return content.empty? ? "<?#{node.target}?>" : "<?#{node.target} #{content}?>"
-          when ::Leptris::XML::Text, CustomizedLeptris::TextSegment
-            return XmlEmitter.escape_text(node.content.to_s)
-          when ::Leptris::XML::Document
-            return serialize_document(node, options)
-          end
-
-          include_decl = options.fetch(:declaration) do
-            options[:no_declaration] ? false : document_has_declaration?(node)
-          end
-          node.to_xml(
-            indent: options.fetch(:indent, 0),
-            no_decl: !include_decl,
-            encoding: options[:encoding],
-          )
-        end
-
-        # moxml canonical serialization: apostrophes stay literal
-        # (only & < > " are escaped) and empty elements expand when the
-        # caller asked for it — matching the other adapters' contract.
-        # Runs segment-aware: CDATA content is literal and must not be
-        # touched.
-        # Regions whose content is literal and must never be rewritten.
-        # Scanned positionally (String#index), not with a regex: the
-        # scan is linear in the input length, so pathological document
-        # content cannot blow up the serializer.
-        LITERAL_REGIONS = {
-          "<!--" => "-->",
-          "<![CDATA[" => "]]>",
-          "<?" => "?>",
-        }.freeze
-
-        def normalize_serialization(xml, options)
-          needs_apos = xml.include?("&apos;")
-          needs_expand = options[:expand_empty] && xml.include?("/>")
-          return xml unless needs_apos || needs_expand
-
-          out = +""
-          pos = 0
-          while pos < xml.length
-            opener_at, terminator = next_literal_region(xml, pos)
-            if opener_at.nil?
-              out << normalize_markup(xml[pos..], needs_apos, needs_expand)
-              break
-            end
-
-            out << normalize_markup(xml[pos...opener_at], needs_apos, needs_expand)
-            search_from = opener_at + opener_at_offset(terminator)
-            close = xml.index(terminator, search_from)
-            close_end = close.nil? ? xml.length : close + terminator.length
-            out << xml[opener_at...close_end]
-            pos = close_end
-          end
-          out
-        end
-
-        # Nearest literal region at/after from: [position, terminator].
-        def next_literal_region(xml, from)
-          best = nil
-          best_terminator = nil
-          LITERAL_REGIONS.each do |opener, terminator|
-            idx = xml.index(opener, from)
-            next if idx.nil?
-
-            if best.nil? || idx < best
-              best = idx
-              best_terminator = terminator
-            end
-          end
-          best.nil? ? nil : [best, best_terminator]
-        end
-
-        # Search for a terminator past its opener's overlap-safe offset
-        # ("-->" cannot start inside "<!--").
-        def opener_at_offset(terminator)
-          terminator == "-->" ? 4 : 0
-        end
-
-        # All quantifiers are possessive and the bare-part class
-        # excludes "/" and ">": the possessive groups can never consume
-        # the closing delimiter, so no backtracking is possible and the
-        # match is linear even on malformed tags.
-        EMPTY_ELEMENT_RE = %r{<([A-Za-z_][\w.:-]*+)((?:"[^"]*+"|'[^']*+'|[^<>"'/]++)*+)/>}
-
-        def normalize_markup(markup, needs_apos, needs_expand)
-          markup = markup.gsub("&apos;", "'") if needs_apos
-          if needs_expand
-            markup = markup.gsub(EMPTY_ELEMENT_RE) do
-              "<#{Regexp.last_match(1)}#{Regexp.last_match(2)}></#{Regexp.last_match(1)}>"
-            end
-          end
-          markup
-        end
-
-        # Documents compose from their parts: the native serializer
-        # only walks the root subtree, so declaration, DOCTYPE, PIs and
-        # document-level text are assembled around it explicitly.
-        def serialize_document(doc, options)
-          # Nokogiri's document shape: every top-level part is
-          # newline-terminated, at any indent — declaration, DOCTYPE,
-          # document PIs, the root element, trailing newline after it.
-          # Document-level text is content, not structure: no added
-          # newline.
-          parts = []
-
-          include_decl = !options[:no_declaration] && options.fetch(:declaration) do
-            document_has_declaration?(doc)
-          end
-          if include_decl
-            declaration = attachments.get(doc, :declaration)
-            parts << (declaration ? declaration.to_xml : default_declaration_xml(doc, options)) << "\n"
-          end
-
-          doctype = attachments.get(doc, :doctype)
-          parts << doctype.to_xml << "\n" if doctype
-
-          native = native_doctype_xml(doc)
-          parts << native << "\n" if native
-
-          if DOC_NODE_SUPPORTED
-            # The libxml2-model document node: prolog PIs/comments,
-            # the root, epilog PIs/comments — in document order, so
-            # epilog parts serialize after the root (issue #130).
-            doc_children = document_node_children(doc)
-            if doc_children
-              doc_children.each { |child| parts << raw_serialize(child, options) << "\n" }
-            else
-              document_pi_nodes(doc).each { |pi| parts << pi.to_xml << "\n" }
-              parts << raw_serialize(doc.root, options) << "\n" if doc.root
-            end
-          else
-            document_pi_nodes(doc).each { |pi| parts << pi.to_xml << "\n" }
-
-            parts << raw_serialize(doc.root, options) << "\n" if doc.root
-          end
-
-          texts = attachments.get(doc, :document_text)
-          texts&.each { |text| parts << XmlEmitter.escape_text(text.content.to_s) }
-
-          parts.join
-        end
-
-        def default_declaration_xml(doc, options)
-          encoding = options[:encoding] || doc.encoding
-          encoding = "UTF-8" if encoding.to_s.empty?
-          XmlEmitter.declaration_xml("1.0", encoding, nil)
-        end
-
-        def marker_text_for(parent, name)
-          return nil unless parent.is_a?(::Leptris::XML::Element)
-
-          marker = "#{Entity::MARKER}#{name};"
-          parent.children.to_a.find do |child|
-            child.is_a?(::Leptris::XML::Text) && child.content == marker
-          end
-        end
-
-        def native_doctype_xml(doc)
-          dt = doc.doctype
-          return nil unless dt
-
-          subset = dt.internal_subset if dt.class.method_defined?(:internal_subset)
-          XmlEmitter.doctype_xml(dt.root_name, dt.public_id, dt.system_id, subset)
-        end
-
         def sax_parse(xml, handler)
           bridge = LeptrisSAXBridge.new(handler)
           xml_string = xml.is_a?(IO) || xml.is_a?(::StringIO) ? xml.read : xml.to_s
@@ -1123,167 +819,6 @@ module Moxml
                 end
           attachments.set(native_doc, :had_source_declaration, had)
         end
-
-        def document_has_declaration?(native)
-          return false unless native.is_a?(::Leptris::XML::Document)
-
-          return true if attachments.get(native, :declaration)
-
-          attachments.get(native, :had_source_declaration) ? true : false
-        end
-
-        # Document-level PI pseudo-nodes, materialized once from the C
-        # list and cached per document: children and serialization read
-        # the same objects, so wrapper mutations round-trip. Build the
-        # cache BEFORE appending a PI with add_pi, or the C-side
-        # addition would be double-counted.
-        # The document node's children, or nil when the node does not
-        # reflect reality: parsed documents always list the root
-        # element among their children, but programmatically built
-        # ones do not (binding gap) — those keep the legacy parts
-        # path.
-        def document_node_children(doc)
-          doc_children = doc.children.to_a
-          has_root = doc_children.any?(::Leptris::XML::Element)
-          return doc_children if has_root
-          return doc_children if doc.root.nil?
-
-          nil
-        end
-
-        def document_pi_nodes(doc)
-          attachments.get(doc, :doc_pi_nodes) || begin
-            nodes = doc.processing_instructions.map do |(target, data)|
-              CustomizedLeptris::DocumentPI.new(target, data, doc)
-            end
-            attachments.set(doc, :doc_pi_nodes, nodes)
-            nodes
-          end
-        end
-
-        def assemble_document_children(doc)
-          children = []
-
-          native_doctype = doc.doctype
-          children << native_doctype if native_doctype
-
-          doctype_wrapper = attachments.get(doc, :doctype)
-          children << doctype_wrapper if doctype_wrapper
-
-          if DOC_NODE_SUPPORTED
-            # The libxml2-model document node lists prolog PIs/comments,
-            # the root, and epilog PIs/comments in document order —
-            # the Nokogiri-shaped contract, epilog anchoring included
-            # (issue #130). Built (programmatic) documents are not yet
-            # fully reflected by the node (binding gap: an attached
-            # root does not appear); document_node_children answers
-            # nil there for the legacy parts path.
-            doc_children = document_node_children(doc)
-            if doc_children
-              children.concat(doc_children)
-            else
-              children.concat(document_pi_nodes(doc))
-              children << doc.root if doc.root
-            end
-          else
-            # Legacy path: document-level PIs live outside the element
-            # tree in a flat pre-root list (libleptris < 1.9.7 C
-            # model); epilog anchoring is not representable there.
-            children.concat(document_pi_nodes(doc))
-
-            children << doc.root if doc.root
-          end
-
-          texts = attachments.get(doc, :document_text)
-          children.concat(texts) if texts
-          children
-        end
-
-        def add_document_child(doc, child)
-          case child
-          when CustomizedLeptris::Declaration
-            child.parent_doc = doc
-            attachments.set(doc, :declaration, child)
-          when CustomizedLeptris::Doctype
-            child.parent_doc = doc
-            attachments.set(doc, :doctype, child)
-          when ::Leptris::XML::DocType
-            raise Moxml::DocumentStructureError.new(
-              "libleptris does not support attaching a native DocType to a document",
-            )
-          when ::Leptris::XML::Element
-            doc.root = child
-          when ::Leptris::XML::ProcessingInstruction
-            document_pi_nodes(doc)
-            doc.add_pi(child.target, child.content.to_s)
-            document_pi_nodes(doc) << CustomizedLeptris::DocumentPI.new(
-              child.target, child.content.to_s, doc
-            )
-          when CustomizedLeptris::DocumentPI
-            document_pi_nodes(doc)
-            doc.add_pi(child.target, child.data)
-            document_pi_nodes(doc) << child
-          when ::Leptris::XML::Text
-            texts = attachments.get(doc, :document_text) || []
-            texts << child
-            attachments.set(doc, :document_text, texts)
-            child
-          else
-            raise Moxml::DocumentStructureError.new(
-              "Unsupported document child: #{child.class}",
-            )
-          end
-          child
-        end
-      end
-
-      # Bridge between the leptris SAX callbacks and Moxml::SAX::Handler.
-      #
-      # @private
-      class LeptrisSAXBridge < ::Leptris::XML::SAX::Document
-        include Moxml::SAX::NamespaceSplitter
-
-        def initialize(handler)
-          @handler = handler
-          super()
-        end
-
-        def start_document
-          @handler.on_start_document
-        end
-
-        def end_document
-          @handler.on_end_document
-        end
-
-        def start_element(name, attrs = [])
-          attr_hash, ns_hash = split_attributes_and_namespaces(attrs)
-          @handler.on_start_element(name, attr_hash, ns_hash)
-        end
-
-        def end_element(name)
-          @handler.on_end_element(name)
-        end
-
-        def characters(string)
-          @handler.on_characters(string)
-        end
-
-        def comment(string)
-          @handler.on_comment(string)
-        end
-
-        def cdata_block(string)
-          @handler.on_cdata(string)
-        end
-
-        def processing_instruction(name, content)
-          @handler.on_processing_instruction(name, content || "")
-        end
-
-        def error(message, _line = 0, _column = 0)
-          @handler.on_error(Moxml::ParseError.new(message))
-        end
       end
     end
   end