moxml 0.5.8 → 0.5.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 77a959afbe83b0cc46a158571f792d07888f7bf29f3a65c1ea88be867892ffcc
-  data.tar.gz: 1a5a9515ba125977cd26e33b878e7ecaaed1a788e450e79f356c54a117c9e6c7
+  metadata.gz: 011d9a8566b2697d8c01a17a1a4f702ace315361dae3b246f8ed5ad5fb79b3e8
+  data.tar.gz: 286839c9aca15e4027d4b01bcdfb432c2036f10234fb408cf10f88e5dcbeac0d
 SHA512:
-  metadata.gz: ff6e651e53a55b5ed4aed1e68eff9fa40e9a58aed81a3709ce101fb315bddbef928dcd1a8b31317fcf7dd42e65b92158191647365bc7c43fba46677551bd82d6
-  data.tar.gz: 3c3ad8fac372d42a2dd9d3e4660bc30987015975031fed6b80c1bfeea864f47ed36676d125132384b72d7ba51a3a1ef743877efd5611fd0ecc2cda96efae29e7
+  metadata.gz: f53698ba5eee597fb6bda3355c1f7dfe0a33442cd3e67a6aedc73a155a23e80f049f2fc63aed6871b6cb2e85723719d7e7f318cc140ef178e5dde4bcd493a095
+  data.tar.gz: 44d1afe3880ebc55dd214a0a7f2b48c69151504b6c5a16646afd88cf4a885184132db9a590552c2531bfda8ea84a92e8fac50a7cfae75379e215582acf0f5bac

data/lib/moxml/adapter/leptris.rb

@@ -30,7 +30,9 @@ module Moxml
 
         def parse(xml, options = {}, _context = nil)
           xml_string = xml.is_a?(IO) || xml.is_a?(StringIO) ? xml.read : xml.to_s
-          processed = preprocess_entities(xml_string)
+          # The marker flag rides preprocess's own `&` scan — no
+          # second full-buffer probe (issue #132 parse-side note).
+          processed, entity_markers = Entity.preprocess_with_marker_flag(xml_string)
 
           # readonly: true (issue #133): the binding memoizes reads and
           # refuses mutations — the parse-and-read lifecycle for
@@ -49,7 +51,7 @@ module Moxml
           doc = Document.new(native_doc, ctx)
 
           record_source_declaration(native_doc, processed)
-          attachments.set(native_doc, :entity_markers, processed.include?(Entity::MARKER))
+          attachments.set(native_doc, :entity_markers, entity_markers)
 
           doc
         end
@@ -310,17 +312,21 @@ module Moxml
         end
 
         def node_type(node)
+          # Frequency-ordered: elements and text dominate every real
+          # document, and Node.wrap dispatches here once per cold
+          # wrap. CDATA must precede Text (CDATA < Text in the
+          # binding).
           case node
+          when ::Leptris::XML::Element then :element
+          when ::Leptris::XML::CDATA then :cdata
+          when ::Leptris::XML::Text, CustomizedLeptris::TextSegment then :text
+          when ::Leptris::XML::Attr then :attribute
+          when ::Leptris::XML::Comment then :comment
+          when ::Leptris::XML::ProcessingInstruction, CustomizedLeptris::DocumentPI then :processing_instruction
           when ::Leptris::XML::Document then :document
           when ::Leptris::XML::DocType, CustomizedLeptris::Doctype then :doctype
           when CustomizedLeptris::Declaration then :declaration
           when CustomizedLeptris::EntityReference then :entity_reference
-          when ::Leptris::XML::CDATA then :cdata
-          when ::Leptris::XML::Comment then :comment
-          when ::Leptris::XML::ProcessingInstruction, CustomizedLeptris::DocumentPI then :processing_instruction
-          when ::Leptris::XML::Text, CustomizedLeptris::TextSegment then :text
-          when ::Leptris::XML::Element then :element
-          when ::Leptris::XML::Attr then :attribute
           else :unknown
           end
         end

data/lib/moxml/entity.rb

@@ -55,9 +55,12 @@ module Moxml
     module_function
 
     # Replace non-standard entity references with markers before
-    # parsing. Always returns a UTF-8 encoded string.
-    def preprocess_entities(xml)
-      return "" if xml.nil?
+    # parsing. Always returns a UTF-8 encoded string, and reports
+    # whether the result can contain markers: the flag rides the
+    # same `&` scan, so callers needing it (leptris parse) avoid a
+    # second full-buffer multibyte probe.
+    def preprocess_with_marker_flag(xml)
+      return ["", false] if xml.nil?
 
       str = if xml.encoding == Encoding::BINARY
               # Binary strings are assumed to be UTF-8. If the bytes are
@@ -78,11 +81,23 @@ module Moxml
       # Fast path: no `&` means no entity references to mark — skip
       # the regex scan and string allocation entirely. The vast
       # majority of XML payloads contain no entity references.
-      return str unless str.include?("&")
+      return [str, false] unless str.include?("&")
 
-      str.gsub(NAME_RE) do |match|
-        STANDARD_ENTITIES.include?(::Regexp.last_match(1)) ? match : "#{MARKER}#{::Regexp.last_match(1)};"
+      marked = false
+      processed = str.gsub(NAME_RE) do |match|
+        name = ::Regexp.last_match(1)
+        if STANDARD_ENTITIES.include?(name)
+          match
+        else
+          marked = true
+          "#{MARKER}#{name};"
+        end
       end
+      [processed, marked]
+    end
+
+    def preprocess_entities(xml)
+      preprocess_with_marker_flag(xml)[0]
     end
 
     # Resolve numeric (&#NN; / &#xNN;) and the five standard named

data/lib/moxml/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Moxml
-  VERSION = "0.5.8"
+  VERSION = "0.5.9"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: moxml
 version: !ruby/object:Gem::Version
-  version: 0.5.8
+  version: 0.5.9
 platform: ruby
 authors:
 - Ribose Inc.