moxml 0.5.17 → 0.5.18

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6de47d8ce88e56853b7523dfbcb2049e61d586878dca573d13bacd85138b4a4e
-  data.tar.gz: 520a050794c1275e5bc519454319a34fd059b9bbcf3f0efd0f5d8e0876bb7e97
+  metadata.gz: c793d84315c4005a5141698aeb716c001d23b7157b768c77cbdb3539a4b08f53
+  data.tar.gz: 35c1d60e6d3a8e17e9768c733d028962bcb6e5798e3c8528b18deaebd855ae5f
 SHA512:
-  metadata.gz: 6b197e6da24e0b40ead4fa25ee944b242ee3484475b2927a16e126faa208f8ff4bb7709795b1d2830b1394fbb0fad8d28f99ed32ec9dbf902710752286965e7c
-  data.tar.gz: 89b1ae523cf06687e67e4d07a088cdef2f942a1b4dcff8ba56f468fb887b1ac3bba936b10145c057eb0f6cf767c9e7ba35e86fb753854ee391f29951f2e17485
+  metadata.gz: '092b193420e9117adbd6dade8718474c9a72de401eb0b7a741d36639bbd7e9285c7e53d55f96b482b17bea3382d1da3adb1cae6bbc7b787c552859d80377db39'
+  data.tar.gz: 18a342a60a7dda872730dd2a9158aa852948596e21fc4613961d0336ece2f12977d02fe434e7fa64429f3ce73015a4434285f3f052425c4eb6d88c20a9571db7

data/docs/_pages/adapter-protocol.adoc

@@ -18,7 +18,9 @@ code disagree.
 == Method groups
 
 Parse and document lifecycle::
-`parse(xml, options, context)`, `create_document`, `create` factories
+`parse(xml, options, context)` — `noblanks: true` drops
+whitespace-only text nodes where the engine has the flag
+(Nokogiri, leptris), `create_document`, `create` factories
 (`create_native_element`, `create_native_text`, `create_native_cdata`,
 `create_native_comment`, `create_native_processing_instruction`,
 `create_native_declaration`, `create_native_doctype`,
@@ -56,8 +58,9 @@ the tracked native; wrappers re-key through `refresh_native!`.
 Serialization::
 `serialize(node, options)`. Options: `indent`, `encoding`,
 `declaration`, `no_declaration`, `expand_empty`, `line_ending`,
-`indent_text` (the indent-unit string — honored where the engine
-has it, e.g. Nokogiri; leptris waits on leptris-ruby#109).
+`indent_text` (the indent-unit string — Nokogiri and
+leptris >= 1.9.45; leptris text-bearing leaves wait on
+leptris/leptris#658).
 Entity-marker restoration is owned by the wrapper layer
 (`Node#to_xml`), guarded by `entity_bearing?`.
 

data/docs/_pages/adapters/leptris.adoc

@@ -30,6 +30,11 @@ ctx.config.adapter_name        # => :leptris / :nokogiri / :rexml (Opal)
 
 == Parse options
 
+`noblanks: true`::
+Drop whitespace-only text nodes (libxml2 `XML_PARSE_NOBLANKS`
+parity, issue #153) — the parse shape canon's pretty-printer
+compares against `Nokogiri::XML(xml, &:noblanks)`.
+
 `readonly: true`::
 The binding memoizes every read and refuses mutations — the
 parse-and-read lifecycle for multi-pass consumers (comparison, diff,
@@ -62,13 +67,13 @@ implementation over one `leptris_node_traverse` call.
 
 == Known limitations (tracked upstream)
 
+* Tab indentation honors the indent-unit string on leptris >= 1.9.45
+  (`indent_text:`), byte-identical to Nokogiri on element-only
+  trees; text-bearing leaves still emit spaces until the engine fix
+  (leptris/leptris#658).
 * A PI preceding the DOCTYPE reorders on serialization — libleptris
   normalizes DOCTYPE-first and the document node does not record its
   relative position.
-* Tab indentation: the binding's `indent_text` is the display-form
-  boolean, not Nokogiri's indent-unit string — the unit ask is
-  leptris-ruby#109. moxml forwards `indent_text:` to Nokogiri
-  meanwhile.
 
 Resolved with leptris-ruby 1.9.42 (leptris/leptris#636/#612): child
 PIs serialize on their own indented lines, DOCTYPE internal subsets

data/lib/moxml/adapter/leptris/serialize.rb

@@ -63,11 +63,15 @@ module Moxml
           include_decl = options.fetch(:declaration) do
             options[:no_declaration] ? false : document_has_declaration?(node)
           end
-          xml = node.to_xml(
+          kwargs = {
             indent: options.fetch(:indent, 0),
             no_decl: !include_decl,
             encoding: options[:encoding],
-          )
+          }
+          if INDENT_UNIT_SUPPORTED && options[:indent_text].is_a?(String)
+            kwargs[:indent_text] = options[:indent_text]
+          end
+          xml = node.to_xml(**kwargs)
           # Element output always ends with the close tag — but the
           # engine's serializer appends a stray trailing newline when
           # the element's last text child is non-ASCII (fixed engine

data/lib/moxml/adapter/leptris.rb

@@ -40,6 +40,15 @@ module Moxml
       LIBXML2_LAYOUT_PARITY =
         Gem::Version.new(::Leptris::VERSION) >= Gem::Version.new("1.9.42")
 
+      # leptris-ruby#109 (1.9.45): Element#to_xml takes the
+      # indent-unit string, so moxml's per-child document composition
+      # can carry `indent_text:` through. Text-bearing leaves still
+      # emit spaces until the engine fix (leptris/leptris#658); the
+      # boolean display form stays document-level and is never
+      # forwarded (the element face raises on it).
+      INDENT_UNIT_SUPPORTED =
+        Gem::Version.new(::Leptris::VERSION) >= Gem::Version.new("1.9.45")
+
       NO_PARSE_ERRORS = [].freeze
       private_constant :NO_PARSE_ERRORS
 
@@ -81,7 +90,7 @@ module Moxml
             ::Leptris::XML::Document.parse(
               processed,
               readonly: options[:readonly] == true,
-              options: dtdattr_parse_options(options),
+              options: parse_flags(options),
             )
           rescue ::Leptris::XML::ParseError => e
             # libleptris has no recovery mode that survives unclosed
@@ -104,11 +113,16 @@ module Moxml
           doc
         end
 
-        # nil unless DTDATTR is requested — the binding treats a nil
-        # options hash as plain defaults (defaults exclude ATTLIST
-        # defaults, matching libxml2/Nokogiri semantics).
-        def dtdattr_parse_options(options)
-          options[:dtdattr] == true ? ::Leptris::XML::ParseOptions.dtdattr : nil
+        # nil when no parse flag is requested — the binding treats a
+        # nil options hash as plain defaults (matching libxml2/
+        # Nokogiri semantics: blanks kept, no ATTLIST defaults).
+        # noblanks (issue #153) drops whitespace-only text nodes,
+        # libxml2 XML_PARSE_NOBLANKS parity.
+        def parse_flags(options)
+          flags = 0
+          flags |= ::Leptris::XML::ParseOptions::DTDATTR if options[:dtdattr] == true
+          flags |= ::Leptris::XML::ParseOptions::NOBLANKS if options[:noblanks] == true
+          flags.zero? ? nil : ::Leptris::XML::ParseOptions.new(flags)
         end
 
         def parse_errors(native_doc)

data/lib/moxml/adapter/nokogiri.rb

@@ -26,11 +26,13 @@ module Moxml
               ::Nokogiri::XML::DocumentFragment.parse(processed_xml) do |config|
                 config.strict.nonet
                 config.recover unless options[:strict]
+                config.noblanks if options[:noblanks]
               end
             else
               ::Nokogiri::XML(processed_xml, nil, "UTF-8") do |config|
                 config.strict.nonet
                 config.recover unless options[:strict]
+                config.noblanks if options[:noblanks]
               end
             end
           rescue ::Nokogiri::XML::SyntaxError => e

data/lib/moxml/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Moxml
-  VERSION = "0.5.17"
+  VERSION = "0.5.18"
 end

data/spec/moxml/adapter/leptris_spec.rb

@@ -185,6 +185,33 @@ RSpec.describe Moxml::Adapter::Leptris do
       expect(doc.to_xml).to include("<?renamed changed?>")
     end
 
+    it "matches raw Nokogiri with tab units on element-only trees" do
+      skip "requires the indent unit (leptris 1.9.45+)" unless described_class::INDENT_UNIT_SUPPORTED
+
+      source = %(<r><a><b/></a><c><d/><e/></c></r>)
+      target = Nokogiri::XML(source).to_xml(indent: 2, indent_text: "\t", encoding: "UTF-8")
+      output = ctx.parse(source).to_xml(
+        indent: 2, declaration: true, expand_empty: false,
+        encoding: "UTF-8", indent_text: "\t"
+      )
+      expect(output).to eq(target)
+    end
+
+    it "drops space-only text nodes with noblanks and matches Nokogiri (issue #153)" do
+      source = %(<a><t>1</t>    <n/></a>)
+      recipe = {
+        indent: 2, declaration: true, expand_empty: false, encoding: "UTF-8"
+      }
+      target = Nokogiri::XML(source, &:noblanks).to_xml(indent: 2, encoding: "UTF-8")
+
+      doc = ctx.parse(source, noblanks: true)
+      expect(doc.root.children.to_a.select(&:text?)).to be_empty
+      expect(doc.to_xml(recipe)).to eq(target)
+
+      via_nokogiri = Moxml.new(:nokogiri).parse(source, noblanks: true).to_xml(recipe)
+      expect(via_nokogiri).to eq(target)
+    end
+
     it "reports the tracked native for a re-added document PI" do
       doc = ctx.parse("<?pi-src orig?><root/>")
       moved = doc.children.to_a[0]

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: moxml
 version: !ruby/object:Gem::Version
-  version: 0.5.17
+  version: 0.5.18
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-08-30 00:00:00.000000000 Z
+date: 2026-08-31 00:00:00.000000000 Z
 dependencies: []
 description: |
   Moxml is a unified XML manipulation library that provides a common API