leptris 1.9.29 → 1.9.31

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f91b02217a813c5c7c8eb267b6b82b3eb7689d857fbd76b7a8b108962d56d18c
-  data.tar.gz: c15ad7755d849144c45176d4e28f819ac090927c8a1e1d6ad58c89fe8a3006fe
+  metadata.gz: 61af1b12021e7a1cf22f04004ea36d27df6f740ff135d039854c51497abf87f3
+  data.tar.gz: 0a842331a02a988b8bfce2920f8878b87c5ff5fdbd4c471f2f04694f4a1b3465
 SHA512:
-  metadata.gz: db0800af7aafe8cf8efb263a0fde99d8876b3d8f487a9cbe738bf2d086a9be8a9e6805e9033b3b695b9064e58d4593f0aee4361dcdc55fa2f920e5a71484acb7
-  data.tar.gz: ae1282d974199e33a98c9361aee2afb36b7dacfb782259380688cd13e480065d3ff59108be44f868b3283f0f11fb958c37d16f28c9eb5fcfc1a6ac6331020c26
+  metadata.gz: e832da72a4e2fe0ddede057023c1e981705a41f196d85e7d7e5d61051d524bddfc2305065fef940ef60af48b87e978bc46be7e61030d598de83fb916db8bba3e
+  data.tar.gz: 7a266c15d5983229591bf414ad0dde95cc93018ba01388bf721f98977c026c164797e1dc805fc9a46625a6b2037c7709a65cb0e0640ca5ed6c46f40614dd37c0

data/CHANGELOG.md

@@ -5,6 +5,34 @@ All notable changes to Leptris will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.9.31] - 2026-08-28
+
+### Fixed
+
+- **PI data consumes the leading whitespace run (leptris-ruby#85,
+  libxml2 parity)**: the engine retains the full whitespace run
+  after the PI target as data where libxml2 consumes it at parse
+  time — every Ruby-facing PI-data read now normalizes through one
+  seam helper (`FFI.read_pi_data`): `PI#content`,
+  `Document#processing_instructions` pairs, the SAX
+  `processing_instruction` callback, pull `:pi` events, and
+  recorder `:pi` events. Whitespace-only data reads as `""`, so
+  "pi-without-data" PIs report empty consistently; trailing
+  whitespace is kept (libxml2 trims only the leading run).
+  Read-time only — `PI#data=` still stores verbatim.
+
+## [1.9.30] - 2026-08-28
+
+### Fixed
+
+- **DTD ATTLIST defaults no longer injected by default** (vendored
+  libleptris 1.9.8, leptris/leptris#606): raw parses leave ATTLIST
+  default attributes out — the libxml2/Nokogiri default the ecosystem
+  compares against, and what W3C C14N 1.1 example 3.3's canonical
+  form assumes. New `Leptris::XML::ParseOptions::DTDATTR` /
+  `.dtdattr` / `#dtdattr?` / `#dtdattr=` opts in (libxml2
+  XML_PARSE_DTDATTR parity).
+
 ## [1.9.29] - 2026-08-28
 
 ### Fixed

data/Rakefile

@@ -8,7 +8,7 @@ RSpec::Core::RakeTask.new(:spec)
 # Pin for `rake compile` and the platform-gem builds. Keep in lockstep
 # with .github/workflows/build.yml (which calls `rake compile`) and the
 # CHANGELOG when libleptris releases.
-LIBLEPTRIS_VERSION = "1.9.7"
+LIBLEPTRIS_VERSION = "1.9.8"
 
 CMAKE_FLAGS = %w[
   -DCMAKE_BUILD_TYPE=Release

data/lib/leptris/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Leptris
-  VERSION = "1.9.29"
+  VERSION = "1.9.31"
 end

data/lib/leptris/xml/document.rb

@@ -295,7 +295,8 @@ class Leptris::XML::Document
     count = Leptris::XML::FFI.leptris_document_pi_count(@c_ptr)
     result = count.times.map do |i|
       [Leptris::XML::FFI.leptris_document_pi_target(@c_ptr, i),
-       Leptris::XML::FFI.leptris_document_pi_data(@c_ptr, i)]
+       Leptris::XML::FFI.read_pi_data(
+         Leptris::XML::FFI.leptris_document_pi_data(@c_ptr, i)).to_s]
     end
     @processing_instructions = result
     @pi_version = @version

data/lib/leptris/xml/ffi.rb

@@ -734,6 +734,10 @@ module Leptris
 
       LEPTRIS_PARSE_DEFAULT = 0
       LEPTRIS_PARSE_DROP_WS_TEXT = 1
+      # libleptris >= 1.9.8 (#606): apply DTD ATTLIST default (and
+      # #FIXED) attribute values at parse time — libxml2
+      # XML_PARSE_DTDATTR opt-in parity.
+      LEPTRIS_PARSE_DTDATTR = 2
 
       # The headers' contract is UTF-8 for every C string, but FFI's
       # read_string hands back ASCII-8BIT — the platform default
@@ -920,6 +924,16 @@ module Leptris
         [raw, status.read_int]
       end
 
+      # libxml2 consumes the whole whitespace run following the PI
+      # target when parsing; the engine retains it as data
+      # (leptris-ruby#85). Every Ruby-facing PI-data read normalizes
+      # here — whitespace-only data becomes "" so
+      # "pi-without-data" PIs report empty consistently. Read-time
+      # only: PI#data= stores verbatim.
+      def self.read_pi_data(data)
+        data&.sub(/\A[ \t\r\n]+/, "")
+      end
+
       # Thread-local scratch buffers for batch handle fetches (round
       # XX): the per-call MemoryPointer new/free was pure cold-path
       # overhead — two allocations and a GC visit per children() /

data/lib/leptris/xml/parse_options.rb

@@ -9,6 +9,14 @@ class Leptris::XML::ParseOptions
   # way do not round-trip pretty-printed formatting byte-for-byte.
   NOBLANKS = Leptris::XML::FFI::LEPTRIS_PARSE_DROP_WS_TEXT
 
+  # Apply DTD ATTLIST default (and #FIXED) attribute values at parse
+  # time (libleptris >= 1.9.8, leptris/leptris#606). Matches libxml2's
+  # XML_PARSE_DTDATTR and Nokogiri's dtdload+dtdattr semantics. Off by
+  # default: the ecosystem compares against libxml2's no-DTDATTR
+  # default, and W3C C14N 1.1 example 3.3's canonical form excludes
+  # defaulted attributes.
+  DTDATTR = Leptris::XML::FFI::LEPTRIS_PARSE_DTDATTR
+
   attr_reader :flags
 
   # Recover (libleptris 1.9.0, #547): a parse failure returns an
@@ -36,6 +44,18 @@ class Leptris::XML::ParseOptions
     @flags & NOBLANKS != 0
   end
 
+  def self.dtdattr
+    new(DTDATTR)
+  end
+
+  def dtdattr?
+    @flags & DTDATTR != 0
+  end
+
+  def dtdattr=(value)
+    if value then @flags |= DTDATTR else @flags &= ~DTDATTR end
+  end
+
   def recover?
     @recover == true
   end

data/lib/leptris/xml/processing_instruction.rb

@@ -16,7 +16,8 @@ class Leptris::XML::ProcessingInstruction < Leptris::XML::Node
   def content
     return @content if memo_hit?(@content_version)
     ensure_alive!
-    result = Leptris::XML::FFI.leptris_pi_node_get_data(@c_ptr).to_s
+    result = Leptris::XML::FFI.read_pi_data(
+      Leptris::XML::FFI.leptris_pi_node_get_data(@c_ptr)).to_s
     if @document
       @content = result
       @content_version = @document.version

data/lib/leptris/xml/pull.rb

@@ -84,13 +84,14 @@ module Leptris::XML::Pull
           base = i * stride
           name_ptr = buffer.get_pointer(base + name_off)
           text_ptr = buffer.get_pointer(base + text_off)
-          Event.new(
-            TYPES[buffer.get_int(base + type_off)],
+          type = TYPES[buffer.get_int(base + type_off)]
+          text = text_ptr.null? ? nil :
+            text_ptr.read_string.force_encoding(Encoding::UTF_8)
+          text = Leptris::XML::FFI.read_pi_data(text) if type == :pi
+          Event.new(type,
             name_ptr.null? ? nil :
               name_ptr.read_string.force_encoding(Encoding::UTF_8),
-            text_ptr.null? ? nil :
-              text_ptr.read_string.force_encoding(Encoding::UTF_8),
-            nil
+            text, nil
           )
         end
         # The attr mirror holds the batch's most recent start.
@@ -125,11 +126,13 @@ module Leptris::XML::Pull
       name_ptr = raw.get_pointer(NAME_OFFSET)
       text_ptr = raw.get_pointer(TEXT_OFFSET)
       attrs = type == :start_element ? capture_attrs : nil
+      text = text_ptr.null? ? nil :
+        text_ptr.read_string.force_encoding(Encoding::UTF_8)
+      text = Leptris::XML::FFI.read_pi_data(text) if type == :pi
       Event.new(
         type,
         name_ptr.null? ? nil : name_ptr.read_string.force_encoding(Encoding::UTF_8),
-        text_ptr.null? ? nil : text_ptr.read_string.force_encoding(Encoding::UTF_8),
-        attrs
+        text, attrs
       )
     end
 

data/lib/leptris/xml/sax/parser.rb

@@ -149,7 +149,8 @@ class Leptris::XML::SAX::Parser
 
     if overridden?(:processing_instruction)
       s[:processing_instruction] = callback(:void, [:pointer, :string, :string]) do |_, target, data|
-        handler.processing_instruction(utf8(target), utf8(data))
+        handler.processing_instruction(
+          utf8(target), Leptris::XML::FFI.read_pi_data(utf8(data)))
       end
     end
 

data/lib/leptris/xml/sax/recorder.rb

@@ -122,9 +122,11 @@ class Leptris::XML::SAX::Recorder
         kind = KIND_BY_CODE[fields[i * 9]]
         if kind && (wanted.nil? || wanted[kind])
           base = i * 9 + 1
+          text = slice(arena, fields[base + 2], fields[base + 3])
+          text = Leptris::XML::FFI.read_pi_data(text) if kind == :pi
           yield kind,
                 slice(arena, fields[base], fields[base + 1]),
-                slice(arena, fields[base + 2], fields[base + 3]),
+                text,
                 attrs_from(arena, fields[base + 4], fields[base + 5]),
                 fields[base + 6], fields[base + 7]
         end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: leptris
 version: !ruby/object:Gem::Version
-  version: 1.9.29
+  version: 1.9.31
 platform: ruby
 authors:
 - Ribose Inc.