leptris 1.9.107.0 → 1.9.115.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 64e0e821d66fb8c8d25debf605648a6d533f432e0882f1a7cecf58b2e2a19e52
-  data.tar.gz: 70bb6cf535b69d0ae0c470459f183d6420e87db4a8bef12c89152f1d739c793b
+  metadata.gz: 8fb86a086496ee90110e37c8049ccb26b472d7a21f0f774a381e7611deb1999a
+  data.tar.gz: 1ec17ae04d09a31ef6e38ead74151be098373d1e0863b8e59755c2ebdb01cc3a
 SHA512:
-  metadata.gz: eadc86a700848a3a0980d0e2af292ded87619a4bd958a0ea897a310c35caf00dfca7d4c1a997e1760d48d18872cb84458440601bc437a120131e6f4344a614b0
-  data.tar.gz: 9d6a4fbc7dc3b88e96c896a4b55d10583b9764979a4d7f8eb3d0a51be3422d870f758a805c566529e85c94c2bcd7512b5715479e4d1e04295ce1936ff78599ab
+  metadata.gz: 4733922a9794ada70fba4b50783b87a4748a04145131bba696eeb1b2ab3ae33d8f76fbcabb531f8fbc93be51f3a53634841f3488f42c238a5d93b22bdd732a75
+  data.tar.gz: e1ffd73a63379edd8c23018ab1477f0627e783a85c52ec8210b82e7efcad16caf063a01bddf661e2b05cae26315bb800484c2560f5841b47d093432d40db9ed7

data/CHANGELOG.md

@@ -5,6 +5,35 @@ 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).
 
+## [1.9.115.0] - 2026-09-09
+
+### Changed
+
+- Lockstep with libleptris 1.9.115: the RELAX NG arc completes —
+  the validator (Jing conformance gate 38/38), `<include>` with
+  Jing's override rules, `<param>` datatype facets (portable
+  matcher), and schema errors on `leptris_last_error`. Required by
+  the RelaxNG binding (#165).
+
+## [1.9.107.1] - 2026-09-08
+
+### Improved
+
+- **SAX drain: bulk kind strip** (TODO.restructure/22 — the moxml
+  0.77-0.93x row): the recorder's dispatch loop read the event
+  kind with a `get_uint8` per EVENT (a memory crossing for every
+  record, dispatched or not); the strip now reads in ONE bulk
+  `get_bytes` + ONE `unpack` per drain via the memoized
+  per-count template — kind codes 0..10 unpack to immediate
+  Fixnums, so the change strictly removes ~count FFI crossings
+  with zero new allocations. Allocation profile (load-independent
+  measurement) is far ahead either way: text-only 32,381 vs
+  Nokogiri's 400,061 allocs/parse (12x fewer); all-events 112,440
+  vs 400,034 (3.6x fewer) — the remaining gap is pure per-event
+  CPU, which this addresses. Timing verification gated on a clean
+  host window (bench staged; the shared machine sat at load
+  40-400 today).
+
 ## [1.9.107.0] - 2026-09-08
 
 ### Changed

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 = "1.9.107"
+LIBLEPTRIS_VERSION = "1.9.115"
 
 CMAKE_FLAGS = %w[
   -DCMAKE_BUILD_TYPE=Release

data/TODO.restructure/22-sax-drain-bulk-strip.md

@@ -0,0 +1,28 @@
+# 22 — SAX drain: bulk kind strip (the 0.77-0.93x row)
+
+Status: CODE DONE — timing verification gated on a clean window
+
+The moxml table shows SAX at 0.77-0.93x Nokogiri (it fully won at
+the 1.9.40-era battery). Investigation under load-404 conditions
+(timing unusable; allocation profiling is load-independent):
+
+- **Allocations are NOT the gap** — measured GC-stat deltas:
+  text-only 32,381 vs Nokogiri's 400,061 allocs/parse (12x fewer);
+  all-events 112,440 vs 400,034 (3.6x fewer).
+- **The time cost was per-event FFI crossings in the drain**: the
+  kind strip was read with a `get_uint8` per EVENT (all events,
+  dispatched or not — a memory crossing each) after the
+  whole-record-unpack was retired for its 2.25M-Integer profile.
+- **Fix**: the kind strip reads in ONE `get_bytes` + ONE `unpack`
+  per drain through the already-defined memoized
+  `KIND_TEMPLATE_FOR` — kind codes 0..10 unpack to IMMEDIATE
+  Fixnums (zero allocation), so this strictly removes ~count FFI
+  crossings per drain with no new allocations. Per-dispatched-event
+  field reads (2-3 `get_uint32`) remain.
+
+- [x] Bulk strip restored; SAX suite green; allocation profile
+      re-verified (32k/112k vs 400k/400k).
+- [ ] **Timing verification** (the actual 0.77-0.93x row): bench
+      staged at /tmp/bench_sax.rb — requires load < 20 (the host
+      has been at 40-400). Gate: text-only and all-events SAX at
+      parity or better vs Nokogiri on the raw binding.

data/lib/leptris/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Leptris
-  VERSION = "1.9.107.0"
+  VERSION = "1.9.115.0"
 end

data/lib/leptris/xml/ffi.rb

@@ -42,6 +42,7 @@ module Leptris
       typedef :pointer, :leptris_xpath_result
       typedef :pointer, :leptris_xpath_ns_set
       typedef :pointer, :leptris_xpath_compiled
+      typedef :pointer, :leptris_relaxng
       typedef :pointer, :leptris_xslt
       typedef :pointer, :leptris_xquery
       typedef :pointer, :leptris_sax_recorder
@@ -733,6 +734,18 @@ attach_function :leptris_parse_string,
       attach_function :leptris_str_has_nonstandard_entity,
         [:string, :size_t], :int
 
+      attach_function :leptris_rng_parse,
+        [:string, :size_t, :pointer], :leptris_relaxng
+      attach_function :leptris_rng_parse_file,
+        [:string, :pointer], :leptris_relaxng
+      attach_function :leptris_rng_free,
+        [:leptris_relaxng], :void
+      # 1 valid; 0 invalid (detail via leptris_rng_error)
+      attach_function :leptris_rng_validate,
+        [:leptris_relaxng, :leptris_document], :int
+      attach_function :leptris_rng_error,
+        [:leptris_relaxng], :string
+
       attach_function :leptris_xslt_parse,
         [:string, :size_t], :leptris_xslt
       attach_function :leptris_xslt_parse_file,

data/lib/leptris/xml/relaxng.rb

@@ -0,0 +1,75 @@
+# frozen_string_literal: true
+
+require "ffi"
+
+module Leptris::XML::RelaxNG
+  module_function
+
+  def parse(schema_xml)
+    Schema.parse(schema_xml)
+  end
+
+  def parse_file(path)
+    Schema.parse_file(path)
+  end
+
+  # A compiled RELAX NG schema (libleptris >= 1.9.115): Jing-parity
+  # validation against the standard DOM — parse once, validate any
+  # number of documents. Schema errors publish to the thread-global
+  # error channel, so failures raise with the engine's detail
+  # ("unknown pattern element: ...", "cannot open schema file ...").
+  #
+  #     rng = Leptris::XML::RelaxNG.parse(schema_xml)
+  #     rng.valid?(doc)      # => true/false
+  #     rng.validate(doc)    # => [] or ["1:0: error: element ..."]
+  #
+  class Schema
+    # GC-managed compiled handle.
+    class Handle < ::FFI::AutoPointer
+      def self.release(ptr)
+        Leptris::XML::FFI.leptris_rng_free(ptr)
+      end
+    end
+
+    # Compile a schema from XML text. Raises Error on a schema
+    # error (detail via leptris_last_error).
+    def self.parse(schema_xml)
+      xml = schema_xml.to_s
+      raw = Leptris::XML::FFI.leptris_rng_parse(xml, xml.bytesize, nil)
+      if raw.null?
+        raise Leptris::XML::Error,
+          "schema parse failed: #{Leptris::XML::FFI.leptris_last_error}"
+      end
+      new(Handle.new(raw))
+    end
+
+    # Compile from a file; <include href="..."> resolves relative to
+    # the file's directory (Jing's override rules apply).
+    def self.parse_file(path)
+      raw = Leptris::XML::FFI.leptris_rng_parse_file(path.to_s, nil)
+      if raw.null?
+        raise Leptris::XML::Error,
+          "schema parse failed: #{Leptris::XML::FFI.leptris_last_error}"
+      end
+      new(Handle.new(raw))
+    end
+
+    def initialize(handle)
+      @handle = handle
+    end
+
+    # Nokogiri shape: an array of error strings (the engine emits
+    # Jing's "line:col: error: message" form), empty when valid.
+    def validate(document)
+      ok = Leptris::XML::FFI.leptris_rng_validate(@handle,
+                                                  document.c_ptr)
+      return [] if ok != 0
+      [Leptris::XML::FFI.leptris_rng_error(@handle)].compact
+    end
+
+    def valid?(document)
+      Leptris::XML::FFI.leptris_rng_validate(@handle,
+                                             document.c_ptr) != 0
+    end
+  end
+end

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

@@ -159,16 +159,20 @@ class Leptris::XML::SAX::Recorder
         @handle, len_ptr)
       arena = arena_ptr.read_bytes(len_ptr.read_uint64)
       count = count_ptr.read_uint64
-      # Kind is the first byte of each record — read it off the C
-      # pointer. The previous path copied every record into Ruby
-      # and unpacked a Fixnum array just for the kind strip
-      # (2.25M Integers on a single-feed drain); one get_uint8 per
-      # event replaces both.
+      # Kind strip in ONE bulk read + ONE unpack per drain: the
+      # per-count template reads the first byte of each record,
+      # skipping the stride (KIND_TEMPLATE_FOR is memoized per
+      # count). Kind codes are 0..10 — unpack yields immediate
+      # Fixnums, so the strip allocates nothing. This replaces a
+      # get_uint8 crossing per EVENT (all events, dispatched or
+      # not) with one memory read per drain — the SAX gap to
+      # Nokogiri's per-event C callback lives exactly here.
+      kinds = records_ptr.get_bytes(0, count * RECORD_STRIDE)
+                         .unpack(KIND_TEMPLATE_FOR[count])
       one_arg_start = dispatched[:start_element] == :one_arg
       i = 0
       while i < count
-        code = records_ptr.get_uint8(i * RECORD_STRIDE)
-        kind = KIND_BY_CODE[code]
+        kind = kinds[i] && KIND_BY_CODE[kinds[i]]
         if kind && dispatched[kind]
           base = i * RECORD_STRIDE
           case kind

data/lib/leptris/xml.rb

@@ -28,6 +28,7 @@ module Leptris
     autoload :ResultAttr, "leptris/xml/result_attr"
     autoload :XSLT, "leptris/xml/xslt"
     autoload :XQuery, "leptris/xml/xquery"
+    autoload :RelaxNG, "leptris/xml/relaxng"
     autoload :Pull, "leptris/xml/pull"
     autoload :Iterparse, "leptris/xml/iterparse"
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: leptris
 version: !ruby/object:Gem::Version
-  version: 1.9.107.0
+  version: 1.9.115.0
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-09-08 00:00:00.000000000 Z
+date: 2026-09-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ffi
@@ -90,6 +90,7 @@ files:
 - TODO.restructure/19-gitignore-hygiene.md
 - TODO.restructure/20-utf8proc-enablement.md
 - TODO.restructure/21-typeddata-variant-prototype.md
+- TODO.restructure/22-sax-drain-bulk-strip.md
 - docs/adr/0001-lockstep-mirror.md
 - docs/adr/0002-utf8-at-the-seam.md
 - docs/adr/0003-readonly-memoization-pattern.md
@@ -119,6 +120,7 @@ files:
 - lib/leptris/xml/parse_options.rb
 - lib/leptris/xml/processing_instruction.rb
 - lib/leptris/xml/pull.rb
+- lib/leptris/xml/relaxng.rb
 - lib/leptris/xml/result_attr.rb
 - lib/leptris/xml/result_text.rb
 - lib/leptris/xml/sax.rb