leptris 1.9.364.2 → 1.9.365.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 25ec026b62db4292174aa0b8a21c05b190e1ffe093338fe20dbcd8aae8a36f88
-  data.tar.gz: f55e338728aa84d4db652a556d4ab965e456caefadb5de21da67f8163d3de142
+  metadata.gz: 973845563957861b68366fd3c90f3a8d3f1a5ba5921e09f2a2dc268542faa8b6
+  data.tar.gz: 71814d603d2c40586dc2e3c3aa9d36750e67a8cdb54864257a9f56cfa076a6c8
 SHA512:
-  metadata.gz: 32a4123617821dc14b225c06d71ddf87239f09f432f76f201e65fc70b8aa511f1816204b5815dee2e8b901d308993b21e197403b6315f43e71a5cc404adeaa69
-  data.tar.gz: 79d51794b1ef9a913d3335241de229be6d8f8698c111af5b725f95b1a8ce8e9f93edc4f5fa3102ff3d719797ea5a8fb7ef4bd6878d55fd578bdc1fc5f326d0c0
+  metadata.gz: f298b9d5e3ac0ffd299ee2323b4efcadddd2c7c7f09be765009c3764d99bbfeb88e3720a92888fbfda3195dfa5bededeca05e38c1790c7c2071fd87807718ed8
+  data.tar.gz: ea9086febdac6a55cb745ce9c240ed7ea2db9ac26843b6b1bfcca43c873a9fbcce1f522dff609ef83a8c62e9af98120d6e9dad18649ba0ec3ea77556c215d0cd

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 = "1.9.364"
+LIBLEPTRIS_VERSION = "1.9.365"
 # Vendored alongside libleptris for fn:normalize-unicode (TODO
 # .restructure/20): built per platform with a RELOCATABLE @rpath
 # install name, loaded by ffi.rb before libleptris so the

data/lib/leptris/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Leptris
-  VERSION = "1.9.364.2"
+  VERSION = "1.9.365.1"
 end

data/vendor-src/README.md

@@ -1,7 +1,7 @@
 Sources vendored in this gem (recompile rights; the ruby
 variant builds them at install via extconf.rb):
 
-- libleptris v1.9.364
+- libleptris v1.9.365
 - utf8proc v2.11.0
 
 Rebuild by hand:

data/vendor-src/libleptris/CHANGELOG.md

@@ -1,5 +1,23 @@
 ## [Unreleased]
 
+## [1.9.365] - 2026-10-16
+
+### Fixed
+
+- **html4: skip the XML-declaration construct in HTML input (#1748, PR #1754).**
+  The html4 lane parsed `<?xml ...?>` as a PI node (target `xml`) whose data
+  carried the terminator `?`, so serialization emitted
+  `<?xml version="1.0" encoding="UTF-8"??>` — and with the serializer's
+  `xml_declaration` riding along (the default `to_xml`), the output carried
+  two declarations, which canon's XHTML pretty-printer degenerated to
+  declaration-only output downstream. libxml2's HTML parser skips the
+  XML-declaration construct entirely; the html4 lane now does the same (the
+  WHATWG lane keeps its specified bogus-comment shape). Red-first gtest pins
+  the contract: `xml_declaration=0` emits no declaration, `1` emits exactly
+  the serializer's own — never the input's remnant, never `??`. Engine suite
+  2047/2047; canon's battery 9/9.
+
+
 ## [1.9.364] - 2026-10-16
 
 ### Added

data/vendor-src/libleptris/CMakeLists.txt

@@ -3,7 +3,7 @@
 cmake_minimum_required(VERSION 3.20)
 
 project(leptris
-    VERSION 1.9.364
+    VERSION 1.9.365
     DESCRIPTION "Fast XML parser and XPath evaluator in pure C"
     LANGUAGES C CXX
 )

data/vendor-src/libleptris/src/leptris/html/html_parse.c

@@ -6685,6 +6685,19 @@ static LeptrisDocument html_parse_shared(
             size_t dlen = (size_t)(de > ds ? de - ds : 0);
             char* tgt = (char*)leptris_pool_alloc(b.pool, tlen + 1);
             char* dat = (char*)leptris_pool_alloc(b.pool, dlen + 1);
+            /* libxml2 HTML parity (#1748): the XML-declaration
+             * construct ('<?xml ...?>') is an XML-ism — the HTML
+             * lane skips it entirely. Retaining it as a PI made the
+             * data carry the terminator '?' (serialized
+             * '<?xml ...??>'), and the declaration metadata + PI
+             * doubled when the serializer's xml_declaration rode
+             * along. */
+            if (tlen == 3 && (ts[0] | 0x20) == 'x' &&
+                (ts[1] | 0x20) == 'm' && (ts[2] | 0x20) == 'l') {
+                p = (de < end) ? de + 1 : end;
+                text = p;
+                continue;
+            }
             if (tgt && dat) {
                 memcpy(tgt, ts, tlen);
                 tgt[tlen] = 0;

data/vendor-src/libleptris/test/html/test_html_builder.cpp

@@ -188,3 +188,43 @@ TEST(HtmlBuilder, RawTextElementNotEscaped) {
     EXPECT_EQ(out.find("&lt;"), std::string::npos) << out;
     leptris_document_free(d);
 }
+
+/* leptris#1748: the XML-declaration construct ('<?xml ...?>') in
+ * HTML input is an XML-ism — libxml2's HTML parser skips it, and
+ * retaining it as a PI (data carrying the terminator '?') made
+ * serialization emit '<?xml ...??>' and double the declaration when
+ * the serializer's own xml_declaration rode along. */
+TEST(HtmlBuilder, Html4DropsXmlDeclarationProlog) {
+    const char* html =
+        "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"
+        "<html xmlns=\"http://www.w3.org/1999/xhtml\">"
+        "<head><title>t</title></head><body><p>x</p></body></html>";
+    LeptrisStatus st = LEPTRIS_OK;
+    LeptrisDocument d =
+        leptris_parse_html4_string(html, strlen(html), &st);
+    ASSERT_EQ(st, LEPTRIS_OK);
+    ASSERT_NE(d, nullptr);
+    for (int decl = 0; decl < 2; decl++) {
+        LeptrisSerializeOptions opts;
+        memset(&opts, 0, sizeof(opts));
+        opts.xml_declaration = decl;
+        opts.encoding = "UTF-8";
+        char* s = leptris_document_serialize(d, &opts);
+        ASSERT_NE(s, nullptr);
+        std::string out(s);
+        leptris_free_string(s);
+        EXPECT_EQ(out.find("??"), std::string::npos)
+            << "decl=" << decl << " got: " << out.substr(0, 90);
+        /* decl=0: the prolog never leaks. decl=1: exactly the
+         * serializer's own declaration — never two, never the
+         * input's remnant. */
+        size_t decls = 0;
+        for (size_t at = out.find("<?xml"); at != std::string::npos;
+             at = out.find("<?xml", at + 1))
+            decls++;
+        EXPECT_EQ(decls, (size_t)decl)
+            << "decl=" << decl << " got: " << out.substr(0, 90);
+        EXPECT_NE(out.find("<html"), std::string::npos) << out;
+    }
+    leptris_document_free(d);
+}

data/vendor-src/libleptris/vcpkg.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://raw.githubusercontent.com/microsoft/vcpkg/master/scripts/vcpkg.schema.json",
   "name": "leptris",
-  "version": "1.9.364",
+  "version": "1.9.365",
   "description": "High-performance XML parser and XPath 1.0 engine in C (libleptris)",
   "homepage": "https://github.com/leptris/leptris",
   "license": "MIT",

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: leptris
 version: !ruby/object:Gem::Version
-  version: 1.9.364.2
+  version: 1.9.365.1
 platform: ruby
 authors:
 - Ribose Inc.