nielsdos · nielsdos · Aug 25, 2023 · Aug 25, 2023 · Aug 25, 2023 · Aug 25, 2023
diff --git a/.github/workflows/push.yml b/.github/workflows/push.yml
@@ -73,13 +73,17 @@ jobs:
             asan: true
     name: "LINUX_X64_${{ matrix.debug && 'DEBUG' || 'RELEASE' }}_${{ matrix.zts && 'ZTS' || 'NTS' }}${{ matrix.asan && '_ASAN' || '' }}"
     runs-on: ubuntu-22.04
-    container:
-      image: ${{ matrix.asan && 'ubuntu:23.04' || null }}
     steps:
       - name: git checkout
         uses: actions/checkout@v4
       - name: apt
         uses: ./.github/actions/apt-x64
+      - name: LLVM 16 (ASAN-only)
+        if: ${{ matrix.asan }}
+        run: |
+          wget https://apt.llvm.org/llvm.sh
+          chmod u+x llvm.sh
+          sudo ./llvm.sh 16
       - name: System info
         run: |
           echo "::group::Show host CPU info"
@@ -110,7 +114,7 @@ jobs:
           configurationParameters: >-
             --${{ matrix.debug && 'enable' || 'disable' }}-debug
             --${{ matrix.zts && 'enable' || 'disable' }}-zts
-            ${{ matrix.asan && 'CFLAGS="-fsanitize=undefined,address -DZEND_TRACK_ARENA_ALLOC" LDFLAGS="-fsanitize=undefined,address" CC=clang CXX=clang++ --disable-opcache-jit' || '' }}
+            ${{ matrix.asan && 'CFLAGS="-fsanitize=undefined,address -DZEND_TRACK_ARENA_ALLOC" LDFLAGS="-fsanitize=undefined,address" CC=clang-16 CXX=clang++-16 --disable-opcache-jit' || '' }}
           skipSlow: ${{ matrix.asan }}
       - name: make
         run: make -j$(/usr/bin/nproc) >/dev/null

diff --git a/UPGRADING b/UPGRADING
@@ -78,6 +78,14 @@ PHP 8.4 UPGRADE NOTES
   . Added constant DOMNode::DOCUMENT_POSITION_CONTAINS.
   . Added constant DOMNode::DOCUMENT_POSITION_CONTAINED_BY.
   . Added constant DOMNode::DOCUMENT_POSITION_IMPLEMENTATION_SPECIFIC.
+  . Implemented DOM HTML5 parsing and serialization.
+    RFC: https://wiki.php.net/rfc/domdocument_html5_parser.
+    This RFC adds the new DOM namespace along with class and constant aliases.
+    There are two new classes to handle HTML and XML documents:
+    DOM\HTMLDocument and DOM\XMLDocument.
+    These classes provide a cleaner API to handle HTML and XML documents.
+    Furthermore, the DOM\HTMLDocument class implements spec-compliant HTML5
+    parsing and serialization.
 
 - XSL:
   . It is now possible to use parameters that contain both single and double

diff --git a/UPGRADING.INTERNALS b/UPGRADING.INTERNALS
@@ -52,6 +52,10 @@ PHP 8.4 INTERNALS UPGRADE NOTES
    - The function php_xsl_create_object() was removed as it was not used
      nor exported.
 
+ d. ext/libxml
+   - Added php_libxml_pretend_ctx_error_ex() to emit errors as if they had come
+     from libxml.
+
 ========================
 4. OpCode changes
 ========================

diff --git a/dom.php b/dom.php
@@ -0,0 +1,22 @@
+<?php
+
+$original = new DOMDocument();
+$original->loadHTML('<!DOCTYPE html>');
+
+$dt = $original->implementation->createDocumentType('html', '', '');
+$original->appendChild($dt);
+/*
+$doctype = $original->doctype->cloneNode();
+var_dump($doctype);
+
+$other = new DOMDocument();
+$doctype = $other->importNode($original->doctype);
+$other->append($doctype);
+
+echo $original->saveXML();
+// Deallocating the original document should not affect the imported node
+unset($original);
+echo $other->saveXML();
+
+echo "-----------------------------\n";
+*/
@@ -12,7 +12,21 @@ if test "$PHP_DOM" != "no"; then
 
   PHP_SETUP_LIBXML(DOM_SHARED_LIBADD, [
     AC_DEFINE(HAVE_DOM,1,[ ])
+    PHP_LEXBOR_CFLAGS="-I@ext_srcdir@/lexbor -DLEXBOR_STATIC"
+    LEXBOR_DIR="lexbor/lexbor"
+    LEXBOR_SOURCES="$LEXBOR_DIR/ports/posix/lexbor/core/memory.c \
+      $LEXBOR_DIR/core/array_obj.c $LEXBOR_DIR/core/array.c $LEXBOR_DIR/core/avl.c $LEXBOR_DIR/core/bst.c $LEXBOR_DIR/core/diyfp.c $LEXBOR_DIR/core/conv.c $LEXBOR_DIR/core/dobject.c $LEXBOR_DIR/core/dtoa.c $LEXBOR_DIR/core/hash.c $LEXBOR_DIR/core/mem.c $LEXBOR_DIR/core/mraw.c $LEXBOR_DIR/core/print.c $LEXBOR_DIR/core/serialize.c $LEXBOR_DIR/core/shs.c $LEXBOR_DIR/core/str.c $LEXBOR_DIR/core/strtod.c \
+      $LEXBOR_DIR/dom/interface.c $LEXBOR_DIR/dom/interfaces/attr.c $LEXBOR_DIR/dom/interfaces/cdata_section.c $LEXBOR_DIR/dom/interfaces/character_data.c $LEXBOR_DIR/dom/interfaces/comment.c $LEXBOR_DIR/dom/interfaces/document.c $LEXBOR_DIR/dom/interfaces/document_fragment.c $LEXBOR_DIR/dom/interfaces/document_type.c $LEXBOR_DIR/dom/interfaces/element.c $LEXBOR_DIR/dom/interfaces/node.c $LEXBOR_DIR/dom/interfaces/processing_instruction.c $LEXBOR_DIR/dom/interfaces/shadow_root.c $LEXBOR_DIR/dom/interfaces/text.c \
+      $LEXBOR_DIR/html/tokenizer/error.c $LEXBOR_DIR/html/tokenizer/state_comment.c $LEXBOR_DIR/html/tokenizer/state_doctype.c $LEXBOR_DIR/html/tokenizer/state_rawtext.c $LEXBOR_DIR/html/tokenizer/state_rcdata.c $LEXBOR_DIR/html/tokenizer/state_script.c $LEXBOR_DIR/html/tokenizer/state.c \
+      $LEXBOR_DIR/html/tree/active_formatting.c $LEXBOR_DIR/html/tree/error.c $LEXBOR_DIR/html/tree/insertion_mode/after_after_body.c $LEXBOR_DIR/html/tree/insertion_mode/after_after_frameset.c $LEXBOR_DIR/html/tree/insertion_mode/after_body.c $LEXBOR_DIR/html/tree/insertion_mode/after_frameset.c $LEXBOR_DIR/html/tree/insertion_mode/after_head.c $LEXBOR_DIR/html/tree/insertion_mode/before_head.c $LEXBOR_DIR/html/tree/insertion_mode/before_html.c $LEXBOR_DIR/html/tree/insertion_mode/foreign_content.c $LEXBOR_DIR/html/tree/insertion_mode/in_body.c $LEXBOR_DIR/html/tree/insertion_mode/in_caption.c $LEXBOR_DIR/html/tree/insertion_mode/in_cell.c $LEXBOR_DIR/html/tree/insertion_mode/in_column_group.c $LEXBOR_DIR/html/tree/insertion_mode/in_frameset.c $LEXBOR_DIR/html/tree/insertion_mode/in_head.c $LEXBOR_DIR/html/tree/insertion_mode/in_head_noscript.c $LEXBOR_DIR/html/tree/insertion_mode/initial.c $LEXBOR_DIR/html/tree/insertion_mode/in_row.c $LEXBOR_DIR/html/tree/insertion_mode/in_select.c $LEXBOR_DIR/html/tree/insertion_mode/in_select_in_table.c $LEXBOR_DIR/html/tree/insertion_mode/in_table_body.c $LEXBOR_DIR/html/tree/insertion_mode/in_table.c $LEXBOR_DIR/html/tree/insertion_mode/in_table_text.c $LEXBOR_DIR/html/tree/insertion_mode/in_template.c $LEXBOR_DIR/html/tree/insertion_mode/text.c $LEXBOR_DIR/html/tree/open_elements.c \
+      $LEXBOR_DIR/encoding/big5.c $LEXBOR_DIR/encoding/decode.c $LEXBOR_DIR/encoding/encode.c $LEXBOR_DIR/encoding/encoding.c $LEXBOR_DIR/encoding/euc_kr.c $LEXBOR_DIR/encoding/gb18030.c $LEXBOR_DIR/encoding/iso_2022_jp_katakana.c $LEXBOR_DIR/encoding/jis0208.c $LEXBOR_DIR/encoding/jis0212.c $LEXBOR_DIR/encoding/range.c $LEXBOR_DIR/encoding/res.c $LEXBOR_DIR/encoding/single.c \
+      $LEXBOR_DIR/html/encoding.c $LEXBOR_DIR/html/interface.c $LEXBOR_DIR/html/parser.c $LEXBOR_DIR/html/token.c $LEXBOR_DIR/html/token_attr.c $LEXBOR_DIR/html/tokenizer.c $LEXBOR_DIR/html/tree.c \
+      $LEXBOR_DIR/html/interfaces/anchor_element.c $LEXBOR_DIR/html/interfaces/area_element.c $LEXBOR_DIR/html/interfaces/audio_element.c $LEXBOR_DIR/html/interfaces/base_element.c $LEXBOR_DIR/html/interfaces/body_element.c $LEXBOR_DIR/html/interfaces/br_element.c $LEXBOR_DIR/html/interfaces/button_element.c $LEXBOR_DIR/html/interfaces/canvas_element.c $LEXBOR_DIR/html/interfaces/data_element.c $LEXBOR_DIR/html/interfaces/data_list_element.c $LEXBOR_DIR/html/interfaces/details_element.c $LEXBOR_DIR/html/interfaces/dialog_element.c $LEXBOR_DIR/html/interfaces/directory_element.c $LEXBOR_DIR/html/interfaces/div_element.c $LEXBOR_DIR/html/interfaces/d_list_element.c $LEXBOR_DIR/html/interfaces/document.c $LEXBOR_DIR/html/interfaces/element.c $LEXBOR_DIR/html/interfaces/embed_element.c $LEXBOR_DIR/html/interfaces/field_set_element.c $LEXBOR_DIR/html/interfaces/font_element.c $LEXBOR_DIR/html/interfaces/form_element.c $LEXBOR_DIR/html/interfaces/frame_element.c $LEXBOR_DIR/html/interfaces/frame_set_element.c $LEXBOR_DIR/html/interfaces/head_element.c $LEXBOR_DIR/html/interfaces/heading_element.c $LEXBOR_DIR/html/interfaces/hr_element.c $LEXBOR_DIR/html/interfaces/html_element.c $LEXBOR_DIR/html/interfaces/iframe_element.c $LEXBOR_DIR/html/interfaces/image_element.c $LEXBOR_DIR/html/interfaces/input_element.c $LEXBOR_DIR/html/interfaces/label_element.c $LEXBOR_DIR/html/interfaces/legend_element.c $LEXBOR_DIR/html/interfaces/li_element.c $LEXBOR_DIR/html/interfaces/link_element.c $LEXBOR_DIR/html/interfaces/map_element.c $LEXBOR_DIR/html/interfaces/marquee_element.c $LEXBOR_DIR/html/interfaces/media_element.c $LEXBOR_DIR/html/interfaces/menu_element.c $LEXBOR_DIR/html/interfaces/meta_element.c $LEXBOR_DIR/html/interfaces/meter_element.c $LEXBOR_DIR/html/interfaces/mod_element.c $LEXBOR_DIR/html/interfaces/object_element.c $LEXBOR_DIR/html/interfaces/o_list_element.c $LEXBOR_DIR/html/interfaces/opt_group_element.c $LEXBOR_DIR/html/interfaces/option_element.c $LEXBOR_DIR/html/interfaces/output_element.c $LEXBOR_DIR/html/interfaces/paragraph_element.c $LEXBOR_DIR/html/interfaces/param_element.c $LEXBOR_DIR/html/interfaces/picture_element.c $LEXBOR_DIR/html/interfaces/pre_element.c $LEXBOR_DIR/html/interfaces/progress_element.c $LEXBOR_DIR/html/interfaces/quote_element.c $LEXBOR_DIR/html/interfaces/script_element.c $LEXBOR_DIR/html/interfaces/select_element.c $LEXBOR_DIR/html/interfaces/slot_element.c $LEXBOR_DIR/html/interfaces/source_element.c $LEXBOR_DIR/html/interfaces/span_element.c $LEXBOR_DIR/html/interfaces/style_element.c $LEXBOR_DIR/html/interfaces/table_caption_element.c $LEXBOR_DIR/html/interfaces/table_cell_element.c $LEXBOR_DIR/html/interfaces/table_col_element.c $LEXBOR_DIR/html/interfaces/table_element.c $LEXBOR_DIR/html/interfaces/table_row_element.c $LEXBOR_DIR/html/interfaces/table_section_element.c $LEXBOR_DIR/html/interfaces/template_element.c $LEXBOR_DIR/html/interfaces/text_area_element.c $LEXBOR_DIR/html/interfaces/time_element.c $LEXBOR_DIR/html/interfaces/title_element.c $LEXBOR_DIR/html/interfaces/track_element.c $LEXBOR_DIR/html/interfaces/u_list_element.c $LEXBOR_DIR/html/interfaces/unknown_element.c $LEXBOR_DIR/html/interfaces/video_element.c $LEXBOR_DIR/html/interfaces/window.c \
+      $LEXBOR_DIR/selectors/selectors.c \
+      $LEXBOR_DIR/ns/ns.c \
+      $LEXBOR_DIR/tag/tag.c"
     PHP_NEW_EXTENSION(dom, [php_dom.c attr.c document.c \
+                            xml_document.c html_document.c html5_serializer.c html5_parser.c namespace_compat.c \
                             domexception.c parentnode.c \
                             processinginstruction.c cdatasection.c \
                             documentfragment.c domimplementation.c \
@@ -21,8 +35,9 @@ if test "$PHP_DOM" != "no"; then
                             nodelist.c text.c comment.c \
                             entityreference.c \
                             notation.c xpath.c dom_iterators.c \
-                            namednodemap.c],
-                            $ext_shared)
+                            namednodemap.c \
+                            $LEXBOR_SOURCES],
+                            $ext_shared,,$PHP_LEXBOR_CFLAGS)
     PHP_SUBST(DOM_SHARED_LIBADD)
     PHP_INSTALL_HEADERS([ext/dom/xml_common.h])
     PHP_ADD_EXTENSION_DEP(dom, libxml)

@@ -8,13 +8,29 @@ if (PHP_DOM == "yes") {
 		CHECK_HEADER_ADD_INCLUDE("libxml/parser.h", "CFLAGS_DOM", PHP_PHP_BUILD + "\\include\\libxml2")
 	) {
 		EXTENSION("dom", "php_dom.c attr.c document.c \
+			xml_document.c html_document.c html5_serializer.c html5_parser.c namespace_compat.c \
 			domexception.c parentnode.c processinginstruction.c \
 			cdatasection.c documentfragment.c domimplementation.c element.c \
 			node.c characterdata.c documenttype.c \
 			entity.c nodelist.c text.c comment.c \
 			entityreference.c \
 			notation.c xpath.c dom_iterators.c \
-			namednodemap.c");
+			namednodemap.c", null, "-Iext/dom/lexbor");
+
+		ADD_SOURCES("ext/dom/lexbor/lexbor/ports/windows_nt/lexbor/core", "memory.c", "dom");
+		ADD_SOURCES("ext/dom/lexbor/lexbor/core", "array_obj.c array.c avl.c bst.c diyfp.c conv.c dobject.c dtoa.c hash.c mem.c mraw.c print.c serialize.c shs.c str.c strtod.c", "dom");
+		ADD_SOURCES("ext/dom/lexbor/lexbor/dom", "interface.c", "dom");
+		ADD_SOURCES("ext/dom/lexbor/lexbor/dom/interfaces", "attr.c cdata_section.c character_data.c comment.c document.c document_fragment.c document_type.c element.c node.c processing_instruction.c shadow_root.c text.c", "dom");
+		ADD_SOURCES("ext/dom/lexbor/lexbor/html/tokenizer", "error.c state_comment.c state_doctype.c state_rawtext.c state_rcdata.c state_script.c state.c", "dom");
+		ADD_SOURCES("ext/dom/lexbor/lexbor/html/tree", "active_formatting.c open_elements.c error.c", "dom");
+		ADD_SOURCES("ext/dom/lexbor/lexbor/html/tree/insertion_mode", "after_after_body.c after_after_frameset.c after_body.c after_frameset.c after_head.c before_head.c before_html.c foreign_content.c in_body.c in_caption.c in_cell.c in_column_group.c in_frameset.c in_head.c in_head_noscript.c initial.c in_row.c in_select.c in_select_in_table.c in_table_body.c in_table.c in_table_text.c in_template.c text.c", "dom");
+		ADD_SOURCES("ext/dom/lexbor/lexbor/html", "encoding.c interface.c parser.c token.c token_attr.c tokenizer.c tree.c", "dom");
+		ADD_SOURCES("ext/dom/lexbor/lexbor/encoding", "big5.c decode.c encode.c encoding.c euc_kr.c gb18030.c iso_2022_jp_katakana.c jis0208.c jis0212.c range.c res.c single.c", "dom");
+		ADD_SOURCES("ext/dom/lexbor/lexbor/html/interfaces", "anchor_element.c area_element.c audio_element.c base_element.c body_element.c br_element.c button_element.c canvas_element.c data_element.c data_list_element.c details_element.c dialog_element.c directory_element.c div_element.c d_list_element.c document.c element.c embed_element.c field_set_element.c font_element.c form_element.c frame_element.c frame_set_element.c head_element.c heading_element.c hr_element.c html_element.c iframe_element.c image_element.c input_element.c label_element.c legend_element.c li_element.c link_element.c map_element.c marquee_element.c media_element.c menu_element.c meta_element.c meter_element.c mod_element.c object_element.c o_list_element.c opt_group_element.c option_element.c output_element.c paragraph_element.c param_element.c picture_element.c pre_element.c progress_element.c quote_element.c script_element.c select_element.c slot_element.c source_element.c span_element.c style_element.c table_caption_element.c table_cell_element.c table_col_element.c table_element.c table_row_element.c table_section_element.c template_element.c text_area_element.c time_element.c title_element.c track_element.c u_list_element.c unknown_element.c video_element.c window.c", "dom");
+		ADD_SOURCES("ext/dom/lexbor/lexbor/selectors", "selectors.c", "dom");
+		ADD_SOURCES("ext/dom/lexbor/lexbor/ns", "ns.c", "dom");
+		ADD_SOURCES("ext/dom/lexbor/lexbor/tag", "tag.c", "dom");
+		ADD_FLAG("CFLAGS_DOM", "/D LEXBOR_STATIC ");
 
 		AC_DEFINE("HAVE_DOM", 1, "DOM support");