Add Lexbor files for URL handling (#18656)

Relates to #14461 and https://wiki.php.net/rfc/url_parsing_api

Author: kocsismate

codecov.yml

@@ -7,6 +7,9 @@ ignore:
   - "ext/lexbor/lexbor/html"
   - "ext/lexbor/lexbor/ns"
   - "ext/lexbor/lexbor/ports"
+  - "ext/lexbor/lexbor/punycode"
   - "ext/lexbor/lexbor/tag"
+  - "ext/lexbor/lexbor/unicode"
+  - "ext/lexbor/lexbor/url"
   - "ext/pcre/pcre2lib"
   - "ext/uri/uriparser"

ext/lexbor/config.m4

@@ -17,6 +17,7 @@ PHP_NEW_EXTENSION([lexbor], m4_normalize([
     $LEXBOR_DIR/core/hash.c
     $LEXBOR_DIR/core/mem.c
     $LEXBOR_DIR/core/mraw.c
+    $LEXBOR_DIR/core/plog.c
     $LEXBOR_DIR/core/print.c
     $LEXBOR_DIR/core/serialize.c
     $LEXBOR_DIR/core/shs.c
@@ -174,7 +175,11 @@ PHP_NEW_EXTENSION([lexbor], m4_normalize([
     $LEXBOR_DIR/html/tree/open_elements.c
     $LEXBOR_DIR/ns/ns.c
     $LEXBOR_DIR/ports/posix/lexbor/core/memory.c
+    $LEXBOR_DIR/punycode/punycode.c
     $LEXBOR_DIR/tag/tag.c
+    $LEXBOR_DIR/unicode/idna.c
+    $LEXBOR_DIR/unicode/unicode.c
+    $LEXBOR_DIR/url/url.c
   ]),
   [no],,
   [-DZEND_ENABLE_STATIC_TSRMLS_CACHE=1 $PHP_LEXBOR_CFLAGS])
@@ -193,7 +198,10 @@ PHP_ADD_BUILD_DIR([
   $ext_builddir/$LEXBOR_DIR/html/tree/insertion_mode
   $ext_builddir/$LEXBOR_DIR/ns
   $ext_builddir/$LEXBOR_DIR/ports/posix/lexbor/core
+  $ext_builddir/$LEXBOR_DIR/punycode
   $ext_builddir/$LEXBOR_DIR/tag
+  $ext_builddir/$LEXBOR_DIR/unicode
+  $ext_builddir/$LEXBOR_DIR/url
 ])
 PHP_ADD_INCLUDE([$ext_srcdir])
 PHP_INSTALL_HEADERS([ext/lexbor], m4_normalize([

ext/lexbor/config.w32

@@ -3,7 +3,7 @@
 EXTENSION("lexbor", "php_lexbor.c", false, "/I " + configure_module_dirname + " /DZEND_ENABLE_STATIC_TSRMLS_CACHE=1");
 PHP_LEXBOR="yes";
 ADD_SOURCES("ext/lexbor/lexbor/ports/windows_nt/lexbor/core", "memory.c", "lexbor");
-ADD_SOURCES("ext/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", "lexbor");
+ADD_SOURCES("ext/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 plog.c print.c serialize.c shs.c str.c strtod.c", "lexbor");
 ADD_SOURCES("ext/lexbor/lexbor/dom", "interface.c", "lexbor");
 ADD_SOURCES("ext/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", "lexbor");
 ADD_SOURCES("ext/lexbor/lexbor/html/tokenizer", "error.c state_comment.c state_doctype.c state_rawtext.c state_rcdata.c state_script.c state.c", "lexbor");
@@ -17,7 +17,10 @@ ADD_SOURCES("ext/lexbor/lexbor/css/selectors", "state.c selectors.c selector.c p
 ADD_SOURCES("ext/lexbor/lexbor/css/syntax", "state.c parser.c syntax.c anb.c tokenizer.c token.c","lexbor");
 ADD_SOURCES("ext/lexbor/lexbor/css/syntax/tokenizer", "error.c","lexbor");
 ADD_SOURCES("ext/lexbor/lexbor/ns", "ns.c","lexbor");
+ADD_SOURCES("ext/lexbor/lexbor/punycode", "punycode.c","lexbor");
 ADD_SOURCES("ext/lexbor/lexbor/tag", "tag.c","lexbor");
+ADD_SOURCES("ext/lexbor/lexbor/unicode", "idna.c unicode.c","lexbor");
+ADD_SOURCES("ext/lexbor/lexbor/url", "url.c","lexbor");
 ADD_FLAG("CFLAGS_LEXBOR", "/D LEXBOR_BUILDING /utf-8");
 
 AC_DEFINE("HAVE_LEXBOR", 1, "Define to 1 if the PHP extension 'lexbor' is available.");

ext/lexbor/lexbor/punycode/base.h

@@ -0,0 +1,30 @@
+/*
+ * Copyright (C) 2023-2024 Alexander Borisov
+ *
+ * Author: Alexander Borisov <[email protected]>
+ */
+
+#ifndef LEXBOR_PUNYCODE_BASE_H
+#define LEXBOR_PUNYCODE_BASE_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "lexbor/core/base.h"
+
+
+#define LXB_PUNYCODE_VERSION_MAJOR 1
+#define LXB_PUNYCODE_VERSION_MINOR 1
+#define LXB_PUNYCODE_VERSION_PATCH 0
+
+#define LEXBOR_PUNYCODE_VERSION_STRING LEXBOR_STRINGIZE(LXB_PUNYCODE_VERSION_MAJOR) "." \
+                                       LEXBOR_STRINGIZE(LXB_PUNYCODE_VERSION_MINOR) "." \
+                                       LEXBOR_STRINGIZE(LXB_PUNYCODE_VERSION_PATCH)
+
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
+#endif /* LEXBOR_PUNYCODE_BASE_H */