[RFC] Add RFC 3986 and WHATWG compliant URL parsing support

.cirrus.yml

@@ -16,7 +16,7 @@ freebsd_task:
     - pkg install -y autoconf bison gmake re2c icu libiconv png freetype2 enchant2 bzip2 t1lib gmp tidyp libsodium libzip libxml2 libxslt openssl oniguruma pkgconf webp libavif
   script:
     - ./buildconf -f
-    - ./configure --prefix=/usr/local --enable-debug --enable-option-checking=fatal --enable-fpm --with-pdo-sqlite --without-pear --with-bz2 --with-avif --with-jpeg --with-webp --with-freetype --enable-gd --enable-exif --with-zip --with-zlib --enable-soap --enable-xmlreader --with-xsl --with-libxml --enable-shmop --enable-pcntl --enable-mbstring --with-curl --enable-sockets --with-openssl --with-iconv=/usr/local --enable-bcmath --enable-calendar --enable-ftp --with-ffi --enable-zend-test --enable-dl-test=shared --enable-intl --with-mhash --with-sodium --enable-werror --with-config-file-path=/etc --with-config-file-scan-dir=/etc/php.d
+    - ./configure --prefix=/usr/local --enable-debug --enable-option-checking=fatal --enable-fpm --with-pdo-sqlite --without-pear --with-bz2 --with-avif --with-jpeg --with-webp --with-freetype --enable-gd --enable-exif --with-zip --with-zlib --enable-soap --enable-xmlreader --with-xsl --with-libxml --enable-shmop --enable-pcntl --enable-mbstring --enable-uri --with-curl --enable-sockets --with-openssl --with-iconv=/usr/local --enable-bcmath --enable-calendar --enable-ftp --with-ffi --enable-zend-test --enable-dl-test=shared --enable-intl --with-mhash --with-sodium --enable-werror --with-config-file-path=/etc --with-config-file-scan-dir=/etc/php.d
     - gmake -j2
     - mkdir /etc/php.d
     - gmake install

.github/actions/configure-macos/action.yml

@@ -47,6 +47,7 @@ runs:
           --enable-pcntl \
           --with-readline="$BREW_OPT"/readline \
           --enable-mbstring \
+          --enable-uri \
           --with-curl \
           --with-gettext="$BREW_OPT"/gettext \
           --enable-sockets \

.github/actions/configure-x32/action.yml

@@ -44,6 +44,7 @@ runs:
             --enable-pcntl \
             --with-readline \
             --enable-mbstring \
+            --enable-uri \
             --with-curl \
             --with-gettext \
             --enable-sockets \

.github/actions/configure-x64/action.yml

@@ -47,6 +47,7 @@ runs:
           --enable-pcntl \
           --without-readline --with-libedit \
           --enable-mbstring \
+          --enable-uri \
           --with-curl \
           --with-gettext \
           --enable-sockets \

.github/labeler.yml

@@ -320,6 +320,11 @@
       - any-glob-to-any-file:
         - ext/tokenizer/**/*
 
+"Extension: uri":
+  - changed-files:
+      - any-glob-to-any-file:
+        - ext/uri/**/*
+
 "Extension: xml":
   - changed-files:
       - any-glob-to-any-file:

EXTENSIONS

@@ -495,6 +495,12 @@ PRIMARY MAINTAINER:  Andrei Zmievski <[email protected]> (2002 - 2002)
 MAINTENANCE:         Maintained
 STATUS:              Working
 -------------------------------------------------------------------------------
+EXTENSION:           uri
+PRIMARY MAINTAINER   Máté Kocsis <[email protected]> (2024 - 2024)
+MAINTENANCE:         Maintained
+STATUS:              Working
+SINCE:               8.5.0
+-------------------------------------------------------------------------------
 EXTENSION:           zip
 PRIMARY MAINTAINER:  Pierre-Alain Joye <[email protected]> (2006 - 2011)
                      Remi Collet <[email protected]> (2013-2020)

Zend/zend_string.h

@@ -598,6 +598,7 @@ EMPTY_SWITCH_DEFAULT_CASE()
 	_(ZEND_STR_PORT,                   "port") \
 	_(ZEND_STR_USER,                   "user") \
 	_(ZEND_STR_PASS,                   "pass") \
+	_(ZEND_STR_PASSWORD,               "password") \
 	_(ZEND_STR_PATH,                   "path") \
 	_(ZEND_STR_QUERY,                  "query") \
 	_(ZEND_STR_FRAGMENT,               "fragment") \

ext/dom/config.m4

@@ -8,7 +8,7 @@ if test "$PHP_DOM" != "no"; then
   PHP_SETUP_LIBXML([DOM_SHARED_LIBADD], [
     AC_DEFINE([HAVE_DOM], [1],
       [Define to 1 if the PHP extension 'dom' is available.])
-    PHP_LEXBOR_CFLAGS="-I@ext_srcdir@/lexbor -DLEXBOR_STATIC"
+    PHP_LEXBOR_CFLAGS="-I@ext_srcdir@/lexbor -DLEXBOR_STATIC -Wno-uninitialized"
     LEXBOR_DIR="lexbor/lexbor"
     LEXBOR_SOURCES=m4_normalize(["
       $LEXBOR_DIR/core/array_obj.c
@@ -22,6 +22,7 @@ if test "$PHP_DOM" != "no"; then
       $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
       $LEXBOR_DIR/core/shs.c
@@ -184,8 +185,12 @@ if test "$PHP_DOM" != "no"; then
       $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/selectors-adapted/selectors.c
       $LEXBOR_DIR/tag/tag.c
+      $LEXBOR_DIR/unicode/idna.c
+      $LEXBOR_DIR/unicode/unicode.c
+      $LEXBOR_DIR/url/url.c
     "])
     PHP_NEW_EXTENSION([dom], m4_normalize([
         attr.c
@@ -242,6 +247,9 @@ if test "$PHP_DOM" != "no"; then
       $ext_builddir/$LEXBOR_DIR/ports/posix/lexbor/core
       $ext_builddir/$LEXBOR_DIR/selectors-adapted
       $ext_builddir/$LEXBOR_DIR/tag
+      $ext_builddir/$LEXBOR_DIR/punycode
+      $ext_builddir/$LEXBOR_DIR/unicode
+      $ext_builddir/$LEXBOR_DIR/url
     ])
     PHP_SUBST([DOM_SHARED_LIBADD])
     PHP_INSTALL_HEADERS([ext/dom], m4_normalize([

ext/dom/lexbor/lexbor/punycode/base.h

@@ -0,0 +1,30 @@
+/*
+ * Copyright (C) 2023 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 0
+#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 */

ext/dom/lexbor/lexbor/punycode/config.cmake

@@ -0,0 +1,3 @@
+set(DEPENDENCIES "core encoding")
+set(DESCRIPTION "The module implemented by PUNYCODE specification.
+Specification: https://www.rfc-editor.org/rfc/inline-errata/rfc3492.html")