diff --git a/ext/tokenizer/Makefile.frag b/ext/tokenizer/Makefile.frag
index f971394741d73..79655a8c8d7ae 100644
--- a/ext/tokenizer/Makefile.frag
+++ b/ext/tokenizer/Makefile.frag
@@ -1,4 +1,7 @@
 $(top_srcdir)/Zend/zend_language_parser.c:
 $(top_srcdir)/Zend/zend_language_scanner.c:
-$(top_srcdir)/ext/tokenizer/tokenizer_data.c: $(top_srcdir)/Zend/zend_language_parser.h
+$(top_srcdir)/ext/tokenizer/tokenizer_data.c: $(top_srcdir)/Zend/zend_language_parser.y $(top_srcdir)/Zend/zend_language_parser.h
+	if test ! -z "$(PHP_EXECUTABLE)" && test -x "$(PHP_EXECUTABLE)"; then \
+		$(PHP_EXECUTABLE) $(srcdir)/tokenizer_data_gen.php; \
+	fi;
 $(builddir)/tokenizer.lo: $(top_srcdir)/Zend/zend_language_parser.c $(top_srcdir)/Zend/zend_language_scanner.c
diff --git a/ext/tokenizer/tokenizer_data.c b/ext/tokenizer/tokenizer_data.c
index 5699c57566b7d..10663442c4c13 100644
--- a/ext/tokenizer/tokenizer_data.c
+++ b/ext/tokenizer/tokenizer_data.c
@@ -16,7 +16,7 @@
 
 /*
    DO NOT EDIT THIS FILE!
-   This file is generated using tokenizer_data_gen.sh
+   This file is generated using tokenizer_data_gen.php
 */
 
 #include "php.h"
diff --git a/ext/tokenizer/tokenizer_data_gen.php b/ext/tokenizer/tokenizer_data_gen.php
new file mode 100644
index 0000000000000..13e6aaa31dc80
--- /dev/null
+++ b/ext/tokenizer/tokenizer_data_gen.php
@@ -0,0 +1,92 @@
+<?php
+
+$infile = 'Zend/zend_language_parser.h';
+$outfile = 'ext/tokenizer/tokenizer_data.c';
+
+if (!file_exists($infile)) {
+    fwrite(STDERR, <<<ERROR
+    $infile is missing.
+    
+    Please, generate the PHP parser files by scripts/dev/genfiles
+    or by running the ./configure build step.
+    ERROR);
+    exit(1);
+}
+
+$result = '';
+
+$result .= <<<CODE
+/*
+   +----------------------------------------------------------------------+
+   | Copyright (c) The PHP Group                                          |
+   +----------------------------------------------------------------------+
+   | This source file is subject to version 3.01 of the PHP license,      |
+   | that is bundled with this package in the file LICENSE, and is        |
+   | available through the world-wide-web at the following url:           |
+   | http://www.php.net/license/3_01.txt                                  |
+   | If you did not receive a copy of the PHP license and are unable to   |
+   | obtain it through the world-wide-web, please send a note to          |
+   | license@php.net so we can mail you a copy immediately.               |
+   +----------------------------------------------------------------------+
+   | Author: Johannes Schlueter <johannes@php.net>                        |
+   +----------------------------------------------------------------------+
+*/
+
+/*
+   DO NOT EDIT THIS FILE!
+   This file is generated using tokenizer_data_gen.php
+*/
+
+#include "php.h"
+#include "zend.h"
+#include <zend_language_parser.h>
+
+
+void tokenizer_register_constants(INIT_FUNC_ARGS) {
+
+CODE;
+
+$incontent = file_get_contents($infile);
+preg_match_all('(^    (?<token_name>T_.*?)\b)m', $incontent, $matches);
+
+foreach ($matches['token_name'] as $tokenName) {
+    if ($tokenName === 'T_NOELSE' || $tokenName === 'T_ERROR') {
+        continue;
+    }
+    $result .= "\tREGISTER_LONG_CONSTANT(\"$tokenName\", $tokenName, CONST_CS | CONST_PERSISTENT);\n";
+}
+$result .= "\tREGISTER_LONG_CONSTANT(\"T_DOUBLE_COLON\", T_PAAMAYIM_NEKUDOTAYIM, CONST_CS | CONST_PERSISTENT);\n";
+
+$result .= <<<CODE
+}
+
+char *get_token_type_name(int token_type)
+{
+\tswitch (token_type) {
+
+
+CODE;
+
+foreach ($matches['token_name'] as $tokenName) {
+    if ($tokenName === 'T_NOELSE' || $tokenName === 'T_ERROR') {
+        continue;
+    }
+    if ($tokenName === 'T_PAAMAYIM_NEKUDOTAYIM') {
+        $result .= "\t\tcase T_PAAMAYIM_NEKUDOTAYIM: return \"T_DOUBLE_COLON\";\n";
+    } else {
+        $result .= "\t\tcase $tokenName: return \"$tokenName\";\n";
+    }
+}
+
+$result .= <<<CODE
+
+\t}
+\treturn NULL;
+}
+
+
+CODE;
+
+file_put_contents($outfile, $result);
+
+echo "Wrote $outfile\n";
diff --git a/ext/tokenizer/tokenizer_data_gen.sh b/ext/tokenizer/tokenizer_data_gen.sh
deleted file mode 100755
index 1dbe77d2e7ebc..0000000000000
--- a/ext/tokenizer/tokenizer_data_gen.sh
+++ /dev/null
@@ -1,78 +0,0 @@
-#!/bin/sh
-#
-# Generate the tokenizer extension data file from the parser header file.
-
-# Go to project root directory.
-cd $(CDPATH= cd -- "$(dirname -- "$0")/../../" && pwd -P)
-
-infile="Zend/zend_language_parser.h"
-outfile="ext/tokenizer/tokenizer_data.c"
-
-if test ! -f "$infile"; then
-  echo "$infile is missing." >&2
-  echo "" >&2
-  echo "Please, generate the PHP parser files by scripts/dev/genfiles" >&2
-  echo "or by running the ./configure build step." >&2
-  exit 1
-fi
-
-echo '/*
-   +----------------------------------------------------------------------+
-   | Copyright (c) The PHP Group                                          |
-   +----------------------------------------------------------------------+
-   | This source file is subject to version 3.01 of the PHP license,      |
-   | that is bundled with this package in the file LICENSE, and is        |
-   | available through the world-wide-web at the following url:           |
-   | http://www.php.net/license/3_01.txt                                  |
-   | If you did not receive a copy of the PHP license and are unable to   |
-   | obtain it through the world-wide-web, please send a note to          |
-   | license@php.net so we can mail you a copy immediately.               |
-   +----------------------------------------------------------------------+
-   | Author: Johannes Schlueter <johannes@php.net>                        |
-   +----------------------------------------------------------------------+
-*/
-
-/*
-   DO NOT EDIT THIS FILE!
-   This file is generated using tokenizer_data_gen.sh
-*/
-
-#include "php.h"
-#include "zend.h"
-#include <zend_language_parser.h>
-
-' > $outfile
-
-echo 'void tokenizer_register_constants(INIT_FUNC_ARGS) {' >> $outfile
-awk '
-	/^    T_(NOELSE|ERROR)/ { next }
-	/^    T_/  { print "	REGISTER_LONG_CONSTANT(\"" $1 "\", " $1 ", CONST_CS | CONST_PERSISTENT);" }
-' < $infile >> $outfile
-echo '	REGISTER_LONG_CONSTANT("T_DOUBLE_COLON", T_PAAMAYIM_NEKUDOTAYIM, CONST_CS | CONST_PERSISTENT);' >> $outfile
-echo '}' >> $outfile
-
-
-echo '
-char *get_token_type_name(int token_type)
-{
-	switch (token_type) {
-' >> $outfile
-
-awk '
-	/^    T_PAAMAYIM_NEKUDOTAYIM/ {
-		print "		case T_PAAMAYIM_NEKUDOTAYIM: return \"T_DOUBLE_COLON\";"
-		next
-	}
-	/^    T_(NOELSE|ERROR)/ { next }
-	/^    T_/ {
-		print "		case " $1 ": return \"" $1 "\";"
-	}
-' < $infile >> $outfile
-
-echo '
-	}
-	return NULL;
-}
-' >> $outfile
-
-echo "Wrote $outfile"