From 3560f11935f8af970a4d077fcc56a7f050a39632 Mon Sep 17 00:00:00 2001
From: Christian Schmidt <cs@blackwoodseven.com>
Date: Sun, 5 Mar 2017 12:35:21 +0100
Subject: [PATCH] Replace mbStrReplace() with str_replace()

By design, UTF-8 allows any byte-oriented substring searching algorithm,
since the sequence of bytes for a character cannot occur anywhere else
([source](https://en.wikipedia.org/wiki/UTF-8#Advantages_3)).

So `str_replace()` also works for UTF-8-encoded strings, assuming that
the input strings are valid UTF-8 strings. The previous implementation
of mbStrReplace() did nothing to detect invalid strings.

Also, `str_replace()` does not support [Unicode equivalence](https://en.wikipedia.org/wiki/Unicode_equivalence),
but nor do the other `mb_string` functions, and nor does `=SUBSTITUTE()` in Excel
(tested on Excel for Mac version 15.19.1, Excel 2016 for Windows and LibreOffice 5.1).

Closes #109
---
 src/PhpSpreadsheet/Calculation/TextData.php   |  2 +-
 src/PhpSpreadsheet/Shared/StringHelper.php    | 38 -------------------
 .../data/Calculation/TextData/SUBSTITUTE.php  | 12 ++++++
 3 files changed, 13 insertions(+), 39 deletions(-)

diff --git a/src/PhpSpreadsheet/Calculation/TextData.php b/src/PhpSpreadsheet/Calculation/TextData.php
index abf05d95..fd9cd7a9 100644
--- a/src/PhpSpreadsheet/Calculation/TextData.php
+++ b/src/PhpSpreadsheet/Calculation/TextData.php
@@ -493,7 +493,7 @@ class TextData
         $instance = floor(Functions::flattenSingleValue($instance));
 
         if ($instance == 0) {
-            return \PhpOffice\PhpSpreadsheet\Shared\StringHelper::mbStrReplace($fromText, $toText, $text);
+            return str_replace($fromText, $toText, $text);
         }
 
         $pos = -1;
diff --git a/src/PhpSpreadsheet/Shared/StringHelper.php b/src/PhpSpreadsheet/Shared/StringHelper.php
index 299a9897..c4945540 100644
--- a/src/PhpSpreadsheet/Shared/StringHelper.php
+++ b/src/PhpSpreadsheet/Shared/StringHelper.php
@@ -550,44 +550,6 @@ class StringHelper
         return preg_split('/(?<!^)(?!$)/u', $string);
     }
 
-    /**
-     * Replace into multi-bytes string.
-     *
-     * Strangely, PHP doesn't have a mb_str_replace multibyte function
-     * As we'll only ever use this function with UTF-8 characters, we can simply "hard-code" the character set
-     *
-     * @param string|string[] $search
-     * @param string|string[] $replace
-     * @param string $subject
-     *
-     * @return string
-     */
-    public static function mbStrReplace($search, $replace, $subject)
-    {
-        if (is_array($subject)) {
-            $ret = [];
-            foreach ($subject as $key => $val) {
-                $ret[$key] = self::mbStrReplace($search, $replace, $val);
-            }
-
-            return $ret;
-        }
-
-        foreach ((array) $search as $key => $s) {
-            if ($s == '' && $s !== 0) {
-                continue;
-            }
-            $r = !is_array($replace) ? $replace : (isset($replace[$key]) ? $replace[$key] : '');
-            $pos = mb_strpos($subject, $s, 0, 'UTF-8');
-            while ($pos !== false) {
-                $subject = mb_substr($subject, 0, $pos, 'UTF-8') . $r . mb_substr($subject, $pos + mb_strlen($s, 'UTF-8'), null, 'UTF-8');
-                $pos = mb_strpos($subject, $s, $pos + mb_strlen($r, 'UTF-8'), 'UTF-8');
-            }
-        }
-
-        return $subject;
-    }
-
     /**
      * Reverse the case of a string, so that all uppercase characters become lowercase
      * and all lowercase characters become uppercase.
diff --git a/tests/data/Calculation/TextData/SUBSTITUTE.php b/tests/data/Calculation/TextData/SUBSTITUTE.php
index 4c4dba1e..23f66a18 100644
--- a/tests/data/Calculation/TextData/SUBSTITUTE.php
+++ b/tests/data/Calculation/TextData/SUBSTITUTE.php
@@ -27,4 +27,16 @@ return [
         'a',
         1,
     ],
+    'Unicode equivalence is not supported' => [
+        "\u{0061}\u{030A}",
+        "\u{0061}\u{030A}",
+        "\u{00E5}",
+        'x',
+    ],
+    'Multibytes are supported' => [
+        'x',
+        "\u{00E5}",
+        "\u{00E5}",
+        'x',
+    ],
 ];