charData - add Zero-Width Non-Joiner, Zero-Width Joiner, & Word-Joiner

textAnsi - don't replace confusable chars (other than whitespace & separators)..  color/highlight is enough

dev/charData.php

@@ -1,4 +1,4 @@
-<?php
+<?php // @phpcs:ignore SlevomatCodingStandard.Files.FileLength.FileTooLong
 
 /**
  * Define characters that will be highlighted / replaced
@@ -179,110 +179,174 @@
     ),
 
     "\xC2\xA0" => array(
+        'class' => 'char-ws',
         'codePoint' => '00A0',
         'desc' => 'NBSP',
         'replaceWith' => '\u{00a0}',
+        'similarTo' => ' ',
     ),
     "\xE1\x9A\x80" => array(
+        'class' => 'char-ws',
         'codePoint' => '1680',
         'desc' => 'Ogham Space Mark',
         'replaceWith' => '\u{1680}',
+        'similarTo' => ' ',
     ),
     "\xE1\xA0\x8E" => array(
+        'class' => 'char-ws',
         'codePoint' => '180E',
-        'desc' => 'Mongolian Vowel Separator',
+        'desc' => 'Mongolian Vowel Separator', // not included in Separator Category (Other, Format)
         'replaceWith' => '\u{180e}',
+        'similarTo' => '',
     ),
     "\xE2\x80\x80" => array(
+        'class' => 'char-ws',
         'codePoint' => '2000',
         'desc' => 'En Quad',
         'replaceWith' => '\u{2000}',
+        'similarTo' => ' ',
     ),
     "\xE2\x80\x81" => array(
+        'class' => 'char-ws',
         'codePoint' => '2001',
         'desc' => 'Em Quad',
         'replaceWith' => '\u{2001}',
+        'similarTo' => ' ',
     ),
     "\xE2\x80\x82" => array(
+        'class' => 'char-ws',
         'codePoint' => '2002',
         'desc' => 'En Space',
         'replaceWith' => '\u{2002}',
+        'similarTo' => ' ',
     ),
     "\xE2\x80\x83" => array(
+        'class' => 'char-ws',
         'codePoint' => '2003',
         'desc' => 'Em Space',
         'replaceWith' => '\u{2003}',
+        'similarTo' => ' ',
     ),
     "\xE2\x80\x84" => array(
+        'class' => 'char-ws',
         'codePoint' => '2004',
-        'desc' => 'Three-Per-Em Space',
+        'desc' => 'Three-Per-Em (thick) Space',
         'replaceWith' => '\u{2004}',
+        'similarTo' => ' ',
     ),
     "\xE2\x80\x85" => array(
+        'class' => 'char-ws',
         'codePoint' => '2005',
-        'desc' => 'Four-Per-Em Space',
+        'desc' => 'Four-Per-Em (mid) Space',
         'replaceWith' => '\u{2005}',
+        'similarTo' => ' ',
     ),
     "\xE2\x80\x86" => array(
+        'class' => 'char-ws',
         'codePoint' => '2006',
         'desc' => 'Six-Per-Em Space',
         'replaceWith' => '\u{2006}',
+        'similarTo' => ' ',
     ),
     "\xE2\x80\x87" => array(
+        'class' => 'char-ws',
         'codePoint' => '2007',
         'desc' => 'Figure Space',
         'replaceWith' => '\u{2007}',
+        'similarTo' => ' ',
     ),
     "\xE2\x80\x88" => array(
+        'class' => 'char-ws',
         'codePoint' => '2008',
         'desc' => 'Punctuation Space',
         'replaceWith' => '\u{2008}',
+        'similarTo' => ' ',
     ),
     "\xE2\x80\x89" => array(
+        'class' => 'char-ws',
         'codePoint' => '2009',
         'desc' => 'Thin Space',
         'replaceWith' => '\u{2009}',
+        'similarTo' => ' ',
     ),
     "\xE2\x80\x8A" => array(
+        'class' => 'char-ws',
         'codePoint' => '200A',
         'desc' => 'Hair Space',
         'replaceWith' => '\u{200a}',
+        'similarTo' => ' ',
     ),
     "\xE2\x80\x8B" => array(
+        'class' => 'char-ws',
         'codePoint' => '200B',
-        'desc' => 'Zero Width Space', // not included in Separator Category
+        'desc' => 'Zero Width Space', // not included in Separator Category (Other, Format)
         'replaceWith' => '\u{200b}',
+        'similarTo' => '',
+    ),
+    "\xE2\x80\x8C" => array(
+        'class' => 'char-ws',
+        'codePoint' => '200C',
+        'desc' => 'Zero Width Non-Joiner', // not included in Separator Category (Other, Format)
+        'replaceWith' => '\u{200c}',
+        'similarTo' => '',
+    ),
+    "\xE2\x80\x8D" => array(
+        'class' => 'char-ws',
+        'codePoint' => '200D',
+        'desc' => 'Zero Width Joiner', // not included in Separator Category (Other, Format)
+        'replaceWith' => '\u{200d}',
+        'similarTo' => '',
     ),
     "\xE2\x80\xA8" => array(
+        'class' => 'char-ws',
         'codePoint' => '2028',
         'desc' => 'Line Separator',
         'replaceWith' => '\u{2028}',
+        'similarTo' => "\n",
     ),
     "\xE2\x80\xA9" => array(
+        'class' => 'char-ws',
         'codePoint' => '2029',
         'desc' => 'Paragraph Separator',
         'replaceWith' => '\u{2029}',
+        'similarTo' => "\n",
     ),
     "\xE2\x80\xAF" => array(
+        'class' => 'char-ws',
         'codePoint' => '202F',
         'desc' => 'Narrow No-Break Space',
         'replaceWith' => '\u{202f}',
+        'similarTo' => ' ',
     ),
     "\xE2\x81\x9F" => array(
+        'class' => 'char-ws',
         'codePoint' => '202F',
         'desc' => 'Medium Mathematical Space',
         'replaceWith' => '\u{205f}',
+        'similarTo' => ' ',
+    ),
+    "\xE2\x81\xA0" => array(
+        'class' => 'char-ws',
+        'codePoint' => '2060',
+        'desc' => 'Word Joiner', // Not included in Separator Category (Other, Format)
+        'replaceWith' => '\u{2060}',
+        'similarTo' => '',
     ),
     "\xE3\x80\x80" => array(
+        'class' => 'char-ws',
         'codePoint' => '3000',
         'desc' => 'Ideographic Space',
         'replaceWith' => '\u{3000}',
+        'similarTo' => ' ',
     ),
     "\xEF\xBB\xBF" => array(
+        'class' => 'char-ws',
         'codePoint' => 'FEFF',
-        'desc' => 'BOM / Zero Width No-Break Space', // not included in Separator Category
+        'desc' => 'BOM / Zero Width No-Break Space', // not included in Separator Category (Other, Format)
         'replaceWith' => '\u{feff}',
+        'similarTo' => '',
     ),
+
     "\xEF\xBF\xBD" => array(
         'codePoint' => 'FFFD',
         'desc' => 'Replacement Character',

src/Debug/Abstraction/Object/Methods.php

@@ -145,9 +145,8 @@ public function toString(Abstraction $abs)
         }
         $val = null;
         try {
-            $val = $obj->__toString();
             /** @var Abstraction|string */
-            $val = $this->abstracter->crate($val, $abs['debugMethod'], $abs['hist']);
+            $val = $this->abstracter->crate($obj->__toString(), $abs['debugMethod'], $abs['hist']);
         } catch (Exception $e) {
             // yes, __toString can throw exception..
             // example: SplFileObject->__toString will throw exception if file doesn't exist

src/Debug/Dump/AbstractValue.php

@@ -68,6 +68,7 @@ public function __construct(Dumper $dumper)
         $this->optionStackPush(array(
             'addQuotes' => true,
             'charHighlight' => true,
+            'charReplace' => true,
         ));
     }
 
@@ -118,7 +119,7 @@ public function dump($val, $opts = array())
      *
      * @param string $str String to search for chars
      *
-     * @return array
+     * @return list<string>
      */
     public function findChars($str)
     {
@@ -338,7 +339,7 @@ abstract protected function dumpString($val, Abstraction $abs = null);
 
     /**
      * escape hex and unicode escape sequences
-     * this allows use to differentiate between '\u{03c5}' and a replaced "\u{03c5}"
+     * this allows us to differentiate between '\u{03c5}' and a replaced "\u{03c5}"
      *
      * @param string $val string value
      *

src/Debug/Dump/Base/Value.php

@@ -281,6 +281,31 @@ protected function getObject()
         return $this->lazyObject;
     }
 
+    /**
+     * Get replacement for character
+     *
+     * @param string $char        single multi-byte character
+     * @param bool   $charReplace whether to replace char with code-point
+     *                            control chars are always replaced
+     *
+     * @return string \x##, \u{####}, or original char
+     */
+    protected function charReplacement($char, $charReplace)
+    {
+        if (\ord($char) < 0x80) {
+            // always replace control chars
+            return '\\x' . \str_pad(\dechex(\ord($char)), 2, '0', STR_PAD_LEFT);
+        }
+        if (isset($this->charData[$char]['class']) && \strpos($this->charData[$char]['class'], 'char-ws') !== false) {
+            // always replace "whitespace" chars
+            $charReplace = true;
+        }
+        if ($charReplace) {
+            return '\\u{' . \str_pad(\dechex(Utf8::ord($char)), 4, '0', STR_PAD_LEFT) . '}';
+        }
+        return $char;
+    }
+
     /**
      * Highlight confusable and other characters
      *
@@ -291,24 +316,11 @@ protected function getObject()
     protected function highlightChars($str)
     {
         $chars = $this->findChars($str);
+        $charReplace = $this->optionGet('charReplace');
         foreach ($chars as $char) {
-            $replacement = $this->charReplacement($char);
+            $replacement = $this->charReplacement($char, $charReplace);
             $str = \str_replace($char, $replacement, $str);
         }
         return $str;
     }
-
-    /**
-     * Get ordinal replacement for character
-     *
-     * @param string $char single multi-byte character
-     *
-     * @return string \x## or \u{####}
-     */
-    protected function charReplacement($char)
-    {
-        return \ord($char) < 0x80
-            ? '\\x' . \str_pad(\dechex(\ord($char)), 2, '0', STR_PAD_LEFT)
-            : '\\u{' . \str_pad(\dechex(Utf8::ord($char)), 4, '0', STR_PAD_LEFT) . '}';
-    }
 }

src/Debug/Dump/TextAnsi.php

@@ -29,7 +29,7 @@ class TextAnsi extends Text
         'escapeCodes' => array(
             'arrayKey' => "\e[38;5;83m",    // yellow
             'binary' => "\e[30;48;5;250m",  // black foreground / grey background
-            'char' => "\e[38;5;208m",       // orange
+            'char' => "\e[34;48;5;14m",     // blue foreground / light-blue background
             'excluded' => "\e[38;5;9m",     // red
             'false' => "\e[91m",            // red
             'keyword' => "\e[38;5;45m",     // blue

src/Debug/Dump/TextAnsi/Value.php

@@ -16,6 +16,7 @@
 use bdk\Debug\Abstraction\Object\Abstraction as ObjectAbstraction;
 use bdk\Debug\Abstraction\Type;
 use bdk\Debug\Dump\Text\Value as TextValue;
+use bdk\Debug\Dump\TextAnsi as Dumper;
 use bdk\Debug\Dump\TextAnsi\TextAnsiObject;
 use bdk\Debug\Utility\Utf8;
 
@@ -30,6 +31,19 @@ class Value extends TextValue
     /** @var TextAnsiObject */
     protected $lazyObject;
 
+    /**
+     * Constructor
+     *
+     * @param Dumper $dumper "parent" dump class
+     */
+    public function __construct(Dumper $dumper)
+    {
+        parent::__construct($dumper); // sets debug and dumper
+        $this->optionStackPush(array(
+            'charReplace' => false,
+        ));
+    }
+
     /**
      * Get escape reset sequence
      *
@@ -356,9 +370,10 @@ protected function getObject()
     protected function highlightChars($str)
     {
         $chars = $this->findChars($str);
+        $charReplace = $this->optionGet('charReplace');
         foreach ($chars as $char) {
             $replacement = $this->cfg['escapeCodes']['char']
-                . $this->charReplacement($char)
+                . $this->charReplacement($char, $charReplace)
                 . $this->escapeReset;
             $str = \str_replace($char, $replacement, $str);
         }