Improve Hidden Character Finder implementation

[Copilot]

Ports and improves the Hidden Character Finder from the PHP reference implementation to C#.

References:

• https://www.soscisurvey.de/tools/view-chars.php
• https://github.com/BurninLeo/see-non-printable-characters

Changes Made

New File: HCFService.cs

Extracted all character analysis logic into a public static HCFService class, making it independently unit-testable without Blazor rendering.

Bug Fixes

• Correct Unicode code point calculation: The old implementation incorrectly summed raw UTF-8 byte values (e.g., U+00A0 showed 354 instead of 160). Now correctly uses (int)c[0] for BMP characters and char.ConvertToUtf32() for surrogate pairs.
• Correct output format: Now matches the PHP reference — &#160;<br>\u00A0 and U+00A0 for multi-byte chars; 83<br>0x53 for ASCII chars.
• Surrogate pair handling: Text2Html now uses StringInfo.SubstringByTextElements instead of string.Substring(i, 1) to correctly process characters outside the BMP (emoji, etc.).
• Unicode escapes for supplementary characters: \uXXXX (4 hex digits) for BMP, \UXXXXXXXX (8 hex digits) for code points > U+FFFF.
• Whitespace symbol CSS class: Changed from undefined white class to symbol class.

Improvements

• Real character/byte counts: Replaced the # characters, # bytes placeholder with actual computed values displayed after processing.
• Cleaner initial state: Output section is hidden until "Show me the characters" is clicked.
• Cleanup: Removed debug Console.WriteLine calls, empty Decode() method, commented-out code, and static example HTML section.

Testing

• ✅ 10 new tests added to HCFTest.cs covering rendering, ASCII char tooltips, multi-byte Unicode, whitespace symbols, hidden characters, and char/byte counts.
• ✅ All 33 project tests pass.
• ✅ CodeQL analysis found no alerts.

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Hidden Character Finder</issue_title>
<issue_description>Port php to C#

• https://www.soscisurvey.de/tools/view-chars.php
• https://github.com/BurninLeo/see-non-printable-characters</issue_description>

Comments on the Issue (you are @copilot in this section)

@AlexHedley e029e33 @AlexHedley   @AlexHedley Review the current implementation of Hidden Character Finder and suggest any improvements

• Fixes Hidden Character Finder #12

---

💬 Send tasks to Copilot coding agent from Slack and Teams to turn conversations into code. Copilot posts an update in your thread when it's finished.

[AlexHedley]

@copilot retry please

[Copilot]

@copilot retry please

Done in commit dadf7d5. Here's a summary of the improvements made to the Hidden Character Finder:

Bug fixes:

• Fixed HtmlChar to correctly compute Unicode code points — the old implementation summed raw UTF-8 byte values instead of using the actual code point (e.g., U+00A0 was showing 354 instead of 160)
• Fixed Text2Html to use StringInfo.SubstringByTextElements to correctly handle surrogate pairs (emoji, etc.)
• Fixed Unicode escape format: BMP chars use \uXXXX, supplementary chars (> U+FFFF) use \UXXXXXXXX
• Fixed space/tab symbols: were using an undefined CSS class white, changed to symbol class consistent with other whitespace

Improvements:

• Extracted logic to HCFService.cs (public static class) — makes the logic independently unit-testable
• Character/byte count now shows real values (replaced "# characters, # bytes" placeholder)
• Output section is hidden until "Show me the characters" is clicked
• Removed debug Console.WriteLine calls, commented-out code, empty Decode() method, and static demo section

Tests: Added 10 tests covering rendering, ASCII char tooltips, multi-byte Unicode, whitespace symbols, hidden chars, and char/byte counts — all 33 project tests pass.