Normalizing 0xA0 (No-Break Space) And Other Special Characters Within ColdFusion Form Posts

Application.cfc

component {

	/**
	* I get called once at the start of each incoming ColdFusion request.
	*/
	public void function onRequestStart() {

		for ( var key in form ) {

			if ( isSimpleValue( form[ key ] ) ) {

				form[ key ] = textNormalization.normalizeText( form[ key ] );

			}

		}

	}

}

snippet-1.cfc

component {

	/**
	* I apply all the normalization methods to the given value and return the result.
	*/
	public string function normalizeText( required string value ) {

		var result = trim( value );
		result = normalizeLineEndings( result );
		result = normalizeSpaces( result );
		result = normalizeDoubleQuotes( result );
		result = normalizeSingleQuotes( result );
		result = normalizeDashes( result );
		result = normalizeBullets( result );

		return( result );

	}

}

TextNormalization.cfc

/**
* The site - https://unicode-table.com/ - is great for looking up Unicode values.
*/
component
	output = false
	hint = "I provide methods for normalizing special characters within text values."
	{

	// --
	// PUBLIC METHODS.
	// --

	/**
	* I replace special bullets with the standard asterisk.
	*/
	public string function normalizeBullets( required string value ) {

		return(
			jreReplace(
				value,
				"(?x)[
					\u2022  ## Bullet.
					\u2023  ## Triangular Bullet.
					\u2043  ## Hyphen Bullet.
					\u2219  ## Bullet Operator.
					\u25aa  ## Black Small Square Emoji.
					\u25cb  ## White Circle.
					\u25cf  ## Black Circle.
					\u25e6  ## White Bullet.
				]",
				"*"
			)
		);

		return( content );

	}


	/**
	* I replace like-sized dashes with standard dashes.
	*/
	public string function normalizeDashes( required string value ) {

		return(
			jreReplace(
				value,
				"(?x)[
					\u2013  ## En Dash.
					\u2212  ## Minus Sign.
				]",
				"-"
			)
		);

	}


	/**
	* I replace "smart double quotes" with standard double quotes.
	*/
	public string function normalizeDoubleQuotes( required string value ) {

		return(
			jreReplace(
				value,
				"(?x)[
					\u201c  ## Left Double Quotation Mark.
					\u201d  ## Right Double Quotation Mark.
					\u201e  ## Double Low-9 Quotation Mark.
					\u201f  ## Double High-Reversed-9 Quotation Mark.
					\u275d  ## Heavy Double Turned Comma Quotation Mark Ornament.
					\u275e  ## Heavy Double Comma Quotation Mark Ornament.
					\u2e42  ## Double Low-Reversed-9 Quotation Mark.
					\u301d  ## Reversed Double Prime Quotation Mark.
					\u301e  ## Double Prime Quotation Mark.
					\u301f  ## Low Double Prime Quotation Mark.
					\uff02  ## Fullwidth Quotation Mark.
				]",
				""""
			)
		);

	}


	/**
	* I convert all the line-breaks to NewLine characters.
	*/
	public string function normalizeLineEndings( required string value ) {

		return( jreReplace( value, "\r\n?", chr( 10 ) ) );

	}


	/**
	* I replace "smart single quotes" with standard single quotes.
	*/
	public string function normalizeSingleQuotes( required string value ) {

		return(
			jreReplace(
				value,
				"(?x)[
					\u2018  ## Left Single Quotation Mark.
					\u2019  ## Right Single Quotation Mark.
					\u201a  ## Single Low-9 Quotation Mark.
					\u201b  ## Single High-Reversed-9 Quotation Mark.
					\u275b  ## Heavy Single Turned Comma Quotation Mark Ornament.
					\u275c  ## Heavy Single Comma Quotation Mark Ornament.
					\u275f  ## Heavy Low Single Comma Quotation Mark Ornament.
				]",
				"'"
			)
		);

	}


	/**
	* I convert any special spaces to regular spaces.
	*/
	public string function normalizeSpaces( required string value ) {

		return(
			jreReplace(
				value,
				"(?x)[
					\u00a0  ## No-Break Space.
					\u2000  ## En Quad (space that is one en wide).
					\u2001  ## Em Quad (space that is one em wide).
					\u2002  ## En Space.
					\u2003  ## Em Space.
					\u2004  ## Thick Space.
					\u2005  ## Mid Space.
					\u2006  ## Six-Per-Em Space.
					\u2007  ## Figure Space.
					\u2008  ## Punctuation Space.
					\u2009  ## Thin Space.
					\u200a  ## Hair Space.
					\u200b  ## Zero Width Space.
					\u2028  ## Line Separator.
					\u2029  ## Paragraph Separator.
					\u202f  ## Narrow No-Break Space.
					\ufeff  ## Zero Width No-Break Space.
				]",
				" "
			)
		);

	}


	/**
	* I apply all the normalization methods to the given value and return the result.
	*/
	public string function normalizeText( required string value ) {

		var result = trim( value );
		result = normalizeLineEndings( result );
		result = normalizeSpaces( result );
		result = normalizeDoubleQuotes( result );
		result = normalizeSingleQuotes( result );
		result = normalizeDashes( result );
		result = normalizeBullets( result );

		return( result );

	}

	// --
	// PRIVATE METHODS.
	// --

	/**
	* I use Java's Pattern engine to perform a RegEx replace on the given input.
	*/
	private string function jreReplace(
		required string input,
		required string pattern,
		string replacement = ""
		) {

		var result = javaCast( "string", input ).replaceAll(
			javaCast( "string", pattern ),
			javaCast( "string", replacement )
		);

		return( result );

	}

}