#
# config file for detox(1)
#
# Remove problematic characters.
#

#
# Default sequence.
#

sequence default {
	safe {
		builtin "safe";
	};
	wipeup {
		remove_trailing;
	};
};

#
# Sequences meant primarily for detox
#

# transliterates ISO 8859-1 into ASCII
sequence "iso8859_1" {
	iso8859_1 {
		builtin "iso8859_1";
	};
	safe {
		builtin "safe";
	};
	wipeup {
		remove_trailing;
	};
};

# transliterates CP-1252 and ISO8859-1 into ASCII
sequence "iso8859_1-legacy" {
	iso8859_1 {
		builtin "cp1252";
	};
	iso8859_1 {
		builtin "iso8859_1";
	};
	safe {
		builtin "safe";
	};
	wipeup {
		remove_trailing;
	};
};

# transliterates UTF-8 into ASCII
sequence "utf_8" {
	utf_8 {
		builtin "unicode";
	};
	safe {
		builtin "safe";
	};
	wipeup {
		remove_trailing;
	};
};

# transliterates CP-1252 and UTF-8 into ASCII
# this is *very* rare
sequence "utf_8-legacy" {
	utf_8 {
		builtin "cp1252";
	};
	utf_8 {
		builtin "unicode";
	};
	safe {
		builtin "safe";
	};
	wipeup {
		remove_trailing;
	};
};

# decodes CGI-escaped characters
sequence "uncgi" {
	uncgi;
	safe {
		builtin "safe";
	};
	wipeup {
		remove_trailing;
	};
};

# converts files to lower case
sequence "lower" {
	safe {
		builtin "safe";
	};
	lower;
	wipeup {
		remove_trailing;
	};
};

#
# Sequences meant primarily for inline-detox
#

# transliterates ISO 8859-1 to ASCII
sequence "iso8859_1-only" {
	iso8859_1 {
		builtin "iso8859_1";
	};
};

# transliterates CP-1252 to ASCII
sequence "cp1252-only" {
	iso8859_1 {
		builtin "cp1252";
	};
};

# transliterates UTF-8 to ASCII
sequence "utf_8-only" {
	utf_8 {
		builtin "unicode";
	};
};

# decodes CGI-escaped characters
sequence "uncgi-only" {
	uncgi;
};

# converts files to lower case
sequence "lower-only" {
	lower;
};


#
# Files to ignore during recursion (detox only)
#
# Any file or directory starting with '.' is automatically ignored except when
# it is passed on the command-line.
#

ignore {
	filename "{arch}";
};