# This module contains some low-level character-handling stuff.

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - #
# Look up a single HTML escape-sequence symbol ("entity")  in  AStbl, #
# or  check  to  see if it's numeric.  The return value is the single #
# character corresponding to the symbol.  - - - - - - - - - - - - - - #
# - - - - - - - - - - - - - - - - - - - -                             #
proc Chr s {
	global V me AStbl
	if [info exists AStbl($s)] {
		set val $AStbl($s)
		if {$V>4} {puts "$me/Chr: AStbl([DSP $s]) is $val"}
	} elseif [scan $s {%d} val] {
	} else {
		if {$V>0} {puts "$me/Chr: ### &$s; not known ###"}
		return &$s;
	}
	format {%c} $val
}

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - #
# Scan x for HTML-encoded characters, and replace them with the chars #
# that they represent.  There are two sorts of encodings that we look #
# for here:  "&foo;" is a symbolic encoding, and is looked up in  the #
# AStbl array above. "&#ddd;" is a numeric encoding, and is converted #
# to the corresponding binary byte.                                   #
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - #
proc Hdecode x {
	global V me AStbl
	set v {}
	global V me 
	while [regexp {^(.*)&(#?)([A-Za-z0-9]+);(.*)$} $x {} x y s z] {
		if {$y != {}} {
			scan $s {%d} val
			set c [format {%c} $val]
		} elseif [info exists AStbl($s)] {
			set c [format {%c} $AStbl($s)]
		} else {
			set c "&$s;"
		}
		set v "$c$z$v"
	}
	return "$x$v"
}

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - #
# Here is our table of symbolic char names.  Note the decimal values. #
# Note  also that some of these are case sensitive in the first char, #
# to distinguish marked upper- and lower- case letters.               #
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - #
global AStbl
array set AStbl {
	sp      32
	quot    34
	amp     38
	lt      60
	gt      62
	nbsp   160
	iexcl  161
	cent   162
	pound  163
	curren 164
	yen    165
	brvbar 166
	sect   167
	uml    168
	copy   169
	ordf   170
	laquo  171
	not    172
	shy    173
	reg    174
	macr   175
	deg    176
	plusmn 177
	sup2   178
	sup3   179
	acute  180
	micro  181
	para   182
	middot 183
	cedil  184
	sup1   185
	ordm   186
	raquo  187
	frac14 188
	frac12 189
	frac34 190
	iquest 191
	Agrave 192
	Aacute 193
	Acirc  194
	Atilde 195
	Auml   196
	Aring  197
	AElig  198
	Aelig  198
	Ccedil 199
	Egrave 200
	Eacute 201
	Ecirc  202
	Euml   203
	Igrave 204
	Iacute 205
	Icirc  206
	Iuml   207
	ETH    208
	Eth    208
	Ntilde 209
	Ograve 210
	Oacute 211
	Ocirc  212
	Otilde 213
	Ouml   214
	times  215
	Oslash 216
	Ugrave 217
	Uacute 218
	Ucirc  219
	Uuml   220
	Yacute 221
	THORN  222
	Thorn  222
	szlig  223
	agrave 224
	aacute 225
	acirc  226
	atilde 227
	auml   228
	aring  229
	aelig  230
	ccedil 231
	egrave 232
	eacute 233
	ecirc  234
	euml   235
	igrave 236
	iacute 237
	icirc  238
	iuml   239
	eth    240
	ntilde 241
	ograve 242
	oacute 243
	ocirc  244
	otilde 245
	ouml   246
	divide 247
	oslash 248
	ugrave 249
	uacute 250
	ucirc  251
	uuml   252
	yacute 253
	thorn  254
	yuml   255
}