Richard Suchenwirth 2002-08-01 - In Solving cryptograms, amazing ways of automated decryption were shown, and CL asked for accessories e.g. for computing character and digram (2-character sequence) frequencies. I could not withstand such as little challenge, so here goes.
proc freq12 string {
# returns a pairlist: character/bigrams and the associated frequency
set last -
set n 0
foreach char [split $string- ""] {
incr n
inc a($char)
inc a($last$char)
set last $char
}
set res {}
foreach i [lsort [array names a]] {
lappend res $i [expr {$a($i)*1./$n}]
}
set res
}
proc inc {varName {amount 1}} {
# create a variable if not exists, then increment
upvar 1 $varName var
if {![info exists var]} {set var 0}
incr var $amount
}% freq12 "TCL-IS-A-SCRIPTING-LANGUAGE" - 0.178571428571 -A 0.0357142857143 -I 0.0357142857143 -L 0.0357142857143 -S 0.0357142857143 -T 0.0357142857143 A 0.107142857143 A- 0.0357142857143 AG 0.0357142857143 AN 0.0357142857143 C 0.0714285714286 CL 0.0357142857143 CR 0.0357142857143 E 0.0357142857143 E- 0.0357142857143 G 0.107142857143 G- 0.0357142857143 GE 0.0357142857143 GU 0.0357142857143 I 0.107142857143 IN 0.0357142857143 IP 0.0357142857143 IS 0.0357142857143 L 0.0714285714286 L- 0.0357142857143 LA 0.0357142857143 N 0.0714285714286 NG 0.0714285714286 P 0.0357142857143 PT 0.0357142857143 R 0.0357142857143 RI 0.0357142857143 S 0.0714285714286 S- 0.0357142857143 SC 0.0357142857143 T 0.0714285714286 TC 0.0357142857143 TI 0.0357142857143 U 0.0357142857143 UA 0.0357142857143