NAME
     stan - stream analyser

SYNOPSIS
     stan [ -bhvV ] [ -f filter ] [ -n number ] [ -p patlen  ]  [
     file ... ]

DESCRIPTION
     Stan creates statistics about the content of files or stdin.
     This  information  can be used in many ways, e.g. to analyze
     encrypted data or measure the quality of random numbers. The
     program  expects  a  list of files at the end of the command
     line, if no files are specified standard input is used.

     Stan is able to create three different types of statistics

  General Statistics
     Stan uses the bytes of the input data to calculate  standard
     statisic  values.   It  calculates the mean, the median, the
     deviation  and  the  chi-squared  value.  If  possible   the
     corresponding  characters  are  printed  after  the  decimal
     value.

  Pattern Statistics
     Stan analyzes all patterns of the length patlen  inside  the
     data stream and outputs the range and counts of patterns.

  Bit Statistics
     Bit statistics are measured using runs. Runs are a sequences
     of  the same bit, therefore stan analyses 0 runs and 1 runs.
     In bit mode stan prints ratio of runs of  a  length  to  the
     next  length.  This  analysis  fits the pseudo random number
     criteria G1 by Golomb. Stan also prints the ratio of 0  runs
     to 1 runs by the length of the runs, this analysis refers to
     the second criteria G2 by Golomb.

OPTIONS
     -b
          Enable  bit  mode.  Create  bit  statistics  about  the
          stream.

     -h
          Print a help screen to stderr.

     -v
          Be verbose. In this mode stan prints  verbose  informa-
          tion about the analysing process and also displays pro-
          gress information. When analysing large files this is a
          usefull option in order to see what acutally is happen-
          ing.


     -V
          Display the version.

     -f filter
          Use a filter before passing the data to  the  analysing
          process.  The  following filter may be used to restrict
          the range of data.

               0 No filter (default)

               1 Analyse only printable characters.

               2 Analyse only alphanumeric characters.

     -n number
          Display number of patterns. The default  value  is  10.
          You  should keep this value rather small since normally
          a lot of patterns will be found in a data stream.

     -p patlen
          Analyse patterns from 1 to patlen length. The length of
          the pattern is measured in bytes.

USAGE
     The interpretation of output generated by  Stan  requires  a
     good  mathematical  / statistcal background. This manual can
     not focus on all aspects of interpreting statistical values.
     The  general  statistics  are  covered  by  most books about
     statistics and analysis.  There is a  book,  Shift  Register
     Sequences written by S.Goloumb (1967), with further informa-
     tion about interpreting the bit statistics.

     Some examples of stan can be found  at  the  stan  homepage,
     http://www.roqe.org/stan.


NOTES
     Stan was designed with efficency in mind,  but  if  you  are
     using  a  large  patlen  , i.e. 6 or above, you may run into
     memory problems, especially if you are analysing  random  or
     nearly  random data. Just remember that there are 256^6 pat-
     terns of the length 6, which could require 281  terabyte  of
     memory!

     If you discover bugs or have any improvements to  stan  con-
     tact the author at kr@roqe.org. You can always grab the latest
     version of stan from http://www.roqe.org/stan.