<?php

$abc = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ';

function sanitydict(&$dict) {
	global $abc;
	$out = array();
	foreach ($dict as $n => $d) {
		$d = strtoupper($d);
		$d = preg_replace("|[^$abc]|ismU", '', $d);
		
		if ($d == '') {
			unset($dict[$n]);
		} else {
			$dict[$n] = $d;
		}
	}
}

function generate_char_haeufigkeit($file) {
        $dict = file($file);
        sanitydict($dict);
        $dict = array_unique($dict);

	$count = array();
	$total = 0;

        foreach ($dict as $d) {
                for ($i=0; $i<strlen($d); $i++) {
                        $c = substr($d, $i, 1);
                        $count[$c]++;
			$total++;
                }
	}

        // Abs -> Rel
        foreach ($count as $n => $f) {
                $count[$n] = $f / $total;
        }

	$max = 0;
	foreach ($count as $c) if ($c > $max) $max = $c;
	$count['max'] = $max;

	return $count;
}

function generate_char_haeufigkeit_start($file) {
        $dict = file($file);
        sanitydict($dict);
        $dict = array_unique($dict);

        $count = array();
        $total = 0;

        foreach ($dict as $d) {
		$total++;
		$i = 0;
                $c = substr($d, $i, 1);
                $count[$c]++;
        }

        // Abs -> Rel
        foreach ($count as $n => $f) {
                $count[$n] = $f / $total;
        }

        $max = 0;
        foreach ($count as $c) if ($c > $max) $max = $c;
        $count['max'] = $max;

        return $count;
}

function generate_char_haeufigkeit_end($file) {
        $dict = file($file);
        sanitydict($dict);
        $dict = array_unique($dict);

        $count = array();
        $total = 0;

        foreach ($dict as $d) {
                $total++;
                $i = strlen($d)-1;
                $c = substr($d, $i, 1);
                $count[$c]++;
        }

        // Abs -> Rel
        foreach ($count as $n => $f) {
                $count[$n] = $f / $total;
        }

        $max = 0;
        foreach ($count as $c) if ($c > $max) $max = $c;
        $count['max'] = $max;

        return $count;
}

function generate_wordcount($file) {
        $dict = file($file);
        sanitydict($dict);
        $dict = array_unique($dict);

	return count($dict);
}

function generate_neighbor_n_lookup($n, $file) {
        $dict = file($file);
        sanitydict($dict);
        $dict = array_unique($dict);

        $folge = array();
        $total = 0;

        foreach ($dict as $d) {
                for ($i=0; $i<strlen($d)-($n-1); $i++) {
                        $c = substr($d, $i, $n);
                        $folge[$c]++;
                        $total++;
                }
        }

        unset($dict);

        // Abs -> Rel
        foreach ($folge as $n => $f) {
                $folge[$n] = $f / $total;
        }

        $max = 0;
        foreach ($folge as $c) if ($c > $max) $max = $c;
        $folge['max'] = $max;

# TODO: fill up

        return $folge;
}

function generate_markov_lookup($file) {
        $n = 2;

        $dict = file($file);
        sanitydict($dict);
        $dict = array_unique($dict);

        $folge = array();
        $total = array();

        foreach ($dict as $d) {
                for ($i=0; $i<strlen($d)-($n-1); $i++) {
                        $c = substr($d, $i, $n);
                        $folge[$c]++;
                        $total[substr($d, $i, 1)]++;
                }
        }

        unset($dict);

        // Abs -> Rel
        foreach ($folge as $n => $f) {
		$total2 = 0;
		global $abc;
		for ($u=0; $u<strlen($abc); $u++) {
        	        $total2 += $total[$abc[$u]];
		}
		$folge[$n] = $f / $total2;
        }

        # TODO: fill up

        return $folge;
}

?>