Raspberry Pi Forums

Code: Select all

pi@pi3-buster-1:~ $ uname -a
Linux pi3-buster-1 4.19.50-v7+ #896 SMP Thu Jun 20 16:11:44 BST 2019 armv7l GNU/Linux
pi@pi3-buster-1:~ $ node -v
v10.15.2

pi@pi3-buster-1:~ $ time node selfgrams.js > selfgrams_js.txt
rss 147.39 MB
heapTotal 114.88 MB
heapUsed 100.21 MB
external 0.01 MB

real    0m16.848s
user    0m18.010s
sys     0m0.401s

pi@pi3-buster-1:~ $ time ./selfgrams.pl > selfgrams_pl.txt

real    0m11.214s
user    0m11.042s
sys     0m0.171s

pi@pi3-buster-1:~ $ md5sum selfgrams_pl.txt selfgrams_js.txt
addeda36a4631afc983f3bff13742e36  selfgrams_pl.txt
addeda36a4631afc983f3bff13742e36  selfgrams_js.txt

Code: Select all

pi@pi3-buster-1:~ $ node -v
v12.6.0

pi@pi3-buster-1:~ $ time ./selfgrams.pl > selfgrams_pl.txt

real    0m11.297s
user    0m11.161s
sys     0m0.111s

pi@pi3-buster-1:~ $ time node selfgrams.js > selfgrams_js.txt
rss 119.24 MB
heapTotal 83.82 MB
heapUsed 77.32 MB
external 0.64 MB

real    0m11.817s
user    0m13.635s
sys     0m0.292s

pi@pi3-buster-1:~ $ md5sum selfgrams_js.txt selfgrams_pl.txt
addeda36a4631afc983f3bff13742e36  selfgrams_js.txt
addeda36a4631afc983f3bff13742e36  selfgrams_pl.txt
pi@pi3-buster-1:~ $

Code: Select all

1000 REM banagram.bas -- Find anagrams
1010 REM Written July 16, 1978 by Eric Olson
1020 REM
1030 REM This program demonstrates using letter counts and linear
1040 REM lists to find anagrams in the insane British dictionary.
1050 REM
2000 REM F$="/usr/share/dict/british-english-insane"
2001 F$="tail.dat"
2010 M0=0:OPEN F$ FOR INPUT AS #1
2015 IF EOF(1)<>0 THEN 2030
2020 INPUT #1,A$:M0=M0+1:GOTO 2015
2030 DIM L$(M0),K$(M0),V0(26)
2040 CLOSE #1:OPEN F$ FOR INPUT AS #1
2050 A1=ASC("a")-1:A2=ASC("0"):N0=0
2060 FOR I=1 TO M0:INPUT #1,A$
2063 FOR J=1 TO 26:V0(J)=0:NEXT J:J=0
2065 IF J>=LEN(A$) THEN 2075
2068 J=J+1:C=ASC(MID$(A$,J,1))-A1
2070 IF (C<1) OR (C>26) THEN 2130
2071 V0(C)=V0(C)+1:GOTO 2065
2075 V$="":FOR J=1 TO 26
2080 V$=V$+CHR$(V0(J)+A2):NEXT J:J=0
2090 IF J>=N0 THEN 2120
2100 J=J+1:IF K$(J)<>V$ THEN 2090
2110 L$(J)=L$(J)+" "+A$+",":GOTO 2130
2120 N0=N0+1:L$(N0)=A$+":":K$(N0)=V$
2130 NEXT I:CLOSE #1
2400 FOR I=1 TO N0:A$=L$(I)
2410 IF RIGHT$(A$,1)=":" THEN 2430
2420 PRINT LEFT$(A$,LEN(A$)-1)
2430 NEXT I
9000 END

Code: Select all

$ tail -n 10000 /usr/share/dict/british-english-insane >tail.dat
$ wc tail.dat
10000 10000 93607 tail.dat
$ time ./bwbasic banagram.bas >banagram-bw.tail

real    18m30.145s
user    18m29.419s
sys 0m0.120s
$ time ./sbrandy banagram-mb.bas >banagram-mb.tail

real    0m23.888s
user    0m23.797s
sys 0m0.071s
$ time ./gplbasic banagram.bas >banagram-gpl.tail

real    0m9.476s
user    0m9.460s
sys 0m0.011s
$ fbc -lang qb banagram.bas
$ time ./banagram >banagram-fbc.tail

real    0m5.330s
user    0m5.313s
sys 0m0.011s
$ time ./anagram.perl >perl.tail

real    0m0.226s
user    0m0.205s
sys 0m0.021s
$ md5sum *.tail
2f0427e2de42059e20bb335e25c5c1ca  banagram-bw.tail
2f0427e2de42059e20bb335e25c5c1ca  banagram-fbc.tail
2f0427e2de42059e20bb335e25c5c1ca  banagram-gpl.tail
2f0427e2de42059e20bb335e25c5c1ca  banagram-mb.tail
2f0427e2de42059e20bb335e25c5c1ca  perl.tail

Code: Select all

1000 REM banagram-mb.bas -- Find anagrams
1010 REM Written July 17, 1978 by Eric Olson
1020 REM
1030 REM This program demonstrates using letter counts and linear
1040 REM lists to find anagrams in the insane British dictionary.
1050 REM
2000 REM F$="/usr/share/dict/british-english-insane"
2001 F$="tail.dat"
2010 M0=0:F1=OPENIN(F$)
2015 IF EOF#(F1)<>0 THEN 2030
2020 A$=GET$#(F1):M0=M0+1:GOTO 2015
2030 DIM L$(M0),K$(M0),V0(26)
2040 CLOSE# F1:F1=OPENIN(F$)
2050 A1=ASC("a")-1:A2=ASC("0"):N0=0
2060 FOR I=1 TO M0:A$=GET$#(F1)
2063 FOR J=1 TO 26:V0(J)=0:NEXT J:J=0
2065 IF J>=LEN(A$) THEN 2075
2068 J=J+1:C=ASC(MID$(A$,J,1))-A1
2070 IF (C<1) OR (C>26) THEN 2130
2071 V0(C)=V0(C)+1:GOTO 2065
2075 V$="":FOR J=1 TO 26
2080 V$=V$+CHR$(V0(J)+A2):NEXT J:J=0
2090 IF J>=N0 THEN 2120
2100 J=J+1:IF K$(J)<>V$ THEN 2090
2110 L$(J)=L$(J)+" "+A$+",":GOTO 2130
2120 N0=N0+1:L$(N0)=A$+":":K$(N0)=V$
2130 NEXT I:CLOSE# F1
2400 FOR I=1 TO N0:A$=L$(I)
2410 IF RIGHT$(A$,1)=":" THEN 2430
2420 PRINT LEFT$(A$,LEN(A$)-1);CHR$(10);
2430 NEXT I
9000 END

Code: Select all

#!/usr/bin/python3

import sys,re
if sys.version[0:3] < "3.6":
    from collections import OrderedDict
    anagrams = OrderedDict()
else:
    anagrams = {}

f = open('/usr/share/dict/british-english-insane','rt')
dictionary = f.read().split('\n')
f.close()

check = re.compile('^[a-z]+$')

for word in dictionary:
    if check.match(word):
        keyl = list(word)
        keyl.sort()
        key = ''.join(keyl)
        if key in anagrams:
            anagrams[key].append(word)
        else:
            anagrams[key] = [word]
output = ''

for v in anagrams.values():
    if len(v) > 1:
        op = ', '.join(v) + '\n'
        output += op.replace(',',':',1)

print(output,end='')

Code: Select all

pi@raspberrypi4:~ $ time ./selfgrams.py > selfgrams_py.txt

real	0m14,493s
user	0m14,221s
sys	0m0,180s
pi@raspberrypi4:~ $ time ./selfgrams.pl > selfgrams_pl.txt

real	0m11,729s
user	0m11,417s
sys	0m0,120s
pi@raspberrypi4:~ $ md5sum selfgrams_pl.txt
bec74aa3b31577edbb291aeb7269a4d5  selfgrams_pl.txt
pi@raspberrypi4:~ $ md5sum selfgrams_py.txt
bec74aa3b31577edbb291aeb7269a4d5  selfgrams_py.txt

Code: Select all

#!/usr/bin/perl -l
# selfgrams4.pl - find words that have valid anagrams
# scruss - 2019-07
my ( %grams, $key, $fh, @out, $k );

open( $fh, '<', '/usr/share/dict/british-english-insane' ) or die "$!\n";
foreach ( grep { /^[a-zèóüäçéáåöñëíâôûøêîïàùú]+$/ && chomp; } <$fh> ) {
    $key = join( '', sort( split( '', $_ ) ) );
    if ( exists( $grams{$key} ) ) {
        $out[ $grams{$key} ] .= ', ' . $_;
    }
    else {
        $grams{$key} = $k;
        $out[$k] = $_;
        $k++;
    }
}
close($fh);

print join( "\n", grep { index( $_, ',' ) >= 0 && s/,/:/; } @out );
exit;

Code: Select all

#!/usr/bin/python3

import sys
if sys.version[0:3] < "3.6":
    from collections import OrderedDict
    anagrams = OrderedDict()
else:
    anagrams = {}

f = open('/usr/share/dict/british-english-insane','rt')
dictionary = f.read().split('\n')
f.close()

for word in dictionary:
    if word.islower() and "'" not in word:
        keyl = list(word)
        keyl.sort()
        key = ''.join(keyl)
        if key in anagrams:
            anagrams[key].append(word)
        else:
            anagrams[key] = [word]
output = ''

for v in anagrams.values():
    if len(v) > 1:
        op = ', '.join(v) + '\n'
        output += op.replace(',',':',1)

print(output,end='')

Code: Select all

pi@raspberrypi4:~ $ time ./selfgramsall.py > selfgrams_py.txt

real	0m12,821s
user	0m12,599s
sys	0m0,160s
pi@raspberrypi4:~ $ time ./selfgramsall.pl > selfgrams_pl.txt

real	0m11,504s
user	0m11,320s
sys	0m0,150s
pi@raspberrypi4:~ $ md5sum selfgrams_pl.txt
a6073146aceaa463645c7685ddd6a9a0  selfgrams_pl.txt
pi@raspberrypi4:~ $ md5sum selfgrams_py.txt
a6073146aceaa463645c7685ddd6a9a0  selfgrams_py.txt

Code: Select all

module wordtest

function isword(s as string) as boolean
    dim i,c as integer
    for i=1 to len(s)
        c=asc(mid(s,i,1))
        if (c<asc("a")) or (c>asc("z")) then
            return false
        end if
    next i
    return true
end function

function main() as integer
    if isword("test") then 
        console.writeline("test is lowercase")
    else
        console.writeline("test is not lowercase")
    end if
    if isword("tEst") then
        console.writeline("tEst is lowercase")
    else
        console.writeline("tEst is not lowercase")
    end if
    return 0
end function

end module

Code: Select all

$ vbnc wordtest.bas 
Visual Basic.Net Compiler version 0.0.0.5943 (Mono 4.0.1 - tarball)
Copyright (C) 2004-2010 Rolf Bjarne Kvinge. All rights reserved.

Compilation successful
Compilation took 00:00:18.4694050
$ mono wordtest.exe
test is lowercase
tEst is not lowercase

Code: Select all

//
// insane-british-anagram.cpp - Find words that have valid anagrams
//                              Words sourced from Debian's british-english-insane dictionary
//
// heater - 2019-07-25
// 
#include <fstream>
#include <string>
#include <iostream>
#include <stdlib.h>
#include <string.h>

#include <unordered_map> 

std::string getFileContents(const char *filename) {
    std::ifstream in(filename, std::ios::in | std::ios::binary);
    if (in) {
        std::string contents;
        in.seekg(0, std::ios::end);
        contents.resize(in.tellg());
        in.seekg(0, std::ios::beg);
        in.read(&contents[0], contents.size());
        in.close();
        return(contents);
    }
    throw(std::runtime_error("Shit happened!"));
}

char* sortString (const char* s) {
    char* string = (char*)malloc(strlen(s) + 1); 
    strcpy (string, s); 
    char temp;
    int i, j;
    int n = strlen(string);

    for (i = 0; i < n-1; i++) {
        for (j = i+1; j < n; j++) {
            if (string[i] > string[j]) {
            temp = string[i];
            string[i] = string[j];
            string[j] = temp;
            }
        }
    }
    return string;
}

int main (int argc, char* argv[]) {
    // Map container for sets of anagrams 
    // An anagram set is simply a string of format like: "whiter: wither, wrihte, writhe"
    std::unordered_map<std::string, std::string> anagramMap;
    std::unordered_map<std::string, std::string>::iterator it;

    auto dictionary = getFileContents("/usr/share/dict/british-english-insane");
    char* dictionaryPtr = (char*)dictionary.c_str();
    char* wordPtr = dictionaryPtr;
    char* charPtr = wordPtr;
    bool reject = false;
    while (1) {
        if (islower(*charPtr)) {
            // We are scanning a valid word
            charPtr++;
        } else if ((*charPtr) == '\n') {
            // We have hit the end of a word, use the word if it's valid
            *charPtr = 0;
            if (!reject) {
                // Do we have a word with this key (potential anagram)?
                char* key = sortString(wordPtr);
                it = anagramMap.find(key);
                if (it == anagramMap.end()) {
                    // No: Add it to the map as start of new anagram set.
                    anagramMap[key] = std::string(wordPtr);
                } else {
                    // Yes: Append it to the existing anagram set.
                    it->second.append(", ").append(wordPtr); 
                }
            }
            charPtr++;
            wordPtr = charPtr;
            reject = false;
        } else if ((*charPtr) != 0) {
            // Invalid character
            reject = true;
            charPtr++;
        } else {
            // End of dictionary
            break;
        }
    }

    // Output all the sets that have more than one word.
    for( auto const& [key, val] : anagramMap )
    {
        // Sets with a "," contain more than one word, the anagrams!
        size_t found = val.find(',');
        if (found != std::string::npos) {
            std::string fart = val;
            fart.replace(found, 1, ":");
            std::cout << fart << std::endl ;
        }
    }
    return (0);
}

Code: Select all

pi@pi3-buster-1:~ $ g++ -std=c++17 -Wall -O3 -o insane-british-anagram insane-british-anagram.cpp
pi@pi3-buster-1:~ $ time ./insane-british-anagram > insane-british-anagram-cpp.txt

real    0m1.931s
user    0m1.580s
sys     0m0.350s
pi@pi3-buster-1:~ $ time node insane-british-anagram.js > insane-british-anagram-js.txt
rss 119.62 MB
heapTotal 83.82 MB
heapUsed 77.3 MB
external 0.64 MB

real    0m11.967s
user    0m13.957s
sys     0m0.231s