Re^4: (german) region code detection

krambambuli wrote:: should work rather very effectively.

I was unsure about that and so I benchmarked.

I used the full list of 5132 region codes. Have no fear! There are not 32K of region codes following, just the (about) 9K of my regular expression which I use to generate the region code list and also the test data.

#!/usr/bin/perl
use strict;
use warnings;

use Benchmark qw(cmpthese);

# All region codes as a big regular expression
my $RC=qr/(0(?:2(?:0(?:[12389]|4[135]|5[123468]|6[456])|1(?:[14]|0[234
+]|29?|3[1237]|5[012346789]|6[123456]|7[1345]|8[123]|9[12356])|2(?:[18
+]|0[2345678]|2[2345678]|3[2345678]|4[12345678]|5[1234567]|6[123456789
+]|7[12345]|9[1234567])|3(?:[14]|0[123456789]|2[3457]|3[0123456789]|5[
+12345789]|6[0123456789]|7[12345789]|8[12345789]|9[12345])|4(?:1|0[123
+456789]|2[123456789]|3[123456]|4[013456789]|5[123456]|6[12345]|7[1234
+]|8[2456])|5(?:1|0[12456789]|2[0123456789]|3[234568]|4[1235678]|5[123
+45678]|6[12345678]|7[12345]|8[12345678]|9[0123456789])|6(?:1|0[123456
+78]|2[012345678]|3[0123456789]|4[1234567]|5[1234567]|6[123467]|7[1234
+5678]|8[0123456789]|9[1234567])|7(?:1|2[12345]|3[23456789]|4[123457]|
+5[01234589]|6[1234]|7[0123456789])|8(?:1|0[1234]|2[12345678]|3[123456
+789]|4[12345]|5[012356789]|6[1234567]|7[1234])|9(?:1|0[2345]|2[123457
+8]|3[1234578]|4[1234578]|5[1234578]|6[1234]|7[123457]|8[12345]|9[1234
+]))|3(?:0|3(?:[15]|0(?:[123467]|5[13456]|8[023456789]|9[34])|2(?:[127
+89]|0[0123456789]|3[012345789])|3(?:[124578]|3[12345678]|6[123456789]
+|9[345678])|4(?:[1246]|3[23456789]|5[124678]|7[023456789]|84)|6(?:[12
+46]|0[123456789]|3[12345678]|5[234567]|7[123456789])|7(?:[125789]|0[1
+2348]|3[1234]|4[12345678]|6[023456789])|8(?:[1256]|3[0123456789]|4[13
+45679]|7[02345678])|9(?:[145]|2[012345689]|3[123]|6[23456789]|7[01234
+56789]|8[123469]))|4(?:[015]|2(?:[135]|0[2345678]|2[1234]|4[1234]|6[1
+23]|9[123456789])|3(?:[1357]|2[124578]|4[12345678]|6[1234]|8[123456])
+|4(?:[13578]|2[23456]|4[13456]|6[1234567]|9[12345678])|6(?:[1246]|0[0
+12345679]|3[2356789]|5[1234689]|7[123]|9[12])|7(?:[1356]|2[12]|4[1235
+6]|7[1234569]|8[1235])|9(?:[1346]|0[1345679]|2[0123456789]|5[3456]|7[
+356789]))|5(?:[15]|0(?:[14]|2[012345678]|3[23]|5[2345678])|2(?:[12358
+9]|0[0123456789]|4[0123456789]|6[345678])|3(?:[1357]|2[2345679]|4[123
+]|6[12345]|8[3456789])|4(?:[1246]|3[34569]|5[123456]|7[12345678])|6(?
+:[1234]|0[0123456789]|9[12345678])|7(?:[13468]|2[2345678]|5[123456]|7
+[12345]|9[23567])|8(?:[13568]|2[02356789]|4[1234]|7[234567]|9[12345])
+|9(?:[1246]|3[0123456789]|5[12345]|7[1345]))|6(?:[15]|0(?:[1356]|2[01
+23456789]|4[123]|7[124567]|8[123457])|2(?:[123489]|0[0123456789]|5[23
+456789])|3(?:[12456]|3[012345678]|7[0123456789])|4(?:[1347]|2[1234567
+8]|5[0123489]|6[12345]|8[1234])|6(?:[13]|0[12345678]|2[1234568]|4[023
+456789]|5[123]|9[12345])|7(?:[12579]|0[12345]|3[0123456789]|4[1234]|6
+[1246]|8[12345])|8(?:[12356]|4[0123456789]|7[013458])|9(?:[135]|2[012
+3456789]|4[013456789]|6[123456789]))|7(?:[15]|2(?:[1234567]|0[0234678
+9]|9[12345678])|3(?:[1357]|2[0123456789]|4[12346789]|6[0123456789]|8[
+1234])|4(?:[145]|2[123]|3[0123456789]|6[234578])|6(?:[12345]|0[012345
+6789])|7(?:[1234]|5[24567]))|8(?:[15]|2(?:1|0[123456789]|2[0123456789
+]|3[1234]|9[234567])|3(?:[1468]|0[0123456789]|2[012345678]|3[1234]|5[
+123456]|7[0123456789]|9[123])|4(?:[1347]|2[23456789]|5[0123456789]|6[
+1246]|8[1234568])|6[01356789]|7(?:[1467]|2[0123456789]|3[1235678]|5[0
+123456789]|8[012345789]|9[123467])|8(?:[136]|2[12345678]|4[1234578]|5
+[012345689]|7[123456]))|9(?:[15]|0(?:[12479]|0[0123456789]|3[01234567
+89]|5[0123456789]|6[12]|8[0123456789])|2(?:[1358]|0[0123456789]|2[123
+456]|4[12345678]|6[2345678]|9[12345678])|3(?:[1357]|2[012345789]|4[12
+3456789]|6[123456]|8[2346789]|9[0123456789])|4(?:[134679]|0[012345678
+9]|2[12345678]|5[123456789]|8[12345789])|6(?:[123456789]|0[012345678]
+)|7(?:[136]|2[1234678]|4[0123456789]|5[1234]|7[123456789])|8(?:[147]|
+2[0123456789]|3[123]|5[123456789]|6[123]|8[123456789])|9(?:[1468]|2[1
+23456789]|3[1234]|5[12345679]|7[1235678]|9[123456789])))|4(?:0|1(?:0[
+123456789]|2[0123456789]|3[123456789]|4[01234689]|5[12345689]|6[12345
+6789]|7[123456789]|8[0123456789]|9[12345])|2(?:1|0[23456789]|2[1234]|
+3[0123456789]|4[0123456789]|5[12345678]|6[0123456789]|7[1234567]|8[12
+3456789]|9[2345678])|3(?:1|0[23578]|2[012346789]|3[0123456789]|4[0234
+6789]|5[12345678]|6[1234567]|7[12]|8[12345]|9[234])|4(?:1|0[123456789
+]|2[12356]|3[12345]|4[1234567]|5[1234568]|6[123456789]|7[12345789]|8[
+0123456789]|9[123456789])|5(?:1|0[12345689]|2[123456789]|3[12345679]|
+4[1234567]|5[0123456789]|6[1234])|6(?:1|0[23456789]|2[1234567]|3[0123
+456789]|4[12346]|51|6[12345678]|7[1234]|8[1234])|7(?:1|0[2345678]|2[1
+2345]|3[1234567]|4[0123456789]|5[12345678]|6[123456789]|7[0123456789]
+|9[123456])|8(?:1|0[23456]|2[123456789]|3[023456789]|4[123456789]|5[1
+23456789]|6[12345]|7[1234567]|8[12345]|9[23])|9(?:1|0[23]|2[012345678
+9]|3[12345689]|4[12345678]|5[0123456789]|6[12345678]|7[1234567]))|5(?
+:0(?:2[12345678]|3[1234567]|4[12345]|5[123456]|6[023456789]|7[1234]|8
+[23456])|1(?:1|0[123589]|2[136789]|3[01256789]|4[123456789]|5[1234567
+89]|6[12345678]|7[1234567]|8[1234567]|9[0123456789])|2(?:1|0[12345678
+9]|2[1234568]|3[12345678]|4[1245678]|5[012345789]|6[123456]|7[1234567
+8]|8[123456]|9[2345])|3(?:1|0[0123456789]|2[0123456789]|3[12345679]|4
+[14567]|5[12345678]|6[12345678]|7[123456789]|8[1234])|4(?:1|0[1234567
+9]|2[123456789]|3[123456789]|4[12345678]|5[123456789]|6[1245678]|7[12
+3456]|8[12345]|9[12345])|5(?:1|0[23456789]|2[012345789]|3[123456]|4[1
+23456]|5[123456]|6[12345]|7[1234]|8[23456]|9[234])|6(?:1|0[123456789]
+|2[123456]|3[123456]|4[12345678]|5[0123456789]|6[12345]|7[1234567]|8[
+123456]|9[123456])|7(?:1|0[234567]|2[123456]|3[1234]|4[123456]|5[1234
+5]|6[13456789]|7[1234567])|8(?:1|0[2345678]|2[0123456789]|3[123456789
+]|4[012345689]|5[012345789]|6[12345]|7[2345]|8[23])|9(?:1|0[123456789
+]|2[123456]|3[12345679]|4[12345678]|5[1234567]|6[123456]|7[135678]))|
+6(?:9|0(?:0[23478]|2[012346789]|3[1234569]|4[123456789]|5[0123456789]
+|6[12368]|7[1348]|8[1234567]|9[23456])|1(?:1|0[123456789]|2[02346789]
+|3[012345689]|4[24567]|5[01245789]|6[1234567]|7[12345]|8[12345678]|9[
+02568])|2(?:1|0[12345679]|2[012346789]|3[123456789]|4[12345679]|5[123
+45678]|6[123456789]|7[12456]|8[1234567]|9[12345678])|3(?:1|0[12345678
+]|2[123456789]|3[123456789]|4[0123456789]|5[12356789]|6[1234]|7[12345
+]|8[1234567]|9[12345678])|4(?:1|0[0123456789]|2[0123456789]|3[0123456
+89]|4[012345679]|5[12345678]|6[1245678]|7[123456789]|8[23456])|5(?:1|
+0[0123456789]|2[234567]|3[123456]|4[12345]|5[0123456789]|6[123456789]
+|7[123458]|8[0123456789]|9[12345679])|6(?:1|2[0123456789]|3[013456789
+]|4[12345678]|5[0123456789]|6[013456789]|7[02345678]|8[1234]|9[123456
+78])|7(?:1|0[1346789]|2[12345678]|3[1234567]|4[1234567]|5[12345678]|6
+[123456]|7[123456]|8[123456789])|8(?:1|0[234569]|2[14567]|3[12345678]
+|4[123489]|5[12345678]|6[1456789]|7[123456]|8[178]|9[3478]))|7(?:0(?:
+2[123456]|3[1234]|4[123456]|5[123456]|6[236]|7[123]|8[12345])|1(?:1|2
+[123456789]|3[012345689]|4[12345678]|5[012346789]|6[123456]|7[123456]
+|8[1234]|9[12345])|2(?:1|0[234]|2[0123456789]|3[1234567]|4[023456789]
+|5[0123456789]|6[0123456789]|7[1234567])|3(?:1|0[023456789]|2[1234567
+89]|3[1234567]|4[0345678]|5[12345678]|6[1234567]|7[13456]|8[123456789
+]|9[12345])|4(?:1|0[234]|2[023456789]|3[123456]|4[0123456789]|5[12345
+6789]|6[1234567]|7[12345678]|8[23456])|5(?:1|0[23456]|2[0245789]|3[12
+34]|4[123456]|5[12345678]|6[123456789]|7[0123456789]|8[1234567])|6(?:
+1|02|2[0123456789]|3[123456]|4[123456]|5[1234567]|6[0123456789]|7[123
+456]|8[12345])|7(?:1|0[23456789]|2[0123456789]|3[12345689]|4[12345678
+]|5[1345]|6[12345]|7[13457])|8(?:1|0[2345678]|2[123456]|3[123456789]|
+4[1234]|5[1234])|9(?:1|0[34567]|3[0123456789]|4[0123456789]|5[0123457
+89]|6[1234567]|7[1234567]))|8(?:9|0(?:2[0123456789]|3[12345689]|4[123
+56]|5[1234567]|6[1234567]|7[123456]|8[123456]|9[12345])|1(?:1|0[2456]
+|2[1234]|3[13456789]|4[123456]|5[12378]|6[15678]|7[016789]|9[123456])
+|2(?:1|0[2345678]|2[123456]|3[012346789]|4[1356789]|5[01234789]|6[123
+56789]|7[12346]|8[12345]|9[123456])|3(?:1|0[2346]|2[0123456789]|3[012
+345678]|4[0123456789]|6[123456789]|7[023456789]|8[0123456789]|9[2345]
+)|4(?:1|0[234567]|2[123467]|3[12345]|4[123456]|5[02346789]|6[01234567
+89])|5(?:1|0[12345679]|3[12345678]|4[123456789]|5[012345678]|6[12345]
+|7[1234]|8[123456]|9[123])|6(?:1|2[123489]|3[013456789]|4[0129]|5[012
+467]|6[12345679]|7[01789]|8[1234567])|7(?:1|0[23456789]|2[12345678]|3
+[12345]|4[12345]|5[12346]|6[12456]|7[1234]|8[12345])|8(?:1|0[12356789
+]|2[12345]|4[1567]|5[1678]|6[012789]))|9(?:0(?:6|7[012345678]|8[01234
+56789]|9[0123479])|1(?:1|0[1234567]|2[0236789]|3[12345]|4[123456789]|
+5[12345678]|6[1234567]|7[0123456789]|8[0123456789]|9[0123456789])|2(?
+:1|0[123456789]|2[01235789]|3[1234568]|4[123456]|5[1234567]|6[0123456
+789]|7[0123456789]|8[0123456789]|9[2345])|3(?:1|0[23567]|2[13456]|3[1
+23456789]|4[0123456789]|5[0123456789]|6[0345679]|7[12345678]|8[123456
+]|9[12345678])|4(?:1|0[123456789]|2[012346789]|3[1345689]|4[12345678]
+|5[1234]|6[123456789]|7[1234]|8[0124]|9[1235789])|5(?:1|0[2345]|2[123
+456789]|3[123456]|4[23456789]|5[123456]|6[0123456789]|7[123456])|6(?:
+1|0[2345678]|2[1245678]|3[123456789]|4[12345678]|5[123456789]|6[12345
+6]|7[1234567]|8[123])|7(?:1|0[148]|2[0123456789]|3[2345678]|4[1245678
+9]|6[123456]|7[123456789])|8(?:1|0[2345]|2[023456789]|3[1234567]|4[12
+345678]|5[1234567]|6[15789]|7[123456])|9(?:1|0[1345678]|2[0123456789]
+|3[1235678]|4[12345678]|5[123456]|6[123456]|7[12345678]))))/;

# Generate all region codes from that.
# So that we have some data to work with.
my @region_code;
foreach ("02000".."99999") {
    push (@region_code, $1) if /^$RC/o;
}

# create a region code hash for krambambuli's algorithm
my %prefixes;
@prefixes{@region_code}= ();

# make the testdata a bit longer
$_.= "xxxxxx" foreach @region_code;

cmpthese (1000, {
  krambambuli => sub { krambambuli($_, \%prefixes) foreach @region_cod
+e; },
  Skeeve      => sub { skeeve($_, \$RC) foreach @region_code; },
});


sub krambambuli {
    my ($phone, $prefixes)= @_;
    my ($pref5, $pref4, $pref3, $pref2) = map { substr( $phone, 0, $_ 
+) } (5, 4, 3, 2);

    my $prefix_length = exists $prefixes->{$pref5} ? 5
                      : exists $prefixes->{$pref4} ? 4
                      : exists $prefixes->{$pref3} ? 3
                      : exists $prefixes->{$pref2} ? 2
                      :                              0
                      ;

    substr($phone, $prefix_length,0)= ' '; # just a slight optimisatio
+n (I guess)
    
    return $phone;
}

sub skeeve {
    my ($phone, $reref)= @_;
    $phone=~ s/^$$reref/$1 /;
    return $phone;
}
[download]

This is the result:

              Rate      Skeeve krambambuli
Skeeve      10.7/s          --        -30%
krambambuli 15.4/s         43%          --
[download]

~~So regular expressions seem to be very efficient. The code is 30% faster.~~ ;-) It isn't. krambambuli is right.

s$$([},&%#}/&/]+}%&{})*;#$&&s&&$^X.($'^"%]=\&(|?*{%
+.+=%;.#_}\&"^"-+%*).}%:##%}={~=~:.")&e&&s""`$''`"e

Comment on Re^4: (german) region code detection - request for thoughts Select or Download Code

Replies are listed 'Best First'.
Re^5: (german) region code detection - request for thoughts by Krambambuli (Curate) on Aug 20, 2008 at 17:16 UTC
This is the result: `Rate Skeeve krambambuli Skeeve 10.7/s -- -30% krambambuli 15.4/s 43% --` [download] Read again... ;) The results are saying the opposite: your code executes approx. 10 times in a second, mine does 15 times. Krambambuli ---	[reply] [d/l]