Regex 为什么我的Perl正则表达式这么慢？
我有以下正则表达式：Regex 为什么我的Perl正则表达式这么慢？,regex,perl,Regex,Perl,我有以下正则表达式： my $scores_compiled_regex = qr{^0 \s+ (\p{Alpha}+\d*) \s+ (\d+ \s*
my $scores_compiled_regex = qr{^0
\s+
(\p{Alpha}+\d*)
\s+
(\d+
\s*
\p{Alpha}*)
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s{2,}
(\d+)?
\s+
\d+ #$
}xos
0 INST, NAME A A- B+ B B- C+ C C- D+ D D- F CR P PR I I* W WP WF AU NR FN FS
0 PALMER, JAN A A- B+ B B- C+ C C- D+ D D- F CR P PR I I* W WP WF AU NR FN FS TOTAL
0 ECON 103 98 35 114 1 14 75 9 35 1 10 1
谢谢，如果您必须接受的格式与您的正则表达式当前接受的格式一样松散，那么您会遇到一个大问题：如果缺少一个或多个数字字段，并且如果一行中有多个空格出现，那么哪个分数对应于哪个列是不明确的 Perl的回溯将通过选择“最左边、最长”的匹配来解决歧义，但是（a）这不一定是您想要的，（b）它需要尝试的可能性的数量与您在行中丢失的数字字段的数量成指数关系，因此速度较慢 为了举例说明，让我们使用一个更简单的正则表达式：
/\A(\d+)?\s{2,}
(\d+)?\s{2,}
(\d+)?\s{2,}
(\d+)?\z/xs;
123 456 789
\s{2，}substr（）请让我知道，如果你需要通过该计划的任何部分走。我没有把它贴在这里，因为它有点长（有评论总比没有好！）。请告诉我您是否希望我这样做。如果列可以为空，则可能是（a）您的数据不明确，并且您遇到了比慢速正则表达式更大的问题，或者（b）您的数据采用固定宽度格式，如下所示：
NAME A A-
foo 123 456
bar 789
fubb 111
如果您有固定宽度的数据，则适当的解析工具是（或），而不是正则表达式。不要为此使用正则表达式。它看起来像一个固定的列格式，所以速度会快得多 下面是一个示例程序，它显示了问题的实质。您仍然需要弄清楚如何集成它，以便知道新的个人记录何时开始等等。我这样做是为了使解包值的格式主要来自标题，这样您就不必花费太多时间计算列（同时也便于它对列位置的更改做出响应）： 对于“Palmer，Jan”的新样品：
首先将队列分成固定宽度的块、空格和所有。然后把这些碎片清理干净。否则，您试图同时做两件容易出错的事情。是的，但它工作（慢）-：），我看不到其他方法。您尝试过拆分吗？或者将解析器生成器用作Parse:：RecDescent？拆分没有帮助，即使列为空，我也需要保留它们。我认为您应该使用
（\d*）（\d+）substr（）unpack（）use strict;
use warnings;
# Column details and sample line, from the post
my $header = q{0 AOZSVIN, TAMSSZ B A A- B+ B B- C+ C C- D+ D D- F CR P PR I I* W WP WF AU NR FN FS};
my $sample = q{0 AAS 150 23 25 16 35 45 14 8 10 2 1 1 4 4 };
# -+--------+-----+-----+---+---+---+---+---+---+---+---+---+---+---+---+---+---+---+---+---+---+---+---+---+---+---+---..
# chars 1212345678912345612345612341234123412341234123412341234123412341234123412341234123412341234123412341234123412341234...
# num. chars: 2 9 6 6 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 *
my $unpack = q{A2A9 A6 A6 A4 A4 A4 A4 A4 A4 A4 A4 A4 A4 A4 A4 A4 A4 A4 A4 A4 A4 A4 A4 A4 A4 A4 A*};
$unpack =~ s/\s//g;
# Get column names from the "$header" variable above
my @column_names = unpack($unpack, $header);
s/\s+$// for @column_names; # get rid of trailing spaces
s/^\s+// for @column_names; # get rid of leading spaces
# Some sample data in same format, to try the script out
my @samples = (
q{0 AAS 150 23 25 16 35 45 14 8 10 2 1 1 4 4 },
q{0 AAS 353 2 3 5 2 6 1 2 },
q{0 T304 480M 3 10 8 8 2 3 2 1 1 1 },
q{0 BIOS 206 3 14 5 11 9 8 4 8 3 1 1 6 7 },
);
my @big_sample = (@samples) ;#x 200_000;
my @unpacked_data_as_arrayrefs;
m y @unpacked_data_as_hashrefs;
my $begin = time;
for my $line ( @big_sample ) {
my @data = unpack($unpack,$line);
s/\s+$// for @data; # get rid of trailing spaces
s/^\s+// for @data; # get rid of leading spaces
push @unpacked_data_as_arrayrefs, [@data]; # stop here if this is all you need
## below converts the data in a hash, based on the column names given
#my %as_hash;
#for ( 0..$#column_names ) {
# $as_hash{ $column_names[$_] } = $data[$_];
#}
#push @unpacked_data_as_hashrefs, { %as_hash };
}
my $tot = time - $begin;
print "Done in $tot seconds\n";
# verify all data is as we expected
# uncomment the ones that test hashref, if the above hashref-building code is also uncommented.
{
use Test::More;
# first sample
is($unpacked_data_as_arrayrefs[0]->[2],'AAS'); # AAS in the third column
is($unpacked_data_as_arrayrefs[0]->[7],'35'); # 35 in the 8th column
# fourth sample
is($unpacked_data_as_arrayrefs[3]->[2],'BIOS');
is($unpacked_data_as_arrayrefs[3]->[15],'6');
# sixth
is($unpacked_data_as_arrayrefs[5]->[7],'114');
is($unpacked_data_as_arrayrefs[5]->[10],'75');
done_testing();
}
NAME A A-
foo 123 456
bar 789
fubb 111
chomp( my $header = <DATA> );
my( $num, $name, $rest ) = unpack "a2 a20 a*", $header;
my @grades = split /(?=\s+)/, $rest;
my @grade_keys = map { /(\S+)/} @grades;
my $format = 'a13 a4 a5 ' . join ' ', map { 'a' . length } @grades;
while( <DATA> ) {
my( $key, $label, $number, @grades ) = unpack $format, $_;
$$_ =~ s/\s//g foreach ( \$key, \$label, \$number );
@{ $hash{$key}{$label}{$number} }{@grade_keys} =
map { s/\s//g; $_ } @grades;
}
use Data::Dumper;
print Dumper( \%hash );
$VAR1 = {
'0' => {
'BIOS' => {
'206' => {
'F' => '6',
'AU' => '',
'FS' => '',
'B-' => '9',
'D+' => '3',
'CR' => '',
'B+' => '5',
'WP' => '7',
'C+' => '8',
'NR' => '',
'C' => '4',
'PR' => '',
'A' => '3',
'W' => '',
'I*' => '',
'A-' => '14',
'P' => '',
'WF' => '',
'B' => '11',
'FN' => '',
'D' => '1',
'D-' => '1',
'I' => '',
'C-' => '8'
}
},
'AAS' => {
'353' => {
'F' => '2',
'AU' => '',
'FS' => '',
'B-' => '6',
'D+' => '',
'CR' => '',
'B+' => '5',
'WP' => '',
'C+' => '',
'NR' => '',
'C' => '1',
'PR' => '',
'A' => '2',
'W' => '',
'I*' => '',
'A-' => '3',
'P' => '',
'WF' => '',
'B' => '2',
'FN' => '',
'D' => '',
'D-' => '',
'I' => '',
'C-' => ''
},
'150' => {
'F' => '4',
'AU' => '',
'FS' => '',
'B-' => '45',
'D+' => '2',
'CR' => '',
'B+' => '16',
'WP' => '4',
'C+' => '14',
'NR' => '',
'C' => '8',
'PR' => '',
'A' => '23',
'W' => '',
'I*' => '',
'A-' => '25',
'P' => '',
'WF' => '',
'B' => '35',
'FN' => '',
'D' => '1',
'D-' => '1',
'I' => '',
'C-' => '10'
}
},
'T304' => {
'480M' => {
'F' => '',
'AU' => '',
'FS' => '1',
'B-' => '2',
'D+' => '',
'CR' => '',
'B+' => '8',
'WP' => '',
'C+' => '3',
'NR' => '',
'C' => '2',
'PR' => '',
'A' => '3',
'W' => '',
'I*' => '',
'A-' => '10',
'P' => '',
'WF' => '1',
'B' => '8',
'FN' => '',
'D' => '',
'D-' => '',
'I' => '',
'C-' => '1'
}
}
}
};
$VAR1 = {
'0' => {
'ECON' => {
'103' => {
'F' => '35',
'AU' => '1',
'FS' => '',
'B-' => '1',
'D+' => '',
'CR' => '',
'B+' => '35',
'WP' => '10',
'C+' => '14',
'NR' => '',
'C' => '75',
'PR' => '',
'A' => '98',
'W' => '',
'I*' => '',
'A-' => '',
'P' => '',
'WF' => '',
'B' => '114',
'FN' => '',
'TOTAL' => '',
'D' => '9',
'D-' => '',
'I' => '1',
'C-' => ''
}
}
}
};