1

对下面的 Perl 文件解析代码 [最后回复 PM @ http://www.perlmonks.org/index.pl?node_id=754947]感到很痛苦：

#!/usr/bin/perl -w

use strict;
use warnings;
#use diagnostics;

use Parse::RecDescent;
use Data::Dumper;

# Enable warnings within the Parse::RecDescent module.

$::RD_ERRORS = 1; # Make sure the parser dies when it encounters an error
$::RD_WARN   = 1; # Enable warnings. This will warn on unused rules &c.
$::RD_HINT   = 1; # Give out hints to help fix problems.
#$::RD_TRACE  = 1; # Trace of parser

#$::AUTOSTUB = 1;

my $grammar = <<'_EOGRAMMAR_';

{
    use strict;
    use warnings;
}
#{ our $errortext = ''; our $errorprefix = '';}
RECORDSTART : /^(RECORD)[\r\n]+/
{
    #print "\n[*] RECORDSTART -> " . $item[1];
    $1;
    #$item[1];
} 

RECORDEND : /^(\.)[\r\n]*/
#/\./
{
    #print "\n[*] RECORDEND -> " . $item[1] . "\n";
    $1;
    #$item[1];
} 

fieldName : /[^ \t\n]+/
{
    #print "\n[*] fieldName -> $item[1]\n";
    $item[1];
}

metaName : /[^ \t\n]+\n?/
{
    $item[1];
}

metaFieldValue: /([^\n]*)\n/
{
    $1;
}

fieldValue : /([^\n]*)\n/
{
    #print "[*] fieldValue -> $item[1] ($1)\n";
    $1;
}

field : /^F/ fieldName fieldValue
{
    #print "[*] Got field named \'" . $item{ fieldName } . '\' with value \'' . $item{ fieldValue } . "\'\n";
    #print "[*] Got metafield named \'" . $item[2] . '\' with value \'' . $item[3] . "\'\n";
    #print Data::Dumper->Dump([$text], ["fieldStuff"]);
    $return = { fieldName => $item[2], fieldValue => $item[3]};
}

metaField : /^\#/ metaName metaFieldValue
{
    #print "[*] Got metafield named \'" . $item{ metaName } . '\' with value \'' . $item{ metaFieldValue } . "\'\n";
    #print "[*] Got metafield named \'" . $item[2] . '\' with value \'' . $item[3] . "\'\n";
    $return = { metaName => $item[2], metaFieldValue => $item[3]};
}

recordBody : field(s)
{
    print "\n[*] field(s)\n";
    #print main::Dumper \@item;
    #print Data::Dumper->Dump([@item], ["field(s)"]);
    $return = 'field(s)';
    #if((length($text) > 3) && (0 == @item))
    if(length($text) > 2)
    {
        $return = undef;
    }
}
|
metaField(s)
{
    print "\n[*] metaField(s)\n";
    #print main::Dumper \@item;
    #print Data::Dumper->Dump([@item], ["metaField(s)"]);
    $return = 'metaField(s)';
    #if((length($text) > 3) && (0 == @item))
    if(length($text) > 2)
    {
        $return = undef;
    }
}
|
<error>
#<error: I am confused in recordBody at $thisoffset!>

#startOfRecord: RECORDSTART recordBody(s /$/) RECORDEND
startOfRecord: RECORDSTART recordBody RECORDEND
#startOfRecord: RECORDSTART ( metaField(s) field(s) ) RECORDEND
#startOfRecord: RECORDSTART ( field(s) metaField(s) ) RECORDEND
{
    #print main::Dumper \@item;
    $return = 'something';
    #$return = $item[1];
    1;
}
|
#<error>
<error: I could not even parse a line line starting at $thisoffset!>
_EOGRAMMAR_

#$skeletonPattern = "#input_type[ \t]*";
#my $metaFieldPattern = qr/[ \t]*#([^ \t]+)[ \t]+(.*)/o; # "#input_type SCDR+", "#filename processed_01_20080616001403.cdr", etc
#my $normalFieldPattern = qr/([ \t]*)([0-9]*)F[ \t]+([^ \t]+)[ \t]+([^ \t\r\n]+)(.*)/; # "1F S_Diagnostic1 62" OR " F S_Diagnostic1 62" OR " F S_Diagnostic1 62" are synonymous, etc

my $testData0 = <<'_EOGTESTA_';
RECORD
F ptc_record_length 00B6
F ptc_charging_start_time 20090604093721
F ptc_charging_end_time 20080604093721
F ptc_called_msrn_ton FF
F ptc_term_mcz_duration 060000
.
_EOGTESTA_

my $testData1 = <<'_EOGTESTA_';
RECORD
#input_id 91210758171x001_0013
#input_type PTC
#output_type MTC
#source_id 01
#filename TTFILE01-0001-20080101000000
#jingalama valuewith#inIt andaSpace
.
_EOGTESTA_

my $testData2 = <<'_EOGTESTA_';
RECORD
F ptc_record_length 00B6
F ptc_charging_start_time 20090604093721
F ptc_charging_end_time 20080604093721
F ptc_called_msrn_ton FF
F ptc_term_mcz_duration 060000
#input_id 91210758171x001_0013
#input_type PTC
#output_type MTC
#source_id 01
#filename TTFILE01-0001-20080101000000
#jingalama valuewith#inIt andaSpace
.
_EOGTESTA_

my $testData3 = <<'_EOGTESTA_';
RECORD
#input_id 91210758171x001_0013
#input_type PTC
#output_type MTC
#source_id 01
#filename TTFILE01-0001-20080101000000
#jingalama valuewith#inIt andaSpace
F ptc_record_length 00B6
F ptc_charging_start_time 20090604093721
F ptc_charging_end_time 20080604093721
F ptc_called_msrn_ton FF
F ptc_term_mcz_duration 060000
.
_EOGTESTA_

my $testData4 = <<'_EOGTESTA_';
RECORD
#input_id 91210758171x001_0013
#output_id 
#input_type PTC
#output_type PTC
#addkey 
#source_id 01
#filename TTFILE01-0001-20080101000000
F ptc_record_length 00B6
F ptc_record_type
F ptc_charging_start_time 20090604093721
F ptc_charging_end_time 20080604093721
F ptc_called_msrn_ton FF
F ptc_term_mcz_duration 060000
F ptc_term_mcz_change_direction 
.
_EOGTESTA_

my $parser = Parse::RecDescent->new($grammar) or die "Bad grammar!\n";;

print $testData0, "\n\n";
$parser->startOfRecord($testData0) ? print "Parsing done sucessfully!\n" : print "Bad input!\n";

print $testData1, "\n\n";
$parser->startOfRecord($testData1) ? print "Parsing done sucessfully!\n" : print "Bad input!\n";

print $testData2, "\n\n";
$parser->startOfRecord($testData2) ? print "Parsing done sucessfully!\n" : print "Bad input!\n";

print $testData3, "\n\n";
$parser->startOfRecord($testData3) ? print "Parsing done sucessfully!\n" : print "Bad input!\n";

print $testData4, "\n\n";
$parser->startOfRecord($testData4) ? print "Parsing done sucessfully!\n" : print "Bad input!\n";

#$parser->startOfRecord($testData) ? print "Parsing done sucessfully!" : die "Bad input!\n";

输出：

记录
F ptc_record_length 00B6
F ptc_charge_start_time 20090604093721
F ptc_charge_end_time 20080604093721
F ptc_called_msrn_ton FF
F ptc_term_mcz_duration 060000
.

[*] 字段
解析成功！
记录
#input_id 91210758171x001_0013
#input_type PTC
#output_type MTC
#source_id 01
#文件名 TTFILE01-0001-20080101000000
#jingalama valuewith#inIt andaSpace
.

[*] 元字段
解析成功！
记录
F ptc_record_length 00B6
F ptc_charge_start_time 20090604093721
F ptc_charge_end_time 20080604093721
F ptc_called_msrn_ton FF
F ptc_term_mcz_duration 060000
#input_id 91210758171x001_0013
#input_type PTC
#output_type MTC
#source_id 01
#文件名 TTFILE01-0001-20080101000000
#jingalama valuewith#inIt andaSpace
.

[*] 字段
输入错误！
记录
#input_id 91210758171x001_0013
#input_type PTC
#output_type MTC
#source_id 01
#文件名 TTFILE01-0001-20080101000000
#jingalama valuewith#inIt andaSpace
F ptc_record_length 00B6
F ptc_charge_start_time 20090604093721
F ptc_charge_end_time 20080604093721
F ptc_called_msrn_ton FF
F ptc_term_mcz_duration 060000
.

[*] 元字段
输入错误！
记录
#input_id 91210758171x001_0013
#output_id
#input_type PTC
#output_type PTC
#addkey
#source_id 01
#文件名 TTFILE01-0001-20080101000000
F ptc_record_length 00B6
F ptc_record_type
F ptc_charge_start_time 20090604093721
F ptc_charge_end_time 20080604093721
F ptc_called_msrn_ton FF
F ptc_term_mcz_duration 060000
F ptc_term_mcz_change_direction
.

[*] 元字段
输入错误！

这是标准错误：

print() 在 C:/laPerl/site/lib/Parse/RecDescent.pm 第 2905 行关闭文件句柄错误。
变量“$errortext”在 C:/laPerl/site/lib/Parse/RecDescent.pm 第 2906 行不可用。
变量“$errorprefix”在 C:/laPerl/site/lib/Parse/RecDescent.pm 第 2906 行不可用。
在 C:/laPerl/site/lib/Parse/RecDescent.pm 第 2850 行的 formline 中使用未初始化的值 $errorprefix。
在 C:/laPerl/site/lib/Parse/RecDescent.pm 第 2850 行的 formline 中使用未初始化的值 $errortext。
在 C:/laPerl/site/lib/Parse/RecDescent.pm 第 2852 行的 formline 中使用未初始化的值 $errortext。
在 C:/laPerl/site/lib/Parse/RecDescent.pm 第 2906 行关闭文件句柄错误上的 write()。
...

有什么建议么？我真的很困惑吗？

谁能弄清楚出了什么问题（ActivePerl 5.10 和 WinXP SP2 的选择除外）？

4

1 回答 1

3

我认为在 XP 上选择 ActivePerl 很好；唯一的问题是语法。

您的 recordBody 语法规则说内部只能有多个字段或多个元字段，而两者之间不能有任何内容。

如果您需要任何字段/元字段的组合，我建议您创建一些人工规则 anyField

anyField : field | metaField

recordBody : anyField(s)
于 2009-04-07T08:25:53.930 回答