Here is some reduced grammer and code that works - parses the metafields (prefix #) correctly, but bums out at the "normal" fields (prefix F)..
Any ideas?
#!/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 er
+ror
$::RD_WARN = 1; # Enable warnings. This will warn on unused rules &c
+.
$::RD_HINT = 1; # Give out hints to help fix problems.
#$::AUTOSTUB = 1;
my $grammar = <<'_EOGRAMMAR_';
#{ our $errortext = ''; our $errorprefix = '';}
RECORDSTART : /^RECORD\r*\n/
{
print "\n[*] RECORDSTART -> " . $item[1];
$item[1];
}
RECORDEND : /^\./
{
print '\n[*] RECORDEND -> ' . $item[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]\n";
$1;
}
field : /^F/ fieldName fieldValue
{
print "[*] Got field named \'" . $item{ fieldName } . '\' with
+ value \'' . $item{ fieldValue } . "\'\n";
print Data::Dumper->Dump([$text], ["fieldStuff"]);
}
metaField : /^\#/ metaName metaFieldValue
{
print "[*] Got metafield named \'" . $item{ metaName } . '\' w
+ith value \'' . $item{ metaFieldValue } . "\'\n";
}
recordBody : field(s)
{
print "\n[*] field(s)\n";
#print main::Dumper \@item;
print Data::Dumper->Dump([$text], ["field(s)"]);
}
|
metaField(s)
{
print "\n[*] metaField(s)\n";
#print main::Dumper \@item;
print Data::Dumper->Dump([$text], ["metaField(s)"]);
}
|
<error>
#<error: I am confused in recordBody at $thisoffset!>
#startOfRecord: RECORDSTART recordBody(s /$/) RECORDEND
startOfRecord: RECORDSTART recordBody RECORDEND { $return = $item[1]
+}
|
#<error>
<error: I could not even parse a line line starting at $thiso
+ffset!>
_EOGRAMMAR_
#$skeletonPattern = "#input_type[ \t]*";
#my $metaFieldPattern = qr/[ \t]*#([^ \t]+)[ \t]+(.*)/o; # "#input_typ
+e 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 $testData = <<'_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 $testData1 = <<'_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_
print $testData, "\n\n";
#<STDIN>;
my $parser = Parse::RecDescent->new($grammar);
$parser->startOfRecord($testData) or die "Bad input!\n";
Output is:
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
.
* RECORDSTART -> RECORD
* Got metafield named 'input_id' with value '91210758171x001_0013'
* Got metafield named 'input_type' with value 'PTC'
* Got metafield named 'output_type' with value 'MTC'
* Got metafield named 'source_id' with value '01'
* Got metafield named 'filename' with value 'TTFILE01-0001-20080101000000'
* Got metafield named 'jingalama' with value 'valuewith#inIt andaSpace'
* metaField(s)
$metaField(s) = '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
.
';
-
Are you posting in the right place? Check out Where do I post X? to know for sure.
-
Posts may use any of the Perl Monks Approved HTML tags. Currently these include the following:
<code> <a> <b> <big>
<blockquote> <br /> <dd>
<dl> <dt> <em> <font>
<h1> <h2> <h3> <h4>
<h5> <h6> <hr /> <i>
<li> <nbsp> <ol> <p>
<small> <strike> <strong>
<sub> <sup> <table>
<td> <th> <tr> <tt>
<u> <ul>
-
Snippets of code should be wrapped in
<code> tags not
<pre> tags. In fact, <pre>
tags should generally be avoided. If they must
be used, extreme care should be
taken to ensure that their contents do not
have long lines (<70 chars), in order to prevent
horizontal scrolling (and possible janitor
intervention).
-
Want more info? How to link
or How to display code and escape characters
are good places to start.
|