bufr.pm:bufrdump.pl_source

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
bufr.pm:bufrdump.pl_source [2012-06-04 09:24:05]
pals 		bufr.pm:bufrdump.pl_source [2022-05-31 09:29:31] (current)
Line 1: Line 1:
-<code perl>+<code perl bufrdump.pl>
 #!/usr/bin/perl -w #!/usr/bin/perl -w
  
Line 38: Line 38:
            'param=s',     # Decode/print specified parameters only            'param=s',     # Decode/print specified parameters only
            'csv',         # Use CSV format for printing            'csv',         # Use CSV format for printing
-           'delimiter=s', # Choose the delimiter for the CVS format +           'delimiter=s', # Choose the delimiter for the CSV format 
-           'sort',        # Sort on stationid (wmonr/nationalnr/call_sign/buoy_id/aircraft)+           'sort',        # Sort on stationid (wmonr/nationalnr/call_sign/buoy_id/aircraft/icao_id/wigosid)
            'sort_on=s',   # Sort on specified parameter            'sort_on=s',   # Sort on specified parameter
            'station=s',   # Filter on list of stations            'station=s',   # Filter on list of stations
Line 81: Line 81:
 my $lon2 = $option{lon2} ? "--lon2 $option{lon2}" : ''; my $lon2 = $option{lon2} ? "--lon2 $option{lon2}" : '';
 my $lat2 = $option{lat2} ? "--lat2 $option{lat2}" : ''; my $lat2 = $option{lat2} ? "--lat2 $option{lat2}" : '';
-my $del = $option{delimiter} ? "$option{delimiter}" : ',';+my $del = $option{delimiter} ? "$option{delimiter}" : ';';
 my $delimiter = $option{delimiter} ? "--delimiter $del" : ''; my $delimiter = $option{delimiter} ? "--delimiter $del" : '';
  
Line 137: Line 137:
             # Build up the message to be (possibly) printed             # Build up the message to be (possibly) printed
             my ($param, $value) = ($line =~ /^(.+)=\s*(.*?)\s*$/);             my ($param, $value) = ($line =~ /^(.+)=\s*(.*?)\s*$/);
 +            # Know only of one case where next check is necessary: if
 +            # a CCITT IA5 value contains new line (\n)
 +            next LINE if !defined $value;
             if ($transform_file && $transform_ref->{$param}) {             if ($transform_file && $transform_ref->{$param}) {
                 # Replace value with transformed value                 # Replace value with transformed value
Line 185: Line 188:
                 if ($txt) {                 if ($txt) {
                     if ($sort) {                     if ($sort) {
-                        # Sort wmonr before nationalnr before call +                        # Sort wmonr before nationalnr before call sign before 
-                        # sign before buoy_id before aircraft+                        # buoy_id before aircraft before icaoid before wigosid
                         if ($msg{wmonr}) {                         if ($msg{wmonr}) {
                             $stnid = '00_' . $msg{wmonr};                             $stnid = '00_' . $msg{wmonr};
Line 197: Line 200:
                         } elsif ($msg{aircraft}) {                         } elsif ($msg{aircraft}) {
                             $stnid = '40_' . $msg{aircraft};                             $stnid = '40_' . $msg{aircraft};
 +                        } elsif ($msg{icao_id}) {
 +                            $stnid = '50_' . $msg{icao_id};
 +                        } elsif ($msg{wigosid}) {
 +                            $stnid = '60_' . $msg{wigosid};
                         } else {                         } else {
                             # Skip observation if no station identification found                             # Skip observation if no station identification found
Line 205: Line 212:
                             my $key = $stnid . '|' . $val;                             my $key = $stnid . '|' . $val;
                             $data_of{$key} = exists $data_of{$key}                             $data_of{$key} = exists $data_of{$key}
-                                ? $data_of{$key} . "$txt\n" : "$txt\n";+                            ? $data_of{$key} . "$txt\n" : "$txt\n";
                         } else {                         } else {
                             $data_of{$stnid} = exists $data_of{$stnid}                             $data_of{$stnid} = exists $data_of{$stnid}
-                                ? $data_of{$stnid} . "$txt\n" : "$txt\n";+                            ? $data_of{$stnid} . "$txt\n" : "$txt\n";
                         }                         }
                     } elsif ($sort_on) {                     } elsif ($sort_on) {
                         my $val = exists $msg{$sort_on} ? $msg{$sort_on} : '';                         my $val = exists $msg{$sort_on} ? $msg{$sort_on} : '';
                         $data_of{$val} = exists $data_of{$val}                         $data_of{$val} = exists $data_of{$val}
-                            ? $data_of{$val} . "$txt\n" : "$txt\n";+                        ? $data_of{$val} . "$txt\n" : "$txt\n";
                     } else {                     } else {
                         # No sorting. We can print the line immediately                         # No sorting. We can print the line immediately
Line 281: Line 288:
          '>=',          '>=',
          '!=',          '!=',
-     );+         '=~', 
 +         '!~', 
 +        );
     my @criteria;     my @criteria;
     my @num_alt; # Number of alternative criteria following this,     my @num_alt; # Number of alternative criteria following this,
Line 309: Line 318:
     # Check that the criteria are properly formatted     # Check that the criteria are properly formatted
     foreach my $criterium (@criteria) {     foreach my $criterium (@criteria) {
-        # Naked parameter is ok +        # Naked parameter possibly preceded by '!' is ok 
-        next if $criterium =~ /^\w+$/;+        next if $criterium =~ /^!?\w+$/;
  
         my $op = (split / +/, $criterium)[1];         my $op = (split / +/, $criterium)[1];
Line 337: Line 346:
         my @p = split /,/, $params;         my @p = split /,/, $params;
         foreach my $name (@p) {         foreach my $name (@p) {
 +            $name =~ s/^\s+//;
 +            $name =~ s/\s+$//;
             if ($name =~ /^!/) {             if ($name =~ /^!/) {
                 $name = substr $name, 1;                 $name = substr $name, 1;
Line 377: Line 388:
         $line =~ s/^\s+//;         $line =~ s/^\s+//;
         $line =~ s/\s+$//;         $line =~ s/\s+$//;
-         next if !$line || $line =~ /^#/;+        next if !$line || $line =~ /^#/;
         my ($param, $transform) = split /=/, $line, 2;         my ($param, $transform) = split /=/, $line, 2;
         die "Invalid transformation in $transform_file:\n$line\n"         die "Invalid transformation in $transform_file:\n$line\n"
Line 399: Line 410:
     return unless $criteria_ref;     return unless $criteria_ref;
  
-    my @ascii_params = qw(aircraft call_sign icao_id name obstime type);+    my @ascii_params = qw(aircraft call_sign icao_id name obstime type wigosid);
  
     # Note that the loop counter $i might be changed in the loop     # Note that the loop counter $i might be changed in the loop
Line 406: Line 417:
         my $criterium = $criteria_ref->[$i];         my $criterium = $criteria_ref->[$i];
         my ($f_param, $f_operator, $f_value) = split / +/, $criterium, 3;         my ($f_param, $f_operator, $f_value) = split / +/, $criterium, 3;
-        # If parameter not present, criterium is obviously not fullfilled + 
-        if (not exists $msg_ref->{$f_param}) { +        # First check for !$par, meaning $par should not be in the observation 
-            if ($num_alt) { +        if (substr($f_param,0,1) eq '!') { 
-                # Criterium not fullfilled, but more alternatives to check +            $f_param = substr($f_param,1); 
-                next; +            # If parameter is present, criterium is not fullfilled 
-            } else {+            if (exists $msg_ref->{$f_param}) { 
 +                next if $num_alt; # More alternatives to check 
                 # Criterium not fulfilled and no more alternatives to                 # Criterium not fulfilled and no more alternatives to
                 # check. This observation should be filtered away                 # check. This observation should be filtered away
                 return 1;                 return 1;
 +            } else {
 +                # Criterium fulfilled. No need to check alternative criteria
 +                $i += $num_alt if $num_alt;
 +                next;
             }             }
 +        }
 +
 +        # If parameter not present, criterium is obviously not fullfilled
 +        if (not exists $msg_ref->{$f_param}) {
 +            next if $num_alt;
 +            return 1;
         }         }
  
Line 432: Line 455:
         my $op;         my $op;
         if ($f_operator eq '<'         if ($f_operator eq '<'
-            | $f_operator eq '<=' +            || $f_operator eq '<=' 
-            | $f_operator eq '>' +            || $f_operator eq '>' 
-            | $f_operator eq '>=') {+            || $f_operator eq '>=' 
 +            || $f_operator eq '=~' 
 +            || $f_operator eq '!~') {
             $op = $f_operator;             $op = $f_operator;
         } elsif ($f_operator eq '='         } elsif ($f_operator eq '='
-                 | $f_operator eq '!=') {+                 || $f_operator eq '!=') {
             if (grep {$_ eq $f_param} @ascii_params) {             if (grep {$_ eq $f_param} @ascii_params) {
                 $msg_value =~ s/\s*$//;                 $msg_value =~ s/\s*$//;
Line 448: Line 473:
         }         }
  
-        if ($f_param eq 'wmonr' || $f_param eq 'buoy_id') { + # Some parameters might need special massaging 
-            # Make non octal by removing leading 0 +        if ($f_operator !~ /~/) { 
-            $msg_value =~ s/^0+//; +            if ($f_param eq 'wmonr' || $f_param eq 'buoy_id') { 
-            $f_value =~ s/^0+//; +                # Make non octal by removing leading 0 
-        } elsif ($f_param eq 'nationalnr') { +                $msg_value =~ s/^0+//; 
-            # Convert to a pure numerical value (float). For 001101 +                $f_value =~ s/^0+// if $f_value != 0; 
-            # State id only numbers between 100 and 699 are operational +            } elsif ($f_param eq 'nationalnr') { 
-            $msg_value =~ s/_0*/./; +                # Convert to a pure numerical value (float). For 001101 
-            $f_value =~ s/_0*/./; +                # State id only numbers between 100 and 699 are operational 
-        } elsif ($f_param eq 'obstime') { +                $msg_value =~ s/_0*/./; 
-            # Convert to a pure numerical value (float) +                $f_value =~ s/_0*/./; 
-            $msg_value =~ s/[-:]//g; +            } elsif ($f_param eq 'obstime') { 
-            $msg_value =~ s/ /./; +                # Convert to a pure numerical value (float) 
-            $f_value =~ s/[-:']//g; +                $msg_value =~ s/[-:]//g; 
-            $f_value =~ s/^ +//; +                $msg_value =~ s/ /./; 
-            $f_value =~ s/ +$//; +                $f_value =~ s/[-:']//g; 
-            $f_value =~ s/ /./;+                $f_value =~ s/^ +//; 
 +                $f_value =~ s/ +$//; 
 +                $f_value =~ s/ /./; 
 +            } elsif ($f_param eq 'name') { 
 +                # Add or correct quoting to "" and ignore casing 
 +                $msg_value = '"' . lc $msg_value . '"'; 
 +                $f_value = lc $f_value; 
 +                if ($f_value =~ /^'.*'$/) { 
 +                    $f_value =~ s/^'//; 
 +                    $f_value =~ s/'$//; 
 +                } 
 +                if ($f_value !~ /^".*"$/) { 
 +                    $f_value = '"' . $f_value . '"'; 
 +                } 
 +            }
         }         }
 +
 + my $condition = "$msg_value $op $f_value";
 + # Some values should be string values
 + if ($f_operator =~ /~/) {
 +     $condition = "q{$msg_value} $op $f_value";
 + } elsif (grep {$_ eq $f_param} @ascii_params) {
 +     $condition = "q{$msg_value} $op q{$f_value}";
 + }
  
         # Finally, do the criterium check         # Finally, do the criterium check
-        if (eval "$msg_value $op $f_value") { + if (eval $condition) { 
-            # No need to check the remaining alternative criteria +     # No need to check the remaining alternative criteria 
-            $i += $num_alt if $num_alt; +     $i += $num_alt if $num_alt; 
-            next; +     next; 
-        } else { + } else { 
-            next if $num_alt; +     next if $num_alt; 
-            return 1; +     return 1; 
-        }+ }
     }     }
  
Line 489: Line 536:
     return if !$req_stations;     return if !$req_stations;
     die "Station list must start with 'wmonr=', 'nationalnr=', "     die "Station list must start with 'wmonr=', 'nationalnr=', "
-        . "'call_sign=', 'buoy_id=' or aircraft='"+        . "'call_sign=', 'buoy_id=', 'aircraft=', 'icao_id' or 'wigosid='"
         unless $req_stations         unless $req_stations
-        =~ /^(wmonr=|nationalnr=|call_sign=|buoy_id=|aircraft=)/;+        =~ /^(wmonr=|nationalnr=|call_sign=|buoy_id=|aircraft=|icao_id=|wigosid=)/;
  
     my ($id, $rest) = split /=/, $req_stations;     my ($id, $rest) = split /=/, $req_stations;
Line 552: Line 599:
     }     }
  
-    my @ascii_params = qw(aircraft call_sign icao_id obstime name type);+    my @ascii_params = qw(aircraft call_sign icao_id obstime name type wigosid);
     my $lexical_sort = grep {$_ eq $sort_on} @ascii_params;     my $lexical_sort = grep {$_ eq $sort_on} @ascii_params;
  
Line 647: Line 694:
                   as they occur there. If using --csv possibly                   as they occur there. If using --csv possibly
                   followed by --delimiter <del>, the parameters vill                   followed by --delimiter <del>, the parameters vill
-                  be printed using the CSV (comma separated values) +                  be printed using the CSV (comma-separated values) 
-                  format, with the delimiter del (default is ',')+                  format, with the delimiter del (default is ';')
   --sort          Sort the decoded observations on station identification;   --sort          Sort the decoded observations on station identification;
                   first stations with wmonr, then stations with nationalnr,                   first stations with wmonr, then stations with nationalnr,
-                  call sign, buoy_id or aircraft (others left out)+                  call_sign, buoy_id, aircraft, icao_id or wigosid 
 +                  (others left out)
   --sort_on <parameter>[-] Sort the decoded observations on increasing   --sort_on <parameter>[-] Sort the decoded observations on increasing
                   values of parameter, or decreasing values if a '-'                   values of parameter, or decreasing values if a '-'
Line 674: Line 722:
                   Force observation type. If this option is not set,                   Force observation type. If this option is not set,
                   will make an educated guess of observation type                   will make an educated guess of observation type
-                  based on metadata in section 1 of each BUFR +                  based on metadata in section 1 of each BUFR message
-                  message.+
   --tablepath <path to BUFR tables>   --tablepath <path to BUFR tables>
                   Set path to BUFR tables (overrides ENV{BUFR_TABLES})                   Set path to BUFR tables (overrides ENV{BUFR_TABLES})
Line 693: Line 740:
 temperature to be printed for a BUFR SYNOP file, either supply temperature to be printed for a BUFR SYNOP file, either supply
  
-  wmonr,call_sign,TA+  wmonr,nationalnr,call_sign,TA
  
 as argument to --params, or supply a <parameter file> which should as argument to --params, or supply a <parameter file> which should
Line 699: Line 746:
  
   wmonr   wmonr
 +  nationalnr
   call_sign   call_sign
   TA   TA
Line 719: Line 767:
 listing may for example start like listing may for example start like
  
-  wmonr,call_sign,TA +  wmonr;nationalnr;call_sign;TA 
-  01001,,-1.5 +  01001;;;-1.5 
-  ,LF5U,9.0+  ;;LF5U;9.0
  
-You can choose another delimiter than comma by use of option +You can choose another delimiter than semicolon by use of option 
---delimiter <del>, e.g. --csv --delimiter ';'+--delimiter <del>, e.g. --csv --delimiter ','
  
 Using --filter will decode only those observations that meet at least Using --filter will decode only those observations that meet at least
Line 730: Line 778:
 in <filter file>, where the BUFR descriptor criteria should come first in <filter file>, where the BUFR descriptor criteria should come first
 in filter file followed by a blank line, then comes the parameter in filter file followed by a blank line, then comes the parameter
-criteria which should match <param> or <param> <operator> <value> +criteria which should match <param> or !<param> or <param> <operator> 
-where operator is one of =, !=, <, <=, > and >=. The parameter+<value> where operator is one of =, !=, =~, !~, <, <=, > and >=. What 
 +follows =~ and !~ should be a Perl match regular expression. The parameter
 criteria may be phrased as alternatives by separating them with '|' on criteria may be phrased as alternatives by separating them with '|' on
 a single line. An example filter file is a single line. An example filter file is
Line 750: Line 799:
  
 which decodes all observations with block number 01, two other which decodes all observations with block number 01, two other
-specific wmo stations and one specific ship, being manned stations and +specific wmo stations and one specific ship, where stations should be 
-having cloud cover different from 8 (but NN must be part of the +manned and have cloud cover with a value different from 8, and have 
-message) and temperature between 5 and 9.5 degrees Celsius and +temperature between 5 and 9.5 degrees Celsius, and contain 
-containing precipitation for last 24 hours. Comment lines starting +precipitation for last 24 hours. Comment lines starting with # will be 
-with # will be ignored.+ignored.
  
 Another example: the filter file (starting with a blank line!) Another example: the filter file (starting with a blank line!)
  
  
-  wmonr+  call_sign =~ /^L[A-N]..$/
   obstime >= '2012-02-10 06:00:00'   obstime >= '2012-02-10 06:00:00'
-  RR_1 | RR_12 | RR_24 +  HW | HWA | PW | PWA 
-  TA < -30 | TA > 30+  FF > 10 | FG_010 > 10
  
-will print only those observations containing a wmonr (skipping ships), +will print only those ship observations for which the 4 character 
-and having obstime larger or equal to the datetime given, and +call_sign starts with 2 letters in the interval LA-LN, and having 
-containing precipitation for 1, 12 or 24 hours, and having temperature +obstime larger or equal to the datetime given, and containing wave 
-below minus 30 or above plus 30 degrees Celsius.+data (specifically: height or period of waves, manually or 
 +automatically measured), and with wind or 10 minutes gust more than 10 
 +m/s.
  
 For convenience, when there are no BUFR descriptor criteria, you might For convenience, when there are no BUFR descriptor criteria, you might
 provide the filter criteria on the command line. Example: provide the filter criteria on the command line. Example:
  
---filter wmonr,'TA > 0','RR_12 | RR_24'+--filter 'wmonr,TA > 0,RR_12 | RR_24, !FF'
  
 will decode only observations with wmonr, having positive temperature will decode only observations with wmonr, having positive temperature
-and containing precipitation for 12 or 24 hours. If (like for --param) +and containing precipitation for 12 or 24 hours and not reporting 
-the filter list consists of one criterium only, a comma must be +wind. If (like for --param) the filter list consists of one criterium 
-appended.+only, a comma must be appended.
  
 To avoid the need of creating a filter file when observations for some To avoid the need of creating a filter file when observations for some
Line 788: Line 839:
   --station buoyid=64607,64609   --station buoyid=64607,64609
   --station aircraft=EU3421,JHCWUURA   --station aircraft=EU3421,JHCWUURA
 +  --station icao_id=ENGM,ENBO
 +  --station wigosid=0-376-0-511,0-20000-0-01492
  
 You cannot mix different kinds of stations this way (before '=' you You cannot mix different kinds of stations this way (before '=' you
-must choose either wmonr, nationalnr, call_sign, buoy_id or +must choose either wmonr, nationalnr, call_sign, buoy_id, aircraft, 
-aircraft). Note also that providing the stations in the BUFR+icao_id or wigosid). Note also that providing the stations in the BUFR
 descriptor part (first part) of the filter file will speed up descriptor part (first part) of the filter file will speed up
 execution time considerably, compared to using option --station. It is execution time considerably, compared to using option --station. It is
  • bufr.pm/bufrdump.pl_source.1338801845.txt.gz
  • Last modified: 2022-05-31 09:23:11
  • (external edit)