Supposed I have a file with Perl-code: does somebody know, if there is a module which could find the closing "}" of a certain subroutine in that file.
For example:
#!/usr/bin/env perl
use warnings;
use 5.012;
routine_one( '{°^°}' );
routine_two();
sub routine_one {
my $arg = shift;
if ( $arg =~ /}\z/ ) {
say "Hello my }";
}
}
sub routine_two {
say '...' for 0 .. 10
}
The module should be able to remove the whole routine_one or it should can tell me the line-number of the closing "}" from that routine.
You want to use PPI if you are going to be parsing Perl code.
#!/usr/bin/env perl
use warnings;
use 5.012;
use PPI;
my $file = 'Example.pm';
my $doc = PPI::Document->new( $file );
$doc->prune( 'PPI::Token::Pod' );
$doc->prune( 'PPI::Token::Comment' );
my $subs = $doc->find( sub { $_[1]->isa('PPI::Statement::Sub') and $_[1]->name eq 'layout' } );
die if #$subs != 1;
my $new = PPI::Document->new( \qq(sub layout {\n say "my new layout_code";\n}) );
my $subs_new = $new->find( sub { $_[1]->isa('PPI::Statement::Sub') and $_[1]->name eq 'layout' } );
$subs->[0]->block->insert_before( $subs_new->[0]->block ) or die $!;
$subs->[0]->block->remove or die $!;
# $subs->[0]->replace( $subs_new->[0] );
# The ->replace method has not yet been implemented at /usr/local/lib/perl5/site_perl/5.12.2/PPI/Element.pm line 743.
$doc->save( $file ) or die $!;
The following will work in case your subroutines don't contain any blank lines, like the one in your example:
#!/usr/bin/perl -w
use strict;
$^I = ".bkp"; # to create a backup file
{
local $/ = ""; # one paragraph constitutes one record
while (<>) {
unless (/^sub routine_one \{.+\}\s+$/s) { # 's' => '.' will also match "\n"
print;
}
}
}
Related
Using Perl I would like to check if the two lines highlighted below exist in a text file . Each line is preceded by a tab.
CF=CFU-ALL-PROV-NONE-YES-NO-NONE-YES;
CF=CFB-ALL-PROV-NONE-YES-YES-NONE-YES;
***CF=CFU-TS10-ACT-NONE-YES-NO-NONE-YES;***
CF=CFNRY-ALL-PROV-NONE-YES-YES-NONE-YES;
CF=CFNRC-ALL-PROV-NONE-YES-NO-NONE-YES;
***CF=CFB-TS10-ACT-NONE-YES-NO-NONE-YES;***
CF=CFD-TS10-REG-9124445544-YES-YES;
I am using the following if statement but it is not matched
if (/\t*CF=(CFU-TS10-ACT-(NONE|\d+))/ && /\t*CF=(CFB-TS10-ACT-(NONE|\d+))/)
{
say "this case is found here .....";
}
What am I doing wrong ?
Edited
This is the program I wrote :-
#!/usr/bin/perl
use strict;
use warnings;
use feature 'say';
my $HSSIN='D:\testproject\HSS-export-test-run-small.txt';
my $ofile = 'D:\testproject\HSS-output.txt';
open (INFILE, $HSSIN) or die "Can't open input file";
open (OUTFILE,"> $ofile" ) or die "Cant open file";
my $add;
my $MSISDN;
my $line;
sub callForwardingsCF()
{
if (/\t*CF=(CFU-TS10-ACT-(NONE|\d+))/ && /\t*CF=(CFB-TS10-ACT-(NONE|+\d+))/)
{
say "this case is found here .....";
}
} # end sub callForwardingsCFD
while (<INFILE>)
{
if (/<SUBEND/)
{
say "SUBEND found";
#$line = $1 if /^\s*MSISDN=(\d+);/;
print OUTFILE "processSingle UpdateCommand GSUB MKEY $line";
print OUTFILE "\n";
}
if ($_ =~ /^\t*MSISDN=(\d+);/)
{ #find MSISDN in file global search
say "STARTER MSISDN is $1";
$MSISDN = $1;
$add = $1;
$line = "$1"; #group 1
}
callForwardingsCF(); #callForwardings
}
close INFILE;
close OUTFILE;
Example of a record in the input file
<BEGINFILE>
<SUBBEGIN
IMSI=232191400029053;
MSISDN=4369050064401;
DEFCALL=TS11;
CURRENTNAM=BOTH;
CAT=COMMON;
TBS=TS11&TS12&TS21&TS22;
VLRLIST=10;
SGSNLIST=10;
SMDP=MSC;
CB=BAOC-ALL-PROV;
CB=BOIC-ALL-PROV;
CB=BOICEXHC-ALL-PROV;
CB=BICROAM-ALL-PROV;
CW=CW-ALL-PROV;
CF=CFU-ALL-PROV-NONE-YES-NO-NONE-YES-65535-NO-NO-NO-NO-NO-NO-NO-NO-NO-NO;
CF=CFB-ALL-PROV-NONE-YES-YES-NONE-YES-65535-NO-NO-NO-NO-NO-NO-NO-NO-NO-NO;
CF=CFU-TS10-ACT-NONE-YES-NO-NONE-YES-65535-YES-YES-NO-NO-NO-NO-NO-NO-NO-NO;
CF=CFNRY-ALL-PROV-NONE-YES-YES-NONE-YES-65535-NO-NO-NO-NO-NO-NO-NO-NO-NO-NO;
CF=CFNRC-ALL-PROV-NONE-YES-NO-NONE-YES-65535-NO-NO-NO-NO-NO-NO-NO-NO-NO-NO;
CF=CFB-TS10-ACT-NONE-YES-NO-NONE-YES-65535-YES-YES-NO-NO-NO-NO-NO-NO-NO-NO;
CF=CFD-TS10-REG-91436903000-YES-YES-25-YES-65535-YES-YES-NO-NO-NO-YES-YES-YES-YES-NO;
TCSISTATE=YES;
OCSISTATE=YES;
CONTROL=SUB;
WPA=0;
GS=HOLD&MPTY&ECT&CLIR&CLIP;
CLIRES=TEMPALLOW;
CLIPOC=NO;
OCSI=10;
CFSMS=ACT-10-914366488325207-YES-YES-NO-NO-NO;
ARD=PROV;
SUBRES=ALLPLMN;
IST_ALERT_TIMER=120;
IST_ALERT_RESPONSE=2;
SUB_AGE=0;
MIMSI=240076400029053-ONELIVE-2-2-1-0-0;
MIMSI=232191400029053-ONELIVE-1-1-1-0-0;
SID=2805158185721065;
MCSISTATE=YES;
CLRBSG=CLIP-YES-NO-NO-NO-NO;
UPLCSLCK=NO;
UPLPSLCK=NO;
DEFOFAID=10;
EPS_PROFILE_ID=1;
TGPPAMBRMAXUL=50000000;
TGPPAMBRMAXDL=150000000;
ARD_EXT=NULL-NULL-NULL-N3GPPNOTALLOWED;
FRAUDTPL_ID=10;
HLR_INDEX=1;
LTEAUTOPROV=NO;
PSSER=1-1-10-1-NONE-DYNAMIC-00000000;
EPSSER=1-10-10-1-NONE-DYNAMIC-00000000-1;
MPS=NO;
<SUBEND
Thanks,
Graham
Per default regexes match linewise.
So if you were trying to match an input that contains multiple lines, you would have to use one of the modifiers that allows the regex to match the entire string.
See the the perl regex documentation - the chapter "Modifiers".
Then you should add the s modifiler and change your if statement to:
if ( /\t*CF=(CFB-TS10-ACT-(NONE|\d+))/s &&
/\t*CF=(CFU-TS10-ACT-(NONE|\d+))/s ) {
say "found";
}
If you read linewise you will never have both of your regexes match for the same line, so you would need to do your regexes seperately as already suggested by the other answer.
#$/ = ""; #without paragraph mode
open my $file, '<', 'data_file';
binmode $file;
while(<$file>){
print $_ if ( $_ =~ /\s+CF=CFU-TS10-ACT-NONE-YES-NO-NONE-YES-\d+-YES-YES-NO-NO-NO-NO-NO-NO-NO-NO;/ ||
$_ =~ /\s+CF=CFB-TS10-ACT-NONE-YES-NO-NONE-YES-\d+-YES-YES-NO-NO-NO-NO-NO-NO-NO-NO;/ );
}
EDIT:
OR, you can do it in paragraph mode if conditions allow it.
$/ = "";
open my $file, '<', 'data_file';
binmode $file;
while(<$file>){
(undef, $first) = split (/\s+(CF=CFU-TS10-ACT-NONE-YES-NO-NONE-YES-\d+-YES-YES-NO-NO-NO-NO-NO-NO-NO-NO;)/, $_);
(undef, $second) = split(/\s+(CF=CFB-TS10-ACT-NONE-YES-NO-NONE-YES-\d+-YES-YES-NO-NO-NO-NO-NO-NO-NO-NO;)/, $_ );
print $first . "\n" . $second;
}
Code is tested and seems to work fine with supplied data.
Also, those are not tabs "\t" ... those are spaces "\s+" preceding those lines. Best thing is to learn your data set before you try to parse it ;)
Typically perl processes file "line by line".
Try something like sample script below:
my($line1,$line2);
while(<STDIN>) {
$line1=$_ if /\t*CF=(CFU-TS10-ACT-(NONE|\d+))/
$line2=$_ if /\t*CF=(CFB-TS10-ACT-(NONE|\d+))/
if( $line1 and $line2 ) {
say "this case is found here .....";
last; # skip processing remaning lines
}
}
Alternatively you may "slurp" whole file into one scalar variable.
I have the following code in a subroutine in Perl for which I keep getting the following error :
Use of uninitialized value $nextLine in pattern match (m//) at catlist.pl line 67, line 2756.
sub extract_testdesc {
my #str = #_;
my $file = $_[0];
my $testname = $_[1];
my #fifo;
# Open the file
open( FILEHANDLE, $file ) or die "couldnt open";
while (<FILEHANDLE>) {
if ( $_ =~ m/\/\*\*/ ) { # if start of comment /**
undef(#fifo);
$nextLine = <FILEHANDLE>;
while ( $nextLine !~ m/\*\// ) { # Add all lines into array until */ is encountered
if ( $nextLine !~ m/\#testlogic.author/ ) {
$nextLine =~ s/\*//g;
if ( $nextLine ne "" ) {
push( #fifo, $nextLine );
}
}
$nextLine = <FILEHANDLE>;
}
}
if ( $_ =~ m/$testname/ ) {
return (#fifo);
}
}
close(FILEHANDLE);
}
What am I doing wrong ? I'm new to Perl so any help is appreciated.
Whenever you use a while loop on a file handle, it's actually synonymous with while (defined($_ = <FILEHANDLE>)) {. This is useful because once the filehandle reaches the eof, it will exit the loop. On the other hand, you are doing manual calls readline calls without testing to see if anything was returned, hence your uninitialized value warnings.
Overall, your goal and logic are confusing. However, perhaps an introduction to the range operator will help you? The following achieves what I think you logic is, but I easily could have misinterpreted.
sub extract_testdesc {
my ($file, $testname) = #_;
my #fifo;
# Open the file
open my $fh, '<', $file or die "couldnt open: $!";
while (<$fh>) {
if ( my $range = m{\Q/**} .. m{\Q*/}) {
#fifo = () if $range == 1;
push #fifo, $_;
} elsif ($_ =~ m/\Q$testname\E/ ) {
return (#fifo);
}
}
close($fh);
}
I wrote a script to match a pattern and return a statement for a file
#!/usr/bin/perl
use strict;
use warnings;
my $file = '/home/Sidtest/sid.txt';
open my $info , $file or die " Couldn't open the $file:$!";
while( my $line = <$info>) {
if ($line =~ m/^#LoadModule ssl_module/) {
print "FileName =",$file," Status = Failed \n";
}
elsif ($line =~ m/^LoadModule ssl_module/) {
print "FileName =",$file," Status = Passed \n";
}
}
close $info;
So now I am trying to modify this script to work for multiple files under the same directory. I haven't been able to do that successfully. Can anyone please help in how I can make it work for any number of files in a directory.
This will read every file in ./directory and foreach file, print out each line.
The print statement can be altered to print if /match/, or whatever you want:
my #dir = <directory/*>;
foreach my $file (#dir){
open my $input, '<', $file;
while (<$input>){
print "PASS: $_\n" if m/^#LoadModule ssl_module/;
[...]
}
}
The variable #ARGV contains a list of arguments sent to the script when started. Loop through #ARGV and call the script with the files you want to process:
#!/usr/bin/perl
use strict;
use warnings;
foreach my $file (#ARGV) {
open my $info , $file or die " Couldn't open the $file:$!";
while( my $line = <$info>) {
if ($line =~ m/^#LoadModule ssl_module/) {
print "FileName =",$file," Status = Failed \n";
}
elsif ($line =~ m/^LoadModule ssl_module/) {
print "FileName =",$file," Status = Passed \n";
}
}
close $info;
}
# process all files *.txt in your dir: ./myscript.pl /home/Sidtest/*.txt
Check perldoc perlrun, and look at the -p and -n parameters. Essentially, they treat your script as if it were the contents of a loop over stdin, where stdin is generated by iterating through the files supplied on the command line. The name of the file currently-being-processed can be accessed using the $ARGV variable.
So, you might go for an approach where your whole script looks more like this, using the -n param, where $_ contains the current line.:
if ( m/^#LoadModule ssl_module/) {
print "FileName =",$ARGV" Status = Failed \n";
} elsif (m/^LoadModule ssl_module/) {
print "FileName =",$ARGV," Status = Passed \n";
}
I found something that I could use on perlmonks.org (http://www.perlmonks.org/?node_id=870806) but I can't get it to work.
I can read the file without issue and build an array. Then, I'd like to compare each index of the array (each regex) to each line of a file, printing out the line before and the line after the matched line.
My code:
# List of regex's. If this file doesn't exist, we can't continue
open ( $fh, "<", $DEF_FILE ) || die ("Can't open regex file: $DEF_FILE");
while (<$fh>) {
chomp;
push (#bad_strings, $_);
}
close $fh || die "Cannot close regex file: $DEF_FILE: $!";
$file = '/tmp/mydirectory/myfile.txt';
eval { open ( $fh, "<", $file ); };
if ($#) {
# If there was an error opening the file, just move on
print "Error opening file: $file.\n";
} else {
# If no error, process the file
foreach $bad_string (#bad_strings) {
$this_line = "";
$do_next = 0;
seek($fh, 0, 0); # move pointer to 0 each time through
while(<$fh>) {
$last_line = $this_line;
$this_line = $_;
my $rege = eval "sub{ \$_[0] =~ $bad_string }"; # Real-time regex
if ($rege->( $this_line )) { # Line 82
print $last_line unless $do_next;
print $this_line;
$do_next = 1;
} else {
print $this_line if $do_next;
$last_line = "";
$do_next = 0;
}
}
}
} # End "if error opening file" check
This was working before when I had just a string per line in the file and performed a simple test such as if ($this_line =~ /$string_to_search_for/i ) but when I switched to regex in the file and a "real-time" eval statement, I now get Can't use string ("") as a subroutine ref while "strict refs" in use at scrub_file.pl line 82 and line 82 is if ($rege->($this_line)) {.
Prior to that error message, I'm receiving: Use of uninitialized value in subroutine entry at scrub_hhsysdump_file.pl line 82, <$fh> I have some understanding of that error message but can't seem to make the perl engine happy with my code thus far.
Still new to perl and always looking for pointers. Thanks in advance.
I fail to see the reason for those eval statements - all they seem to do is make the code a lot more complicated and difficult to debug.
But $rege is undef because eval "sub{ \$_[0] =~ $bad_string }" isn't working, due to the string having a syntax error. I don't know what's in $DEF_FILE, but unless it has properly-delimited regular expressions then you need to add the delimiters in the eval string.
my $rege = eval "sub{ \$_[0] =~ /$bad_string/ }"
may work, but you may need /\Q$bad_string/ instead if the strings in $DEF_FILE contain regex metacharacters and you want them to be treated as literal characters.
I suggest this version of your program which seems to do what you need without the fuss of the eval calls.
use strict;
use warnings;
use Fcntl ':seek';
my $DEF_FILE = 'myfile';
my #bad_strings = do {
open my $fh, '<', $DEF_FILE or die qq(Can't open regex file "$DEF_FILE": $!);
<$fh>;
};
chomp #bad_strings;
my $file = '/tmp/mydirectory/myfile.txt';
open my $fh, '<', $file or die qq(Unable to open "$file" for input: $!);
for my $bad_string (#bad_strings) {
my $regex = qr/$bad_string/;
my ($last_line, $this_line, $do_next) = ('', '', 0);
seek $fh, 0, SEEK_SET;
while (<$fh>) {
($last_line, $this_line) = ($this_line, $_);
if ($this_line =~ $regex) {
print $last_line unless $do_next;
print $this_line;
$do_next = 1;
}
else {
print $this_line if $do_next;
$do_next = 0;
}
}
}
I have created a Perl file to load in an array of "Stop words".
Then I load in a directory with ".ner" files contained in it.
Each file gets opened and each word is split and compared to the words in the stop file.
If the word matches the word it is changed to "" (nothing-and gets removed)
I then copy the file to another location. So I can differentiate between files with stop words and files without.
But does this change the file to now contain no stop words or will it revert back to the original?
#!/usr/bin/perl
#use strict;
#use warnings;
my #stops;
my #file;
use File::Copy;
open( STOPWORD, "/Users/jen/stopWordList.txt" ) or die "Can't Open: $!\n";
#stops = <STOPWORD>;
while (<STOPWORD>) #read each line into $_
{
chomp #stops; # Remove newline from $_
push #stops, $_; # add the line to #triggers
}
close STOPWORD;
$dirtoget="/Users/jen/temp/";
opendir(IMD, $dirtoget) || die("Cannot open directory");
#thefiles= readdir(IMD);
foreach $f (#thefiles){
if ($f =~ m/\.ner$/){
print $f,"\n";
open (FILE, "/Users/jen/temp/$f")or die"Cannot open FILE";
if ( FILE eq "" ) {
close FILE;
}
else{
while (<FILE>) {
foreach $word(split(/\|/)){
foreach $x (#stops) {
if ($x =~ m/\b\Q$word\E\b/) {
$word = '';
copy("/Users/jen/temp/$f","/Users/jen/correct/$f")or die "Copy failed: $!";
close FILE;
}
}
}
}
}
}
}
closedir(IMD);
exit 0;
The format of the file I am splitting and comparing is as follows:
'<title>|NN|O Woman|NNP|O jumped|VBD|O for|IN|O life|NN|O after|IN|O firebomb|NN|O attack|NN|O -|:|O National|NNP|I-ORG News|NNP|I-ORG ,|,|I-ORG Frontpage|NNP|I-ORG -|:|I-ORG Independent.ie</title>|NNP|'
Should I be outlining where the words should be split ie: split(/|/)?
You should ALWAYS use :
use strict;
use warnings;
use three args open and test opening for failure.
As said codaddict A split with no arguments is equivalent to split(' ', $_).
Here is a proposal to achieve the job (as far as I well understood what you wanted).
#!/usr/bin/perl
use strict;
use warnings;
use 5.10.1;
my #stops = qw(put here your stop words);
my %stops = map{$_ => 1} #stops;
my #thefiles;
my $path = '/Users/jen/temp/';
my $out = $path.'outputfile';
open my $fout, '>', $out or die "can't open '$out' for writing : $!";
foreach my $file(#thefiles) {
next unless $file =~ /\.ner$/;
open my $fh, '<', $path.$file or die "can't open '$file' for reading : $!";
my #lines = <$file>;
close $fh;
foreach my $line(#lines) {
my #words = split/\|/,$line;
foreach my $word(#words) {
$word = '' if exists $stops{$word};
}
print $fout join '|',#words;
}
}
close $out;
A split with no arguments is equivalent to split(' ', $_).
Since you want the lines to be split on | you need to do:
split/\|/
#jenniem001,
open FILE, ("<$fh")||die("cant");undef $/;my $whole_file = <FILE>;foreach my $word (#words){$whole_file=~s/\b\Q$word\E\b//ig;}open FILE (">>$duplicate")||die("cant");print FILE $whole_file;
That will remove stops from your file and create a duplicate. Just call give $duplicate a name :)