Perl Notes from Udemy [Learn Perl 5 By Doing It]

Perl 模块安装

参考：
各个平台下 Perl 模块安装总结
官网介绍
Error: Can’t create ‘/Library/Perl/5.18/App’：改用sudo

Section 1: Basic Perl: Getting Started

T2. Hello World

use strict;
use warnings;

sub main {
   
	print "Hello World!\n";
}

main();

T3. Downloading Text and Images With Perl

use strict;
use warnings;

use LWP::Simple;

sub main {
   
	
	print "Downloading ...\n";
	# Download the specified HTML page and print it to the console.
	# print get("http://www.caveofprogramming.com/");
	
	# Download the Cave of Programming home page HTML and save it to "home.html"
	# getstore("http://www.caveofprogramming.com/", "home.html");
	
	# Download logo.png from the Internet and store it in a file named "logo.png"
	my $code = getstore('http://www.caveofprogramming.com/wp-content/themes/squiffy/images/logo.png', "logo.png");
	
	# Did we get code 200 (successful request) ?
	if($code == 200) {
   
		print "Success\n";
	}
	else {
   
		print "Failed\n";
	}
	
	print "Finished\n";
}

main();

T4. Arrays and Checking Whether Files Exist

use strict;
use warnings;

$|=1;

sub main {
   

 	# An array of file names. Note the "@"" for array
	my @files = (
		'/Users//Desktop/Perl/Tutorial2.pl',
		'/Users//Desktop/Perl/Tutorial3.pl',
		'/Users//Desktop/Perl/Tutorial4.pl',
	);

	# foreach loops through the array, setting the loop
	# variable ($file in this case) to each value in turn.
	
	foreach my $file (@files) {
   
		
		# -f tests if a file exists.
		if ( -f $file ) {
   
			print "Found file: $file\n";
		}
		else {
   
			print "File not found: $file\n";
		}
	}

}

main();

T5. Reading Files and Beginning Regular Expressions

use strict;
use warnings;

# turn off output buffering
$|=1;

sub main {
   
	my $file = '/Users//Desktop/Perl/egg.txt';
	
	# Either successfully open the file or else die (stop the program)
	open(INPUT, $file) or die("Input file $file not found.\n");
	
	# Read each line from the file, one line at a time.
	while(my $line = <INPUT>) {
   
		if($line=~/egg/) {
   
			print "$line\n";
		}
	}

	close(INPUT);
}

main();

T6. Writing Files and Replacing Text

use strict;
use warnings;

$|=1;

sub main {
   
	
	# open $input for reading
	my $input = '/Users//Desktop/Perl/egg.txt';
	open(INPUT, $input) or die("Input file $input not found.\n");
	
	# open $output for writing
	my $output = 'output.txt';
	open(OUTPUT, '>'.$output) or die "Can't create $output.\n";
	
	# Read the input file one line at a time.
	while(my $line = <INPUT>) {
   
		
		# If this line has the word "egg" in it, write it
		# to the output file, otherwise ignore it.
		# \b matches the edges (boundaries) of words.
		if($line =~ /\begg\b/) {
   
			$line =~ s/\begg\b/dinosaur/ig; # i: case insensitive, g: global
			print OUTPUT $line;
		}
	}

	close(INPUT);
	close(OUTPUT);
}

main();

T7. Wildcards in Regular Expressions

use strict;
use warnings;

$|=1;

sub main {
   
	my $file = 'C:\tutorial\perl\mymanjeeves.txt';
	
	open(INPUT, $file) or die("Input file $file not found.\n");
	
	while(my $line = <INPUT>) {
   
		
		# The dot matches any character, even space or punctuation
		# e.g. the example below matches
		# I was
		# I said
		# If an
		# I take 
		# etc.
		# (only five characters including the space are actually matched by the epxression)
		if($line =~ /I..a./) {
   
			print $line;
		}
	}

	close(INPUT);
}

main();

T8. Groups: Finding Out What You Actually Matched

use strict;
use warnings;

$|=1;

sub main {
   
	my $file = 'C:\tutorial\perl\mymanjeeves.txt';
	
	open(INPUT, $file) or die("Input file $file not found.\n");
	
	while(my $line = <INPUT>) {
   

		# Surround the bits you want to "capture" with round brackets
		if($line =~ /(I..a.)(...)/) {
   
			# The stuff matched by the first set of round brackets is now in $1
			# The stuff matched by the second set is in $2
			print "First match: '$1'; second match:'$2'\n";
		}
	}

	close(INPUT);
}

main();

T9. Quantifiers: Greedy vs. Non-Greedy

use strict;
use warnings;

$|=1;

sub main {
   
	my $file = 'C:\tutorial\perl\mymanjeeves.txt';
	
	open(INPUT, $file) or die("Input file $file not found.\n");
	
	while(my $line = <INPUT>) {
   
		
		# * matches zero or more of the preceding character; e.g.
		# d* matches zero or more d's 7* zero or more 7's, etc.
		# .* matches zero or more of any character, as many as possible
		# .*? matches zero or more of any character, as few as possible
		

		if($line =~ /(s.*?n)/) {
   
			print "$1\n";
		}
	}

	close(INPUT);
}

main();

If you want to match a ., remember to use \..

T10. Escape Sequences

use strict;
use warnings;

$|=1;

sub main {
   
	
	# \d digit
	# \s space
	# \S non-space
	# \w alphanumeric
	
	# Some examples; in the following examples,
	# each example shows the text, the regular expression
	# and the output, in that order.
	
	# Digits:
	# 'I am 117 years old tomorrow.'
	# (\d+)
	# Matched: '117'
	
	# Space (will also match a tab)
	# I am 117 years old tomorrow.
	# (am\s*\d+)
	# Matched: 'am 117'
	
	# \S (non space -- note, capital 'S')
	# 'I am 117 years old tomorrow.'
	# (y\S+)
	# Matched: 'years'
	
	# Alphanumeric, including underscore
	# \w
	# 'Iam117yearsold_tomorrow.'
	# (y\w*)
	# Matched: 'yearsold_tomorrow'
	
	my $text = 'I am 117 years old tomorrow.';
	
	if($text =~ /(y\S+)/) {
   
		print "Matched: '$1'\n";
	}

	
	
}

main();

T11. Numeric Quantifiers

use strict;
use warnings;

$|=1;

sub main {
   
	
	# * zero or more of the preceding character, as many as possible
	# + one or more of the preceding, as many as possible
	# *? zero or more of the preceding character, as few as possible
	# +? one or more of the preceding, as few as possible
	# {5} five of the preceding
	# {3,6} at least three and at most 6
	# {3,} at least three 

	my $text = 'DE$75883';
	
	if($text =~ /(DE\$\d{3,})/) {
   
		print "Matched: '$1'\n";
	}
}

main();

Section 2: More on Reading Files Line By Line: Tips, Tricks and Vital Knowledge

T13. Split and reading csv files

use strict;
use warnings;

$|=1;

sub main {
   
	my $input = 'test.csv';	
	# execute if the condition is FALSE
	unless(open(INPUT, $input)) {
    
		die "\nCannot open $input\n";
	}
	<INPUT>; # get rid of header
	# if not use $line, then can use $_
	while(my $line = <INPUT>) {
    
		my @values = split ',', $line;
		print $values[1] . "\n";
	}
	close INPUT;
}

main();

T14. Join and Viewing Data Using Data::Dumper

use strict;
use warnings;

use Data::Dumper;

$|=1;

sub main {
   
	my $input = 'test.csv';
	unless(open(INPUT, $input)) {
   
		die "\nCannot open $input\n";
	}	
	<INPUT>;	
	while(my $line = <INPUT>) {
   		
		my @values = split ',', $line;
		# print join '|', @values;		
		print Dumper(@values);
	}	
	close INPUT;
}

main();

Execution output:

$VAR1 = 'Isaac Newton';
$VAR2 = '99.10';
$VAR3 = '15051999
';
$VAR1 = 'Albert Einstein';
$VAR2 = '13.20';
$VAR3 = '11062012
';
$VAR1 = 'Carl Scheele';
$VAR2 = '66.23';
$VAR3 = '01012000
';
$VAR1 = 'Rene Descartes';
$VAR2 = '0.57';
$VAR3 = '10072033
';

The problem is that at the end of each line, there is a \n which is the reason why '; is printed out at the next line.

T15. Chomp and Removing Spaces in Splits

use strict;
use warnings;

use Data::Dumper;

$|=1;

sub main {
   	
	my $input = 'test.csv';	
	unless(open(INPUT, $input)) {
   
		die "\nCannot open $input\n";
     }
	<INPUT>;	
	while(my $line = <INPUT>) {
   		
		chomp $line; # chomp
		# get rid of space
		my @values = split /\s*,\s*/, $line; 		
		print Dumper(@values);
	}
	close INPUT;
}

main();

chomp()
Using the Perl chomp() function
perl中chomp的使用

T16. “Pushing” Onto Arrays

use strict;
use warnings;

use Data::Dumper;

$|=1;

sub main {
   
	
	my @array;		
	push @array, 'apple';
	push @array, 'banana';
	push @array, 'peach';
	
	foreach my $element(@array) {
   
		print $element . "\n";
	}
}

main();

T17. Array of arrays

use strict;
use warnings;
use Data::Dumper;

my @animals = ('dog', 'cat', 'rabbit');
my @fruits = ('apple', 'banana', 'orange');

my $fruits_ref = \@fruits; # create a reference
print $fruits_ref->[0] . "\n";

my @values;

push @values, \@animals;
push @values, \@fruits;

print Dumper(@values);

Output:

apple
$VAR1 = [
          'dog',
          'cat',
          'rabbit'
        ];
$VAR2 = [
          'apple',
          'banana',
          'orange'
        ];

use strict;
use warnings;
use Data::Dumper;

$|=1;

sub main {
   
	my $input = 'test.csv';
	unless(open(INPUT, $input)) {
   
		die "\nCannot open $input\n";
	}	
	<INPUT>;	
	my @lines;
	while(my $line = <INPUT>) {
   		
		chomp $line;		
		my @values = split /\s*,\s*/, $line;
		push @lines, \@values;
	}
	close INPUT;
	print $lines[3][1] . "\n";
	foreach my $line(@lines) {
   
		print Dumper($line);
		print "Name " . $line->[0] . "\n";
	}
}

main();

Output:

0.57
$VAR1 = [
          'Isaac Newton',
          '99.10',
          '15051999'  
        ];
Name Isaac Newton
$VAR1 = [
          'Albert Einstein',
          '13.20',
          '11062012'
        ];
Name Albert Einstein
$VAR1 = [
          'Carl Scheele',
          '66.23',
          '01012000'
        ];
Name Carl Scheele
$VAR1 = [
          'Rene Descartes',
          '0.57',
          '10072033'
        ];
Name Rene Descartes

T18. Hashes: Lookup Tables in Perl

use strict;
use warnings;
use Data::Dumper;

$| = 1;

sub main {
   
	my %months = (
		1 => "Jan",
		5 => "May",
		7 => "Jul",
	);
	
	print $months{
   5} . "\n";
	my %days;
	
	$days{
   "Sunday"} = 1;
	$days{
   "Monday"} = 2;
	$days{
   "Friday"} = 6;
	
	my $day = $days{
   "Friday"};	
	print "Friday is day $day\n";
}

main();

the order of hash can not be relied on.

T19. Iterating over Hashes

use strict;
use warnings;
use Data::Dumper;

$| = 1;

sub main {
   
	my %foods = (
		"mice" => "cheese",
		"dogs" => "meat",
		"birds" => "seeds",
	);	
	
	# We can define an array of variables like this:
	# round brackets are required
	my ($one, $two, $three) = (13, 21, 38);
	print "The value of \$two is $two\n";
	while( my ($key, $value) = each %foods) {
   
		print "$key: $value\n";
	}
	
	# sort the key according to the order of A-Z
	foreach my $key(sort keys %foods) {
   
		my $value = $foods{
   $key};
		
		print "$key = $value\n";
	}

}

main();

Output:

The value of $two is 21
dogs: meat
birds: seeds
mice: cheese
birds = seeds
dogs = meat
mice = cheese

T20. Array of Hashes

use strict;
use warnings;
use Data::Dumper;

$| = 1;

sub main {
   
	my %hash1 = (
		"cat" => "meat",
		"birds" => "seeds",
		"fish" => "worms",
	);
	
	my @test;
	# We could push a reference to a hash onto an array.
	push @test, \%hash1;	
	# We could also just refer to the element after the end of the array
	# and by setting it, create it:
	$test[1] = \%hash1;	
	print $test[0]{
   "birds"} . "\n";
	print $test[1]{
   "fish"} . "\n";
}

main();

Output:

seeds
worms

T21. Storing CSV Data in a Data Structure

use strict;
use warnings;
use Data::Dumper;

$|=1;

sub main {
   
	
	my $input = 'test.csv';	
	unless(open(INPUT, $input)) {
   
		die "\nCannot open $input\n";
	}

	<INPUT>;

	my @data;

	while(my $line = <INPUT>) {
   
		chomp $line;
		my ($name, $payment, $date) = split /\s*,\s*/, $line;
		my %values = (
			"Name" => $name,
			"Payment" => $payment,
			"Date" => $date,
		);
		push @data, \%values;
	}
	
	close INPUT;
	foreach my $data(@data){
   
		print $data -> {
   "Payment"} . "\n";
	}
	print "Descartes: " . $data[3]-> {
   "Name"} . "\n";
	print "Descartes: " . $data[3]{
   "Name"} . "\n";	
}

main();

T22. Validating CSV Data

use strict;
use warnings;
use Data::Dumper;

$|=1;

sub main {
   
	
	my $input = 'test.csv';	
	unless(open(INPUT, $input)) {
   
		die "\nCannot open $input\n";
	}

	<INPUT>;

	my @data;

	LINE: while(my $line = <INPUT>) {
   
		chomp $line;
		my @values = split /\s*,\s*/, $line;
		if (scalar(@values) < 3){
   
			print "Invalid line: $line\n";
			next LINE;
		}

		foreach my $value(@values){
   
			if ($value eq ''){
   
				print "Invalid line: $line\n";
				next LINE;
			}
		}

		my ($name, $payment, $date) = @values;
		my %values = (
			"Name" => $name,
			"Payment" => $payment,
			"Date" => $date,
		);
		push @data, \%values;
	}
	
	close INPUT;
	foreach my $data(@data){
   
		print $data -> {
   "Payment"} . "\n";
	}
	print "Descartes: " . $data[3]-> {
   "Name"} . "\n";
}

main();

Input:

Name,Payment,Date
Isaac Newton ,99.1,15051999
Albert Einstein,13.2,11062012
Carl Scheele,66.23,1012000
Rene Descartes,0.57,10072033
Sarah,10,
,,
Nicolas,0,

Output:

Invalid line: Sarah,10,
Invalid line: ,,
Invalid line: Nicolas,0,
99.1
13.2
66.23
0.57
Descartes: Rene Descartes

T23. Cleaning CSV Data

use strict;
use warnings;
use Data::Dumper;

$|=1;

sub main {
   
	
	my $input = 'test.csv';	
	unless(open(INPUT, $input)) {
   
		die "\nCannot open $input\n";
	}

	<INPUT>;

	my @data;

	LINE: while(my $line = <INPUT>) {
   
		# replace the space at the beginning of the line 
		$line =~ s/^\s*//; 
		# replace the space at the end of the line
		$line =~ s/\s*$//; 
		# replace the space at the beginning and end of the line
		# g stands for global, replace as many as possible
		$line =~ s/^\s*|\s*$//g; 

		$line =~ /\S+/ or next;
		chomp $line;
		my @values = split /\s*,\s*/, $line;
		if (scalar(@values) < 3){
   
			print "Invalid line: $line\n";
			next LINE;
		}

		foreach my $value(@values){
   
			if ($value eq ''){
   
				print "Invalid line: $line\n";
				next LINE;
			}
		}

		my ($name, $payment, $date) = @values;
		my %values = (
			"Name" => $name,
			"Payment" => $payment,
			"Date" => $date,
		);
		push @data, \%values;
	}
	
	close INPUT;