[PATCH/RFC v4 07/10] send-email: reduce dependancies impact on parse_address_line
It may not be easily readable without colors, so there are the scripts at the end. You can change the tested input by changing lines after the "cat >.tmplist" line in testall.sh. (There are two scripts testall.sh and testone.perl).
Here are the tests results:
Input:
Split:
M::A :
Same : Yes
----------
Input: Jane
Split: Jane
M::A : Jane
Same : Yes
----------
Input: jdoe@example.com
Split: jdoe@example.com
M::A : jdoe@example.com
Same : Yes
----------
Input: <jdoe@example.com>
Split: jdoe@example.com
M::A : jdoe@example.com
Same : Yes
----------
Input: Jane <jdoe@example.com>
Split: Jane <jdoe@example.com>
M::A : Jane <jdoe@example.com>
Same : Yes
----------
Input: Jane Doe <jdoe@example.com>
Split: Jane Doe <jdoe@example.com>
M::A : Jane Doe <jdoe@example.com>
Same : Yes
----------
Input: Jane\ Doe <jdoe@example.com>
Split: "Jane\ Doe" <jdoe@example.com>
M::A : "Jane \ Doe" <jdoe@example.com>
Same : No
----------
Input: "Jane" <jdoe@example.com>
Split: "Jane" <jdoe@example.com>
M::A : "Jane" <jdoe@example.com>
Same : Yes
----------
Input: "Doe, Jane" <jdoe@example.com>
Split: "Doe, Jane" <jdoe@example.com>
M::A : "Doe, Jane" <jdoe@example.com>
Same : Yes
----------
Input: "Doe, Ja"ne <jdoe@example.com>
Split: "Doe, Ja ne" <jdoe@example.com>
M::A : "Doe, Ja" ne <jdoe@example.com>
Same : No
----------
Input: "Doe, Katarina" Jane <jdoe@example.com>
Split: "Doe, Katarina Jane" <jdoe@example.com>
M::A : "Doe, Katarina" Jane <jdoe@example.com>
Same : No
----------
Input: "Jane@:;\>.,()<Doe" <jdoe@example.com>
Split: "Jane@:;\>.,()<Doe" <jdoe@example.com>
M::A : "Jane@:;\>.,()<Doe" <jdoe@example.com>
Same : Yes
----------
Input: Jane@:;\.,()<>Doe <jdoe@example.com>
Split: Jane@:
: "\."
: Doe <jdoe@example.com> ()
M::A : Jane@:
: \.
: Doe <jdoe@example.com> ()
Same : No
----------
Input: Jane!#$%&'*+-/=?^_{|}~Doe' <jdoe@example.com>
Split: Jane!#$%&'*+-/=?^_{|}~Doe' <jdoe@example.com>
M::A : Jane!#$%&'*+-/=?^_{|}~Doe' <jdoe@example.com>
Same : Yes
----------
Input: "<jdoe@example.com>"
Split: "<jdoe@example.com>"
M::A : "<jdoe@example.com>"
Same : Yes
----------
Input: "Jane jdoe@example.com"
Split: "Jane jdoe@example.com"
M::A : "Jane jdoe@example.com"
Same : Yes
----------
Input: Jane Doe <jdoe @ example.com >
Split: Jane Doe <jdoe@example.com>
M::A : Jane Doe <jdoe@example.com>
Same : Yes
----------
Input: Jane Doe < jdoe@example.com >
Split: Jane Doe <jdoe@example.com>
M::A : Jane Doe <jdoe@example.com>
Same : Yes
----------
Input: Jane @ Doe @ Jane @ Doe
Split: Jane@Doe@Jane@Doe
M::A : Jane@Doe@Jane@Doe
Same : Yes
----------
Input: Jane jdoe@example.com
Split: Janejdoe@example.com
M::A : Jane
: jdoe@example.com
Same : No
----------
Input: <jdoe@example.com> Jane Doe
Split: jdoe@example.comJaneDoe
M::A : Jane Doe <jdoe@example.com>
Same : No
----------
Input: Jane <jdoe@example.com> Doe
Split: Jane <jdoe@example.comDoe>
M::A : Jane Doe <jdoe@example.com>
Same : No
----------
Input: "Jane, 'Doe'" <jdoe@example.com>
Split: "Jane, 'Doe'" <jdoe@example.com>
M::A : "Jane, 'Doe'" <jdoe@example.com>
Same : Yes
----------
Input: 'Doe, "Jane' <jdoe@example.com>
Split: 'Doe
: " Jane' <jdoe@example.com>
M::A : 'Doe
: " Jane' <jdoe@example.com>
Same : Yes
----------
Input: "Jane" "Do"e <jdoe@example.com>
Split: "Jane" "Do" e <jdoe@example.com>
M::A : "Jane" "Do" e <jdoe@example.com>
Same : Yes
----------
Input: "Jane' Doe" <jdoe@example.com>
Split: "Jane' Doe" <jdoe@example.com>
M::A : "Jane' Doe" <jdoe@example.com>
Same : Yes
----------
Input: "Jane Doe <jdoe@example.com>" <jdoe@example.com>
Split: "Jane Doe <jdoe@example.com>" <jdoe@example.com>
M::A : "Jane Doe <jdoe@example.com>" <jdoe@example.com>
Same : Yes
----------
Input: "Jane\" Doe" <jdoe@example.com>
Split: "Jane\" Doe" <jdoe@example.com>
M::A : "Jane\" Doe" <jdoe@example.com>
Same : Yes
----------
Input: Doe, jane <jdoe@example.com>
Split: Doe
: jane <jdoe@example.com>
M::A : Doe
: jane <jdoe@example.com>
Same : Yes
----------
Input: "Jane Doe <jdoe@example.com>
Split: " Jane Doe <jdoe@example.com>
M::A : " Jane Doe <jdoe@example.com>
Same : Yes
----------
Input: "Jane "Kat"a" ri"na" ",Doe" <jdoe@example.com>
Split: "Jane Kat a ri na ,Doe" <jdoe@example.com>
M::A : "Jane " Kat "a" ri "na" ",Doe" <jdoe@example.com>
Same : No
----------
Input: Jane Doe
Split: Jane Doe
M::A : Jane
: Doe
Same : No
----------
Input: Jane "Doe <jdoe@example.com>"
Split: "Jane Doe <jdoe@example.com>"
M::A : Jane
: "Doe <jdoe@example.com>"
Same : No
----------
Input: \"Jane Doe <jdoe@example.com>
Split: "\"Jane Doe" <jdoe@example.com>
M::A : \ " Jane Doe <jdoe@example.com>
Same : No
----------
Input: Jane\"\" Doe <jdoe@example.com>
Split: "Jane\"\" Doe" <jdoe@example.com>
M::A : Jane \ " \ " Doe <jdoe@example.com>
Same : No
----------
Input: 'Jane 'Doe' <jdoe@example.com>
Split: 'Jane 'Doe' <jdoe@example.com>
M::A : 'Jane 'Doe' <jdoe@example.com>
Same : Yes
----------
Input: 'Jane "Katarina\" \' Doe' <jdoe@example.com>
Split: "'Jane Katarina\" \' Doe'" <jdoe@example.com>
M::A : 'Jane " Katarina \ " \ ' Doe' <jdoe@example.com>
Same : No**********************************************************************
* SCRIPTS PART *
**********************************************************************
---------------------------- testall.sh ----------------------------
#!/bin/sh
cat >.tmplist <<EOF
Jane jdoe@example.com <jdoe@example.com> Jane <jdoe@example.com> Jane Doe <jdoe@example.com> Jane\ Doe <jdoe@example.com> "Jane" <jdoe@example.com> "Doe, Jane" <jdoe@example.com> "Doe, Ja"ne <jdoe@example.com> "Doe, Katarina" Jane <jdoe@example.com> "Jane@:;\>.,()<Doe" <jdoe@example.com> Jane@:;\.,()<>Doe <jdoe@example.com> Jane!#$%&'*+-/=?^_{|}~Doe' <jdoe@example.com> "<jdoe@example.com>" "Jane jdoe@example.com" Jane Doe <jdoe @ example.com > Jane Doe < jdoe@example.com > Jane @ Doe @ Jane @ Doe Jane jdoe@example.com <jdoe@example.com> Jane Doe Jane <jdoe@example.com> Doe "Jane, 'Doe'" <jdoe@example.com> 'Doe, "Jane' <jdoe@example.com> "Jane" "Do"e <jdoe@example.com> "Jane' Doe" <jdoe@example.com> "Jane Doe <jdoe@example.com>" <jdoe@example.com> "Jane\" Doe" <jdoe@example.com> Doe, jane <jdoe@example.com> "Jane Doe <jdoe@example.com> "Jane "Kat"a" ri"na" ",Doe" <jdoe@example.com> Jane Doe Jane "Doe <jdoe@example.com>" \"Jane Doe <jdoe@example.com> Jane\"\" Doe <jdoe@example.com> 'Jane 'Doe' <jdoe@example.com> 'Jane "Katarina\" \' Doe' <jdoe@example.com> EOF
cat .tmplist | while read -r line
do
echo "Input: $line"
./testone.perl "$line"
echo ----------
done---------------------------- testone.perl ----------------------------
#!/usr/bin/perl
use strict; use warnings;
use Term::ANSIColor; use Mail::Address; use Text::ParseWords;
my $string = $ARGV[0];
sub split_addrs {
my $re_comment = qr/\((?:[^)]*)\)/;
my $re_quote = qr/"(?:[^\"\\]|\\.)*"/;
my $re_word = qr/(?:[^]["\s()<>:;@\\,.]|\\.)+/;
my $re_token = qr/(?:$re_quote|$re_word|$re_comment|\S)/; my @tokens = map { $_ =~ /\s*($re_token)\s*/g } @_;
push @tokens, ","; my (@addr_list, @phrase, @address, @comment, @buffer) = ();
foreach my $token (@tokens) {
if ($token =~ /^[,;]$/) {
if (@address) {
push @address, @buffer;
} else {
push @phrase, @buffer;
}
my $str_phrase = join ' ', @phrase;
my $str_address = join '', @address;
my $str_comment = join ' ', @comment;
if ($str_phrase =~ /[][()<>:;@\\,.\000-\037\177]/) {
$str_phrase =~ s/(^|[^\\])"/$1/g;
$str_phrase = qq["$str_phrase"];
}
if ($str_address ne "" && $str_phrase ne "") {
$str_address = qq[<$str_address>];
}
my $str_mailbox = "$str_phrase $str_address $str_comment";
$str_mailbox =~ s/^\s*|\s*$//g;
push @addr_list, $str_mailbox if ($str_mailbox);
@phrase = @address = @comment = @buffer = ();
} elsif ($token =~ /^\(/) {
push @comment, $token;
} elsif ($token eq "<") {
push @phrase, (splice @address), (splice @buffer);
} elsif ($token eq ">") {
push @address, (splice @buffer);
} elsif ($token eq "@") {
push @address, (splice @buffer), "@";
} elsif ($token eq ".") {
push @address, (splice @buffer), ".";
} else {
push @buffer, $token;
}
} return @addr_list;
}
sub old_split {
quotewords('\s*,\s*', 1, $_[0]);
}my @tab = split_addrs($string); my @ref = map { $_->format } Mail::Address->parse($string); # my @old = old_split($string); #can be printed to see the difference
my $tabstring = join "\n", @tab; my $refstring = join "\n", @ref; my $same = ($tabstring eq $refstring);
$tabstring =~ s/\n/\n : /g; $refstring =~ s/\n/\n : /g;
print color 'bold yellow'; print "Split: ", "$tabstring", "\n";
print color 'bold blue'; print "M::A : ", "$refstring", "\n";
if ($same) {
print color 'bold green';
print "Same : ", "Yes", "\n";
} else {
print color 'bold red';
print "Same : ", "No", "\n";
}print color 'reset';
Remi Lespinet
