📄 diff.pm
字号:
sub LCS
{
my $a = shift; # array ref
my $b = shift; # array ref or hash ref
my $matchVector = _longestCommonSubsequence( $a, $b, 0, @_ );
my @retval;
my $i;
for ( $i = 0 ; $i <= $#$matchVector ; $i++ )
{
if ( defined( $matchVector->[$i] ) )
{
push ( @retval, $a->[$i] );
}
}
return wantarray ? @retval : \@retval;
}
sub LCS_length
{
my $a = shift; # array ref
my $b = shift; # array ref or hash ref
return _longestCommonSubsequence( $a, $b, 1, @_ );
}
sub LCSidx
{
my $a= shift @_;
my $b= shift @_;
my $match= _longestCommonSubsequence( $a, $b, 0, @_ );
my @am= grep defined $match->[$_], 0..$#$match;
my @bm= @{$match}[@am];
return \@am, \@bm;
}
sub compact_diff
{
my $a= shift @_;
my $b= shift @_;
my( $am, $bm )= LCSidx( $a, $b, @_ );
my @cdiff;
my( $ai, $bi )= ( 0, 0 );
push @cdiff, $ai, $bi;
while( 1 ) {
while( @$am && $ai == $am->[0] && $bi == $bm->[0] ) {
shift @$am;
shift @$bm;
++$ai, ++$bi;
}
push @cdiff, $ai, $bi;
last if ! @$am;
$ai = $am->[0];
$bi = $bm->[0];
push @cdiff, $ai, $bi;
}
push @cdiff, 0+@$a, 0+@$b
if $ai < @$a || $bi < @$b;
return wantarray ? @cdiff : \@cdiff;
}
sub diff
{
my $a = shift; # array ref
my $b = shift; # array ref
my $retval = [];
my $hunk = [];
my $discard = sub {
push @$hunk, [ '-', $_[0], $a->[ $_[0] ] ];
};
my $add = sub {
push @$hunk, [ '+', $_[1], $b->[ $_[1] ] ];
};
my $match = sub {
push @$retval, $hunk
if 0 < @$hunk;
$hunk = []
};
traverse_sequences( $a, $b,
{ MATCH => $match, DISCARD_A => $discard, DISCARD_B => $add }, @_ );
&$match();
return wantarray ? @$retval : $retval;
}
sub sdiff
{
my $a = shift; # array ref
my $b = shift; # array ref
my $retval = [];
my $discard = sub { push ( @$retval, [ '-', $a->[ $_[0] ], "" ] ) };
my $add = sub { push ( @$retval, [ '+', "", $b->[ $_[1] ] ] ) };
my $change = sub {
push ( @$retval, [ 'c', $a->[ $_[0] ], $b->[ $_[1] ] ] );
};
my $match = sub {
push ( @$retval, [ 'u', $a->[ $_[0] ], $b->[ $_[1] ] ] );
};
traverse_balanced(
$a,
$b,
{
MATCH => $match,
DISCARD_A => $discard,
DISCARD_B => $add,
CHANGE => $change,
},
@_
);
return wantarray ? @$retval : $retval;
}
########################################
my $Root= __PACKAGE__;
package Algorithm::Diff::_impl;
use strict;
sub _Idx() { 0 } # $me->[_Idx]: Ref to array of hunk indices
# 1 # $me->[1]: Ref to first sequence
# 2 # $me->[2]: Ref to second sequence
sub _End() { 3 } # $me->[_End]: Diff between forward and reverse pos
sub _Same() { 4 } # $me->[_Same]: 1 if pos 1 contains unchanged items
sub _Base() { 5 } # $me->[_Base]: Added to range's min and max
sub _Pos() { 6 } # $me->[_Pos]: Which hunk is currently selected
sub _Off() { 7 } # $me->[_Off]: Offset into _Idx for current position
sub _Min() { -2 } # Added to _Off to get min instead of max+1
sub Die
{
require Carp;
Carp::confess( @_ );
}
sub _ChkPos
{
my( $me )= @_;
return if $me->[_Pos];
my $meth= ( caller(1) )[3];
Die( "Called $meth on 'reset' object" );
}
sub _ChkSeq
{
my( $me, $seq )= @_;
return $seq + $me->[_Off]
if 1 == $seq || 2 == $seq;
my $meth= ( caller(1) )[3];
Die( "$meth: Invalid sequence number ($seq); must be 1 or 2" );
}
sub getObjPkg
{
my( $us )= @_;
return ref $us if ref $us;
return $us . "::_obj";
}
sub new
{
my( $us, $seq1, $seq2, $opts ) = @_;
my @args;
for( $opts->{keyGen} ) {
push @args, $_ if $_;
}
for( $opts->{keyGenArgs} ) {
push @args, @$_ if $_;
}
my $cdif= Algorithm::Diff::compact_diff( $seq1, $seq2, @args );
my $same= 1;
if( 0 == $cdif->[2] && 0 == $cdif->[3] ) {
$same= 0;
splice @$cdif, 0, 2;
}
my @obj= ( $cdif, $seq1, $seq2 );
$obj[_End] = (1+@$cdif)/2;
$obj[_Same] = $same;
$obj[_Base] = 0;
my $me = bless \@obj, $us->getObjPkg();
$me->Reset( 0 );
return $me;
}
sub Reset
{
my( $me, $pos )= @_;
$pos= int( $pos || 0 );
$pos += $me->[_End]
if $pos < 0;
$pos= 0
if $pos < 0 || $me->[_End] <= $pos;
$me->[_Pos]= $pos || !1;
$me->[_Off]= 2*$pos - 1;
return $me;
}
sub Base
{
my( $me, $base )= @_;
my $oldBase= $me->[_Base];
$me->[_Base]= 0+$base if defined $base;
return $oldBase;
}
sub Copy
{
my( $me, $pos, $base )= @_;
my @obj= @$me;
my $you= bless \@obj, ref($me);
$you->Reset( $pos ) if defined $pos;
$you->Base( $base );
return $you;
}
sub Next {
my( $me, $steps )= @_;
$steps= 1 if ! defined $steps;
if( $steps ) {
my $pos= $me->[_Pos];
my $new= $pos + $steps;
$new= 0 if $pos && $new < 0;
$me->Reset( $new )
}
return $me->[_Pos];
}
sub Prev {
my( $me, $steps )= @_;
$steps= 1 if ! defined $steps;
my $pos= $me->Next(-$steps);
$pos -= $me->[_End] if $pos;
return $pos;
}
sub Diff {
my( $me )= @_;
$me->_ChkPos();
return 0 if $me->[_Same] == ( 1 & $me->[_Pos] );
my $ret= 0;
my $off= $me->[_Off];
for my $seq ( 1, 2 ) {
$ret |= $seq
if $me->[_Idx][ $off + $seq + _Min ]
< $me->[_Idx][ $off + $seq ];
}
return $ret;
}
sub Min {
my( $me, $seq, $base )= @_;
$me->_ChkPos();
my $off= $me->_ChkSeq($seq);
$base= $me->[_Base] if !defined $base;
return $base + $me->[_Idx][ $off + _Min ];
}
sub Max {
my( $me, $seq, $base )= @_;
$me->_ChkPos();
my $off= $me->_ChkSeq($seq);
$base= $me->[_Base] if !defined $base;
return $base + $me->[_Idx][ $off ] -1;
}
sub Range {
my( $me, $seq, $base )= @_;
$me->_ChkPos();
my $off = $me->_ChkSeq($seq);
if( !wantarray ) {
return $me->[_Idx][ $off ]
- $me->[_Idx][ $off + _Min ];
}
$base= $me->[_Base] if !defined $base;
return ( $base + $me->[_Idx][ $off + _Min ] )
.. ( $base + $me->[_Idx][ $off ] - 1 );
}
sub Items {
my( $me, $seq )= @_;
$me->_ChkPos();
my $off = $me->_ChkSeq($seq);
if( !wantarray ) {
return $me->[_Idx][ $off ]
- $me->[_Idx][ $off + _Min ];
}
return
@{$me->[$seq]}[
$me->[_Idx][ $off + _Min ]
.. ( $me->[_Idx][ $off ] - 1 )
];
}
sub Same {
my( $me )= @_;
$me->_ChkPos();
return wantarray ? () : 0
if $me->[_Same] != ( 1 & $me->[_Pos] );
return $me->Items(1);
}
my %getName;
BEGIN {
%getName= (
same => \&Same,
diff => \&Diff,
base => \&Base,
min => \&Min,
max => \&Max,
range=> \&Range,
items=> \&Items, # same thing
);
}
sub Get
{
my $me= shift @_;
$me->_ChkPos();
my @value;
for my $arg ( @_ ) {
for my $word ( split ' ', $arg ) {
my $meth;
if( $word !~ /^(-?\d+)?([a-zA-Z]+)([12])?$/
|| not $meth= $getName{ lc $2 }
) {
Die( $Root, ", Get: Invalid request ($word)" );
}
my( $base, $name, $seq )= ( $1, $2, $3 );
push @value, scalar(
4 == length($name)
? $meth->( $me )
: $meth->( $me, $seq, $base )
);
}
}
if( wantarray ) {
return @value;
} elsif( 1 == @value ) {
return $value[0];
}
Die( 0+@value, " values requested from ",
$Root, "'s Get in scalar context" );
}
my $Obj= getObjPkg($Root);
no strict 'refs';
for my $meth ( qw( new getObjPkg ) ) {
*{$Root."::".$meth} = \&{$meth};
*{$Obj ."::".$meth} = \&{$meth};
}
for my $meth ( qw(
Next Prev Reset Copy Base Diff
Same Items Range Min Max Get
_ChkPos _ChkSeq
) ) {
*{$Obj."::".$meth} = \&{$meth};
}
1;
__END__
=head1 NAME
Algorithm::Diff - Compute `intelligent' differences between two files / lists
=head1 SYNOPSIS
require Algorithm::Diff;
# This example produces traditional 'diff' output:
my $diff = Algorithm::Diff->new( \@seq1, \@seq2 );
$diff->Base( 1 ); # Return line numbers, not indices
while( $diff->Next() ) {
next if $diff->Same();
my $sep = '';
if( ! $diff->Items(2) ) {
sprintf "%d,%dd%d\n",
$diff->Get(qw( Min1 Max1 Max2 ));
} elsif( ! $diff->Items(1) ) {
sprintf "%da%d,%d\n",
$diff->Get(qw( Max1 Min2 Max2 ));
} else {
$sep = "---\n";
sprintf "%d,%dc%d,%d\n",
$diff->Get(qw( Min1 Max1 Min2 Max2 ));
}
print "< $_" for $diff->Items(1);
print $sep;
print "> $_" for $diff->Items(2);
}
# Alternate interfaces:
use Algorithm::Diff qw(
LCS LCS_length LCSidx
diff sdiff compact_diff
traverse_sequences traverse_balanced );
@lcs = LCS( \@seq1, \@seq2 );
$lcsref = LCS( \@seq1, \@seq2 );
$count = LCS_length( \@seq1, \@seq2 );
( $seq1idxref, $seq2idxref ) = LCSidx( \@seq1, \@seq2 );
# Complicated interfaces:
@diffs = diff( \@seq1, \@seq2 );
@sdiffs = sdiff( \@seq1, \@seq2 );
@cdiffs = compact_diff( \@seq1, \@seq2 );
traverse_sequences(
\@seq1,
\@seq2,
{ MATCH => \&callback1,
DISCARD_A => \&callback2,
DISCARD_B => \&callback3,
},
\&key_generator,
@extra_args,
);
traverse_balanced(
\@seq1,
\@seq2,
{ MATCH => \&callback1,
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -