File: Diff.pm

package info (click to toggle)
libmail-mbox-messageparser-perl 1.5000%2Bpristine-3
  • links: PTS, VCS
  • area: main
  • in suites: lenny
  • size: 1,308 kB
  • ctags: 426
  • sloc: perl: 7,033; makefile: 38
file content (409 lines) | stat: -rw-r--r-- 11,173 bytes parent folder | download | duplicates (3)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
#line 1 "inc/Text/Diff.pm - /Library/Perl/5.8.1/Text/Diff.pm"
package Text::Diff;

$VERSION = 0.35;

#line 49

use Exporter;
@ISA = qw( Exporter );
@EXPORT = qw( diff );

use strict;
use Carp;
use Algorithm::Diff qw( traverse_sequences );

## Hunks are made of ops.  An op is the starting index for each
## sequence and the opcode:
use constant A       => 0;   # Array index before match/discard
use constant B       => 1;
use constant OPCODE  => 2;   # "-", " ", "+"
use constant FLAG    => 3;   # What to display if not OPCODE "!"


#line 146

my %internal_styles = (
    Unified  => undef,
    Context  => undef,
    OldStyle => undef,
    Table    => undef,   ## "internal", but in another module
);

sub diff {
    my @seqs = ( shift, shift );
    my $options = shift || {};

    for my $i ( 0..1 ) {
        my $seq = $seqs[$i];
	my $type = ref $seq;

        while ( $type eq "CODE" ) {
	    $seqs[$i] = $seq = $seq->( $options );
	    $type = ref $seq;
	}

	my $AorB = !$i ? "A" : "B";

        if ( $type eq "ARRAY" ) {
            ## This is most efficient :)
            $options->{"OFFSET_$AorB"} = 0
                unless defined $options->{"OFFSET_$AorB"};
        }
        elsif ( $type eq "SCALAR" ) {
            $seqs[$i] = [split( /^/m, $$seq )];
            $options->{"OFFSET_$AorB"} = 1
                unless defined $options->{"OFFSET_$AorB"};
        }
        elsif ( ! $type ) {
            $options->{"OFFSET_$AorB"} = 1
                unless defined $options->{"OFFSET_$AorB"};
	    $options->{"FILENAME_$AorB"} = $seq
	        unless defined $options->{"FILENAME_$AorB"};
	    $options->{"MTIME_$AorB"} = (stat($seq))[9]
	        unless defined $options->{"MTIME_$AorB"};

            local $/ = "\n";
            open F, "<$seq" or carp "$!: $seq";
            $seqs[$i] = [<F>];
            close F;

        }
        elsif ( $type eq "GLOB" || UNIVERSAL::isa( $seq, "IO::Handle" ) ) {
            $options->{"OFFSET_$AorB"} = 1
                unless defined $options->{"OFFSET_$AorB"};
            local $/ = "\n";
            $seqs[$i] = [<$seq>];
        }
        else {
            confess "Can't handle input of type ", ref;
        }
    }

    ## Config vars
    my $output;
    my $output_handler = $options->{OUTPUT};
    my $type = ref $output_handler ;
    if ( ! defined $output_handler ) {
        $output = "";
        $output_handler = sub { $output .= shift };
    }
    elsif ( $type eq "CODE" ) {
        ## No problems, mate.
    }
    elsif ( $type eq "SCALAR" ) {
        my $out_ref = $output_handler;
        $output_handler = sub { $$out_ref .= shift };
    }
    elsif ( $type eq "ARRAY" ) {
        my $out_ref = $output_handler;
        $output_handler = sub { push @$out_ref, shift };
    }
    elsif ( $type eq "GLOB" || UNIVERSAL::isa $output_handler, "IO::Handle" ) {
        my $output_handle = $output_handler;
        $output_handler = sub { print $output_handle shift };
    }
    else {
        croak "Unrecognized output type: $type";
    }

    my $style  = $options->{STYLE};
    $style = "Unified" unless defined $options->{STYLE};
    $style = "Text::Diff::$style" if exists $internal_styles{$style};

    if ( ! $style->can( "hunk" ) ) {
	eval "require $style; 1" or die $@;
    }

    $style = $style->new
	if ! ref $style && $style->can( "new" );

    my $ctx_lines = $options->{CONTEXT};
    $ctx_lines = 3 unless defined $ctx_lines;
    $ctx_lines = 0 if $style->isa( "Text::Diff::OldStyle" );

    my @keygen_args = $options->{KEYGEN_ARGS}
        ? @{$options->{KEYGEN_ARGS}}
        : ();

    ## State vars
    my $diffs = 0; ## Number of discards this hunk
    my $ctx   = 0; ## Number of " " (ctx_lines) ops pushed after last diff.
    my @ops;       ## ops (" ", +, -) in this hunk
    my $hunks = 0; ## Number of hunks

    my $emit_ops = sub {
        $output_handler->( $style->file_header( @seqs,     $options ) )
	    unless $hunks++;
        $output_handler->( $style->hunk_header( @seqs, @_, $options ) );
        $output_handler->( $style->hunk       ( @seqs, @_, $options ) );
        $output_handler->( $style->hunk_footer( @seqs, @_, $options ) );
    };

    ## We keep 2*ctx_lines so that if a diff occurs
    ## at 2*ctx_lines we continue to grow the hunk instead
    ## of emitting diffs and context as we go. We
    ## need to know the total length of both of the two
    ## subsequences so the line count can be printed in the
    ## header.
    my $dis_a = sub {push @ops, [@_[0,1],"-"]; ++$diffs ; $ctx = 0 };
    my $dis_b = sub {push @ops, [@_[0,1],"+"]; ++$diffs ; $ctx = 0 };

    traverse_sequences(
        @seqs,
        {
            MATCH => sub {
                push @ops, [@_[0,1]," "];

                if ( $diffs && ++$ctx > $ctx_lines * 2 ) {
        	   $emit_ops->( [ splice @ops, 0, $#ops - $ctx_lines ] );
        	   $ctx = $diffs = 0;
                }

                ## throw away context lines that aren't needed any more
                shift @ops if ! $diffs && @ops > $ctx_lines;
            },
            DISCARD_A => $dis_a,
            DISCARD_B => $dis_b,
        },
        $options->{KEYGEN},  # pass in user arguments for key gen function
        @keygen_args,
    );

    if ( $diffs ) {
        $#ops -= $ctx - $ctx_lines if $ctx > $ctx_lines;
        $emit_ops->( \@ops );
    }

    $output_handler->( $style->file_footer( @seqs, $options ) ) if $hunks;

    return defined $output ? $output : $hunks;
}


sub _header {
    my ( $h ) = @_;
    my ( $p1, $fn1, $t1, $p2, $fn2, $t2 ) = @{$h}{
        "FILENAME_PREFIX_A",
        "FILENAME_A",
        "MTIME_A",
        "FILENAME_PREFIX_B",
        "FILENAME_B",
        "MTIME_B"
    };

    ## remember to change Text::Diff::Table if this logic is tweaked.
    return "" unless defined $fn1 && defined $fn2;

    return join( "",
        $p1, " ", $fn1, defined $t1 ? "\t" . localtime $t1 : (), "\n",
        $p2, " ", $fn2, defined $t2 ? "\t" . localtime $t2 : (), "\n",
    );
}

## _range encapsulates the building of, well, ranges.  Turns out there are
## a few nuances.
sub _range {
    my ( $ops, $a_or_b, $format ) = @_;

    my $start = $ops->[ 0]->[$a_or_b];
    my $after = $ops->[-1]->[$a_or_b];

    ## The sequence indexes in the lines are from *before* the OPCODE is
    ## executed, so we bump the last index up unless the OP indicates
    ## it didn't change.
    ++$after
        unless $ops->[-1]->[OPCODE] eq ( $a_or_b == A ? "+" : "-" );

    ## convert from 0..n index to 1..(n+1) line number.  The unless modifier
    ## handles diffs with no context, where only one file is affected.  In this
    ## case $start == $after indicates an empty range, and the $start must
    ## not be incremented.
    my $empty_range = $start == $after;
    ++$start unless $empty_range;

    return
        $start == $after
            ? $format eq "unified" && $empty_range
                ? "$start,0"
                : $start
            : $format eq "unified"
                ? "$start,".($after-$start+1)
                : "$start,$after";
}


sub _op_to_line {
    my ( $seqs, $op, $a_or_b, $op_prefixes ) = @_;

    my $opcode = $op->[OPCODE];
    return () unless defined $op_prefixes->{$opcode};

    my $op_sym = defined $op->[FLAG] ? $op->[FLAG] : $opcode;
    $op_sym = $op_prefixes->{$op_sym};
    return () unless defined $op_sym;

    $a_or_b = $op->[OPCODE] ne "+" ? 0 : 1 unless defined $a_or_b;
    return ( $op_sym, $seqs->[$a_or_b][$op->[$a_or_b]] );
}


#line 397

{
    package Text::Diff::Base;
    sub new         {
        my $proto = shift;
	return bless { @_ }, ref $proto || $proto;
    }

    sub file_header { return "" }
    sub hunk_header { return "" }
    sub hunk        { return "" }
    sub hunk_footer { return "" }
    sub file_footer { return "" }
}


#line 456

@Text::Diff::Unified::ISA = qw( Text::Diff::Base );

sub Text::Diff::Unified::file_header {
    shift; ## No instance data
    my $options = pop ;

    _header(
        { FILENAME_PREFIX_A => "---", FILENAME_PREFIX_B => "+++", %$options }
    );
}

#line 475

sub Text::Diff::Unified::hunk_header {
    shift; ## No instance data
    pop; ## Ignore options
    my $ops = pop;

    return join( "",
        "@@ -",
        _range( $ops, A, "unified" ),
        " +",
        _range( $ops, B, "unified" ),
        " @@\n",
    );
}


#line 498

sub Text::Diff::Unified::hunk {
    shift; ## No instance data
    pop; ## Ignore options
    my $ops = pop;

    my $prefixes = { "+" => "+", " " => " ", "-" => "-" };

    return join "", map _op_to_line( \@_, $_, undef, $prefixes ), @$ops
}


#line 587


@Text::Diff::Context::ISA = qw( Text::Diff::Base );

sub Text::Diff::Context::file_header {
    _header { FILENAME_PREFIX_A=>"***", FILENAME_PREFIX_B=>"---", %{$_[-1]} };
}


sub Text::Diff::Context::hunk_header {
    return "***************\n";
}

sub Text::Diff::Context::hunk {
    shift; ## No instance data
    pop; ## Ignore options
    my $ops = pop;
    ## Leave the sequences in @_[0,1]

    my $a_range = _range( $ops, A, "" );
    my $b_range = _range( $ops, B, "" );

    ## Sigh.  Gotta make sure that differences that aren't adds/deletions
    ## get prefixed with "!", and that the old opcodes are removed.
    my $after;
    for ( my $start = 0; $start <= $#$ops ; $start = $after ) {
        ## Scan until next difference
        $after = $start + 1;
        my $opcode = $ops->[$start]->[OPCODE];
        next if $opcode eq " ";

        my $bang_it;
        while ( $after <= $#$ops && $ops->[$after]->[OPCODE] ne " " ) {
            $bang_it ||= $ops->[$after]->[OPCODE] ne $opcode;
            ++$after;
        }

        if ( $bang_it ) {
            for my $i ( $start..($after-1) ) {
                $ops->[$i]->[FLAG] = "!";
            }
        }
    }

    my $b_prefixes = { "+" => "+ ",  " " => "  ", "-" => undef, "!" => "! " };
    my $a_prefixes = { "+" => undef, " " => "  ", "-" => "- ",  "!" => "! " };

    return join( "",
        "*** ", $a_range, " ****\n",
        map( _op_to_line( \@_, $_, A, $a_prefixes ), @$ops ),
        "--- ", $b_range, " ----\n",
        map( _op_to_line( \@_, $_, B, $b_prefixes ), @$ops ),
    );
}
#line 655

@Text::Diff::OldStyle::ISA = qw( Text::Diff::Base );

sub _op {
    my $ops = shift;
    my $op = $ops->[0]->[OPCODE];
    $op = "c" if grep $_->[OPCODE] ne $op, @$ops;
    $op = "a" if $op eq "+";
    $op = "d" if $op eq "-";
    return $op;
}

sub Text::Diff::OldStyle::hunk_header {
    shift; ## No instance data
    pop; ## ignore options
    my $ops = pop;

    my $op = _op $ops;

    return join "", _range( $ops, A, "" ), $op, _range( $ops, B, "" ), "\n";
}

sub Text::Diff::OldStyle::hunk {
    shift; ## No instance data
    pop; ## ignore options
    my $ops = pop;
    ## Leave the sequences in @_[0,1]

    my $a_prefixes = { "+" => undef,  " " => undef, "-" => "< "  };
    my $b_prefixes = { "+" => "> ",   " " => undef, "-" => undef };

    my $op = _op $ops;

    return join( "",
        map( _op_to_line( \@_, $_, A, $a_prefixes ), @$ops ),
        $op eq "c" ? "---\n" : (),
        map( _op_to_line( \@_, $_, B, $b_prefixes ), @$ops ),
    );
}

#line 724

1;