--- amv.pl 2007/07/19 21:16:30 7 +++ amv.pl 2007/07/21 11:05:43 15 @@ -7,14 +7,32 @@ # Various useful links used to produce this: # http://www.moviecodec.com/topics/15431p1.html # http://en.wikipedia.org/wiki/RIFF_(File_format) +# http://www.obrador.com/essentialjpeg/HeaderInfo.htm +# http://lists.helixcommunity.org/pipermail/datatype-dev/2005-January/001886.html use strict; use Data::Dump qw/dump/; use Carp qw/confess/; +use File::Path; +use Getopt::Long; + +my $dump = 0; +my $debug = 0; +my $dump_dir = '/tmp/dump/'; + +GetOptions( + "dump!" => \$dump, + "debug!" => \$debug, + "dump-dir=s" => \$dump_dir, +); my $path = shift @ARGV || die "usage: $0 movie.amv\n"; + +rmtree $dump_dir if -e $dump_dir; +mkpath $dump_dir || die "can't create $dump_dir: $!"; + open(my $fh, '<', $path) || die "can't open $path: $!"; # offset in file @@ -24,11 +42,20 @@ my $d; sub hex_dump { - my $bytes = shift || return; + return unless $dump; + + my ( $bytes, $offset ) = @_; + return unless $bytes; + + my $old_o; + if (defined($offset)) { + $old_o = $o; + $o = $offset; + } my $ascii = $bytes; $ascii =~ s/\W/./gs; - my $hex = unpack('h*', $bytes); + my $hex = uc( unpack('h*', $bytes) ); $hex =~ s/(..)/$1 /g; # calculate number of characters for offset #my $d = length( sprintf("%x",length($bytes)) ); @@ -45,6 +72,8 @@ last; } } + + $o = $old_o if $old_o; } sub x { @@ -66,7 +95,7 @@ if ( $format ) { my @data = unpack($format, $bytes); - warn "## unpacked = ",dump(@data),"\n"; + warn "## unpacked = ",dump(@data),"\n" if $debug; return @data; } else { return $bytes; @@ -81,19 +110,337 @@ if ( $expected_len ) { confess "expected $expected_len bytes for $part got $len" if $len != $expected_len; } - printf ">> %s - %d 0x%x bytes\n", $part, $len, $len; + printf "<< %s - %d 0x%x bytes\n", $part, $len, $len; x($len) if $skip; return $len; } -my ( $riff, $amv ) = x(12, 'Z8Z4'); -die "not RIFF but $riff" if $riff ne 'RIFF'; -die "not AMV but $amv" if $amv ne 'AMV '; +sub huffman { + +# JPEG DHT Segment for YCrCb omitted from MJPG data +return +"\xFF\xC4\x01\xA2" . +"\x00\x00\x01\x05\x01\x01\x01\x01\x01\x01\x00\x00\x00\x00\x00" . +"\x00\x00\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0A\x0B\x01" . +"\x00\x03\x01\x01\x01\x01\x01\x01\x01\x01\x01\x00\x00\x00\x00" . +"\x00\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0A\x0B\x10\x00" . +"\x02\x01\x03\x03\x02\x04\x03\x05\x05\x04\x04\x00\x00\x01\x7D" . +"\x01\x02\x03\x00\x04\x11\x05\x12\x21\x31\x41\x06\x13\x51\x61" . +"\x07\x22\x71\x14\x32\x81\x91\xA1\x08\x23\x42\xB1\xC1\x15\x52" . +"\xD1\xF0\x24\x33\x62\x72\x82\x09\x0A\x16\x17\x18\x19\x1A\x25" . +"\x26\x27\x28\x29\x2A\x34\x35\x36\x37\x38\x39\x3A\x43\x44\x45" . +"\x46\x47\x48\x49\x4A\x53\x54\x55\x56\x57\x58\x59\x5A\x63\x64" . +"\x65\x66\x67\x68\x69\x6A\x73\x74\x75\x76\x77\x78\x79\x7A\x83" . +"\x84\x85\x86\x87\x88\x89\x8A\x92\x93\x94\x95\x96\x97\x98\x99" . +"\x9A\xA2\xA3\xA4\xA5\xA6\xA7\xA8\xA9\xAA\xB2\xB3\xB4\xB5\xB6" . +"\xB7\xB8\xB9\xBA\xC2\xC3\xC4\xC5\xC6\xC7\xC8\xC9\xCA\xD2\xD3" . +"\xD4\xD5\xD6\xD7\xD8\xD9\xDA\xE1\xE2\xE3\xE4\xE5\xE6\xE7\xE8" . +"\xE9\xEA\xF1\xF2\xF3\xF4\xF5\xF6\xF7\xF8\xF9\xFA\x11\x00\x02" . +"\x01\x02\x04\x04\x03\x04\x07\x05\x04\x04\x00\x01\x02\x77\x00" . +"\x01\x02\x03\x11\x04\x05\x21\x31\x06\x12\x41\x51\x07\x61\x71" . +"\x13\x22\x32\x81\x08\x14\x42\x91\xA1\xB1\xC1\x09\x23\x33\x52" . +"\xF0\x15\x62\x72\xD1\x0A\x16\x24\x34\xE1\x25\xF1\x17\x18\x19" . +"\x1A\x26\x27\x28\x29\x2A\x35\x36\x37\x38\x39\x3A\x43\x44\x45" . +"\x46\x47\x48\x49\x4A\x53\x54\x55\x56\x57\x58\x59\x5A\x63\x64" . +"\x65\x66\x67\x68\x69\x6A\x73\x74\x75\x76\x77\x78\x79\x7A\x82" . +"\x83\x84\x85\x86\x87\x88\x89\x8A\x92\x93\x94\x95\x96\x97\x98" . +"\x99\x9A\xA2\xA3\xA4\xA5\xA6\xA7\xA8\xA9\xAA\xB2\xB3\xB4\xB5" . +"\xB6\xB7\xB8\xB9\xBA\xC2\xC3\xC4\xC5\xC6\xC7\xC8\xC9\xCA\xD2" . +"\xD3\xD4\xD5\xD6\xD7\xD8\xD9\xDA\xE2\xE3\xE4\xE5\xE6\xE7\xE8" . +"\xE9\xEA\xF2\xF3\xF4\xF5\xF6\xF7\xF8\xF9\xFA"; + +} + +sub mkjpg { + my ($path,$data) = @_; + open(my $fh, '>', $path) || die "can't create $path: $!"; + + confess "no SOI marker in data" if substr($data,0,2) ne "\xFF\xD8"; + $data = substr($data,2); + + my $header = + "\xFF\xD8". # Start of Image (SOI) marker +#------------------------------------------------------------------ + "\xFF\xE0". # JFIF marker + pack("nZ5CCCnnCC", + 16, # length + 'JFIF', # identifier + 1,1, # version + 0, # units (none) + 1,1, # X,Y density + 0,0, # X,Y thumbnail + ). +#------------------------------------------------------------------ + "\xFF\xC0". # Start of frame + pack("ncnncc9", + 17, # len + 8, # sample precision in bits + 120,160, # X,Y size + 3, # number of components + 1,0x21,0, # Component ID, H+V sampling factors, Quantization table number + 2,0x11,1, + 3,0x11,1, + ). +#------------------------------------------------------------------ + "\xFF\xDB". # Define Quantization table marker + "\x00\x84". # len + "\x00". # 8 bit values, (byte) table 0 + "\x10\x0B\x0C\x0E\x0C". + "\x0A\x10\x0E\x0D\x0E". + "\x12\x11\x10\x13\x18". + "\x28\x1A\x18\x16\x16". + "\x18\x31\x23\x25\x1D". + "\x28\x3A\x33\x3D\x3C". + "\x39\x33\x38\x37\x40". + "\x48\x5C\x4E\x40\x44". + "\x57\x45\x37\x38\x50". + "\x6D\x51\x57\x5F\x62". + "\x67\x68\x67\x3E\x4D". + "\x71\x79\x70\x64\x78". + "\x5C\x65\x67\x63". + "\x01". # 8 bit values, (byte) table 1 + "\x11\x12\x12\x18\x15". + "\x18\x2F\x1A\x1A\x2F". + "\x63\x42\x38\x42\x63". + "\x63\x63\x63\x63\x63". + "\x63\x63\x63\x63\x63". + "\x63\x63\x63\x63\x63". + "\x63\x63\x63\x63\x63". + "\x63\x63\x63\x63\x63". + "\x63\x63\x63\x63\x63". + "\x63\x63\x63\x63\x63". + "\x63\x63\x63\x63\x63". + "\x63\x63\x63\x63\x63". + "\x63\x63\x63\x63". +#------------------------------------------------------------------ +# huffman("\x00"). # 0 DC +# huffman("\x01"). # 1 DC +# huffman("\x10"). # 0 AC +# huffman("\x11"). # 1 AC +#------------------------------------------------------------------ + # Define huffman table (section B.2.4.1) + "\xFF\xC4". # Marker + "\x00\x1F". # Length (31 bytes) + "\x00". # DC, (byte) table 0 + "\x00\x01\x05\x01\x01". + "\x01\x01\x01\x01\x00". + "\x00\x00\x00\x00\x00". + "\x00\x00\x01\x02\x03". + "\x04\x05\x06\x07\x08". + "\x09\x0A\x0B". + # Define huffman table (section B.2.4.1) + "\xFF\xC4". # Marker + "\x00\xB5". # Length (181 bytes) + "\x10". # AC, (byte) table 0 + "\x00\x02\x01\x03\x03". + "\x02\x04\x03\x05\x05". + "\x04\x04\x00\x00\x01". + "\x7D\x01\x02\x03\x00". + "\x04\x11\x05\x12\x21". + "\x31\x41\x06\x13\x51". + "\x61\x07\x22\x71\x14". + "\x32\x81\x91\xA1\x08". + "\x23\x42\xB1\xC1\x15". + "\x52\xD1\xF0\x24\x33". + "\x62\x72\x82\x09\x0A". + "\x16\x17\x18\x19\x1A". + "\x25\x26\x27\x28\x29". + "\x2A\x34\x35\x36\x37". + "\x38\x39\x3A\x43\x44". + "\x45\x46\x47\x48\x49". + "\x4A\x53\x54\x55\x56". + "\x57\x58\x59\x5A\x63". + "\x64\x65\x66\x67\x68". + "\x69\x6A\x73\x74\x75". + "\x76\x77\x78\x79\x7A". + "\x83\x84\x85\x86\x87". + "\x88\x89\x8A\x92\x93". + "\x94\x95\x96\x97\x98". + "\x99\x9A\xA2\xA3\xA4". + "\xA5\xA6\xA7\xA8\xA9". + "\xAA\xB2\xB3\xB4\xB5". + "\xB6\xB7\xB8\xB9\xBA". + "\xC2\xC3\xC4\xC5\xC6". + "\xC7\xC8\xC9\xCA\xD2". + "\xD3\xD4\xD5\xD6\xD7". + "\xD8\xD9\xDA\xE1\xE2". + "\xE3\xE4\xE5\xE6\xE7". + "\xE8\xE9\xEA\xF1\xF2". + "\xF3\xF4\xF5\xF6\xF7". + "\xF8\xF9\xFA". + # Define huffman table (section B.2.4.1) + "\xFF\xC4". # Marker + "\x00\x1F". # Length (31 bytes) + "\x01". # DC, (byte) table 1 + "\x00\x03\x01\x01\x01". + "\x01\x01\x01\x01\x01". + "\x01\x00\x00\x00\x00". + "\x00\x00\x01\x02\x03". + "\x04\x05\x06\x07\x08". + "\x09\x0A\x0B". + # Define huffman table (section B.2.4.1) + "\xFF\xC4". # Marker + "\x00\xB5". # Length (181 bytes) + "\x11". # AC, (byte) table 1 + "\x00\x02\x01\x02\x04". + "\x04\x03\x04\x07\x05". + "\x04\x04\x00\x01\x02". + "\x77\x00\x01\x02\x03". + "\x11\x04\x05\x21\x31". + "\x06\x12\x41\x51\x07". + "\x61\x71\x13\x22\x32". + "\x81\x08\x14\x42\x91". + "\xA1\xB1\xC1\x09\x23". + "\x33\x52\xF0\x15\x62". + "\x72\xD1\x0A\x16\x24". + "\x34\xE1\x25\xF1\x17". + "\x18\x19\x1A\x26\x27". + "\x28\x29\x2A\x35\x36". + "\x37\x38\x39\x3A\x43". + "\x44\x45\x46\x47\x48". + "\x49\x4A\x53\x54\x55". + "\x56\x57\x58\x59\x5A". + "\x63\x64\x65\x66\x67". + "\x68\x69\x6A\x73\x74". + "\x75\x76\x77\x78\x79". + "\x7A\x82\x83\x84\x85". + "\x86\x87\x88\x89\x8A". + "\x92\x93\x94\x95\x96". + "\x97\x98\x99\x9A\xA2". + "\xA3\xA4\xA5\xA6\xA7". + "\xA8\xA9\xAA\xB2\xB3". + "\xB4\xB5\xB6\xB7\xB8". + "\xB9\xBA\xC2\xC3\xC4". + "\xC5\xC6\xC7\xC8\xC9". + "\xCA\xD2\xD3\xD4\xD5". + "\xD6\xD7\xD8\xD9\xDA". + "\xE2\xE3\xE4\xE5\xE6". + "\xE7\xE8\xE9\xEA\xF2". + "\xF3\xF4\xF5\xF6\xF7". + "\xF8\xF9\xFA". +#------------------------------------------------------------------ + "\xFF\xDA". # Start of Scan marker + pack("nC11", + 12, # length + 3, # number of components + 1,0x00, # Scan 1: use DC/AC huff tables 0/0 + 2,0x11, # Scan 2: use DC/AC huff tables 1/1 + 3,0x11, # Scan 3: use DC/AC huff tables 1/1 + 0,0x3f, # Ss, Se + 0, # Ah, Ai (not used) + ); +#------------------------------------------------------------------ + + my $header = + # SOI + "\xFF\xD8". + # JFIF + "\xFF\xE0". + "\x00\x0e\x41\x56\x49\x31\x00\x00\x00\x00\x00\x00\x00\x00". + "\xff\xDD\x00\x04\x00\x00". + # quantization table + "\xFF\xDB". + "\x00\x43\x00\x21\x16\x18". + "\x1D\x18\x14\x21\x1D\x1B\x1D\x25". + "\x23\x21\x27\x31\x53\x36\x31\x2D". + "\x2D\x31\x65\x48\x4c\x3c\x53\x78". + "\x6a\x7e\x7c\x76\x6a\x74\x72\x85". + "\x95\xbf\xa2\x85\x8d\xb4\x8f\x72". + "\x74\xa6\xe2\xa8\xb4\xc5\xcb\xd6". + "\xd8\xd6\x80\xa0\xeb\xfb\xe8\xd0". + "\xf9\xbf\xd2\xd6\xcd". + # quantization table + "\xff\xdb". + "\x00\x43\x01\x23\x25\x25\x31\x2b\x31". + "\x61\x36\x36\x61\xcd\x89\x74\x89". + "\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd". + "\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd". + "\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd". + "\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd". + "\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd". + "\xcd\xcd\xcd\xcd\xcd\xcd\xcd\xcd". + "\xcd\xcd". + # Define huffman table (section B.2.4.1) + "\xFF\xC4". # Marker + "\x00\x1F". # Length (31 bytes) + "\x00". # DC luminance, table 0 + "\x00\x01\x05\x01\x01\x01\x01\x01\x01\x00\x00\x00\x00\x00\x00\x00". + "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0A\x0B". + # Define huffman table (section B.2.4.1) + "\xFF\xC4". # Marker + "\x00\x1F". # Length (31 bytes) + "\x01". # DC chrominance, table 1 + "\x00\x03\x01\x01\x01\x01\x01\x01\x01\x01\x01\x00". + "\x00\x00\x00\x00". + "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0A\x0B". + # Define huffman table (section B.2.4.1) + "\xFF\xC4". # Marker + "\x00\xB5". # Length (181 bytes) + "\x10". # AC luminance, table 0 + "\x00\x02\x01\x03\x03\x02\x04\x03\x05\x05\x04\x04\x00\x00\x01\x7D". + "\x01\x02\x03\x00\x04\x11\x05\x12". + "\x21\x31\x41\x06\x13\x51\x61\x07\x22\x71\x14\x32". + "\x81\x91\xA1\x08\x23\x42\xB1\xC1\x15\x52\xD1\xF0". + "\x24\x33\x62\x72\x82\x09\x0A\x16\x17\x18\x19\x1A". + "\x25\x26\x27\x28\x29\x2A\x34\x35\x36\x37\x38\x39". + "\x3A\x43\x44\x45\x46\x47\x48\x49\x4A\x53\x54\x55". + "\x56\x57\x58\x59\x5A\x63\x64\x65\x66\x67\x68\x69". + "\x6A\x73\x74\x75\x76\x77\x78\x79\x7A\x83\x84\x85". + "\x86\x87\x88\x89\x8A\x92\x93\x94\x95\x96\x97\x98". + "\x99\x9A\xA2\xA3\xA4\xA5\xA6\xA7\xA8\xA9\xAA\xB2". + "\xB3\xB4\xB5\xB6\xB7\xB8\xB9\xBA\xC2\xC3\xC4\xC5". + "\xC6\xC7\xC8\xC9\xCA\xD2\xD3\xD4\xD5\xD6\xD7\xD8". + "\xD9\xDA\xE1\xE2\xE3\xE4\xE5\xE6\xE7\xE8\xE9\xEA". + "\xF1\xF2\xF3\xF4\xF5\xF6\xF7\xF8\xF9\xFA". + #/* Define huffman table (section B.2.4.1) */ + "\xFF\xC4". # Marker + "\x00\xB5". # Length (181 bytes) + "\x11". # AC chrominance, table 1 + "\x00\x02\x01\x02\x04\x04\x03\x04\x07\x05\x04\x04". + "\x00\x01\x02\x77". + "\x00\x01\x02\x03\x11\x04\x05\x21". + "\x31\x06\x12\x41\x51\x07\x61\x71\x13\x22\x32\x81". + "\x08\x14\x42\x91\xA1\xB1\xC1\x09\x23\x33\x52\xF0". + "\x15\x62\x72\xD1\x0A\x16\x24\x34\xE1\x25\xF1\x17". + "\x18\x19\x1A\x26\x27\x28\x29\x2A\x35\x36\x37\x38". + "\x39\x3A\x43\x44\x45\x46\x47\x48\x49\x4A\x53\x54". + "\x55\x56\x57\x58\x59\x5A\x63\x64\x65\x66\x67\x68". + "\x69\x6A\x73\x74\x75\x76\x77\x78\x79\x7A\x82\x83". + "\x84\x85\x86\x87\x88\x89\x8A\x92\x93\x94\x95\x96". + "\x97\x98\x99\x9A\xA2\xA3\xA4\xA5\xA6\xA7\xA8\xA9". + "\xAA\xB2\xB3\xB4\xB5\xB6\xB7\xB8\xB9\xBA\xC2\xC3". + "\xC4\xC5\xC6\xC7\xC8\xC9\xCA\xD2\xD3\xD4\xD5\xD6". + "\xD7\xD8\xD9\xDA\xE2\xE3\xE4\xE5\xE6\xE7\xE8\xE9". + "\xEA\xF2\xF3\xF4\xF5\xF6\xF7\xF8\xF9\xFA". + # start of frame + "\xff\xc0". + "\x00\x11\x08". + pack("nn", 120, 160). + "\x03\x01\x21\x00\x02\x11\x01\x03\x11\x01". + # + "\xff\xda". + "\x00\x0c\x03\x01\x00\x02\x11\x03\x11". + "\x00\x3f\x00"; + + if ( $dump ) { + warn "## created JPEG header...\n"; + hex_dump( $header, 0 ); + } + + print $fh $header || die "can't write header into $path: $!"; + print $fh $data || die "can't write frame into $path: $!"; + close $fh || die "can't close $path: $!"; + print ">> created $path ", -s $path, " bytes\n"; +} + +my ( $riff, $amv ) = x(12, 'Z4x4Z4'); +die "$path not RIFF but $riff" if $riff ne 'RIFF'; +die "$path not AMV but $amv" if $amv ne 'AMV '; while ( ! defined($d->{eof}) ) { my ( $list, $name ) = x(12,'A4x4A4'); die "not LIST but $list" if $list ne 'LIST'; - print "> $list .. $name\n"; + print "< $list * $name\n"; if ( $name eq 'hdrl' ) { @@ -108,7 +455,7 @@ } x($len, 'Vx28VVVx8CCv'); printf "## %s %d*%d %s fps (%d ms/frame) %02d:%02d:%02d\n", - $h->{path}, + $path, $h->{width}, $h->{height}, $h->{fps}, $h->{ms_per_frame}, $h->{hh}, $h->{mm}, $h->{ss}; @@ -124,12 +471,13 @@ while (1) { my $frame = $d->{movi}++; - my $len = next_part( '00dc', 0, 1 ); + my $len = next_part( '00dc' ); last unless $len; - printf ">> %s 00dc - frame %d jpeg %d 0x%x bytes\n", $name, $frame, $len, $len; + printf "<< %s 00dc - frame %d jpeg %d 0x%x bytes\n", $name, $frame, $len, $len; + mkjpg( sprintf("$dump_dir/%03d.jpg", $frame ), x($len) ); - my $len = next_part( '01wb', 0, 1 ); - printf ">> %s 01wb - frame %d audio %d 0x%x bytes\n", $name, $frame, $len, $len; + $len = next_part( '01wb', 0, 1 ); + printf "<< %s 01wb - frame %d audio %d 0x%x bytes\n", $name, $frame, $len, $len; }; } else {