Re-Implementing SHPHack

[MarkSheppard]

I've been reimplementing SHP Ed functions in HTML5/Javascript as a way to modernize it and teach myself more programming skills.

However, I'm hitting a blank wall when it comes to the SHP decompression code.

I've got access to Fred's old SHPEd source code (see attached); and I think I've identified the decryption routine in SPF.cpp:

//---------------------------------------------------------------------------
// read the shp data (for icon n) into the pseudo image
// this does not use the header info for lines, but reads
// until it finds KEY BYTE 88 Next byte 0.
void __fastcall read_SPicon_shp(FILE *inf, int n)
{
int ch,b,r,i,l=0;
long fpos;

fseek(inf,icon_add[n]+HEADER_SIZE,0);
pix_pos=0;
far_right=0;
far_bottom=0;
do
{
// read data and decode
ch=fgetc(inf);

//==== this section checks for end =====
if (ch==-1) break;// for last image this is end of shp
fgetpos(inf,&fpos);
if ((n<(icons-1)) && fpos>icon_add[n+1]) break;
// ==== end of end check ===========
r=ch%2;
b=ch/2;
if (b==0 && r==1) // a skip over
{
ch=fgetc(inf);
for (i=0; i put_pix(l,BACK_COLOR);
if (pix_pos>far_right) far_right=pix_pos;
}
else if (b==0) // end of line
{
++l;
pix_pos=0;
}
else if (r==0) // a run of bytes
{
ch=fgetc(inf); // the color #
for (i=0; i put_pix(l,ch);
if (pix_pos>far_right) far_right=pix_pos;
}
else // b!0 and r==1 ... read the next b bytes as color #'s
{
for (i=0; i {
ch=fgetc(inf);
put_pix(l,ch);
}
if (pix_pos>far_right) far_right=pix_pos;
}
} while (true); //exit this loop with break
far_bottom=l;
}

I'm thinking that it decodes as:

Read Character

R = Character % 2
B = Character / 2

###########

EOF Test:
If Character EQUAL TO -1 break, this is End of SHP.

##########

TEST ONE:

IF B equals 0 AND R equals 1
(I think Char = 1, which returns B = 0.5 and R = 1)

We have a huge string of blank pixels coming up.

Read the next character in the file. That character is the number of pixels that we paint as the transparent background color.

############

TEST TWO:

If B equals 0

End of SHP Line -- I think this used to mark the end of each row in the SHP file, i.e. incremeting from y = 0 to y =1 and so on.

###########

TEST THREE:

IF R equals 0

Read the next character in the file; that character is the color index number from the palette.

We then paint a number of pixels equal to "B" with that color we just grabbed.

##############

TEST FOUR:

IF B NOT ZERO and R EQUAL ONE

Read the next [b] bytes as color numbers?

Basically this says that the next B characters are direct image colors; probably used to save space when you have a lot of different characters, to avoid the use of space wasting couplets.

[Mobhack]

see the attatched document extracted from the VFX library documentation

cheers
Andy

[Karagin]

Interesting...this sounds like fun and headaches but fun at the same time.

[MarkSheppard]

Originally Posted by Mobhack

see the attatched document extracted from the VFX library documentation

cheers
Andy

It took me a few moments to figure out what that was.

All this time, I thought SSI basically developed the SHP standard "in house".

I guess by the early 1990s, things had become complicated enough that for graphics libraries, it was simpler to buy the middleware graphics package from Miles Design?

...that makes sense the more I think about it, given that:

A.) SP1 and SP2 had silly video sequences to show off CDROM capability, and those must have been early Smacker/RAD video codecs.

B.) The 3 million and one different video cards and sound cards at the time, all with their own competing standards.

[DRG]

The main point is Fred figured this all out just before we started converting SP2 into SP2WW2 and the work I did and feedback allowed him to iron out the final little issues and this is AFAIK the only game still actively using SHP and LBM and what we have now works and it "ain't broke" and there is little need for improving it although I have slightly tweaked it for this next release.....but only a tweak