Detect-It-Easy/db/read
2023-01-03 09:11:02 +01:00

176 lines
6.6 KiB
Text

// Supplemental read functions.
// Authors: unknown guy, Kaens (TG @kaens)
// Lots of legacy,
// TODO update the old scripts to use the new functions,
// and get rid of the functions themselves
const _BE = true; const _LE = false; //endianness for read_uint16+
//little-endian = reversed notation (Intel),
//big-endian = direct notation (TCP/IP, Motorola, Amiga, ZX Spectrum)
// ---------- START OF PRE-v3.06 CODE --------------------
/**
* Read a big-endian word.
* @param {UInt} nOffset - The offset in the file.
* @returns {UShort} The word value.
* @alias Binary.readBEWord
*/
File.readBEWord = function(nOffset)
{
return File.read_uint16(nOffset,_BE)
// return (File.readByte(nOffset) << 8) + File.readByte(nOffset+1);
}
/**
* Read a big-endian dword.
* @param {UInt} nOffset - The offset in the file.
* @returns {UInt} The dword value.
* @alias Binary.readBEDword
*/
File.readBEDword = function(nOffset)
{
return File.read_uint32(nOffset,_BE)
}
/**
* Read a word, selecting endianness.
* @param {UInt} nOffset - The offset in the file.
* @param {Bool} bBE - True for big-endian.
* @returns {UShort} The word value.
* @alias Binary.readEWord
*/
File.readEWord = function(nOffset,bBE)
{
return File.read_uint16(nOffset,bBE)
}
/**
* Read a dword, selecting endianness.
* @param {UInt} nOffset - The offset in the file.
* @param {Bool} bBE - True for big-endian.
* @returns {UInt} The dword value.
* @alias Binary.readEDWord
*/
File.readEDword = function(nOffset,bBE)
{
return File.read_uint16(nOffset,bBE)
}
/**
* Read a short (signed 16-bit) value.
* @param {UInt} nOffset - The offset in the file.
* @returns {Short} The short value.
* @alias Binary.readShort
*/
File.readShort = function(nOffset)
{
return File.read_int16(nOffset,_LE)
}
// -------- END OF PRE-v3.06 CODE
const CP437="ÇüéâäàåçêëèïîìÄÅÉæÆôöòûùÿÖÜ¢£¥₧ƒáíóúñѪº¿⌐¬½¼¡«»░▒▓│┤╡╢╖╕╣║╗╝╜╛"+
"┐└┴┬├─┼╞╟╚╔╩╦╠═╬╧╨╤╥╙╘╒╓╫╪┘┌█▄▌▐▀αßΓπΣσµτΦΘΩδ∞φε∩≡±≥≤⌠⌡÷≈°∙·√ⁿ²■ ";
const JISX0201="→-‚ƒ„…†‡ˆ‰Š‹Œ↑޳™‘’“”•–—˜™š›œ¢žŸ"+//decided to mix it with cp1252
"→。「」、・ヲァィゥェォャュョッーアイウエカキクケコサシスセソタチツテトナニヌネノハヒフヘホマミムメモヤユヨラリルレロワン゙゚"+
"àáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ"
/**
* Derive a string hexadecimal value, zero-padded.
* @param {Int} a - the numerical value.
* @param {UInt} padz (optional,default=2) - how many characters to zero-pad.
* @returns {String} The hex value, capital letters A~F, ending with "h".
*/
function Hex(a,padz) {
if(padz==undefined) padz=2;
var minus=""; if(a<0) { a=-a; minus="-" }
var r = a.toString(16).toUpperCase(); var pads="";
if(r.length < padz) pads = Array(1 + padz - r.length).join('0');
return minus+pads+r+"h"
}
/**
* Read a byte array from file.
* @param {UInt} ofs - the offset to start from.
* @param {ByteArray} len - the amount of bytes to read.
* @returns {[uint8]} The file slice. If you go beyond EoF, read_uint8 only knows what happens.
*/
function readBytes(ofs,len) { //for now; feels like this should be a system function
var s=[];
for (i=0;i<len;i++) s.push(File.read_uint8(ofs+i));
return s;
}
/**
* Decode a 1-byte encoding from a byte array using the 128-byte-long table given.
* @param {[uint8]} ansi - an array returned by readBytes.
* @param {String[0x80]} dectbl - a decoding table; just make a const here in db/read for that
* @param {bool} zstop (optional, default=true) - whether to stop reading on 0 (ASCIIZ behaviour)
* @returns {String} a string value usable with js.
*/
function decEncoding(ansi,dectbl,zstop) {
if(zstop==undefined) zstop=true;
var s=""; var bit8=0;
for(i=0; i<ansi.length; i++)
if ((ansi[i]==0) && zstop) break; else
if(ansi[i] < 0x80)
switch(ansi[i]) { // 7-bit variation processing
case 0x0E: if(dectbl == "JISX0201") bit8=0x80; break;
case 0x0F: if(dectbl == "JISX0201") bit8=0; break;
case 0x5C: if(dectbl == "JISX0201") s+="¥"; break;
case 0x7E: if(dectbl == "JISX0201") s+="‾"; break;
default: s += String.fromCharCode(bit8+ansi[i]);
}
else s+=dectbl[ansi[i]-0x80];
return s;
}
/**
* Decode a 1-byte encoding from file using the 128-byte-long table given.
* @param {UInt} ofs - the offset to start from.
* @param {ByteArray} len - the amount of bytes to read.
* @param {String[0x80]} dectbl - a decoding table; just make a const here in db/read for that
* @param {bool} zstop (optional, default=true) - whether to stop reading on 0 (ASCIIZ behaviour)
* @returns {String} a string value usable with js.
*/
function decAnsi(ofs,len,dectbl,zstop) {
var s="";
if(zstop==undefined) zstop=true;
for (i=0;i<len;i++) {
b = Binary.read_uint8(ofs+i);
if ((b==0) && zstop) break; else
if(b < 0x80) s+=String.fromCharCode(b);
else s+=dectbl[b-0x80];
}
return s;
}
/**
* sOptions.append a string (optionally prefixed) if the space-trimmed string is not empty.
* @param {variant} a - the string to output (safe to accidentally drop a non-string in)
* @param {String} prefix (optional) - what to put in front of the output string
*/
function sOptionT(a,prefix) { if ((""+a).trim() != "")
if(prefix != undefined) sOptions = sOptions.append(prefix+a.trim())
else sOptions = sOptions.append((""+a).trim()) }
/**
* sOptions.append a string (optionally prefixed) if the string is not empty.
* @param {variant} a - the string to output (safe to accidentally drop a non-string in)
* @param {String} prefix (optional) - what to put in front of the output string
*/
function sOption(a,prefix) { if ((""+a) != "")
if(prefix != undefined) sOptions = sOptions.append(prefix+a)
else sOptions = sOptions.append(""+a) }
/**
* A shorthand for the situation where you compare the file suffix to what you'd expect. Use as the option to isHeuristicScan being true.
* @param {String} a - the expected file suffix, case-insensitive, no heading period unlike Python
* @returns {bool} if a match is reached
*/
function extIs(a) { return Binary.getFileSuffix().toLowerCase() == a.toLowerCase() }