Re: retriving escape unicode sequences from files ...
On 8/4/2012 1:47 PM, qwertmonkey@syberianoutpost.ru wrote:
~
I would use your pattern matcher but instead of
"Character.toString((char)Integer.parseInt" ... stuff, I would use a look-up
table
~
You could.
But I am not sure that it is practical.
Here is the outline of my code:
~
// __
private HashMap<String, Integer> HMHex2Int;
// __
private final String aRegXPtrn = "\\\\u([0-9a-f]{4})";
private final Pattern UKdRegX = Pattern.compile(aRegXPtrn,
Pattern.CASE_INSENSITIVE);
// __
private final String[] aHex2ByteTbl = new String[]{
"00", "01", "02", "03", "04", "05", "06", "07",
"08", "09", "0a", "0b", "0c", "0d", "0e", "0f",
"10", "11", "12", "13", "14", "15", "16", "17",
"18", "19", "1a", "1b", "1c", "1d", "1e", "1f",
"20", "21", "22", "23", "24", "25", "26", "27",
"28", "29", "2a", "2b", "2c", "2d", "2e", "2f",
"30", "31", "32", "33", "34", "35", "36", "37",
"38", "39", "3a", "3b", "3c", "3d", "3e", "3f",
"40", "41", "42", "43", "44", "45", "46", "47",
"48", "49", "4a", "4b", "4c", "4d", "4e", "4f",
"50", "51", "52", "53", "54", "55", "56", "57",
"58", "59", "5a", "5b", "5c", "5d", "5e", "5f",
"60", "61", "62", "63", "64", "65", "66", "67",
"68", "69", "6a", "6b", "6c", "6d", "6e", "6f",
"70", "71", "72", "73", "74", "75", "76", "77",
"78", "79", "7a", "7b", "7c", "7d", "7e", "7f",
"80", "81", "82", "83", "84", "85", "86", "87",
"88", "89", "8a", "8b", "8c", "8d", "8e", "8f",
"90", "91", "92", "93", "94", "95", "96", "97",
"98", "99", "9a", "9b", "9c", "9d", "9e", "9f",
"a0", "a1", "a2", "a3", "a4", "a5", "a6", "a7",
"a8", "a9", "aa", "ab", "ac", "ad", "ae", "af",
"b0", "b1", "b2", "b3", "b4", "b5", "b6", "b7",
"b8", "b9", "ba", "bb", "bc", "bd", "be", "bf",
"c0", "c1", "c2", "c3", "c4", "c5", "c6", "c7",
"c8", "c9", "ca", "cb", "cc", "cd", "ce", "cf",
"d0", "d1", "d2", "d3", "d4", "d5", "d6", "d7",
"d8", "d9", "da", "db", "dc", "dd", "de", "df",
"e0", "e1", "e2", "e3", "e4", "e5", "e6", "e7",
"e8", "e9", "ea", "eb", "ec", "ed", "ee", "ef",
"f0", "f1", "f2", "f3", "f4", "f5", "f6", "f7",
"f8", "f9", "fa", "fb", "fc", "fd", "fe", "ff"
};
~
// __ ctor
~
HMHex2Int = new HashMap<String, Integer>();
for(int i = 0; (i < aHex2ByteTbl.length); ++i){ HMHex2Int.put(aHex2ByteTbl[i], HMHex2Int.size()); }
~
then:
~
// __ converts from \(\)u#### (front slash u sequences not turn to strings by the compiler) to unikd
public String unescapeHex2String(String aFSU) throws UnsupportedEncodingException{
StringBuilder aBldr = null;
// __
int iFSUL;
if((aFSU != null) && ((iFSUL = aFSU.length()) > 0)){
int[] iHex = new int[2];
int iHexArL = iHex.length;
String aUKdS;
aBldr = new StringBuilder();
// __
Matcher UKdRegXMtx = UKdRegX.matcher(aFSU);
// __
while (UKdRegXMtx.find()){
aUKdS = aFSU.substring((UKdRegXMtx.start() + 2), UKdRegXMtx.end());
// __
for(int j = 0; (j < iHexArL); ++j){ iHex[j] = HMHex2Byte.get(aUKdS.substring(2*j, 2*(j + 1)).toLowerCase()).intValue(); }// j [0, iHexArL)
// __
aBldr.append((char)(16*iHex[0] + iHex[1]));
}
}// ((aFSU != null) && ((iFSUL = aFSU.length()) > 0))
// __
return(aBldr.toString());
}
~
But:
1) the code is difficult to read
2) HMHex2Byte is not declared - it probably is HMHex2Int
3) it seems as if you lookup 4 bit values in an 8 bit table??
4) the code does not handle code points >255
Arne