mudhorn/zxing
1
0
Fork 0
mirror of https://github.com/zxing/zxing.git synced 2025-03-05 20:48:51 -08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Another tweak to get some valid ISO-8859-1 strings like "frédéric" to be guessed correctly

Browse source 
git-svn-id: https://zxing.googlecode.com/svn/trunk@1021 59b500cc-1b3d-0410-9834-0bbf25fbcc57
This commit is contained in:
srowen 2009-07-17 09:30:46 +00:00
parent 38f73bca64
commit 636c00e844
1 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
core/src/com/google/zxing/qrcode/decoder/DecodedBitStreamParser.java
View file

@ -258,7 +258,7 @@ final class DecodedBitStreamParser {
int length = bytes.length; int length = bytes.length;
boolean canBeISO88591 = true; boolean canBeISO88591 = true;
boolean canBeShiftJIS = true; boolean canBeShiftJIS = true;
boolean sawDoubleByteStart = false; int maybeDoubleByteCount = 0;
int maybeSingleByteKatakanaCount = 0; int maybeSingleByteKatakanaCount = 0;
boolean sawLatin1Supplement = false; boolean sawLatin1Supplement = false;
boolean lastWasPossibleDoubleByteStart = false; boolean lastWasPossibleDoubleByteStart = false;
@ -305,7 +305,7 @@ final class DecodedBitStreamParser {
if (nextValue < 0x40 || nextValue > 0xFC) { if (nextValue < 0x40 || nextValue > 0xFC) {
canBeShiftJIS = false; canBeShiftJIS = false;
} else { } else {
sawDoubleByteStart = true; maybeDoubleByteCount++;
} }
// There is some conflicting information out there about which bytes can follow which in // There is some conflicting information out there about which bytes can follow which in
// double-byte Shift_JIS characters. The rule above seems to be the one that matches practice. // double-byte Shift_JIS characters. The rule above seems to be the one that matches practice.
@ -317,10 +317,10 @@ final class DecodedBitStreamParser {
} }
// Distinguishing Shift_JIS and ISO-8859-1 can be a little tough. The crude heuristic is: // Distinguishing Shift_JIS and ISO-8859-1 can be a little tough. The crude heuristic is:
// - If we saw // - If we saw
// - at least one byte that starts a double-byte value (bytes that are rare in ISO-8859-1), or // - at least three byte that starts a double-byte value (bytes that are rare in ISO-8859-1), or
// - over 5% of bytes that could be single-byte Katakana (also rare in ISO-8859-1), // - over 5% of bytes that could be single-byte Katakana (also rare in ISO-8859-1),
// - and, saw no sequences that are invalid in Shift_JIS, then we conclude Shift_JIS // - and, saw no sequences that are invalid in Shift_JIS, then we conclude Shift_JIS
if (canBeShiftJIS && (sawDoubleByteStart || 20 * maybeSingleByteKatakanaCount > length)) { if (canBeShiftJIS && (maybeDoubleByteCount >= 3 || 20 * maybeSingleByteKatakanaCount > length)) {
return SHIFT_JIS; return SHIFT_JIS;
} }
// Otherwise, we default to ISO-8859-1 unless we know it can't be // Otherwise, we default to ISO-8859-1 unless we know it can't be