Improvement to Shift_JIS encoding detector to avoid detecting some UTF-8 strings...

[zxing.git] / core / src / com / google / zxing / qrcode / decoder / DecodedBitStreamParser.java

diff --git a/core/src/com/google/zxing/qrcode/decoder/DecodedBitStreamParser.java b/core/src/com/google/zxing/qrcode/decoder/DecodedBitStreamParser.java
index 16bfb62..c3a440b 100644 (file)
--- a/core/src/com/google/zxing/qrcode/decoder/DecodedBitStreamParser.java
+++ b/core/src/com/google/zxing/qrcode/decoder/DecodedBitStreamParser.java
@@ -80,12 +80,15 @@ final class DecodedBitStreamParser {
         if (mode.equals(Mode.FNC1_FIRST_POSITION) || mode.equals(Mode.FNC1_SECOND_POSITION)) {
           // We do little with FNC1 except alter the parsed result a bit according to the spec
           fc1InEffect = true;
+        } else if (mode.equals(Mode.STRUCTURED_APPEND)) {
+          // not really supported; all we do is ignore it
+          // Read next 8 bits (symbol sequence #) and 8 bits (parity data), then continue
+          bits.readBits(16);
         } else if (mode.equals(Mode.ECI)) {
           // Count doesn't apply to ECI
-          try {
-            int value = parseECIValue(bits);
-            currentCharacterSetECI = CharacterSetECI.getCharacterSetECIByValue(value);
-          } catch (IllegalArgumentException iae) {
+          int value = parseECIValue(bits);
+          currentCharacterSetECI = CharacterSetECI.getCharacterSetECIByValue(value);
+          if (currentCharacterSetECI == null) {
             throw ReaderException.getInstance();
           }
         } else {
@@ -282,10 +285,9 @@ final class DecodedBitStreamParser {
       if (!lastWasPossibleDoubleByteStart && ((value >= 0xF0 && value <= 0xFF) || value == 0x80 || value == 0xA0)) {
         canBeShiftJIS = false;
       }
-      if (((value >= 0x81 && value <= 0x9F) || (value >= 0xE0 && value <= 0xEF)) && i < length - 1) {
+      if (((value >= 0x81 && value <= 0x9F) || (value >= 0xE0 && value <= 0xEF))) {
         // These start double-byte characters in Shift_JIS. Let's see if it's followed by a valid
         // second byte.
-        sawDoubleByteStart = true;
         if (lastWasPossibleDoubleByteStart) {
           // If we just checked this and the last byte for being a valid double-byte
           // char, don't check starting on this byte. If this and the last byte
@@ -296,12 +298,18 @@ final class DecodedBitStreamParser {
           // ... otherwise do check to see if this plus the next byte form a valid
           // double byte pair encoding a character.
           lastWasPossibleDoubleByteStart = true;
-          int nextValue = bytes[i + 1] & 0xFF;
-          if (nextValue < 0x40 || nextValue > 0xFC) {
+          if (i >= bytes.length - 1) {
             canBeShiftJIS = false;
+          } else {
+            int nextValue = bytes[i + 1] & 0xFF;
+            if (nextValue < 0x40 || nextValue > 0xFC) {
+              canBeShiftJIS = false;
+            } else {
+              sawDoubleByteStart = true;
+            }
+            // 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.
           }
-          // 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.
         }
       } else {
         lastWasPossibleDoubleByteStart = false;