Expand ECI support and enforce binary mode when ECI is set

backend/dotcode.c

@@ -1213,6 +1213,11 @@ int dotcode(struct zint_symbol *symbol, const unsigned char source[], int length
     unsigned char* codeword_array = (unsigned char *) _alloca(length * 3 * sizeof (unsigned char));
 #endif /* _MSC_VER */
     
+    if (symbol->eci > 811799) {
+        strcpy(symbol->errtxt, "Invalid ECI");
+        return ZINT_ERROR_INVALID_OPTION;
+    }
+
     data_length = dotcode_encode_message(symbol, source, length, codeword_array, &binary_finish);
 
     ecc_length = 3 + (data_length / 2);

backend/gridmtx.c

@@ -1054,6 +1054,11 @@ int grid_matrix(struct zint_symbol *symbol, const unsigned char source[], size_t
 
     if (symbol->output_options & READER_INIT) reader = 1;
     
+    if (symbol->eci > 811799) {
+        strcpy(symbol->errtxt, "Invalid ECI");
+        return ZINT_ERROR_INVALID_OPTION;
+    }
+
     error_number = gm_encode(gbdata, length, binary, reader, symbol->eci, symbol->debug);
     if (error_number != 0) {
         strcpy(symbol->errtxt, "Input data too long (E31)");

backend/library.c

@@ -485,7 +485,6 @@ static int supports_eci(const int symbology) {
         case BARCODE_DOTCODE:
         case BARCODE_GRIDMATRIX:
         case BARCODE_HANXIN:
-        case BARCODE_UPNQR:
             result = 1;
             break;
     }
@@ -992,6 +991,10 @@ int ZBarcode_Encode(struct zint_symbol *symbol, const unsigned char *source,int
         symbol->input_mode = DATA_MODE;
     }
     
+    if (symbol->eci != 3) {
+        symbol->input_mode = DATA_MODE;
+    }
+
     if (symbol->input_mode == GS1_MODE) {
         for (i = 0; i < in_length; i++) {
             if (source[i] == '\0') {

backend/pdf417.c

@@ -559,12 +559,10 @@ void numbprocess(int *chainemc, int *mclength, char chaine[], int start, int len
 /* 366 */
 static int pdf417(struct zint_symbol *symbol, unsigned char chaine[], const size_t length) {
     int i, k, j, indexchaine, indexliste, mode, longueur, loop, mccorrection[520], offset;
-    int total, chainemc[2700], mclength, c1, c2, c3, dummy[35], codeerr;
+    int total, chainemc[2700], mclength, c1, c2, c3, dummy[35];
     char pattern[580];
     int debug = symbol->debug;
 
-    codeerr = 0;
-
     /* 456 */
     indexliste = 0;
     indexchaine = 0;
@@ -639,6 +637,11 @@ static int pdf417(struct zint_symbol *symbol, unsigned char chaine[], const size
         }
     }
     
+    if (symbol->eci > 811799) {
+        strcpy(symbol->errtxt, "Invalid ECI");
+        return ZINT_ERROR_INVALID_OPTION;
+    }
+    
     for (i = 0; i < indexliste; i++) {
         switch (liste[1][i]) {
             case TEX: /* 547 - text mode */
@@ -821,7 +824,7 @@ static int pdf417(struct zint_symbol *symbol, unsigned char chaine[], const size
     symbol->width =(int)strlen(pattern);
 
     /* 843 */
-    return codeerr;
+    return 0;
 }
 
 /* 345 */
@@ -863,6 +866,9 @@ int pdf417enc(struct zint_symbol *symbol, unsigned char source[], const size_t l
                 strcpy(symbol->errtxt, "Data too long for specified number of columns (D65)");
                 error_number = ZINT_ERROR_TOO_LONG;
                 break;
+            case ZINT_ERROR_INVALID_OPTION:
+                error_number = codeerr;
+                break;
             default:
                 strcpy(symbol->errtxt, "Something strange happened (D66)");
                 error_number = ZINT_ERROR_ENCODING_PROBLEM;
@@ -936,6 +942,11 @@ int micro_pdf417(struct zint_symbol *symbol, unsigned char chaine[], const size_
         mclength++;
     }
     
+    if (symbol->eci > 811799) {
+        strcpy(symbol->errtxt, "Invalid ECI");
+        return ZINT_ERROR_INVALID_OPTION;
+    }
+    
     if (symbol->eci != 3) {
         /* Encoding ECI assignment number, according to Table 8 */
         if (symbol->eci <= 899) {

docs/manual.txt

@@ -424,9 +424,8 @@ The --binary option prevents Zint from performing any convertion of the data
 before placing in the barcode symbol and should be used if you are encoding raw 
 binary or encrypted data.
 
-If your platform does not use Unicode or if you are using data from file which 
+If you are using data from file which is not UTF-8 formatted then you can 
-is not stored in UTF-8 then you can specify the encoding by using the --binary 
+specify the encoding by using the --eci= switch followed by the appropriate number 
-switch in combination with the --eci= switch followed by the appropriate number 
 from the table below. This procedure adds an ECI flag in the barcode data which 
 tells the barcode reader to change character encoding.
 
@@ -448,13 +447,25 @@ ECI Code  |  Character Encoding Scheme
 16        |  ISO-8859-14 - Latin alphabet No. 8 (Celtic)
 17        |  ISO-8859-15 - Latin alphabet No. 9
 18        |  ISO-8859-16 - Latin alphabet No. 10
+20 *      |  Shift-JIS (JISX 0208 amd JISX 0201)
 21        |  Windows-1250 - Latin 2 (Central Europe)
 22        |  Windows-1251 - Cyrillic
 23        |  Windows-1252 - Latin 1
 24        |  Windows-1256 - Arabic
+25 *      |  UCS-2 Unicode (High order byte first)
 26        |  Unicode (UTF-8)
+27        |  ISO-646:1991 7-bit character set
+28 *      |  Big-5 (Taiwan) Chinese Character Set
+29 *      |  GB (PRC) Chinese Character Set
+30 *      |  Korean Character Set (KSX1001:1998)
 --------------------------------------------------------
 
+* Note: When using the ECI flag Zint will treat all input data as raw binary.
+This means that data which is encoded using a multiple-byte encoding schemes
+(other than UTF-8) will not use optimal compression. It is therefore
+recommended that data using these schemes be converted to UTF-8 using iconv
+or similar before passing it to Zint.
+
 4.11 Batch processing
 ---------------------
 Data can be batch processed by reading from a text file and producing a 
@@ -553,7 +564,7 @@ options available, and also gives the exact version of the software.
 The -t or --types option gives the table of symbologies along with the symbol
 ID numbers.
 
-The -e or --ecinos option gives a list of the ECI codes supported by Zint.
+The -e or --ecinos option gives a list of the ECI codes.
 
 4.16 Other output options
 -------------------------

frontend/main.c

@@ -134,11 +134,18 @@ void show_eci(void) {
             "16: ISO-8859-14 - Latin alphabet No. 8 (Celtic)\n"
             "17: ISO-8859-15 - Latin alphabet No. 9\n"
             "18: ISO-8859-16 - Latin alphabet No. 10\n"
+            "20: ** Shift-JIS (JISX 0208 amd JISX 0201)\n"
             "21: Windows-1250\n"
             "22: Windows-1251\n"
             "23: Windows-1252\n"
             "24: Windows-1256\n"
+            "25: ** UCS-2 Unicode (High order byte first)\n"
             "26: Unicode (UTF-8)\n"
+            "27: ISO-646:1991 7-bit character set\n"
+            "28: ** Big-5 (Taiwan) Chinese Character Set\n"
+            "29: ** GB (PRC) Chinese Character Set\n"
+            "30: ** Korean Character Set (KSX1001:1998)\n"
+            "** See note in section 4.10 of the manual"
     );
 }
 
@@ -683,7 +690,7 @@ int main(int argc, char **argv) {
                     strncpy(filetype, optarg, (size_t) 3);
                 }
                 if (!strcmp(long_options[option_index].name, "eci")) {
-                    if ((atoi(optarg) >= 0) && (atoi(optarg) <= 30)) {
+                    if ((atoi(optarg) >= 0) && (atoi(optarg) <= 999999)) {
                         my_symbol->eci = atoi(optarg);
                     } else {
                         fprintf(stderr, "Invalid ECI code (A18)\n");