TShark: Add a "-E bom=" option.

Add an option to print the UTF-8 BOM.

Change-Id: I3d30c67852b9b89d1548b0f957d97fd8e8741049
Reviewed-on: https://code.wireshark.org/review/15318
Petri-Dish: Gerald Combs <gerald@wireshark.org>
Tested-by: Petri Dish Buildbot <buildbot-no-reply@wireshark.org>
Reviewed-by: Jaap Keuter <jaap.keuter@xs4all.nl>
Reviewed-by: Gerald Combs <gerald@wireshark.org>

doc/tshark.pod

@@ -309,6 +309,9 @@ selected.
 
 Options are:
 
+B<bom=y|n> If B<y>, prepend output with the UTF-8 byte order mark
+(hexadecimal ef, bb, bf). Defaults to B<n>.
+
 B<header=y|n> If B<y>, print a list of the field names given using B<-e>
 as the first line of the output; the field name will be separated using
 the same character as the field values.  Defaults to B<n>.

epan/print.c

@@ -68,6 +68,7 @@ typedef struct {
 } write_field_data_t;
 
 struct _output_fields {
+    gboolean     print_bom;
     gboolean     print_header;
     gchar        separator;
     gchar        occurrence;
@@ -1199,6 +1200,19 @@ gboolean output_fields_set_option(output_fields_t *info, gchar *option)
         }
         return TRUE;
     }
+    else if (0 == strcmp(option_name, "bom")) {
+        switch (*option_value) {
+        case 'n':
+            info->print_bom = FALSE;
+            break;
+        case 'y':
+            info->print_bom = TRUE;
+            break;
+        default:
+            return FALSE;
+        }
+        return TRUE;
+    }
 
     return FALSE;
 }
@@ -1206,6 +1220,7 @@ gboolean output_fields_set_option(output_fields_t *info, gchar *option)
 void output_fields_list_options(FILE *fh)
 {
     fprintf(fh, "TShark: The available options for field output \"E\" are:\n");
+    fputs("bom=y|n    Prepend output with the UTF-8 BOM (def: N: no)\n", fh);
     fputs("header=y|n    Print field abbreviations as first line of output (def: N: no)\n", fh);
     fputs("separator=/t|/s|<character>   Set the separator to use;\n     \"/t\" = tab, \"/s\" = space (def: /t: tab)\n", fh);
     fputs("occurrence=f|l|a  Select the occurrence of a field to use;\n     \"f\" = first, \"l\" = last, \"a\" = all (def: a: all)\n", fh);
@@ -1227,6 +1242,11 @@ void write_fields_preamble(output_fields_t* fields, FILE *fh)
     g_assert(fh);
     g_assert(fields->fields);
 
+    if (fields->print_bom) {
+        fputs(UTF8_BOM, fh);
+    }
+
+
     if (!fields->print_header) {
         return;
     }
@@ -1491,6 +1511,7 @@ get_field_hex_value(GSList *src_list, field_info *fi)
 output_fields_t* output_fields_new(void)
 {
     output_fields_t* fields     = g_new(output_fields_t, 1);
+    fields->print_bom           = FALSE;
     fields->print_header        = FALSE;
     fields->separator           = '\t';
     fields->occurrence          = 'a';

tshark.c

@@ -377,6 +377,7 @@ print_usage(FILE *output)
   fprintf(output, "                           _ws.col.Info)\n");
   fprintf(output, "                           this option can be repeated to print multiple fields\n");
   fprintf(output, "  -E<fieldsoption>=<value> set options for output when -Tfields selected:\n");
+  fprintf(output, "     bom=y|n               print a UTF-8 BOM\n");
   fprintf(output, "     header=y|n            switch headers on and off\n");
   fprintf(output, "     separator=/t|/s|<char> select tab, space, printable character as separator\n");
   fprintf(output, "     occurrence=f|l|a      print first, last or all occurrences of each field\n");

wsutil/utf8_entities.h

@@ -58,6 +58,9 @@
 #define UTF8_BALLOT_X                   "\xe2\x9c\x97"      /* 10007 / 0x2717 */
 #define UTF8_LONG_RIGHTWARDS_ARROW      "\xe2\x9f\xb6"      /* 10230 / 0x27f6 */
 
+#define UTF8_ZERO_WIDTH_NO_BREAK_SPACE  "\xef\xbb\xbf"      /* 65279 / 0xffef */
+#define UTF8_BOM UTF8_ZERO_WIDTH_NO_BREAK_SPACE
+
 #endif /* __UTF8_ENTITIES_H__ */
 
 /*