Add a get_ebcdic_string() routine, similar to other get_XXX_string() routines.

Use it in epan/tvbuff.c.

Do some other cleanups while we're at it.

Change-Id: I7aed37a568373b896aacfd23f986d445b58b77b7
Reviewed-on: https://code.wireshark.org/review/1342
Reviewed-by: Guy Harris <guy@alum.mit.edu>

1 files changed, 153 insertions, 128 deletions

diff --git a/epan/charsets.c b/epan/charsets.c
index d3e61b00af..5a97dd5caa 100644
--- a/epan/charsets.c
+++ b/epan/charsets.c
@@ -62,119 +62,6 @@
  *    http://www-03.ibm.com/systems/i/software/globalization/codepages.html
  */
 
-/* ASCII/EBCDIC conversion tables from
- * http://www.room42.com/store/computer_center/code_tables.shtml
- */
-#if 0
-static guint8 ASCII_translate_EBCDIC [ 256 ] = {
-    0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08,
-    0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
-    0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18,
-    0x19, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F,
-    0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D,
-    0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
-    0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8,
-    0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
-    0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8,
-    0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
-    0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
-    0xE8, 0xE9, 0xAD, 0xE0, 0xBD, 0x5F, 0x6D,
-    0x7D, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88,
-    0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
-    0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7,
-    0xA8, 0xA9, 0xC0, 0x6A, 0xD0, 0xA1, 0x4B,
-    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
-    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
-    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
-    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
-    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
-    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
-    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
-    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
-    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
-    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
-    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
-    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
-    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
-    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
-    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
-    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B
-};
-
-void
-ASCII_to_EBCDIC(guint8 *buf, guint bytes)
-{
-    guint    i;
-    guint8    *bufptr;
-
-    bufptr = buf;
-
-    for (i = 0; i < bytes; i++, bufptr++) {
-        *bufptr = ASCII_translate_EBCDIC[*bufptr];
-    }
-}
-
-guint8
-ASCII_to_EBCDIC1(guint8 c)
-{
-    return ASCII_translate_EBCDIC[c];
-}
-#endif
-
-static guint8 EBCDIC_translate_ASCII [ 256 ] = {
-    0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08,
-    0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
-    0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18,
-    0x19, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F,
-    0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28,
-    0x29, 0x2A, 0x2B, 0x2C, 0x2D, 0x2E, 0x2F,
-    0x2E, 0x2E, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38,
-    0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x2E, 0x3F,
-    0x20, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
-    0x2E, 0x2E, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
-    0x26, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
-    0x2E, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0x5E,
-    0x2D, 0x2F, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
-    0x2E, 0x7C, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
-    0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
-    0x2E, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
-    0x2E, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68,
-    0x69, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
-    0x2E, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71,
-    0x72, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
-    0x2E, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79,
-    0x7A, 0x2E, 0x2E, 0x2E, 0x5B, 0x2E, 0x2E,
-    0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
-    0x2E, 0x2E, 0x2E, 0x2E, 0x5D, 0x2E, 0x2E,
-    0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48,
-    0x49, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
-    0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51,
-    0x52, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
-    0x5C, 0x2E, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59,
-    0x5A, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
-    0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38,
-    0x39, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E
-};
-
-void
-EBCDIC_to_ASCII(guint8 *buf, guint bytes)
-{
-    guint   i;
-    guint8 *bufptr;
-
-    bufptr = buf;
-
-    for (i = 0; i < bytes; i++, bufptr++) {
-        *bufptr = EBCDIC_translate_ASCII[*bufptr];
-    }
-}
-
-guint8
-EBCDIC_to_ASCII1(guint8 c)
-{
-    return EBCDIC_translate_ASCII[c];
-}
-
 /*
  * Given a wmem scope, a pointer, and a length, treat the string of bytes
  * referred to by the pointer and length as an ASCII string, with all bytes
@@ -207,8 +94,8 @@ get_ascii_string(wmem_allocator_t *scope, const guint8 *ptr, gint length)
 
 /*
  * Given a wmem scope, a pointer, and a length, treat the string of bytes
- * referred to by them as an ISO 8859/1 string, and return a pointer to a
- * UTF-8 string, allocated using the wmem scope.
+ * referred to by the pointer and length as an ISO 8859/1 string, and
+ * return a pointer to a UTF-8 string, allocated using the wmem scope.
  */
 guint8 *
 get_8859_1_string(wmem_allocator_t *scope, const guint8 *ptr, gint length)
@@ -587,12 +474,12 @@ const gunichar2 charset_table_cp437[0x80] = {
 
 /*
  * Given a wmem scope, a pointer, and a length, and a translation table,
- * treat the string of bytes referred to by them as a string encoded
- * using one octet per character, with octets with the high-order bit
- * clear being ASCII and octets with the high-order bit set being
- * mapped by the translation table to 2-byte Unicode Basic Multilingual
- * Plane characters (including REPLACEMENT CHARACTER), and return a
- * pointer to a UTF-8 string, allocated using the wmem scope.
+ * treat the string of bytes referred to by the pointer and length as a
+ * string encoded using one octet per character, with octets with the
+ * high-order bit clear being ASCII and octets with the high-order bit
+ * set being mapped by the translation table to 2-byte Unicode Basic
+ * Multilingual Plane characters (including REPLACEMENT CHARACTER), and
+ * return a pointer to a UTF-8 string, allocated using the wmem scope.
  */
 guint8 *
 get_unichar2_string(wmem_allocator_t *scope, const guint8 *ptr, gint length, const gunichar2 table[0x80])
@@ -617,9 +504,10 @@ get_unichar2_string(wmem_allocator_t *scope, const guint8 *ptr, gint length, con
 
 /*
  * Given a wmem scope, a pointer, and a length, treat the string of bytes
- * referred to by them as a UCS-2 encoded string containing characters
- * from the Basic Multilingual Plane (plane 0) of Unicode, return a
- * pointer to a UTF-8 string, allocated with the wmem scope.
+ * referred to by the pointer and length as a UCS-2 encoded string
+ * containing characters from the Basic Multilingual Plane (plane 0) of
+ * Unicode, and return a pointer to a UTF-8 string, allocated with the
+ * wmem scope.
  *
  * Encoding parameter should be ENC_BIG_ENDIAN or ENC_LITTLE_ENDIAN.
  *
@@ -657,8 +545,8 @@ get_ucs_2_string(wmem_allocator_t *scope, const guint8 *ptr, gint length, const
 
 /*
  * Given a wmem scope, a pointer, and a length, treat the string of bytes
- * referred to by them as a UTF-16 encoded string, return a pointer to
- * a UTF-8 string, allocated with the wmem scope.
+ * referred to by the pointer and length as a UTF-16 encoded string, and
+ * return a pointer to a UTF-8 string, allocated with the wmem scope.
  *
  * Encoding parameter should be ENC_BIG_ENDIAN or ENC_LITTLE_ENDIAN.
  *
@@ -748,8 +636,8 @@ get_utf_16_string(wmem_allocator_t *scope, const guint8 *ptr, gint length, const
 
 /*
  * Given a wmem scope, a pointer, and a length, treat the string of bytes
- * referred to by them as a UCS-4 encoded string, return a pointer to
- * a UTF-8 string, allocated with the wmem scope.
+ * referred to by the pointer and length as a UCS-4 encoded string, and
+ * return a pointer to a UTF-8 string, allocated with the wmem scope.
  *
  * Encoding parameter should be ENC_BIG_ENDIAN or ENC_LITTLE_ENDIAN
  *
@@ -1009,6 +897,143 @@ get_ascii_7bits_string(wmem_allocator_t *scope, const guint8 *ptr,
 	return (guint8 *)wmem_strbuf_finalize(strbuf);
 }
 
+/* ASCII/EBCDIC conversion tables from
+ * http://www.room42.com/store/computer_center/code_tables.shtml
+ */
+#if 0
+static guint8 ASCII_translate_EBCDIC [ 256 ] = {
+    0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08,
+    0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
+    0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18,
+    0x19, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F,
+    0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D,
+    0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
+    0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7, 0xF8,
+    0xF9, 0x7A, 0x5E, 0x4C, 0x7E, 0x6E, 0x6F,
+    0x7C, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7, 0xC8,
+    0xC9, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6,
+    0xD7, 0xD8, 0xD9, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
+    0xE8, 0xE9, 0xAD, 0xE0, 0xBD, 0x5F, 0x6D,
+    0x7D, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88,
+    0x89, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96,
+    0x97, 0x98, 0x99, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7,
+    0xA8, 0xA9, 0xC0, 0x6A, 0xD0, 0xA1, 0x4B,
+    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
+    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
+    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
+    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
+    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
+    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
+    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
+    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
+    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
+    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
+    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
+    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
+    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
+    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
+    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B,
+    0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B, 0x4B
+};
+
+void
+ASCII_to_EBCDIC(guint8 *buf, guint bytes)
+{
+    guint    i;
+    guint8    *bufptr;
+
+    bufptr = buf;
+
+    for (i = 0; i < bytes; i++, bufptr++) {
+        *bufptr = ASCII_translate_EBCDIC[*bufptr];
+    }
+}
+
+guint8
+ASCII_to_EBCDIC1(guint8 c)
+{
+    return ASCII_translate_EBCDIC[c];
+}
+#endif
+
+static guint8 EBCDIC_translate_ASCII [ 256 ] = {
+    0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08,
+    0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
+    0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18,
+    0x19, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F,
+    0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28,
+    0x29, 0x2A, 0x2B, 0x2C, 0x2D, 0x2E, 0x2F,
+    0x2E, 0x2E, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38,
+    0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x2E, 0x3F,
+    0x20, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
+    0x2E, 0x2E, 0x2E, 0x3C, 0x28, 0x2B, 0x7C,
+    0x26, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
+    0x2E, 0x21, 0x24, 0x2A, 0x29, 0x3B, 0x5E,
+    0x2D, 0x2F, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
+    0x2E, 0x7C, 0x2C, 0x25, 0x5F, 0x3E, 0x3F,
+    0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
+    0x2E, 0x3A, 0x23, 0x40, 0x27, 0x3D, 0x22,
+    0x2E, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68,
+    0x69, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
+    0x2E, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, 0x70, 0x71,
+    0x72, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
+    0x2E, 0x7E, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79,
+    0x7A, 0x2E, 0x2E, 0x2E, 0x5B, 0x2E, 0x2E,
+    0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
+    0x2E, 0x2E, 0x2E, 0x2E, 0x5D, 0x2E, 0x2E,
+    0x7B, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48,
+    0x49, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
+    0x7D, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, 0x50, 0x51,
+    0x52, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
+    0x5C, 0x2E, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59,
+    0x5A, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E,
+    0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38,
+    0x39, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E, 0x2E
+};
+
+void
+EBCDIC_to_ASCII(guint8 *buf, guint bytes)
+{
+    guint   i;
+    guint8 *bufptr;
+
+    bufptr = buf;
+
+    for (i = 0; i < bytes; i++, bufptr++) {
+        *bufptr = EBCDIC_translate_ASCII[*bufptr];
+    }
+}
+
+guint8
+EBCDIC_to_ASCII1(guint8 c)
+{
+    return EBCDIC_translate_ASCII[c];
+}
+
+/*
+ * Given a wmem scope, a pointer, and a length, and a translation table,
+ * treat the string of bytes referred to by the pointer and length as a
+ * string encoded in EBCDIC using one octet per character, and return a
+ * pointer to a UTF-8 string, allocated using the wmem scope.
+ */
+guint8 *
+get_ebcdic_string(wmem_allocator_t *scope, const guint8 *ptr, gint length)
+{
+	wmem_strbuf_t *str;
+
+	str = wmem_strbuf_sized_new(scope, length+1, 0);
+
+	while (length > 0) {
+		guint8 ch = *ptr;
+
+		wmem_strbuf_append_unichar(str, EBCDIC_translate_ASCII[ch]);
+		ptr++;
+		length--;
+	}
+
+	return (guint8 *) wmem_strbuf_finalize(str);
+}
+
 /*
  * Editor modelines  -  http://www.wireshark.org/tools/modelines.html
  *