Move print_hex_data_buffer() to wsutil

Move this generic function to wsutil so it can be used
by other libraries.

5 files changed, 12 insertions, 237 deletions

diff --git a/epan/charsets.c b/epan/charsets.c
index 6cc7b7b0a2..094e63791c 100644
--- a/epan/charsets.c
+++ b/epan/charsets.c
@@ -1343,119 +1343,6 @@ get_ascii_7bits_string(wmem_allocator_t *scope, const guint8 *ptr,
     return (guint8 *)wmem_strbuf_finalize(strbuf);
 }
 
-/* ASCII/EBCDIC conversion tables from
- * https://web.archive.org/web/20060813174742/http://www.room42.com/store/computer_center/code_tables.shtml
- */
-#if 0
-static const 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 const 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];
-}
-
 /* Tables for EBCDIC code pages */
 
 /* EBCDIC common; based on the table in appendix H of ESA/370 Principles
diff --git a/epan/charsets.h b/epan/charsets.h
index 7502afd374..3bafc0131a 100644
--- a/epan/charsets.h
+++ b/epan/charsets.h
@@ -230,15 +230,6 @@ get_euc_kr_string(wmem_allocator_t *scope, const guint8 *ptr, gint length);
 WS_DLL_PUBLIC guint8 *
 get_t61_string(wmem_allocator_t *scope, const guint8 *ptr, gint length);
 
-#if 0
-void ASCII_to_EBCDIC(guint8 *buf, guint bytes);
-guint8 ASCII_to_EBCDIC1(guint8 c);
-#endif
-WS_DLL_PUBLIC
-void EBCDIC_to_ASCII(guint8 *buf, guint bytes);
-WS_DLL_PUBLIC
-guint8 EBCDIC_to_ASCII1(guint8 c);
-
 #ifdef __cplusplus
 }
 #endif /* __cplusplus */
diff --git a/epan/print.c b/epan/print.c
index e9811fb87c..574e70b60a 100644
--- a/epan/print.c
+++ b/epan/print.c
@@ -30,6 +30,7 @@
 #include <wsutil/json_dumper.h>
 #include <wsutil/filesystem.h>
 #include <wsutil/utf8_entities.h>
+#include <wsutil/str_util.h>
 #include <wsutil/ws_assert.h>
 #include <ftypes/ftypes.h>
 
@@ -2022,112 +2023,18 @@ print_hex_data(print_stream_t *stream, epan_dissect_t *edt, guint hexdump_option
     return TRUE;
 }
 
-/*
- * This routine is based on a routine created by Dan Lasley
- * <DLASLEY@PROMUS.com>.
- *
- * It was modified for Wireshark by Gilbert Ramirez and others.
- */
-
-#define MAX_OFFSET_LEN   8       /* max length of hex offset of bytes */
-#define BYTES_PER_LINE  16      /* max byte values printed on a line */
-#define HEX_DUMP_LEN    (BYTES_PER_LINE*3)
-                                /* max number of characters hex dump takes -
-                                   2 digits plus trailing blank */
-#define DATA_DUMP_LEN   (HEX_DUMP_LEN + 2 + 2 + BYTES_PER_LINE)
-                                /* number of characters those bytes take;
-                                   3 characters per byte of hex dump,
-                                   2 blanks separating hex from ASCII,
-                                   2 optional ASCII dump delimiters,
-                                   1 character per byte of ASCII dump */
-#define MAX_LINE_LEN    (MAX_OFFSET_LEN + 2 + DATA_DUMP_LEN)
-                                /* number of characters per line;
-                                   offset, 2 blanks separating offset
-                                   from data dump, data dump */
-
-static gboolean
-print_hex_data_buffer(print_stream_t *stream, const guchar *cp,
-                      guint length, packet_char_enc encoding, guint ascii_option)
+static gboolean print_hex_data_line(void *stream, const char *line)
 {
-    register unsigned int ad, i, j, k, l;
-    guchar                c;
-    gchar                 line[MAX_LINE_LEN + 1];
-    unsigned int          use_digits;
-
-    static gchar binhex[16] = {
-        '0', '1', '2', '3', '4', '5', '6', '7',
-        '8', '9', 'a', 'b', 'c', 'd', 'e', 'f'};
-
-    /*
-     * How many of the leading digits of the offset will we supply?
-     * We always supply at least 4 digits, but if the maximum offset
-     * won't fit in 4 digits, we use as many digits as will be needed.
-     */
-    if (((length - 1) & 0xF0000000) != 0)
-        use_digits = 8; /* need all 8 digits */
-    else if (((length - 1) & 0x0F000000) != 0)
-        use_digits = 7; /* need 7 digits */
-    else if (((length - 1) & 0x00F00000) != 0)
-        use_digits = 6; /* need 6 digits */
-    else if (((length - 1) & 0x000F0000) != 0)
-        use_digits = 5; /* need 5 digits */
-    else
-        use_digits = 4; /* we'll supply 4 digits */
-
-    ad = 0;
-    i = 0;
-    j = 0;
-    k = 0;
-    while (i < length) {
-        if ((i & 15) == 0) {
-            /*
-             * Start of a new line.
-             */
-            j = 0;
-            l = use_digits;
-            do {
-                l--;
-                c = (ad >> (l*4)) & 0xF;
-                line[j++] = binhex[c];
-            } while (l != 0);
-            line[j++] = ' ';
-            line[j++] = ' ';
-            memset(line+j, ' ', DATA_DUMP_LEN);
+    return print_line(stream, 0, line);
+}
 
-            /*
-             * Offset in line of ASCII dump.
-             */
-            k = j + HEX_DUMP_LEN + 2;
-            if (ascii_option == HEXDUMP_ASCII_DELIMIT)
-                line[k++] = '|';
-        }
-        c = *cp++;
-        line[j++] = binhex[c>>4];
-        line[j++] = binhex[c&0xf];
-        j++;
-        if (ascii_option != HEXDUMP_ASCII_EXCLUDE ) {
-            if (encoding == PACKET_CHAR_ENC_CHAR_EBCDIC) {
-                c = EBCDIC_to_ASCII1(c);
-            }
-            line[k++] = ((c >= ' ') && (c < 0x7f)) ? c : '.';
-        }
-        i++;
-        if (((i & 15) == 0) || (i == length)) {
-            /*
-             * We'll be starting a new line, or
-             * we're finished printing this buffer;
-             * dump out the line we've constructed,
-             * and advance the offset.
-             */
-            if (ascii_option == HEXDUMP_ASCII_DELIMIT)
-                line[k++] = '|';
-            line[k] = '\0';
-            if (!print_line(stream, 0, line))
-                return FALSE;
-            ad += 16;
-        }
-    }
-    return TRUE;
+static gboolean print_hex_data_buffer(print_stream_t *stream, const guchar *cp,
+                                      guint length, packet_char_enc encoding,
+                                      guint hexdump_options)
+{
+    return hex_dump_buffer(print_hex_data_line, stream, cp, length,
+                        encoding == PACKET_CHAR_ENC_CHAR_EBCDIC ? HEXDUMP_ENC_EBCDIC : HEXDUMP_ENC_ASCII,
+                        hexdump_options);
 }
 
 gsize output_fields_num_fields(output_fields_t* fields)
diff --git a/epan/print.h b/epan/print.h
index 7b31b0f9a0..9473611cd3 100644
--- a/epan/print.h
+++ b/epan/print.h
@@ -82,17 +82,6 @@ WS_DLL_PUBLIC gboolean proto_tree_print(print_dissections_e print_dissections,
                                         print_stream_t *stream);
 
 /*
- * Hexdump options for ASCII:
- */
-
-#define HEXDUMP_ASCII_MASK            (0x0003U)
-#define HEXDUMP_ASCII_OPTION(option)  ((option) & HEXDUMP_ASCII_MASK)
-
-#define HEXDUMP_ASCII_INCLUDE         (0x0000U) /* include ASCII section no delimiters (legacy tshark behavior) */
-#define HEXDUMP_ASCII_DELIMIT         (0x0001U) /* include ASCII section with delimiters, useful for reliable detection of last hexdata */
-#define HEXDUMP_ASCII_EXCLUDE         (0x0002U) /* exclude ASCII section from hexdump reports, if we really don't want or need it */
-
-/*
  * Hexdump option for displaying data sources:
  */
 
diff --git a/epan/print_stream.h b/epan/print_stream.h
index d41d4f10ba..63c73efb62 100644
--- a/epan/print_stream.h
+++ b/epan/print_stream.h
@@ -16,6 +16,7 @@
 #include "ws_symbol_export.h"
 
 #include <wsutil/color.h>
+#include <wsutil/str_util.h>
 
 #ifdef __cplusplus
 extern "C" {