forked from osmocom/wireshark
Update documentation to reflect removal of tvb_get_unicode_string*, full
support for (correct) UTF-16, and new string encodings. svn path=/trunk/; revision=54320
This commit is contained in:
parent
2af870ce4c
commit
ab9aa3c859
|
@ -256,7 +256,6 @@ void tvb_get_guid(tvbuff_t *tvb, const gint offset, e_guid_t *guid, const guint
|
|||
String accessors:
|
||||
|
||||
guint8 *tvb_get_string(wmem_allocator_t *scope, tvbuff_t *tvb, const gint offset, const gint length);
|
||||
gchar *tvb_get_unicode_string(wmem_allocator_t *scope, tvbuff_t *tvb, const gint offset, gint length, const guint encoding);
|
||||
guint8 *tvb_get_string_enc(wmem_allocator_t *scope, tvbuff_t *tvb, const gint offset, const gint length, const guint encoding);
|
||||
|
||||
Returns a null-terminated buffer containing data from the specified
|
||||
|
@ -268,15 +267,13 @@ tvb_get_string() returns a buffer allocated by g_malloc() if scope is set
|
|||
to NULL (in that case memory must be explicitely freed), or with the
|
||||
allocator lifetime if scope is not NULL.
|
||||
|
||||
tvb_get_unicode_string() is a unicode (UTF-16) version of above. This
|
||||
is intended for reading UTF-16 unicode strings out of a tvbuff and
|
||||
returning them as a UTF-8 string for use in Wireshark. The offset and
|
||||
returned length pointer are in bytes, not UTF-16 characters.
|
||||
tvb_get_string_enc() is a version of tvb_get_string() that takes a
|
||||
string encoding as an argument. See below for a list of encoding values
|
||||
for strings.
|
||||
|
||||
guint8 *tvb_get_stringz(wmem_allocator_t *scope, tvbuff_t *tvb, const gint offset, gint *lengthp);
|
||||
guint8 *tvb_get_stringz_enc(wmem_allocator_t *scope, tvbuff_t *tvb, const gint offset, gint *lengthp, const guint encoding);
|
||||
const guint8 *tvb_get_const_stringz(tvbuff_t *tvb, const gint offset, gint *lengthp);
|
||||
gchar *tvb_get_unicode_stringz(wmem_allocator_t *scope, tvbuff_t *tvb, const gint offset, gint *lengthp, const guint encoding);
|
||||
gint tvb_get_nstringz(tvbuff_t *tvb, const gint offset, const guint bufsize, guint8* buffer);
|
||||
gint tvb_get_nstringz0(tvbuff_t *tvb, const gint offset, const guint bufsize, guint8* buffer);
|
||||
|
||||
|
@ -290,19 +287,15 @@ tvb_get_stringz() returns a buffer allocated by g_malloc() if scope is set
|
|||
to NULL (in that case memory must be explicitely freed), or with the
|
||||
allocator lifetime if scope is not NULL.
|
||||
|
||||
tvb_get_stringz_enc() is a version of tvb_get_stringz() that takes a
|
||||
string encoding as an argument. See below for a list of encoding values
|
||||
for strings.
|
||||
|
||||
tvb_get_const_stringz() returns a pointer to the (const) string in the tvbuff.
|
||||
You do not need to free() this buffer, it will happen automatically once the
|
||||
next packet is dissected. This function is slightly more efficient than the
|
||||
others because it does not allocate memory and copy the string.
|
||||
|
||||
tvb_get_unicode_stringz() is a unicode (UTF-16) version of above.
|
||||
This is intended for reading UTF-16 unicode strings out of a tvbuff
|
||||
and returning them as a UTF-8 string for use in Wireshark. The offset and
|
||||
returned length pointer are in bytes, not UTF-16 characters.
|
||||
|
||||
tvb_get_faked_unicode() has been superseded by tvb_get_string(), which
|
||||
properly handles Unicode (UTF-16) strings by converting them to UTF-8.
|
||||
|
||||
Byte Array Accessors:
|
||||
|
||||
gchar *tvb_bytes_to_str(tvbuff_t *tvb, gint offset, gint len);
|
||||
|
@ -1371,13 +1364,16 @@ currently supported are:
|
|||
ENC_ASCII - ASCII (currently treated as UTF-8; in the future,
|
||||
all bytes with the 8th bit set will be treated as
|
||||
errors)
|
||||
ENC_UTF_8 - UTF-8
|
||||
ENC_UCS_2 - UCS-2
|
||||
ENC_UTF_16 - UTF-16 (currently treated as UCS-2; in the future,
|
||||
surrogate pairs will be handled, and non-valid 16-bit
|
||||
code points and surrogate pairs will be treated as
|
||||
errors)
|
||||
ENC_UTF_8 - UTF-8-encoded Unicode
|
||||
ENC_UTF_16 - UTF-16-encoded Unicode, with surrogate pairs
|
||||
ENC_UCS_2 - UCS-2-encoded subset of Unicode, with no surrogate pairs
|
||||
and thus no code points above 0xFFFF
|
||||
ENC_EBCDIC - EBCDIC
|
||||
ENC_WINDOWS_1250 - Windows-1250 code page
|
||||
ENC_ISO_8859_1 - ISO 8859-1
|
||||
ENC_ISO_8859_2 - ISO 8859-2
|
||||
ENC_ISO_8859_5 - ISO 8859-5
|
||||
ENC_ISO_8859_9 - ISO 8859-9
|
||||
|
||||
Other encodings will be added in the future.
|
||||
|
||||
|
|
Loading…
Reference in New Issue