| 1 |
.\" -*- mode: troff; coding: utf-8 -*- |
| 2 |
.\" Automatically generated by Pod::Man 5.0102 (Pod::Simple 3.45) |
| 3 |
.\" |
| 4 |
.\" Standard preamble: |
| 5 |
.\" ======================================================================== |
| 6 |
.de Sp \" Vertical space (when we can't use .PP) |
| 7 |
.if t .sp .5v |
| 8 |
.if n .sp |
| 9 |
.. |
| 10 |
.de Vb \" Begin verbatim text |
| 11 |
.ft CW |
| 12 |
.nf |
| 13 |
.ne \\$1 |
| 14 |
.. |
| 15 |
.de Ve \" End verbatim text |
| 16 |
.ft R |
| 17 |
.fi |
| 18 |
.. |
| 19 |
.\" \*(C` and \*(C' are quotes in nroff, nothing in troff, for use with C<>. |
| 20 |
.ie n \{\ |
| 21 |
. ds C` "" |
| 22 |
. ds C' "" |
| 23 |
'br\} |
| 24 |
.el\{\ |
| 25 |
. ds C` |
| 26 |
. ds C' |
| 27 |
'br\} |
| 28 |
.\" |
| 29 |
.\" Escape single quotes in literal strings from groff's Unicode transform. |
| 30 |
.ie \n(.g .ds Aq \(aq |
| 31 |
.el .ds Aq ' |
| 32 |
.\" |
| 33 |
.\" If the F register is >0, we'll generate index entries on stderr for |
| 34 |
.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index |
| 35 |
.\" entries marked with X<> in POD. Of course, you'll have to process the |
| 36 |
.\" output yourself in some meaningful fashion. |
| 37 |
.\" |
| 38 |
.\" Avoid warning from groff about undefined register 'F'. |
| 39 |
.de IX |
| 40 |
.. |
| 41 |
.nr rF 0 |
| 42 |
.if \n(.g .if rF .nr rF 1 |
| 43 |
.if (\n(rF:(\n(.g==0)) \{\ |
| 44 |
. if \nF \{\ |
| 45 |
. de IX |
| 46 |
. tm Index:\\$1\t\\n%\t"\\$2" |
| 47 |
.. |
| 48 |
. if !\nF==2 \{\ |
| 49 |
. nr % 0 |
| 50 |
. nr F 2 |
| 51 |
. \} |
| 52 |
. \} |
| 53 |
.\} |
| 54 |
.rr rF |
| 55 |
.\" ======================================================================== |
| 56 |
.\" |
| 57 |
.IX Title "Encode::GSM0338 3perl" |
| 58 |
.TH Encode::GSM0338 3perl 2025-11-16 "perl v5.40.1" "Perl Programmers Reference Guide" |
| 59 |
.\" For nroff, turn off justification. Always turn off hyphenation; it makes |
| 60 |
.\" way too many mistakes in technical documents. |
| 61 |
.if n .ad l |
| 62 |
.nh |
| 63 |
.SH NAME |
| 64 |
Encode::GSM0338 \-\- ETSI GSM 03.38 Encoding |
| 65 |
.SH SYNOPSIS |
| 66 |
.IX Header "SYNOPSIS" |
| 67 |
.Vb 3 |
| 68 |
\& use Encode qw/encode decode/; |
| 69 |
\& $gsm0338 = encode("gsm0338", $unicode); # loads Encode::GSM0338 implicitly |
| 70 |
\& $unicode = decode("gsm0338", $gsm0338); # ditto |
| 71 |
.Ve |
| 72 |
.SH DESCRIPTION |
| 73 |
.IX Header "DESCRIPTION" |
| 74 |
GSM0338 is for GSM handsets. Though it shares alphanumerals with ASCII, |
| 75 |
control character ranges and other parts are mapped very differently, |
| 76 |
mainly to store Greek characters. There are also escape sequences |
| 77 |
(starting with 0x1B) to cover e.g. the Euro sign. |
| 78 |
.PP |
| 79 |
This was once handled by Encode::Bytes but because of all those |
| 80 |
unusual specifications, Encode 2.20 has relocated the support to |
| 81 |
this module. |
| 82 |
.PP |
| 83 |
This module implements only \fIGSM 7 bit Default Alphabet\fR and |
| 84 |
\&\fIGSM 7 bit default alphabet extension table\fR according to standard |
| 85 |
3GPP TS 23.038 version 16. Therefore \fINational Language Single Shift\fR |
| 86 |
and \fINational Language Locking Shift\fR are not implemented nor supported. |
| 87 |
.SS Septets |
| 88 |
.IX Subsection "Septets" |
| 89 |
This modules operates with octets (like any other Encode module) and not |
| 90 |
with packed septets (unlike other GSM standards). Therefore for processing |
| 91 |
binary SMS or parts of GSM TPDU payload (3GPP TS 23.040) it is needed to do |
| 92 |
conversion between octets and packed septets. For this purpose perl's \f(CW\*(C`pack\*(C'\fR |
| 93 |
and \f(CW\*(C`unpack\*(C'\fR functions may be useful: |
| 94 |
.PP |
| 95 |
.Vb 2 |
| 96 |
\& $bytes = substr(pack(\*(Aq(b*)*\*(Aq, unpack \*(Aq(A7)*\*(Aq, unpack \*(Aqb*\*(Aq, $septets), 0, $num_of_septets); |
| 97 |
\& $unicode = decode(\*(AqGSM0338\*(Aq, $bytes); |
| 98 |
\& |
| 99 |
\& $bytes = encode(\*(AqGSM0338\*(Aq, $unicode); |
| 100 |
\& $septets = pack \*(Aqb*\*(Aq, join \*(Aq\*(Aq, map { substr $_, 0, 7 } unpack \*(Aq(A8)*\*(Aq, unpack \*(Aqb*\*(Aq, $bytes; |
| 101 |
\& $num_of_septets = length $bytes; |
| 102 |
.Ve |
| 103 |
.PP |
| 104 |
Please note that for correct decoding of packed septets it is required to |
| 105 |
know number of septets packed in binary buffer as binary buffer is always |
| 106 |
padded with zero bits and 7 zero bits represents character \f(CW\*(C`@\*(C'\fR. Number |
| 107 |
of septets is also stored in TPDU payload when dealing with 3GPP TS 23.040. |
| 108 |
.SH BUGS |
| 109 |
.IX Header "BUGS" |
| 110 |
Encode::GSM0338 2.7 and older versions (part of Encode 3.06) incorrectly |
| 111 |
handled zero bytes (character \f(CW\*(C`@\*(C'\fR). This was fixed in Encode::GSM0338 |
| 112 |
version 2.8 (part of Encode 3.07). |
| 113 |
.SH "SEE ALSO" |
| 114 |
.IX Header "SEE ALSO" |
| 115 |
3GPP TS 23.038 <https://www.3gpp.org/dynareport/23038.htm> |
| 116 |
.PP |
| 117 |
ETSI TS 123 038 V16.0.0 (2020\-07) <https://www.etsi.org/deliver/etsi_ts/123000_123099/123038/16.00.00_60/ts_123038v160000p.pdf> |
| 118 |
.PP |
| 119 |
Encode |