[M] Change in pysim[master]: support UCS-2 characters in EF.MMSUP, EF.ADN, EF.SPN, EF.PNN, EF.ECC

laforge has submitted this change. ( https://gerrit.osmocom.org/c/pysim/+/35453?usp=email ) Change subject: support UCS-2 characters in EF.MMSUP, EF.ADN, EF.SPN, EF.PNN, EF.ECC ...................................................................... support UCS-2 characters in EF.MMSUP, EF.ADN, EF.SPN, EF.PNN, EF.ECC Now that we have support for the UCS-2 encoding as per TS 102 221 Annex A, we can start to make use of it from various file constructs. As some specs say "Either 7-bit GSM or UCS-2" we also introduce a related automatic GsmOrUcs2Adapter and GsmOrUcs2String class. Change-Id: I4eb8aea0a13260a143e2c60fca73c3c4312fd3b2 --- M pySim/construct.py M pySim/ts_31_102.py M pySim/ts_51_011.py 3 files changed, 56 insertions(+), 4 deletions(-) Approvals: fixeria: Looks good to me, but someone else must approve Jenkins Builder: Verified laforge: Looks good to me, approved diff --git a/pySim/construct.py b/pySim/construct.py index 778a878..1ed3576 100644 --- a/pySim/construct.py +++ b/pySim/construct.py @@ -48,6 +48,29 @@ def _encode(self, obj, context, path): return codecs.encode(obj, "utf-8") +class GsmOrUcs2Adapter(Adapter): + """Try to encode into a GSM 03.38 string; if that fails, fall back to UCS-2 as described + in TS 102 221 Annex A.""" + def _decode(self, obj, context, path): + # In case the string contains only 0xff bytes we interpret it as an empty string + if obj == b'\xff' * len(obj): + return "" + # one of the magic bytes of TS 102 221 Annex A + if obj[0] in [0x80, 0x81, 0x82]: + ad = Ucs2Adapter(GreedyBytes) + else: + ad = GsmString(GreedyBytes) + return ad._decode(obj, context, path) + + def _encode(self, obj, context, path): + # first try GSM 03.38; then fall back to TS 102 221 Annex A UCS-2 + try: + ad = GsmString(GreedyBytes) + return ad._encode(obj, context, path) + except: + ad = Ucs2Adapter(GreedyBytes) + return ad._encode(obj, context, path) + class Ucs2Adapter(Adapter): """convert a bytes() type that contains UCS2 encoded characters encoded as defined in TS 102 221 Annex A to normal python string representation (and back).""" @@ -447,6 +470,20 @@ ''' return GsmStringAdapter(Rpad(Bytes(n), pattern=b'\xff'), codec='gsm03.38') +def GsmOrUcs2String(n): + ''' + GSM 03.38 or UCS-2 (TS 102 221 Annex A) encoded byte string of fixed length n. + Encoder appends padding bytes (b'\\xff') to maintain + length. Decoder removes those trailing bytes. + + Exceptions are raised for invalid characters + and length excess. + + Parameters: + n (Integer): Fixed length of the encoded byte string + ''' + return GsmOrUcs2Adapter(Rpad(Bytes(n), pattern=b'\xff')) + class GreedyInteger(Construct): """A variable-length integer implementation, think of combining GrredyBytes with BytesInteger.""" def __init__(self, signed=False, swapped=False, minlen=0): diff --git a/pySim/ts_31_102.py b/pySim/ts_31_102.py index 16526c2..1a35cb7 100644 --- a/pySim/ts_31_102.py +++ b/pySim/ts_31_102.py @@ -529,7 +529,7 @@ cc_construct = BcdAdapter(Rpad(Bytes(3))) category_construct = FlagsEnum(Byte, police=1, ambulance=2, fire_brigade=3, marine_guard=4, mountain_rescue=5, manual_ecall=6, automatic_ecall=7) - alpha_construct = GsmStringAdapter(Rpad(GreedyBytes)) + alpha_construct = GsmOrUcs2Adapter(Rpad(GreedyBytes)) def __init__(self, fid='6fb7', sfid=0x01, name='EF.ECC', desc='Emergency Call Codes'): diff --git a/pySim/ts_51_011.py b/pySim/ts_51_011.py index 422b35e..6523769 100644 --- a/pySim/ts_51_011.py +++ b/pySim/ts_51_011.py @@ -145,7 +145,7 @@ def __init__(self, fid='6f3a', sfid=None, name='EF.ADN', desc='Abbreviated Dialing Numbers', ext=1, **kwargs): super().__init__(fid, sfid=sfid, name=name, desc=desc, rec_len=(14, 30), **kwargs) ext_name = 'ext%u_record_id' % ext - self._construct = Struct('alpha_id'/COptional(GsmStringAdapter(Rpad(Bytes(this._.total_len-14)), codec='ascii')), + self._construct = Struct('alpha_id'/COptional(GsmOrUcs2Adapter(Rpad(Bytes(this._.total_len-14)))), 'len_of_bcd'/Int8ub, 'ton_npi'/TonNpi, 'dialing_nr'/ExtendedBcdAdapter(BcdAdapter(Rpad(Bytes(10)))), @@ -514,7 +514,7 @@ 'hide_in_oplmn'/Flag, 'show_in_hplmn'/Flag, # Bytes 2..17 - 'spn'/Bytewise(GsmString(16)) + 'spn'/Bytewise(GsmOrUcs2String(16)) ) # TS 51.011 Section 10.3.13 @@ -929,7 +929,7 @@ # TS 51.011 Section 10.3.54 class EF_MMSUP(LinFixedEF): class MMS_UserPref_ProfileName(BER_TLV_IE, tag=0x81): - pass + _construct = GsmOrUcs2Adapter(GreedyBytes) class MMS_UserPref_Info(BER_TLV_IE, tag=0x82): pass -- To view, visit https://gerrit.osmocom.org/c/pysim/+/35453?usp=email To unsubscribe, or for help writing mail filters, visit https://gerrit.osmocom.org/settings Gerrit-Project: pysim Gerrit-Branch: master Gerrit-Change-Id: I4eb8aea0a13260a143e2c60fca73c3c4312fd3b2 Gerrit-Change-Number: 35453 Gerrit-PatchSet: 6 Gerrit-Owner: laforge <laforge(a)osmocom.org> Gerrit-Reviewer: Jenkins Builder Gerrit-Reviewer: dexter <pmaier(a)sysmocom.de> Gerrit-Reviewer: fixeria <vyanitskiy(a)sysmocom.de> Gerrit-Reviewer: laforge <laforge(a)osmocom.org> Gerrit-MessageType: merged