Merge pull request #43 from Bernardo-MG/develop

Develop

cwr/__init__.py

@@ -7,5 +7,5 @@
     :license: MIT, see LICENSE for more details.
 """
 
-__version__ = '0.0.14'
+__version__ = '0.0.15'
 __license__ = 'MIT'

cwr/grammar/factory/field.py

@@ -163,31 +163,10 @@ class DefaultFieldTerminalRuleFactory(OptionFieldTerminalRuleFactory):
     Factory for acquiring fields rules using the default configuration.
     """
 
-    def __init__(self, field_configs, field_values=None, field_rules=None, actions=None):
+    def __init__(self, field_configs, adapters, field_values=None, field_rules=None, actions=None):
         super(DefaultFieldTerminalRuleFactory, self).__init__(field_configs)
 
-        # TODO: Don't do this manually
-        self._adapters['alphanum'] = AlphanumAdapter()
-        self._adapters['alphanum_ext'] = ExtendedAlphanumAdapter()
-        self._adapters['numeric'] = NumericAdapter()
-        self._adapters['boolean'] = BooleanAdapter()
-        self._adapters['flag'] = FlagAdapter()
-        self._adapters['date'] = DateAdapter()
-        self._adapters['time'] = TimeAdapter()
-        self._adapters['date_time'] = DateTimeAdapter()
-        self._adapters['blank'] = BlankAdapter()
-        self._adapters['lookup'] = LookupAdapter()
-        self._adapters['iswc'] = ISWCAdapter()
-        self._adapters['ipi_name_n'] = IPINameNumberAdapter()
-        self._adapters['ipi_base_n'] = IPIBaseNumberAdapter()
-        self._adapters['percentage'] = PercentageAdapter()
-        self._adapters['ean13'] = EAN13Adapter()
-        self._adapters['isrc'] = ISRCAdapter()
-        self._adapters['visan'] = VISANAdapter()
-        self._adapters['avi'] = AudioVisualKeydapter()
-        self._adapters['charset'] = CharSetAdapter()
-        self._adapters['alphanum_variable'] = VariableAlphanumAdapter()
-        self._adapters['numeric_float'] = NumericFloatAdapter()
+        self._adapters = adapters
 
         # Field values are optional
         self._field_values = field_values

cwr/grammar/field/special.py

@@ -6,7 +6,7 @@
 
 from cwr.other import ISWCCode, IPIBaseNumber, VISAN, AVIKey
 from cwr.grammar.field import basic
-from data_commonworks.accessor import CWRConfiguration
+from data_commonworks.accessor import CWRConfiguration, CWRTables
 
 
 """
@@ -260,22 +260,106 @@ def isrc(name=None):
     :return: grammar for an ISRC field
     """
 
+    config = CWRTables()
+
+    if name is None:
+        name = 'ISRC Field'
+
+    separator = pp.Literal('-')
+    country = basic.lookup(config.get_data('isrc_country_code'))
+    registrant = basic.alphanum(3)
+    year = pp.Regex('[0-9]{2}')
+    work_id = pp.Regex('[0-9]{2}')
+
+    field = _isrc_short(name) | _isrc_long(name)
+
+    field.setName(name)
+
+    return field.setResultsName('isrc')
+
+
+def _isrc_short(name=None):
+    """
+    Creates the grammar for a short ISRC code.
+
+    ISRC stands for International Standard Recording Code, which is the standard ISO 3901. This stores information
+    identifying a particular recording.
+
+    This variant contains separator for the parts, and follows the pattern:
+    CC-XXX-YY-NN
+
+    Where each code means:
+    - CC: country code
+    - XXX: registrant
+    - YY: year
+    - NN: work id
+
+    :param name: name for the field
+    :return: grammar for an ISRC field
+    """
+
+    config = CWRTables()
+
     if name is None:
         name = 'ISRC Field'
 
     separator = pp.Literal('-')
-    country = basic.alphanum(2)
+    country = basic.lookup(config.get_data('isrc_country_code'))
     registrant = basic.alphanum(3)
     year = pp.Regex('[0-9]{2}')
     work_id = pp.Regex('[0-9]{2}')
 
     field = pp.Combine(country + separator + registrant + separator + year + separator + work_id)
 
+    country.setName('ISO-2 Country Code')
+    registrant.setName('Registrant')
+    year.setName('Year')
+    work_id.setName('Work ID')
+
     field.setName(name)
 
-    # TODO: Fix this field
-    field = basic.alphanum(12)
-    field = field.setName(name)
+    return field.setResultsName('isrc')
+
+
+def _isrc_long(name=None):
+    """
+    Creates the grammar for a short ISRC code.
+
+    ISRC stands for International Standard Recording Code, which is the standard ISO 3901. This stores information
+    identifying a particular recording.
+
+    This variant contain no separator for the parts, and follows the pattern:
+    CCXXXYYNNNNN
+
+    Where each code means:
+    - CC: country code
+    - XXX: registrant
+    - YY: year
+    - NNNNN: work id
+
+    :param name: name for the field
+    :return: grammar for an ISRC field
+    """
+
+    config = CWRTables()
+
+    if name is None:
+        name = 'ISRC Field'
+
+    separator = pp.Literal('-')
+    country = basic.lookup(config.get_data('isrc_country_code'))
+    registrant = basic.alphanum(3)
+    year = pp.Regex('[0-9]{2}')
+    work_id = pp.Regex('[0-9]{5}')
+
+    field = pp.Combine(country + registrant + year + work_id)
+
+    country.setName('ISO-2 Country Code')
+    registrant.setName('Registrant')
+    year.setName('Year')
+    work_id.setName('Work ID')
+
+    field.setName(name)
 
     return field.setResultsName('isrc')
 

cwr/parser/decoder/common.py

@@ -79,7 +79,7 @@ def decode(self, text):
 
         For this a Pyparsing grammar rule will be applied to the string.
 
-        :param data: the data to decode
+        :param text: the data to decode
         :return: a class representing the data
         """
         return self._grammar.parseString(text)

cwr/parser/decoder/file.py

@@ -8,6 +8,7 @@
 from cwr.grammar.factory.rule import DefaultRuleFactory
 from cwr.grammar.factory.decorator import RecordRuleDecorator, GroupRuleDecorator
 from cwr.parser.decoder.dictionary import *
+from cwr.grammar.factory.adapter import *
 
 
 """
@@ -84,6 +85,34 @@ def _default_record_decoders():
     return decoders
 
 
+def _default_adapters():
+    adapters = {}
+
+    adapters['alphanum'] = AlphanumAdapter()
+    adapters['alphanum_ext'] = ExtendedAlphanumAdapter()
+    adapters['numeric'] = NumericAdapter()
+    adapters['boolean'] = BooleanAdapter()
+    adapters['flag'] = FlagAdapter()
+    adapters['date'] = DateAdapter()
+    adapters['time'] = TimeAdapter()
+    adapters['date_time'] = DateTimeAdapter()
+    adapters['blank'] = BlankAdapter()
+    adapters['lookup'] = LookupAdapter()
+    adapters['iswc'] = ISWCAdapter()
+    adapters['ipi_name_n'] = IPINameNumberAdapter()
+    adapters['ipi_base_n'] = IPIBaseNumberAdapter()
+    adapters['percentage'] = PercentageAdapter()
+    adapters['ean13'] = EAN13Adapter()
+    adapters['isrc'] = ISRCAdapter()
+    adapters['visan'] = VISANAdapter()
+    adapters['avi'] = AudioVisualKeydapter()
+    adapters['charset'] = CharSetAdapter()
+    adapters['alphanum_variable'] = VariableAlphanumAdapter()
+    adapters['numeric_float'] = NumericFloatAdapter()
+
+    return adapters
+
+
 def default_file_decoder():
     """
     Creates a decoder which parses a CWR file, creating a CWRFile class instance from it.
@@ -95,7 +124,7 @@ def default_file_decoder():
     _data = _config.load_field_config('table')
     _data.update(_config.load_field_config('common'))
 
-    _factory_field = DefaultFieldTerminalRuleFactory(_data, CWRTables())
+    _factory_field = DefaultFieldTerminalRuleFactory(_data, _default_adapters(), field_values=CWRTables())
 
     _rules = _config.load_transaction_config('common')
     _rules.update(_config.load_record_config('common'))
@@ -121,7 +150,7 @@ def default_filename_decoder():
     _data.update(_config.load_field_config('common'))
     _data.update(_config.load_field_config('filename'))
 
-    _factory_field = DefaultFieldTerminalRuleFactory(_data, CWRTables())
+    _factory_field = DefaultFieldTerminalRuleFactory(_data, _default_adapters(), field_values=CWRTables())
 
     _group_rule_factory = DefaultRuleFactory(_config.load_record_config('filename'), _factory_field)
 
@@ -162,6 +191,13 @@ def decode(self, data):
         """
         filename = self._filename_decoder.decode(data['filename'])
 
+        file_data = data['contents']
+        i = 0
+        while file_data[i:i + 1] != 'H':
+            i += 1
+        if i > 0:
+            data['contents'] = file_data[i:]
+
         transmission = self._file_decoder.decode(data['contents'])[0]
 
         return CWRFile(filename, transmission)

data_commonworks/cwr_isrc_country_code.csv

@@ -0,0 +1 @@
+AC,AD,AE,AF,AG,AI,AL,AM,AN,AO,AR,AS,AT,AU,AW,AX,AZ,BA,BB,BD,BE,BF,BG,BH,BI,BJ,BL,BM,BN,BO,BR,BS,BT,BW,BY,BZ,CA,CD,CF,CG,CH,CI,CK,CL,CM,CN,CO,CR,CU,CV,CY,CZ,DE,DJ,DK,DM,DO,DZ,EC,EE,EG,EH,ER,ES,ET,FI,FJ,FK,FM,FO,FR,GA,GB,GD,GE,GF,GG,GH,GI,GL,GM,GN,GP,GQ,GR,GT,GU,GW,GY,HK,HN,HR,HT,HU,ID,IE,IL,IM,IN,IQ,IR,IS,IT,JE,JM,JO,JP,KE,KG,KH,KI,KM,KN,Kosovo,KP,KR,KW,KY,KZ,LA,LB,LC,LI,LK,LR,LS,LT,LU,LV,LY,MA,MC,MD,ME,MF,MG,MH,MK,ML,MM,MN,MO,MP,MQ,MR,MS,MT,MU,MV,MW,MX,MY,MZ,NA,NC,NE,NF,NG,NI,NL,NO,NP,NR,NU,NZ,OECS,OM,PA,PE,PF,PG,PH,PK,PL,PM,PN,PR,PS,PT,PW,PY,QA,RE,RO,RS,RU,RW,SA,SB,SC,SD,SE,SG,SH,SI,SJ,SK,SL,SM,SN,SO,SR,ST,SV,SY,SZ,TC,TD,TG,TH,TJ,TK,TL,TM,TN,TO,TR,TT,TV,TW,TZ,UA,UG,US,UY,UZ,VA,VC,VE,VG,VI,VN,VU,WF,WS,YE,YT,Yugoslavia,ZA,ZM,ZW,QR,CP,DG,ZZ