rdf+bcp47+hxl (#41): current refactoring done; starting metadata insp…

…ection features

officina/999999999/0/999999999_54872.py

@@ -47,6 +47,7 @@
     bcp47_rdf_extension_poc,
     hxltm_carricato,
     HXLTMAdRDFSimplicis,
+    hxltm_carricato_brevibus,
     rdf_namespaces_extras
 )
 
@@ -98,6 +99,13 @@
 
 
 Temporary tests . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
+(Debug information in JSON)
+    {0} --objectivum-formato=_temp_bcp47_meta_in_json \
+--rdf-namespaces-archivo=\
+999999999/1568346/data/hxlstandard-rdf-namespaces-example.hxl.csv \
+999999999/1568346/data/unesco-thesaurus.bcp47g.tsv
+
+(Data operations)
     {0} --objectivum-formato=_temp_bcp47 --rdf-namespaces-archivo=\
 999999999/1568346/data/hxlstandard-rdf-namespaces-example.hxl.csv \
 999999999/1568346/data/unesco-thesaurus.bcp47g.tsv
@@ -237,6 +245,7 @@ def make_args(self, hxl_output=True):
                 # #    - Uses '.ndjson' as extension
                 # 'application/x-ndjson',
                 '_temp_bcp47',
+                '_temp_bcp47_meta_in_json',
             ],
             # required=True
             default='application/x-turtle'
@@ -280,7 +289,6 @@ def make_args(self, hxl_output=True):
             default=None
         )
 
-
         # praefīxum	, n, s, nominativus,
         #                         https://en.wiktionary.org/wiki/praefixus#Latin
         # cōnfigūrātiōnī, f, s, dativus,
@@ -332,6 +340,16 @@ def execute_cli(self, pyargs, stdin=STDIN, stdout=sys.stdout,
             # print(RDF_NAMESPACES_EXTRAS)
             # pass
 
+        # @TODO maybe refactor this temporary part
+        if pyargs.objectivum_formato == '_temp_bcp47_meta_in_json':
+            caput, data = hxltm_carricato_brevibus(
+                _infile, _stdin, punctum_separato="\t")
+
+            meta = bcp47_rdf_extension_poc(
+                caput, data, objective_bag=pyargs.rdf_bag, est_meta=True)
+            print(json.dumps(meta, sort_keys=False, ensure_ascii=False))
+            return self.EXIT_OK
+
         # @TODO remove thsi temporary part
         if pyargs.objectivum_formato == '_temp_bcp47':
             caput, data = hxltm_carricato(

officina/999999999/0/L999999999_0.py

@@ -1356,6 +1356,10 @@ def bcp47_rdf_extension_relationship(
             for subject in item_meta['extension']['r']['rdf:subject']:
                 # is_pivot_key = False
                 subject_key, subject_value = subject.split(':')
+                _temp1, _temp2 = subject.split('||')
+                subject_key = _temp1
+                subject_value = _temp2.replace(':NOP', '')
+                # raise ValueError(subject)
                 # if subject.startswith('∀'):
                 #     is_pivot_key = True
                 #     subject = subject.replace('∀', '')
@@ -1434,6 +1438,7 @@ def bcp47_rdf_extension_poc(
         objective_bag: str = '1',
         _auxiliary_bags: List[str] = None,
         namespaces: List[dict] = None,
+        est_meta: bool = False,
         strictum: bool = True
 ) -> dict:
     """bcp47_rdf_extension_poc _summary_
@@ -1472,7 +1477,6 @@ def bcp47_rdf_extension_poc(
     result = {
         'header': header,
         'header_result': [],
-        'data': data,
         # 'rdf:subject': None,
         # 'rdf:predicate': [],
         # 'rdf:object': None,
@@ -1481,6 +1485,7 @@ def bcp47_rdf_extension_poc(
         'triples': [],
         # We always start with default prefixes
         'prefixes': RDF_NAMESPACES,
+        'data': data,
         '_error': [],
     }
     # return {}
@@ -1568,10 +1573,13 @@ def _helper_aux(
         #         len(bag_meta['prefix']) > 0:
         #     value_prefixes = bag_meta['prefix']
 
-        for predicate in bag_meta['rdf:predicate']:
+        for predicate_and_subject in bag_meta['rdf:predicate']:
             if not object_literal:
                 continue
 
+            _temp1, _temp2 = predicate_and_subject.split('||')
+            predicate = _temp1
+
             if value_separator is not None and \
                 object_literal.find(value_separator) > -1 and \
                     object_literal.find('\\' + value_separator) == -1:
@@ -1641,10 +1649,9 @@ def _helper_aux(
             if len(aux_triples) > 0:
                 result['triples'].extend(aux_triples)
 
-    # raise ValueError(meta)
-
-    # result['prefixes'] = RDF_NAMESPACES
-    # result['prefixes'] = meta['prefixes']
+    if est_meta:
+        # return bag_meta
+        return result
 
     return result
     # return result['triples']
@@ -3863,6 +3870,69 @@ def hxltm_carricato(
     return caput, data
 
 
+def hxltm_carricato_brevibus(
+    archivum_trivio: str = None,
+    est_stdin: bool = False,
+    punctum_separato: str = ",",
+    data_lineis: int = 3,
+    est_hxl: bool = False
+) -> list:
+    """hxltm_carricato_brevibus read only header and part of the data
+
+    Note: this helper is not as efficent as read line by line. But some
+    operations already require such task.
+
+    Trivia:
+    - carricātō, n, s, dativus, https://en.wiktionary.org/wiki/carricatus#Latin
+      - verbum: https://en.wiktionary.org/wiki/carricatus#Latin
+    - capitī, s, n, https://en.wiktionary.org/wiki/caput#Latin
+    - brevibus, pl, m/f/n, https://en.wiktionary.org/wiki/brevis#Latin
+
+    Args:
+        archivum_trivio (str, optional): Path to file. Defaults to None.
+        est_stdin (bool, optional): Is the file stdin?. Defaults to False.
+
+    Returns:
+        list: list of [caput, data], where data is array of lines
+    """
+    caput = []
+
+    if est_stdin:
+        _data = []
+        for linea in sys.stdin:
+            if len(caput) == 0:
+                # caput = linea
+                # _reader_caput = csv.reader(linea)
+                _gambi = [linea, linea]
+                _reader_caput = csv.reader(_gambi, delimiter=punctum_separato)
+                caput = next(_reader_caput)
+            else:
+                if data_lineis <= 0:
+                    pass
+                else:
+                    data_lineis -= 1
+                    _data.append(linea)
+        _reader = csv.reader(_data)
+        return caput, list(_reader)
+        # return caput
+    # else:
+    #     fons = archivum_trivio
+    data = []
+    with open(archivum_trivio, 'r') as _fons:
+        _csv_reader = csv.reader(_fons, delimiter=punctum_separato)
+        for linea in _csv_reader:
+            if len(caput) == 0:
+                caput = linea
+            else:
+                if data_lineis <= 0:
+                    break
+                else:
+                    data_lineis -= 1
+                    data.append(linea)
+
+    return caput, data
+
+
 def hxltm_cum_ordinibus_ex_columnis(
     caput: list, data: list, quaestio: list, data_referentibus: dict = None
 ) -> Tuple[list, list]:

officina/999999999/1568346/bcp47-to-hxl-to-rdf.sh

@@ -290,7 +290,7 @@ bcp47_and_hxlrdf_roundtrip__drill() {
 
 # echo "test"
 
-# bcp47_to_hxl_to_rdf__tests
+bcp47_to_hxl_to_rdf__tests
 # test_unesco_thesaurus
 
 bcp47_and_hxlrdf_roundtrip__drill