Merge remote-tracking branch 'upstream/hotfixes' into release

pm4py/__init__.py

@@ -18,7 +18,7 @@
 
 from pm4py import util, objects, statistics, algo, visualization, llm, connectors
 from pm4py import analysis, conformance, convert, discovery, filtering, hof, ml, ocel, org, read, sim, stats, utils, vis, write
-from pm4py.read import read_xes, read_dfg, read_bpmn, read_pnml, read_ptml, read_ocel, read_ocel_csv, read_ocel_xml, read_ocel_json, read_ocel_sqlite, read_ocel2, read_ocel2_sqlite, read_ocel2_xml
+from pm4py.read import read_xes, read_dfg, read_bpmn, read_pnml, read_ptml, read_ocel, read_ocel_csv, read_ocel_xml, read_ocel_json, read_ocel_sqlite, read_ocel2, read_ocel2_sqlite, read_ocel2_json, read_ocel2_xml
 from pm4py.write import write_xes, write_dfg, write_bpmn, write_pnml, write_ptml, write_ocel, write_ocel_json, write_ocel_csv, write_ocel_xml, write_ocel_sqlite, write_ocel2, write_ocel2_sqlite, write_ocel2_xml
 from pm4py.utils import format_dataframe, parse_process_tree, serialize, deserialize, set_classifier, parse_event_log_string, project_on_event_attribute, \
     sample_cases, sample_events, rebase, parse_powl_model_string

pm4py/meta.py

@@ -16,7 +16,7 @@
 '''
 
 __name__ = 'pm4py'
-VERSION = '2.7.9.2'
+VERSION = '2.7.9.3'
 __version__ = VERSION
 __doc__ = 'Process mining for Python'
 __author__ = 'Fraunhofer Institute for Applied Information Technology FIT'

pm4py/objects/ocel/importer/jsonocel/variants/classic.py

@@ -79,12 +79,16 @@ def get_base_ocel(json_obj: Any, parameters: Optional[Dict[Any, Any]] = None):
             dct[k] = v
         this_rel = {}
         for obj in ev[constants.OCEL_OMAP_KEY]:
-            this_rel[obj] = {event_id: ev_id, event_activity: ev[event_activity],
-                              event_timestamp: parser.apply(ev[event_timestamp]), object_id: obj,
-                              object_type: types_dict[obj]}
+            if obj in types_dict:
+                this_rel[obj] = {event_id: ev_id, event_activity: ev[event_activity],
+                                  event_timestamp: parser.apply(ev[event_timestamp]), object_id: obj,
+                                  object_type: types_dict[obj]}
         if constants.OCEL_TYPED_OMAP_KEY in ev:
             for element in ev[constants.OCEL_TYPED_OMAP_KEY]:
-                this_rel[element[object_id]][constants.DEFAULT_QUALIFIER] = element[constants.DEFAULT_QUALIFIER]
+                if object_id in element:
+                    key1 = element[object_id]
+                    if key1 in this_rel:
+                        this_rel[key1][constants.DEFAULT_QUALIFIER] = element[constants.DEFAULT_QUALIFIER]
         for obj in this_rel:
             relations.append(this_rel[obj])
         events.append(dct)

pm4py/objects/ocel/importer/sqlite/variants/ocel20.py

@@ -38,6 +38,7 @@ class Parameters(Enum):
     INTERNAL_INDEX = constants.PARAM_INTERNAL_INDEX
     QUALIFIER = constants.PARAM_QUALIFIER
     CHANGED_FIELD = constants.PARAM_CHNGD_FIELD
+    CUMCOUNT = "cumcount"
     VALIDATION = "validation"
     EXCEPT_IF_INVALID = "except_if_invalid"
 
@@ -60,6 +61,7 @@ def apply(file_path: str, parameters: Optional[Dict[Any, Any]] = None):
     internal_index = exec_utils.get_param_value(Parameters.INTERNAL_INDEX, parameters, constants.DEFAULT_INTERNAL_INDEX)
     qualifier_field = exec_utils.get_param_value(Parameters.QUALIFIER, parameters, constants.DEFAULT_QUALIFIER)
     changed_field = exec_utils.get_param_value(Parameters.CHANGED_FIELD, parameters, constants.DEFAULT_CHNGD_FIELD)
+    cumcount_field = exec_utils.get_param_value(Parameters.CUMCOUNT, parameters, "@@cumcount")
 
     if validation:
         satisfied, unsatisfied = ocel20_rel_validation.apply(file_path)
@@ -115,9 +117,14 @@ def apply(file_path: str, parameters: Optional[Dict[Any, Any]] = None):
 
     events_timestamp = event_types_coll[[event_id, event_timestamp]].to_dict('records')
     events_timestamp = {x[event_id]: x[event_timestamp] for x in events_timestamp}
+    object_types_coll[cumcount_field] = object_types_coll.groupby(object_id).cumcount()
+
     if changed_field in object_types_coll:
         objects = object_types_coll[object_types_coll[changed_field].isna()]
         object_changes = object_types_coll[~object_types_coll[changed_field].isna()]
+        if len(objects) == 0:
+            objects = object_types_coll[object_types_coll[cumcount_field] == 0]
+            object_changes = object_types_coll[object_types_coll[cumcount_field] > 0]
         if len(object_changes) == 0:
             object_changes = None
         del objects[changed_field]
@@ -126,6 +133,7 @@ def apply(file_path: str, parameters: Optional[Dict[Any, Any]] = None):
         object_changes = None
 
     del objects[event_timestamp]
+    del objects[cumcount_field]
 
     E2O = pd.read_sql("SELECT * FROM event_object", conn)
     E2O = E2O.rename(columns={"ocel_event_id": event_id, "ocel_object_id": object_id, "ocel_qualifier": qualifier_field})

pm4py/objects/ocel/importer/xmlocel/variants/ocel20.py

@@ -26,7 +26,6 @@
 from pm4py.util import exec_utils, dt_parsing, pandas_utils
 from pm4py.objects.ocel.util import ocel_consistency
 
-
 class Parameters(Enum):
     EVENT_ID = constants.PARAM_EVENT_ID
     EVENT_ACTIVITY = constants.PARAM_EVENT_ACTIVITY
@@ -41,12 +40,25 @@ class Parameters(Enum):
 
 def parse_xml(value, tag_str_lower, parser):
     if "float" in tag_str_lower:
+        if value == "null":
+            return 0
         return float(value)
     elif "date" in tag_str_lower:
-        return parser.apply(value)
+        return embed_date_parser(parser.apply, value)
     return str(value)
 
 
+def embed_date_parser(date_parser, x):
+    try:
+        return date_parser(x)
+    except:
+        from dateutil.parser import parse
+        try:
+            return parse(x)
+        except:
+            return parse(x, fuzzy=True)
+
+
 def apply(file_path: str, parameters: Optional[Dict[Any, Any]] = None) -> OCEL:
     if parameters is None:
         parameters = {}
@@ -134,7 +146,7 @@ def apply(file_path: str, parameters: Optional[Dict[Any, Any]] = None) -> OCEL:
                             if attribute_time == "0" or attribute_time.startswith("1970-01-01T00:00:00"):
                                 obj_dict[attribute_name] = attribute_text
                             else:
-                                attribute_time = date_parser.apply(attribute_time)
+                                attribute_time = embed_date_parser(date_parser.apply, attribute_time)
                                 obj_change_dict = {object_id_column: object_id, object_type_column: object_type, attribute_name: attribute_text, changed_field: attribute_name, event_timestamp_column: attribute_time}
                                 object_changes_list.append(obj_change_dict)
 
@@ -148,7 +160,7 @@ def apply(file_path: str, parameters: Optional[Dict[Any, Any]] = None) -> OCEL:
             for event in child:
                 event_id = event.get("id")
                 event_type = event.get("type")
-                event_time = date_parser.apply(event.get("time"))
+                event_time = embed_date_parser(date_parser.apply, event.get("time"))
 
                 ev_dict = {event_id_column: event_id, event_activity_column: event_type, event_timestamp_column: event_time}
 
@@ -158,9 +170,9 @@ def apply(file_path: str, parameters: Optional[Dict[Any, Any]] = None) -> OCEL:
                             target_object_id = target_object.get("object-id")
                             qualifier = target_object.get("qualifier")
 
-                            rel_dict = {event_id_column: event_id, event_activity_column: event_type, event_timestamp_column: event_time, object_id_column: target_object_id, object_type_column: obj_type_dict[target_object_id], qualifier_field: qualifier}
-
-                            relations_list.append(rel_dict)
+                            if target_object_id in obj_type_dict:
+                                rel_dict = {event_id_column: event_id, event_activity_column: event_type, event_timestamp_column: event_time, object_id_column: target_object_id, object_type_column: obj_type_dict[target_object_id], qualifier_field: qualifier}
+                                relations_list.append(rel_dict)
                     elif child2.tag.endswith("attributes"):
                         for attribute in child2:
                             attribute_name = attribute.get("name")

pm4py/read.py

@@ -325,7 +325,7 @@ def read_ocel2(file_path: str, encoding: str = constants.DEFAULT_ENCODING) -> OC
         return read_ocel2_sqlite(file_path, encoding=encoding)
     elif file_path.lower().endswith("xml") or file_path.lower().endswith("xmlocel"):
         return read_ocel2_xml(file_path, encoding=encoding)
-    elif file_path.lower().endswith("jsonocel"):
+    elif file_path.lower().endswith("json") or file_path.lower().endswith("jsonocel"):
         return read_ocel2_json(file_path, encoding=encoding)