feat: added internal annotation with multiple value

README.md

@@ -66,7 +66,7 @@ For more details check our [Installation](https://openvariant.readthedocs.io/en/
 ## Examples
 
 We offer a bunch of [Examples](examples) to we be able to understand how OpenVariant can be applied. Also, check 
-[Examples](./examples) section in OpenVariant's documentation.
+[Examples](https://openvariant.readthedocs.io/en/latest/examples.html) section in OpenVariant's documentation.
 
 ## Contributing
 

annotation_template.yaml

@@ -25,6 +25,7 @@ annotation: # Columns to parse
   # be extracted and parsed as values in the output
   - type: 'internal'
     field: string
+    value: string # Text to represent multiple fieldSource; optional
     fieldSource: # Columns to look for in the input files; required
       - string
       - string

main.py

@@ -1,6 +1,6 @@
 from os import getcwd
 
-from openvariant import find_files, Annotation, Variant
+from openvariant import findfiles, Annotation, Variant
 
 # where = "VAR != 4 AND (VAR != 5 OR VAR != 10)"
 # where_clauses = parse_where(where)
@@ -14,11 +14,10 @@
 #print(res)
 
 
-annotation = Annotation(f"{getcwd()}/tests/data/dataset/dataset.yaml")
+#annotation = Annotation(f"{getcwd()}/tests/data/dataset/dataset.yaml")
 
-#for file, _ in find_files(f"{getcwd()}/tests/data/dataset/"):
-
-result = Variant(f"{getcwd()}/tests/data/dataset/sample3/", annotation)
-for line in result.read():
-    print(f"Line in a dict: {line}")
-    break
+for file, ann in findfiles(f"{getcwd()}/tests/data/dataset/sample3"):
+    result = Variant(file, ann)
+    for line in result.read():
+        print(f"Line in a dict: {line}")
+        break

openvariant/annotation/builder.py

@@ -88,6 +88,7 @@ def _static_builder(x: dict, base_path: str = None) -> StaticBuilder:
         value = x[AnnotationKeys.VALUE.value]
     except KeyError:
         raise KeyError('Static annotation is wrong specified.')
+
     return AnnotationTypes.STATIC.name, value
 
 
@@ -109,7 +110,7 @@ def _internal_builder(x: dict, base_path: str = None) -> InternalBuilder:
     try:
         value = x[AnnotationKeys.VALUE.value]
     except KeyError:
-        value = float('nan')
+        value = None
 
     return AnnotationTypes.INTERNAL.name, x[AnnotationKeys.FIELD_SOURCE.value], Builder("(lambda y: y)") \
         if AnnotationKeys.FUNCTION.value not in x or x[AnnotationKeys.FUNCTION.value] is None or \

openvariant/annotation/process.py

@@ -10,7 +10,7 @@
 from openvariant.plugins.context import Context
 
 StaticProcess = Tuple[str, float or int or str, Callable]
-InternalProcess = Tuple[str, Optional[int], Callable]
+InternalProcess = Tuple[str, Tuple[dict, str], str]
 FilenameProcess = Tuple[str, float or int or str, Callable]
 DirnameProcess = Tuple[str, float or int or str, Callable]
 PluginProcess = Tuple[str, Context, Callable]
@@ -59,18 +59,34 @@ def _internal_process(x: InternalBuilder, original_header: List = [] or None, fi
     Callable
         Function to execute on the fixed value
     """
-    field_pos = None
+    field_pos = {}
     try:
-        for i, h in enumerate(original_header):
-            if h in set(x[1]):
-                field_pos = i
-                break
+        header_dict = {field: num for num, field in list(enumerate(original_header))}
+        for source in x[1]:
+            if isinstance(source, List):
+                for s in source:
+                    try:
+                        field_pos.update({s: header_dict[s]})
+                    except KeyError:
+                        field_pos = {}
+                        pass
+                if len(field_pos) == len(source):
+                    break
+                else:
+                    field_pos = {}
+            else:
+                try:
+                    field_pos = {source: header_dict[source]}
+                    break
+                except KeyError:
+                    pass
+
     except TypeError:
         raise TypeError(f'Unable to parser {x[0]} annotation')
     except SyntaxError:
         raise SyntaxError(f'Unable to parser function lambda on {x[0]} annotation')
 
-    return AnnotationTypes.INTERNAL.name, field_pos, x[2]
+    return AnnotationTypes.INTERNAL.name, (field_pos, x[3]), x[2]
 
 
 def _filename_process(x: FilenameBuilder, original_header: List = [] or None, file_path: str = None,

openvariant/variant/variant.py

@@ -201,7 +201,15 @@ def _parser(self, file_path: str, annotation: Annotation, group_by: str, display
                         elif type_ann == AnnotationTypes.MAPPING.name:
                             mapping_values[head] = header[head]
                         elif type_ann == AnnotationTypes.INTERNAL.name:
-                            value = line[value] if value is not None else None
+                            if len(value[0]) == 1:
+                                pos = list(value[0].values())[0]
+                                value = line[pos] if value is not None else None
+                            else:
+                                pos = {}
+                                for val, position in value[0].items():
+                                    pos.update({val: line[position]})
+                                value = value[1].format(**pos)
+
                             line_dict[head] = _parse_field(value, func)
                         else:
                             line_dict[head] = _parse_field(value, func)

tests/data/dataset/sample3/sample3.yaml

@@ -3,6 +3,7 @@ pattern:
 format: tsv
 
 columns:
+- ID
 - CHROMOSOME
 - POSITION
 - REF
@@ -12,6 +13,11 @@ columns:
 - PLATFORM
 
 annotation:
+- type: internal
+  field: ID
+  value: '{Hugo_Symbol}_{NCBI_Build}'
+  fieldSource:
+  - ['Hugo_Symbol', 'NCBI_Build']
 - type: internal
   field: CHROMOSOME
   fieldSource: