#124 standardize annotation ordering and format file fxn calls

scribe-org · Jun 2, 2024 · 7553fd6 · 7553fd6
1 parent 7e4ca2e
commit 7553fd6
Show file tree

Hide file tree

Showing 18 changed files with 97 additions and 182 deletions.
diff --git a/src/scribe_data/language_data_extraction/English/nouns/format_nouns.py b/src/scribe_data/language_data_extraction/English/nouns/format_nouns.py
@@ -8,10 +8,12 @@
 
 from scribe_data.utils import export_formatted_data, load_queried_data
 
+LANGUAGE = "English"
+DATA_TYPE = "nouns"
 file_path = sys.argv[0]
 
 nouns_list, update_data_in_use, data_path = load_queried_data(
-    file_path=file_path, language="English", data_type="nouns"
+    file_path=file_path, language=LANGUAGE, data_type=DATA_TYPE
 )
 
 nouns_formatted = {}
@@ -79,8 +81,8 @@
 export_formatted_data(
     formatted_data=nouns_formatted,
     update_data_in_use=update_data_in_use,
-    language="English",
-    data_type="nouns",
+    language=LANGUAGE,
+    data_type=DATA_TYPE,
 )
 
 os.remove(data_path)
diff --git a/src/scribe_data/language_data_extraction/English/verbs/format_verbs.py b/src/scribe_data/language_data_extraction/English/verbs/format_verbs.py
@@ -8,10 +8,12 @@
 
 from scribe_data.utils import export_formatted_data, load_queried_data
 
+LANGUAGE = "English"
+DATA_TYPE = "verbs"
 file_path = sys.argv[0]
 
 verbs_list, update_data_in_use, data_path = load_queried_data(
-    file_path=file_path, language="English", data_type="verbs"
+    file_path=file_path, language=LANGUAGE, data_type=DATA_TYPE
 )
 
 verbs_formatted = {}
@@ -66,8 +68,8 @@
 export_formatted_data(
     formatted_data=verbs_formatted,
     update_data_in_use=update_data_in_use,
-    language="English",
-    data_type="verbs",
+    language=LANGUAGE,
+    data_type=DATA_TYPE,
 )
 
 os.remove(data_path)
diff --git a/src/scribe_data/language_data_extraction/French/nouns/format_nouns.py b/src/scribe_data/language_data_extraction/French/nouns/format_nouns.py
@@ -10,33 +10,18 @@
     export_formatted_data,
     load_queried_data,
     map_genders,
+    order_annotations,
 )
 
+LANGUAGE = "French"
+DATA_TYPE = "nouns"
 file_path = sys.argv[0]
 
 nouns_list, update_data_in_use, data_path = load_queried_data(
-    file_path=file_path, language="French", data_type="nouns"
+    file_path=file_path, language=LANGUAGE, data_type=DATA_TYPE
 )
 
 
-def order_annotations(annotation):
-    """
-    Standardizes the annotations that are presented to users where more than one is applicable.
-
-    Parameters
-    ----------
-        annotation : str
-            The annotation to be returned to the user in the command bar.
-    """
-    single_annotations = ["F", "M", "PL"]
-    if annotation in single_annotations:
-        return annotation
-
-    annotation_split = sorted([a for a in set(annotation.split("/")) if a != ""])
-
-    return "/".join(annotation_split)
-
-
 nouns_formatted = {}
 
 for noun_vals in nouns_list:
@@ -102,8 +87,8 @@ def order_annotations(annotation):
 export_formatted_data(
     formatted_data=nouns_formatted,
     update_data_in_use=update_data_in_use,
-    language="French",
-    data_type="nouns",
+    language=LANGUAGE,
+    data_type=DATA_TYPE,
 )
 
 os.remove(data_path)
diff --git a/src/scribe_data/language_data_extraction/French/verbs/format_verbs.py b/src/scribe_data/language_data_extraction/French/verbs/format_verbs.py
@@ -8,10 +8,12 @@
 
 from scribe_data.utils import export_formatted_data, load_queried_data
 
+LANGUAGE = "French"
+DATA_TYPE = "verbs"
 file_path = sys.argv[0]
 
 verbs_list, update_data_in_use, data_path = load_queried_data(
-    file_path=file_path, language="French", data_type="verbs"
+    file_path=file_path, language=LANGUAGE, data_type=DATA_TYPE
 )
 
 verbs_formatted = {}
@@ -63,8 +65,8 @@
 export_formatted_data(
     formatted_data=verbs_formatted,
     update_data_in_use=update_data_in_use,
-    language="French",
-    data_type="verbs",
+    language=LANGUAGE,
+    data_type=DATA_TYPE,
 )
 
 os.remove(data_path)
diff --git a/src/scribe_data/language_data_extraction/German/nouns/format_nouns.py b/src/scribe_data/language_data_extraction/German/nouns/format_nouns.py
@@ -10,33 +10,18 @@
     export_formatted_data,
     load_queried_data,
     map_genders,
+    order_annotations,
 )
 
+LANGUAGE = "German"
+DATA_TYPE = "nouns"
 file_path = sys.argv[0]
 
 nouns_list, update_data_in_use, data_path = load_queried_data(
-    file_path=file_path, language="German", data_type="nouns"
+    file_path=file_path, language=LANGUAGE, data_type=DATA_TYPE
 )
 
 
-def order_annotations(annotation):
-    """
-    Standardizes the annotations that are presented to users where more than one is applicable.
-
-    Parameters
-    ----------
-        annotation : str
-            The annotation to be returned to the user in the command bar.
-    """
-    single_annotations = ["F", "M", "N", "PL"]
-    if annotation in single_annotations:
-        return annotation
-
-    annotation_split = sorted([a for a in set(annotation.split("/")) if a != ""])
-
-    return "/".join(annotation_split)
-
-
 nouns_formatted = {}
 
 for noun_vals in nouns_list:
@@ -164,8 +149,8 @@ def order_annotations(annotation):
 export_formatted_data(
     formatted_data=nouns_formatted,
     update_data_in_use=update_data_in_use,
-    language="German",
-    data_type="nouns",
+    language=LANGUAGE,
+    data_type=DATA_TYPE,
 )
 
 os.remove(data_path)
diff --git a/src/scribe_data/language_data_extraction/German/prepositions/format_prepositions.py b/src/scribe_data/language_data_extraction/German/prepositions/format_prepositions.py
@@ -13,10 +13,12 @@
     order_annotations,
 )
 
+LANGUAGE = "German"
+DATA_TYPE = "prepositions"
 file_path = sys.argv[0]
 
 prepositions_list, update_data_in_use, data_path = load_queried_data(
-    file_path=file_path, language="German", data_type="prepositions"
+    file_path=file_path, language=LANGUAGE, data_type=DATA_TYPE
 )
 
 prepositions_formatted = {}
@@ -75,8 +77,8 @@
 export_formatted_data(
     formatted_data=prepositions_formatted,
     update_data_in_use=update_data_in_use,
-    language="German",
-    data_type="prepositions",
+    language=LANGUAGE,
+    data_type=DATA_TYPE,
 )
 
 os.remove(data_path)
diff --git a/src/scribe_data/language_data_extraction/German/verbs/format_verbs.py b/src/scribe_data/language_data_extraction/German/verbs/format_verbs.py
@@ -13,10 +13,12 @@
 
 from scribe_data.utils import export_formatted_data, load_queried_data
 
+LANGUAGE = "German"
+DATA_TYPE = "verbs"
 file_path = sys.argv[0]
 
 verbs_list, update_data_in_use, data_path = load_queried_data(
-    file_path=file_path, language="German", data_type="verbs"
+    file_path=file_path, language=LANGUAGE, data_type=DATA_TYPE
 )
 
 verbs_formatted = {}
@@ -142,8 +144,8 @@ def assign_past_participle(verb, tense):
 export_formatted_data(
     formatted_data=verbs_formatted,
     update_data_in_use=update_data_in_use,
-    language="German",
-    data_type="verbs",
+    language=LANGUAGE,
+    data_type=DATA_TYPE,
 )
 
 os.remove(data_path)
diff --git a/src/scribe_data/language_data_extraction/Italian/nouns/format_nouns.py b/src/scribe_data/language_data_extraction/Italian/nouns/format_nouns.py
@@ -10,33 +10,18 @@
     export_formatted_data,
     load_queried_data,
     map_genders,
+    order_annotations,
 )
 
+LANGUAGE = "Italian"
+DATA_TYPE = "nouns"
 file_path = sys.argv[0]
 
 nouns_list, update_data_in_use, data_path = load_queried_data(
-    file_path=file_path, language="Italian", data_type="nouns"
+    file_path=file_path, language=LANGUAGE, data_type=DATA_TYPE
 )
 
 
-def order_annotations(annotation):
-    """
-    Standardizes the annotations that are presented to users where more than one is applicable.
-
-    Parameters
-    ----------
-        annotation : str
-            The annotation to be returned to the user in the command bar.
-    """
-    single_annotations = ["F", "M", "PL"]
-    if annotation in single_annotations:
-        return annotation
-
-    annotation_split = sorted([a for a in set(annotation.split("/")) if a != ""])
-
-    return "/".join(annotation_split)
-
-
 nouns_formatted = {}
 
 for noun_vals in nouns_list:
@@ -103,8 +88,8 @@ def order_annotations(annotation):
 export_formatted_data(
     formatted_data=nouns_formatted,
     update_data_in_use=update_data_in_use,
-    language="Italian",
-    data_type="nouns",
+    language=LANGUAGE,
+    data_type=DATA_TYPE,
 )
 
 os.remove(data_path)
diff --git a/src/scribe_data/language_data_extraction/Italian/verbs/format_verbs.py b/src/scribe_data/language_data_extraction/Italian/verbs/format_verbs.py
@@ -8,10 +8,12 @@
 
 from scribe_data.utils import export_formatted_data, load_queried_data
 
+LANGUAGE = "Italian"
+DATA_TYPE = "verbs"
 file_path = sys.argv[0]
 
 verbs_list, update_data_in_use, data_path = load_queried_data(
-    file_path=file_path, language="Italian", data_type="verbs"
+    file_path=file_path, language=LANGUAGE, data_type=DATA_TYPE
 )
 
 verbs_formatted = {}
@@ -57,8 +59,8 @@
 export_formatted_data(
     formatted_data=verbs_formatted,
     update_data_in_use=update_data_in_use,
-    language="Italian",
-    data_type="verbs",
+    language=LANGUAGE,
+    data_type=DATA_TYPE,
 )
 
 os.remove(data_path)
diff --git a/src/scribe_data/language_data_extraction/Portuguese/nouns/format_nouns.py b/src/scribe_data/language_data_extraction/Portuguese/nouns/format_nouns.py
@@ -10,33 +10,18 @@
     export_formatted_data,
     load_queried_data,
     map_genders,
+    order_annotations,
 )
 
+LANGUAGE = "Portuguese"
+DATA_TYPE = "nouns"
 file_path = sys.argv[0]
 
 nouns_list, update_data_in_use, data_path = load_queried_data(
-    file_path=file_path, language="Portuguese", data_type="nouns"
+    file_path=file_path, language=LANGUAGE, data_type=DATA_TYPE
 )
 
 
-def order_annotations(annotation):
-    """
-    Standardizes the annotations that are presented to users where more than one is applicable.
-
-    Parameters
-    ----------
-        annotation : str
-            The annotation to be returned to the user in the command bar.
-    """
-    single_annotations = ["F", "M", "PL"]
-    if annotation in single_annotations:
-        return annotation
-
-    annotation_split = sorted([a for a in set(annotation.split("/")) if a != ""])
-
-    return "/".join(annotation_split)
-
-
 nouns_formatted = {}
 
 for noun_vals in nouns_list:
@@ -103,8 +88,8 @@ def order_annotations(annotation):
 export_formatted_data(
     formatted_data=nouns_formatted,
     update_data_in_use=update_data_in_use,
-    language="Portuguese",
-    data_type="nouns",
+    language=LANGUAGE,
+    data_type=DATA_TYPE,
 )
 
 os.remove(data_path)
diff --git a/src/scribe_data/language_data_extraction/Portuguese/verbs/format_verbs.py b/src/scribe_data/language_data_extraction/Portuguese/verbs/format_verbs.py
@@ -8,10 +8,12 @@
 
 from scribe_data.utils import export_formatted_data, load_queried_data
 
+LANGUAGE = "Portuguese"
+DATA_TYPE = "verbs"
 file_path = sys.argv[0]
 
 verbs_list, update_data_in_use, data_path = load_queried_data(
-    file_path=file_path, language="Portuguese", data_type="verbs"
+    file_path=file_path, language=LANGUAGE, data_type=DATA_TYPE
 )
 
 verbs_formatted = {}
@@ -57,8 +59,8 @@
 export_formatted_data(
     formatted_data=verbs_formatted,
     update_data_in_use=update_data_in_use,
-    language="Portuguese",
-    data_type="verbs",
+    language=LANGUAGE,
+    data_type=DATA_TYPE,
 )
 
 os.remove(data_path)