#39 #44 #23 formatting of files and adding words to translate

environment.yml

@@ -4,20 +4,20 @@ channels:
   - defaults
 dependencies:
   - python=3.9
-  - black>=19.10b0
+  - beautifulsoup4>=4.12.0
   - defusedxml=0.7.1
-  - pandas>=1.5.3
-  - pytest-cov>=3.0.0
-  - sentencepiece>=0.1.95
-  - tabulate>=0.8.9
-  - transformers>=4.12
-  - tqdm=4.59.0
+  - pandas>=2.0.3
+  - pytest-cov>=4.0.0
+  - sentencepiece>=0.1.99
+  - tabulate>=0.8.10
+  - transformers>=4.24.0
+  - tqdm=4.65.0
   - pip:
-      - beautifulsoup4==4.9.3
-      - emoji>=2.2.0
-      - mwparserfromhell>=0.6
+      - black>=23.7.0
+      - emoji>=2.8.0
+      - mwparserfromhell>=0.6.5
       - PyICU>=2.10.2 # Make sure to fulfill PyICU dependencies, see https://gitlab.pyicu.org/main/pyicu#installing-pyicu
       - python-dateutil>=2.8.2
-      - regex>=2023.3.23
+      - regex>=2023.8.8
       - SPARQLWrapper>=2.0.0
-      - tensorflow>=2.5.1
+      - tensorflow>=2.11.0

src/scribe_data/extract_transform/English/nouns/format_nouns.py

@@ -5,8 +5,6 @@
 Formats the nouns queried from Wikidata using query_nouns.sparql.
 """
 
-# pylint: disable=invalid-name
-
 import collections
 import json
 import os
@@ -17,7 +15,7 @@
 PATH_TO_SCRIBE_DATA_SRC = f"{PATH_TO_SCRIBE_ORG}Scribe-Data/src"
 sys.path.insert(0, PATH_TO_SCRIBE_DATA_SRC)
 
-from scribe_data.load.update_utils import get_path_from_et_dir
+from scribe_data.utils import get_path_from_et_dir
 
 file_path = sys.argv[0]
 
@@ -30,24 +28,6 @@
     with open(f"./{LANGUAGE}/nouns/nouns_queried.json", encoding="utf-8") as f:
         nouns_list = json.load(f)
 
-
-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 = ["PL"] # Gender annotations added here when genders are added.
-    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:
@@ -74,15 +54,7 @@ def order_annotations(annotation):
                         }
                 else:
                     # Mark plural as a possible form if it isn't already.
-                    if (
-                        "PL" not in nouns_formatted[noun_vals["plural"]]["form"]
-                        and nouns_formatted[noun_vals["plural"]]["form"] != ""
-                    ):
-                        nouns_formatted[noun_vals["plural"]]["form"] = (
-                            nouns_formatted[noun_vals["plural"]]["form"] + "/PL"
-                        )
-
-                    elif nouns_formatted[noun_vals["plural"]]["form"] == "":
+                    if nouns_formatted[noun_vals["plural"]]["form"] == "":
                         nouns_formatted[noun_vals["plural"]]["form"] = "PL"
 
                     # Assign itself as a plural if possible (maybe wasn't for prior versions).
@@ -95,12 +67,14 @@ def order_annotations(annotation):
                     "plural": "",
                     "form": "",
                 }
+
     elif "plural" in noun_vals.keys():
         if noun_vals["plural"] not in nouns_formatted:
             nouns_formatted[noun_vals["plural"]] = {
                 "plural": "isPlural",
                 "form": "PL",
             }
+
         else:
             # Mark plural as a possible form if it isn't already.
             if (
@@ -114,9 +88,6 @@ def order_annotations(annotation):
             elif nouns_formatted[noun_vals["plural"]]["form"] == "":
                 nouns_formatted[noun_vals["plural"]]["form"] = "PL"
 
-for k in nouns_formatted:
-    nouns_formatted[k]["form"] = order_annotations(nouns_formatted[k]["form"])
-
 nouns_formatted = collections.OrderedDict(sorted(nouns_formatted.items()))
 
 org_path = get_path_from_et_dir()
@@ -131,4 +102,4 @@ def order_annotations(annotation):
 with open(export_path, "w", encoding="utf-8",) as file:
     json.dump(nouns_formatted, file, ensure_ascii=False, indent=0)
 
-print(f"Wrote file nouns.json with {len(nouns_formatted)} nouns.")
+print(f"Wrote file nouns.json with {len(nouns_formatted)} nouns.")