#95 update formatting files to work with update_data.py

scribe-org · Jan 15, 2022 · fe3ec56 · fe3ec56
1 parent 3fd4006
commit fe3ec56
Show file tree

Hide file tree

Showing 14 changed files with 296 additions and 121 deletions.
diff --git a/Data/French/nouns/format_nouns.py b/Data/French/nouns/format_nouns.py
@@ -7,9 +7,15 @@
 
 import collections
 import json
+import sys
 
-with open("nounsQueried.json") as f:
-    nouns_list = json.load(f)
+file_path = sys.argv[0]
+if "French/nouns/" not in file_path:
+    with open("nounsQueried.json") as f:
+        nouns_list = json.load(f)
+else:  # is being called by update_data.py
+    with open("./French/nouns/nounsQueried.json") as f:
+        nouns_list = json.load(f)
 
 
 def map_genders(wikidata_gender):
@@ -18,7 +24,7 @@ def map_genders(wikidata_gender):
     """
     if wikidata_gender in ["masculine", "Q499327"]:
         return "M"
-    if wikidata_gender in ["feminine", "Q1775415"]:
+    elif wikidata_gender in ["feminine", "Q1775415"]:
         return "F"
     else:
         return ""  # nouns could have a gender that is not valid as an attribute
@@ -105,11 +111,17 @@ def order_annotations(annotation):
 
 nouns_formatted = collections.OrderedDict(sorted(nouns_formatted.items()))
 
-with open(
-    "../../../Keyboards/LanguageKeyboards/French/Data/nouns.json",
-    "w",
-    encoding="utf-8",
-) as f:
-    json.dump(nouns_formatted, f, ensure_ascii=False, indent=2)
+if "French/nouns/" not in file_path:
+    with open(
+        "../../../Keyboards/LanguageKeyboards/French/Data/nouns.json",
+        "w",
+        encoding="utf-8",
+    ) as f:
+        json.dump(nouns_formatted, f, ensure_ascii=False, indent=2)
+else:  # is being called by update_data.py
+    with open(
+        "../Keyboards/LanguageKeyboards/French/Data/nouns.json", "w", encoding="utf-8",
+    ) as f:
+        json.dump(nouns_formatted, f, ensure_ascii=False, indent=2)
 
 print(f"Wrote file nouns.json with {len(nouns_formatted)} nouns.")
diff --git a/Data/French/verbs/format_verbs.py b/Data/French/verbs/format_verbs.py
@@ -7,9 +7,15 @@
 
 import collections
 import json
+import sys
 
-with open("verbsQueried.json") as f:
-    verbs_list = json.load(f)
+file_path = sys.argv[0]
+if "French/verbs/" not in file_path:
+    with open("verbsQueried.json") as f:
+        verbs_list = json.load(f)
+else:  # is being called by update_data.py
+    with open("./French/verbs/verbsQueried.json") as f:
+        verbs_list = json.load(f)
 
 verbs_formatted = {}
 
@@ -59,11 +65,17 @@ def fix_tense(tense):
 
 verbs_formatted = collections.OrderedDict(sorted(verbs_formatted.items()))
 
-with open(
-    "../../../Keyboards/LanguageKeyboards/French/Data/verbs.json",
-    "w",
-    encoding="utf-8",
-) as f:
-    json.dump(verbs_formatted, f, ensure_ascii=False, indent=2)
+if "French/verbs/" not in file_path:
+    with open(
+        "../../../Keyboards/LanguageKeyboards/French/Data/verbs.json",
+        "w",
+        encoding="utf-8",
+    ) as f:
+        json.dump(verbs_formatted, f, ensure_ascii=False, indent=2)
+else:  # is being called by update_data.py
+    with open(
+        "../Keyboards/LanguageKeyboards/French/Data/verbs.json", "w", encoding="utf-8",
+    ) as f:
+        json.dump(verbs_formatted, f, ensure_ascii=False, indent=2)
 
 print(f"Wrote file verbs.json with {len(verbs_formatted)} verbs.")
diff --git a/Data/German/nouns/format_nouns.py b/Data/German/nouns/format_nouns.py
@@ -7,9 +7,15 @@
 
 import collections
 import json
+import sys
 
-with open("nounsQueried.json") as f:
-    nouns_list = json.load(f)
+file_path = sys.argv[0]
+if "German/nouns/" not in file_path:
+    with open("nounsQueried.json") as f:
+        nouns_list = json.load(f)
+else:  # is being called by update_data.py
+    with open("./German/nouns/nounsQueried.json") as f:
+        nouns_list = json.load(f)
 
 
 def map_genders(wikidata_gender):
@@ -23,9 +29,9 @@ def map_genders(wikidata_gender):
     """
     if wikidata_gender in ["masculine", "Q499327"]:
         return "M"
-    if wikidata_gender in ["feminine", "Q1775415"]:
+    elif wikidata_gender in ["feminine", "Q1775415"]:
         return "F"
-    if wikidata_gender in ["neuter", "Q1775461"]:
+    elif wikidata_gender in ["neuter", "Q1775461"]:
         return "N"
     else:
         return ""  # nouns could have a gender that is not valid as an attribute
@@ -173,11 +179,17 @@ def order_annotations(annotation):
 
 nouns_formatted = collections.OrderedDict(sorted(nouns_formatted.items()))
 
-with open(
-    "../../../Keyboards/LanguageKeyboards/German/Data/nouns.json",
-    "w",
-    encoding="utf-8",
-) as f:
-    json.dump(nouns_formatted, f, ensure_ascii=False, indent=2)
+if "German/nouns/" not in file_path:
+    with open(
+        "../../../Keyboards/LanguageKeyboards/German/Data/nouns.json",
+        "w",
+        encoding="utf-8",
+    ) as f:
+        json.dump(nouns_formatted, f, ensure_ascii=False, indent=2)
+else:  # is being called by update_data.py
+    with open(
+        "../Keyboards/LanguageKeyboards/German/Data/nouns.json", "w", encoding="utf-8",
+    ) as f:
+        json.dump(nouns_formatted, f, ensure_ascii=False, indent=2)
 
 print(f"Wrote file nouns.json with {len(nouns_formatted)} nouns.")
diff --git a/Data/German/prepositions/format_prepositions.py b/Data/German/prepositions/format_prepositions.py
@@ -7,9 +7,15 @@
 
 import collections
 import json
+import sys
 
-with open("prepositionsQueried.json") as f:
-    prepositions_list = json.load(f)
+file_path = sys.argv[0]
+if "German/prepositions/" not in file_path:
+    with open("prepositionsQueried.json") as f:
+        prepositions_list = json.load(f)
+else:  # is being called by update_data.py
+    with open("./German/prepositions/prepositionsQueried.json") as f:
+        prepositions_list = json.load(f)
 
 
 def convert_cases(case):
@@ -70,11 +76,19 @@ def order_annotations(annotation):
 
 prepositions_formatted = collections.OrderedDict(sorted(prepositions_formatted.items()))
 
-with open(
-    "../../../Keyboards/LanguageKeyboards/German/Data/prepositions.json",
-    "w",
-    encoding="utf-8",
-) as f:
-    json.dump(prepositions_formatted, f, ensure_ascii=False, indent=2)
+if "German/prepositions/" not in file_path:
+    with open(
+        "../../../Keyboards/LanguageKeyboards/German/Data/prepositions.json",
+        "w",
+        encoding="utf-8",
+    ) as f:
+        json.dump(prepositions_formatted, f, ensure_ascii=False, indent=2)
+else:  # is being called by update_data.py
+    with open(
+        "../Keyboards/LanguageKeyboards/German/Data/prepositions.json",
+        "w",
+        encoding="utf-8",
+    ) as f:
+        json.dump(prepositions_formatted, f, ensure_ascii=False, indent=2)
 
 print(f"Wrote file prepositions.json with {len(prepositions_formatted)} prepositions.")
diff --git a/Data/German/verbs/format_verbs.py b/Data/German/verbs/format_verbs.py
@@ -7,9 +7,15 @@
 
 import collections
 import json
+import sys
 
-with open("verbsQueried.json") as f:
-    verbs_list = json.load(f)
+file_path = sys.argv[0]
+if "German/verbs/" not in file_path:
+    with open("verbsQueried.json") as f:
+        verbs_list = json.load(f)
+else:  # is being called by update_data.py
+    with open("./German/verbs/verbsQueried.json") as f:
+        verbs_list = json.load(f)
 
 verbs_formatted = {}
 
@@ -133,11 +139,17 @@ def assign_past_participle(verb, tense):
 
 verbs_formatted = collections.OrderedDict(sorted(verbs_formatted.items()))
 
-with open(
-    "../../../Keyboards/LanguageKeyboards/German/Data/verbs.json",
-    "w",
-    encoding="utf-8",
-) as f:
-    json.dump(verbs_formatted, f, ensure_ascii=False, indent=2)
+if "German/verbs/" not in file_path:
+    with open(
+        "../../../Keyboards/LanguageKeyboards/German/Data/verbs.json",
+        "w",
+        encoding="utf-8",
+    ) as f:
+        json.dump(verbs_formatted, f, ensure_ascii=False, indent=2)
+else:  # is being called by update_data.py
+    with open(
+        "../Keyboards/LanguageKeyboards/German/Data/verbs.json", "w", encoding="utf-8",
+    ) as f:
+        json.dump(verbs_formatted, f, ensure_ascii=False, indent=2)
 
 print(f"Wrote file verbs.json with {len(verbs_formatted)} verbs.")
diff --git a/Data/Portuguese/nouns/format_nouns.py b/Data/Portuguese/nouns/format_nouns.py
@@ -7,9 +7,15 @@
 
 import collections
 import json
+import sys
 
-with open("nounsQueried.json") as f:
-    nouns_list = json.load(f)
+file_path = sys.argv[0]
+if "Portuguese/nouns/" not in file_path:
+    with open("nounsQueried.json") as f:
+        nouns_list = json.load(f)
+else:  # is being called by update_data.py
+    with open("./Portuguese/nouns/nounsQueried.json") as f:
+        nouns_list = json.load(f)
 
 
 def map_genders(wikidata_gender):
@@ -18,7 +24,7 @@ def map_genders(wikidata_gender):
     """
     if wikidata_gender in ["masculine", "Q499327"]:
         return "M"
-    if wikidata_gender in ["feminine", "Q1775415"]:
+    elif wikidata_gender in ["feminine", "Q1775415"]:
         return "F"
     else:
         return ""  # nouns could have a gender that is not valid as an attribute
@@ -105,11 +111,19 @@ def order_annotations(annotation):
 
 nouns_formatted = collections.OrderedDict(sorted(nouns_formatted.items()))
 
-with open(
-    "../../../Keyboards/LanguageKeyboards/Portuguese/Data/nouns.json",
-    "w",
-    encoding="utf-8",
-) as f:
-    json.dump(nouns_formatted, f, ensure_ascii=False, indent=2)
+if "Portuguese/nouns/" not in file_path:
+    with open(
+        "../../../Keyboards/LanguageKeyboards/Portuguese/Data/nouns.json",
+        "w",
+        encoding="utf-8",
+    ) as f:
+        json.dump(nouns_formatted, f, ensure_ascii=False, indent=2)
+else:  # is being called by update_data.py
+    with open(
+        "../Keyboards/LanguageKeyboards/Portuguese/Data/nouns.json",
+        "w",
+        encoding="utf-8",
+    ) as f:
+        json.dump(nouns_formatted, f, ensure_ascii=False, indent=2)
 
 print(f"Wrote file nouns.json with {len(nouns_formatted)} nouns.")
diff --git a/Data/Portuguese/verbs/format_verbs.py b/Data/Portuguese/verbs/format_verbs.py
@@ -7,9 +7,15 @@
 
 import collections
 import json
+import sys
 
-with open("verbsQueried.json") as f:
-    verbs_list = json.load(f)
+file_path = sys.argv[0]
+if "Portuguese/verbs/" not in file_path:
+    with open("verbsQueried.json") as f:
+        verbs_list = json.load(f)
+else:  # is being called by update_data.py
+    with open("./Portuguese/verbs/verbsQueried.json") as f:
+        verbs_list = json.load(f)
 
 verbs_formatted = {}
 
@@ -52,11 +58,19 @@
 
 verbs_formatted = collections.OrderedDict(sorted(verbs_formatted.items()))
 
-with open(
-    "../../../Keyboards/LanguageKeyboards/Portuguese/Data/verbs.json",
-    "w",
-    encoding="utf-8",
-) as f:
-    json.dump(verbs_formatted, f, ensure_ascii=False, indent=2)
+if "Portuguese/verbs/" not in file_path:
+    with open(
+        "../../../Keyboards/LanguageKeyboards/Portuguese/Data/verbs.json",
+        "w",
+        encoding="utf-8",
+    ) as f:
+        json.dump(verbs_formatted, f, ensure_ascii=False, indent=2)
+else:  # is being called by update_data.py
+    with open(
+        "../Keyboards/LanguageKeyboards/Portuguese/Data/verbs.json",
+        "w",
+        encoding="utf-8",
+    ) as f:
+        json.dump(verbs_formatted, f, ensure_ascii=False, indent=2)
 
 print(f"Wrote file verbs.json with {len(verbs_formatted)} verbs.")
diff --git a/Data/Russian/nouns/format_nouns.py b/Data/Russian/nouns/format_nouns.py
@@ -7,9 +7,15 @@
 
 import collections
 import json
+import sys
 
-with open("nounsQueried.json") as f:
-    nouns_list = json.load(f)
+file_path = sys.argv[0]
+if "Russian/nouns/" not in file_path:
+    with open("nounsQueried.json") as f:
+        nouns_list = json.load(f)
+else:  # is being called by update_data.py
+    with open("./Russian/nouns/nounsQueried.json") as f:
+        nouns_list = json.load(f)
 
 
 def map_genders(wikidata_gender):
@@ -23,9 +29,9 @@ def map_genders(wikidata_gender):
     """
     if wikidata_gender in ["masculine", "Q499327"]:
         return "M"
-    if wikidata_gender in ["feminine", "Q1775415"]:
+    elif wikidata_gender in ["feminine", "Q1775415"]:
         return "F"
-    if wikidata_gender in ["neuter", "Q1775461"]:
+    elif wikidata_gender in ["neuter", "Q1775461"]:
         return "N"
     else:
         return ""  # nouns could have a gender that is not valid as an attribute
@@ -173,11 +179,17 @@ def order_annotations(annotation):
 
 nouns_formatted = collections.OrderedDict(sorted(nouns_formatted.items()))
 
-with open(
-    "../../../Keyboards/LanguageKeyboards/Russian/Data/nouns.json",
-    "w",
-    encoding="utf-8",
-) as f:
-    json.dump(nouns_formatted, f, ensure_ascii=False, indent=2)
+if "Russian/nouns/" not in file_path:
+    with open(
+        "../../../Keyboards/LanguageKeyboards/Russian/Data/nouns.json",
+        "w",
+        encoding="utf-8",
+    ) as f:
+        json.dump(nouns_formatted, f, ensure_ascii=False, indent=2)
+else:  # is being called by update_data.py
+    with open(
+        "../Keyboards/LanguageKeyboards/Russian/Data/nouns.json", "w", encoding="utf-8",
+    ) as f:
+        json.dump(nouns_formatted, f, ensure_ascii=False, indent=2)
 
 print(f"Wrote file nouns.json with {len(nouns_formatted)} nouns.")