From db0682203cff791cb630411b9898888d63b6e911 Mon Sep 17 00:00:00 2001
From: Nitsud Yarg <relay01@gmail.com>
Date: Wed, 22 Apr 2026 22:11:44 -0700
Subject: [PATCH] these two are it

---
 add-readings.py   | 21 +++++++++------------
 get-properties.py |  3 ++-
 2 files changed, 11 insertions(+), 13 deletions(-)

diff --git a/add-readings.py b/add-readings.py
index 7dc3fcb..8369b97 100644
--- a/add-readings.py
+++ b/add-readings.py
@@ -58,27 +58,24 @@ def annotate_phrase(text: str) -> str:
 
 #print(annotate_phrase("私は学校へ行きます"))
 
-with open("words-readings.json", "r", encoding="utf-16le") as f:
-    readings = json.load(f)
-
-with open("dump.json", "r", encoding="utf-16le") as f:
+with open("dump2.json", "r", encoding="utf-16") as f:
     dump = json.load(f)
 
 vocab_dict = {}
 ## A micab phrase based word parser
 for cd in dump:
-    print(dump[cd]['nm'])
-    # node = tagger.parseToNode(dump[cd]['nm'])
+    print(dump[cd]['name_J'])
+    # node = tagger.parseToNode(dump[cd]['name_J'])
     # while node:
     #     # node.surface is the word; node.feature contains POS tags
     #     if node.surface:
     #         print(f"{node.surface}\t{node.feature}")
     #     node = node.next
-    anottated = annotate_phrase(dump[cd]['nm'])
-    if anottated['reading'] != dump[cd]['nm']:
+    anottated = annotate_phrase(dump[cd]['name_J'])
+    if anottated['reading'] != dump[cd]['name_J']:
         print(anottated['reading'])
         dump[cd]['kana'] = anottated['reading']
-    cd_nm = dump[cd]['nm']
+    cd_nm = dump[cd]['name_J']
     for word in anottated['vocab']:
         # Skip punctuation words hopefully
         if len(word) == 1 and has_kanji(word) == False:
@@ -93,11 +90,11 @@ for cd in dump:
         if cd_nm not in vocab_dict[word]['Examples']:
             vocab_dict[word]['Examples'] += (cd_nm,)
     print()
-    phrase = dump[cd]['de']
+    phrase = dump[cd]['desc_J']
     anottated = annotate_phrase(phrase)
     if anottated['reading'] != phrase:
         #print(anottated['reading'])
-        dump[cd]['furi_de'] = anottated['reading']
+        dump[cd]['desc_Furi'] = anottated['reading']
     for word in anottated['vocab']:
         if len(word) == 1 and has_kanji(word) == False:
             continue
@@ -114,7 +111,7 @@ for cd in dump:
 
 vocab_dict = sorted(vocab_dict.items(), key= lambda x: x[1]['count'], reverse=True)
 
-with open("dump-withkana2.json", "w", encoding="utf-16") as outfile:
+with open("dump2.json", "w", encoding="utf-16") as outfile:
     json.dump(dump, outfile, ensure_ascii=False, indent=2)
 
 with open("dump-vocab.json", "w", encoding="utf-16") as outfile:
diff --git a/get-properties.py b/get-properties.py
index 5d5cb25..a145ae1 100644
--- a/get-properties.py
+++ b/get-properties.py
@@ -1,6 +1,7 @@
 import mmap
 import struct
 from pathlib import Path
+import json
 
 prop_data = Path(f"YGO_2020/bin/CARD_Prop.bin").read_bytes() # Get all the bytes
 
@@ -86,7 +87,7 @@ desc_data = Path(f"YGO_2020/bin/CARD_Desc_{language_code}.bin").read_bytes()
 
 get_props()
 
-with open("dump2.json", "w", encoding="utf-16le") as outfile:
+with open("dump2.json", "w", encoding="utf-16") as outfile:
     json.dump(cd_db, outfile, ensure_ascii=False, indent=2)
 
 print()