From da0bdf703b377f17693df0d33e3d9e3162537e7f Mon Sep 17 00:00:00 2001
From: Christian Risi <75698846+CnF-Gris@users.noreply.github.com>
Date: Sat, 4 Oct 2025 19:42:29 +0200
Subject: [PATCH] Added a way to see vocabulary size

---
 Project_Model/Libs/BPE/Classes/NanoSocratesSpecial.py | 4 ++++
 Project_Model/Libs/BPE/Classes/TokeNanoCore.py        | 8 +++++++-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/Project_Model/Libs/BPE/Classes/NanoSocratesSpecial.py b/Project_Model/Libs/BPE/Classes/NanoSocratesSpecial.py
index 61d4741..010ff79 100644
--- a/Project_Model/Libs/BPE/Classes/NanoSocratesSpecial.py
+++ b/Project_Model/Libs/BPE/Classes/NanoSocratesSpecial.py
@@ -29,6 +29,10 @@ class NanoSocratesSpecial(Encoder):
         VOC_LENGTH = len(self.__vocabulary)
         return BPE_OFFSET + VOC_LENGTH + 1
 
+    @property
+    def vocabulary_size(self) -> int:
+        return len(self.vocabulary)
+
     @property
     def vocabulary(self) -> dict[str, int]:
         return self.__vocabulary
diff --git a/Project_Model/Libs/BPE/Classes/TokeNanoCore.py b/Project_Model/Libs/BPE/Classes/TokeNanoCore.py
index f726a95..86bca19 100644
--- a/Project_Model/Libs/BPE/Classes/TokeNanoCore.py
+++ b/Project_Model/Libs/BPE/Classes/TokeNanoCore.py
@@ -24,7 +24,13 @@ class TokeNanoCore:
         self.__splitter = NanoSocratesSplitter(SPECIAL_REGEX, BPE_VOCABULARY_SIZE)
         self.__special_encoder = NanoSocratesSpecial(
             BPE_VOCABULARY_SIZE, special_token_list
-        ) 
+        )
+
+    @property
+    def vocabulary_size(self):
+        BPE_VOC_SIZE = self.__bpe_encoder.vocabulary_size
+        SPECIAL_VOC_SIZE = self.__special_encoder.vocabulary_size
+        return BPE_VOC_SIZE + SPECIAL_VOC_SIZE
 
     def encode(self, corpus: str) -> list[int]:
         output: list[int] = []