Now seems to be working

flask_be/engine/cooccorrenze.py

@@ -44,6 +44,9 @@ class cooccorrenze(basicQueries):
             df_new = pd.DataFrame(columns=list(listatesti.columns))
             cod_cols = []
 
+            ##########################################
+            # KORA: questo blocco sembra troppo lento!
+            ##########################################
             for index1, row1 in listatesti.iterrows():
                 for index2, row2 in textlist.iterrows():
                     cond1 = row1['ntx'] == row2['ntx']
@@ -56,6 +59,11 @@ class cooccorrenze(basicQueries):
                         cod_cols.append(f'cod{cod}')
                         df_new = pd.concat([df_new, row1.to_frame().T])
 
+            ##########################################
+            # KORA: fino a qui
+            ##########################################
+
+
             listatesti = df_new
 
             cod += 1

flask_be/engine/decoder/test_decoder_kora.py

@@ -385,6 +385,7 @@ def getKeyByCode(keyFile):
     with open(keyFile, 'r') as file1:
         reader = csv.reader(file1)
         key = [int(row[0]) for index, row in enumerate(reader) if index>1]
+        # Apparently, only the first half of the key is actually used!
         halfKeyLen = len(key)//2
         key=key[:halfKeyLen]
         return key
@@ -422,27 +423,40 @@ def shiftchar(char0, shift):
     return chr(ord(char0) + shift)
 
 # %%
+from os import listdir
+
 keyPath = 'keys/'
-key_p07 = getKeyByCode(keyPath+'key_p07.csv')
-# %%
-with open('../../../db/ndg2.gat4/itxt/p07', 'rb') as file1:
-    file1.seek(4)
-    p07_enc = file1.read().decode(encoding="utf-32-le")
-# %%
-print( decodeTextByKey(p07_enc[21:1000], key_p07, 21) )
-# %%
-affa2==key_p07
-# %%
-for i, entry in enumerate(affa2):
-    print(i, entry==key_p07[i])
+itxtPath = '../../../db/ndg2.gat4/itxt/'
+
+files = listdir(keyPath)
+keyFiles = [file for file in files if (file.startswith('key_') and file.endswith('.csv'))]
+
+keys = {}
+files = {}
+for keyFile in keyFiles:
+    code = keyFile.replace('key_', '').replace('.csv', '')
+    try:
+        keys[code] = getKeyByCode(keyPath+keyFile)
+        with open('../../../db/ndg2.gat4/itxt/'+code, 'rb') as file1:
+            file1.seek(4)
+            files[code] = file1.read().decode(encoding="utf-32-le")
+    except:
+        pass
+#
+codes = keys.keys()
 # %%
-affamezzi=affa2[:166]
+import random
+
+decoded = {}
+for ind, code in enumerate(codes):
+    rand1 = random.randint(1, 15)
+    rand2 = random.randint(1, 15)+500
+    decoded[code] = decodeTextByKey(files[code][rand1:rand2], keys[code], rand1)
+    print(ind, code)
+    print(decoded[code])
+    print()
 # %%
-print(affa2[166:])
+codes
 # %%
-affamezzi==affa2[166:]
+decoded['fq']
 # %%
-from os import listdir
-
-files = listdir(keyPath)
-keyFiles = [file for file in files if (file.startswith('key_') and file.endswith('.csv'))]

flask_be/interface_sqlite3/encdec/de_code.py

@@ -37,6 +37,8 @@ class keyRing:
         with open(self.keyPath + keyFile, 'r') as file1:
             reader = csv.reader(file1)
             key = [int(row[0]) for index, row in enumerate(reader) if index>1]
+            halfKeyLen = len(key)//2
+            key=key[:halfKeyLen]
             return key
 
 

flask_be/interface_sqlite3/query_handlers.py

@@ -72,7 +72,7 @@ class queryHandlerBasicSqlite(QueryHandlerAbstract):
         
         if self.textsEncoded and self.keyRing.textKeys.get(sigla) is not None:
             key = self.keyRing.textKeys.get(sigla)
-            cont = dc.decodeTextByKey(cont, key, minChar)
+            cont = dc.decodeTextByKey(cont, key, minChar-1)
         
         return cont