Upload 3 files

.gitattributes

@@ -111,3 +111,4 @@ Danbooru[[:space:]]Prompt[[:space:]]Selector/TEST2024/NAIA_0101_console_testv2.e
 Danbooru[[:space:]]Prompt[[:space:]]Selector/TEST2024/NAIA_0102_testv2.exe filter=lfs diff=lfs merge=lfs -text
 Danbooru[[:space:]]Prompt[[:space:]]Selector/TEST2024/NAIA_0103_testv2.exe filter=lfs diff=lfs merge=lfs -text
 Danbooru[[:space:]]Prompt[[:space:]]Selector/TEST2024/NAIA_0105_testv2.exe filter=lfs diff=lfs merge=lfs -text
+Danbooru[[:space:]]Prompt[[:space:]]Selector/TEST2024/NAIA_0107_testv3.exe filter=lfs diff=lfs merge=lfs -text

Danbooru Prompt Selector/TEST2024/NAIA_0107_testv3.exe

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9feca3cdd1196a20b982072bdc329aa28eb4cf5282199f8dc4fa59f8881c3521
+size 837947086

Danbooru Prompt Selector/TEST2024/NAIA_search.py

@@ -92,7 +92,22 @@ def process_perfect_negative_group(df, perfect_negative_group):
 
     return df
 
-def search(df, search_request, exclude_request, E, N, S, G):
+def extract_and_split(search_request):
+    curly_brace_group = []
+    while '{' in search_request:
+        start_index = search_request.find('{')
+        end_index = search_request.find('}')
+        if end_index != -1:
+            curly_brace_content = search_request[start_index:end_index + 1]
+            curly_brace_group.append(curly_brace_content)
+            search_request = search_request.replace(curly_brace_content, '', 1)
+        else:
+            break
+
+    split_requests = [item.strip() for item in search_request.split(',') if item.strip()]
+    return curly_brace_group, split_requests
+
+def search(df, search_request, exclude_request, E=None, N=None, S=None, G=None):
     if(E == 0):
         df = df[~(df['rating'] == 'e')]
     if(N == 0):
@@ -108,9 +123,8 @@ def search(df, search_request, exclude_request, E, N, S, G):
 
     #search_request에 대한 처리
     #처리순서 normal -> curly -> asterisk
-    split_requests = [item.strip() for item in search_request.split(',')]
-
-    curly_brace_group = [item for item in split_requests if item.startswith('{') and item.endswith('}')]
+    #solo, 1girl, {hololive, animal ears|nijisanji, loli}
+    curly_brace_group, split_requests = extract_and_split(search_request)
     asterisk_group = [item for item in split_requests if item.startswith('*')]
     normal_group = [item for item in split_requests if item not in curly_brace_group + asterisk_group]
     #normal_group = [re.escape(item) if any(char in item for char in special_chars) else item for item in normal_group]
@@ -132,35 +146,54 @@ def search(df, search_request, exclude_request, E, N, S, G):
             if(len(df) == 0):
                 return None
 
-        #OR 처리
-        if curly_brace_group:
-            for keyword in curly_brace_group:
-                or_search_keyword = [item.strip() for item in keyword[1:-1].split('|')]
-                results = pd.DataFrame()
-                for keyword in or_search_keyword:
-                    if keyword.startswith('*'):
-                        keyword = keyword[1:]
-                    request_regex = False
-                    if any(char in keyword for char in special_chars): 
-                        keyword = re.escape(keyword)
-                        request_regex = True
+    #OR 처리
+    if curly_brace_group:
+        for keyword in curly_brace_group:
+            or_search_keyword = [item.strip() for item in keyword[1:-1].split('|')]
+            results = pd.DataFrame()
+            for keyword in or_search_keyword:
+                keywords = [item.strip() for item in keyword.split(',')]
+                matched_rows = None
+                for keyword in keywords:
                     for column in ['copyright', 'character', 'artist', 'meta', 'general']:
-                        if request_regex: matched_rows = df[df[column].str.contains(keyword, na=False, regex=True)]
-                        else: matched_rows = df[df[column].str.contains(keyword, na=False)]
-                        if not matched_rows.empty:
-                            results = pd.concat([results, matched_rows])
+                        request_regex = False
+                        if any(char in keyword for char in special_chars): 
+                            keyword = re.escape(keyword)
+                            request_regex = True
+                        if keyword == keywords[0]:
+                            if request_regex: matched_rows = df[df[column].str.contains(keyword, na=False, regex=True)]
+                            else: matched_rows = df[df[column].str.contains(keyword, na=False)]
+                        else:
+                            print(keyword, len(matched_rows))
+                            if request_regex:
+                                ndf = matched_rows[matched_rows[column].str.contains(keyword, na=False, regex=True)]
+                            else: 
+                                ndf = matched_rows[matched_rows[column].str.contains(keyword, na=False)]
+                            print(keyword, len(matched_rows), len(ndf))
+                            if not ndf.empty:
+                                matched_rows = ndf.copy()
+                        if keyword == keywords[0] and not matched_rows.empty:
                             break
-                del[[df]]
-                df = results.copy()
-                del[[results]]
-            if(len(df) == 0):
-                return None
-        
-        #Perfect Matching 처리
-        if asterisk_group:
-            df = process_asterisk_group(df,asterisk_group)
-            if(len(df) == 0):
-                return None
+                        else:
+                            if not matched_rows.empty and not ndf.empty:
+                                ndf = None
+                                break
+
+                if not matched_rows.empty:
+                    results = pd.concat([results, matched_rows])
+                    print(results)
+            del[[df]]
+            results = results.drop_duplicates()
+            df = results.copy()
+            del[[results]]
+        if(len(df) == 0):
+            return None
+    
+    #Perfect Matching 처리
+    if asterisk_group:
+        df = process_asterisk_group(df,asterisk_group)
+        if(len(df) == 0):
+            return None
     
     #Exclude 처리
     if negative_split_requests:
@@ -174,17 +207,3 @@ def search(df, search_request, exclude_request, E, N, S, G):
             if(len(df) == 0):
                 return None
     return df
-    
-
-
-
-
-
-
-
-
-
-
-
-
-