오탈자 관련 오류 수정

DIW_2505C.json

@@ -596,7 +596,7 @@
       "value": true,
       "points": 3,
       "category": "Boolean",
-      "item": "문구 (…지역이 해당하는 티그리스강과…)/이 → 에 글자바꿈"
+      "item": "문구 (…지역이 해당하는 티그리스강과…)/이 → 에 글자바꿈"  
     },
     "32": {
       "path": "boolean(//CHAR[contains(translate(text(), ' ', ''),'나는반드')])",

diwScoring2.py

@@ -1004,42 +1004,45 @@ class XMLScorer:
         return xml_data
     
     def typo_check(self, correct_answer_file, user_answer_file, chart_xml):
+        
+        # 문자열 리스트를 필터링
+        def clean_text_list(text_list, ignore_words=None):
+            result = []
+            for text in text_list:
+                if ignore_words:
+                    text = text.replace(ignore_words, '')
+                text = text.replace(' ', '')  # 공백 제거
+                text = re.sub(r'\d+\.\s*|-', '', text)  # 숫자. / - 제거
+                result.append(text)
+            return result
+        
+        # 1. 텍스트 추출
+        # 2. 공백제거, 특정 형식 제거
+        # 3. 리스트를 문자열로 변환
+        
         user_answer_root = ET.parse(user_answer_file).getroot()
         correct_answer_root = ET.parse(correct_answer_file).getroot()
         
         # xpath로 바이너리 부분추출
         user_input_text = user_answer_root.xpath('//CHAR//text()[not(ancestor::HEADER) and not(ancestor::TABLE)]')
-        user_table_text = user_answer_root.xpath('//TABLE//CHAR//text()')
-        user_input_text += user_table_text
-
         correct_input_text = correct_answer_root.xpath('//CHAR//text()[not(ancestor::HEADER) and not(ancestor::TABLE)]')
-        correct_table_text = correct_answer_root.xpath('//TABLE//CHAR//text()')
-        correct_input_text += correct_table_text
         
-        # 차트 XML에서 제목 추출
+        # 테이블 구간 추출
+        user_table_text = user_answer_root.xpath('//TABLE//CHAR//text()')
+        correct_table_text = correct_answer_root.xpath('//TABLE//CHAR//text()')
+        
+        # 차트 XML에서 차트제목 추출
         if chart_xml is not None:
             chart_xml_tree = ET.fromstring(chart_xml)
                 
             # 차트 제목 추출
-            user_chart_title = chart_xml_tree.xpath('/c:chartSpace/c:chart/c:title/c:tx/c:rich/a:p/a:r/a:t', namespaces={'c': 'http://schemas.openxmlformats.org/drawingml/2006/chart', 'a': 'http://schemas.openxmlformats.org/drawingml/2006/main'})
+            chart_title = chart_xml_tree.xpath('/c:chartSpace/c:chart/c:title/c:tx/c:rich/a:p/a:r/a:t', namespaces={'c': 'http://schemas.openxmlformats.org/drawingml/2006/chart', 'a': 'http://schemas.openxmlformats.org/drawingml/2006/main'})
             
             # 차트 제목이 존재하는 경우
-            if user_chart_title:
+            if chart_title:
-                user_input_text.append(user_chart_title[0].text)
+                user_chart_title = chart_title[0].text
-
-                # 차트 제목 정답 텍스트 추출
                 correct_chart_title = self.scoring_criteria["2"]["50"]["searchValue"]
-                correct_input_text.append(correct_chart_title)
 
-        # 각 요소에서 공백 제거
-        user_input_text = [text.replace(' ', '') for text in user_input_text]
-        correct_input_text = [text.replace(' ', '') for text in correct_input_text]
-
-        
-        # 숫자와 특정 형식 제거 (예: 1., 2., 3., -)
-        user_input_text = [re.sub(r'\d+\.\s*|-', '', text) for text in user_input_text]
-        correct_input_text = [re.sub(r'\d+\.\s*|-', '', text) for text in correct_input_text]
-    
         try :
             ignore_word = self.scoring_criteria["2"]["29"]["ignoreWord"]
             # 특정 단어 제거
@@ -1052,20 +1055,49 @@ class XMLScorer:
             ignore_word = None
         
         # print(f"ignore_word: {ignore_word}")
-                
+        
+        # 문자열 필터링
+        correct_input_text = clean_text_list(correct_input_text, ignore_word)
+        user_input_text = clean_text_list(user_input_text, ignore_word)
+        
+        correct_table_text = clean_text_list(correct_table_text)
+        user_table_text = clean_text_list(user_table_text)
+        
+        correct_chart_title = clean_text_list(correct_chart_title)
+        user_chart_title = clean_text_list(user_chart_title)
+    
         # 리스트를 하나의 문자열로 변경
+        correct_input_text_str = ''.join(correct_input_text)
         user_input_text_str = ''.join(user_input_text)
-        currect_input_text_str = ''.join(correct_input_text)
 
+        correct_table_text_str = ''.join(correct_table_text)
+        user_table_text_str = ''.join(user_table_text)
+        
+        correct_chart_title_str = ''.join(correct_chart_title)
+        user_chart_title_str = ''.join(user_chart_title)
+        
         print("user_input_text as string:")
         print(user_input_text_str)
-        print("\ncurrect_input_text_answer as string:")
+        print("\n")
-        print(currect_input_text_str)
+        print("correct_input_text_answer as string:")
+        print(correct_input_text_str)
         
         # 문자열의 차이를 비교
-        diff = difflib.ndiff(currect_input_text_str, user_input_text_str)
+        text_diff = difflib.ndiff(correct_input_text_str, user_input_text_str)
-        diff_list = list(diff)
+        table_text_diff = difflib.ndiff(correct_table_text_str, user_table_text_str)
-
+        chart_title_diff = difflib.ndiff(correct_chart_title_str, user_chart_title_str)
+        
+        # text_diff = difflib.ndiff(correct_input_text, user_input_text)
+        # table_text_diff = difflib.ndiff(correct_table_text, user_table_text)
+        # chart_title_diff = difflib.ndiff(correct_chart_title, user_chart_title)
+        # diff_list = list(diff)
+        text_list = list(text_diff)
+        table_list = list(table_text_diff)
+        chart_list = list(chart_title_diff)
+        
+        diff_list = text_list + table_list + chart_list
+        # diff_list = text_list + table_list
+        
         # 차이점을 정리하여 result_diff에 저장
         result_diff = []
         
@@ -1275,8 +1307,8 @@ def main():
         # 'D',
     ]
 
-    test_mode = False
+    # test_mode = False
-    # test_mode = True #/TEST 폴더 채점시 
+    test_mode = True #/TEST 폴더 채점시 
     
     output_excel_paths = []
     for exam_type in exam_types:

zzz.xbook

@@ -1 +1 @@
-[{"kind":2,"language":"xpath","value":"//a:t[text()='클라우드 보안투자']/ancestor::a:r//a:ea/@typeface"},{"kind":2,"language":"xpath","value":"boolean(//FONTFACE[@Lang='Hangul']/FONT[@Id=//CHARSHAPE/FONTID/@Hangul]/@Name='바탕' and //CHARSHAPE/@Height='1000' and //PARASHAPE/PARAMARGIN/@LineSpacing='160' and //PARASHAPE/@Align='Justify')"},{"kind":2,"language":"xpath","value":"//FONTFACE[@Lang='Hangul']/FONT[@Id=//CHARSHAPE/FONTID/@Hangul]/@Name='바탕'"},{"kind":2,"language":"xpath","value":"//FONTFACE[@Lang='Hangul']/FONT[@Id=//CHARSHAPE/FONTID/@Hangul]/@Name='바탕' and //CHARSHAPE/@Height='1000' and //PARASHAPE/PARAMARGIN/@LineSpacing='160' and //PARASHAPE/@Align='Justify')"},{"kind":2,"language":"xpath","value":"/HWPML/BODY/SECTION/P[19]"},{"kind":2,"language":"xpath","value":"//SECTION"},{"kind":2,"language":"xpath","value":"//P"},{"kind":2,"language":"xpath","value":"//P[.//FIELDBEGIN[@Type='Hyperlink'] and .//CHAR[contains(., 'http')]]"},{"kind":2,"language":"xpath","value":"//PICTURE[./IMAGE[@BinItem=//BINITEM[@Format='JPG']/@BinData]]/SHAPEOBJECT/POSITION[not(@TreatAsChar='true')]/@HorzOffset"},{"kind":2,"language":"xpath","value":"//CHARSHAPE[@Id=//TEXT[CHAR[text()='지']]/@CharShape]/@Height"},{"kind":2,"language":"xpath","value":"//TEXT[CHAR[text()='지']]/@CharShape"}]
+[{"kind":2,"language":"xpath","value":"//a:t[text()='클라우드 보안투자']/ancestor::a:r//a:ea/@typeface"},{"kind":2,"language":"xpath","value":"boolean(//FONTFACE[@Lang='Hangul']/FONT[@Id=//CHARSHAPE/FONTID/@Hangul]/@Name='바탕' and //CHARSHAPE/@Height='1000' and //PARASHAPE/PARAMARGIN/@LineSpacing='160' and //PARASHAPE/@Align='Justify')"},{"kind":2,"language":"xpath","value":"//FONTFACE[@Lang='Hangul']/FONT[@Id=//CHARSHAPE/FONTID/@Hangul]/@Name='바탕'"},{"kind":2,"language":"xpath","value":"//FONTFACE[@Lang='Hangul']/FONT[@Id=//CHARSHAPE/FONTID/@Hangul]/@Name='바탕' and //CHARSHAPE/@Height='1000' and //PARASHAPE/PARAMARGIN/@LineSpacing='160' and //PARASHAPE/@Align='Justify')"},{"kind":2,"language":"xpath","value":"/HWPML/BODY/SECTION/P[19]"},{"kind":2,"language":"xpath","value":"//SECTION"},{"kind":2,"language":"xpath","value":"//P"},{"kind":2,"language":"xpath","value":"//P[.//FIELDBEGIN[@Type='Hyperlink'] and .//CHAR[contains(., 'http')]]"},{"kind":2,"language":"xpath","value":"//PICTURE[./IMAGE[@BinItem=//BINITEM[@Format='JPG']/@BinData]]/SHAPEOBJECT/POSITION[not(@TreatAsChar='true')]/@HorzOffset"},{"kind":2,"language":"xpath","value":"//CHARSHAPE[@Id=//TEXT[CHAR[text()='지']]/@CharShape]/@Height"},{"kind":2,"language":"xpath","value":"//TABLE//CHAR//text()"}]