From a88e3603279bd64f15c93f3b5e2c8ef8af0035de Mon Sep 17 00:00:00 2001
From: waterdrw <waterdrw@gmail.com>
Date: Sat, 18 Jan 2025 00:13:20 +0900
Subject: [PATCH] =?UTF-8?q?XML=20=EB=82=B4=EC=9A=A9=20=EC=A4=91=20Chart=20?=
 =?UTF-8?q?XML=20=EB=82=B4=EC=9A=A9=EC=9D=B4=20=EC=97=86=EC=9C=BC=EB=A9=B4?=
 =?UTF-8?q?=200=EC=A0=90=20=EC=B2=98=EB=A6=AC=EB=A1=9C=20=EB=84=98?=
 =?UTF-8?q?=EC=96=B4=EA=B0=80=EB=8F=84=EB=A1=9D=20=EB=A1=9C=EC=A7=81=20?=
 =?UTF-8?q?=EC=88=98=EC=A0=95?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 score5.py | 94 ++++++++++++++++++++++++++-----------------------------
 1 file changed, 44 insertions(+), 50 deletions(-)

diff --git a/score5.py b/score5.py
index 0f9c899..95cb5b8 100644
--- a/score5.py
+++ b/score5.py
@@ -52,14 +52,13 @@ class XMLScorer:
                 return None
             
     def chart_query_xml(self, tree, xpath, namespaces):
-        try:
-            result = tree.xpath(xpath, namespaces=namespaces)
-            if type(result) is list and len(result) == 0:
-                return None
-            
-            return result
-        except ET.XPathEvalError as e:
+        
+        result = tree.xpath(xpath, namespaces=namespaces)
+        if type(result) is list and len(result) == 0:
             return None
+        
+        return result
+    
     
     # 유사한 텍스트 찾기
     def find_similar_text(self, root, target_text, threshold=0.5):
@@ -109,7 +108,7 @@ class XMLScorer:
             }
             
             if chart_xml is None:
-                chart_tree = ET.fromstring('')
+                chart_tree = ET.fromstring('<xml></xml>')
             else:
                 chart_tree = ET.fromstring(chart_xml)
             
@@ -235,47 +234,42 @@ class XMLScorer:
             }
             
     def binary_to_chartxml(self, xml_path):
-        try:
-            print(f'binary_to_chartxml {xml_path}')
-            tree = ET.parse(xml_path)
-            root = tree.getroot()
-            
-            binary_data = root.xpath('//BINDATA[@Id=//BINITEM[@Format="OLE"]/@BinData]/text()')
-            if not binary_data:
-                raise ValueError("No binary data found in the XML.")
-            binary_data = binary_data[0].encode('utf-8')
-
-            # <BINDATA ...> 태그와 그 내부 내용을 삭제합니다.
-            encoded_data = re.sub(b'<BINDATA.*?>', b'', binary_data)
-            encoded_data = encoded_data.replace(b'</BINDATA>', b'')
-            encoded_data = encoded_data.replace(b'\r\n', b'')
-
-            # base64 디코딩을 수행합니다.
-            decoded_data = base64.b64decode(encoded_data+b'==')
-                
-            # 디코딩된 데이터 내용 중 xml 형식만 추출할 때 <c:chartSpace>, </c:chartSpace> 사이의 데이터만 추출.
-            start = decoded_data.find(b'<?xml')
-            print(start)
-            end = decoded_data.find(b'</c:chartSpace>')
-            print(end)
-            xml_data = decoded_data[start:end+len(b'</c:chartSpace>')]
-
-            # 디코딩된 데이터를 파일로 저장합니다.
-            base_filename = os.path.splitext(xml_path)[0]
-            new_filename = f'{base_filename}.xml'
-            with open(new_filename, 'wb') as file:
-                    file.write(xml_data)
-            
-            return xml_data
         
-        except ET.ParseError as e:
-            print(f"XML 파싱 오류: {str(e)}")
-        except IndexError as e:
-            print(f"IndexError: {str(e)}")
-        except ValueError as e:
-            print(f"ValueError: {str(e)}")
-        except Exception as e:
-            print(f"Unexpected error: {str(e)}")
+        print(f'binary_to_chartxml {xml_path}')
+        tree = ET.parse(xml_path)
+        root = tree.getroot()
+        
+        binary_data = root.xpath('//BINDATA[@Id=//BINITEM[@Format="OLE"]/@BinData]/text()')
+        if not binary_data:
+            return None
+        binary_data = binary_data[0].encode('utf-8')
+
+        # <BINDATA ...> 태그와 그 내부 내용을 삭제합니다.
+        encoded_data = re.sub(b'<BINDATA.*?>', b'', binary_data)
+        encoded_data = encoded_data.replace(b'</BINDATA>', b'')
+        encoded_data = encoded_data.replace(b'\r\n', b'')
+
+        # base64 디코딩을 수행합니다.
+        decoded_data = base64.b64decode(encoded_data+b'==')
+            
+        # 디코딩된 데이터 내용 중 xml 형식만 추출할 때 <c:chartSpace>, </c:chartSpace> 사이의 데이터만 추출.
+        start = decoded_data.find(b'<?xml')
+        print(start)
+        end = decoded_data.find(b'</c:chartSpace>')
+        print(end)
+        xml_data = decoded_data[start:end+len(b'</c:chartSpace>')]
+
+        if -1 in [start, end]:
+            return None
+        
+        # 디코딩된 데이터를 파일로 저장합니다.
+        base_filename = os.path.splitext(xml_path)[0]
+        new_filename = f'{base_filename}.xml'
+        with open(new_filename, 'wb') as file:
+                file.write(xml_data)
+        
+        return xml_data
+    
     
     # XML 파일 채점
     def score_directory(self, xml_directory):
@@ -365,10 +359,10 @@ class XMLScorer:
 
 
 def main():
-    scoring_criteria_path = r'C:\Users\dra\project\HWP-Scoring\scoring_criteria.json'
+    scoring_criteria_path = r'./scoring_criteria.json'
 
     # xml(hml)파일 디렉토리 경로
-    xml_directory = r'C:\Users\dra\project\HWP-Scoring\output'
+    xml_directory = r'./output'
 
     # 채점 클래스 초기화
     scorer = XMLScorer(scoring_criteria_path)