add --fix-xml

압축파일 내의 경로를 제거하도록 util.py 수정

.gitignore

@@ -9,3 +9,6 @@ __pycache__/
 metadata_1.json
 metadata_mi.json
 main.spec
+.vscode/settings.json
+build/
+dist/

UtilPack.py

@@ -232,10 +232,9 @@ def ExtractZIP(zip_file: str, extract_to: str):
 
 #
 def CreateZIP(output_zip: str, files: list[str]) -> bool:
-    with zipfile.ZipFile(output_zip, 'w') as zf:
+    with zipfile.ZipFile(output_zip, 'w', compression=zipfile.ZIP_DEFLATED) as zf:
         for file in files:
-            pathTemp = os.path.join('root', os.path.basename(file))
-            zf.write(file, pathTemp)
+            zf.write(file, os.path.basename(file))
     
     bRet = False
     if os.path.exists(output_zip):

main.py

@@ -39,6 +39,8 @@ def main(argc, argv):
     parser.add_argument('--print', dest='bPrint', action='store_true', help='comicinfo.xml 출력')
     parser.add_argument('--metadata', dest='bMetadata', action='store_true', help='.metadata 파일로부터 ComicInfo.xml 생성 및 CBZ에 추가')
     parser.add_argument('--verbose', dest='bVerbose', action='store_true', help='상세 로그 출력')
+    parser.add_argument('--fix-arc-path', dest='bFixArcPath', action='store_true', help='CBZ 아카이브의 내부 폴더 구조를 제거합니다.')
+    parser.add_argument('--fix-xml', dest='bFixXml', action='store_true', help='ComicInfo.xml의 특수문자(&) 이스케이프 및 문법 오류를 검사하고 수정합니다.')
     parser.add_argument('-v', '--version', action='version', version='ComicInfoXMLConv 1.0')
 
     args = parser.parse_args(argv[1:])  # argv[0]은 스크립트 이름 제외
@@ -52,68 +54,13 @@ def main(argc, argv):
     # 태그 파싱
     if args.info_tags is not None and len(args.info_tags) > 0:
         util.DbgOut(f"입력된 태그: {args.info_tags}", True)
-        listTags = args.info_tags.split(',')
-        util.DbgOut(f"태그 리스트: {listTags}", True)
+        # listTags = args.info_tags.split(',') # This variable is not used
+        # util.DbgOut(f"태그 리스트: {listTags}", True)
     
     # 단일 파일 처리 (--in 옵션)
     if True == util.IsExistsPath(args.arc_file):
         util.DbgOut(f"대상 파일: {args.arc_file}", True)
-        
-        # Path 변수 확장
-        arc_title = ExpandPathVars(args.info_title, args.arc_file)
-        arc_writer = ExpandPathVars(args.info_writer, args.arc_file)
-        arc_series = ExpandPathVars(args.info_series, args.arc_file)
-        arc_volume = ExpandPathVars(args.info_volume, args.arc_file)
-        arc_number = ExpandPathVars(args.info_number, args.arc_file)
-        arc_tags = args.info_tags.split(',') if args.info_tags else []
-        
-        # .metadata 옵션이 활성화된 경우
-        if True == args.bMetadata:
-            ProcessMetadataToCBZ(args.arc_file, args.bPrint, 
-                                   arc_volume, arc_number, args.info_count,
-                                   arc_title, arc_writer, arc_series,
-                                   arc_tags if arc_tags else None)
-            return
-        
-        listArcContents = util.GetZipContentList(args.arc_file)
-        
-        if True == any(item.lower() == "comicinfo.xml" for item in listArcContents):
-            util.DbgOut(f"comicinfo.xml 발견됨: {args.arc_file}", True)
-
-            comicinfo_xml_bytes = util.GetZippedFileByte(args.arc_file, "ComicInfo.xml")
-            if None != comicinfo_xml_bytes:  
-                modified = ModComicInfoXML(comicinfo_xml_bytes, arc_title, arc_writer, arc_series, arc_tags,
-                                              info_number=arc_number, info_volume=arc_volume, info_count=args.info_count)
-                
-                if True == args.bPrint:
-                    if modified is not None:
-                        print(modified.decode('utf-8'))
-                    else:
-                        print(comicinfo_xml_bytes.decode('utf-8'))
-                elif modified is not None:
-                    util.AddFileToZip(args.arc_file, "ComicInfo.xml", modified)
-                    util.DbgOut(f"ComicInfo.xml 업데이트됨: {args.arc_file}", True)
-        
-        else:
-            util.DbgOut(f"comicinfo.xml 없음: {args.arc_file}", True)
-            if arc_volume or arc_number or arc_title or arc_writer or arc_series or arc_tags or args.info_count:
-                new_xml = CreateComicInfoXML(
-                    info_title=arc_title if arc_title else "",
-                    info_writer=arc_writer if arc_writer else "",
-                    info_series=arc_series if arc_series else "",
-                    tags=arc_tags if arc_tags else [],
-                    pages=[],
-                    volume=arc_volume if arc_volume else "",
-                    number=arc_number if arc_number else "",
-                    count=int(args.info_count) if args.info_count is not None else -1
-                )
-                if new_xml:
-                    if True == args.bPrint:
-                        print(new_xml)
-                    else:
-                        util.AddFileToZip(args.arc_file, "ComicInfo.xml", new_xml.encode('utf-8'))
-                        util.DbgOut(f"ComicInfo.xml 생성됨: {args.arc_file}", True)
-        
+        process_archive_file(args.arc_file, args)
         return
     
     # 폴더 처리 (--root 옵션) - 하위 폴더 포함, CBZ 파일만 처리
@@ -127,66 +74,101 @@ def main(argc, argv):
                 continue
             
             util.DbgOut(f"파일 발견: {strFullPath}", True)
-    
-            # Path 변수 확장 (파일마다 달라짐)
-            arc_title = ExpandPathVars(args.info_title, strFullPath)
-            arc_writer = ExpandPathVars(args.info_writer, strFullPath)
-            arc_series = ExpandPathVars(args.info_series, strFullPath)
-            arc_volume = ExpandPathVars(args.info_volume, strFullPath)
-            arc_number = ExpandPathVars(args.info_number, strFullPath)
-            arc_tags = args.info_tags.split(',') if args.info_tags else []
-    
-            # .metadata 옵션이 활성화된 경우
-            if True == args.bMetadata:
-                ProcessMetadataToCBZ(strFullPath, args.bPrint, 
-                                       arc_volume, arc_number, args.info_count,
-                                       arc_title, arc_writer, arc_series,
-                                       arc_tags if arc_tags else None)
-                continue
-
-            listArcContents = util.GetZipContentList(strFullPath)
-            
-            if True == any(item.lower() == "comicinfo.xml" for item in listArcContents):
-                util.DbgOut(f"comicinfo.xml 발견됨: {strFullPath}", True)
-
-                comicinfo_xml_bytes = util.GetZippedFileByte(strFullPath, "ComicInfo.xml")
-                if None != comicinfo_xml_bytes:  
-                    modified = ModComicInfoXML(comicinfo_xml_bytes, arc_title, arc_writer, arc_series, arc_tags,
-                                                  info_number=arc_number, info_volume=arc_volume, info_count=args.info_count)
-                    
-                    if True == args.bPrint:
-                        if modified is not None:
-                            print(modified.decode('utf-8'))
-                        else:
-                            print(comicinfo_xml_bytes.decode('utf-8'))
-                    elif modified is not None:
-                        util.AddFileToZip(strFullPath, "ComicInfo.xml", modified)
-                        util.DbgOut(f"ComicInfo.xml 업데이트됨: {strFullPath}", True)
-            
-            else:
-                util.DbgOut(f"comicinfo.xml 없음: {strFullPath}", True)
-                if arc_volume or arc_number or arc_title or arc_writer or arc_series or arc_tags or args.info_count:
-                    new_xml = CreateComicInfoXML(
-                        info_title=arc_title if arc_title else "",
-                        info_writer=arc_writer if arc_writer else "",
-                        info_series=arc_series if arc_series else "",
-                        tags=arc_tags if arc_tags else [],
-                        pages=[],
-                        volume=arc_volume if arc_volume else "",
-                        number=arc_number if arc_number else "",
-                        count=int(args.info_count) if args.info_count is not None else -1
-                    )
-                    if new_xml:
-                        if True == args.bPrint:
-                            print(new_xml)
-                        else:
-                            util.AddFileToZip(strFullPath, "ComicInfo.xml", new_xml.encode('utf-8'))
-                            util.DbgOut(f"ComicInfo.xml 생성됨: {strFullPath}", True)
-            
+            process_archive_file(strFullPath, args)
 
     return
 
-#
+def process_archive_file(archive_path: str, args: argparse.Namespace):
+    """지정된 아카이브 파일에 대해 ComicInfo.xml을 처리합니다."""
+    # --fix-arc-path 옵션 처리
+    if args.bFixArcPath:
+        if FlattenZipArchive(archive_path):
+            util.DbgOut(f"아카이브 폴더 구조 제거 완료: {archive_path}", True)
+
+    # Path 변수 확장
+    arc_title = ExpandPathVars(args.info_title, archive_path)
+    arc_writer = ExpandPathVars(args.info_writer, archive_path)
+    arc_series = ExpandPathVars(args.info_series, archive_path)
+    arc_volume = ExpandPathVars(args.info_volume, archive_path)
+    arc_number = ExpandPathVars(args.info_number, archive_path)
+    arc_tags = args.info_tags.split(',') if args.info_tags else []
+
+    # info_count를 int로 변환 (argparse에서 str로 파싱됨)
+    arc_count = int(args.info_count) if args.info_count is not None else None
+
+    # .metadata 옵션이 활성화된 경우
+    if args.bMetadata:
+        ProcessMetadataToCBZ(archive_path, args.bPrint,
+                               arc_volume, arc_number, arc_count,
+                               arc_title, arc_writer, arc_series,
+                               arc_tags if arc_tags else None)
+        return
+
+    listArcContents = util.GetZipContentList(archive_path)
+    
+    comicinfo_path_in_zip = None
+    for item in listArcContents:
+        # os.path.basename은 '/' 또는 '\' 구분자를 사용하여 경로의 마지막 부분을 반환합니다.
+        if os.path.basename(item.lower()) == "comicinfo.xml":
+            comicinfo_path_in_zip = item
+            break
+    has_comicinfo = comicinfo_path_in_zip is not None
+
+    if has_comicinfo:
+        util.DbgOut(f"comicinfo.xml 발견됨: {archive_path} (경로: {comicinfo_path_in_zip})", True)
+        comicinfo_xml_bytes = util.GetZippedFileByte(archive_path, comicinfo_path_in_zip)
+        if comicinfo_xml_bytes:
+            fixed_xml = None
+            if args.bFixXml:
+                fixed_xml, msgs = ValidateAndFixComicInfoXML(comicinfo_xml_bytes)
+                for msg in msgs:
+                    util.DbgOut(msg, True)
+                if fixed_xml is not None:
+                    comicinfo_xml_bytes = fixed_xml
+
+            has_mods = any([arc_title, arc_writer, arc_series, arc_tags,
+                           arc_number, arc_volume, arc_count])
+
+            if not has_mods:
+                if fixed_xml is not None:
+                    util.AddFileToZip(archive_path, comicinfo_path_in_zip, fixed_xml)
+                    util.DbgOut(f"ComicInfo.xml 특수문자 수정 완료: {archive_path}", True)
+                if args.bPrint:
+                    print(comicinfo_xml_bytes.decode('utf-8'))
+                return
+
+            modified = ModComicInfoXML(comicinfo_xml_bytes, arc_title, arc_writer, arc_series, arc_tags,
+                                          info_number=arc_number, info_volume=arc_volume, info_count=arc_count)
+
+            if args.bPrint:
+                output = modified.decode('utf-8') if modified else comicinfo_xml_bytes.decode('utf-8')
+                print(output)
+            elif modified:
+                util.AddFileToZip(archive_path, comicinfo_path_in_zip, modified)
+                util.DbgOut(f"ComicInfo.xml 업데이트됨: {archive_path} (경로: {comicinfo_path_in_zip})", True)
+            elif fixed_xml is not None:
+                util.AddFileToZip(archive_path, comicinfo_path_in_zip, fixed_xml)
+                util.DbgOut(f"ComicInfo.xml 특수문자 수정 완료: {archive_path}", True)
+    else:
+        util.DbgOut(f"comicinfo.xml 없음: {archive_path}", True)
+        if arc_volume or arc_number or arc_title or arc_writer or arc_series or arc_tags or arc_count is not None:
+            new_xml = CreateComicInfoXML(
+                info_title=arc_title or "",
+                info_writer=arc_writer or "",
+                info_series=arc_series or "",
+                tags=arc_tags,
+                pages=[],
+                volume=arc_volume or "",
+                number=arc_number or "",
+                count=arc_count if arc_count is not None else -1
+            )
+            if new_xml:
+                if args.bPrint:
+                    print(new_xml)
+                else:
+                    util.AddFileToZip(archive_path, "ComicInfo.xml", new_xml.encode('utf-8'))
+                    util.DbgOut(f"ComicInfo.xml 생성됨: {archive_path}", True)
+
 def ExpandPathVars(text: str | None, filepath: str) -> str | None:
     """Replace path template variables (<filename>, <parentfolder>, etc.) with actual values.
     After variable expansion, if the result has a :s/pattern/replacement/ suffix,
@@ -194,7 +176,9 @@ def ExpandPathVars(text: str | None, filepath: str) -> str | None:
     """
     if not text:
         return text
-    dirpath = os.path.dirname(filepath)
+    # 경로 정규화: ./ 또는 ../ 등 상대 경로 표현을 제거하여 정확한 폴더명 추출
+    normpath = os.path.normpath(filepath)
+    dirpath = os.path.dirname(normpath)
     cur_folder = os.path.basename(dirpath) if dirpath else ""
     par_folder = os.path.basename(os.path.dirname(dirpath)) if dirpath and os.path.dirname(dirpath) else ""
     filename_no_ext = os.path.splitext(os.path.basename(filepath))[0]
@@ -202,7 +186,6 @@ def ExpandPathVars(text: str | None, filepath: str) -> str | None:
 
     var_map = {
         "filename": filename_no_ext,
-        "parentfolder": cur_folder,
         "currentfolder": cur_folder,
         "parentfolder": par_folder,
         "fullpath": filepath,
@@ -215,8 +198,8 @@ def ExpandPathVars(text: str | None, filepath: str) -> str | None:
     for key, value in var_map.items():
         result = result.replace(f"<{key}>", value)
 
-    # After variable expansion, check for :s/pattern/replacement/ suffix
-    m = re.match(r'^(.*):s(.)(.+?)\2(.*?)(?:\2([ig]*))?$', result, re.DOTALL)
+    # After variable expansion, check for :s/pattern/replacement/ or s/pattern/replacement/ suffix
+    m = re.match(r'^(.*):?s(.)(.+?)\2(.*?)(?:\2([ig]*))?$', result, re.DOTALL)
     if m:
         source = m.group(1)
         delim = m.group(2)
@@ -228,6 +211,8 @@ def ExpandPathVars(text: str | None, filepath: str) -> str | None:
         if 'i' in flags_str:
             flags |= re.IGNORECASE
         count = 0 if 'g' in flags_str else 1
+        # source가 비어있으면 정규식 미적용 (ResolveRegexTransform에서 처리)
+        if source:
             try:
                 result = re.sub(pattern, replacement_safe, source, count=count, flags=flags)
             except re.error:
@@ -235,6 +220,48 @@ def ExpandPathVars(text: str | None, filepath: str) -> str | None:
 
     return result
 
+def FlattenZipArchive(zip_path: str) -> bool:
+    """
+    ZIP 아카이브의 내부 폴더 구조를 제거합니다.
+    모든 파일을 루트 디렉토리로 이동시킵니다.
+    
+    Args:
+        zip_path: ZIP 파일 경로
+        
+    Returns:
+        구조가 변경되었으면 True, 아니면 False
+    """
+    try:
+        needs_flattening = False
+        with util.zipfile.ZipFile(zip_path, 'r') as zin:
+            for item in zin.infolist():
+                if '/' in item.filename or '\\' in item.filename:
+                    needs_flattening = True
+                    break
+        
+        if not needs_flattening:
+            return False
+
+        temp_zip = zip_path + '.tmp'
+        
+        with util.zipfile.ZipFile(zip_path, 'r') as zin:
+            with util.zipfile.ZipFile(temp_zip, 'w') as zout:
+                for item in zin.infolist():
+                    if item.is_dir():
+                        continue
+                    data = zin.read(item.filename)
+                    new_name = os.path.basename(item.filename)
+                    zout.writestr(new_name, data)
+        
+        util.shutil.move(temp_zip, zip_path)
+        return True
+        
+    except Exception as e:
+        util.DbgOut(f"아카이브 구조 변경 중 오류 발생: {e}", True)
+        if 'temp_zip' in locals() and os.path.exists(temp_zip):
+            os.remove(temp_zip)
+        return False
+
 
 def ResolveRegexTransform(text: str | None, current_value: str | None) -> str | None:
     """Apply regex substitution if text uses s/pattern/replacement/ syntax.
@@ -258,6 +285,38 @@ def ResolveRegexTransform(text: str | None, current_value: str | None) -> str |
     return text
 
 
+def ValidateAndFixComicInfoXML(xml_bytes: bytes) -> tuple[bytes | None, list[str]]:
+    try:
+        ET.fromstring(xml_bytes)
+        return (None, ["XML is well-formed."])
+    except ET.ParseError as e:
+        msgs = [f"Parse error: {e}"]
+
+    try:
+        text = xml_bytes.decode('utf-8')
+    except UnicodeDecodeError:
+        msgs.append("Cannot decode XML (expected UTF-8).")
+        return (None, msgs)
+
+    text, count = re.subn(
+        r'&(?!(?:amp|lt|gt|quot|apos);|#\d+;|#x[0-9a-fA-F]+;)',
+        '&amp;',
+        text
+    )
+    if count > 0:
+        msgs.append(f"Fixed {count} unescaped & character(s).")
+        fixed_bytes = text.encode('utf-8')
+        try:
+            ET.fromstring(fixed_bytes)
+            msgs.append("XML is now well-formed.")
+        except ET.ParseError as e2:
+            msgs.append(f"Remaining issues after fix: {e2}")
+        return (fixed_bytes, msgs)
+
+    msgs.append("No fixable issues found.")
+    return (None, msgs)
+
+
 def ParsePathForComicInfo(strFullPath: str) -> dict:
     """
     파일 경로에서 작가, 제목, 번호를 추출합니다.
@@ -443,7 +502,7 @@ def ConvertLanguageToISO(lang_name: str) -> str:
 
 #
 def ProcessMetadataToCBZ(strArcPath: str, bPrint: bool = False,
-                          volume: str = "-1", number: str = "", count: int = -1,
+                          volume: str = "-1", number: str = "", count: int | None = None,
                           info_title: str = None, info_writer: str = None,
                           info_series: str = None, tags: list[str] = None) -> bool:
     """