add --fix-xml

압축파일 내의 경로를 제거하도록 util.py 수정

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

@@ -40,6 +40,7 @@ def main(argc, argv):
     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
@@ -92,10 +93,13 @@ def process_archive_file(archive_path: str, args: argparse.Namespace):
     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, args.info_count,
+                               arc_volume, arc_number, arc_count,
                                arc_title, arc_writer, arc_series,
                                arc_tags if arc_tags else None)
         return
@@ -114,8 +118,27 @@ def process_archive_file(archive_path: str, args: argparse.Namespace):
         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=args.info_count)
+                                          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')
@@ -123,9 +146,12 @@ def process_archive_file(archive_path: str, args: argparse.Namespace):
             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 args.info_count:
+        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 "",
@@ -134,7 +160,7 @@ def process_archive_file(archive_path: str, args: argparse.Namespace):
                 pages=[],
                 volume=arc_volume or "",
                 number=arc_number or "",
-                count=int(args.info_count) if args.info_count is not None else -1
+                count=arc_count if arc_count is not None else -1
             )
             if new_xml:
                 if args.bPrint:
@@ -150,7 +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]
@@ -170,8 +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)
@@ -183,10 +211,12 @@ 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
-        try:
-            result = re.sub(pattern, replacement_safe, source, count=count, flags=flags)
-        except re.error:
-            pass
+        # source가 비어있으면 정규식 미적용 (ResolveRegexTransform에서 처리)
+        if source:
+            try:
+                result = re.sub(pattern, replacement_safe, source, count=count, flags=flags)
+            except re.error:
+                pass
 
     return result
 
@@ -255,6 +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.
@@ -440,7 +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:
     """