more stuff

comicapi/archivers/zip.py

@@ -9,102 +9,13 @@ import zipfile
 from typing import cast
 
 import chardet
+from zipremove import ZipFile
 
 from comicapi.archivers import Archiver
 
 logger = logging.getLogger(__name__)
 
 
-class ZipFile(zipfile.ZipFile):
-
-    def remove(self, zinfo_or_arcname):  # type: ignore
-        """Remove a member from the archive."""
-
-        if self.mode not in ("w", "x", "a"):
-            raise ValueError("remove() requires mode 'w', 'x', or 'a'")
-        if not self.fp:
-            raise ValueError("Attempt to write to ZIP archive that was already closed")
-        if self._writing:  # type: ignore[attr-defined]
-            raise ValueError("Can't write to ZIP archive while an open writing handle exists")
-
-        # Make sure we have an existing info object
-        if isinstance(zinfo_or_arcname, zipfile.ZipInfo):
-            zinfo = zinfo_or_arcname
-            # make sure zinfo exists
-            if zinfo not in self.filelist:
-                raise KeyError("There is no item %r in the archive" % zinfo_or_arcname)
-        else:
-            # get the info object
-            zinfo = self.getinfo(zinfo_or_arcname)
-
-        return self._remove_members({zinfo})
-
-    def _remove_members(self, members, *, remove_physical=True, chunk_size=2**20):  # type: ignore
-        """Remove members in a zip file.
-        All members (as zinfo) should exist in the zip; otherwise the zip file
-        will erroneously end in an inconsistent state.
-        """
-        fp = self.fp
-        assert fp
-        entry_offset = 0
-        member_seen = False
-
-        # get a sorted filelist by header offset, in case the dir order
-        # doesn't match the actual entry order
-        filelist = sorted(self.filelist, key=lambda x: x.header_offset)
-        for i in range(len(filelist)):
-            info = filelist[i]
-            is_member = info in members
-
-            if not (member_seen or is_member):
-                continue
-
-            # get the total size of the entry
-            try:
-                offset = filelist[i + 1].header_offset
-            except IndexError:
-                offset = self.start_dir
-            entry_size = offset - info.header_offset
-
-            if is_member:
-                member_seen = True
-                entry_offset += entry_size
-
-                # update caches
-                self.filelist.remove(info)
-                try:
-                    del self.NameToInfo[info.filename]
-                except KeyError:
-                    pass
-                continue
-
-            # update the header and move entry data to the new position
-            if remove_physical:
-                old_header_offset = info.header_offset
-                info.header_offset -= entry_offset
-                read_size = 0
-                while read_size < entry_size:
-                    fp.seek(old_header_offset + read_size)
-                    data = fp.read(min(entry_size - read_size, chunk_size))
-                    fp.seek(info.header_offset + read_size)
-                    fp.write(data)
-                    fp.flush()
-                    read_size += len(data)
-
-        # Avoid missing entry if entries have a duplicated name.
-        # Reverse the order as NameToInfo normally stores the last added one.
-        for info in reversed(self.filelist):
-            self.NameToInfo.setdefault(info.filename, info)
-
-        # update state
-        if remove_physical:
-            self.start_dir -= entry_offset
-        self._didModify = True
-
-        # seek to the start of the central dir
-        fp.seek(self.start_dir)
-
-
 class ZipArchiver(Archiver):
     """ZIP implementation"""
 
@@ -149,7 +60,7 @@ class ZipArchiver(Archiver):
         try:
             with ZipFile(self.path, mode="a", allowZip64=True, compression=zipfile.ZIP_DEFLATED) as zf:
                 if archive_file in files:
-                    zf.remove(archive_file)
+                    zf.repack([zf.remove(archive_file)])
             return True
         except (zipfile.BadZipfile, OSError) as e:
             logger.error("Error writing zip archive [%s]: %s :: %s", e, self.path, archive_file)
@@ -163,7 +74,7 @@ class ZipArchiver(Archiver):
             # now just add the archive file as a new one
             with ZipFile(self.path, mode="a", allowZip64=True, compression=zipfile.ZIP_DEFLATED) as zf:
                 if archive_file in files:
-                    zf.remove(archive_file)
+                    zf.repack([zf.remove(archive_file)])
                 zf.writestr(archive_file, data)
             return True
         except (zipfile.BadZipfile, OSError) as e:

comictaggerlib/cli.py

@@ -590,9 +590,6 @@ class CLI:
             self.output(f"Processing {utils.path_to_short_str(ca.path)}...")
 
         md, tags_read = self.create_local_metadata(ca, self.config.Runtime_Options__tags_read)
-        if md.issue is None or md.issue == "":
-            if self.config.Auto_Tag__assume_issue_one:
-                md.issue = "1"
 
         matches: list[IssueResult] = []
         # now, search online
@@ -629,11 +626,15 @@ class CLI:
                     return res, match_results
 
             else:
-                qt_md = self.try_quick_tag(ca, md)
+                query_md = md.copy()
+                qt_md = self.try_quick_tag(ca, query_md)
+                if query_md.issue is None or query_md.issue == "":
+                    if self.config.Auto_Tag__assume_issue_one:
+                        query_md.issue = "1"
                 if qt_md is None or qt_md.is_empty:
                     if qt_md is not None:
                         self.output("Failed to find match via quick tag")
-                    ct_md, matches, res, match_results = self.normal_tag(ca, tags_read, md, match_results)  # type: ignore[assignment]
+                    ct_md, matches, res, match_results = self.normal_tag(ca, tags_read, query_md, match_results)  # type: ignore[assignment]
                     if res is not None:
                         return res, match_results
                 else:

comictaggerlib/ctsettings/types.py

@@ -194,7 +194,7 @@ def parse_metadata_from_string(mdstr: str) -> GenericMetadata:
                 else:
                     value = t(value)
         except (ValueError, TypeError):
-            raise argparse.ArgumentTypeError(f"Invalid syntax for tag '{key}': {value}")
+            raise argparse.ArgumentTypeError(f"Invalid syntax for tag {key!r}: {value!r}")
         return value
 
     md = GenericMetadata()
@@ -240,6 +240,8 @@ def parse_metadata_from_string(mdstr: str) -> GenericMetadata:
             else:
                 raise argparse.ArgumentTypeError(f"'{key}' is not a valid tag name")
         md.is_empty = empty
+    except argparse.ArgumentTypeError as e:
+        raise e
     except Exception as e:
         logger.exception("Unable to read metadata from the commandline '%s'", mdstr)
         raise Exception("Unable to read metadata from the commandline") from e

setup.cfg

@@ -50,6 +50,8 @@ install_requires =
     text2digits
     typing-extensions>=4.3.0
     wordninja
+    zipremove
+    pyicu
 python_requires = >=3.9
 
 [options.packages.find]
@@ -73,16 +75,16 @@ pyinstaller40 =
 
 [options.extras_require]
 7z =
-    py7zr
+    py7zr<1
 all =
     PyQt5
     PyQtWebEngine
-    comicinfoxml==0.4.*
+    comicinfoxml==0.5.*
     gcd-talker>0.1.0
     metron-talker>0.1.5
     pillow-avif-plugin>=1.4.1
     pillow-jxl-plugin>=1.2.5
-    py7zr
+    py7zr<1
     rarfile>=4.0
     pyicu;sys_platform == 'linux' or sys_platform == 'darwin'
 archived_tags =
@@ -92,13 +94,12 @@ avif =
 cbr =
     rarfile>=4.0
 cix =
-    comicinfoxml==0.4.*
+    comicinfoxml==0.5.*
 gcd =
     gcd-talker>0.1.0
 gui =
     PyQt5
 icu =
-    pyicu;sys_platform == 'linux' or sys_platform == 'darwin'
 jxl =
     pillow-jxl-plugin>=1.2.5
 metron =
@@ -106,10 +107,10 @@ metron =
 pyinstaller =
     PyQt5
     PyQtWebEngine
-    comicinfoxml==0.4.*
+    comicinfoxml==0.5.*
     pillow-avif-plugin>=1.4.1
     pillow-jxl-plugin>=1.2.5
-    py7zr
+    py7zr<1
     rarfile>=4.0
     pyicu;sys_platform == 'linux' or sys_platform == 'darwin'
 qtw =

tests/utils_test.py

@@ -28,7 +28,9 @@ def test_os_sorted():
         "!cover",
     ]
 
-    assert comicapi.utils.os_sorted(page_name_list) == [
+    sorted_list = comicapi.utils.os_sorted(page_name_list)
+
+    assert sorted_list == [
         "!cover",
         "!cover.jpg",
         "!cover.tar.gz",