diff --git a/comicapi/comicarchive.py b/comicapi/comicarchive.py
index 6a7a398..721b0e3 100644
--- a/comicapi/comicarchive.py
+++ b/comicapi/comicarchive.py
@@ -368,7 +368,7 @@ class RarArchiver(UnknownArchiver):
def __init__(self, path: pathlib.Path | str, rar_exe_path: str = "rar") -> None:
super().__init__(path)
- self.rar_exe_path = rar_exe_path
+ self.rar_exe_path = shutil.which(rar_exe_path) or ""
# windows only, keeps the cmd.exe from popping up
if platform.system() == "Windows":
@@ -687,7 +687,7 @@ class ComicArchive:
self.page_count: int | None = None
self.page_list: list[str] = []
- self.rar_exe_path = rar_exe_path
+ self.rar_exe_path = shutil.which(rar_exe_path or "rar") or ""
self.ci_xml_filename = "ComicInfo.xml"
self.comet_default_filename = "CoMet.xml"
self.reset_cache()
@@ -746,7 +746,12 @@ class ComicArchive:
self.read_metadata(style)
def rename(self, path: pathlib.Path | str) -> None:
- self.path = pathlib.Path(path)
+ new_path = pathlib.Path(path).absolute()
+ if new_path == self.path:
+ return
+ os.makedirs(new_path.parent, 0o777, True)
+ shutil.move(path, new_path)
+ self.path = new_path
self.archiver.path = pathlib.Path(path)
def sevenzip_test(self) -> bool:
@@ -863,7 +868,7 @@ class ComicArchive:
def get_page_name(self, index: int) -> str:
if index is None:
- return None
+ return ""
page_list = self.get_page_name_list()
@@ -1148,8 +1153,8 @@ class ComicArchive:
for n in self.archiver.get_filename_list():
if os.path.dirname(n) == "" and os.path.splitext(n)[1].casefold() == ".xml":
# read in XML file, and validate it
+ data = ""
try:
- data = ""
d = self.archiver.read_file(n)
if d:
data = d.decode("utf-8")
@@ -1247,10 +1252,10 @@ class ComicArchive:
return metadata
- def export_as_zip(self, zipfilename: str) -> bool:
+ def export_as_zip(self, zip_filename: pathlib.Path | str) -> bool:
if self.archive_type == self.ArchiveType.Zip:
# nothing to do, we're already a zip
return True
- zip_archiver = ZipArchiver(zipfilename)
+ zip_archiver = ZipArchiver(zip_filename)
return zip_archiver.copy_from_archive(self.archiver)
diff --git a/comicapi/comicbookinfo.py b/comicapi/comicbookinfo.py
index 9201dfb..88223d6 100644
--- a/comicapi/comicbookinfo.py
+++ b/comicapi/comicbookinfo.py
@@ -98,13 +98,11 @@ class ComicBookInfo:
metadata.critical_rating = utils.xlate(cbi["rating"], True)
metadata.credits = cbi["credits"]
- metadata.tags = cbi["tags"]
+ metadata.tags = set(cbi["tags"]) if cbi["tags"] is not None else set()
# make sure credits and tags are at least empty lists and not None
if metadata.credits is None:
metadata.credits = []
- if metadata.tags is None:
- metadata.tags = []
# need the language string to be ISO
if metadata.language is not None:
@@ -133,7 +131,7 @@ class ComicBookInfo:
cbi_container = CBIContainer(
{
- "appID": "ComicTagger/" + "1.0.0",
+ "appID": "ComicTagger/1.0.0",
"lastModified": str(datetime.now()),
"ComicBookInfo/1.0": {},
}
diff --git a/comicapi/comicinfoxml.py b/comicapi/comicinfoxml.py
index bade43a..10a599a 100644
--- a/comicapi/comicinfoxml.py
+++ b/comicapi/comicinfoxml.py
@@ -54,13 +54,11 @@ class ComicInfoXml:
return self.convert_xml_to_metadata(tree)
def string_from_metadata(self, metadata: GenericMetadata, xml: bytes = b"") -> str:
- tree = self.convert_metadata_to_xml(self, metadata, xml)
+ tree = self.convert_metadata_to_xml(metadata, xml)
tree_str = ET.tostring(tree.getroot(), encoding="utf-8", xml_declaration=True).decode("utf-8")
return str(tree_str)
- def convert_metadata_to_xml(
- self, filename: ComicInfoXml, metadata: GenericMetadata, xml: bytes = b""
- ) -> ElementTree:
+ def convert_metadata_to_xml(self, metadata: GenericMetadata, xml: bytes = b"") -> ElementTree:
# shorthand for the metadata
md = metadata
@@ -261,6 +259,8 @@ class ComicInfoXml:
p: dict[str, Any] = page.attrib
if "Image" in p:
p["Image"] = int(p["Image"])
+ if "DoublePage" in p:
+ p["DoublePage"] = True if p["DoublePage"].casefold() in ("yes", "true", "1") else False
md.pages.append(cast(ImageMetadata, p))
md.is_empty = False
@@ -268,7 +268,7 @@ class ComicInfoXml:
return md
def write_to_external_file(self, filename: str, metadata: GenericMetadata, xml: bytes = b"") -> None:
- tree = self.convert_metadata_to_xml(self, metadata, xml)
+ tree = self.convert_metadata_to_xml(metadata, xml)
tree.write(filename, encoding="utf-8", xml_declaration=True)
def read_from_external_file(self, filename: str) -> GenericMetadata:
diff --git a/comicapi/filenamelexer.py b/comicapi/filenamelexer.py
index c8d134a..c35d83f 100644
--- a/comicapi/filenamelexer.py
+++ b/comicapi/filenamelexer.py
@@ -1,5 +1,5 @@
# Extracted and mutilated from https://github.com/lordwelch/wsfmt
-# Which was extracted and mutliated from https://github.com/golang/go/tree/master/src/text/template/parse
+# Which was extracted and mutilated from https://github.com/golang/go/tree/master/src/text/template/parse
from __future__ import annotations
import calendar
@@ -138,7 +138,7 @@ class Lexer:
# AcceptRun consumes a run of runes from the valid set.
def accept_run(self, valid: str) -> None:
while self.get() in valid:
- pass
+ continue
self.backup()
diff --git a/comicapi/filenameparser.py b/comicapi/filenameparser.py
index 393ffb4..c69102e 100644
--- a/comicapi/filenameparser.py
+++ b/comicapi/filenameparser.py
@@ -114,7 +114,7 @@ class FileNameParser:
# remove any "of NN" phrase with spaces (problem: this could break on
# some titles)
- filename = re.sub(r"of [\d]+", self.repl, filename)
+ filename = re.sub(r"of \d+", self.repl, filename)
# we should now have a cleaned up filename version with all the words in
# the same positions as original filename
@@ -143,7 +143,7 @@ class FileNameParser:
# first look for a word with "#" followed by digits with optional suffix
# this is almost certainly the issue number
for w in reversed(word_list):
- if re.match(r"#[-]?(([0-9]*\.[0-9]+|[0-9]+)(\w*))", w[0]):
+ if re.match(r"#-?((\d*\.\d+|\d+)(\w*))", w[0]):
found = True
break
@@ -151,7 +151,7 @@ class FileNameParser:
# list
if not found:
w = word_list[-1]
- if re.match(r"[-]?(([0-9]*\.[0-9]+|[0-9]+)(\w*))", w[0]):
+ if re.match(r"-?((\d*\.\d+|\d+)(\w*))", w[0]):
found = True
# now try to look for a # followed by any characters
@@ -245,7 +245,7 @@ class FileNameParser:
if match:
year = match.group()
# remove non-digits
- year = re.sub(r"[^0-9]", "", year)
+ year = re.sub(r"\D", "", year)
return year
def get_remainder(self, filename: str, year: str, count: str, volume: str, issue_end: int) -> str:
@@ -332,7 +332,7 @@ eof = filenamelexer.Item(filenamelexer.ItemType.EOF, -1, "")
# Extracted and mutilated from https://github.com/lordwelch/wsfmt
-# Which was extracted and mutliated from https://github.com/golang/go/tree/master/src/text/template/parse
+# Which was extracted and mutilated from https://github.com/golang/go/tree/master/src/text/template/parse
class Parser:
"""docstring for FilenameParser"""
diff --git a/comicapi/genericmetadata.py b/comicapi/genericmetadata.py
index 244ae9a..ccbc1c1 100644
--- a/comicapi/genericmetadata.py
+++ b/comicapi/genericmetadata.py
@@ -20,8 +20,9 @@ possible, however lossy it might be
# limitations under the License.
from __future__ import annotations
+import copy
+import dataclasses
import logging
-from dataclasses import dataclass, field
from typing import Any, TypedDict
from comicapi import utils
@@ -65,7 +66,7 @@ class CreditMetadata(TypedDict):
primary: bool
-@dataclass
+@dataclasses.dataclass
class GenericMetadata:
writer_synonyms = ["writer", "plotter", "scripter"]
penciller_synonyms = ["artist", "penciller", "penciler", "breakdowns"]
@@ -115,9 +116,9 @@ class GenericMetadata:
teams: str | None = None
locations: str | None = None
- credits: list[CreditMetadata] = field(default_factory=list)
- tags: list[str] = field(default_factory=list)
- pages: list[ImageMetadata] = field(default_factory=list)
+ credits: list[CreditMetadata] = dataclasses.field(default_factory=list)
+ tags: set[str] = dataclasses.field(default_factory=set)
+ pages: list[ImageMetadata] = dataclasses.field(default_factory=list)
# Some CoMet-only items
price: str | None = None
@@ -133,6 +134,14 @@ class GenericMetadata:
self.is_empty = False
break
+ def copy(self) -> GenericMetadata:
+ return copy.deepcopy(self)
+
+ def replace(self, /, **kwargs: Any) -> GenericMetadata:
+ tmp = self.copy()
+ tmp.__dict__.update(kwargs)
+ return tmp
+
def overlay(self, new_md: GenericMetadata) -> None:
"""Overlay a metadata object on this one
@@ -244,7 +253,7 @@ class GenericMetadata:
def add_credit(self, person: str, role: str, primary: bool = False) -> None:
- credit: CreditMetadata = {"person": person, "role": role, "primary": primary}
+ credit = CreditMetadata(person=person, role=role, primary=primary)
# look to see if it's not already there...
found = False
@@ -360,91 +369,91 @@ class GenericMetadata:
self.imprint = imprint
-md_test = GenericMetadata()
-
-md_test.is_empty = False
-md_test.tag_origin = None
-md_test.series = "Cory Doctorow's Futuristic Tales of the Here and Now"
-md_test.issue = "1"
-md_test.title = "Anda's Game"
-md_test.publisher = "IDW Publishing"
-md_test.month = 10
-md_test.year = 2007
-md_test.day = 1
-md_test.issue_count = 6
-md_test.volume = 1
-md_test.genre = "Sci-Fi"
-md_test.language = "en"
-md_test.comments = (
- "For 12-year-old Anda, getting paid real money to kill the characters of players who were cheating"
- " in her favorite online computer game was a win-win situation. Until she found out who was paying her,"
- " and what those characters meant to the livelihood of children around the world."
+md_test: GenericMetadata = GenericMetadata(
+ is_empty=False,
+ tag_origin=None,
+ series="Cory Doctorow's Futuristic Tales of the Here and Now",
+ issue="1",
+ title="Anda's Game",
+ publisher="IDW Publishing",
+ month=10,
+ year=2007,
+ day=1,
+ issue_count=6,
+ volume=1,
+ genre="Sci-Fi",
+ language="en",
+ comments=(
+ "For 12-year-old Anda, getting paid real money to kill the characters of players who were cheating"
+ " in her favorite online computer game was a win-win situation. Until she found out who was paying her,"
+ " and what those characters meant to the livelihood of children around the world."
+ ),
+ volume_count=None,
+ critical_rating=3.0,
+ country=None,
+ alternate_series="Tales",
+ alternate_number="2",
+ alternate_count=7,
+ imprint="craphound.com",
+ notes="Tagged with ComicTagger 1.3.2a5 using info from Comic Vine on 2022-04-16 15:52:26. [Issue ID 140529]",
+ web_link="https://comicvine.gamespot.com/cory-doctorows-futuristic-tales-of-the-here-and-no/4000-140529/",
+ format="Series",
+ manga="No",
+ black_and_white=None,
+ page_count=24,
+ maturity_rating="Everyone 10+",
+ story_arc="Here and Now",
+ series_group="Futuristic Tales",
+ scan_info="(CC BY-NC-SA 3.0)",
+ characters="Anda",
+ teams="Fahrenheit",
+ locations="lonely cottage ",
+ credits=[
+ CreditMetadata(primary=False, person="Dara Naraghi", role="Writer"),
+ CreditMetadata(primary=False, person="Esteve Polls", role="Penciller"),
+ CreditMetadata(primary=False, person="Esteve Polls", role="Inker"),
+ CreditMetadata(primary=False, person="Neil Uyetake", role="Letterer"),
+ CreditMetadata(primary=False, person="Sam Kieth", role="Cover"),
+ CreditMetadata(primary=False, person="Ted Adams", role="Editor"),
+ ],
+ tags=set(),
+ pages=[
+ ImageMetadata(Image=0, ImageHeight="1280", ImageSize="195977", ImageWidth="800", Type=PageType.FrontCover),
+ ImageMetadata(Image=1, ImageHeight="2039", ImageSize="611993", ImageWidth="1327"),
+ ImageMetadata(Image=2, ImageHeight="2039", ImageSize="783726", ImageWidth="1327"),
+ ImageMetadata(Image=3, ImageHeight="2039", ImageSize="679584", ImageWidth="1327"),
+ ImageMetadata(Image=4, ImageHeight="2039", ImageSize="788179", ImageWidth="1327"),
+ ImageMetadata(Image=5, ImageHeight="2039", ImageSize="864433", ImageWidth="1327"),
+ ImageMetadata(Image=6, ImageHeight="2039", ImageSize="765606", ImageWidth="1327"),
+ ImageMetadata(Image=7, ImageHeight="2039", ImageSize="876427", ImageWidth="1327"),
+ ImageMetadata(Image=8, ImageHeight="2039", ImageSize="852622", ImageWidth="1327"),
+ ImageMetadata(Image=9, ImageHeight="2039", ImageSize="800205", ImageWidth="1327"),
+ ImageMetadata(Image=10, ImageHeight="2039", ImageSize="746243", ImageWidth="1326"),
+ ImageMetadata(Image=11, ImageHeight="2039", ImageSize="718062", ImageWidth="1327"),
+ ImageMetadata(Image=12, ImageHeight="2039", ImageSize="532179", ImageWidth="1326"),
+ ImageMetadata(Image=13, ImageHeight="2039", ImageSize="686708", ImageWidth="1327"),
+ ImageMetadata(Image=14, ImageHeight="2039", ImageSize="641907", ImageWidth="1327"),
+ ImageMetadata(Image=15, ImageHeight="2039", ImageSize="805388", ImageWidth="1327"),
+ ImageMetadata(Image=16, ImageHeight="2039", ImageSize="668927", ImageWidth="1326"),
+ ImageMetadata(Image=17, ImageHeight="2039", ImageSize="710605", ImageWidth="1327"),
+ ImageMetadata(Image=18, ImageHeight="2039", ImageSize="761398", ImageWidth="1326"),
+ ImageMetadata(Image=19, ImageHeight="2039", ImageSize="743807", ImageWidth="1327"),
+ ImageMetadata(Image=20, ImageHeight="2039", ImageSize="552911", ImageWidth="1326"),
+ ImageMetadata(Image=21, ImageHeight="2039", ImageSize="556827", ImageWidth="1327"),
+ ImageMetadata(Image=22, ImageHeight="2039", ImageSize="675078", ImageWidth="1326"),
+ ImageMetadata(
+ Bookmark="Interview",
+ Image=23,
+ ImageHeight="2032",
+ ImageSize="800965",
+ ImageWidth="1338",
+ Type=PageType.Letters,
+ ),
+ ],
+ price=None,
+ is_version_of=None,
+ rights=None,
+ identifier=None,
+ last_mark=None,
+ cover_image=None,
)
-md_test.volume_count = None
-md_test.critical_rating = 3.0
-md_test.country = None
-md_test.alternate_series = "Tales"
-md_test.alternate_number = "2"
-md_test.alternate_count = 7
-md_test.imprint = "craphound.com"
-md_test.notes = "Tagged with ComicTagger 1.3.2a5 using info from Comic Vine on 2022-04-16 15:52:26. [Issue ID 140529]"
-md_test.web_link = "https://comicvine.gamespot.com/cory-doctorows-futuristic-tales-of-the-here-and-no/4000-140529/"
-md_test.format = "Series"
-md_test.manga = "No"
-md_test.black_and_white = None
-md_test.page_count = 24
-md_test.maturity_rating = "Everyone 10+"
-md_test.story_arc = "Here and Now"
-md_test.series_group = "Futuristic Tales"
-md_test.scan_info = "(CC BY-NC-SA 3.0)"
-md_test.characters = "Anda"
-md_test.teams = "Fahrenheit"
-md_test.locations = "lonely cottage "
-md_test.credits = [
- CreditMetadata({"primary": False, "person": "Dara Naraghi", "role": "Writer"}),
- CreditMetadata({"primary": False, "person": "Esteve Polls", "role": "Penciller"}),
- CreditMetadata({"primary": False, "person": "Esteve Polls", "role": "Inker"}),
- CreditMetadata({"primary": False, "person": "Neil Uyetake", "role": "Letterer"}),
- CreditMetadata({"primary": False, "person": "Sam Kieth", "role": "Cover"}),
- CreditMetadata({"primary": False, "person": "Ted Adams", "role": "Editor"}),
-]
-md_test.tags = []
-md_test.pages = [
- {"Image": 0, "ImageHeight": "1280", "ImageSize": "195977", "ImageWidth": "800", "Type": PageType.FrontCover},
- {"Image": 1, "ImageHeight": "2039", "ImageSize": "611993", "ImageWidth": "1327"},
- {"Image": 2, "ImageHeight": "2039", "ImageSize": "783726", "ImageWidth": "1327"},
- {"Image": 3, "ImageHeight": "2039", "ImageSize": "679584", "ImageWidth": "1327"},
- {"Image": 4, "ImageHeight": "2039", "ImageSize": "788179", "ImageWidth": "1327"},
- {"Image": 5, "ImageHeight": "2039", "ImageSize": "864433", "ImageWidth": "1327"},
- {"Image": 6, "ImageHeight": "2039", "ImageSize": "765606", "ImageWidth": "1327"},
- {"Image": 7, "ImageHeight": "2039", "ImageSize": "876427", "ImageWidth": "1327"},
- {"Image": 8, "ImageHeight": "2039", "ImageSize": "852622", "ImageWidth": "1327"},
- {"Image": 9, "ImageHeight": "2039", "ImageSize": "800205", "ImageWidth": "1327"},
- {"Image": 10, "ImageHeight": "2039", "ImageSize": "746243", "ImageWidth": "1326"},
- {"Image": 11, "ImageHeight": "2039", "ImageSize": "718062", "ImageWidth": "1327"},
- {"Image": 12, "ImageHeight": "2039", "ImageSize": "532179", "ImageWidth": "1326"},
- {"Image": 13, "ImageHeight": "2039", "ImageSize": "686708", "ImageWidth": "1327"},
- {"Image": 14, "ImageHeight": "2039", "ImageSize": "641907", "ImageWidth": "1327"},
- {"Image": 15, "ImageHeight": "2039", "ImageSize": "805388", "ImageWidth": "1327"},
- {"Image": 16, "ImageHeight": "2039", "ImageSize": "668927", "ImageWidth": "1326"},
- {"Image": 17, "ImageHeight": "2039", "ImageSize": "710605", "ImageWidth": "1327"},
- {"Image": 18, "ImageHeight": "2039", "ImageSize": "761398", "ImageWidth": "1326"},
- {"Image": 19, "ImageHeight": "2039", "ImageSize": "743807", "ImageWidth": "1327"},
- {"Image": 20, "ImageHeight": "2039", "ImageSize": "552911", "ImageWidth": "1326"},
- {"Image": 21, "ImageHeight": "2039", "ImageSize": "556827", "ImageWidth": "1327"},
- {"Image": 22, "ImageHeight": "2039", "ImageSize": "675078", "ImageWidth": "1326"},
- {
- "Bookmark": "Interview",
- "Image": 23,
- "ImageHeight": "2032",
- "ImageSize": "800965",
- "ImageWidth": "1338",
- "Type": PageType.Letters,
- },
-]
-md_test.price = None
-md_test.is_version_of = None
-md_test.rights = None
-md_test.identifier = None
-md_test.last_mark = None
-md_test.cover_image = None
diff --git a/comicapi/issuestring.py b/comicapi/issuestring.py
index c468fc8..5911bd9 100644
--- a/comicapi/issuestring.py
+++ b/comicapi/issuestring.py
@@ -113,6 +113,4 @@ class IssueString:
# return the float, with no suffix
if len(self.suffix) == 1 and self.suffix.isnumeric():
return (self.num or 0) + unicodedata.numeric(self.suffix)
-
- return 0.5
return self.num
diff --git a/comicapi/utils.py b/comicapi/utils.py
index a23bc87..fe674ee 100644
--- a/comicapi/utils.py
+++ b/comicapi/utils.py
@@ -26,6 +26,7 @@ from shutil import which # noqa: F401
from typing import Any, Mapping
import pycountry
+import thefuzz.fuzz
logger = logging.getLogger(__name__)
@@ -108,6 +109,10 @@ def remove_articles(text: str) -> str:
"the",
"the",
"with",
+ "ms",
+ "mrs",
+ "mr",
+ "dr",
]
new_text = ""
for word in text.split(" "):
@@ -121,26 +126,48 @@ def remove_articles(text: str) -> str:
def sanitize_title(text: str, basic: bool = False) -> str:
# normalize unicode and convert to ascii. Does not work for everything eg ½ to 1⁄2 not 1/2
- text = unicodedata.normalize("NFKD", text)
- # comicvine keeps apostrophes a part of the word
- text = text.replace("'", "")
- text = text.replace('"', "")
- if not basic:
- # comicvine ignores punctuation and accents, TODO: only remove punctuation accents and similar
- text = re.sub(r"[^A-Za-z0-9]+", " ", text)
+ text = unicodedata.normalize("NFKD", text).casefold()
+ if basic:
+ # comicvine keeps apostrophes a part of the word
+ text = text.replace("'", "")
+ text = text.replace('"', "")
+ else:
+ # comicvine ignores punctuation and accents
+ # remove all characters that are not a letter, separator (space) or number
+ # replace any "dash punctuation" with a space
+ # makes sure that batman-superman and self-proclaimed stay separate words
+ text = "".join(
+ c if not unicodedata.category(c) in ("Pd",) else " "
+ for c in text
+ if unicodedata.category(c)[0] in "LZN" or unicodedata.category(c) in ("Pd",)
+ )
# remove extra space and articles and all lower case
- text = remove_articles(text).casefold().strip()
+ text = remove_articles(text).strip()
return text
-def unique_file(file_name: str) -> str:
+def titles_match(search_title: str, record_title: str, threshold: int = 90) -> int:
+ sanitized_search = sanitize_title(search_title)
+ sanitized_record = sanitize_title(record_title)
+ ratio = thefuzz.fuzz.ratio(sanitized_search, sanitized_record)
+ logger.debug(
+ "search title: %s ; record title: %s ; ratio: %d ; match threshold: %d",
+ search_title,
+ record_title,
+ ratio,
+ threshold,
+ )
+ return ratio >= threshold
+
+
+def unique_file(file_name: pathlib.Path) -> pathlib.Path:
+ name = file_name.name
counter = 1
- file_name_parts = os.path.splitext(file_name)
while True:
- if not os.path.lexists(file_name):
+ if not file_name.exists():
return file_name
- file_name = file_name_parts[0] + " (" + str(counter) + ")" + file_name_parts[1]
+ file_name = file_name.with_name(name + " (" + str(counter) + ")")
counter += 1
@@ -204,7 +231,7 @@ class ImprintDict(dict):
if the key does not exist the key is returned as the publisher unchanged
"""
- def __init__(self, publisher: str, mapping=(), **kwargs) -> None:
+ def __init__(self, publisher: str, mapping: tuple | Mapping = (), **kwargs: dict) -> None:
super().__init__(mapping, **kwargs)
self.publisher = publisher
diff --git a/comictaggerlib/applicationlogwindow.py b/comictaggerlib/applicationlogwindow.py
index f37fa26..9a3c2e2 100644
--- a/comictaggerlib/applicationlogwindow.py
+++ b/comictaggerlib/applicationlogwindow.py
@@ -12,18 +12,18 @@ logger = logging.getLogger(__name__)
class QTextEditLogger(QtCore.QObject, logging.Handler):
qlog = QtCore.pyqtSignal(str)
- def __init__(self, formatter: logging.Formatter, level: int):
+ def __init__(self, formatter: logging.Formatter, level: int) -> None:
super().__init__()
self.setFormatter(formatter)
self.setLevel(level)
- def emit(self, record):
+ def emit(self, record: logging.LogRecord) -> None:
msg = self.format(record)
self.qlog.emit(msg.strip())
class ApplicationLogWindow(QtWidgets.QDialog):
- def __init__(self, log_handler: QTextEditLogger, parent=None):
+ def __init__(self, log_handler: QTextEditLogger, parent: QtCore.QObject = None) -> None:
super().__init__(parent)
uic.loadUi(ComicTaggerSettings.get_ui_file("logwindow.ui"), self)
@@ -43,7 +43,7 @@ class ApplicationLogWindow(QtWidgets.QDialog):
self._button.clicked.connect(self.test)
self.textEdit.setTabStopDistance(self.textEdit.tabStopDistance() * 2)
- def test(self):
+ def test(self) -> None:
logger.debug("damn, a bug")
logger.info("something to remember")
logger.warning("that's not right")
diff --git a/comictaggerlib/autotagstartwindow.py b/comictaggerlib/autotagstartwindow.py
index a48d418..c26e8cd 100644
--- a/comictaggerlib/autotagstartwindow.py
+++ b/comictaggerlib/autotagstartwindow.py
@@ -17,7 +17,7 @@ from __future__ import annotations
import logging
-from PyQt5 import QtCore, QtGui, QtWidgets, uic
+from PyQt5 import QtCore, QtWidgets, uic
from comictaggerlib.settings import ComicTaggerSettings
@@ -39,7 +39,7 @@ class AutoTagStartWindow(QtWidgets.QDialog):
self.cbxSpecifySearchString.setChecked(False)
self.cbxSplitWords.setChecked(False)
- self.leNameLengthMatchTolerance.setText(str(self.settings.id_length_delta_thresh))
+ self.sbNameMatchSearchThresh.setValue(self.settings.id_series_match_identify_thresh)
self.leSearchString.setEnabled(False)
self.cbxSaveOnLowConfidence.setChecked(self.settings.save_on_low_confidence)
@@ -49,13 +49,12 @@ class AutoTagStartWindow(QtWidgets.QDialog):
self.cbxRemoveAfterSuccess.setChecked(self.settings.remove_archive_after_successful_match)
self.cbxAutoImprint.setChecked(self.settings.auto_imprint)
- nlmt_tip = """ The Name Length Match Tolerance is for eliminating automatic
- search matches that are too long compared to your series name search. The higher
+ nlmt_tip = """The Name Match Ratio Threshold: Auto-Identify is for eliminating automatic
+ search matches that are too long compared to your series name search. The lower
it is, the more likely to have a good match, but each search will take longer and
- use more bandwidth. Too low, and only the very closest lexical matches will be
- explored."""
+ use more bandwidth. Too high, and only the very closest matches will be explored."""
- self.leNameLengthMatchTolerance.setToolTip(nlmt_tip)
+ self.sbNameMatchSearchThresh.setToolTip(nlmt_tip)
ss_tip = """
The series search string specifies the search string to be used for all selected archives.
@@ -65,9 +64,6 @@ class AutoTagStartWindow(QtWidgets.QDialog):
self.leSearchString.setToolTip(ss_tip)
self.cbxSpecifySearchString.setToolTip(ss_tip)
- validator = QtGui.QIntValidator(0, 99, self)
- self.leNameLengthMatchTolerance.setValidator(validator)
-
self.cbxSpecifySearchString.stateChanged.connect(self.search_string_toggle)
self.auto_save_on_low = False
@@ -76,7 +72,7 @@ class AutoTagStartWindow(QtWidgets.QDialog):
self.ignore_leading_digits_in_filename = False
self.remove_after_success = False
self.search_string = ""
- self.name_length_match_tolerance = self.settings.id_length_delta_thresh
+ self.name_length_match_tolerance = self.settings.id_series_match_search_thresh
self.split_words = self.cbxSplitWords.isChecked()
def search_string_toggle(self) -> None:
@@ -91,7 +87,7 @@ class AutoTagStartWindow(QtWidgets.QDialog):
self.assume_issue_one = self.cbxAssumeIssueOne.isChecked()
self.ignore_leading_digits_in_filename = self.cbxIgnoreLeadingDigitsInFilename.isChecked()
self.remove_after_success = self.cbxRemoveAfterSuccess.isChecked()
- self.name_length_match_tolerance = int(self.leNameLengthMatchTolerance.text())
+ self.name_length_match_tolerance = int(self.leNameMatchThresh.text())
self.split_words = self.cbxSplitWords.isChecked()
# persist some settings
diff --git a/comictaggerlib/cbltransformer.py b/comictaggerlib/cbltransformer.py
index d858e3a..34194c3 100644
--- a/comictaggerlib/cbltransformer.py
+++ b/comictaggerlib/cbltransformer.py
@@ -32,7 +32,7 @@ class CBLTransformer:
# helper funcs
def append_to_tags_if_unique(item: str) -> None:
if item.casefold() not in (tag.casefold() for tag in self.metadata.tags):
- self.metadata.tags.append(item)
+ self.metadata.tags.add(item)
def add_string_list_to_tags(str_list: str | None) -> None:
if str_list:
diff --git a/comictaggerlib/cli.py b/comictaggerlib/cli.py
index 84681b0..8c20967 100644
--- a/comictaggerlib/cli.py
+++ b/comictaggerlib/cli.py
@@ -20,7 +20,7 @@ import argparse
import json
import logging
import os
-import shutil
+import pathlib
import sys
from pprint import pprint
@@ -28,7 +28,7 @@ from comicapi import utils
from comicapi.comicarchive import ComicArchive, MetaDataStyle
from comicapi.genericmetadata import GenericMetadata
from comictaggerlib.cbltransformer import CBLTransformer
-from comictaggerlib.filerenamer import FileRenamer
+from comictaggerlib.filerenamer import FileRenamer, get_rename_dir
from comictaggerlib.issueidentifier import IssueIdentifier
from comictaggerlib.resulttypes import IssueResult, MultipleMatch, OnlineMatchResults
from comictaggerlib.settings import ComicTaggerSettings
@@ -514,21 +514,18 @@ def process_file_cli(
)
return
- folder = os.path.dirname(os.path.abspath(filename))
- if settings.rename_move_dir and len(settings.rename_dir.strip()) > 3:
- folder = settings.rename_dir.strip()
+ folder = get_rename_dir(ca, settings.rename_dir if settings.rename_move_dir else None)
- new_abs_path = utils.unique_file(os.path.join(folder, new_name))
+ full_path = folder / new_name
- if os.path.join(folder, new_name) == os.path.abspath(filename):
+ if full_path == ca.path:
print(msg_hdr + "Filename is already good!", file=sys.stderr)
return
suffix = ""
if not opts.dryrun:
# rename the file
- os.makedirs(os.path.dirname(new_abs_path), 0o777, True)
- shutil.move(filename, new_abs_path)
+ ca.rename(utils.unique_file(full_path))
else:
suffix = " (dry-run, no change)"
@@ -539,18 +536,18 @@ def process_file_cli(
if batch_mode:
msg_hdr = f"{ca.path}: "
- if not ca.is_rar():
- logger.error(msg_hdr + "Archive is not a RAR.")
+ if ca.is_zip():
+ logger.error(msg_hdr + "Archive is already a zip file.")
return
- rar_file = os.path.abspath(os.path.abspath(filename))
- new_file = os.path.splitext(rar_file)[0] + ".cbz"
+ filename_path = pathlib.Path(filename).absolute()
+ new_file = filename_path.with_suffix(".cbz")
- if opts.abort_on_conflict and os.path.lexists(new_file):
- print(msg_hdr + f"{os.path.split(new_file)[1]} already exists in the that folder.")
+ if opts.abort_on_conflict and new_file.exists():
+ print(msg_hdr + f"{new_file.name} already exists in the that folder.")
return
- new_file = utils.unique_file(os.path.join(new_file))
+ new_file = utils.unique_file(new_file)
delete_success = False
export_success = False
@@ -559,16 +556,14 @@ def process_file_cli(
export_success = True
if opts.delete_after_zip_export:
try:
- os.unlink(rar_file)
- except OSError:
- logger.exception(msg_hdr + "Error deleting original RAR after export")
- delete_success = False
- else:
+ filename_path.unlink(missing_ok=True)
delete_success = True
+ except OSError:
+ logger.exception(msg_hdr + "Error deleting original archive after export")
+ delete_success = False
else:
# last export failed, so remove the zip, if it exists
- if os.path.lexists(new_file):
- os.remove(new_file)
+ new_file.unlink(missing_ok=True)
else:
msg = msg_hdr + f"Dry-run: Would try to create {os.path.split(new_file)[1]}"
if opts.delete_after_zip_export:
diff --git a/comictaggerlib/coverimagewidget.py b/comictaggerlib/coverimagewidget.py
index 3300ed2..4c06410 100644
--- a/comictaggerlib/coverimagewidget.py
+++ b/comictaggerlib/coverimagewidget.py
@@ -92,6 +92,7 @@ class CoverImageWidget(QtWidgets.QWidget):
) -> None:
super().__init__(parent)
+ self.cover_fetcher = ImageFetcher()
uic.loadUi(ComicTaggerSettings.get_ui_file("coverimagewidget.ui"), self)
reduce_widget_font_size(self.label)
@@ -195,7 +196,7 @@ class CoverImageWidget(QtWidgets.QWidget):
self.update_content()
- def primary_url_fetch_complete(self, primary_url: str, thumb_url: str | None) -> None:
+ def primary_url_fetch_complete(self, primary_url: str, thumb_url: str | None = None) -> None:
self.url_list.append(str(primary_url))
self.imageIndex = 0
self.imageCount = len(self.url_list)
diff --git a/comictaggerlib/filerenamer.py b/comictaggerlib/filerenamer.py
index fd41e38..975aacc 100644
--- a/comictaggerlib/filerenamer.py
+++ b/comictaggerlib/filerenamer.py
@@ -25,12 +25,22 @@ from typing import Any, cast
from pathvalidate import sanitize_filename
+from comicapi.comicarchive import ComicArchive
from comicapi.genericmetadata import GenericMetadata
from comicapi.issuestring import IssueString
logger = logging.getLogger(__name__)
+def get_rename_dir(ca: ComicArchive, rename_dir: str | pathlib.Path | None) -> pathlib.Path:
+ folder = ca.path.parent.absolute()
+ if rename_dir is not None:
+ if isinstance(rename_dir, str):
+ rename_dir = rename_dir.strip()
+ folder = pathlib.Path(rename_dir).absolute()
+ return folder
+
+
class MetadataFormatter(string.Formatter):
def __init__(self, smart_cleanup: bool = False, platform: str = "auto") -> None:
super().__init__()
@@ -80,17 +90,9 @@ class MetadataFormatter(string.Formatter):
field_name = field_name.casefold()
# this is some markup, find the object and do the formatting
- # handle arg indexing when empty field_names are given.
- if field_name == "":
- if auto_arg_index is False:
- raise ValueError("cannot switch from manual field specification to automatic field numbering")
- field_name = str(auto_arg_index)
- auto_arg_index += 1
- elif field_name.isdigit():
- if auto_arg_index:
- raise ValueError("cannot switch from manual field specification to automatic field numbering")
- # disable auto arg incrementing, if it gets used later on, then an exception will be raised
- auto_arg_index = False
+ # handle arg indexing when digit field_names are given.
+ if field_name.isdigit():
+ raise ValueError("cannot use a number as a field name")
# given the field_name, find the object it references
# and the argument it came from
@@ -101,8 +103,8 @@ class MetadataFormatter(string.Formatter):
obj = self.convert_field(obj, conversion) # type: ignore
# expand the format spec, if needed
- format_spec, auto_arg_index = self._vformat(
- cast(str, format_spec), args, kwargs, used_args, recursion_depth - 1, auto_arg_index=auto_arg_index
+ format_spec, _ = self._vformat(
+ cast(str, format_spec), args, kwargs, used_args, recursion_depth - 1, auto_arg_index=False
)
# format the object and append to the result
@@ -118,7 +120,7 @@ class MetadataFormatter(string.Formatter):
fmt_obj = str(sanitize_filename(fmt_obj, platform=self.platform))
result.append(fmt_obj)
- return "".join(result), auto_arg_index
+ return "".join(result), False
class FileRenamer:
@@ -168,16 +170,17 @@ class FileRenamer:
md_dict["month_name"] = ""
md_dict["month_abbr"] = ""
- for Component in pathlib.PureWindowsPath(template).parts:
+ new_basename = ""
+ for component in pathlib.PureWindowsPath(template).parts:
if (
self.platform.casefold() in ["universal", "windows"] or sys.platform.casefold() in ["windows"]
) and self.smart_cleanup:
# colons get special treatment
- Component = Component.replace(": ", " - ")
- Component = Component.replace(":", "-")
+ component = component.replace(": ", " - ")
+ component = component.replace(":", "-")
new_basename = str(
- sanitize_filename(fmt.vformat(Component, args=[], kwargs=Default(md_dict)), platform=self.platform)
+ sanitize_filename(fmt.vformat(component, args=[], kwargs=Default(md_dict)), platform=self.platform)
).strip()
new_name = os.path.join(new_name, new_basename)
diff --git a/comictaggerlib/fileselectionlist.py b/comictaggerlib/fileselectionlist.py
index aeb6dd4..385ae18 100644
--- a/comictaggerlib/fileselectionlist.py
+++ b/comictaggerlib/fileselectionlist.py
@@ -17,13 +17,16 @@ from __future__ import annotations
import logging
import os
+import platform
from typing import Callable, cast
from PyQt5 import QtCore, QtWidgets, uic
from comicapi import utils
from comicapi.comicarchive import ComicArchive
+from comictaggerlib.optionalmsgdialog import OptionalMessageDialog
from comictaggerlib.settings import ComicTaggerSettings
+from comictaggerlib.settingswindow import linuxRarHelp, macRarHelp, windowsRarHelp
from comictaggerlib.ui.qtutils import center_window_on_parent, reduce_widget_font_size
logger = logging.getLogger(__name__)
@@ -88,6 +91,7 @@ class FileSelectionList(QtWidgets.QWidget):
self.addAction(self.separator)
self.dirty_flag_verification = dirty_flag_verification
+ self.rar_ro_shown = False
def get_sorting(self) -> tuple[int, int]:
col = self.twList.horizontalHeader().sortIndicatorSection()
@@ -190,6 +194,7 @@ class FileSelectionList(QtWidgets.QWidget):
QtCore.QCoreApplication.processEvents()
first_added = None
+ rar_added = False
self.twList.setSortingEnabled(False)
for idx, f in enumerate(filelist):
QtCore.QCoreApplication.processEvents()
@@ -200,8 +205,12 @@ class FileSelectionList(QtWidgets.QWidget):
center_window_on_parent(progdialog)
QtCore.QCoreApplication.processEvents()
row = self.add_path_item(f)
- if first_added is None and row is not None:
- first_added = row
+ if row is not None:
+ ca = self.get_archive_by_row(row)
+ if ca and ca.is_rar():
+ rar_added = True
+ if first_added is None:
+ first_added = row
progdialog.hide()
QtCore.QCoreApplication.processEvents()
@@ -216,6 +225,9 @@ class FileSelectionList(QtWidgets.QWidget):
else:
QtWidgets.QMessageBox.information(self, "File/Folder Open", "No readable comic archives were found.")
+ if rar_added and not utils.which(self.settings.rar_exe_path or "rar"):
+ self.rar_ro_message()
+
self.twList.setSortingEnabled(True)
# Adjust column size
@@ -229,6 +241,26 @@ class FileSelectionList(QtWidgets.QWidget):
if self.twList.columnWidth(FileSelectionList.folderColNum) > 200:
self.twList.setColumnWidth(FileSelectionList.folderColNum, 200)
+ def rar_ro_message(self) -> None:
+ if not self.rar_ro_shown:
+ if platform.system() == "Windows":
+ rar_help = windowsRarHelp
+
+ elif platform.system() == "Darwin":
+ rar_help = macRarHelp
+
+ else:
+ rar_help = linuxRarHelp
+
+ OptionalMessageDialog.msg_no_checkbox(
+ self,
+ "RAR Files are Read-Only",
+ "It looks like you have opened a RAR/CBR archive,\n"
+ "however ComicTagger cannot currently write to them without the rar program and are marked read only!\n\n"
+ f"{rar_help}",
+ )
+ self.rar_ro_shown = True
+
def is_list_dupe(self, path: str) -> bool:
return self.get_current_list_row(path) >= 0
@@ -344,7 +376,7 @@ class FileSelectionList(QtWidgets.QWidget):
try:
fi.ca.read_cix()
except Exception:
- ...
+ pass
fi.ca.has_cbi()
def get_selected_archive_list(self) -> list[ComicArchive]:
diff --git a/comictaggerlib/imagefetcher.py b/comictaggerlib/imagefetcher.py
index f88d66a..a229ac4 100644
--- a/comictaggerlib/imagefetcher.py
+++ b/comictaggerlib/imagefetcher.py
@@ -38,7 +38,7 @@ logger = logging.getLogger(__name__)
class ImageFetcherException(Exception):
- pass
+ ...
def fetch_complete(image_data: bytes | QtCore.QByteArray) -> None:
diff --git a/comictaggerlib/imagehasher.py b/comictaggerlib/imagehasher.py
index 0d21203..f8662ff 100755
--- a/comictaggerlib/imagehasher.py
+++ b/comictaggerlib/imagehasher.py
@@ -49,7 +49,7 @@ class ImageHasher:
def average_hash(self) -> int:
try:
- image = self.image.resize((self.width, self.height), Image.ANTIALIAS).convert("L")
+ image = self.image.resize((self.width, self.height), Image.Resampling.LANCZOS).convert("L")
except Exception:
logger.exception("average_hash error")
return 0
diff --git a/comictaggerlib/imagepopup.py b/comictaggerlib/imagepopup.py
index ff72c51..1c63cfa 100644
--- a/comictaggerlib/imagepopup.py
+++ b/comictaggerlib/imagepopup.py
@@ -51,7 +51,7 @@ class ImagePopup(QtWidgets.QDialog):
self.clientBgPixmap = bg.scaled(
screen_size.width(),
screen_size.height(),
- QtCore.Qt.AspectRatioMode.KeepAspectRatio,
+ QtCore.Qt.AspectRatioMode.IgnoreAspectRatio,
QtCore.Qt.SmoothTransformation,
)
self.setMask(self.clientBgPixmap.mask())
diff --git a/comictaggerlib/issueidentifier.py b/comictaggerlib/issueidentifier.py
index 35704a4..b83c0b8 100644
--- a/comictaggerlib/issueidentifier.py
+++ b/comictaggerlib/issueidentifier.py
@@ -59,11 +59,11 @@ class Score(TypedDict):
class IssueIdentifierNetworkError(Exception):
- pass
+ ...
class IssueIdentifierCancelled(Exception):
- pass
+ ...
class IssueIdentifier:
@@ -98,7 +98,7 @@ class IssueIdentifier:
# used to eliminate series names that are too long based on our search
# string
- self.length_delta_thresh = settings.id_length_delta_thresh
+ self.series_match_thresh = settings.id_series_match_identify_thresh
# used to eliminate unlikely publishers
self.publisher_filter = [s.strip().casefold() for s in settings.id_publisher_filter.split(",")]
@@ -122,8 +122,8 @@ class IssueIdentifier:
def set_additional_metadata(self, md: GenericMetadata) -> None:
self.additional_metadata = md
- def set_name_length_delta_threshold(self, delta: int) -> None:
- self.length_delta_thresh = delta
+ def set_name_series_match_threshold(self, delta: int) -> None:
+ self.series_match_thresh = delta
def set_publisher_filter(self, flt: list[str]) -> None:
self.publisher_filter = flt
@@ -177,35 +177,29 @@ class IssueIdentifier:
def get_search_keys(self) -> SearchKeys:
ca = self.comic_archive
- search_keys: SearchKeys = {
- "series": None,
- "issue_number": None,
- "month": None,
- "year": None,
- "issue_count": None,
- }
if ca is None:
return None
-
+ search_keys: SearchKeys
if self.only_use_additional_meta_data:
- search_keys["series"] = self.additional_metadata.series
- search_keys["issue_number"] = self.additional_metadata.issue
- search_keys["year"] = self.additional_metadata.year
- search_keys["month"] = self.additional_metadata.month
- search_keys["issue_count"] = self.additional_metadata.issue_count
+ search_keys = SearchKeys(
+ series=self.additional_metadata.series,
+ issue_number=self.additional_metadata.issue,
+ year=self.additional_metadata.year,
+ month=self.additional_metadata.month,
+ issue_count=self.additional_metadata.issue_count,
+ )
return search_keys
# see if the archive has any useful meta data for searching with
- if ca.has_cix():
- try:
+ try:
+ if ca.has_cix():
internal_metadata = ca.read_cix()
- except Exception as e:
- logger.error("Failed to load metadata for %s: %s", ca.path, e)
- elif ca.has_cbi():
- internal_metadata = ca.read_cbi()
- else:
- internal_metadata = ca.read_cbi()
+ else:
+ internal_metadata = ca.read_cbi()
+ except Exception as e:
+ internal_metadata = GenericMetadata()
+ logger.error("Failed to load metadata for %s: %s", ca.path, e)
# try to get some metadata from filename
md_from_filename = ca.metadata_from_filename(
@@ -215,45 +209,22 @@ class IssueIdentifier:
self.settings.remove_publisher,
)
+ working_md = md_from_filename.copy()
+
+ working_md.overlay(internal_metadata)
+ working_md.overlay(self.additional_metadata)
+
# preference order:
# 1. Additional metadata
# 1. Internal metadata
# 1. Filename metadata
-
- if self.additional_metadata.series is not None:
- search_keys["series"] = self.additional_metadata.series
- elif internal_metadata.series is not None:
- search_keys["series"] = internal_metadata.series
- else:
- search_keys["series"] = md_from_filename.series
-
- if self.additional_metadata.issue is not None:
- search_keys["issue_number"] = self.additional_metadata.issue
- elif internal_metadata.issue is not None:
- search_keys["issue_number"] = internal_metadata.issue
- else:
- search_keys["issue_number"] = md_from_filename.issue
-
- if self.additional_metadata.year is not None:
- search_keys["year"] = self.additional_metadata.year
- elif internal_metadata.year is not None:
- search_keys["year"] = internal_metadata.year
- else:
- search_keys["year"] = md_from_filename.year
-
- if self.additional_metadata.month is not None:
- search_keys["month"] = self.additional_metadata.month
- elif internal_metadata.month is not None:
- search_keys["month"] = internal_metadata.month
- else:
- search_keys["month"] = md_from_filename.month
-
- if self.additional_metadata.issue_count is not None:
- search_keys["issue_count"] = self.additional_metadata.issue_count
- elif internal_metadata.issue_count is not None:
- search_keys["issue_count"] = internal_metadata.issue_count
- else:
- search_keys["issue_count"] = md_from_filename.issue_count
+ search_keys = SearchKeys(
+ series=working_md.series,
+ issue_number=working_md.issue,
+ year=working_md.year,
+ month=working_md.month,
+ issue_count=working_md.issue_count,
+ )
return search_keys
@@ -294,9 +265,7 @@ class IssueIdentifier:
if self.cover_url_callback is not None:
self.cover_url_callback(url_image_data)
- remote_cover_list = []
-
- remote_cover_list.append(Score({"url": primary_img_url, "hash": self.calculate_hash(url_image_data)}))
+ remote_cover_list = [Score(url=primary_img_url, hash=self.calculate_hash(url_image_data))]
if self.cancel:
raise IssueIdentifierCancelled
@@ -317,7 +286,7 @@ class IssueIdentifier:
if self.cover_url_callback is not None:
self.cover_url_callback(alt_url_image_data)
- remote_cover_list.append(Score({"url": alt_url, "hash": self.calculate_hash(alt_url_image_data)}))
+ remote_cover_list.append(Score(url=alt_url, hash=self.calculate_hash(alt_url_image_data)))
if self.cancel:
raise IssueIdentifierCancelled
@@ -332,9 +301,7 @@ class IssueIdentifier:
for local_cover_hash in local_cover_hash_list:
for remote_cover_item in remote_cover_list:
score = ImageHasher.hamming_distance(local_cover_hash, remote_cover_item["hash"])
- score_list.append(
- Score({"score": score, "url": remote_cover_item["url"], "hash": remote_cover_item["hash"]})
- )
+ score_list.append(Score(score=score, url=remote_cover_item["url"], hash=remote_cover_item["hash"]))
if use_log:
self.log_msg(score, False)
@@ -431,15 +398,13 @@ class IssueIdentifier:
if int(keys["year"]) < int(item["start_year"]):
date_approved = False
- # assume that our search name is close to the actual name, say
- # within ,e.g. 5 chars
- # sanitize both the search string and the result so that
- # we are comparing the same type of data
- shortened_key = utils.sanitize_title(keys["series"])
- shortened_item_name = utils.sanitize_title(item["name"])
- if len(shortened_item_name) < (len(shortened_key) + self.length_delta_thresh):
- length_approved = True
-
+ aliases = []
+ if item["aliases"]:
+ aliases = item["aliases"].split("\n")
+ for name in [item["name"], *aliases]:
+ if utils.titles_match(keys["series"], name, self.series_match_thresh):
+ length_approved = True
+ break
# remove any series from publishers on the filter
if item["publisher"] is not None:
publisher = item["publisher"]
diff --git a/comictaggerlib/issueselectionwindow.py b/comictaggerlib/issueselectionwindow.py
index 1ec92ce..2cb3b60 100644
--- a/comictaggerlib/issueselectionwindow.py
+++ b/comictaggerlib/issueselectionwindow.py
@@ -138,18 +138,18 @@ class IssueSelectionWindow(QtWidgets.QDialog):
if len(parts) > 1:
item_text = parts[0] + "-" + parts[1]
- QTW_item = QtWidgets.QTableWidgetItem(item_text)
- QTW_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
- QTW_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
- self.twList.setItem(row, 1, QTW_item)
+ qtw_item = QtWidgets.QTableWidgetItem(item_text)
+ qtw_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
+ qtw_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
+ self.twList.setItem(row, 1, qtw_item)
item_text = record["name"]
if item_text is None:
item_text = ""
- QTW_item = QtWidgets.QTableWidgetItem(item_text)
- QTW_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
- QTW_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
- self.twList.setItem(row, 2, QTW_item)
+ qtw_item = QtWidgets.QTableWidgetItem(item_text)
+ qtw_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
+ qtw_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
+ self.twList.setItem(row, 2, qtw_item)
if (
IssueString(record["issue_number"]).as_string().casefold()
diff --git a/comictaggerlib/main.py b/comictaggerlib/main.py
index 97e0bac..f119782 100755
--- a/comictaggerlib/main.py
+++ b/comictaggerlib/main.py
@@ -93,7 +93,7 @@ try:
except ImportError as e:
def show_exception_box(log_msg: str) -> None:
- pass
+ ...
logger.error(str(e))
qt_available = False
@@ -116,7 +116,7 @@ def update_publishers() -> None:
def ctmain() -> None:
opts = parse_cmd_line()
- SETTINGS = ComicTaggerSettings(opts.config_path)
+ settings = ComicTaggerSettings(opts.config_path)
os.makedirs(ComicTaggerSettings.get_settings_folder() / "logs", exist_ok=True)
stream_handler = logging.StreamHandler()
@@ -149,18 +149,18 @@ def ctmain() -> None:
for pkg in sorted(importlib_metadata.distributions(), key=lambda x: x.name):
logger.debug("%s\t%s", pkg.name, pkg.version)
- talker_api = ComicTalker(SETTINGS.comic_info_source)
+ talker_api = ComicTalker(settings.comic_info_source)
utils.load_publishers()
update_publishers()
if not qt_available and not opts.no_gui:
opts.no_gui = True
- logger.warn("PyQt5 is not available. ComicTagger is limited to command-line mode.")
+ logger.warning("PyQt5 is not available. ComicTagger is limited to command-line mode.")
if opts.no_gui:
try:
- cli.cli_mode(opts, SETTINGS, talker_api)
+ cli.cli_mode(opts, settings, talker_api)
except Exception:
logger.exception("CLI mode failed")
else:
@@ -196,7 +196,7 @@ def ctmain() -> None:
QtWidgets.QApplication.processEvents()
try:
- tagger_window = TaggerWindow(opts.files, SETTINGS, talker_api, opts=opts)
+ tagger_window = TaggerWindow(opts.files, settings, talker_api, opts=opts)
tagger_window.setWindowIcon(QtGui.QIcon(ComicTaggerSettings.get_graphic("app.png")))
tagger_window.show()
diff --git a/comictaggerlib/optionalmsgdialog.py b/comictaggerlib/optionalmsgdialog.py
index 6ba86b2..23c2de3 100644
--- a/comictaggerlib/optionalmsgdialog.py
+++ b/comictaggerlib/optionalmsgdialog.py
@@ -112,3 +112,14 @@ class OptionalMessageDialog(QtWidgets.QDialog):
d.exec()
return d.was_accepted, d.theCheckBox.isChecked()
+
+ @staticmethod
+ def msg_no_checkbox(
+ parent: QtWidgets.QWidget, title: str, msg: str, checked: bool = False, check_text: str = ""
+ ) -> bool:
+
+ d = OptionalMessageDialog(parent, StyleMessage, title, msg, checked=checked, check_text=check_text)
+ d.theCheckBox.hide()
+
+ d.exec()
+ return d.theCheckBox.isChecked()
diff --git a/comictaggerlib/pagelisteditor.py b/comictaggerlib/pagelisteditor.py
index ca93d4f..85530ee 100644
--- a/comictaggerlib/pagelisteditor.py
+++ b/comictaggerlib/pagelisteditor.py
@@ -120,10 +120,10 @@ class PageListEditor(QtWidgets.QWidget):
if show_shortcut:
text = text + " (" + shortcut + ")"
self.cbPageType.addItem(text, user_data)
- actionItem = QtWidgets.QAction(shortcut, self)
- actionItem.triggered.connect(lambda: self.select_page_type_item(self.cbPageType.findData(user_data)))
- actionItem.setShortcut(shortcut)
- self.addAction(actionItem)
+ action_item = QtWidgets.QAction(shortcut, self)
+ action_item.triggered.connect(lambda: self.select_page_type_item(self.cbPageType.findData(user_data)))
+ action_item.setShortcut(shortcut)
+ self.addAction(action_item)
def select_page_type_item(self, idx: int) -> None:
if self.cbPageType.isEnabled():
@@ -133,19 +133,19 @@ class PageListEditor(QtWidgets.QWidget):
def get_new_indexes(self, movement: int) -> list[tuple[int, int]]:
selection = self.listWidget.selectionModel().selectedRows()
selection.sort(reverse=movement > 0)
- newindexes: list[int] = []
- oldindexes: list[int] = []
+ new_indexes: list[int] = []
+ old_indexes: list[int] = []
for x in selection:
current = x.row()
- oldindexes.append(current)
+ old_indexes.append(current)
if 0 <= current + movement <= self.listWidget.count() - 1:
- if len(newindexes) < 1 or current + movement != newindexes[-1]:
+ if len(new_indexes) < 1 or current + movement != new_indexes[-1]:
current += movement
- newindexes.append(current)
- oldindexes.sort()
- newindexes.sort()
- return list(zip(newindexes, oldindexes))
+ new_indexes.append(current)
+ old_indexes.sort()
+ new_indexes.sort()
+ return list(zip(new_indexes, old_indexes))
def set_selection(self, indexes: list[tuple[int, int]]) -> list[tuple[int, int]]:
selection_ranges: list[tuple[int, int]] = []
diff --git a/comictaggerlib/renamewindow.py b/comictaggerlib/renamewindow.py
index 7f5af28..a34df90 100644
--- a/comictaggerlib/renamewindow.py
+++ b/comictaggerlib/renamewindow.py
@@ -16,15 +16,13 @@
from __future__ import annotations
import logging
-import os
-import shutil
-from typing import TypedDict
from PyQt5 import QtCore, QtWidgets, uic
from comicapi import utils
from comicapi.comicarchive import ComicArchive, MetaDataStyle
-from comictaggerlib.filerenamer import FileRenamer
+from comicapi.genericmetadata import GenericMetadata
+from comictaggerlib.filerenamer import FileRenamer, get_rename_dir
from comictaggerlib.settings import ComicTaggerSettings
from comictaggerlib.settingswindow import SettingsWindow
from comictaggerlib.ui.qtutils import center_window_on_parent
@@ -33,11 +31,6 @@ from comictalker.comictalker import ComicTalker
logger = logging.getLogger(__name__)
-class RenameItem(TypedDict):
- archive: ComicArchive
- new_name: str
-
-
class RenameWindow(QtWidgets.QDialog):
def __init__(
self,
@@ -64,35 +57,28 @@ class RenameWindow(QtWidgets.QDialog):
self.talker_api = talker_api
self.comic_archive_list = comic_archive_list
self.data_style = data_style
- self.rename_list: list[RenameItem] = []
+ self.rename_list: list[str] = []
self.btnSettings.clicked.connect(self.modify_settings)
self.renamer = FileRenamer(None, platform="universal" if self.settings.rename_strict else "auto")
- self.config_renamer()
self.do_preview()
- def config_renamer(self) -> None:
+ def config_renamer(self, ca: ComicArchive, md: GenericMetadata | None = None) -> str:
self.renamer.set_template(self.settings.rename_template)
self.renamer.set_issue_zero_padding(self.settings.rename_issue_number_padding)
self.renamer.set_smart_cleanup(self.settings.rename_use_smart_string_cleanup)
- def do_preview(self) -> None:
- self.twList.setRowCount(0)
-
- self.twList.setSortingEnabled(False)
-
- for ca in self.comic_archive_list:
-
- new_ext = ca.path.suffix # default
- if self.settings.rename_extension_based_on_archive:
- if ca.is_sevenzip():
- new_ext = ".cb7"
- elif ca.is_zip():
- new_ext = ".cbz"
- elif ca.is_rar():
- new_ext = ".cbr"
+ new_ext = ca.path.suffix # default
+ if self.settings.rename_extension_based_on_archive:
+ if ca.is_sevenzip():
+ new_ext = ".cb7"
+ elif ca.is_zip():
+ new_ext = ".cbz"
+ elif ca.is_rar():
+ new_ext = ".cbr"
+ if md is None:
md = ca.read_metadata(self.data_style)
if md.is_empty:
md = ca.metadata_from_filename(
@@ -101,9 +87,17 @@ class RenameWindow(QtWidgets.QDialog):
self.settings.remove_fcbd,
self.settings.remove_publisher,
)
- self.renamer.set_metadata(md)
- self.renamer.move = self.settings.rename_move_dir
+ self.renamer.set_metadata(md)
+ self.renamer.move = self.settings.rename_move_dir
+ return new_ext
+ def do_preview(self) -> None:
+ self.twList.setRowCount(0)
+
+ self.twList.setSortingEnabled(False)
+
+ for ca in self.comic_archive_list:
+ new_ext = self.config_renamer(ca)
try:
new_name = self.renamer.determine_name(new_ext)
except Exception as e:
@@ -125,13 +119,13 @@ class RenameWindow(QtWidgets.QDialog):
old_name_item = QtWidgets.QTableWidgetItem()
new_name_item = QtWidgets.QTableWidgetItem()
- item_text = os.path.split(ca.path)[0]
+ item_text = str(ca.path.parent)
folder_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
self.twList.setItem(row, 0, folder_item)
folder_item.setText(item_text)
folder_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, item_text)
- item_text = os.path.split(ca.path)[1]
+ item_text = str(ca.path.name)
old_name_item.setFlags(QtCore.Qt.ItemFlag.ItemIsSelectable | QtCore.Qt.ItemFlag.ItemIsEnabled)
self.twList.setItem(row, 1, old_name_item)
old_name_item.setText(item_text)
@@ -142,13 +136,7 @@ class RenameWindow(QtWidgets.QDialog):
new_name_item.setText(new_name)
new_name_item.setData(QtCore.Qt.ItemDataRole.ToolTipRole, new_name)
- dict_item = RenameItem(
- {
- "archive": ca,
- "new_name": new_name,
- }
- )
- self.rename_list.append(dict_item)
+ self.rename_list.append(new_name)
# Adjust column sizes
self.twList.setVisible(False)
@@ -165,7 +153,6 @@ class RenameWindow(QtWidgets.QDialog):
settingswin.show_rename_tab()
settingswin.exec()
if settingswin.result():
- self.config_renamer()
self.do_preview()
def accept(self) -> None:
@@ -177,34 +164,29 @@ class RenameWindow(QtWidgets.QDialog):
center_window_on_parent(prog_dialog)
QtCore.QCoreApplication.processEvents()
- for idx, item in enumerate(self.rename_list):
+ for idx, comic in enumerate(zip(self.comic_archive_list, self.rename_list)):
QtCore.QCoreApplication.processEvents()
if prog_dialog.wasCanceled():
break
idx += 1
prog_dialog.setValue(idx)
- prog_dialog.setLabelText(item["new_name"])
+ prog_dialog.setLabelText(comic[1])
center_window_on_parent(prog_dialog)
QtCore.QCoreApplication.processEvents()
- folder = os.path.dirname(os.path.abspath(item["archive"].path))
- if self.settings.rename_move_dir and len(self.settings.rename_dir.strip()) > 3:
- folder = self.settings.rename_dir.strip()
+ folder = get_rename_dir(comic[0], self.settings.rename_dir if self.settings.rename_move_dir else None)
- new_abs_path = utils.unique_file(os.path.join(folder, item["new_name"]))
+ full_path = folder / comic[1]
- if os.path.join(folder, item["new_name"]) == item["archive"].path:
- logger.info(item["new_name"], "Filename is already good!")
+ if full_path == comic[0].path:
+ logger.info("%s: Filename is already good!", comic[1])
continue
- if not item["archive"].is_writable(check_rar_status=False):
+ if not comic[0].is_writable(check_rar_status=False):
continue
- os.makedirs(os.path.dirname(new_abs_path), 0o777, True)
- shutil.move(item["archive"].path, new_abs_path)
-
- item["archive"].rename(new_abs_path)
+ comic[0].rename(utils.unique_file(full_path))
prog_dialog.hide()
QtCore.QCoreApplication.processEvents()
diff --git a/comictaggerlib/settings.py b/comictaggerlib/settings.py
index 39ed6d7..df4d3a4 100644
--- a/comictaggerlib/settings.py
+++ b/comictaggerlib/settings.py
@@ -102,7 +102,8 @@ class ComicTaggerSettings:
self.last_filelist_sorted_order = 0
# identifier settings
- self.id_length_delta_thresh = 5
+ self.id_series_match_search_thresh = 90
+ self.id_series_match_identify_thresh = 91
self.id_publisher_filter = "Panini Comics, Abril, Planeta DeAgostini, Editorial Televisa, Dino Comics"
self.comic_info_source = "comicvine" # Default to CV as should always be present
@@ -181,10 +182,12 @@ class ComicTaggerSettings:
elif os.path.exists(r"C:\Program Files (x86)\WinRAR\Rar.exe"):
self.rar_exe_path = r"C:\Program Files (x86)\WinRAR\Rar.exe"
else:
+ if os.path.exists("/opt/homebrew/bin"):
+ utils.add_to_path("/opt/homebrew/bin")
# see if it's in the path of unix user
rarpath = utils.which("rar")
if rarpath is not None:
- self.rar_exe_path = rarpath
+ self.rar_exe_path = "rar"
if self.rar_exe_path != "":
self.save()
if self.rar_exe_path != "":
@@ -236,8 +239,10 @@ class ComicTaggerSettings:
if self.config.has_option("auto", "last_filelist_sorted_order"):
self.last_filelist_sorted_order = self.config.getint("auto", "last_filelist_sorted_order")
- if self.config.has_option("identifier", "id_length_delta_thresh"):
- self.id_length_delta_thresh = self.config.getint("identifier", "id_length_delta_thresh")
+ if self.config.has_option("identifier", "id_series_match_search_thresh"):
+ self.id_series_match_search_thresh = self.config.getint("identifier", "id_series_match_search_thresh")
+ if self.config.has_option("identifier", "id_series_match_identify_thresh"):
+ self.id_series_match_identify_thresh = self.config.getint("identifier", "id_series_match_identify_thresh")
if self.config.has_option("identifier", "id_publisher_filter"):
self.id_publisher_filter = self.config.get("identifier", "id_publisher_filter")
if self.config.has_option("identifier", "always_use_publisher_filter"):
@@ -364,7 +369,8 @@ class ComicTaggerSettings:
if not self.config.has_section("identifier"):
self.config.add_section("identifier")
- self.config.set("identifier", "id_length_delta_thresh", self.id_length_delta_thresh)
+ self.config.set("identifier", "id_series_match_search_thresh", self.id_series_match_search_thresh)
+ self.config.set("identifier", "id_series_match_identify_thresh", self.id_series_match_identify_thresh)
self.config.set("identifier", "id_publisher_filter", self.id_publisher_filter)
self.config.set("identifier", "always_use_publisher_filter", self.always_use_publisher_filter)
diff --git a/comictaggerlib/settingswindow.py b/comictaggerlib/settingswindow.py
index 43ecfdf..55ff693 100644
--- a/comictaggerlib/settingswindow.py
+++ b/comictaggerlib/settingswindow.py
@@ -18,6 +18,7 @@ from __future__ import annotations
import html
import logging
import os
+import pathlib
import platform
from PyQt5 import QtCore, QtGui, QtWidgets, uic
@@ -33,29 +34,29 @@ from comictalker.comictalker import ComicTalker
logger = logging.getLogger(__name__)
windowsRarHelp = """
-