comictagger/comictaggerlib/filerenamer.py

252 lines
9.6 KiB
Python
Raw Normal View History

"""Functions for renaming files based on metadata"""
2022-06-02 18:32:16 -07:00
#
# Copyright 2012-2014 ComicTagger Authors
2022-06-02 18:32:16 -07:00
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
2022-06-02 18:32:16 -07:00
#
# http://www.apache.org/licenses/LICENSE-2.0
2022-06-02 18:32:16 -07:00
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
2022-06-02 18:32:16 -07:00
from __future__ import annotations
import calendar
2022-04-04 18:59:26 -07:00
import logging
import os
import pathlib
import string
2023-04-22 17:54:58 -07:00
from collections.abc import Mapping, Sequence
2022-11-23 22:16:46 -08:00
from typing import Any, cast
from pathvalidate import Platform, normalize_platform, sanitize_filename
from comicapi.comicarchive import ComicArchive
Code cleanup Remove no longer used google scripts Remove convenience files from comicataggerlib and import comicapi directly Add type-hints to facilitate auto-complete tools Make PyQt5 code more compatible with PyQt6 Implement automatic tooling isort and black for code formatting Line length has been set to 120 flake8 for code standards with exceptions: E203 - Whitespace before ':' - format compatiblity with black E501 - Line too long - flake8 line limit cannot be set E722 - Do not use bare except - fixing bare except statements is a lot of overhead and there are already many in the codebase These changes, along with some manual fixes creates much more readable code. See examples below: diff --git a/comicapi/comet.py b/comicapi/comet.py index d1741c5..52dc195 100644 --- a/comicapi/comet.py +++ b/comicapi/comet.py @@ -166,7 +166,2 @@ class CoMet: - if credit['role'].lower() in set(self.editor_synonyms): - ET.SubElement( - root, - 'editor').text = "{0}".format( - credit['person']) @@ -174,2 +169,4 @@ class CoMet: self.indent(root) + if credit["role"].lower() in set(self.editor_synonyms): + ET.SubElement(root, "editor").text = str(credit["person"]) diff --git a/comictaggerlib/autotagmatchwindow.py b/comictaggerlib/autotagmatchwindow.py index 4338176..9219f01 100644 --- a/comictaggerlib/autotagmatchwindow.py +++ b/comictaggerlib/autotagmatchwindow.py @@ -63,4 +63,3 @@ class AutoTagMatchWindow(QtWidgets.QDialog): self.skipButton, QtWidgets.QDialogButtonBox.ActionRole) - self.buttonBox.button(QtWidgets.QDialogButtonBox.Ok).setText( - "Accept and Write Tags") + self.buttonBox.button(QtWidgets.QDialogButtonBox.StandardButton.Ok).setText("Accept and Write Tags") diff --git a/comictaggerlib/cli.py b/comictaggerlib/cli.py index 688907d..dbd0c2e 100644 --- a/comictaggerlib/cli.py +++ b/comictaggerlib/cli.py @@ -293,7 +293,3 @@ def process_file_cli(filename, opts, settings, match_results): if opts.raw: - print(( - "{0}".format( - str( - ca.readRawCIX(), - errors='ignore')))) + print(ca.read_raw_cix()) else:
2022-04-01 16:50:46 -07:00
from comicapi.genericmetadata import GenericMetadata
from comicapi.issuestring import IssueString
2022-11-23 22:16:46 -08:00
from comictaggerlib.defaults import DEFAULT_REPLACEMENTS, Replacement, Replacements
2022-04-04 18:59:26 -07:00
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 = pathlib.Path(rename_dir.strip())
folder = rename_dir.absolute()
return folder
class MetadataFormatter(string.Formatter):
def __init__(
2022-11-23 22:16:46 -08:00
self, smart_cleanup: bool = False, platform: str = "auto", replacements: Replacements = DEFAULT_REPLACEMENTS
) -> None:
super().__init__()
self.smart_cleanup = smart_cleanup
self.platform = normalize_platform(platform)
self.replacements = replacements
2022-05-17 13:57:04 -07:00
def format_field(self, value: Any, format_spec: str) -> str:
if value is None or value == "":
return ""
2022-05-17 13:57:04 -07:00
return cast(str, super().format_field(value, format_spec))
def convert_field(self, value: Any, conversion: str) -> str:
if conversion == "u":
return str(value).upper()
if conversion == "l":
return str(value).casefold()
if conversion == "c":
return str(value).capitalize()
if conversion == "S":
return str(value).swapcase()
if conversion == "t":
return str(value).title()
Convert ComicIssue into GenericMetadata I could not find a good reason for ComicIssue to exist other than that it had more attributes than GenericMetadata, so it has been replaced. New attributes for GenericMetadata: series_id: a string uniquely identifying the series to tag_origin series_aliases: alternate series names that are not the canonical name title_aliases: alternate issue titles that are not the canonical name alternate_images: a list of urls to alternate cover images Updated attributes for GenericMetadata: genre -> genres: str -> list[str] comments -> description: str -> str story_arc -> story_arcs: str -> list[str] series_group -> series_groups: str -> list[str] character -> characters: str -> list[str] team -> teams: str -> list[str] location -> locations: str -> list[str] tag_origin -> tag_origin: str -> TagOrigin (tuple[str, str]) ComicSeries has been relocated to the ComicAPI package, currently has no usage within ComicAPI. CreditMetadata has been renamed to Credit and has replaced Credit from ComicTalker. fetch_series has been added to ComicTalker, this is currently only used in the GUI when a series is selected and does not already contain the needed fields, this function should always be cached. A new split function has been added to ComicAPI, all uses of split on single characters have been updated to use this cleanup_html and the corresponding setting are now only used in ComicTagger proper, for display we want any html directly from the upstream. When applying the metadata we then strip the description of any html. A new conversion has been added to the MetadataFormatter: j: joins any lists into a string with ', '. Note this is a valid operation on strings as well, it will add ', ' in between every character. parse_settings now assigns the given ComicTaggerPaths object to the result ensuring that the correct path is always used.
2023-08-02 09:00:04 -07:00
if conversion == "j":
return ", ".join(list(str(v) for v in value))
return cast(str, super().convert_field(value, conversion))
def handle_replacements(self, string: str, replacements: list[Replacement]) -> str:
for find, replace, strict_only in replacements:
if self.is_strict() or not strict_only:
string = string.replace(find, replace)
return string
def none_replacement(self, value: Any, replacement: str, r: str) -> Any:
if r == "-" and value is None or value == "":
return replacement
if r == "+" and value is not None:
return replacement
return value
def split_replacement(self, field_name: str) -> tuple[str, str, str]:
if "-" in field_name:
return field_name.rpartition("-")
if "+" in field_name:
return field_name.rpartition("+")
return field_name, "", ""
def is_strict(self) -> bool:
return self.platform in [Platform.UNIVERSAL, Platform.WINDOWS]
2022-05-17 13:57:04 -07:00
def _vformat(
self,
format_string: str,
2023-04-22 17:54:58 -07:00
args: Sequence[Any],
kwargs: Mapping[str, Any],
2022-05-17 13:57:04 -07:00
used_args: set[Any],
recursion_depth: int,
auto_arg_index: int = 0,
) -> tuple[str, int]:
if recursion_depth < 0:
raise ValueError("Max string recursion exceeded")
result = []
lstrip = False
for literal_text, field_name, format_spec, conversion in self.parse(format_string):
# output the literal text
if literal_text:
if lstrip:
literal_text = literal_text.lstrip("-_)}]#")
if self.smart_cleanup:
literal_text = self.handle_replacements(literal_text, self.replacements.literal_text)
lspace = literal_text[0].isspace() if literal_text else False
rspace = literal_text[-1].isspace() if literal_text else False
literal_text = " ".join(literal_text.split())
if literal_text == "":
literal_text = " "
else:
if lspace:
literal_text = " " + literal_text
if rspace:
literal_text += " "
result.append(literal_text)
lstrip = False
# if there's a field, output it
if field_name is not None and field_name != "":
field_name, r, replacement = self.split_replacement(field_name)
field_name = field_name.casefold()
# this is some markup, find the object and do the formatting
2022-07-13 19:56:34 -07:00
# 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
obj, arg_used = self.get_field(field_name, args, kwargs)
used_args.add(arg_used)
obj = self.none_replacement(obj, replacement, r)
# do any conversion on the resulting object
2022-05-17 13:57:04 -07:00
obj = self.convert_field(obj, conversion) # type: ignore
# expand the format spec, if needed
2022-07-13 19:56:34 -07:00
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
fmt_obj = self.format_field(obj, format_spec)
if fmt_obj == "" and result and self.smart_cleanup and literal_text:
if self.str_contains(result[-1], "({["):
lstrip = True
if result:
if " " in result[-1]:
result[-1], _, _ = result[-1].rstrip().rpartition(" ")
result[-1] = result[-1].rstrip("-_({[#")
if self.smart_cleanup:
# colons and slashes get special treatment
fmt_obj = self.handle_replacements(fmt_obj, self.replacements.format_value)
fmt_obj = " ".join(fmt_obj.split())
2022-05-17 13:57:04 -07:00
fmt_obj = str(sanitize_filename(fmt_obj, platform=self.platform))
result.append(fmt_obj)
2022-07-13 19:56:34 -07:00
return "".join(result), False
def str_contains(self, chars: str, string: str) -> bool:
for char in chars:
if char in string:
return True
return False
class FileRenamer:
2022-11-23 22:16:46 -08:00
def __init__(
self,
metadata: GenericMetadata | None,
platform: str = "auto",
replacements: Replacements = DEFAULT_REPLACEMENTS,
) -> None:
self.template = "{publisher}/{series}/{series} v{volume} #{issue} (of {issue_count}) ({year})"
self.smart_cleanup = True
self.issue_zero_padding = 3
2022-05-17 13:57:04 -07:00
self.metadata = metadata or GenericMetadata()
self.move = False
self.platform = platform
2022-11-23 22:16:46 -08:00
self.replacements = replacements
self.original_name = ""
self.move_only = False
def set_metadata(self, metadata: GenericMetadata, original_name: str) -> None:
Code cleanup Remove no longer used google scripts Remove convenience files from comicataggerlib and import comicapi directly Add type-hints to facilitate auto-complete tools Make PyQt5 code more compatible with PyQt6 Implement automatic tooling isort and black for code formatting Line length has been set to 120 flake8 for code standards with exceptions: E203 - Whitespace before ':' - format compatiblity with black E501 - Line too long - flake8 line limit cannot be set E722 - Do not use bare except - fixing bare except statements is a lot of overhead and there are already many in the codebase These changes, along with some manual fixes creates much more readable code. See examples below: diff --git a/comicapi/comet.py b/comicapi/comet.py index d1741c5..52dc195 100644 --- a/comicapi/comet.py +++ b/comicapi/comet.py @@ -166,7 +166,2 @@ class CoMet: - if credit['role'].lower() in set(self.editor_synonyms): - ET.SubElement( - root, - 'editor').text = "{0}".format( - credit['person']) @@ -174,2 +169,4 @@ class CoMet: self.indent(root) + if credit["role"].lower() in set(self.editor_synonyms): + ET.SubElement(root, "editor").text = str(credit["person"]) diff --git a/comictaggerlib/autotagmatchwindow.py b/comictaggerlib/autotagmatchwindow.py index 4338176..9219f01 100644 --- a/comictaggerlib/autotagmatchwindow.py +++ b/comictaggerlib/autotagmatchwindow.py @@ -63,4 +63,3 @@ class AutoTagMatchWindow(QtWidgets.QDialog): self.skipButton, QtWidgets.QDialogButtonBox.ActionRole) - self.buttonBox.button(QtWidgets.QDialogButtonBox.Ok).setText( - "Accept and Write Tags") + self.buttonBox.button(QtWidgets.QDialogButtonBox.StandardButton.Ok).setText("Accept and Write Tags") diff --git a/comictaggerlib/cli.py b/comictaggerlib/cli.py index 688907d..dbd0c2e 100644 --- a/comictaggerlib/cli.py +++ b/comictaggerlib/cli.py @@ -293,7 +293,3 @@ def process_file_cli(filename, opts, settings, match_results): if opts.raw: - print(( - "{0}".format( - str( - ca.readRawCIX(), - errors='ignore')))) + print(ca.read_raw_cix()) else:
2022-04-01 16:50:46 -07:00
self.metadata = metadata
self.original_name = original_name
2022-05-17 13:57:04 -07:00
def set_issue_zero_padding(self, count: int) -> None:
self.issue_zero_padding = count
2022-05-17 13:57:04 -07:00
def set_smart_cleanup(self, on: bool) -> None:
self.smart_cleanup = on
2022-05-17 13:57:04 -07:00
def set_template(self, template: str) -> None:
self.template = template
2022-05-17 13:57:04 -07:00
def determine_name(self, ext: str) -> str:
2022-11-22 16:51:26 -08:00
class Default(dict[str, Any]):
2022-05-17 13:57:04 -07:00
def __missing__(self, key: str) -> str:
return "{" + key + "}"
md = self.metadata
Code cleanup Remove no longer used google scripts Remove convenience files from comicataggerlib and import comicapi directly Add type-hints to facilitate auto-complete tools Make PyQt5 code more compatible with PyQt6 Implement automatic tooling isort and black for code formatting Line length has been set to 120 flake8 for code standards with exceptions: E203 - Whitespace before ':' - format compatiblity with black E501 - Line too long - flake8 line limit cannot be set E722 - Do not use bare except - fixing bare except statements is a lot of overhead and there are already many in the codebase These changes, along with some manual fixes creates much more readable code. See examples below: diff --git a/comicapi/comet.py b/comicapi/comet.py index d1741c5..52dc195 100644 --- a/comicapi/comet.py +++ b/comicapi/comet.py @@ -166,7 +166,2 @@ class CoMet: - if credit['role'].lower() in set(self.editor_synonyms): - ET.SubElement( - root, - 'editor').text = "{0}".format( - credit['person']) @@ -174,2 +169,4 @@ class CoMet: self.indent(root) + if credit["role"].lower() in set(self.editor_synonyms): + ET.SubElement(root, "editor").text = str(credit["person"]) diff --git a/comictaggerlib/autotagmatchwindow.py b/comictaggerlib/autotagmatchwindow.py index 4338176..9219f01 100644 --- a/comictaggerlib/autotagmatchwindow.py +++ b/comictaggerlib/autotagmatchwindow.py @@ -63,4 +63,3 @@ class AutoTagMatchWindow(QtWidgets.QDialog): self.skipButton, QtWidgets.QDialogButtonBox.ActionRole) - self.buttonBox.button(QtWidgets.QDialogButtonBox.Ok).setText( - "Accept and Write Tags") + self.buttonBox.button(QtWidgets.QDialogButtonBox.StandardButton.Ok).setText("Accept and Write Tags") diff --git a/comictaggerlib/cli.py b/comictaggerlib/cli.py index 688907d..dbd0c2e 100644 --- a/comictaggerlib/cli.py +++ b/comictaggerlib/cli.py @@ -293,7 +293,3 @@ def process_file_cli(filename, opts, settings, match_results): if opts.raw: - print(( - "{0}".format( - str( - ca.readRawCIX(), - errors='ignore')))) + print(ca.read_raw_cix()) else:
2022-04-01 16:50:46 -07:00
template = self.template
Code cleanup Remove no longer used google scripts Remove convenience files from comicataggerlib and import comicapi directly Add type-hints to facilitate auto-complete tools Make PyQt5 code more compatible with PyQt6 Implement automatic tooling isort and black for code formatting Line length has been set to 120 flake8 for code standards with exceptions: E203 - Whitespace before ':' - format compatiblity with black E501 - Line too long - flake8 line limit cannot be set E722 - Do not use bare except - fixing bare except statements is a lot of overhead and there are already many in the codebase These changes, along with some manual fixes creates much more readable code. See examples below: diff --git a/comicapi/comet.py b/comicapi/comet.py index d1741c5..52dc195 100644 --- a/comicapi/comet.py +++ b/comicapi/comet.py @@ -166,7 +166,2 @@ class CoMet: - if credit['role'].lower() in set(self.editor_synonyms): - ET.SubElement( - root, - 'editor').text = "{0}".format( - credit['person']) @@ -174,2 +169,4 @@ class CoMet: self.indent(root) + if credit["role"].lower() in set(self.editor_synonyms): + ET.SubElement(root, "editor").text = str(credit["person"]) diff --git a/comictaggerlib/autotagmatchwindow.py b/comictaggerlib/autotagmatchwindow.py index 4338176..9219f01 100644 --- a/comictaggerlib/autotagmatchwindow.py +++ b/comictaggerlib/autotagmatchwindow.py @@ -63,4 +63,3 @@ class AutoTagMatchWindow(QtWidgets.QDialog): self.skipButton, QtWidgets.QDialogButtonBox.ActionRole) - self.buttonBox.button(QtWidgets.QDialogButtonBox.Ok).setText( - "Accept and Write Tags") + self.buttonBox.button(QtWidgets.QDialogButtonBox.StandardButton.Ok).setText("Accept and Write Tags") diff --git a/comictaggerlib/cli.py b/comictaggerlib/cli.py index 688907d..dbd0c2e 100644 --- a/comictaggerlib/cli.py +++ b/comictaggerlib/cli.py @@ -293,7 +293,3 @@ def process_file_cli(filename, opts, settings, match_results): if opts.raw: - print(( - "{0}".format( - str( - ca.readRawCIX(), - errors='ignore')))) + print(ca.read_raw_cix()) else:
2022-04-01 16:50:46 -07:00
new_name = ""
Code cleanup Remove no longer used google scripts Remove convenience files from comicataggerlib and import comicapi directly Add type-hints to facilitate auto-complete tools Make PyQt5 code more compatible with PyQt6 Implement automatic tooling isort and black for code formatting Line length has been set to 120 flake8 for code standards with exceptions: E203 - Whitespace before ':' - format compatiblity with black E501 - Line too long - flake8 line limit cannot be set E722 - Do not use bare except - fixing bare except statements is a lot of overhead and there are already many in the codebase These changes, along with some manual fixes creates much more readable code. See examples below: diff --git a/comicapi/comet.py b/comicapi/comet.py index d1741c5..52dc195 100644 --- a/comicapi/comet.py +++ b/comicapi/comet.py @@ -166,7 +166,2 @@ class CoMet: - if credit['role'].lower() in set(self.editor_synonyms): - ET.SubElement( - root, - 'editor').text = "{0}".format( - credit['person']) @@ -174,2 +169,4 @@ class CoMet: self.indent(root) + if credit["role"].lower() in set(self.editor_synonyms): + ET.SubElement(root, "editor").text = str(credit["person"]) diff --git a/comictaggerlib/autotagmatchwindow.py b/comictaggerlib/autotagmatchwindow.py index 4338176..9219f01 100644 --- a/comictaggerlib/autotagmatchwindow.py +++ b/comictaggerlib/autotagmatchwindow.py @@ -63,4 +63,3 @@ class AutoTagMatchWindow(QtWidgets.QDialog): self.skipButton, QtWidgets.QDialogButtonBox.ActionRole) - self.buttonBox.button(QtWidgets.QDialogButtonBox.Ok).setText( - "Accept and Write Tags") + self.buttonBox.button(QtWidgets.QDialogButtonBox.StandardButton.Ok).setText("Accept and Write Tags") diff --git a/comictaggerlib/cli.py b/comictaggerlib/cli.py index 688907d..dbd0c2e 100644 --- a/comictaggerlib/cli.py +++ b/comictaggerlib/cli.py @@ -293,7 +293,3 @@ def process_file_cli(filename, opts, settings, match_results): if opts.raw: - print(( - "{0}".format( - str( - ca.readRawCIX(), - errors='ignore')))) + print(ca.read_raw_cix()) else:
2022-04-01 16:50:46 -07:00
2022-11-23 22:16:46 -08:00
fmt = MetadataFormatter(self.smart_cleanup, platform=self.platform, replacements=self.replacements)
md_dict = vars(md)
md_dict["web_link"] = ""
if md.web_links:
md_dict["web_link"] = md.web_links[0]
md_dict["issue"] = IssueString(md.issue).as_string(pad=self.issue_zero_padding)
for role in ["writer", "penciller", "inker", "colorist", "letterer", "cover artist", "editor"]:
md_dict[role] = md.get_primary_credit(role)
if (isinstance(md.month, int) or isinstance(md.month, str) and md.month.isdigit()) and 0 < int(md.month) < 13:
md_dict["month_name"] = calendar.month_name[int(md.month)]
md_dict["month_abbr"] = calendar.month_abbr[int(md.month)]
else:
md_dict["month_name"] = ""
md_dict["month_abbr"] = ""
2022-07-18 12:17:13 -07:00
new_basename = ""
for component in pathlib.PureWindowsPath(template).parts:
2022-05-17 13:57:04 -07:00
new_basename = str(
2022-07-18 12:17:13 -07:00
sanitize_filename(fmt.vformat(component, args=[], kwargs=Default(md_dict)), platform=self.platform)
).strip()
new_name = os.path.join(new_name, new_basename)
if self.move_only:
new_folder = os.path.join(new_name, os.path.splitext(self.original_name)[0])
return new_folder + ext
if self.move:
return new_name.strip() + ext
return new_basename.strip() + ext