txt2ebook 0.1.139__tar.gz → 0.1.141__tar.gz

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/.pre-commit-config.yaml

@@ -86,7 +86,6 @@ repos:
           - flake8-pytest-style
           - flake8-simplify
         args:
-          - --docstring-convention=google
           - --show-source
           - --max-line-length=79
           - --docstring-convention=google

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/CHANGELOG.md

@@ -7,6 +7,19 @@ and this project adheres to [0-based versioning](https://0ver.org/).
 
 ## [Unreleased]
 
+## v0.1.141 (2025-05-25)
+
+- Bump and sort deps
+- Switch `venv` backend to `uv` in `nox`
+
+## v0.1.140 (2025-05-18)
+
+- Bump deps
+- Bump local editable installation
+- Remove duplicate `pre-commit` config item
+- Remove unused `cjkwrap` import
+- Remove unused field import
+
 ## v0.1.139 (2025-05-11)
 
 - Bump deps
@@ -189,13 +202,12 @@ and this project adheres to [0-based versioning](https://0ver.org/).
 
 - Bump deps and `pre-commit` hooks
 - Migrate `typ` and `pdf` format to subcommand
-- Migrate deprecated regex-* options test cases
+- Migrate deprecated regex-\* options test cases
 - Refactor `massage` subcommand
 - Refactor language detection and validation
 - Remove Tokenizer from handling `fullwidth` flag
 - Set `deps` job in `nox` to Python 3.9
 
-
 ## v0.1.113 (2024-11-10)
 
 - Extract top keywords from txt file

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: txt2ebook
-Version: 0.1.139
+Version: 0.1.141
 Summary: CLI tool to convert txt file to ebook format
 Project-URL: Homepage, https://github.com/kianmeng/txt2ebook
 Project-URL: Repository, https://github.com/kianmeng/txt2ebook
@@ -108,12 +108,12 @@ positional arguments:
     typ
       generate ebook in Typst format
 
-options:
-  -of, --output-folder OUTPUT_FOLDER
+optional arguments:
+  -of OUTPUT_FOLDER, --output-folder OUTPUT_FOLDER
       set default output folder (default: 'output')
   -p, --purge
       remove converted ebooks specified by --output-folder option (default: 'False')
-  -l, --language LANGUAGE
+  -l LANGUAGE, --language LANGUAGE
       language of the ebook (default: 'None')
   -rw, --raise-on-warning
       raise exception and stop parsing upon warning

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/README.md

@@ -65,12 +65,12 @@ positional arguments:
     typ
       generate ebook in Typst format
 
-options:
-  -of, --output-folder OUTPUT_FOLDER
+optional arguments:
+  -of OUTPUT_FOLDER, --output-folder OUTPUT_FOLDER
       set default output folder (default: 'output')
   -p, --purge
       remove converted ebooks specified by --output-folder option (default: 'False')
-  -l, --language LANGUAGE
+  -l LANGUAGE, --language LANGUAGE
       language of the ebook (default: 'None')
   -rw, --raise-on-warning
       raise exception and stop parsing upon warning

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/noxfile.py

@@ -16,10 +16,11 @@
 """Nox configuration."""
 
 import datetime
-import re
 
 import nox
 
+nox.options.default_venv_backend = "uv"
+
 
 @nox.session(python="3.9")
 def deps(session: nox.Session) -> None:
@@ -188,9 +189,13 @@ def release(session: nox.Session) -> None:
     """Bump release."""
     _uv_install(session)
 
-    before_version = session.run("uv", "version", "--short", silent=True).strip()
+    before_version = session.run(
+        "uv", "version", "--short", silent=True
+    ).strip()
     session.run("uv", "version", "--bump", "patch")
-    after_version = session.run("uv", "version", "--short", silent=True).strip()
+    after_version = session.run(
+        "uv", "version", "--short", silent=True
+    ).strip()
 
     _search_and_replace(
         "src/txt2ebook/__init__.py", before_version, after_version
@@ -216,8 +221,7 @@ def release(session: nox.Session) -> None:
 
 
 def _uv_install(session: nox.Session) -> None:
-    session.install("uv")
-    session.run("uv", "sync")
+    session.run("uv", "sync", "--active")
 
 
 def _search_and_replace(file, search, replace) -> None:

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/pyproject.toml

@@ -1,16 +1,16 @@
 [project]
 name = "txt2ebook"
-version = "0.1.139"
+version = "0.1.141"
 description = "CLI tool to convert txt file to ebook format"
 authors = [{ name = "Kian-Meng Ang", email = "kianmeng@cpan.org" }]
 requires-python = "~=3.9"
 readme = "README.md"
 license = "AGPL-3.0-or-later"
 keywords = [
-    "txt",
+    "cjk",
     "ebook",
     "epub",
-    "cjk",
+    "txt",
 ]
 classifiers = [
     "Development Status :: 4 - Beta",
@@ -35,16 +35,16 @@ dependencies = [
     "CJKwrap~=2.2",
     "EbookLib>=0.17.1,<0.18",
     "bs4>=0.0.1,<0.0.2",
+    "importlib-resources>=6.1.1,<7",
+    "jieba>=0.42.1,<0.43",
     "langdetect>=1.0.9,<2",
-    "regex>=2021.11.10,<2022",
+    "lxml>=5.2.2,<6",
+    "pylatex>=1.4.2,<2",
     "pypandoc~=1.11",
-    "typing-extensions>=4.5.0,<5",
+    "regex>=2021.11.10,<2022",
     "reportlab>=4.0.0,<5",
+    "typing-extensions>=4.5.0,<5",
     "typst>=0.13.0",
-    "importlib-resources>=6.1.1,<7",
-    "pylatex>=1.4.2,<2",
-    "lxml>=5.2.2,<6",
-    "jieba>=0.42.1,<0.43",
 ]
 
 [project.urls]
@@ -58,24 +58,24 @@ tte = "txt2ebook.cli:main"
 [dependency-groups]
 dev = [
     "babel>=2.12.1,<3",
-    "scripttest~=1.3",
+    "bandit~=1.7.1",
     "flake8-simplify>=0.21.0,<0.22",
-    "nox>=2024.4.15,<2025",
-    "nox-poetry>=1.0.3,<2",
-    "vulture~=2.11",
     "mypy>=1.10.0,<2",
-    "bandit~=1.7.1",
+    "myst-parser>=3.0.1,<4",
+    "nox-poetry>=1.0.3,<2",
+    "nox>=2024.4.15,<2025",
     "pep8-naming>=0.13.3,<0.14",
+    "pre-commit>=2.20,<2.21",
     "pylint>=3.2.0,<4",
-    "pytest>=8.2.0,<9",
     "pytest-cov>=5.0.0,<6",
     "pytest-randomly>=3.15.0,<4",
     "pytest-xdist>=3.6.1,<4",
-    "pre-commit>=2.20,<2.21",
-    "sphinx>=7.3.7,<8",
-    "myst-parser>=3.0.1,<4",
-    "sphinx-copybutton>=0.5.2,<0.6",
+    "pytest>=8.2.0,<9",
+    "scripttest~=1.3",
     "sphinx-autodoc-typehints>=2.2.2,<3",
+    "sphinx-copybutton>=0.5.2,<0.6",
+    "sphinx>=7.3.7,<8",
+    "vulture~=2.11",
 ]
 
 [build-system]

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/src/txt2ebook/__init__.py

@@ -18,7 +18,6 @@
 import argparse
 import logging
 import platform
-from typing import Optional
 import sys
 
 import langdetect
@@ -51,7 +50,9 @@ def setup_logger(config: argparse.Namespace) -> None:
     )
 
 
-def log_or_raise_on_warning(message: str, raise_on_warning: bool = False) -> None:
+def log_or_raise_on_warning(
+    message: str, raise_on_warning: bool = False
+) -> None:
     """Logs a warning message or raises an exception.
 
     Args:
@@ -87,7 +88,7 @@ def detect_and_expect_language(content: str, config_language: str) -> str:
     Returns:
         The configured language, or the detected language if none is
         configured.
-"""
+    """
     detect_language = langdetect.detect(content)
     config_language = config_language or detect_language
     logger.info("Config language: %s", config_language)

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/src/txt2ebook/cli.py

@@ -15,9 +15,9 @@
 
 """txt2ebook/tte is a cli tool to convert txt file to ebook format.
 
-  website: https://github.com/kianmeng/txt2ebook
-  changelog: https://github.com/kianmeng/txt2ebook/blob/master/CHANGELOG.md
-  issues: https://github.com/kianmeng/txt2ebook/issues
+website: https://github.com/kianmeng/txt2ebook
+changelog: https://github.com/kianmeng/txt2ebook/blob/master/CHANGELOG.md
+issues: https://github.com/kianmeng/txt2ebook/issues
 """
 
 import argparse
@@ -150,7 +150,7 @@ def main(args: Optional[Sequence[str]] = None):
             else:
                 logger.error(
                     "subcommand '%s' is missing its execution function.",
-                    parsed_args.command
+                    parsed_args.command,
                 )
                 parser.print_help(sys.stderr)
 

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/src/txt2ebook/formats/__init__.py

@@ -15,10 +15,7 @@
 
 """Packpage of different e-book formats."""
 
-import argparse
-from typing import Union
 
-import txt2ebook.models.book
 from txt2ebook.formats.epub import TEMPLATES as EPUB_TEMPLATES
 from txt2ebook.formats.epub import EpubWriter
 from txt2ebook.formats.gmi import GmiWriter

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/src/txt2ebook/helpers/__init__.py

@@ -17,9 +17,6 @@
 
 import logging
 import re
-import sys
-from importlib import import_module
-from typing import Any
 
 logger = logging.getLogger(__name__)
 
@@ -42,4 +39,4 @@ def lower_underscore(string: str) -> str:
         >>> lower_underscore("Hello\tWorld")
         'hello_world'
     """
-    return re.sub(r'\s+', '_', string.lower().strip())
+    return re.sub(r"\s+", "_", string.lower().strip())

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/src/txt2ebook/models/book.py

@@ -40,9 +40,7 @@ class Book:
     language: str = field(default="")
     cover: str = field(default="", repr=False)
     raw_content: str = field(default="", repr=False)
-    toc: List[Union[Volume, Chapter]] = field(
-        default_factory=list, repr=False
-    )
+    toc: List[Union[Volume, Chapter]] = field(default_factory=list, repr=False)
 
     def stats(self) -> Counter:
         """Returns the statistics count for the parsed tokens.
@@ -61,12 +59,14 @@ class Book:
         authors = ", ".join(self.authors)
         format_options = {
             1: f"{self.title}_{authors}",
-            2: f"{authors}_{self.title}"
+            2: f"{authors}_{self.title}",
         }
         try:
             return format_options[filename_format]
         except KeyError:
-            raise AttributeError(f"Invalid filename format: '{filename_format}'!")
+            raise AttributeError(
+                f"Invalid filename format: '{filename_format}'!"
+            )
 
     def debug(self, verbosity: int = 1) -> None:
         """Dump debug log of sections in self.toc."""

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/src/txt2ebook/parser.py

@@ -17,11 +17,10 @@
 
 import argparse
 import logging
-from dataclasses import dataclass, field
+from dataclasses import dataclass
 from importlib import import_module
 from typing import List, Tuple, Union
 
-import cjkwrap
 import regex as re
 
 from txt2ebook.models import Book, Chapter, Volume
@@ -88,7 +87,9 @@ class Parser:
         Returns:
             str: The formatted section header.
         """
-        if not getattr(self.config, "header_number", False) or self.config.language not in (
+        if not getattr(
+            self.config, "header_number", False
+        ) or self.config.language not in (
             "zh-cn",
             "zh-tw",
         ):

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/src/txt2ebook/subcommands/epub.py

@@ -19,10 +19,9 @@ import argparse
 import logging
 import sys
 
-from txt2ebook.subcommands.parse import run as parse_txt
-from txt2ebook.formats.epub import EpubWriter
 from txt2ebook.formats import EPUB_TEMPLATES
-
+from txt2ebook.formats.epub import EpubWriter
+from txt2ebook.subcommands.parse import run as parse_txt
 
 logger = logging.getLogger(__name__)
 
@@ -30,8 +29,9 @@ logger = logging.getLogger(__name__)
 def build_subparser(subparsers) -> None:
     """Build the subparser."""
     epub_parser = subparsers.add_parser(
-        "epub", help="generate ebook in EPUB format",
-        formatter_class=argparse.RawTextHelpFormatter
+        "epub",
+        help="generate ebook in EPUB format",
+        formatter_class=argparse.RawTextHelpFormatter,
     )
 
     epub_parser.set_defaults(func=run)

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/src/txt2ebook/subcommands/gmi.py

@@ -19,9 +19,8 @@ import argparse
 import logging
 import sys
 
-from txt2ebook.subcommands.parse import run as parse_txt
 from txt2ebook.formats.gmi import GmiWriter
-
+from txt2ebook.subcommands.parse import run as parse_txt
 
 logger = logging.getLogger(__name__)
 

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/src/txt2ebook/subcommands/md.py

@@ -19,9 +19,8 @@ import argparse
 import logging
 import sys
 
-from txt2ebook.subcommands.parse import run as parse_txt
 from txt2ebook.formats.md import MdWriter as MarkdownWriter
-
+from txt2ebook.subcommands.parse import run as parse_txt
 
 logger = logging.getLogger(__name__)
 

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/src/txt2ebook/subcommands/pdf.py

@@ -19,10 +19,9 @@ import argparse
 import logging
 import sys
 
-from txt2ebook.subcommands.parse import run as parse_txt
-from txt2ebook.formats.pdf import PdfWriter
 from txt2ebook.formats import PAGE_SIZES
-
+from txt2ebook.formats.pdf import PdfWriter
+from txt2ebook.subcommands.parse import run as parse_txt
 
 logger = logging.getLogger(__name__)
 

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/src/txt2ebook/subcommands/typ.py

@@ -19,10 +19,9 @@ import argparse
 import logging
 import sys
 
-from txt2ebook.subcommands.parse import run as parse_txt
-from txt2ebook.formats.typ import TypWriter
 from txt2ebook.formats import PAGE_SIZES
-
+from txt2ebook.formats.typ import TypWriter
+from txt2ebook.subcommands.parse import run as parse_txt
 
 logger = logging.getLogger(__name__)
 

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/src/txt2ebook/tokenizer.py

@@ -169,7 +169,6 @@ class Tokenizer:
 
         return metadata
 
-
     def _tokenize_content(self) -> None:
         # Determine the actual content part, after any metadata block
         metadata_block_re = (

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/tests/fixtures/sample.txt

@@ -8,6 +8,16 @@
 花间一壶酒，独酌无相亲。
 举杯邀明月，对影成三人。
 
+This is a paragraph with some halfwidth characters like 123, ABC, and symbols !@#$.
+
+This paragraph has
+multiple newlines
+
+
+between lines.
+
+This is a very long line that should be wrapped when a width is specified. It needs to be long enough to exceed the typical default width and force wrapping. Let's make it even longer to be sure. This is a very long line that should be wrapped when a width is specified. It needs to be long enough to exceed the typical default width and force wrapping. Let's make it even longer to be sure.
+
 第1章 月既不解饮
 
 我歌月徘徊，我舞影零乱。醒时同交欢，醉后各分散。永结无情游，相期邈云汉。

{txt2ebook-0.1.139 → txt2ebook-0.1.141}/tests/test_subcommand_epub.py

@@ -1,7 +1,6 @@
 # pylint: disable=C0114,C0116
 
 import pytest
-
 from ebooklib import epub
 
 

txt2ebook-0.1.141/tests/test_subcommand_massage.py

@@ -0,0 +1,115 @@
+# pylint: disable=C0114,C0116
+
+import pytest
+
+
+@pytest.mark.parametrize("option", ["-rl", "--regex-delete-line"])
+def test_delete_line_regex(tte, infile, option):
+    txtfile = infile("sample.txt")
+    tte("massage", txtfile, "-ow", option, "我歌月徘徊")
+
+    with open(txtfile, encoding="utf8") as file:
+        content = file.read()
+        assert "我歌月徘徊" not in content
+
+
+@pytest.mark.parametrize("option", ["-rr", "--regex-replace"])
+def test_single_replace_regex(tte, infile, option):
+    txtfile = infile("sample.txt")
+
+    tte("massage", txtfile, "-ow", option, "章", "章:")
+
+    with open(txtfile, encoding="utf8") as file:
+        content = file.read()
+        assert "第1章:" in content
+        assert "第2章:" in content
+        assert "第3章:" in content
+
+
+@pytest.mark.parametrize("option", ["-rd", "--regex-delete"])
+def test_single_delete_regex(tte, infile, option):
+    txtfile = infile("sample.txt")
+    tte("massage", txtfile, "-ow", option, "歌月", option, "我")
+
+    with open(txtfile, encoding="utf8") as file:
+        content = file.read()
+        assert "徘徊，舞影零乱。" in content
+
+
+@pytest.mark.parametrize("option", ["-fw", "--fullwidth"])
+def test_fullwidth(tte, infile, option):
+    txtfile = infile("sample.txt")
+    tte("massage", txtfile, "-ow", option)
+
+    with open(txtfile, encoding="utf8") as file:
+        content = file.read()
+        # Check for conversion of halfwidth characters
+        assert "１２３" in content
+        assert "ＡＢＣ" in content
+        assert "！＠＃＄" in content
+
+
+@pytest.mark.parametrize("option", ["-sn", "--single-newline"])
+def test_single_newline(tte, infile, option):
+    txtfile = infile("sample.txt")
+    tte("massage", txtfile, "-ow", option)
+
+    with open(txtfile, encoding="utf8") as file:
+        content = file.read()
+        # Check that multiple newlines are reduced to single newlines between paragraphs
+        assert "This paragraph has\n\nmultiple newlines" in content
+        assert "between lines.\n\nThis is a very long line" in content
+        # Ensure single newlines within a paragraph are preserved by wrapping logic
+        # (though single_newline runs before wrapping, the effect is tested here)
+        assert "花间一壶酒，独酌无相亲。\n\n举杯邀明月，对影成三人。" in content
+
+
+@pytest.mark.parametrize("option", ["-w", "--width"])
+def test_width(tte, infile, option):
+    txtfile = infile("sample.txt")
+    # Use a small width to force wrapping
+    tte("massage", txtfile, "-ow", option, "40")
+
+    with open(txtfile, encoding="utf8") as file:
+        content = file.read()
+        # Check that the long line is wrapped
+        long_line_wrapped = "This is a very long line that should be\nwrapped when a width is specified. It needs\nto be long enough to exceed the typical\ndefault width and force wrapping. Let's\nmake it even longer to be sure. This is a\nvery long line that should be wrapped when\na width is specified. It needs to be long\nenough to exceed the typical default width\nand force wrapping. Let's make it even\nlonger to be sure."
+        assert long_line_wrapped in content
+
+
+@pytest.mark.parametrize("option", ["-ps", "--paragraph_separator"])
+def test_paragraph_separator(tte, infile, option):
+    txtfile = infile("sample.txt")
+    separator = "<br>"
+    tte("massage", txtfile, "-ow", option, separator)
+
+    with open(txtfile, encoding="utf8") as file:
+        content = file.read()
+        # Check that the custom separator is used between paragraphs
+        assert "花间一壶酒，独酌无相亲。" + separator + "举杯邀明月，对影成三人。" in content
+        assert "between lines." + separator + "This is a very long line" in content
+
+
+def test_multiple_regex(tte, infile):
+    txtfile = infile("sample.txt")
+    # Apply multiple regex options
+    tte(
+        "massage",
+        txtfile,
+        "-ow",
+        "-rl",
+        "我歌月徘徊",  # Delete line
+        "-rr",
+        "章",
+        "章:",  # Replace
+        "-rd",
+        "无相亲",  # Delete word/phrase
+    )
+
+    with open(txtfile, encoding="utf8") as file:
+        content = file.read()
+        # Check all regex effects
+        assert "我歌月徘徊" not in content  # Line deleted
+        assert "第1章:" in content  # Replace applied
+        assert "独酌无相亲" not in content  # Word/phrase deleted
+        assert "花间一壶酒，独酌。" in content  # Check surrounding text after deletion