txt2ebook 0.1.158__tar.gz → 0.1.160__tar.gz

{txt2ebook-0.1.158/src/txt2ebook.egg-info → txt2ebook-0.1.160}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: txt2ebook
-Version: 0.1.158
+Version: 0.1.160
 Summary: CLI tool to convert txt file to ebook format
 Author-email: Kian-Meng Ang <kianmeng@cpan.org>
 License-Expression: AGPL-3.0-or-later

{txt2ebook-0.1.158 → txt2ebook-0.1.160}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "txt2ebook"
-version = "0.1.158"
+version = "0.1.160"
 description = "CLI tool to convert txt file to ebook format"
 authors = [{ name = "Kian-Meng Ang", email = "kianmeng@cpan.org" }]
 requires-python = "~=3.9"
@@ -89,6 +89,20 @@ build-backend = "setuptools.build_meta"
 # verify through: uv run ruff check --show-settings
 [tool.ruff]
 line-length = 79
+target-version = "py313"
+exclude = [
+    "docs/",
+    "docs/source/conf.py",
+]
+
+[tool.ruff.lint]
+extend-select = [
+    "E",
+    "W",
+]
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"
 
 [tool.setuptools.packages.find]
 where = ["src"]

{txt2ebook-0.1.158 → txt2ebook-0.1.160}/src/txt2ebook/__init__.py

@@ -15,6 +15,7 @@
 
 """Common shared functions."""
 
+from importlib import metadata
 import argparse
 import logging
 import platform
@@ -24,7 +25,7 @@ import langdetect
 
 logger = logging.getLogger(__name__)
 
-__version__ = "0.1.126"
+__version__ = metadata.version("txt2ebook")
 
 
 def setup_logger(config: argparse.Namespace) -> None:

{txt2ebook-0.1.158 → txt2ebook-0.1.160}/src/txt2ebook/formats/base.py

@@ -24,7 +24,6 @@ import shutil
 import subprocess
 import sys
 from abc import ABC, abstractmethod
-from datetime import datetime as dt
 from importlib import import_module
 from pathlib import Path
 
@@ -155,7 +154,9 @@ class BaseWriter(ABC):
         extension = self._get_file_extension_for_split()
         txt_filename = Path(self.config.input_file.name)
 
-        export_filename = self._get_metadata_filename_for_split(txt_filename, extension)
+        export_filename = self._get_metadata_filename_for_split(
+            txt_filename, extension
+        )
         export_filename.parent.mkdir(parents=True, exist_ok=True)
         logger.info("Creating %s", export_filename)
         with open(export_filename, "w", encoding="utf8") as file:
@@ -163,7 +164,9 @@ class BaseWriter(ABC):
 
         sc_seq = 1
         if self.config.with_toc:
-            export_filename = self._get_toc_filename_for_split(txt_filename, extension)
+            export_filename = self._get_toc_filename_for_split(
+                txt_filename, extension
+            )
             export_filename.parent.mkdir(parents=True, exist_ok=True)
             logger.info("Creating %s", export_filename)
             with open(export_filename, "w", encoding="utf8") as file:
@@ -178,8 +181,15 @@ class BaseWriter(ABC):
             if isinstance(section, Volume):
                 for chapter in section.chapters:
                     chapter_seq = str(ct_seq).rjust(2, "0")
-                    export_filename = self._get_volume_chapter_filename_for_split(
-                        txt_filename, section_seq, chapter_seq, section, chapter, extension
+                    export_filename = (
+                        self._get_volume_chapter_filename_for_split(
+                            txt_filename,
+                            section_seq,
+                            chapter_seq,
+                            section,
+                            chapter,
+                            extension,
+                        )
                     )
                     export_filename.parent.mkdir(parents=True, exist_ok=True)
                     logger.info("Creating %s", export_filename)
@@ -201,15 +211,16 @@ class BaseWriter(ABC):
 
             sc_seq = sc_seq + 1
 
-    @abstractmethod
-    def _get_metadata_filename_for_split(self, txt_filename: Path, extension: str) -> Path:
+    def _get_metadata_filename_for_split(
+        self, txt_filename: Path, extension: str
+    ) -> Path:
         raise NotImplementedError
 
-    @abstractmethod
-    def _get_toc_filename_for_split(self, txt_filename: Path, extension: str) -> Path:
+    def _get_toc_filename_for_split(
+        self, txt_filename: Path, extension: str
+    ) -> Path:
         raise NotImplementedError
 
-    @abstractmethod
     def _get_volume_chapter_filename_for_split(
         self,
         txt_filename: Path,
@@ -221,9 +232,12 @@ class BaseWriter(ABC):
     ) -> Path:
         raise NotImplementedError
 
-    @abstractmethod
     def _get_chapter_filename_for_split(
-        self, txt_filename: Path, section_seq: str, chapter: Chapter, extension: str
+        self,
+        txt_filename: Path,
+        section_seq: str,
+        chapter: Chapter,
+        extension: str,
     ) -> Path:
         raise NotImplementedError
 

{txt2ebook-0.1.158 → txt2ebook-0.1.160}/src/txt2ebook/formats/gmi.py

@@ -38,7 +38,9 @@ class GmiWriter(BaseWriter):
             output_filename.parent.mkdir(parents=True, exist_ok=True)
 
             with open(output_filename, "w", encoding="utf8") as file:
-                logger.info("Generate Gemini file: %s", output_filename.resolve())
+                logger.info(
+                    "Generate Gemini file: %s", output_filename.resolve()
+                )
                 file.write(self._to_gmi())
 
             if self.config.open:
@@ -58,7 +60,9 @@ class GmiWriter(BaseWriter):
     def _get_file_extension_for_split(self) -> str:
         return ".gmi"
 
-    def _get_metadata_filename_for_split(self, txt_filename: Path, extension: str) -> Path:
+    def _get_metadata_filename_for_split(
+        self, txt_filename: Path, extension: str
+    ) -> Path:
         return Path(
             txt_filename.resolve().parent.joinpath(
                 self.config.output_folder,
@@ -68,7 +72,9 @@ class GmiWriter(BaseWriter):
             )
         )
 
-    def _get_toc_filename_for_split(self, txt_filename: Path, extension: str) -> Path:
+    def _get_toc_filename_for_split(
+        self, txt_filename: Path, extension: str
+    ) -> Path:
         return Path(
             txt_filename.resolve().parent.joinpath(
                 self.config.output_folder,
@@ -104,13 +110,19 @@ class GmiWriter(BaseWriter):
         )
 
     def _get_chapter_filename_for_split(
-        self, txt_filename: Path, section_seq: str, chapter: Chapter, extension: str
+        self,
+        txt_filename: Path,
+        section_seq: str,
+        chapter: Chapter,
+        extension: str,
     ) -> Path:
         return Path(
             txt_filename.resolve().parent.joinpath(
                 self.config.output_folder,
                 lower_underscore(
-                    (f"{section_seq}_{txt_filename.stem}_{chapter.title}{extension}")
+                    (
+                        f"{section_seq}_{txt_filename.stem}_{chapter.title}{extension}"
+                    )
                 ),
             )
         )

{txt2ebook-0.1.158 → txt2ebook-0.1.160}/src/txt2ebook/formats/md.py

@@ -17,7 +17,6 @@
 
 import logging
 from pathlib import Path
-from pathlib import Path
 
 from txt2ebook.formats.base import BaseWriter
 from txt2ebook.helpers import lower_underscore
@@ -38,7 +37,9 @@ class MdWriter(BaseWriter):
             output_filename.parent.mkdir(parents=True, exist_ok=True)
 
             with open(output_filename, "w", encoding="utf8") as file:
-                logger.info("Generate Markdown file: %s", output_filename.resolve())
+                logger.info(
+                    "Generate Markdown file: %s", output_filename.resolve()
+                )
                 file.write(self._to_md())
 
             if self.config.open:
@@ -58,7 +59,9 @@ class MdWriter(BaseWriter):
     def _get_file_extension_for_split(self) -> str:
         return ".md"
 
-    def _get_metadata_filename_for_split(self, txt_filename: Path, extension: str) -> Path:
+    def _get_metadata_filename_for_split(
+        self, txt_filename: Path, extension: str
+    ) -> Path:
         return Path(
             txt_filename.resolve().parent.joinpath(
                 self.config.output_folder,
@@ -68,7 +71,9 @@ class MdWriter(BaseWriter):
             )
         )
 
-    def _get_toc_filename_for_split(self, txt_filename: Path, extension: str) -> Path:
+    def _get_toc_filename_for_split(
+        self, txt_filename: Path, extension: str
+    ) -> Path:
         return Path(
             txt_filename.resolve().parent.joinpath(
                 self.config.output_folder,
@@ -104,13 +109,19 @@ class MdWriter(BaseWriter):
         )
 
     def _get_chapter_filename_for_split(
-        self, txt_filename: Path, section_seq: str, chapter: Chapter, extension: str
+        self,
+        txt_filename: Path,
+        section_seq: str,
+        chapter: Chapter,
+        extension: str,
     ) -> Path:
         return Path(
             txt_filename.resolve().parent.joinpath(
                 self.config.output_folder,
                 lower_underscore(
-                    (f"{section_seq}_{txt_filename.stem}_{chapter.title}{extension}")
+                    (
+                        f"{section_seq}_{txt_filename.stem}_{chapter.title}{extension}"
+                    )
                 ),
             )
         )

{txt2ebook-0.1.158 → txt2ebook-0.1.160}/src/txt2ebook/formats/txt.py

@@ -54,11 +54,15 @@ class TxtWriter(BaseWriter):
                     .parent.joinpath(
                         lower_underscore(
                             Path(self.config.input_file.name).stem
-                            + "_" + ymd_hms + ".txt"
+                            + "_"
+                            + ymd_hms
+                            + ".txt"
                         )
                     )
                 )
-                logger.info("Backup source text file: %s", backup_filename.resolve())
+                logger.info(
+                    "Backup source text file: %s", backup_filename.resolve()
+                )
                 shutil.copyfile(output_filename, backup_filename)
 
             with open(output_filename, "w", encoding="utf8") as file:
@@ -68,27 +72,23 @@ class TxtWriter(BaseWriter):
             if self.config.open:
                 self._open_file(output_filename)
 
-    
-
-    
-
-    def _get_metadata_filename_for_split(self, txt_filename: Path, extension: str) -> Path:
+    def _get_metadata_filename_for_split(
+        self, txt_filename: Path, extension: str
+    ) -> Path:
         return Path(
             txt_filename.resolve().parent.joinpath(
                 self.config.output_folder,
-                lower_underscore(
-                    f"00_{txt_filename.stem}_" + self._("metadata") + extension
-                ),
+                f"00_{txt_filename.stem}_" + self._("metadata") + extension,
             )
         )
 
-    def _get_toc_filename_for_split(self, txt_filename: Path, extension: str) -> Path:
+    def _get_toc_filename_for_split(
+        self, txt_filename: Path, extension: str
+    ) -> Path:
         return Path(
             txt_filename.resolve().parent.joinpath(
                 self.config.output_folder,
-                lower_underscore(
-                    f"01_{txt_filename.stem}_" + self._("toc") + extension
-                ),
+                f"01_{txt_filename.stem}_" + self._("toc") + extension,
             )
         )
 
@@ -104,36 +104,86 @@ class TxtWriter(BaseWriter):
         return Path(
             txt_filename.resolve().parent.joinpath(
                 self.config.output_folder,
-                lower_underscore(
-                    (
-                        f"{section_seq}"
-                        f"_{chapter_seq}"
-                        f"_{txt_filename.stem}"
-                        f"_{volume.title}"
-                        f"_{chapter.title}"
-                        f"{extension}"
-                    )
+                (
+                    f"{section_seq}"
+                    f"_{chapter_seq}"
+                    f"_{txt_filename.stem}"
+                    f"_{volume.title}"
+                    f"_{chapter.title}"
+                    f"{extension}"
                 ),
             )
         )
 
     def _get_chapter_filename_for_split(
-        self, txt_filename: Path, section_seq: str, chapter: Chapter, extension: str
+        self,
+        txt_filename: Path,
+        section_seq: str,
+        chapter: Chapter,
+        extension: str,
     ) -> Path:
         return Path(
             txt_filename.resolve().parent.joinpath(
                 self.config.output_folder,
-                lower_underscore(
-                    (f"{section_seq}_{txt_filename.stem}_{chapter.title}{extension}")
+                (
+                    f"{section_seq}_{txt_filename.stem}_{chapter.title}{extension}"
                 ),
             )
         )
 
+    def _export_multiple_files(self) -> None:
+        """Export multiple files based on volume and chapter."""
+        txt_filename = Path(self.config.input_file.name)
+        txt_filename.parent.joinpath(self.config.output_folder).mkdir(
+            parents=True, exist_ok=True
+        )
+
+        # 1. Write metadata file
+        metadata_filename = self._get_metadata_filename_for_split(
+            txt_filename, ".txt"
+        )
+        with open(metadata_filename, "w", encoding="utf8") as file:
+            logger.info("Creating %s", metadata_filename.resolve())
+            file.write(self._to_metadata_txt())
+
+        # 2. Write volume/chapter files
+        section_seq = 0
+        chapter_seq = 0
+        for section in self.book.toc:
+            if isinstance(section, Volume):
+                section_seq += 1
+                chapter_seq = 0
+                for chapter in section.chapters:
+                    chapter_seq += 1
+                    output_filename = self._get_volume_chapter_filename_for_split(
+                        txt_filename,
+                        str(section_seq).rjust(2, "0"),
+                        str(chapter_seq).rjust(2, "0"),
+                        section,
+                        chapter,
+                        ".txt",
+                    )
+                    with open(output_filename, "w", encoding="utf8") as file:
+                        logger.info("Creating %s", output_filename.resolve())
+                        file.write(self._to_volume_chapter_txt(section, chapter))
+            elif isinstance(section, Chapter):
+                section_seq += 1
+                output_filename = self._get_chapter_filename_for_split(
+                    txt_filename,
+                    str(section_seq).rjust(2, "0"),
+                    section,
+                    ".txt",
+                )
+                with open(output_filename, "w", encoding="utf8") as file:
+                    logger.info("Creating %s", output_filename.resolve())
+                    file.write(self._to_chapter_txt(section))
+
+        if self.config.open:
+            self._open_file(metadata_filename)
+
     def _to_txt(self) -> str:
         toc = self._to_toc("-") if self.config.with_toc else ""
         return self._to_metadata_txt() + toc + self._to_body_txt()
-
-    def _to_body_txt(self) -> str:
         content = []
         for section in self.book.toc:
             if isinstance(section, Volume):

{txt2ebook-0.1.158 → txt2ebook-0.1.160}/src/txt2ebook/formats/typ.py

@@ -235,10 +235,14 @@ class TypWriter(BaseWriter):
         """
         )
 
-    def _get_metadata_filename_for_split(self, txt_filename: Path, extension: str) -> Path:
+    def _get_metadata_filename_for_split(
+        self, txt_filename: Path, extension: str
+    ) -> Path:
         return Path(self._output_folder(), "metadata").with_suffix(extension)
 
-    def _get_toc_filename_for_split(self, txt_filename: Path, extension: str) -> Path:
+    def _get_toc_filename_for_split(
+        self, txt_filename: Path, extension: str
+    ) -> Path:
         return Path(self._output_folder(), "toc").with_suffix(extension)
 
     def _get_volume_chapter_filename_for_split(
@@ -254,7 +258,11 @@ class TypWriter(BaseWriter):
         return Path(self._output_folder(), filename).with_suffix(extension)
 
     def _get_chapter_filename_for_split(
-        self, txt_filename: Path, section_seq: str, chapter: Chapter, extension: str
+        self,
+        txt_filename: Path,
+        section_seq: str,
+        chapter: Chapter,
+        extension: str,
     ) -> Path:
         filename = f"{section_seq}-{lower_underscore(chapter.title)}"
         return Path(self._output_folder(), filename).with_suffix(extension)

{txt2ebook-0.1.158 → txt2ebook-0.1.160}/src/txt2ebook/subcommands/epub.py

@@ -38,10 +38,10 @@ def build_subparser(subparsers) -> None:
 
     epub_parser.add_argument(
         "input_file",
-        nargs="*",
+        nargs=1,
         type=argparse.FileType("rb"),
-        help="source text filenames (can use glob patterns)",
-        metavar="TXT_FILENAMES",
+        help="source text filename",
+        metavar="TXT_FILENAME",
     )
 
     epub_parser.add_argument(
@@ -125,12 +125,12 @@ def run(args: argparse.Namespace) -> None:
     """
     input_sources = []
 
-    if not sys.stdin.isatty():
-        # piped input, use stdin as the single input source
-        input_sources.append(sys.stdin)
-    elif args.input_file:
-        # multiple file(s)
+    if args.input_file:
+        # File path(s) were explicitly provided on the command line
         input_sources.extend(args.input_file)
+    elif not sys.stdin.isatty():
+        # No file path provided, check for piped input
+        input_sources.append(sys.stdin)
     else:
         logger.error("No input files provided.")
         sys.exit(1)
@@ -147,6 +147,10 @@ def run(args: argparse.Namespace) -> None:
         current_file_args = argparse.Namespace(**vars(args))
         current_file_args.input_file = current_input_stream
 
+        logger.debug(
+            "Create separate volume page: %s", current_file_args.volume_page
+        )
+
         # if an explicit output_file was provided, it must apply to the first
         # input
         if i > 0 and args.output_file:

{txt2ebook-0.1.158 → txt2ebook-0.1.160}/src/txt2ebook/subcommands/massage.py

@@ -28,7 +28,9 @@ from bs4 import UnicodeDammit
 
 from txt2ebook import detect_and_expect_language
 from txt2ebook.exceptions import EmptyFileError
+from txt2ebook.formats.txt import TxtWriter
 from txt2ebook.models.book import Book
+from txt2ebook.parser import Parser
 from txt2ebook.zh_utils import zh_halfwidth_to_fullwidth, zh_words_to_numbers
 
 logger = logging.getLogger(__name__)
@@ -216,26 +218,27 @@ def run(args: argparse.Namespace) -> None:
         None
     """
     massaged_txt = massage_txt(args)
-    if args.overwrite:
-        _overwrite_file(args, massaged_txt)
-    else:
-        _new_file(args, massaged_txt)
 
-    # args.language = detect_and_expect_language(massaged_txt, args.language)
-    # config_lang = args.language.replace("-", "_")
-    # langconf = import_module(f"txt2ebook.languages.{config_lang}")
-    # args.with_toc = False
-    # parser = Parser(massaged_txt, args, langconf)
-    # book = parser.parse()
+    if args.split_volume_and_chapter:
+        args.language = detect_and_expect_language(massaged_txt, args.language)
+        config_lang = args.language.replace("-", "_")
+        langconf = import_module(f"txt2ebook.languages.{config_lang}")
+        args.with_toc = False
+        parser = Parser(massaged_txt, args, langconf)
+        book = parser.parse()
 
-    # if args.debug:
-    #     book.debug(args.verbose)
+        if args.debug:
+            book.debug(args.verbose)
 
-    # if args.header_number:
-    #     book = header_number(args, book)
+        if args.header_number:
+            book = header_number(args, book)
 
-    # writer = TxtWriter(book, args)
-    # writer.write()
+        writer = TxtWriter(book, args)
+        writer.write()
+    elif args.overwrite:
+        _overwrite_file(args, massaged_txt)
+    else:
+        _new_file(args, massaged_txt)
 
 
 def _overwrite_file(args, massaged_txt) -> None:
@@ -356,11 +359,13 @@ def massage_txt(args: argparse.Namespace) -> str:
     if args.re_delete_line:
         body = do_delete_line_regex(args, body)
 
-    if args.single_newline:
-        body = do_single_newline(args, body)
-
     if args.width:
         body = do_wrapping(args, body)
+    elif args.single_newline:
+        body = do_single_newline(args, body)
+    else:
+        # Apply paragraph separation and line unwrapping by default
+        body = _unwrap_content(args, body)
 
     return f"{metadata}{body}"
 
@@ -376,6 +381,7 @@ def to_unix_newline(content: str) -> str:
     """
     return content.replace("\r\n", "\n").replace("\r", "\n")
 
+
 def do_reindent_paragraph(args, content: str) -> str:
     """Reindent each paragraph.
 
@@ -385,16 +391,16 @@ def do_reindent_paragraph(args, content: str) -> str:
     Returns:
         str: The formatted book content.
     """
-    paragraphs = re.split(r'\n\s*\n+', content)
+    paragraphs = re.split(r"\n\s*\n+", content)
     reindented_paragraphs = []
     for paragraph in paragraphs:
-        lines = paragraph.split('\n')
+        lines = paragraph.split("\n")
         reindented_lines = []
         for line in lines:
             stripped_line = line.strip()
             reindented_lines.append(stripped_line)
 
-        reindented_paragraph = '\n'.join(reindented_lines)
+        reindented_paragraph = "\n".join(reindented_lines)
         reindented_paragraph = "　　" + reindented_paragraph
         reindented_paragraphs.append(reindented_paragraph)
 
@@ -542,7 +548,7 @@ def _unwrap_content(args: argparse.Namespace, content: str) -> str:
     Returns:
         str: The formatted book content.
     """
-    paragraphs = content.split(args.paragraph_separator)
+    paragraphs = re.split(r"\n\s*\n+", content)
     processed_paragraphs = []
     for paragraph in paragraphs:
         single_line_paragraph = " ".join(paragraph.splitlines())

{txt2ebook-0.1.158 → txt2ebook-0.1.160/src/txt2ebook.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: txt2ebook
-Version: 0.1.158
+Version: 0.1.160
 Summary: CLI tool to convert txt file to ebook format
 Author-email: Kian-Meng Ang <kianmeng@cpan.org>
 License-Expression: AGPL-3.0-or-later

{txt2ebook-0.1.158 → txt2ebook-0.1.160}/src/txt2ebook.egg-info/SOURCES.txt

@@ -44,18 +44,6 @@ src/txt2ebook/subcommands/parse.py
 src/txt2ebook/subcommands/pdf.py
 src/txt2ebook/subcommands/tex.py
 src/txt2ebook/subcommands/typ.py
-tests/test_header_number_flag.py
-tests/test_input_file_arg.py
-tests/test_language_option.py
-tests/test_output_file_arg.py
-tests/test_overwrite_flag.py
 tests/test_parser.py
-tests/test_purge_flag.py
-tests/test_quiet_flag.py
-tests/test_sort_volume_and_chapter_flag.py
-tests/test_split_volume_and_chapter_flag.py
-tests/test_test_parsing_flag.py
 tests/test_tokenizer.py
-tests/test_txt2ebook.py
-tests/test_verbose_flag.py
-tests/test_volume_page_flag.py
+tests/test_txt2ebook.py

{txt2ebook-0.1.158 → txt2ebook-0.1.160}/tests/test_parser.py

@@ -15,7 +15,6 @@
 import argparse
 import pytest
 from importlib import import_module
-from argparse import Namespace
 
 from txt2ebook.parser import Parser
 
@@ -67,7 +66,7 @@ def test_parsing_two_newlines_as_paragraph_separator(config):
 
 剑号巨阙，珠称夜光，果珍李柰，菜重芥姜。(paragraph 1)
 """
-    langconf = import_module(f"txt2ebook.languages.en")
+    langconf = import_module("txt2ebook.languages.en")
     parser = Parser(content, config, langconf)
     [chapter1, chapter2] = parser.parse().toc
     assert len(chapter1.paragraphs) == 2
@@ -89,7 +88,7 @@ def test_parsing_one_newline_as_paragraph_separator(config):
 剑号巨阙，珠称夜光，果珍李柰，菜重芥姜。(paragraph 1)
 """
     config.paragraph_separator = "\n"
-    langconf = import_module(f"txt2ebook.languages.en")
+    langconf = import_module("txt2ebook.languages.en")
     parser = Parser(content, config, langconf)
     book = parser.parse()
     [chapter1, chapter2] = book.toc