txt2ebook 0.1.160__py3-none-any.whl → 0.1.162__py3-none-any.whl

txt2ebook/cli.py

@@ -23,7 +23,7 @@ issues: https://github.com/kianmeng/txt2ebook/issues
 import argparse
 import logging
 import sys
-from typing import Optional, Sequence
+from typing import Sequence
 
 import txt2ebook.subcommands
 from txt2ebook import __version__, setup_logger
@@ -71,6 +71,15 @@ def build_parser() -> argparse.ArgumentParser:
         ),
     )
 
+    parser.add_argument(
+        "-y",
+        "--yes",
+        default=False,
+        action="store_true",
+        dest="yes",
+        help="assume yes to all prompts (default: '%(default)s')",
+    )
+
     parser.add_argument(
         "-l",
         "--language",
@@ -134,7 +143,7 @@ def build_parser() -> argparse.ArgumentParser:
     return parser
 
 
-def main(args: Optional[Sequence[str]] = None):
+def main(args: Sequence[str] | None = None):
     """Set the main entrypoint of the CLI script."""
     args = args or sys.argv[1:]
 

txt2ebook/exceptions.py

@@ -16,5 +16,9 @@
 """List of all exceptions used for this application."""
 
 
+class InputError(Exception):
+    """Raised when the input arguments are invalid."""
+
+
 class EmptyFileError(Exception):
     """Raised when the input file has no content."""

txt2ebook/formats/base.py

@@ -24,8 +24,8 @@ import shutil
 import subprocess
 import sys
 from abc import ABC, abstractmethod
-from importlib import import_module
 from pathlib import Path
+from types import ModuleType
 
 from txt2ebook.helpers import lower_underscore
 from txt2ebook.models import Book, Chapter, Volume
@@ -36,22 +36,23 @@ logger = logging.getLogger(__name__)
 class BaseWriter(ABC):
     """Base class for writing to ebook format."""
 
-    def __init__(self, book: Book, opts: argparse.Namespace) -> None:
+    def __init__(
+        self, book: Book, opts: argparse.Namespace, langconf: ModuleType
+    ) -> None:
         """Create a Writer module.
 
         Args:
             book(Book): The book model which contains metadata and table of
             contents of volumes and chapters.
             opts(argparse.Namespace): The configs from the command-line.
+            langconf(ModuleType): The language configuration module.
 
         Returns:
             None
         """
         self.book = book
         self.config = opts
-
-        config_lang = self.config.language.replace("-", "_")
-        self.langconf = import_module(f"txt2ebook.languages.{config_lang}")
+        self.langconf = langconf
 
         if not self.config.output_file:
             self._refresh_output_folder()
@@ -84,7 +85,8 @@ class BaseWriter(ABC):
                 shutil.rmtree(cwd)
             else:
                 answer = input(
-                    f"Are you sure to purge output folder: {cwd.absolute()}? [y/N] "
+                    f"Are you sure to purge output folder: {cwd.absolute()}? "
+                    "[y/N] "
                 )
                 if answer.lower() == "y":
                     logger.debug("Purge output folder: %s", cwd.absolute())
@@ -148,18 +150,18 @@ class BaseWriter(ABC):
     def _get_file_extension_for_split(self) -> str:
         raise NotImplementedError
 
-    def _export_multiple_files(self) -> None:
+    def _export_multiple_files(self) -> Path:
         logger.info("Split multiple files")
 
         extension = self._get_file_extension_for_split()
         txt_filename = Path(self.config.input_file.name)
 
-        export_filename = self._get_metadata_filename_for_split(
+        metadata_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:
+        metadata_filename.parent.mkdir(parents=True, exist_ok=True)
+        logger.info("Creating %s", metadata_filename)
+        with open(metadata_filename, "w", encoding="utf8") as file:
             file.write(self._to_metadata_txt())
 
         sc_seq = 1
@@ -211,6 +213,8 @@ class BaseWriter(ABC):
 
             sc_seq = sc_seq + 1
 
+        return metadata_filename
+
     def _get_metadata_filename_for_split(
         self, txt_filename: Path, extension: str
     ) -> Path:

txt2ebook/formats/epub.py

@@ -19,7 +19,7 @@ import logging
 import uuid
 from importlib.resources import contents, read_text
 from pathlib import Path
-from typing import Optional
+
 
 from ebooklib import epub
 
@@ -181,7 +181,7 @@ class EpubWriter(BaseWriter):
         return epub_html
 
     def _build_chapter(
-        self, chapter: Chapter, volume: Optional[Volume] = None
+        self, chapter: Chapter, volume: Volume | None = None
     ) -> epub.EpubHtml:
         """Generate the whole chapter to HTML."""
         if volume:

txt2ebook/formats/txt.py

@@ -39,7 +39,9 @@ class TxtWriter(BaseWriter):
         if self.config.input_file.name == "<stdin>":
             logger.info("Skip backup source text file as content from stdin")
         elif self.config.split_volume_and_chapter:
-            self._export_multiple_files()
+            metadata_filename = self._export_multiple_files()
+            if self.config.open:
+                self._open_file(metadata_filename)
         else:
             output_filename = self._output_filename(".txt")
             output_filename.parent.mkdir(parents=True, exist_ok=True)
@@ -72,114 +74,19 @@ 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:
-        return Path(
-            txt_filename.resolve().parent.joinpath(
-                self.config.output_folder,
-                f"00_{txt_filename.stem}_" + self._("metadata") + extension,
-            )
-        )
-
-    def _get_toc_filename_for_split(
-        self, txt_filename: Path, extension: str
-    ) -> Path:
-        return Path(
-            txt_filename.resolve().parent.joinpath(
-                self.config.output_folder,
-                f"01_{txt_filename.stem}_" + self._("toc") + extension,
-            )
-        )
+    def _get_toc_content_for_split(self) -> str:
+        return self._to_toc("-")
 
-    def _get_volume_chapter_filename_for_split(
-        self,
-        txt_filename: Path,
-        section_seq: str,
-        chapter_seq: str,
-        volume: Volume,
-        chapter: Chapter,
-        extension: str,
-    ) -> Path:
-        return Path(
-            txt_filename.resolve().parent.joinpath(
-                self.config.output_folder,
-                (
-                    f"{section_seq}"
-                    f"_{chapter_seq}"
-                    f"_{txt_filename.stem}"
-                    f"_{volume.title}"
-                    f"_{chapter.title}"
-                    f"{extension}"
-                ),
-            )
-        )
+    def _get_volume_chapter_content_for_split(
+        self, volume: Volume, chapter: Chapter
+    ) -> str:
+        return self._to_volume_chapter_txt(volume, chapter)
 
-    def _get_chapter_filename_for_split(
-        self,
-        txt_filename: Path,
-        section_seq: str,
-        chapter: Chapter,
-        extension: str,
-    ) -> Path:
-        return Path(
-            txt_filename.resolve().parent.joinpath(
-                self.config.output_folder,
-                (
-                    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))
+    def _get_chapter_content_for_split(self, chapter: Chapter) -> str:
+        return self._to_chapter_txt(chapter)
 
-        if self.config.open:
-            self._open_file(metadata_filename)
+    def _get_file_extension_for_split(self) -> str:
+        return ".txt"
 
     def _to_txt(self) -> str:
         toc = self._to_toc("-") if self.config.with_toc else ""

txt2ebook/formats/typ.py

@@ -140,7 +140,8 @@ class TypWriter(BaseWriter):
             f"""
             #set page(paper: "{self._get_pagesize()}", numbering: none)
             #align(center + horizon, text(17pt)[{self.book.title}])
-            #align(center + horizon, text(17pt)[{", ".join(self.book.authors)}])
+            #align(center + horizon, text(17pt)[
+                {", ".join(self.book.authors)}])
             #pagebreak()
 
         """

txt2ebook/helpers/__init__.py

@@ -22,7 +22,8 @@ logger = logging.getLogger(__name__)
 
 
 def lower_underscore(string: str) -> str:
-    """Convert a string to lower case and replace multiple spaces to single underscore.
+    """Convert a string to lower case and replace multiple spaces to single
+    underscore.
 
     Args:
         string (str): A string.

txt2ebook/models/book.py

@@ -18,7 +18,7 @@
 import logging
 from collections import Counter
 from dataclasses import dataclass, field
-from typing import List, Union
+from typing import List
 
 from txt2ebook.models.chapter import Chapter
 from txt2ebook.models.volume import Volume
@@ -38,7 +38,7 @@ 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[Volume | Chapter] = field(default_factory=list, repr=False)
 
     def stats(self) -> Counter:
         """Returns the statistics count for the parsed tokens.

txt2ebook/parser.py

@@ -17,14 +17,15 @@
 
 import argparse
 import logging
+from collections import Counter
 from dataclasses import dataclass
 from types import ModuleType
-from typing import List, Tuple, Union
+from typing import List, Tuple
 
 import regex as re
 
 from txt2ebook.models import Book, Chapter, Volume
-from txt2ebook.tokenizer import Tokenizer
+from txt2ebook.tokenizer import Token, Tokenizer
 from txt2ebook.zh_utils import zh_halfwidth_to_fullwidth, zh_words_to_numbers
 
 logger = logging.getLogger(__name__)
@@ -55,7 +56,7 @@ class Parser:
         Returns:
           txt2ebook.models.Book: The Book model.
         """
-        tokenizer = Tokenizer(self.raw_content, self.config)
+        tokenizer = Tokenizer(self.raw_content, self.config, self.langconf)
 
         (book_title, authors, translators, tags, index, toc) = (
             self.parse_tokens(tokenizer)
@@ -79,6 +80,28 @@ class Parser:
 
         return book
 
+    def _pad_header_number(self, words: str, length: int) -> str:
+        """Left pad the section number if found as halfwidth or fullwidth
+        integer.
+        """
+        # left pad the section number if found as halfwidth integer
+        match = re.match(rf"第([{self.langconf.HALFWIDTH_NUMS}]*)", words)
+        if match and match.group(1) != "":
+            header_nums = match.group(1)
+            return words.replace(
+                header_nums, str(header_nums).rjust(length, "0")
+            )
+
+        # left pad the section number if found as fullwidth integer
+        match = re.match(rf"第([{self.langconf.FULLWIDTH_NUMS}]*)", words)
+        if match and match.group(1) != "":
+            header_nums = match.group(1)
+            return words.replace(
+                header_nums, str(header_nums).rjust(length, "０")
+            )
+
+        return words
+
     def words_to_nums(self, words: str, length: int) -> str:
         """Convert header from words to numbers.
 
@@ -99,22 +122,13 @@ class Parser:
         ):
             return words
 
-        # left pad the section number if found as halfwidth integer
-        match = re.match(rf"第([{self.langconf.HALFWIDTH_NUMS}]*)", words)
-        if match and match.group(1) != "":
-            header_nums = match.group(1)
-            return words.replace(
-                header_nums, str(header_nums).rjust(length, "0")
-            )
-
-        # left pad the section number if found as fullwidth integer
-        match = re.match(rf"第([{self.langconf.FULLWIDTH_NUMS}]*)", words)
-        if match and match.group(1) != "":
-            header_nums = match.group(1)
-            return words.replace(
-                header_nums, str(header_nums).rjust(length, "０")
-            )
+        # Check if the header is already a number and pad it
+        padded_words = self._pad_header_number(words, length)
+        if padded_words != words:
+            return padded_words
 
+        # Convert words to numbers and then apply fullwidth conversion if
+        # configured
         replaced_words = zh_words_to_numbers(words, length=length)
 
         if hasattr(self.config, "fullwidth") and self.config.fullwidth:
@@ -127,14 +141,102 @@ class Parser:
         )
         return replaced_words
 
+    def _process_metadata_token(self, token: Token, book_data: dict) -> None:
+        """Process metadata tokens (TITLE, AUTHOR, TAG, INDEX, TRANSLATOR)."""
+        if token.type == "TITLE":
+            book_data["book_title"] = token.value
+        elif token.type == "AUTHOR":
+            book_data["authors"].append(token.value)
+        elif token.type == "TAG":
+            book_data["tags"].append(token.value)
+        elif token.type == "INDEX":
+            book_data["index"] = token.value.split(" ")
+        elif token.type == "TRANSLATOR":
+            book_data["translators"].append(token.value)
+
+    def _process_volume_chapter_token(
+        self,
+        token: Token,
+        toc: List[Volume | Chapter],
+        stats: Counter,
+        current_volume: Volume,
+        current_chapter: Chapter,
+    ) -> Tuple[Volume, Chapter]:
+        """Process VOLUME_CHAPTER token and update current volume/chapter."""
+        [volume, chapter] = token.value
+
+        volume_title = self.words_to_nums(volume.value, 2)
+        if current_volume.title != volume_title:
+            current_volume = Volume(title=volume_title)
+            toc.append(current_volume)
+
+        chapter_title = self.words_to_nums(
+            chapter.value, len(str(stats.get("VOLUME_CHAPTER")))
+        )
+        if current_chapter.title != chapter_title:
+            current_chapter = Chapter(title=chapter_title)
+            if isinstance(toc[-1], Volume):
+                toc[-1].add_chapter(current_chapter)
+
+        return current_volume, current_chapter
+
+    def _process_volume_token(
+        self,
+        token: Token,
+        toc: List[Volume | Chapter],
+        stats: Counter,
+        current_volume: Volume,
+    ) -> Volume:
+        """Process VOLUME token and update current volume."""
+        volume_title = self.words_to_nums(
+            token.value, len(str(stats.get("VOLUME")))
+        )
+        if current_volume.title != volume_title:
+            current_volume = Volume(title=volume_title)
+            toc.append(current_volume)
+        return current_volume
+
+    def _process_chapter_token(
+        self,
+        token: Token,
+        toc: List[Volume | Chapter],
+        stats: Counter,
+        current_chapter: Chapter,
+    ) -> Chapter:
+        """Process CHAPTER token and update current chapter."""
+        chapter_title = self.words_to_nums(
+            token.value, len(str(stats.get("CHAPTER")))
+        )
+        if current_chapter.title != chapter_title:
+            current_chapter = Chapter(title=chapter_title)
+
+            if toc and isinstance(toc[-1], Volume):
+                toc[-1].add_chapter(current_chapter)
+            else:
+                toc.append(current_chapter)
+        return current_chapter
+
+    def _process_paragraph_token(
+        self, token: Token, toc: List[Volume | Chapter]
+    ) -> None:
+        """Process PARAGRAPH token and add it to the current chapter."""
+        if toc:
+            if isinstance(toc[-1], Volume):
+                toc[-1].chapters[-1].add_paragraph(token.value)
+
+            if isinstance(toc[-1], Chapter):
+                toc[-1].add_paragraph(token.value)
+
     def parse_tokens(self, tokenizer: Tokenizer) -> Tuple:
         """Parse the tokens and organize into book structure."""
-        toc: List[Union[Volume, Chapter]] = []
-        book_title = ""
-        authors = []
-        tags = []
-        index = []
-        translators = []
+        toc: List[Volume | Chapter] = []
+        book_data = {
+            "book_title": "",
+            "authors": [],
+            "tags": [],
+            "index": [],
+            "translators": [],
+        }
         current_volume = Volume("")
         current_chapter = Chapter("")
 
@@ -162,80 +264,48 @@ class Parser:
             ):
                 logger.debug(repr(token))
 
-            if token.type == "TITLE":
-                book_title = token.value
-
-            if token.type == "AUTHOR":
-                authors.append(token.value)
-
-            if token.type == "TAG":
-                tags.append(token.value)
-
-            if token.type == "INDEX":
-                index = token.value.split(" ")
-
-            if token.type == "TRANSLATOR":
-                translators.append(token.value)
-
-            if token.type == "VOLUME_CHAPTER":
-                [volume, chapter] = token.value
-
-                volume_title = self.words_to_nums(volume.value, 2)
-                if current_volume.title != volume_title:
-                    current_volume = Volume(title=volume_title)
-                    toc.append(current_volume)
-
-                chapter_title = self.words_to_nums(
-                    chapter.value, len(str(stats.get("VOLUME_CHAPTER")))
+            if token.type in [
+                "TITLE",
+                "AUTHOR",
+                "TAG",
+                "INDEX",
+                "TRANSLATOR",
+            ]:
+                self._process_metadata_token(token, book_data)
+            elif token.type == "VOLUME_CHAPTER":
+                (current_volume, current_chapter) = (
+                    self._process_volume_chapter_token(
+                        token, toc, stats, current_volume, current_chapter
+                    )
                 )
-                if current_chapter.title != chapter_title:
-                    current_chapter = Chapter(title=chapter_title)
-                    if isinstance(toc[-1], Volume):
-                        toc[-1].add_chapter(current_chapter)
-
-            if token.type == "VOLUME":
-                volume_title = self.words_to_nums(
-                    token.value, len(str(stats.get("VOLUME")))
+            elif token.type == "VOLUME":
+                current_volume = self._process_volume_token(
+                    token, toc, stats, current_volume
                 )
-                if current_volume.title != volume_title:
-                    current_volume = Volume(title=volume_title)
-                    toc.append(current_volume)
-
-            if token.type == "CHAPTER":
-                chapter_title = self.words_to_nums(
-                    token.value, len(str(stats.get("CHAPTER")))
+            elif token.type == "CHAPTER":
+                current_chapter = self._process_chapter_token(
+                    token, toc, stats, current_chapter
                 )
-                if current_chapter.title != chapter_title:
-                    current_chapter = Chapter(title=chapter_title)
-
-                    if toc and isinstance(toc[-1], Volume):
-                        toc[-1].add_chapter(current_chapter)
-                    else:
-                        toc.append(current_chapter)
-
-            if token.type == "PARAGRAPH":
-                if toc:
-                    if isinstance(toc[-1], Volume):
-                        toc[-1].chapters[-1].add_paragraph(token.value)
-
-                    if isinstance(toc[-1], Chapter):
-                        toc[-1].add_paragraph(token.value)
+            elif token.type == "PARAGRAPH":
+                self._process_paragraph_token(token, toc)
 
         # Use authors if set explicitly from command line.
         if hasattr(self.config, "author") and self.config.author:
-            authors = self.config.author
+            book_data["authors"] = self.config.author
 
         if hasattr(self.config, "title") and self.config.title:
-            book_title = self.config.title
+            book_data["book_title"] = self.config.title
 
         if hasattr(self.config, "translator") and self.config.translator:
-            translators = self.config.translator
+            book_data["translators"] = self.config.translator
 
-        logger.info("Found or set book title: %s", book_title)
-        logger.info("Found or set authors: %s", repr(authors))
-        logger.info("Found or set translators: %s", repr(translators))
-        logger.info("Found or set tags: %s", repr(tags))
-        logger.info("Found or set index: %s", repr(index))
+        logger.info("Found or set book title: %s", book_data["book_title"])
+        logger.info("Found or set authors: %s", repr(book_data["authors"]))
+        logger.info(
+            "Found or set translators: %s", repr(book_data["translators"])
+        )
+        logger.info("Found or set tags: %s", repr(book_data["tags"]))
+        logger.info("Found or set index: %s", repr(book_data["index"]))
 
         if (
             hasattr(self.config, "sort_volume_and_chapter")
@@ -243,7 +313,14 @@ class Parser:
         ):
             self.sort_volume_and_chapter(toc)
 
-        return (book_title, authors, translators, tags, index, toc)
+        return (
+            book_data["book_title"],
+            book_data["authors"],
+            book_data["translators"],
+            book_data["tags"],
+            book_data["index"],
+            toc,
+        )
 
     def sort_volume_and_chapter(self, toc: List) -> None:
         """Sort by title of volumes and its chapters.

txt2ebook/subcommands/epub.py

@@ -19,6 +19,7 @@ import argparse
 import logging
 import sys
 
+from txt2ebook.exceptions import InputError
 from txt2ebook.formats import EPUB_TEMPLATES
 from txt2ebook.formats.epub import EpubWriter
 from txt2ebook.subcommands.parse import run as parse_txt
@@ -133,14 +134,15 @@ def run(args: argparse.Namespace) -> None:
         input_sources.append(sys.stdin)
     else:
         logger.error("No input files provided.")
-        sys.exit(1)
+        raise InputError("No input files provided.")
 
     if len(input_sources) > 1 and args.output_file:
-        logger.error(
+        msg = (
             "Cannot specify a single output file when "
             "processing multiple input files."
         )
-        sys.exit(1)
+        logger.error(msg)
+        raise InputError(msg)
 
     for i, current_input_stream in enumerate(input_sources):
         # ensures that `input_file` and `output_file` are correctly isolated
@@ -156,8 +158,8 @@ def run(args: argparse.Namespace) -> None:
         if i > 0 and args.output_file:
             current_file_args.output_file = None
 
-        book = parse_txt(current_file_args)
-        writer = EpubWriter(book, current_file_args)
+        book, langconf = parse_txt(current_file_args)
+        writer = EpubWriter(book, current_file_args, langconf)
         writer.write()
 
         # close the file stream if it was opened by argparse.FileType and is

txt2ebook/subcommands/gmi.py

@@ -19,6 +19,7 @@ import argparse
 import logging
 import sys
 
+from txt2ebook.exceptions import InputError
 from txt2ebook.formats.gmi import GmiWriter
 from txt2ebook.subcommands.parse import run as parse_txt
 
@@ -114,6 +115,41 @@ def run(args: argparse.Namespace) -> None:
     Returns:
         None
     """
-    book = parse_txt(args)
-    writer = GmiWriter(book, args)
-    writer.write()
+    input_sources = []
+
+    if args.input_file:
+        # File path(s) were explicitly provided on the command line
+        input_sources.append(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.")
+        raise InputError("No input files provided.")
+
+    if len(input_sources) > 1 and args.output_file:
+        msg = (
+            "Cannot specify a single output file when "
+            "processing multiple input files."
+        )
+        logger.error(msg)
+        raise InputError(msg)
+
+    for i, current_input_stream in enumerate(input_sources):
+        # ensures that `input_file` and `output_file` are correctly isolated
+        current_file_args = argparse.Namespace(**vars(args))
+        current_file_args.input_file = current_input_stream
+
+        # if an explicit output_file was provided, it must apply to the first
+        # input
+        if i > 0 and args.output_file:
+            current_file_args.output_file = None
+
+        book, langconf = parse_txt(current_file_args)
+        writer = GmiWriter(book, current_file_args, langconf)
+        writer.write()
+
+        # close the file stream if it was opened by argparse.FileType and is
+        # not sys.stdin.
+        if current_input_stream is not sys.stdin:
+            current_input_stream.close()

txt2ebook/subcommands/md.py

@@ -19,6 +19,7 @@ import argparse
 import logging
 import sys
 
+from txt2ebook.exceptions import InputError
 from txt2ebook.formats.md import MdWriter as MarkdownWriter
 from txt2ebook.subcommands.parse import run as parse_txt
 
@@ -114,6 +115,41 @@ def run(args: argparse.Namespace) -> None:
     Returns:
         None
     """
-    book = parse_txt(args)
-    writer = MarkdownWriter(book, args)
-    writer.write()
+    input_sources = []
+
+    if args.input_file:
+        # File path(s) were explicitly provided on the command line
+        input_sources.append(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.")
+        raise InputError("No input files provided.")
+
+    if len(input_sources) > 1 and args.output_file:
+        msg = (
+            "Cannot specify a single output file when "
+            "processing multiple input files."
+        )
+        logger.error(msg)
+        raise InputError(msg)
+
+    for i, current_input_stream in enumerate(input_sources):
+        # ensures that `input_file` and `output_file` are correctly isolated
+        current_file_args = argparse.Namespace(**vars(args))
+        current_file_args.input_file = current_input_stream
+
+        # if an explicit output_file was provided, it must apply to the first
+        # input
+        if i > 0 and args.output_file:
+            current_file_args.output_file = None
+
+        book, langconf = parse_txt(current_file_args)
+        writer = MarkdownWriter(book, current_file_args, langconf)
+        writer.write()
+
+        # close the file stream if it was opened by argparse.FileType and is
+        # not sys.stdin.
+        if current_input_stream is not sys.stdin:
+            current_input_stream.close()

txt2ebook/subcommands/parse.py

@@ -19,6 +19,8 @@ import argparse
 import logging
 import sys
 from importlib import import_module
+from types import ModuleType
+from typing import Tuple
 
 import jieba.analyse
 from bs4 import UnicodeDammit
@@ -59,14 +61,15 @@ def build_subparser(subparsers) -> None:
     parse_parser.set_defaults(func=run)
 
 
-def run(args: argparse.Namespace) -> Book:
+def run(args: argparse.Namespace) -> Tuple[Book, ModuleType]:
     """Run env subcommand.
 
     Args:
         args (argparse.Namespace): Config from command line arguments
 
     Returns:
-        None
+        Tuple[Book, ModuleType]: The Book model and the language
+        configuration module.
     """
     logger.info("Parsing txt file: %s", args.input_file.name)
 
@@ -94,4 +97,4 @@ def run(args: argparse.Namespace) -> Book:
     if args.debug:
         book.debug(args.verbose)
 
-    return book
+    return book, langconf

txt2ebook/subcommands/pdf.py

@@ -19,6 +19,7 @@ import argparse
 import logging
 import sys
 
+from txt2ebook.exceptions import InputError
 from txt2ebook.formats import PAGE_SIZES
 from txt2ebook.formats.pdf import PdfWriter
 from txt2ebook.subcommands.parse import run as parse_txt
@@ -104,6 +105,41 @@ def run(args: argparse.Namespace) -> None:
     Returns:
         None
     """
-    book = parse_txt(args)
-    writer = PdfWriter(book, args)
-    writer.write()
+    input_sources = []
+
+    if args.input_file:
+        # File path(s) were explicitly provided on the command line
+        input_sources.append(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.")
+        raise InputError("No input files provided.")
+
+    if len(input_sources) > 1 and args.output_file:
+        msg = (
+            "Cannot specify a single output file when "
+            "processing multiple input files."
+        )
+        logger.error(msg)
+        raise InputError(msg)
+
+    for i, current_input_stream in enumerate(input_sources):
+        # ensures that `input_file` and `output_file` are correctly isolated
+        current_file_args = argparse.Namespace(**vars(args))
+        current_file_args.input_file = current_input_stream
+
+        # if an explicit output_file was provided, it must apply to the first
+        # input
+        if i > 0 and args.output_file:
+            current_file_args.output_file = None
+
+        book, langconf = parse_txt(current_file_args)
+        writer = PdfWriter(book, current_file_args, langconf)
+        writer.write()
+
+        # close the file stream if it was opened by argparse.FileType and is
+        # not sys.stdin.
+        if current_input_stream is not sys.stdin:
+            current_input_stream.close()

txt2ebook/subcommands/tex.py

@@ -19,6 +19,7 @@ import argparse
 import logging
 import sys
 
+from txt2ebook.exceptions import InputError
 from txt2ebook.formats.tex import TexWriter
 from txt2ebook.subcommands.parse import run as parse_txt
 
@@ -122,14 +123,15 @@ def run(args: argparse.Namespace) -> None:
         input_sources.extend(args.input_file)
     else:
         logger.error("No input files provided.")
-        sys.exit(1)
+        raise InputError("No input files provided.")
 
     if len(input_sources) > 1 and args.output_file:
-        logger.error(
+        msg = (
             "Cannot specify a single output file when "
             "processing multiple input files."
         )
-        sys.exit(1)
+        logger.error(msg)
+        raise InputError(msg)
 
     for i, current_input_stream in enumerate(input_sources):
         # ensures that `input_file` and `output_file` are correctly isolated
@@ -141,8 +143,8 @@ def run(args: argparse.Namespace) -> None:
         if i > 0 and args.output_file:
             current_file_args.output_file = None
 
-        book = parse_txt(current_file_args)
-        writer = TexWriter(book, current_file_args)
+        book, langconf = parse_txt(current_file_args)
+        writer = TexWriter(book, current_file_args, langconf)
         writer.write()
 
         # close the file stream if it was opened by argparse.FileType and is

txt2ebook/subcommands/typ.py

@@ -13,16 +13,22 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
-"""typ subcommand."""
-
 import argparse
+
 import logging
+
 import sys
 
+
+from txt2ebook.exceptions import InputError
+
 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__)
 
 
@@ -124,46 +130,70 @@ def build_subparser(subparsers) -> None:
 def run(args: argparse.Namespace) -> None:
     """Run typ subcommand.
 
+
+
     Args:
+
         args (argparse.Namespace): Config from command line arguments
 
+
+
     Returns:
+
         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)
+
         input_sources.extend(args.input_file)
+
     else:
         logger.error("No input files provided.")
-        sys.exit(1)
+
+        raise InputError("No input files provided.")
 
     if len(input_sources) > 1 and args.output_file:
-        logger.error(
+        msg = (
             "Cannot specify a single output file when "
             "processing multiple input files."
         )
-        sys.exit(1)
+
+        logger.error(msg)
+
+        raise InputError(msg)
 
     for i, current_input_stream in enumerate(input_sources):
         # ensures that `input_file` and `output_file` are correctly isolated
+
         current_file_args = argparse.Namespace(**vars(args))
+
         current_file_args.input_file = current_input_stream
 
         # if an explicit output_file was provided, it must apply to the first
+
         # input
+
         if i > 0 and args.output_file:
             current_file_args.output_file = None
 
-        book = parse_txt(current_file_args)
-        writer = TypWriter(book, current_file_args)
+        book, langconf = parse_txt(current_file_args)
+
+        writer = TypWriter(book, current_file_args, langconf)
+
         writer.write()
 
         # close the file stream if it was opened by argparse.FileType and is
+
         # not sys.stdin.
+
         if current_input_stream is not sys.stdin:
             current_input_stream.close()

txt2ebook/tokenizer.py

@@ -20,7 +20,7 @@ import logging
 import re
 from collections import Counter
 from dataclasses import dataclass, field
-from importlib import import_module
+from types import ModuleType
 from typing import Any, Dict, List
 
 from txt2ebook import log_or_raise_on_warning
@@ -55,17 +55,21 @@ class Tokenizer:
     raw_content: str = field(repr=False)
     metadata_marker: str = field(repr=False)
     config: argparse.Namespace = field(repr=False)
+    langconf: ModuleType = field(repr=False)
     tokens: List[Token] = field(default_factory=List, repr=False)
     lineno_lookup: Dict = field(default_factory=Dict, repr=False)
 
-    def __init__(self, raw_content: str, config: argparse.Namespace) -> None:
+    def __init__(
+        self,
+        raw_content: str,
+        config: argparse.Namespace,
+        langconf: ModuleType,
+    ) -> None:
         """Set the constructor for the Tokenizer."""
         self.raw_content = raw_content
         self.config = config
         self.metadata_marker = "---"
-
-        config_lang = config.language.replace("-", "_")
-        self.langconf = import_module(f"txt2ebook.languages.{config_lang}")
+        self.langconf = langconf
 
         lookupcontent = raw_content[:]
         lineno_lookup = {}
@@ -184,7 +188,8 @@ class Tokenizer:
         else:
             # No metadata block found according to the pattern,
             # so assume all raw_content is the actual content.
-            # _extract_metadata would have already logged/warned if metadata was expected.
+            # _extract_metadata would have already logged/warned if metadata
+            # was expected.
             content_str = self.raw_content
 
         content_str = content_str.strip(self.config.paragraph_separator)

{txt2ebook-0.1.160.dist-info → txt2ebook-0.1.162.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: txt2ebook
-Version: 0.1.160
+Version: 0.1.162
 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
@@ -13,17 +13,17 @@ Classifier: Natural Language :: Chinese (Simplified)
 Classifier: Natural Language :: Chinese (Traditional)
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Classifier: Topic :: Text Processing
 Classifier: Topic :: Text Processing :: Filters
 Classifier: Topic :: Text Processing :: General
 Classifier: Topic :: Text Processing :: Markup :: HTML
 Classifier: Topic :: Text Processing :: Markup :: Markdown
-Requires-Python: ~=3.9
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
 Requires-Dist: CJKwrap~=2.2

{txt2ebook-0.1.160.dist-info → txt2ebook-0.1.162.dist-info}/RECORD

@@ -1,43 +1,43 @@
 txt2ebook/__init__.py,sha256=KWWLxYHPy59AKS4tUen_9OLb7YhqYDUJP21nvh-knBc,3106
 txt2ebook/__main__.py,sha256=L29rlfPSx9XMnVaHBYP2dyYgDmutJvONR3yUejjYwRY,855
-txt2ebook/cli.py,sha256=i8NrYJyC9ckMC5opCGkIcs42p4AFzhE0lTGKSU-S8Zw,4418
-txt2ebook/exceptions.py,sha256=PT3m85PE5QopHHUfRwEQzp0kJ4AA9yjLO6V6lYC8WhQ,858
-txt2ebook/parser.py,sha256=ITn6pGHO4vTfdrYouVV2mEe9jUM2zm3-FKEcspp2qzI,8968
-txt2ebook/tokenizer.py,sha256=UGyOBGxlKOXJtvP2UFp38EgFym8-PAU3A7Jl9RF3w6Y,10299
+txt2ebook/cli.py,sha256=cB9j6ZS0QugOHYH982QuJuJvNkOKpFR0r-tXFkWJqSQ,4607
+txt2ebook/exceptions.py,sha256=Rowz2jLhopDIV8M0Wma-lojppPjgbvPvBkxSXtLldGQ,944
+txt2ebook/parser.py,sha256=DGxyhuzHJhyHkipoApc-J29H1zoRLYKl2v0EWx8G_q8,11634
+txt2ebook/tokenizer.py,sha256=rIRljJYiiBd0Mi1-aCAL88P658a60mdVGluvE9OluGo,10312
 txt2ebook/zh_utils.py,sha256=0Yq9r-JL4HntW68vFR6TBP9yQim1a07mfsh_sp-XmaE,4887
 txt2ebook/formats/__init__.py,sha256=_fW9UuoOTFxCKlej6t-PsFzJOqDFLzVatCci9tcPQeE,1645
-txt2ebook/formats/base.py,sha256=bPpfKZwz3KeEtNRYJPZJJIKRcANGs_tw5a3uOw1pzSs,9625
-txt2ebook/formats/epub.py,sha256=IVz-FmYQlcChOw38YqfKy46bPVSIrHyxA_94iz06N3Y,6941
+txt2ebook/formats/base.py,sha256=aMD_a3_dv7k07j5EWREkBZdRQJE3mZ1lfpnxJk0UE28,9683
+txt2ebook/formats/epub.py,sha256=tac53gqc4YKdIy9SlxzcY3LaLgSJ_XGFs9GGcPaycco,6911
 txt2ebook/formats/gmi.py,sha256=tUCEHtRHDupEPJ8dYPpxpE6yEKHCk8PRXR0zgjJFgsI,5837
 txt2ebook/formats/md.py,sha256=ZleBFNOGRhWr5WgcA8uyLXBxJm1bdQaunqzjocQYSkI,5587
 txt2ebook/formats/pdf.py,sha256=tr_ozVlL976yo7Ggny71zjOwzSd6tSnHTl7mcsLII_g,7263
 txt2ebook/formats/tex.py,sha256=V5B1nPR-WzGc4jqWu-BqxfQhtQsUTKM_sZZJsCcDBAk,5897
-txt2ebook/formats/txt.py,sha256=1f-e53oPyhyElLLKqZZ4_HJxIJkwyVjZLi0pnl02EM8,7929
-txt2ebook/formats/typ.py,sha256=0WjGeZHxbdCV1grYkEpgUocehWfmeJz8Ur9cT2ADlFI,8269
+txt2ebook/formats/txt.py,sha256=yWyuKuCWsElGhRZ-hdfcvQXFwEZMDzJ_Lbela6IQgNc,4630
+txt2ebook/formats/typ.py,sha256=iMskvU4I26HbOo8JbgE5urZi43o9JJ6O5Ysi-lJyzP8,8286
 txt2ebook/formats/templates/__init__.py,sha256=f3K7pJByNmmvu-wvziks6qb2QnnLmkDjUACXyw2s60E,760
 txt2ebook/formats/templates/epub/__init__.py,sha256=-XVLvnknTJTmQZY9UTH705vMcHgy56rQVRTusYawEZ4,766
-txt2ebook/helpers/__init__.py,sha256=c2EItHvPABDORfgfjArfa5XR--43es4D1tKWqaPcBxY,1309
+txt2ebook/helpers/__init__.py,sha256=TltRlsKOaB3FdXqVBKVmsnSFidBCOhRMVx4HjPR2bm0,1313
 txt2ebook/languages/__init__.py,sha256=1AfDn-D0q-dvODGP-9KxPHY_Wtk-ifZdN1FutZMT9-Q,763
 txt2ebook/languages/en.py,sha256=8qsmbKB69M3SD9nBnSX8rP8hAL_RFkhB-zyH93INgaQ,999
 txt2ebook/languages/zh_cn.py,sha256=ryKMeaNgX2J6BGrHl7KZL9S6HwIlTyLk75z3lvVQIi4,1960
 txt2ebook/languages/zh_tw.py,sha256=_fdXOOSLK0nTMuBe1Om2qjb4zr2PVd6N4xi2rrYkNTI,1515
 txt2ebook/models/__init__.py,sha256=Z3zClWLj08Q8HgaWV1RRgIKatEhIUfYBAVWm-j4m05w,930
-txt2ebook/models/book.py,sha256=P-SQabvrRgWoafrk0tw6zjD-3hq_r8_jGvgTORUS-DM,2730
+txt2ebook/models/book.py,sha256=xZFVuS3XZ2CBR11_ySo0jxPsUTV8nKVcRccF2FSgsDk,2717
 txt2ebook/models/chapter.py,sha256=6YvUDHzR6amGMZgkQl_xHWrYZUmlfpF7mnDLilG2BpA,1686
 txt2ebook/models/volume.py,sha256=koz1KfWjvGWLFbmGEQlZ23frsP93cDsuBMySYBHiXm8,1597
 txt2ebook/subcommands/__init__.py,sha256=ldhzvsrMsR8lZmhZef77JFz0jValpV3pytFfwJSkjls,1146
 txt2ebook/subcommands/env.py,sha256=gEzra4b6guy7pRZUTCWX1_eiR7JmrtR1Z-J-vxljvMY,1549
-txt2ebook/subcommands/epub.py,sha256=xaXKATCioRVr-vN_Lw4SqQxJdm6dSWs-y3RyTpV3ZV8,4824
-txt2ebook/subcommands/gmi.py,sha256=ANnPg-RFsylTo44fUzFOSHN1fC3Ce82gBzrv-sBv5fU,3318
+txt2ebook/subcommands/epub.py,sha256=T-Uex74HYU1BWfuAcnnoXO0wHoVYVorsXLGfPotCTrc,4951
+txt2ebook/subcommands/gmi.py,sha256=pvp_bQLSttPo5HVcZJxABdPwBf3LBtoGOYy_yEu5Z4A,4698
 txt2ebook/subcommands/massage.py,sha256=f_moVt19n60QH2T2J_EwZnCv1JNFrqLGu5j2VZfp_Lk,15793
-txt2ebook/subcommands/md.py,sha256=PmIqrqrnzLywvN4qTkle0V9N3FTIJGRWpC0Xbk76B5o,3329
-txt2ebook/subcommands/parse.py,sha256=xjhW8I9zS5DL3n3m04RyFofgci-6-_L6aF3d4N7c7M4,2938
-txt2ebook/subcommands/pdf.py,sha256=1JQtpugzAIaho6G3CK1rGYk74hotAexXZxPH9PHpRps,2980
-txt2ebook/subcommands/tex.py,sha256=8XqTV5GsOEr7sGSLUJB-B1KefIMxW3_BDq_Jm96Bt1Y,4369
-txt2ebook/subcommands/typ.py,sha256=xeJ_cPmyq_uouUBiH2kbcscckHLqewPmu9j0WO36sXY,4814
-txt2ebook-0.1.160.dist-info/licenses/LICENSE.md,sha256=tGtFDwxWTjuR9syrJoSv1Hiffd2u8Tu8cYClfrXS_YU,31956
-txt2ebook-0.1.160.dist-info/METADATA,sha256=p4n4nz_UYd-ZVgSxC2h32VQLDGxiXiL-bf464pObSMA,5295
-txt2ebook-0.1.160.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-txt2ebook-0.1.160.dist-info/entry_points.txt,sha256=3jm5vpUsDRgoM6S3CQVMMiP7tJQqfq1vfV0sh_KaK9s,74
-txt2ebook-0.1.160.dist-info/top_level.txt,sha256=pesdk4CJRlfhUXVD9vH3Dd_F8ATlLQoqlUsUnU8SJMw,10
-txt2ebook-0.1.160.dist-info/RECORD,,
+txt2ebook/subcommands/md.py,sha256=MvGwzOtYA8c96jw3leDnXspY2s6WRY2BZNTZkvcFtUY,4709
+txt2ebook/subcommands/parse.py,sha256=Qwca1Nha5vrkfnsXoo9qbHL7SWAXFkfaVfkFcgDFs6E,3103
+txt2ebook/subcommands/pdf.py,sha256=lg4da1XhDOywuxB5fjvtf9JmmJGbpCQdUarY5IFS3V4,4360
+txt2ebook/subcommands/tex.py,sha256=szEVokaWfP4QnKBtmknIqTtS39xSc1JLWwt_q-a0PFk,4496
+txt2ebook/subcommands/typ.py,sha256=jKcL52vTw7_9FxlrtdGrD5JDHPvz5Q6x0jWISVWyTVw,4948
+txt2ebook-0.1.162.dist-info/licenses/LICENSE.md,sha256=tGtFDwxWTjuR9syrJoSv1Hiffd2u8Tu8cYClfrXS_YU,31956
+txt2ebook-0.1.162.dist-info/METADATA,sha256=JpZ7-SScM4OCD0JOm8q6t_5kEAWHcUlDRRMZuFFFXKM,5297
+txt2ebook-0.1.162.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+txt2ebook-0.1.162.dist-info/entry_points.txt,sha256=3jm5vpUsDRgoM6S3CQVMMiP7tJQqfq1vfV0sh_KaK9s,74
+txt2ebook-0.1.162.dist-info/top_level.txt,sha256=pesdk4CJRlfhUXVD9vH3Dd_F8ATlLQoqlUsUnU8SJMw,10
+txt2ebook-0.1.162.dist-info/RECORD,,