txt2ebook 0.1.107__tar.gz → 0.1.108__tar.gz

{txt2ebook-0.1.107 → txt2ebook-0.1.108}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: txt2ebook
-Version: 0.1.107
+Version: 0.1.108
 Summary: CLI tool to convert txt file to ebook format
 Home-page: https://github.com/kianmeng/txt2ebook
 License: AGPL-3.0-or-later

{txt2ebook-0.1.107 → txt2ebook-0.1.108}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "txt2ebook"
-version = "0.1.107"
+version = "0.1.108"
 description = "CLI tool to convert txt file to ebook format"
 authors = ["Kian-Meng Ang <kianmeng@cpan.org>"]
 license = "AGPL-3.0-or-later"
@@ -44,7 +44,7 @@ lxml = "^5.2.2"
 
 [tool.poetry.scripts]
 txt2ebook = 'txt2ebook.txt2ebook:main'
-tte = 'txt2ebook.txt2ebook:main'
+tte = 'txt2ebook.cli:main'
 
 [tool.poetry.group.dev.dependencies]
 babel = "^2.12.1"

{txt2ebook-0.1.107 → txt2ebook-0.1.108}/src/txt2ebook/__init__.py

@@ -22,7 +22,7 @@ import sys
 
 logger = logging.getLogger(__name__)
 
-__version__ = "0.1.107"
+__version__ = "0.1.108"
 
 
 def setup_logger(config: argparse.Namespace) -> None:

txt2ebook-0.1.108/src/txt2ebook/cli.py

@@ -0,0 +1,271 @@
+# Copyright (C) 2021,2022,2023,2024 Kian-Meng Ang
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# 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/>.
+
+"""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
+"""
+
+import argparse
+import logging
+import sys
+from typing import Optional, Sequence
+
+import txt2ebook.subcommands.env
+import txt2ebook.subcommands.parse
+import txt2ebook.subcommands.massage
+from txt2ebook import __version__, setup_logger
+
+logger = logging.getLogger(__name__)
+
+
+def build_parser(
+    args: Optional[Sequence[str]] = [],
+) -> argparse.ArgumentParser:
+    """Build the CLI parser."""
+    parser = argparse.ArgumentParser(
+        prog="txt2ebook",
+        add_help=False,
+        description=__doc__,
+        formatter_class=lambda prog: argparse.RawTextHelpFormatter(
+            prog, max_help_position=6
+        ),
+    )
+
+    parser.add_argument(
+        "-t",
+        "--title",
+        dest="title",
+        default=None,
+        help="title of the ebook (default: '%(default)s')",
+        metavar="TITLE",
+    )
+
+    parser.add_argument(
+        "-l",
+        "--language",
+        dest="language",
+        default=None,
+        help="language of the ebook (default: '%(default)s')",
+        metavar="LANGUAGE",
+    )
+
+    parser.add_argument(
+        "-a",
+        "--author",
+        dest="author",
+        default=[],
+        action="append",
+        help="author of the ebook (default: '%(default)s')",
+        metavar="AUTHOR",
+    )
+
+    parser.add_argument(
+        "-c",
+        "--cover",
+        dest="cover",
+        default=None,
+        help="cover of the ebook",
+        metavar="IMAGE_FILENAME",
+    )
+
+    parser.add_argument(
+        "-tr",
+        "--translator",
+        dest="translator",
+        default=[],
+        action="append",
+        help="translator of the ebook (default: '%(default)s')",
+        metavar="TRANSLATOR",
+    )
+
+    parser.add_argument(
+        "-fw",
+        "--fullwidth",
+        default=False,
+        action="store_true",
+        dest="fullwidth",
+        help="convert ASCII character from halfwidth to fullwidth",
+    )
+
+
+    parser.add_argument(
+        "-ra",
+        "--regex-author",
+        dest="re_author",
+        default=[],
+        action="append",
+        help="regex to parse author of the book (default: by LANGUAGE)",
+        metavar="REGEX",
+    )
+
+    parser.add_argument(
+        "-rc",
+        "--regex-chapter",
+        dest="re_chapter",
+        default=[],
+        action="append",
+        help="regex to parse chapter header (default: by LANGUAGE)",
+        metavar="REGEX",
+    )
+
+    parser.add_argument(
+        "-rvc",
+        "--regex-volume-chapter",
+        dest="re_volume_chapter",
+        default=[],
+        action="append",
+        help=(
+            "regex to parse volume and chapter header "
+            "(default: by LANGUAGE)"
+        ),
+        metavar="REGEX",
+    )
+
+    parser.add_argument(
+        "-rv",
+        "--regex-volume",
+        dest="re_volume",
+        default=[],
+        action="append",
+        help="regex to parse volume header (default: by LANGUAGE)",
+        metavar="REGEX",
+    )
+
+    parser.add_argument(
+        "-hn",
+        "--header-number",
+        default=False,
+        action="store_true",
+        dest="header_number",
+        help="convert section header from words to numbers",
+    )
+
+    parser.add_argument(
+        "-ps",
+        "--paragraph_separator",
+        dest="paragraph_separator",
+        type=lambda value: value.encode("utf-8").decode("unicode_escape"),
+        default="\n\n",
+        help="paragraph separator (default: %(default)r)",
+        metavar="SEPARATOR",
+    )
+
+    parser.add_argument(
+        "-rt",
+        "--regex-title",
+        dest="re_title",
+        default=[],
+        action="append",
+        help="regex to parse title of the book (default: by LANGUAGE)",
+        metavar="REGEX",
+    )
+
+    parser.add_argument(
+        "-ss",
+        "--sort-volume-and-chapter",
+        default=False,
+        action="store_true",
+        dest="sort_volume_and_chapter",
+        help="short volume and chapter",
+    )
+
+    parser.add_argument(
+        "-rw",
+        "--raise-on-warning",
+        default=False,
+        action="store_true",
+        dest="raise_on_warning",
+        help="raise exception and stop parsing upon warning",
+    )
+
+    parser.add_argument(
+        "-q",
+        "--quiet",
+        default=False,
+        action="store_true",
+        dest="quiet",
+        help="suppress all logging",
+    )
+
+    parser.add_argument(
+        "-v",
+        "--verbose",
+        default=0,
+        action="count",
+        dest="verbose",
+        help="show verbosity of debugging log, use -vv, -vvv for more details",
+    )
+
+    parser.add_argument(
+        "-d",
+        "--debug",
+        default=False,
+        action="store_true",
+        dest="debug",
+        help="show debugging log and stacktrace",
+    )
+
+    parser.add_argument(
+        "-h",
+        "--help",
+        action="help",
+        default=argparse.SUPPRESS,
+        help="show this help message and exit",
+    )
+
+    parser.add_argument(
+        "-V",
+        "--version",
+        action="version",
+        version=f"%(prog)s {__version__}",
+    )
+
+    subparsers = parser.add_subparsers(help="sub-command help")
+    txt2ebook.subcommands.parse.build_subparser(subparsers)
+    txt2ebook.subcommands.massage.build_subparser(subparsers)
+    txt2ebook.subcommands.env.build_subparser(subparsers)
+
+    return parser
+
+
+def main(args: Optional[Sequence[str]] = None):
+    """Set the main entrypoint of the CLI script."""
+    args = args or sys.argv[1:]
+
+    try:
+        parser = build_parser()
+        if len(args) == 0:
+            parser.print_help(sys.stderr)
+        else:
+            parsed_args = parser.parse_args(args)
+            setup_logger(parsed_args)
+
+            if hasattr(parsed_args, "func"):
+                logger.debug(parsed_args)
+                parsed_args.func(parsed_args)
+            else:
+                parser.print_help(sys.stderr)
+
+    except Exception as error:
+        logger.error(
+            "error: %s",
+            getattr(error, "message", str(error)),
+            exc_info=("-d" in args or "--debug" in args),
+        )
+
+        raise SystemExit(1) from None

{txt2ebook-0.1.107 → txt2ebook-0.1.108}/src/txt2ebook/models/book.py

@@ -40,7 +40,6 @@ class Book:
     language: str = field(default="")
     cover: str = field(default="", repr=False)
     raw_content: str = field(default="", repr=False)
-    massaged_content: str = field(default="", repr=False)
     toc: List[Union[Volume, Chapter]] = field(
         default_factory=lambda: [], repr=False
     )

{txt2ebook-0.1.107 → txt2ebook-0.1.108}/src/txt2ebook/parser.py

@@ -52,8 +52,7 @@ class Parser:
         Returns:
           txt2ebook.models.Book: The Book model.
         """
-        massaged_content = self.massage()
-        tokenizer = Tokenizer(massaged_content, self.config)
+        tokenizer = Tokenizer(self.raw_content, self.config)
 
         (book_title, authors, translators, tags, index, toc) = (
             self.parse_tokens(tokenizer)
@@ -68,7 +67,6 @@ class Parser:
             index=index,
             cover=self.config.cover,
             raw_content=self.raw_content,
-            massaged_content=massaged_content,
             toc=toc,
         )
 
@@ -252,121 +250,3 @@ class Parser:
                 section.chapters.sort(key=lambda x: x.title)
 
         toc.sort(key=lambda x: x.title if isinstance(x, Volume) else "")
-
-    def massage(self) -> str:
-        """Massage the txt content.
-
-        Returns:
-            str: The formatted book content
-        """
-        content = self.raw_content
-
-        content = Parser.to_unix_newline(content)
-
-        if self.config.fullwidth and self.config.language in (
-            "zh-cn",
-            "zh-tw",
-        ):
-            logger.info("Convert halfwidth ASCII characters to fullwidth")
-            content = zh_halfwidth_to_fullwidth(content)
-
-        if self.config.re_delete:
-            content = self.do_delete_regex(content)
-
-        if self.config.re_replace:
-            content = self.do_replace_regex(content)
-
-        if self.config.re_delete_line:
-            content = self.do_delete_line_regex(content)
-
-        if self.config.width:
-            content = self.do_wrapping(content)
-
-        return content
-
-    @staticmethod
-    def to_unix_newline(content: str) -> str:
-        """Convert all other line ends to Unix line end.
-
-        Args:
-            content(str): The formatted book content.
-
-        Returns:
-            str: The formatted book content.
-        """
-        return content.replace("\r\n", "\n").replace("\r", "\n")
-
-    def do_delete_regex(self, content: str) -> str:
-        """Remove words/phrases based on regex.
-
-        Args:
-            content(str): The formatted book content.
-
-        Returns:
-            str: The formatted book content.
-        """
-        for delete_regex in self.config.re_delete:
-            content = re.sub(
-                re.compile(rf"{delete_regex}", re.MULTILINE), "", content
-            )
-        return content
-
-    def do_replace_regex(self, content: str) -> str:
-        """Replace words/phrases based on regex.
-
-        Args:
-            content(str): The formatted book content.
-
-        Returns:
-            str: The formatted book content.
-        """
-        regex = self.config.re_replace
-        if isinstance(regex, list):
-            for search, replace in regex:
-                content = re.sub(
-                    re.compile(rf"{search}", re.MULTILINE),
-                    rf"{replace}",
-                    content,
-                )
-
-        return content
-
-    def do_delete_line_regex(self, content: str) -> str:
-        """Delete whole line based on regex.
-
-        Args:
-            content(str): The formatted book content.
-
-        Returns:
-            str: The formatted book content.
-        """
-        for delete_line_regex in self.config.re_delete_line:
-            content = re.sub(
-                re.compile(rf"^.*{delete_line_regex}.*$", re.MULTILINE),
-                "",
-                content,
-            )
-        return content
-
-    def do_wrapping(self, content: str) -> str:
-        """Wrap or fill CJK text.
-
-        Args:
-            content (str): The formatted book content.
-
-        Returns:
-            str: The formatted book content.
-        """
-        logger.info("Wrapping paragraph to width: %s", self.config.width)
-
-        paragraphs = []
-        # We don't remove empty line and keep all formatting as it.
-        for paragraph in content.split("\n"):
-            paragraph = paragraph.strip()
-
-            lines = cjkwrap.wrap(paragraph, width=self.config.width)
-            paragraph = "\n".join(lines)
-            paragraphs.append(paragraph)
-
-        wrapped_content = "\n".join(paragraphs)
-        return wrapped_content

txt2ebook-0.1.108/src/txt2ebook/subcommands/env.py

@@ -0,0 +1,52 @@
+# Copyright (C) 2021,2022,2023,2024 Kian-Meng Ang
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# 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/>.
+
+"""Env subcommand."""
+
+import argparse
+import logging
+import platform
+import sys
+
+from txt2ebook import __version__
+
+logger = logging.getLogger(__name__)
+
+
+def build_subparser(subparsers) -> None:
+    """Build the subparser."""
+    env_parser = subparsers.add_parser(
+        "env", help="print environment information for bug reporting"
+    )
+
+    env_parser.set_defaults(func=run)
+
+
+def run(_args: argparse.Namespace) -> None:
+    """Run env subcommand.
+
+    Args:
+        config (argparse.Namespace): Config from command line arguments
+
+    Returns:
+        None
+    """
+    sys_version = sys.version.replace("\n", "")
+    print(
+        f"txt2ebook: {__version__}",
+        f"python: {sys_version}",
+        f"platform: {platform.platform()}",
+        sep="\n",
+    )

txt2ebook-0.1.108/src/txt2ebook/subcommands/massage.py

@@ -0,0 +1,220 @@
+# Copyright (C) 2021,2022,2023,2024 Kian-Meng Ang
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# 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/>.
+
+"""Env subcommand."""
+
+import argparse
+import logging
+import sys
+
+import cjkwrap
+import regex as re
+from bs4 import UnicodeDammit
+
+from txt2ebook.exceptions import EmptyFileError
+from txt2ebook.zh_utils import zh_halfwidth_to_fullwidth
+
+logger = logging.getLogger(__name__)
+
+
+def build_subparser(subparsers) -> None:
+    """Build the subparser."""
+    massage_parser = subparsers.add_parser(
+        "massage", help="massage the source txt file"
+    )
+
+    massage_parser.add_argument(
+        "input_file",
+        nargs=None if sys.stdin.isatty() else "?",  # type: ignore
+        type=argparse.FileType("rb"),
+        default=None if sys.stdin.isatty() else sys.stdin,
+        help="source text filename",
+        metavar="TXT_FILENAME",
+    )
+
+    massage_parser.add_argument(
+        "-rd",
+        "--regex-delete",
+        dest="re_delete",
+        default=[],
+        action="append",
+        help="regex to delete word or phrase (default: '%(default)s')",
+        metavar="REGEX",
+    )
+
+    massage_parser.add_argument(
+        "-rr",
+        "--regex-replace",
+        dest="re_replace",
+        nargs=2,
+        default=[],
+        action="append",
+        help="regex to search and replace (default: '%(default)s')",
+        metavar="REGEX",
+    )
+
+    massage_parser.add_argument(
+        "-rl",
+        "--regex-delete-line",
+        dest="re_delete_line",
+        default=[],
+        action="append",
+        help="regex to delete whole line (default: '%(default)s')",
+        metavar="REGEX",
+    )
+
+    massage_parser.add_argument(
+        "-w",
+        "--width",
+        dest="width",
+        type=int,
+        default=None,
+        help="width for line wrapping",
+        metavar="WIDTH",
+    )
+
+    massage_parser.set_defaults(func=run)
+
+
+def run(args: argparse.Namespace) -> None:
+    """Run massage subcommand.
+
+    Args:
+        args (argparse.Namespace): args.from command line arguments
+
+    Returns:
+        None
+    """
+    logger.info("Parsing txt file: %s", args.input_file.name)
+
+    unicode = UnicodeDammit(args.input_file.read())
+    logger.info("Detect encoding : %s", unicode.original_encoding)
+
+    content = unicode.unicode_markup
+    if not content:
+        raise EmptyFileError(
+            f"Empty file content in {args.input_file.name}"
+        )
+
+    content = to_unix_newline(content)
+
+    if args.fullwidth and args.language in ("zh-cn", "zh-tw"):
+        logger.info("Convert halfwidth ASCII characters to fullwidth")
+        content = zh_halfwidth_to_fullwidth(content)
+
+    if args.re_delete:
+        content = do_delete_regex(args, content)
+
+    if args.re_replace:
+        content = do_replace_regex(args, content)
+
+    if args.re_delete_line:
+        content = do_delete_line_regex(args, content)
+
+    if args.width:
+        content = do_wrapping(args, content)
+
+    return content
+
+
+def to_unix_newline(content: str) -> str:
+    """Convert all other line ends to Unix line end.
+
+    Args:
+        content(str): The formatted book content.
+
+    Returns:
+        str: The formatted book content.
+    """
+    return content.replace("\r\n", "\n").replace("\r", "\n")
+
+
+def do_delete_regex(args, content: str) -> str:
+    """Remove words/phrases based on regex.
+
+    Args:
+        content(str): The formatted book content.
+
+    Returns:
+        str: The formatted book content.
+    """
+    for delete_regex in args.re_delete:
+        content = re.sub(
+            re.compile(rf"{delete_regex}", re.MULTILINE), "", content
+        )
+    return content
+
+
+def do_replace_regex(args, content: str) -> str:
+    """Replace words/phrases based on regex.
+
+    Args:
+        content(str): The formatted book content.
+
+    Returns:
+        str: The formatted book content.
+    """
+    regex = args.re_replace
+    if isinstance(regex, list):
+        for search, replace in regex:
+            content = re.sub(
+                re.compile(rf"{search}", re.MULTILINE),
+                rf"{replace}",
+                content,
+            )
+
+    return content
+
+
+def do_delete_line_regex(args, content: str) -> str:
+    """Delete whole line based on regex.
+
+    Args:
+        content(str): The formatted book content.
+
+    Returns:
+        str: The formatted book content.
+    """
+    for delete_line_regex in args.re_delete_line:
+        content = re.sub(
+            re.compile(rf"^.*{delete_line_regex}.*$", re.MULTILINE),
+            "",
+            content,
+        )
+    return content
+
+
+def do_wrapping(args, content: str) -> str:
+    """Wrap or fill CJK text.
+
+    Args:
+        content (str): The formatted book content.
+
+    Returns:
+        str: The formatted book content.
+    """
+    logger.info("Wrapping paragraph to width: %s", args.width)
+
+    paragraphs = []
+    # We don't remove empty line and keep all formatting as it.
+    for paragraph in content.split("\n"):
+        paragraph = paragraph.strip()
+
+        lines = cjkwrap.wrap(paragraph, width=args.width)
+        paragraph = "\n".join(lines)
+        paragraphs.append(paragraph)
+
+    wrapped_content = "\n".join(paragraphs)
+    return wrapped_content

txt2ebook-0.1.108/src/txt2ebook/subcommands/parse.py

@@ -0,0 +1,86 @@
+# Copyright (C) 2021,2022,2023,2024 Kian-Meng Ang
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+#
+# 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/>.
+
+"""Env subcommand."""
+
+import argparse
+import logging
+import sys
+
+from bs4 import UnicodeDammit
+from langdetect import detect
+
+from txt2ebook.exceptions import EmptyFileError
+from txt2ebook.parser import Parser
+
+logger = logging.getLogger(__name__)
+
+
+def build_subparser(subparsers) -> None:
+    """Build the subparser."""
+    parse_parser = subparsers.add_parser(
+        "parse", help="parse and validate the txt file"
+    )
+
+    parse_parser.add_argument(
+        "input_file",
+        nargs=None if sys.stdin.isatty() else "?",  # type: ignore
+        type=argparse.FileType("rb"),
+        default=None if sys.stdin.isatty() else sys.stdin,
+        help="source text filename",
+        metavar="TXT_FILENAME",
+    )
+
+    parse_parser.set_defaults(func=run)
+
+
+def run(args: argparse.Namespace) -> None:
+    """Run env subcommand.
+
+    Args:
+        args (argparse.Namespace): Config from command line arguments
+
+    Returns:
+        None
+    """
+    logger.info("Parsing txt file: %s", args.input_file.name)
+
+    unicode = UnicodeDammit(args.input_file.read())
+    logger.info("Detect encoding : %s", unicode.original_encoding)
+
+    content = unicode.unicode_markup
+    if not content:
+        raise EmptyFileError(
+            f"Empty file content in {args.input_file.name}"
+        )
+
+    args_language = args.language
+    detect_language = detect(content)
+    args.language = args_language or detect_language
+    logger.info("args language: %s", args_language)
+    logger.info("Detect language: %s", detect_language)
+
+    if args_language and args_language != detect_language:
+        logger.warning(
+            "args (%s) and detect (%s) language mismatch",
+            args_language,
+            detect_language,
+        )
+
+    parser = Parser(content, args)
+    book = parser.parse()
+
+    if args.debug:
+        book.debug(args.verbose)

{txt2ebook-0.1.107 → txt2ebook-0.1.108}/src/txt2ebook/tokenizer.py

@@ -168,7 +168,9 @@ class Tokenizer:
             return []
 
         metadata = match[1].split("\n")
-        logger.debug("Metadata: %s", metadata)
+        for metadata_field in metadata:
+            logger.info("Metadata: %s", metadata_field)
+
         return metadata
 
     def _tokenize_content(self) -> None: