txt2ebook 0.1.118__py3-none-any.whl → 0.1.119__py3-none-any.whl

txt2ebook/__init__.py

@@ -24,29 +24,30 @@ import langdetect
 
 logger = logging.getLogger(__name__)
 
-__version__ = "0.1.118"
+__version__ = "0.1.119"
 
 
 def setup_logger(config: argparse.Namespace) -> None:
-    """Configure the global logger.
+    """Sets up logging configuration based on command-line arguments.
 
     Args:
-        config(argparse.Namespace): Config that contains arguments
+        config (argparse.Namespace): Namespace containing parsed arguments.
     """
     if config.quiet:
         logging.disable(logging.NOTSET)
-    else:
-        logformat = {
-            True: "%(levelname)5s: %(message)s",
-            False: "%(message)s",
-        }
-
-        logging.basicConfig(
-            level=config.debug and logging.DEBUG or logging.INFO,
-            stream=sys.stdout,
-            format=logformat[config.debug],
-            datefmt="%Y-%m-%d %H:%M:%S",
-        )
+        return
+
+    level = logging.DEBUG if config.debug else logging.INFO
+    format_string = (
+        "%(levelname)5s: %(message)s" if config.debug else "%(message)s"
+    )
+
+    logging.basicConfig(
+        level=level,
+        format=format_string,
+        stream=sys.stdout,
+        datefmt="%Y-%m-%d %H:%M:%S",
+    )
 
 
 def log_or_raise_on_warning(msg: str, raise_on_warning: bool = False) -> None:

txt2ebook/parser.py

@@ -65,7 +65,7 @@ class Parser:
             translators=translators,
             tags=tags,
             index=index,
-            cover=self.config.cover,
+            cover=getattr(self.config, "cover", ""),
             raw_content=self.raw_content,
             toc=toc,
         )
@@ -231,7 +231,10 @@ class Parser:
         logger.info("Found or set tags: %s", repr(tags))
         logger.info("Found or set index: %s", repr(index))
 
-        if hasattr(self.config, "sort_volume_and_chapter") and self.config.sort_volume_and_chapter:
+        if (
+            hasattr(self.config, "sort_volume_and_chapter")
+            and self.config.sort_volume_and_chapter
+        ):
             self.sort_volume_and_chapter(toc)
 
         return (book_title, authors, translators, tags, index, toc)

txt2ebook/subcommands/__init__.py

@@ -25,8 +25,7 @@ def build_subparser(subparsers):
 
     subcommands = {
         name: importlib.import_module(name)
-        for finder, name, ispkg
-        in iter_namespace
+        for finder, name, ispkg in iter_namespace
     }
 
     for subcommand in subcommands.values():

txt2ebook/subcommands/env.py

@@ -44,9 +44,9 @@ def run(_args: argparse.Namespace) -> None:
         None
     """
     sys_version = sys.version.replace("\n", "")
-    print(
+    env = [
         f"txt2ebook: {__version__}",
         f"python: {sys_version}",
         f"platform: {platform.platform()}",
-        sep="\n",
-    )
+    ]
+    print(*env, sep="\n")

txt2ebook/subcommands/massage.py

@@ -18,6 +18,7 @@
 import argparse
 import logging
 import sys
+from importlib import import_module
 
 import cjkwrap
 import regex as re
@@ -26,8 +27,9 @@ 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
+from txt2ebook.zh_utils import zh_halfwidth_to_fullwidth, zh_words_to_numbers
 
 logger = logging.getLogger(__name__)
 
@@ -55,6 +57,15 @@ def build_subparser(subparsers) -> None:
         metavar="EBOOK_FILENAME",
     )
 
+    massage_parser.add_argument(
+        "-hn",
+        "--header-number",
+        default=False,
+        action="store_true",
+        dest="header_number",
+        help="convert section header from words to numbers",
+    )
+
     massage_parser.add_argument(
         "-sp",
         "--split-volume-and-chapter",
@@ -126,6 +137,29 @@ def build_subparser(subparsers) -> None:
         help="short volume and chapter",
     )
 
+    massage_parser.add_argument(
+        "-op",
+        "--open",
+        default=False,
+        action="store_true",
+        dest="open",
+        help="open the generated file using default program",
+    )
+
+    massage_parser.add_argument(
+        "-ff",
+        "--filename-format",
+        dest="filename_format",
+        type=int,
+        default=None,
+        help=(
+            "the output filename format "
+            "(default: TXT_FILENAME [EBOOK_FILENAME])\n"
+            "1 - title_authors.EBOOK_EXTENSION\n"
+            "2 - authors_title.EBOOK_EXTENSION"
+        ),
+    )
+
     massage_parser.set_defaults(func=run)
 
 
@@ -147,10 +181,75 @@ def run(args: argparse.Namespace) -> None:
     if args.debug:
         book.debug(args.verbose)
 
+    if args.header_number:
+        book = header_number(args, book)
+
     writer = TxtWriter(book, args)
     writer.write()
 
 
+def header_number(args: argparse.Namespace, book: Book) -> Book:
+    """Convert header number from words to numbers."""
+    stats = book.stats()
+
+    seq_lengths = {
+        "Volume": len(str(stats.get("Volume", 2))),
+        "Chapter": len(str(stats.get("Chapter", 2))),
+    }
+
+    for toc_item in book.toc:
+        toc_type = type(toc_item).__name__
+        if toc_type in seq_lengths:
+            toc_item.title = words_to_nums(
+                args, toc_item.title, seq_lengths[toc_type]
+            )
+
+    return book
+
+
+def words_to_nums(args: argparse.Namespace, words: str, length: int) -> str:
+    """Convert header from words to numbers.
+
+    For example, `第一百零八章` becomes `第108章`.
+
+    Args:
+        words(str): The line that contains section header in words.
+        length(int): The number of left zero-padding to prepend.
+
+    Returns:
+        str: The formatted section header.
+    """
+    config_lang = args.language.replace("-", "_")
+    langconf = import_module(f"txt2ebook.languages.{config_lang}")
+
+    if args.language not in ("zh-cn", "zh-tw"):
+        return words
+
+    # left pad the section number if found as halfwidth integer
+    match = re.match(rf"第([{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([{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"))
+
+    replaced_words = zh_words_to_numbers(words, length=length)
+
+    if args.fullwidth:
+        replaced_words = zh_halfwidth_to_fullwidth(replaced_words)
+
+    logger.debug(
+        "Convert header to numbers: %s -> %s",
+        words[:10],
+        replaced_words[:10],
+    )
+    return replaced_words
+
+
 def massage_txt(args: argparse.Namespace) -> str:
     """Massage the text file."""
     logger.info("Parsing txt file: %s", args.input_file.name)
@@ -160,9 +259,7 @@ def massage_txt(args: argparse.Namespace) -> str:
 
     content = unicode.unicode_markup
     if not content:
-        raise EmptyFileError(
-            f"Empty file content in {args.input_file.name}"
-        )
+        raise EmptyFileError(f"Empty file content in {args.input_file.name}")
 
     content = to_unix_newline(content)
 

txt2ebook/subcommands/parse.py

@@ -64,9 +64,7 @@ def run(args: argparse.Namespace) -> Book:
 
     content = unicode.unicode_markup
     if not content:
-        raise EmptyFileError(
-            f"Empty file content in {args.input_file.name}"
-        )
+        raise EmptyFileError(f"Empty file content in {args.input_file.name}")
 
     args_language = args.language
     detect_language = detect(content)

txt2ebook/tokenizer.py

@@ -205,7 +205,10 @@ class Tokenizer:
             rf"^{self.langconf.DEFAULT_RE_VOLUME}\s*"
             rf"{self.langconf.DEFAULT_RE_CHAPTER}"
         )
-        if hasattr(self.config, "re_volume_chapter") and self.config.re_volume_chapter:
+        if (
+            hasattr(self.config, "re_volume_chapter")
+            and self.config.re_volume_chapter
+        ):
             re_volume_chapter = self.config.re_volume_chapter[0]
 
         match = re.search(re_volume_chapter, line)

txt2ebook/txt2ebook.py

@@ -30,7 +30,12 @@ from typing import Optional, Sequence
 
 from bs4 import UnicodeDammit
 
-from txt2ebook import __version__, print_env, setup_logger, detect_and_expect_language
+from txt2ebook import (
+    __version__,
+    print_env,
+    setup_logger,
+    detect_and_expect_language,
+)
 from txt2ebook.exceptions import EmptyFileError
 from txt2ebook.formats import (
     EBOOK_FORMATS,

{txt2ebook-0.1.118.dist-info → txt2ebook-0.1.119.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: txt2ebook
-Version: 0.1.118
+Version: 0.1.119
 Summary: CLI tool to convert txt file to ebook format
 Home-page: https://github.com/kianmeng/txt2ebook
 License: AGPL-3.0-or-later

{txt2ebook-0.1.118.dist-info → txt2ebook-0.1.119.dist-info}/RECORD

@@ -1,4 +1,4 @@
-txt2ebook/__init__.py,sha256=r5aWMH49Q1ILOROsS6PzTWiGcLRvqOU9swMs1vm6usE,2681
+txt2ebook/__init__.py,sha256=iohYWQYl2xqJZNU_hSkVkfs-JeUr5IMRQzAiLUxlcEA,2701
 txt2ebook/__main__.py,sha256=gMLvgpqc_BL4cBqNe0vqErRF5dlJPAbvqu1zndcAHYI,850
 txt2ebook/cli.py,sha256=8yrYmixLbQCwAwdd_u0A3SSHDxIEZLI04lg53Ec3XwY,5622
 txt2ebook/exceptions.py,sha256=b2HDsXdqweLJbvSJEGt48nxvGkZq20SfYezSjwp77JU,842
@@ -32,22 +32,22 @@ txt2ebook/models/__init__.py,sha256=8_k1oI_PnPMekhdZCXiTtg5WghdR6fugQEHJHsy1-Ds,
 txt2ebook/models/book.py,sha256=Q4EzFFAGigz4MPSM9Vu_F-JxNOWjm82469Vy8-vq-pw,2758
 txt2ebook/models/chapter.py,sha256=buECAklNQgM3tDehzyVO9YfA_F0iXyLq2PaMZGV_Zaw,1681
 txt2ebook/models/volume.py,sha256=HyT4XO9yZ8d0PgZVfMMyAYUDFv58RrUmsSFNNmU-sHY,1592
-txt2ebook/parser.py,sha256=mrkpwyPwnFjrJUCQ7ghTgWmVJ0Q4m9R93MIM-tcqm08,8759
-txt2ebook/subcommands/__init__.py,sha256=KB4AH5-rgwagjIEBgPThyASDESD61nYWrGujZ2qYVzE,1149
-txt2ebook/subcommands/env.py,sha256=26wcAhEbjKfWYeNiIsjm9TTaBUyNDYx1MYUtV2ZFkmg,1481
+txt2ebook/parser.py,sha256=XlVjCKSUdAPKvp2655xWwHMOnpA8Qhe6ysExxdl8_ss,8811
+txt2ebook/subcommands/__init__.py,sha256=RU5YLwFz_SLrFpMz8vSYU6dwco3ZGe97zSVwFl1fMp4,1141
+txt2ebook/subcommands/env.py,sha256=nY7mmBkV2y1WonwUpJZAAZ141aeUCUtPZRACk18WoaY,1490
 txt2ebook/subcommands/epub.py,sha256=SdU4NYCNgGbioe-6Je88gvQbycIQDa4sPcvlnUvSOrY,3194
 txt2ebook/subcommands/gmi.py,sha256=l_YaxXwdp9L8h2xu2bTNPcY5hOGp6sJAEE9E1zuL1rc,3008
-txt2ebook/subcommands/massage.py,sha256=NkXW95MkwVyKPm1NMV8cekPAQ9NJQx3DGAGgpsRj5MY,7249
+txt2ebook/subcommands/massage.py,sha256=VB31ZKAKIprK6ccigpmHr87LTNjgHxlXxYvbhy7Zfds,10187
 txt2ebook/subcommands/md.py,sha256=MF74qdG7aHDRRI0XZYGlZdyMz07HKDQ7-xSe_dhAbsU,3019
-txt2ebook/subcommands/parse.py,sha256=BpEHs-gFYbJK1-50FPUX_3INfuxkgL5Glgpd3IBdJfs,2730
+txt2ebook/subcommands/parse.py,sha256=nklsxk_S2iswPWKlqa_azbjQOi5PHx8BwMuXV5yCOCs,2708
 txt2ebook/subcommands/pdf.py,sha256=SVsFz3oW4RDLM51O7G7Y8PqoTNoKOSEYMqDfak6DDgg,2976
 txt2ebook/subcommands/tex.py,sha256=TEOazBTfFlE1-eW1oyG1g_IE8hXYZUvKbmH3sBAFMHo,3126
 txt2ebook/subcommands/typ.py,sha256=l5CKeHIrnGHRMvjowXr3mT5WgWEHTQc34nJYgtzGKJw,3370
-txt2ebook/tokenizer.py,sha256=785qIUg1WybCUtNG7r_m3zZv0P0DlSQhlH_TEVyrdbo,9554
-txt2ebook/txt2ebook.py,sha256=ZP-5RxZcKasoowjuJjUR1yEBzHqekOBPruGvyj47sKg,13539
+txt2ebook/tokenizer.py,sha256=KJud1GAZIzeZtPWjAKc78q675pOfvIhBQYqOTmkfJm8,9590
+txt2ebook/txt2ebook.py,sha256=zNgxSmvEPpw7iiOq4gf9K5jsrJm0BqNQGM3MSAYh0F0,13560
 txt2ebook/zh_utils.py,sha256=EgKVbwqYGaTGswQUGcOCeSfRelzwkAb9WWY9TrsX1x4,4882
-txt2ebook-0.1.118.dist-info/LICENSE.md,sha256=tGtFDwxWTjuR9syrJoSv1Hiffd2u8Tu8cYClfrXS_YU,31956
-txt2ebook-0.1.118.dist-info/METADATA,sha256=F65ktavW0mkRmWr4H-dDCw7lEcRdffdsvv076ibQ6YM,7845
-txt2ebook-0.1.118.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-txt2ebook-0.1.118.dist-info/entry_points.txt,sha256=JLW3Iv7eUyABlQeUFiUWQhLKfRdnB9o5SIcNlneGR0Q,77
-txt2ebook-0.1.118.dist-info/RECORD,,
+txt2ebook-0.1.119.dist-info/LICENSE.md,sha256=tGtFDwxWTjuR9syrJoSv1Hiffd2u8Tu8cYClfrXS_YU,31956
+txt2ebook-0.1.119.dist-info/METADATA,sha256=5vwCS_b0PjoI37CgdjvrtwKt5fas1hsvuPerYtNscRU,7845
+txt2ebook-0.1.119.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+txt2ebook-0.1.119.dist-info/entry_points.txt,sha256=JLW3Iv7eUyABlQeUFiUWQhLKfRdnB9o5SIcNlneGR0Q,77
+txt2ebook-0.1.119.dist-info/RECORD,,