txt2ebook 0.1.113__tar.gz → 0.1.117__tar.gz

{txt2ebook-0.1.113 → txt2ebook-0.1.117}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: txt2ebook
-Version: 0.1.113
+Version: 0.1.117
 Summary: CLI tool to convert txt file to ebook format
 Home-page: https://github.com/kianmeng/txt2ebook
 License: AGPL-3.0-or-later
@@ -20,6 +20,7 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Text Processing
 Classifier: Topic :: Text Processing :: Filters
 Classifier: Topic :: Text Processing :: General
@@ -37,7 +38,7 @@ Requires-Dist: pypandoc (>=1.11,<2.0)
 Requires-Dist: regex (>=2021.11.10,<2022.0.0)
 Requires-Dist: reportlab (>=4.0.0,<5.0.0)
 Requires-Dist: typing-extensions (>=4.5.0,<5.0.0)
-Requires-Dist: typst (>=0.10.0,<0.11.0)
+Requires-Dist: typst (>=0.12.0,<0.13.0)
 Project-URL: Repository, https://github.com/kianmeng/txt2ebook
 Description-Content-Type: text/markdown
 

{txt2ebook-0.1.113 → txt2ebook-0.1.117}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "txt2ebook"
-version = "0.1.113"
+version = "0.1.117"
 description = "CLI tool to convert txt file to ebook format"
 authors = ["Kian-Meng Ang <kianmeng@cpan.org>"]
 license = "AGPL-3.0-or-later"
@@ -20,6 +20,7 @@ classifiers = [
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
     "Topic :: Text Processing",
     "Topic :: Text Processing :: Filters",
     "Topic :: Text Processing :: General",
@@ -37,7 +38,7 @@ regex = "^2021.11.10"
 pypandoc = "^1.11"
 typing-extensions = "^4.5.0"
 reportlab = "^4.0.0"
-typst = "^0.10.0"
+typst = "^0.12.0"
 importlib-resources = "^6.1.1"
 pylatex = "^1.4.2"
 lxml = "^5.2.2"

{txt2ebook-0.1.113 → txt2ebook-0.1.117}/src/txt2ebook/__init__.py

@@ -20,9 +20,11 @@ import logging
 import platform
 import sys
 
+import langdetect
+
 logger = logging.getLogger(__name__)
 
-__version__ = "0.1.113"
+__version__ = "0.1.117"
 
 
 def setup_logger(config: argparse.Namespace) -> None:
@@ -69,3 +71,19 @@ def print_env() -> None:
         f"platform: {platform.platform()}",
         sep="\n",
     )
+
+
+def detect_and_expect_language(content: str, config_language: str) -> str:
+    """Detect and expect the language of the txt content."""
+    detect_language = langdetect.detect(content)
+    config_language = config_language or detect_language
+    logger.info("Config language: %s", config_language)
+    logger.info("Detect language: %s", detect_language)
+
+    if config_language and config_language != detect_language:
+        logger.warning(
+            "Config (%s) and detect (%s) language mismatch",
+            config_language,
+            detect_language,
+        )
+    return config_language

{txt2ebook-0.1.113 → txt2ebook-0.1.117}/src/txt2ebook/cli.py

@@ -21,18 +21,13 @@
 """
 
 import argparse
+import importlib
 import logging
+import pkgutil
 import sys
 from typing import Optional, Sequence
 
-import txt2ebook.subcommands.env
-import txt2ebook.subcommands.epub
-import txt2ebook.subcommands.gmi
-import txt2ebook.subcommands.massage
-import txt2ebook.subcommands.md
-import txt2ebook.subcommands.parse
-import txt2ebook.subcommands.pdf
-import txt2ebook.subcommands.tex
+import txt2ebook.subcommands
 from txt2ebook import __version__, setup_logger
 
 logger = logging.getLogger(__name__)
@@ -127,50 +122,6 @@ def build_parser(
         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",
@@ -190,16 +141,6 @@ def build_parser(
         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(
         "-ff",
         "--filename-format",
@@ -215,24 +156,6 @@ def build_parser(
         metavar="FILENAME_FORMAT",
     )
 
-    parser.add_argument(
-        "-op",
-        "--open",
-        default=False,
-        action="store_true",
-        dest="open",
-        help="open the generated file using default program",
-    )
-
-    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",
@@ -285,14 +208,17 @@ def build_parser(
     )
 
     subparsers = parser.add_subparsers(help="sub-command help")
-    txt2ebook.subcommands.parse.build_subparser(subparsers)
-    txt2ebook.subcommands.massage.build_subparser(subparsers)
-    txt2ebook.subcommands.epub.build_subparser(subparsers)
-    txt2ebook.subcommands.tex.build_subparser(subparsers)
-    txt2ebook.subcommands.pdf.build_subparser(subparsers)
-    txt2ebook.subcommands.md.build_subparser(subparsers)
-    txt2ebook.subcommands.gmi.build_subparser(subparsers)
-    txt2ebook.subcommands.env.build_subparser(subparsers)
+
+    iter_namespace = pkgutil.iter_modules(
+        txt2ebook.subcommands.__path__, txt2ebook.subcommands.__name__ + "."
+    )
+    subcommands = {
+        name: importlib.import_module(name)
+        for finder, name, ispkg
+        in iter_namespace
+    }
+    for subcommand in subcommands.values():
+        subcommand.build_subparser(subparsers)
 
     return parser
 

{txt2ebook-0.1.113 → txt2ebook-0.1.117}/src/txt2ebook/formats/typ.py

@@ -36,6 +36,11 @@ logger = logging.getLogger(__name__)
 class TypWriter(BaseWriter):
     """Module for writing ebook in Typst (typ) format."""
 
+    def __post_init__(self):
+        """Post init code."""
+        self.index_keywords = self.config.index_keyword + self.book.index
+        logger.debug("Index keywords: %s", self.index_keywords)
+
     def write(self) -> None:
         """Generate Typst files."""
         self._new_file()
@@ -61,7 +66,8 @@ class TypWriter(BaseWriter):
 
     def _to_typ(self) -> str:
         return (
-            self._to_metadata_typ()
+            self._include_packages()
+            + self._to_metadata_typ()
             + self._to_cover()
             + self._to_outline()
             + '#set page(numbering: "1")'
@@ -69,6 +75,15 @@ class TypWriter(BaseWriter):
             + "#counter(page).update(1)"
             + "\n"
             + self._to_body_txt()
+            + self._index_pages()
+        )
+
+    def _include_packages(self) -> str:
+        return textwrap.dedent(
+            """
+                #import "@preview/in-dexter:0.5.3": *
+
+        """
         )
 
     def _to_metadata_typ(self) -> str:
@@ -80,9 +95,10 @@ class TypWriter(BaseWriter):
           numbering: "1",
           number-align: right,
         )
+
         #show heading.where(
           level: 1
-        ): it => block(width: 100%)[
+        ): it => block(width: 100%, below: 1.5em)[
           #set align(center)
           #set text(16pt, weight: "regular")
           #smallcaps(it.body)
@@ -90,20 +106,30 @@ class TypWriter(BaseWriter):
 
         #show heading.where(
           level: 2
-        ): it => block(width: 100%)[
+        ): it => block(width: 100%, below: 1.5em)[
           #set align(center)
           #set text(14pt, weight: "regular")
           #smallcaps(it.body)
         ]
 
         #set par(
-          justify: true,
+          first-line-indent: 2em,
+          justify: true
         )
+
         #set text(
           font: "Noto Serif CJK SC",
           size: 12pt,
         )
 
+        #show outline.entry: it => {{
+          text(it, fill: red)
+        }}
+
+        #show link: it => {{
+          text(it, fill: red)
+        }}
+
         """
         )
 
@@ -111,7 +137,8 @@ class TypWriter(BaseWriter):
         return textwrap.dedent(
             f"""
             #set page(paper: "{self._get_pagesize()}", numbering: none)
-            #align(center, text(17pt)[{self.book.title}])
+            #align(center + horizon, text(17pt)[{self.book.title}])
+            #align(center + horizon, text(17pt)[{", ".join(self.book.authors)}])
             #pagebreak()
 
         """
@@ -122,7 +149,7 @@ class TypWriter(BaseWriter):
             textwrap.dedent(
                 f"""
             #set page(paper: "{self._get_pagesize()}", numbering: none)
-            #outline(title: [目录], indent: 2em,)
+            #outline(title: [目录], indent: 1em)
             #pagebreak()
             """
             )
@@ -157,14 +184,37 @@ class TypWriter(BaseWriter):
         return (
             f"{header} {chapter.title}"
             + self.config.paragraph_separator
-            + self.config.paragraph_separator.join(chapter.paragraphs)
-            + "#pagebreak()"
+            + self._process_paragraphs(chapter.paragraphs)
+            + "\n#pagebreak()\n"
         )
 
     def _to_volume_chapter_txt(self, volume, chapter) -> str:
         return (
             f"= {volume.title} {chapter.title}"
             + self.config.paragraph_separator
-            + self.config.paragraph_separator.join(chapter.paragraphs)
-            + "#pagebreak()"
+            + self._process_paragraphs(chapter.paragraphs)
+            + "\n#pagebreak()\n"
+        )
+
+    def _process_paragraphs(self, paragraphs) -> str:
+        pars = []
+        for paragraph in paragraphs:
+            par = paragraph.strip()
+            for keyword in self.index_keywords:
+                replace = rf"#index[{keyword}]#link(<index>)[{keyword}]"
+                par = par.replace(keyword, replace)
+            pars.append(par)
+
+        return self.config.paragraph_separator.join(pars)
+
+    def _index_pages(self) -> str:
+        return textwrap.dedent(
+            """
+            = 目录 <index>
+
+            #set text(size: 8pt)
+            #columns(3)[
+                #make-index(outlined: false, use-page-counter: false)
+            ]
+        """
         )

{txt2ebook-0.1.113 → txt2ebook-0.1.117}/src/txt2ebook/parser.py

@@ -231,7 +231,7 @@ class Parser:
         logger.info("Found or set tags: %s", repr(tags))
         logger.info("Found or set index: %s", repr(index))
 
-        if 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-0.1.113 → txt2ebook-0.1.117}/src/txt2ebook/subcommands/epub.py

@@ -79,6 +79,15 @@ def build_subparser(subparsers) -> None:
         help="generate each volume as separate page",
     )
 
+    epub_parser.add_argument(
+        "-op",
+        "--open",
+        default=False,
+        action="store_true",
+        dest="open",
+        help="open the generated file using default program",
+    )
+
 
 def run(args: argparse.Namespace) -> None:
     """Run epub subcommand.

{txt2ebook-0.1.113 → txt2ebook-0.1.117}/src/txt2ebook/subcommands/gmi.py

@@ -64,14 +64,22 @@ def build_subparser(subparsers) -> None:
     )
 
     gmi_parser.add_argument(
-        "-toc",
-        "--table-of-content",
+        "--toc",
         default=False,
-        action="store_true",
+        action=argparse.BooleanOptionalAction,
         dest="with_toc",
         help="add table of content",
     )
 
+    gmi_parser.add_argument(
+        "-op",
+        "--open",
+        default=False,
+        action="store_true",
+        dest="open",
+        help="open the generated file using default program",
+    )
+
 
 def run(args: argparse.Namespace) -> None:
     """Run md subcommand.

{txt2ebook-0.1.113 → txt2ebook-0.1.117}/src/txt2ebook/subcommands/massage.py

@@ -23,7 +23,10 @@ import cjkwrap
 import regex as re
 from bs4 import UnicodeDammit
 
+from txt2ebook import detect_and_expect_language
 from txt2ebook.exceptions import EmptyFileError
+from txt2ebook.formats.txt import TxtWriter
+from txt2ebook.parser import Parser
 from txt2ebook.zh_utils import zh_halfwidth_to_fullwidth
 
 logger = logging.getLogger(__name__)
@@ -44,6 +47,35 @@ def build_subparser(subparsers) -> None:
         metavar="TXT_FILENAME",
     )
 
+    massage_parser.add_argument(
+        "output_file",
+        nargs="?",
+        default=None,
+        help="converted ebook filename (default: 'TXT_FILENAME.txt')",
+        metavar="EBOOK_FILENAME",
+    )
+
+    massage_parser.add_argument(
+        "-sp",
+        "--split-volume-and-chapter",
+        default=False,
+        action="store_true",
+        dest="split_volume_and_chapter",
+        help=(
+            "split volume or chapter into separate file and "
+            "ignore the --overwrite option"
+        ),
+    )
+
+    massage_parser.add_argument(
+        "-ow",
+        "--overwrite",
+        default=False,
+        action="store_true",
+        dest="overwrite",
+        help="overwrite massaged TXT_FILENAME",
+    )
+
     massage_parser.add_argument(
         "-rd",
         "--regex-delete",
@@ -85,6 +117,15 @@ def build_subparser(subparsers) -> None:
         metavar="WIDTH",
     )
 
+    massage_parser.add_argument(
+        "-ss",
+        "--sort-volume-and-chapter",
+        default=False,
+        action="store_true",
+        dest="sort_volume_and_chapter",
+        help="short volume and chapter",
+    )
+
     massage_parser.set_defaults(func=run)
 
 
@@ -97,6 +138,21 @@ def run(args: argparse.Namespace) -> None:
     Returns:
         None
     """
+    massaged_txt = massage_txt(args)
+    args.language = detect_and_expect_language(massaged_txt, args.language)
+    args.with_toc = False
+    parser = Parser(massaged_txt, args)
+    book = parser.parse()
+
+    if args.debug:
+        book.debug(args.verbose)
+
+    writer = TxtWriter(book, args)
+    writer.write()
+
+
+def massage_txt(args: argparse.Namespace) -> str:
+    """Massage the text file."""
     logger.info("Parsing txt file: %s", args.input_file.name)
 
     unicode = UnicodeDammit(args.input_file.read())

{txt2ebook-0.1.113 → txt2ebook-0.1.117}/src/txt2ebook/subcommands/md.py

@@ -64,14 +64,22 @@ def build_subparser(subparsers) -> None:
     )
 
     md_parser.add_argument(
-        "-toc",
-        "--table-of-content",
+        "--toc",
         default=False,
-        action="store_true",
+        action=argparse.BooleanOptionalAction,
         dest="with_toc",
         help="add table of content",
     )
 
+    md_parser.add_argument(
+        "-op",
+        "--open",
+        default=False,
+        action="store_true",
+        dest="open",
+        help="open the generated file using default program",
+    )
+
 
 def run(args: argparse.Namespace) -> None:
     """Run md subcommand.

{txt2ebook-0.1.113 → txt2ebook-0.1.117}/src/txt2ebook/subcommands/pdf.py

@@ -62,9 +62,18 @@ def build_subparser(subparsers) -> None:
         metavar="PAGE_SIZE",
     )
 
+    pdf_parser.add_argument(
+        "-op",
+        "--open",
+        default=False,
+        action="store_true",
+        dest="open",
+        help="open the generated file using default program",
+    )
+
 
 def run(args: argparse.Namespace) -> None:
-    """Run md subcommand.
+    """Run pdf subcommand.
 
     Args:
         config (argparse.Namespace): Config from command line arguments

{txt2ebook-0.1.113 → txt2ebook-0.1.117}/src/txt2ebook/subcommands/tex.py

@@ -68,6 +68,15 @@ def build_subparser(subparsers) -> None:
 
     tex_parser.set_defaults(func=run)
 
+    tex_parser.add_argument(
+        "-op",
+        "--open",
+        default=False,
+        action="store_true",
+        dest="open",
+        help="open the generated file using default program",
+    )
+
 
 def run(args: argparse.Namespace) -> None:
     """Run tex subcommand.

txt2ebook-0.1.117/src/txt2ebook/subcommands/typ.py

@@ -0,0 +1,103 @@
+# 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/>.
+
+"""md subcommand."""
+
+import argparse
+import logging
+import sys
+
+from txt2ebook.subcommands.parse import run as parse_txt
+from txt2ebook.formats.typ import TypWriter
+from txt2ebook.formats import PAGE_SIZES
+
+
+logger = logging.getLogger(__name__)
+
+
+def build_subparser(subparsers) -> None:
+    """Build the subparser."""
+    typ_parser = subparsers.add_parser(
+        "typ", help="generate ebook in Typst format"
+    )
+
+    typ_parser.set_defaults(func=run)
+
+    typ_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",
+    )
+
+    typ_parser.add_argument(
+        "output_file",
+        nargs="?",
+        default=None,
+        help="converted ebook filename (default: 'TXT_FILENAME.typ')",
+        metavar="EBOOK_FILENAME",
+    )
+
+    typ_parser.add_argument(
+        "-pz",
+        "--page-size",
+        dest="page_size",
+        default="a5",
+        choices=PAGE_SIZES,
+        help="page size of the ebook (default: '%(default)s')",
+        metavar="PAGE_SIZE",
+    )
+
+    typ_parser.add_argument(
+        "--toc",
+        default=False,
+        action=argparse.BooleanOptionalAction,
+        dest="with_toc",
+        help="add table of content",
+    )
+
+    typ_parser.add_argument(
+        "-ik",
+        "--index-keyword",
+        dest="index_keyword",
+        action="append",
+        default=[],
+        help="keyword to index (default: '%(default)s')",
+    )
+
+    typ_parser.add_argument(
+        "-op",
+        "--open",
+        default=False,
+        action="store_true",
+        dest="open",
+        help="open the generated file using default program",
+    )
+
+
+def run(args: argparse.Namespace) -> None:
+    """Run typ subcommand.
+
+    Args:
+        config (argparse.Namespace): Config from command line arguments
+
+    Returns:
+        None
+    """
+    book = parse_txt(args)
+    writer = TypWriter(book, args)
+    writer.write()

{txt2ebook-0.1.113 → txt2ebook-0.1.117}/src/txt2ebook/tokenizer.py

@@ -62,11 +62,7 @@ class Tokenizer:
         """Set the constructor for the Tokenizer."""
         self.raw_content = raw_content
         self.config = config
-
-        if self.config.fullwidth:
-            self.metadata_marker = "－－－"
-        else:
-            self.metadata_marker = "---"
+        self.metadata_marker = "---"
 
         config_lang = config.language.replace("-", "_")
         self.langconf = import_module(f"txt2ebook.languages.{config_lang}")
@@ -118,11 +114,11 @@ class Tokenizer:
         """Tokenize the metadata of the book."""
         for line in self._extract_metadata():
             re_title = f"^{self.langconf.DEFAULT_RE_TITLE}"
-            if self.config.re_title:
+            if hasattr(self.config, "re_title") and self.config.re_title:
                 re_title = self.config.re_title[0]
 
             re_author = f"{self.langconf.DEFAULT_RE_AUTHOR}"
-            if self.config.re_author:
+            if hasattr(self.config, "re_author") and self.config.re_author:
                 re_author = self.config.re_author[0]
 
             token_type_regex_map = [
@@ -209,7 +205,7 @@ class Tokenizer:
             rf"^{self.langconf.DEFAULT_RE_VOLUME}\s*"
             rf"{self.langconf.DEFAULT_RE_CHAPTER}"
         )
-        if 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)
@@ -232,7 +228,7 @@ class Tokenizer:
         token = None
 
         re_volume = rf"^{self.langconf.DEFAULT_RE_VOLUME}$"
-        if self.config.re_volume:
+        if hasattr(self.config, "re_volume") and self.config.re_volume:
             re_volume = "(" + "|".join(self.config.re_volume) + ")"
 
         match = re.search(re_volume, line)
@@ -248,7 +244,7 @@ class Tokenizer:
         token = None
 
         re_chapter = rf"^{self.langconf.DEFAULT_RE_CHAPTER}$"
-        if self.config.re_chapter:
+        if hasattr(self.config, "re_chapter") and self.config.re_chapter:
             re_chapter = "(" + "|".join(self.config.re_chapter) + ")"
 
         match = re.search(re_chapter, line)

{txt2ebook-0.1.113 → txt2ebook-0.1.117}/src/txt2ebook/txt2ebook.py

@@ -29,9 +29,8 @@ import time
 from typing import Optional, Sequence
 
 from bs4 import UnicodeDammit
-from langdetect import detect
 
-from txt2ebook import __version__, print_env, setup_logger
+from txt2ebook import __version__, print_env, setup_logger, detect_and_expect_language
 from txt2ebook.exceptions import EmptyFileError
 from txt2ebook.formats import (
     EBOOK_FORMATS,
@@ -62,19 +61,7 @@ def run(config: argparse.Namespace) -> None:
                 f"Empty file content in {config.input_file.name}"
             )
 
-        config_language = config.language
-        detect_language = detect(content)
-        config.language = config_language or detect_language
-        logger.info("Config language: %s", config_language)
-        logger.info("Detect language: %s", detect_language)
-
-        if config_language and config_language != detect_language:
-            logger.warning(
-                "Config (%s) and detect (%s) language mismatch",
-                config_language,
-                detect_language,
-            )
-
+        config.language = detect_and_expect_language(content, config.language)
         parser = Parser(content, config)
         book = parser.parse()