txt2ebook 0.1.123__tar.gz → 0.1.125__tar.gz

{txt2ebook-0.1.123 → txt2ebook-0.1.125}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: txt2ebook
-Version: 0.1.123
+Version: 0.1.125
 Summary: CLI tool to convert txt file to ebook format
 Home-page: https://github.com/kianmeng/txt2ebook
 License: AGPL-3.0-or-later

{txt2ebook-0.1.123 → txt2ebook-0.1.125}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "txt2ebook"
-version = "0.1.123"
+version = "0.1.125"
 description = "CLI tool to convert txt file to ebook format"
 authors = ["Kian-Meng Ang <kianmeng@cpan.org>"]
 license = "AGPL-3.0-or-later"
@@ -64,7 +64,6 @@ pytest-cov = "^5.0.0"
 pytest-randomly = "^3.15.0"
 pytest-xdist = "^3.6.1"
 pre-commit = "~2.20"
-pybabel = "^0.0.0.dev0"
 sphinx = "^7.3.7"
 myst-parser = "^3.0.1"
 sphinx-copybutton = "^0.5.2"

{txt2ebook-0.1.123 → txt2ebook-0.1.125}/src/txt2ebook/__init__.py

@@ -24,7 +24,7 @@ import langdetect
 
 logger = logging.getLogger(__name__)
 
-__version__ = "0.1.123"
+__version__ = "0.1.125"
 
 
 def setup_logger(config: argparse.Namespace) -> None:

{txt2ebook-0.1.123 → txt2ebook-0.1.125}/src/txt2ebook/subcommands/massage.py

@@ -66,6 +66,25 @@ def build_subparser(subparsers) -> None:
         help="convert section header from words to numbers",
     )
 
+    massage_parser.add_argument(
+        "-fw",
+        "--fullwidth",
+        default=False,
+        action="store_true",
+        dest="fullwidth",
+        help="use fullwidth character (only for zh-cn and zh-tw)",
+    )
+
+    massage_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",
+    )
+
     massage_parser.add_argument(
         "-sp",
         "--split-volume-and-chapter",
@@ -137,6 +156,15 @@ def build_subparser(subparsers) -> None:
         help="short volume and chapter",
     )
 
+    massage_parser.add_argument(
+        "-sn",
+        "--single-newline",
+        default=False,
+        action="store_true",
+        dest="single_newline",
+        help="format paragraph by single newline",
+    )
+
     massage_parser.add_argument(
         "-op",
         "--open",
@@ -263,23 +291,28 @@ def massage_txt(args: argparse.Namespace) -> str:
 
     content = to_unix_newline(content)
 
+    (metadata, body) = extract_metadata_and_body(args, 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)
+        body = zh_halfwidth_to_fullwidth(body)
 
     if args.re_delete:
-        content = do_delete_regex(args, content)
+        body = do_delete_regex(args, body)
 
     if args.re_replace:
-        content = do_replace_regex(args, content)
+        body = do_replace_regex(args, body)
 
     if args.re_delete_line:
-        content = do_delete_line_regex(args, content)
+        body = do_delete_line_regex(args, body)
+
+    if args.single_newline:
+        body = do_single_newline(args, body)
 
     if args.width:
-        content = do_wrapping(args, content)
+        body = do_wrapping(args, body)
 
-    return content
+    return f"{metadata}\n\n{body}"
 
 
 def to_unix_newline(content: str) -> str:
@@ -349,6 +382,38 @@ def do_delete_line_regex(args, content: str) -> str:
     return content
 
 
+def extract_metadata_and_body(_args, content: str) -> tuple:
+    """Extract the metadata and body.
+
+    Args:
+        content (str): The formatted book content.
+
+    Returns:
+        tuple: The metadata and body content.
+    """
+    metadata = ""
+    body = ""
+    match = re.search(r"---(.*?)---", content, re.DOTALL)
+    if match:
+        metadata = match.group(0).strip()
+        body = content.replace(metadata, "", 1)
+
+    return (metadata, body)
+
+
+def do_single_newline(args, content: str) -> str:
+    """Set single newline.
+
+    Args:
+        content (str): The formatted book content.
+
+    Returns:
+        str: The formatted book content.
+    """
+    modified_content = re.sub(r"\n+", "\n\n", content)
+    return modified_content
+
+
 def do_wrapping(args, content: str) -> str:
     """Wrap or fill CJK text.
 

{txt2ebook-0.1.123 → txt2ebook-0.1.125}/src/txt2ebook/tokenizer.py

@@ -169,7 +169,9 @@ class Tokenizer:
 
         return metadata
 
+
     def _tokenize_content(self) -> None:
+        # TODO: split by metadata and content
         content = self.raw_content.split(f"{self.metadata_marker}\n\n")[1]
         content = content.strip(self.config.paragraph_separator)
         lines = content.split(self.config.paragraph_separator)