txt2ebook 0.1.43__py3-none-any.whl → 0.1.45__py3-none-any.whl

CHANGELOG.md

@@ -7,6 +7,42 @@ and this project adheres to [0-based versioning](https://0ver.org/).
 
 ## [Unreleased]
 
+## v0.1.45 (2023-07-23)
+
+### Added
+
+- Add `-of` or `--output-folder` to set a default `output` folder to prevent
+  clutter
+
+### Changed
+
+- Rename and standardize extra `tox` environment names
+- Refactor and optimize tokenizing metadata header of a source `txt` file
+- Force all source text file to follow a YAML-inspired metadata header
+- Parse and include translators into metadata of a book
+
+### Fixed
+
+- Fix missing dashes in metadata header when exporting `txt` format
+- Fix missing translator field in metadata for `md` and `gmi` format
+- Refactor all toc markups for `md`, `gmi`, and `txt` format
+
+## v0.1.44 (2023-07-16)
+
+### Added
+
+- Add test fixture with metadata
+
+### Changed
+
+- Update `pyenv` installation steps in contributing doc
+- Use active virtualenvs in `poetry` in contributing doc
+
+### Fixed
+
+- Fix not using book title as output file name when input source from
+  redirection or piping
+
 ## v0.1.43 (2023-07-09)
 
 ### Added

CONTRIBUTING.md

@@ -11,10 +11,19 @@ cd txt2ebook
 
 To set up different Python environments, we need to install all supported
 Python version using <https://github.com/pyenv/pyenv>. Once you've installed
-Pyenv, run the command below:
+Pyenv, install these additional Pyenv plugins:
 
 ```console
+git clone https://github.com/pyenv/pyenv-doctor.git "$(pyenv root)/plugins/pyenv-doctor"
+pyenv doctor
+
+git clone https://github.com/pyenv/pyenv-update.git $(pyenv root)/plugins/pyenv-update
 pyenv update
+```
+
+Run the command below to install all Python versions:
+
+```console
 pyenv install $(cat .python-version)
 ```
 
@@ -24,6 +33,7 @@ Setting up development environment and install dependencies:
 python -m pip install --upgrade pip poetry
 poetry install
 poetry check
+poetry config virtualenvs.prefer-active-python true
 ```
 
 Spawn a shell in virtual environment for your development:
@@ -38,15 +48,15 @@ Show all available tox tasks:
 $ tox -av
 ...
 default environments:
-py38    -> testing against python3.8
-py39    -> testing against python3.9
-py310   -> testing against python3.10
-py311   -> testing against python3.11
+py38  -> testing against python3.8
+py39  -> testing against python3.9
+py310 -> testing against python3.10
+py311 -> testing against python3.11
 
 additional environments:
-cover   -> generate code coverage report in html
-doc     -> generate sphinx documentation in html
-gettext -> update pot/po/mo files
+cov   -> generate code coverage report in html
+doc   -> generate sphinx documentation in html
+pot   -> update translations (pot/po/mo) files
 ```
 
 To run specific test:

txt2ebook/__init__.py

@@ -21,7 +21,7 @@ import sys
 
 logger = logging.getLogger(__name__)
 
-__version__ = "0.1.43"
+__version__ = "0.1.45"
 
 
 def setup_logger(config: argparse.Namespace) -> None:

txt2ebook/formats/base.py

@@ -25,7 +25,7 @@ from pathlib import Path
 from typing import Any
 
 from txt2ebook.helpers import lower_underscore
-from txt2ebook.models import Book
+from txt2ebook.models import Book, Chapter, Volume
 
 logger = logging.getLogger(__name__)
 
@@ -79,8 +79,6 @@ class BaseWriter(ABC):
         if self.config.filename_format:
             filename = self.book.filename_format(self.config.filename_format)
         else:
-            filename = "default"
-
             if self.output_file:
                 filename = str(self.output_file)
             elif isinstance(
@@ -88,14 +86,50 @@ class BaseWriter(ABC):
             ):
                 if self.input_file.name != "<stdin>":
                     filename = self.input_file.name
-            elif self.book.title:
-                filename = self.book.title
+                # input from redirection or piping
+                elif self.book.title:
+                    filename = self.book.title
+            else:
+                filename = "default"
 
         file = Path(filename)
-        return Path(file.parent, lower_underscore(file.stem)).with_suffix(
-            extension
+
+        # do not create to output folder when we explicit set the output path
+        # and file
+        if self.config.output_file:
+            return Path(file.parent, lower_underscore(file.stem)).with_suffix(
+                extension
+            )
+
+        return Path(
+            file.parent, self.config.output_folder, lower_underscore(file.stem)
+        ).with_suffix(extension)
+
+    def _to_metadata_txt(self) -> str:
+        metadata = [
+            self._("title:") + self.book.title,
+            self._("author:") + "，".join(self.book.authors),
+            self._("translator:") + "，".join(self.book.translators),
+            self._("tag:") + "，".join(self.book.tags),
+        ]
+        return (
+            "---\n" + "\n".join(metadata) + "\n---" + self.paragraph_separator
         )
 
+    def _to_toc(self, list_symbol, header_symbol="") -> str:
+        toc = ""
+        toc += header_symbol + self._("toc") + "\n"
+
+        for section in self.book.toc:
+            if isinstance(section, Volume):
+                toc += f"\n{list_symbol} " + section.title
+                for chapter in section.chapters:
+                    toc += f"\n  {list_symbol} " + chapter.title
+            if isinstance(section, Chapter):
+                toc += f"\n{list_symbol} " + section.title
+
+        return toc + self.paragraph_separator
+
     @abstractmethod
     def write(self) -> None:
         """Generate text files."""

txt2ebook/formats/epub.py

@@ -94,7 +94,7 @@ class EpubWriter(BaseWriter):
         output_filename = self._output_filename(".epub")
         output_filename.parent.mkdir(parents=True, exist_ok=True)
         epub.write_epub(output_filename, book, {})
-        logger.info("Generate EPUB file: %s", output_filename)
+        logger.info("Generate EPUB file: %s", output_filename.resolve())
 
     def _build_nav(self, book: epub.EpubBook) -> None:
         book.add_item(epub.EpubNcx())

txt2ebook/formats/gmi.py

@@ -62,7 +62,7 @@ class GmiWriter(BaseWriter):
             )
             logger.info("Creating %s", export_filename)
             with open(export_filename, "w", encoding="utf8") as file:
-                file.write(self._to_toc())
+                file.write(self._to_toc("*", "# "))
 
             sc_seq = 2
 
@@ -114,38 +114,16 @@ class GmiWriter(BaseWriter):
 
     def _new_file(self) -> None:
         new_filename = self._output_filename(".gmi")
+        new_filename.parent.mkdir(parents=True, exist_ok=True)
+
         with open(new_filename, "w", encoding="utf8") as file:
             logger.info("Generate GemText file: %s", new_filename.resolve())
             file.write(self._to_md())
 
     def _to_md(self) -> str:
-        toc = self._to_toc() if self.with_toc else ""
+        toc = self._to_toc("*", "# ") if self.with_toc else ""
         return self._to_metadata_txt() + toc + self._to_body_txt()
 
-    def _to_toc(self) -> str:
-        toc = []
-        toc.append("#" + self._("toc") + "\n")
-
-        for section in self.book.toc:
-            if isinstance(section, Volume):
-                toc.append(section.title)
-                for chapter in section.chapters:
-                    toc.append(chapter.title)
-            if isinstance(section, Chapter):
-                toc.append(section.title)
-
-        return "\n* ".join(toc) + self.paragraph_separator
-
-    def _to_metadata_txt(self) -> str:
-        metadata = [
-            self._("title:") + self.book.title,
-            self._("author:") + "，".join(self.book.authors),
-            self._("tag:") + "，".join(self.book.tags),
-        ]
-        return (
-            "---\n" + "\n".join(metadata) + "\n---" + self.paragraph_separator
-        )
-
     def _to_body_txt(self) -> str:
         content = []
         for section in self.book.toc:

txt2ebook/formats/md.py

@@ -61,7 +61,7 @@ class MdWriter(BaseWriter):
             )
             logger.info("Creating %s", export_filename)
             with open(export_filename, "w", encoding="utf8") as file:
-                file.write(self._to_toc())
+                file.write(self._to_toc("-", "# "))
 
             sc_seq = 2
 
@@ -113,38 +113,16 @@ class MdWriter(BaseWriter):
 
     def _new_file(self) -> None:
         new_filename = self._output_filename(".md")
+        new_filename.parent.mkdir(parents=True, exist_ok=True)
+
         with open(new_filename, "w", encoding="utf8") as file:
             logger.info("Generate Markdown file: %s", new_filename.resolve())
             file.write(self._to_md())
 
     def _to_md(self) -> str:
-        toc = self._to_toc() if self.with_toc else ""
+        toc = self._to_toc("-", "# ") if self.with_toc else ""
         return self._to_metadata_txt() + toc + self._to_body_txt()
 
-    def _to_toc(self) -> str:
-        toc = []
-        toc.append(self._("toc") + "\n")
-
-        for section in self.book.toc:
-            if isinstance(section, Volume):
-                toc.append(section.title)
-                for chapter in section.chapters:
-                    toc.append(chapter.title)
-            if isinstance(section, Chapter):
-                toc.append(section.title)
-
-        return "\n- ".join(toc) + self.paragraph_separator
-
-    def _to_metadata_txt(self) -> str:
-        metadata = [
-            self._("title:") + self.book.title,
-            self._("author:") + "，".join(self.book.authors),
-            self._("tag:") + "，".join(self.book.tags),
-        ]
-        return (
-            "---\n" + "\n".join(metadata) + "\n---" + self.paragraph_separator
-        )
-
     def _to_body_txt(self) -> str:
         content = []
         for section in self.book.toc:

txt2ebook/formats/txt.py

@@ -71,7 +71,7 @@ class TxtWriter(BaseWriter):
             )
             logger.info("Creating %s", export_filename)
             with open(export_filename, "w", encoding="utf8") as file:
-                file.write(self._to_toc())
+                file.write(self._to_toc("-"))
 
             sc_seq = 2
 
@@ -135,6 +135,8 @@ class TxtWriter(BaseWriter):
                 )
             )
 
+        new_filename.parent.mkdir(parents=True, exist_ok=True)
+
         with open(new_filename, "w", encoding="utf8") as file:
             file.write(self._to_txt())
             logger.info("Generate TXT file: %s", new_filename.resolve())
@@ -147,32 +149,9 @@ class TxtWriter(BaseWriter):
             logger.info("Overwrite txt file: %s", txt_filename.resolve())
 
     def _to_txt(self) -> str:
-        toc = self._to_toc() if self.with_toc else ""
+        toc = self._to_toc("-") if self.with_toc else ""
         return self._to_metadata_txt() + toc + self._to_body_txt()
 
-    def _to_toc(self) -> str:
-        toc = []
-        toc.append(self._("toc") + "\n")
-
-        for section in self.book.toc:
-            if isinstance(section, Volume):
-                toc.append(section.title)
-                for chapter in section.chapters:
-                    toc.append(chapter.title)
-            if isinstance(section, Chapter):
-                toc.append(section.title)
-
-        return "\n- ".join(toc) + self.paragraph_separator
-
-    def _to_metadata_txt(self) -> str:
-        metadata = [
-            self._("title:") + self.book.title,
-            self._("author:") + "，".join(self.book.authors),
-            self._("translator:") + "，".join(self.book.translators),
-            self._("tag:") + "，".join(self.book.tags),
-        ]
-        return "\n".join(metadata) + self.paragraph_separator
-
     def _to_body_txt(self) -> str:
         content = []
         for section in self.book.toc:

txt2ebook/languages/zh_cn.py

@@ -52,6 +52,7 @@ RE_CHAPTERS = [
 DEFAULT_RE_TITLE = r"书名：(.*)"
 DEFAULT_RE_AUTHOR = r"作者：(.*)"
 DEFAULT_RE_TAG = r"标签：(.*)"
+DEFAULT_RE_TRANSLATOR = r"翻译：(.*)"
 DEFAULT_RE_VOLUME = "(" + "|".join(RE_VOLUMES) + ")"
 DEFAULT_RE_CHAPTER = "(" + "|".join(RE_CHAPTERS) + ")"
 

txt2ebook/locales/en/LC_MESSAGES/txt2ebook.po

@@ -5,7 +5,7 @@
 msgid ""
 msgstr ""
 "Project-Id-Version: \n"
-"POT-Creation-Date: 2023-07-09 17:44+0800\n"
+"POT-Creation-Date: 2023-07-22 20:57+0800\n"
 "PO-Revision-Date: 2023-06-17 00:06+0800\n"
 "Last-Translator: \n"
 "Language-Team: \n"
@@ -16,37 +16,33 @@ msgstr ""
 "Generated-By: pygettext.py 1.5\n"
 "X-Generator: Poedit 3.2.2\n"
 
-#: src/txt2ebook/formats/epub.py:142
-msgid "cover"
-msgstr "Cover"
-
-#: src/txt2ebook/formats/gmi.py:46 src/txt2ebook/formats/md.py:45
-#: src/txt2ebook/formats/txt.py:55
-msgid "metadata"
-msgstr "Metadata"
-
-#: src/txt2ebook/formats/gmi.py:59 src/txt2ebook/formats/gmi.py:127
-#: src/txt2ebook/formats/md.py:58 src/txt2ebook/formats/md.py:126
-#: src/txt2ebook/formats/pdf.py:126 src/txt2ebook/formats/txt.py:68
-#: src/txt2ebook/formats/txt.py:155
-msgid "toc"
-msgstr "Table of Content"
-
-#: src/txt2ebook/formats/gmi.py:141 src/txt2ebook/formats/md.py:140
-#: src/txt2ebook/formats/txt.py:169
+#: src/txt2ebook/formats/base.py:110 src/txt2ebook/formats/md.py:128
 msgid "title:"
 msgstr "Title:"
 
-#: src/txt2ebook/formats/gmi.py:142 src/txt2ebook/formats/md.py:141
-#: src/txt2ebook/formats/txt.py:170
+#: src/txt2ebook/formats/base.py:111 src/txt2ebook/formats/md.py:129
 msgid "author:"
 msgstr "Author:"
 
-#: src/txt2ebook/formats/gmi.py:143 src/txt2ebook/formats/md.py:142
-#: src/txt2ebook/formats/txt.py:172
+#: src/txt2ebook/formats/base.py:112 src/txt2ebook/formats/md.py:130
+msgid "translator:"
+msgstr "Translator:"
+
+#: src/txt2ebook/formats/base.py:113 src/txt2ebook/formats/md.py:131
 msgid "tag:"
 msgstr "Tag:"
 
-#: src/txt2ebook/formats/txt.py:171
-msgid "translator:"
-msgstr "Translator:"
+#: src/txt2ebook/formats/base.py:121 src/txt2ebook/formats/gmi.py:59
+#: src/txt2ebook/formats/md.py:58 src/txt2ebook/formats/pdf.py:126
+#: src/txt2ebook/formats/txt.py:68
+msgid "toc"
+msgstr "Table of Content"
+
+#: src/txt2ebook/formats/epub.py:142
+msgid "cover"
+msgstr "Cover"
+
+#: src/txt2ebook/formats/gmi.py:46 src/txt2ebook/formats/md.py:45
+#: src/txt2ebook/formats/txt.py:55
+msgid "metadata"
+msgstr "Metadata"

txt2ebook/locales/txt2ebook.pot

@@ -5,7 +5,7 @@
 msgid ""
 msgstr ""
 "Project-Id-Version: PACKAGE VERSION\n"
-"POT-Creation-Date: 2023-07-09 17:44+0800\n"
+"POT-Creation-Date: 2023-07-22 20:57+0800\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
 "Language-Team: LANGUAGE <LL@li.org>\n"
@@ -15,38 +15,34 @@ msgstr ""
 "Generated-By: pygettext.py 1.5\n"
 
 
-#: src/txt2ebook/formats/epub.py:142
-msgid "cover"
+#: src/txt2ebook/formats/base.py:110 src/txt2ebook/formats/md.py:128
+msgid "title:"
 msgstr ""
 
-#: src/txt2ebook/formats/gmi.py:46 src/txt2ebook/formats/md.py:45
-#: src/txt2ebook/formats/txt.py:55
-msgid "metadata"
+#: src/txt2ebook/formats/base.py:111 src/txt2ebook/formats/md.py:129
+msgid "author:"
 msgstr ""
 
-#: src/txt2ebook/formats/gmi.py:59 src/txt2ebook/formats/gmi.py:127
-#: src/txt2ebook/formats/md.py:58 src/txt2ebook/formats/md.py:126
-#: src/txt2ebook/formats/pdf.py:126 src/txt2ebook/formats/txt.py:68
-#: src/txt2ebook/formats/txt.py:155
-msgid "toc"
+#: src/txt2ebook/formats/base.py:112 src/txt2ebook/formats/md.py:130
+msgid "translator:"
 msgstr ""
 
-#: src/txt2ebook/formats/gmi.py:141 src/txt2ebook/formats/md.py:140
-#: src/txt2ebook/formats/txt.py:169
-msgid "title:"
+#: src/txt2ebook/formats/base.py:113 src/txt2ebook/formats/md.py:131
+msgid "tag:"
 msgstr ""
 
-#: src/txt2ebook/formats/gmi.py:142 src/txt2ebook/formats/md.py:141
-#: src/txt2ebook/formats/txt.py:170
-msgid "author:"
+#: src/txt2ebook/formats/base.py:121 src/txt2ebook/formats/gmi.py:59
+#: src/txt2ebook/formats/md.py:58 src/txt2ebook/formats/pdf.py:126
+#: src/txt2ebook/formats/txt.py:68
+msgid "toc"
 msgstr ""
 
-#: src/txt2ebook/formats/gmi.py:143 src/txt2ebook/formats/md.py:142
-#: src/txt2ebook/formats/txt.py:172
-msgid "tag:"
+#: src/txt2ebook/formats/epub.py:142
+msgid "cover"
 msgstr ""
 
-#: src/txt2ebook/formats/txt.py:171
-msgid "translator:"
+#: src/txt2ebook/formats/gmi.py:46 src/txt2ebook/formats/md.py:45
+#: src/txt2ebook/formats/txt.py:55
+msgid "metadata"
 msgstr ""
 

txt2ebook/locales/zh-cn/LC_MESSAGES/txt2ebook.po

@@ -5,7 +5,7 @@
 msgid ""
 msgstr ""
 "Project-Id-Version: \n"
-"POT-Creation-Date: 2023-07-09 17:44+0800\n"
+"POT-Creation-Date: 2023-07-22 20:57+0800\n"
 "PO-Revision-Date: 2023-06-17 00:04+0800\n"
 "Last-Translator: \n"
 "Language-Team: \n"
@@ -16,37 +16,33 @@ msgstr ""
 "Generated-By: pygettext.py 1.5\n"
 "X-Generator: Poedit 3.2.2\n"
 
-#: src/txt2ebook/formats/epub.py:142
-msgid "cover"
-msgstr "封面"
-
-#: src/txt2ebook/formats/gmi.py:46 src/txt2ebook/formats/md.py:45
-#: src/txt2ebook/formats/txt.py:55
-msgid "metadata"
-msgstr "元数据"
-
-#: src/txt2ebook/formats/gmi.py:59 src/txt2ebook/formats/gmi.py:127
-#: src/txt2ebook/formats/md.py:58 src/txt2ebook/formats/md.py:126
-#: src/txt2ebook/formats/pdf.py:126 src/txt2ebook/formats/txt.py:68
-#: src/txt2ebook/formats/txt.py:155
-msgid "toc"
-msgstr "目录"
-
-#: src/txt2ebook/formats/gmi.py:141 src/txt2ebook/formats/md.py:140
-#: src/txt2ebook/formats/txt.py:169
+#: src/txt2ebook/formats/base.py:110 src/txt2ebook/formats/md.py:128
 msgid "title:"
 msgstr "书名："
 
-#: src/txt2ebook/formats/gmi.py:142 src/txt2ebook/formats/md.py:141
-#: src/txt2ebook/formats/txt.py:170
+#: src/txt2ebook/formats/base.py:111 src/txt2ebook/formats/md.py:129
 msgid "author:"
 msgstr "作者："
 
-#: src/txt2ebook/formats/gmi.py:143 src/txt2ebook/formats/md.py:142
-#: src/txt2ebook/formats/txt.py:172
+#: src/txt2ebook/formats/base.py:112 src/txt2ebook/formats/md.py:130
+msgid "translator:"
+msgstr "翻译："
+
+#: src/txt2ebook/formats/base.py:113 src/txt2ebook/formats/md.py:131
 msgid "tag:"
 msgstr "票签："
 
-#: src/txt2ebook/formats/txt.py:171
-msgid "translator:"
-msgstr "翻译："
+#: src/txt2ebook/formats/base.py:121 src/txt2ebook/formats/gmi.py:59
+#: src/txt2ebook/formats/md.py:58 src/txt2ebook/formats/pdf.py:126
+#: src/txt2ebook/formats/txt.py:68
+msgid "toc"
+msgstr "目录"
+
+#: src/txt2ebook/formats/epub.py:142
+msgid "cover"
+msgstr "封面"
+
+#: src/txt2ebook/formats/gmi.py:46 src/txt2ebook/formats/md.py:45
+#: src/txt2ebook/formats/txt.py:55
+msgid "metadata"
+msgstr "元数据"

txt2ebook/locales/zh-tw/LC_MESSAGES/txt2ebook.po

@@ -1,7 +1,7 @@
 msgid ""
 msgstr ""
 "Project-Id-Version: \n"
-"POT-Creation-Date: 2023-07-09 17:44+0800\n"
+"POT-Creation-Date: 2023-07-22 20:57+0800\n"
 "PO-Revision-Date: \n"
 "Last-Translator: \n"
 "Language-Team: \n"
@@ -11,37 +11,33 @@ msgstr ""
 "Content-Transfer-Encoding: 8bit\n"
 "X-Generator: Poedit 3.2.2\n"
 
-#: src/txt2ebook/formats/epub.py:142
-msgid "cover"
-msgstr "封面"
-
-#: src/txt2ebook/formats/gmi.py:46 src/txt2ebook/formats/md.py:45
-#: src/txt2ebook/formats/txt.py:55
-msgid "metadata"
-msgstr "元数据"
-
-#: src/txt2ebook/formats/gmi.py:59 src/txt2ebook/formats/gmi.py:127
-#: src/txt2ebook/formats/md.py:58 src/txt2ebook/formats/md.py:126
-#: src/txt2ebook/formats/pdf.py:126 src/txt2ebook/formats/txt.py:68
-#: src/txt2ebook/formats/txt.py:155
-msgid "toc"
-msgstr "目录"
-
-#: src/txt2ebook/formats/gmi.py:141 src/txt2ebook/formats/md.py:140
-#: src/txt2ebook/formats/txt.py:169
+#: src/txt2ebook/formats/base.py:110 src/txt2ebook/formats/md.py:128
 msgid "title:"
 msgstr "书名："
 
-#: src/txt2ebook/formats/gmi.py:142 src/txt2ebook/formats/md.py:141
-#: src/txt2ebook/formats/txt.py:170
+#: src/txt2ebook/formats/base.py:111 src/txt2ebook/formats/md.py:129
 msgid "author:"
 msgstr "作者："
 
-#: src/txt2ebook/formats/gmi.py:143 src/txt2ebook/formats/md.py:142
-#: src/txt2ebook/formats/txt.py:172
+#: src/txt2ebook/formats/base.py:112 src/txt2ebook/formats/md.py:130
+msgid "translator:"
+msgstr "翻译："
+
+#: src/txt2ebook/formats/base.py:113 src/txt2ebook/formats/md.py:131
 msgid "tag:"
 msgstr "标签："
 
-#: src/txt2ebook/formats/txt.py:171
-msgid "translator:"
-msgstr "翻译："
+#: src/txt2ebook/formats/base.py:121 src/txt2ebook/formats/gmi.py:59
+#: src/txt2ebook/formats/md.py:58 src/txt2ebook/formats/pdf.py:126
+#: src/txt2ebook/formats/txt.py:68
+msgid "toc"
+msgstr "目录"
+
+#: src/txt2ebook/formats/epub.py:142
+msgid "cover"
+msgstr "封面"
+
+#: src/txt2ebook/formats/gmi.py:46 src/txt2ebook/formats/md.py:45
+#: src/txt2ebook/formats/txt.py:55
+msgid "metadata"
+msgstr "元数据"

txt2ebook/parser.py

@@ -141,6 +141,7 @@ class Parser:
         book_title = ""
         authors = []
         tags = []
+        translators = []
         current_volume = Volume("")
         current_chapter = Chapter("")
 
@@ -177,6 +178,9 @@ class Parser:
             if token.type == "TAG":
                 tags.append(token.value)
 
+            if token.type == "TRANSLATOR":
+                translators.append(token.value)
+
             if token.type == "VOLUME_CHAPTER":
                 [volume, chapter] = token.value
 
@@ -230,6 +234,7 @@ class Parser:
         logger.info("Found or set book title: %s", book_title)
         logger.info("Found or set authors: %s", repr(authors))
         logger.info("Found or set categories: %s", repr(tags))
+        logger.info("Found or set translators: %s", repr(translators))
 
         return (book_title, authors, tags, toc)
 
@@ -332,7 +337,7 @@ class Parser:
         Returns:
             str: The formatted book content.
         """
-        for delete_line_regex in self.get_regex("delete_line"):
+        for delete_line_regex in self.config.re_delete_line:
             content = re.sub(
                 re.compile(rf"^.*{delete_line_regex}.*$", re.MULTILINE),
                 "",

txt2ebook/tokenizer.py

@@ -53,6 +53,7 @@ class Tokenizer:
     """Tokenizer class to parse text content."""
 
     raw_content: str = field(repr=False)
+    metadata_marker: str = field(repr=False)
     config: argparse.Namespace = field(repr=False)
     tokens: List[Token] = field(default_factory=List, repr=False)
     lineno_lookup: Dict = field(default_factory=Dict, repr=False)
@@ -62,6 +63,11 @@ class Tokenizer:
         self.raw_content = raw_content
         self.config = config
 
+        if self.config.fullwidth:
+            self.metadata_marker = "－－－"
+        else:
+            self.metadata_marker = "---"
+
         config_lang = config.language.replace("-", "_")
         self.langconf = import_module(f"txt2ebook.languages.{config_lang}")
 
@@ -71,29 +77,8 @@ class Tokenizer:
             lineno_lookup[line[:10]] = lineno
         self.lineno_lookup = lineno_lookup
 
-        self.tokens = self.parse()
-
-    def __getattr__(self, key: str) -> Any:
-        """Get a value of the config based on key name.
-
-        This function is called when an attribute is not found on an object
-        instance or not set in `__init__` function.
-
-        Args:
-            key(str): The key attribute name of the config, language config,
-            and current class.
-
-        Returns:
-            Any: The value of a key, if found. Otherwise raise AttributeError
-            exception.
-        """
-        if hasattr(self.config, key):
-            return getattr(self.config, key)
-
-        if hasattr(self.langconf, key):
-            return getattr(self.langconf, key)
-
-        raise AttributeError(f"invalid config key: '{key}'!")
+        self.tokens = []
+        self.parse()
 
     def __repr__(self) -> str:
         """Return the string representation of Tokenizer for debugging purpose.
@@ -106,27 +91,14 @@ class Tokenizer:
             self.__class__.__name__, self.raw_content[:5], self.stats()
         )
 
-    def parse(self) -> List:
+    def parse(self) -> None:
         """Parse the content into tokens.
 
         Returns:
-          List: The list of tokens.
+          None
         """
-        content = self.raw_content.rstrip(self.paragraph_separator)
-        lines = content.split(self.paragraph_separator)
-
-        if len(lines) <= 1:
-            msg = (
-                f"Cannot split content by {repr(self.paragraph_separator)}. "
-                "Check if content have newline with spaces."
-            )
-            log_or_raise_on_warning(msg, self.config.raise_on_warning)
-
-        tokens: List[Token] = []
-        for line in lines:
-            self._tokenize_line(line, tokens)
-
-        return tokens
+        self._tokenize_metadata()
+        self._tokenize_content()
 
     def stats(self) -> Counter:
         """Returns the statistics count for the parsed tokens.
@@ -138,68 +110,100 @@ class Tokenizer:
         logger.debug("Token stats: %s", repr(stats))
         return stats
 
-    def _tokenize_line(self, line: str, tokens: List) -> None:
+    def _tokenize_line(self, line: str) -> None:
         """Tokenize each line after we split by paragraph separator."""
-        _ = (
-            self._tokenize_header(line, tokens)
-            or self._tokenize_metadata(line, tokens)
-            or self._tokenize_paragraph(line, tokens)
-        )
-
-    def _tokenize_metadata(self, line: str, tokens: List) -> bool:
-        """Tokenize the metadata of the book.
+        _ = self._tokenize_header(line) or self._tokenize_paragraph(line)
+
+    def _tokenize_metadata(self) -> None:
+        """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:
+                re_title = self.config.re_title[0]
+
+            re_author = f"{self.langconf.DEFAULT_RE_AUTHOR}"
+            if self.config.re_author:
+                re_author = self.config.re_author[0]
+
+            token_type_regex_map = [
+                ("TITLE", re_title),
+                ("AUTHOR", re_author),
+                ("TAG", f"{self.langconf.DEFAULT_RE_TAG}"),
+                ("TRANSLATOR", f"{self.langconf.DEFAULT_RE_TRANSLATOR}"),
+            ]
+
+            token = None
+            for token_type, regex in token_type_regex_map:
+                match = re.search(regex, line)
+                if match:
+                    token_value = match.group(1).strip()
+                    token = Token(
+                        token_type, token_value, self._lineno(token_value)
+                    )
+                    self.tokens.append(token)
+
+    def _extract_metadata(self) -> List:
+        """Extract YAML-inspired metadata header from file context.
+
+        Metadata header with line number as follows:
+
+            1 ---
+            2 书名：
+            3 作者：
+            4 标签：
+            5 翻译：
+            6 ---
 
-        Metadata at the top of the file was grouped and separate as single
-        newline. By default, the content, or paragraph was separated by two
-        newlines. Hence, we have to group it into one token.
-
-        Also, we can split the metadata line as these lines can also contains
-        chapter content, which can also contains newlines.
         """
-        re_title = f"^{self.DEFAULT_RE_TITLE}"
-        if self.config.re_title:
-            re_title = self.config.re_title[0]
+        match = re.search(
+            rf"^(?:{self.metadata_marker})\n(.*)\n(?:{self.metadata_marker})$",
+            self.raw_content,
+            re.MULTILINE | re.DOTALL,
+        )
+        if not match:
+            msg = "Missing or invalid metadata."
+            log_or_raise_on_warning(msg, self.config.raise_on_warning)
+            return []
 
-        re_author = f"\n{self.DEFAULT_RE_AUTHOR}"
-        if self.config.re_author:
-            re_author = self.config.re_author[0]
+        metadata = match[1].split("\n")
+        logger.debug("Metadata: %s", metadata)
+        return metadata
 
-        token_type_regex_map = [
-            ("TITLE", re_title),
-            ("AUTHOR", re_author),
-            ("TAG", f"\n{self.DEFAULT_RE_TAG}"),
-        ]
+    def _tokenize_content(self) -> None:
+        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)
 
-        token = None
-        for token_type, regex in token_type_regex_map:
-            match = re.search(regex, line)
-            if match:
-                token_value = match.group(1).strip()
-                token = Token(
-                    token_type, token_value, self._lineno(token_value)
-                )
-                tokens.append(token)
+        if len(lines) <= 1:
+            msg = (
+                "Cannot split content by "
+                f"{repr(self.config.paragraph_separator)}. "
+                "Check if content have newline with spaces."
+            )
+            log_or_raise_on_warning(msg, self.config.raise_on_warning)
 
-        return bool(token)
+        for line in lines:
+            self._tokenize_line(line)
 
-    def _tokenize_header(self, line: str, tokens: List) -> bool:
+    def _tokenize_header(self, line: str) -> bool:
         """Tokenize section headers.
 
         Note that we parse in such sequence: chapter, volume, volume_chapter to
         prevent unnecessary calls as we've more chapters than volumes.
         """
         return (
-            self._tokenize_chapter(line, tokens)
-            or self._tokenize_volume_chapter(line, tokens)
-            or self._tokenize_volume(line, tokens)
+            self._tokenize_chapter(line)
+            or self._tokenize_volume_chapter(line)
+            or self._tokenize_volume(line)
         )
 
-    def _tokenize_volume_chapter(self, line: str, tokens: List) -> bool:
+    def _tokenize_volume_chapter(self, line: str) -> bool:
         line = self._validate_section_header("volume chapter", line)
         token = None
 
         re_volume_chapter = (
-            rf"^{self.DEFAULT_RE_VOLUME}\s*{self.DEFAULT_RE_CHAPTER}"
+            rf"^{self.langconf.DEFAULT_RE_VOLUME}\s*"
+            rf"{self.langconf.DEFAULT_RE_CHAPTER}"
         )
         if self.config.re_volume_chapter:
             re_volume_chapter = self.config.re_volume_chapter[0]
@@ -215,15 +219,15 @@ class Tokenizer:
                     Token("CHAPTER", chapter, self._lineno(chapter)),
                 ],
             )
-            tokens.append(token)
+            self.tokens.append(token)
 
         return bool(token)
 
-    def _tokenize_volume(self, line: str, tokens: List) -> bool:
+    def _tokenize_volume(self, line: str) -> bool:
         line = self._validate_section_header("volume", line)
         token = None
 
-        re_volume = rf"^{self.DEFAULT_RE_VOLUME}$"
+        re_volume = rf"^{self.langconf.DEFAULT_RE_VOLUME}$"
         if self.config.re_volume:
             re_volume = "(" + "|".join(self.config.re_volume) + ")"
 
@@ -231,15 +235,15 @@ class Tokenizer:
         if match:
             volume = match.group(1).strip()
             token = Token("VOLUME", volume, self._lineno(volume))
-            tokens.append(token)
+            self.tokens.append(token)
 
         return bool(token)
 
-    def _tokenize_chapter(self, line: str, tokens: List) -> bool:
+    def _tokenize_chapter(self, line: str) -> bool:
         line = self._validate_section_header("chapter", line)
         token = None
 
-        re_chapter = rf"^{self.DEFAULT_RE_CHAPTER}$"
+        re_chapter = rf"^{self.langconf.DEFAULT_RE_CHAPTER}$"
         if self.config.re_chapter:
             re_chapter = "(" + "|".join(self.config.re_chapter) + ")"
 
@@ -247,12 +251,12 @@ class Tokenizer:
         if match:
             chapter = match.group(1).strip()
             token = Token("CHAPTER", chapter, self._lineno(chapter))
-            tokens.append(token)
+            self.tokens.append(token)
 
         return bool(token)
 
-    def _tokenize_paragraph(self, line: str, tokens: List) -> bool:
-        tokens.append(Token("PARAGRAPH", line, self._lineno(line)))
+    def _tokenize_paragraph(self, line: str) -> bool:
+        self.tokens.append(Token("PARAGRAPH", line, self._lineno(line)))
         return True
 
     def _validate_section_header(self, header_type: str, line: str) -> str:

txt2ebook/txt2ebook.py

@@ -114,6 +114,14 @@ def build_parser(
         metavar="EBOOK_FILENAME",
     )
 
+    parser.add_argument(
+        "-of",
+        "--output-folder",
+        dest="output_folder",
+        default="output",
+        help="set default output folder (default: '%(default)s')",
+    )
+
     parser.add_argument(
         "-f",
         "--format",

{txt2ebook-0.1.43.dist-info → txt2ebook-0.1.45.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: txt2ebook
-Version: 0.1.43
+Version: 0.1.45
 Summary: CLI tool to convert txt file to ebook format
 Home-page: https://github.com/kianmeng/txt2ebook
 License: AGPL-3.0-or-later
@@ -20,10 +20,6 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Topic :: Text Processing
 Classifier: Topic :: Text Processing :: Filters
 Classifier: Topic :: Text Processing :: General

{txt2ebook-0.1.43.dist-info → txt2ebook-0.1.45.dist-info}/RECORD

@@ -1,43 +1,43 @@
-CHANGELOG.md,sha256=54GQstmx9pi0ijmjG9iuQlv9p7vemTqat9_Raq6hUNg,18005
-CONTRIBUTING.md,sha256=75Ik1RrezRrFkPSesTTYxWSxtKNY7_Av42Mt-8dUFTA,2004
+CHANGELOG.md,sha256=CMTnOue9v10kCcfT0erpykMhQlRccQSLmlsEkOERi6k,18912
+CONTRIBUTING.md,sha256=rmcbJPvVVIoIHJohtO6y9UaY4PUdWm4kuxLTirFyotg,2335
 LICENSE.md,sha256=tGtFDwxWTjuR9syrJoSv1Hiffd2u8Tu8cYClfrXS_YU,31956
-txt2ebook/__init__.py,sha256=9sZlWqwUBKm4DORriJpLB20trE6OrZE2GYAMP0oNRi0,1649
+txt2ebook/__init__.py,sha256=3R_AsDSGLfyMPv40-Yb93fWrwFDcHNxYcC9PFeszips,1649
 txt2ebook/__main__.py,sha256=69yaheH-Fv2VIPS0T9kiVmiMluSgLGvwo1fa7badX2I,845
 txt2ebook/exceptions.py,sha256=Y6rqjXhiKIxNeKWVqvAqsUAOaBFKxlUE5Tm5EBcoi9w,837
 txt2ebook/formats/__init__.py,sha256=lVclUeBZ0Rf_zEAYyzc6m5ak2wXV3696d1tv4gMP9GQ,2322
-txt2ebook/formats/base.py,sha256=gmOyrOgmCxyw1MsD1ZLTJ1vIGTHnObPaehzoucZfI8M,3362
-txt2ebook/formats/epub.py,sha256=NOo6aYeAFeghhum1lneGCcMzsZErQlqwoSegx2G6Sps,6788
-txt2ebook/formats/gmi.py,sha256=5Ao4ageER-VsWWfl1ANhQIs2WXdKP7i4l5YroUkGvKk,6820
-txt2ebook/formats/md.py,sha256=tE8ksTkvpRu85-IxUyQIpp3pG2JDi6-9ZVOOOalulgk,6563
+txt2ebook/formats/base.py,sha256=Zm0w_3GY8x2x8E-IzVo-KfYUCw2gsBT0-S3lNK600k4,4694
+txt2ebook/formats/epub.py,sha256=PpUCvyvzKWM8fO-n2raPW-ZKIY0pkiQ07Y6YTWa6a1o,6798
+txt2ebook/formats/gmi.py,sha256=fNFSamuvcWXZYP2pLR1vrXCx3-JcD4hVYVy4nlyATUg,6095
+txt2ebook/formats/md.py,sha256=AIzf_eofrmxnMHqC5ZKRWp1quqHo8-gDrQHwHcjYAmI,5844
 txt2ebook/formats/pdf.py,sha256=rs4OJoEB4JBHR0BBd8P8x1YRYVcDXpLyI3SBJ8RzzFs,7107
 txt2ebook/formats/templates/__init__.py,sha256=0Hhm7Dayb7eB9h2cFo2103H4Tr6ie0ySMZ5gR01q6ag,750
 txt2ebook/formats/templates/epub/__init__.py,sha256=O2sdWRhkuamReBR20WedGWosLp8Dt8NZ33aXzyNQuLQ,756
 txt2ebook/formats/templates/epub/clean.css,sha256=AnEwMckzUSKcjKsDiWtJW1oaceuklt2tyuS1VbpVK1s,462
 txt2ebook/formats/templates/epub/condense.css,sha256=Fz80ZqkPsFRmGdURduAxqMV8drD0CCUlrv41P8rUsm8,477
 txt2ebook/formats/templates/epub/noindent.css,sha256=_O5Tv90TKyyPBRdgjuNKFwtKFbdheh2V9PtDhgRUg3U,483
-txt2ebook/formats/txt.py,sha256=K1DXcmxuAzUW8bzYgxh6UGBFevUPL12IXzYR5NrVgIU,7504
+txt2ebook/formats/txt.py,sha256=4c2vAgE4QGPRo7aMECmRFNjQx2g7M_aARuQSeM4xKa8,6746
 txt2ebook/helpers/__init__.py,sha256=5EFTheYifNYk24rniaehnxd0NRR4K3aakSldZTVot1c,1966
 txt2ebook/languages/__init__.py,sha256=-c9-YQEkXnb9LKLoi7EtNlQLAw2SqDKVw2UXlWt9Dl0,753
 txt2ebook/languages/en.py,sha256=xCIhL431eUgoGwci4LCBkso8bR2LBhxKqWCPczKKoJQ,915
-txt2ebook/languages/zh_cn.py,sha256=rfAXIlDcWe6SiqFFQp_ShCKIDX3lZ85pjKkxF4JXiQU,1878
+txt2ebook/languages/zh_cn.py,sha256=DZh-M4JcZdix-Bv4su_Aq2bBYBg4COYFHB8LEzbv0Gs,1919
 txt2ebook/languages/zh_tw.py,sha256=UyZQ8RYiSTaIXjk8W3GHaspdIEHclTtjRAoEk1X8XVw,1374
 txt2ebook/locales/en/LC_MESSAGES/txt2ebook.mo,sha256=NWBAcL3xlPkQqT8xFK9JCY8OrNtPOIw4s2OPHkvueA4,572
-txt2ebook/locales/en/LC_MESSAGES/txt2ebook.po,sha256=RPjcd3f_RyfIau6Mzy_tHTM9rwoqqIzEXiXPZO_Hymw,1424
-txt2ebook/locales/txt2ebook.pot,sha256=4fh4QBrtRqf_ePcBKl2U6Dttiv3PNiwg9wl5QL3pO8M,1382
+txt2ebook/locales/en/LC_MESSAGES/txt2ebook.po,sha256=R-vQlS_pQXuJl7rBfP7TonK-il3hSH_GQn5sUVZOwtM,1285
+txt2ebook/locales/txt2ebook.pot,sha256=l6l9Nf2oYclg0r5oWLMt15rzW3Kr_ajbI1JFLRPHqd0,1243
 txt2ebook/locales/zh-cn/LC_MESSAGES/txt2ebook.mo,sha256=PbZcaLjJpfCx-xw_rzUbYnrPoPlxPGIUaV-hmJQq_9s,572
-txt2ebook/locales/zh-cn/LC_MESSAGES/txt2ebook.po,sha256=FbJwMeQv6LVhz-Ntasp0cvJvbyfu4R2-bflqlCHxHms,1424
+txt2ebook/locales/zh-cn/LC_MESSAGES/txt2ebook.po,sha256=FHog4JJ0CTj1lm2nMqRRW28K_KavBfgBckvIQsH-RO0,1285
 txt2ebook/locales/zh-tw/LC_MESSAGES/txt2ebook.mo,sha256=z-kUOMpQFjy1CjV3eyf38vXww9uH54uww5s4DWt2k6g,523
-txt2ebook/locales/zh-tw/LC_MESSAGES/txt2ebook.po,sha256=ShlJj1DdKf6klVCMwillIbZ6lnx1p7nkNU15mWvzi6Y,1271
+txt2ebook/locales/zh-tw/LC_MESSAGES/txt2ebook.po,sha256=AaMZHY78QmlgF40K8w6mmSO-_4AyN1Z1xeNoX3_6LTI,1132
 txt2ebook/models/__init__.py,sha256=oHf4YvkEV7qKHhHiGxl4m95DSJ3zSIW2uJQec-BwXrc,920
 txt2ebook/models/book.py,sha256=OMKyw-j4pAVfldvFSTNIFKMp_dqG4Hogy7947st9Z2o,2754
 txt2ebook/models/chapter.py,sha256=PhPHraG3QNgY4C-USAzTDpDPVNsvTL8yC3r2iTW42KU,1676
 txt2ebook/models/volume.py,sha256=4n6a9cF69NTcOmWTxT1sVm-Bjvf-fagJ2E8thVX4uzg,1587
-txt2ebook/parser.py,sha256=AK3rkY9uItu7AJQnl2b5sMroqJgbxxQdKsOAEfo3nXU,11929
-txt2ebook/tokenizer.py,sha256=lsgGZSVpKl5fC6eEf8eIrGKZIVQnLqKM1Kenn4xJ-u4,9263
-txt2ebook/txt2ebook.py,sha256=GpZjqd7AEW0Mq-Ey8Ikorc8SLorJVB0yeIIL6BhD-5c,11449
+txt2ebook/parser.py,sha256=6TJeHOOFtHvy1h9zaeVj3BdDTye9pJHiTWFtvMUMXR4,12114
+txt2ebook/tokenizer.py,sha256=kzUW-xtAU4zgDxyUmPZZ7HNbjGDeOQX0MYr3_eOuByM,9313
+txt2ebook/txt2ebook.py,sha256=t6SOHdhWQFufZoZcpJ2b5gfY5gUPuSTxvMrnsSq_ErU,11646
 txt2ebook/zh_utils.py,sha256=CM6SnsQhJWzSevcJWQ_9Pj028JUGbG3v0AG6xK_KgBY,4877
-txt2ebook-0.1.43.dist-info/LICENSE.md,sha256=tGtFDwxWTjuR9syrJoSv1Hiffd2u8Tu8cYClfrXS_YU,31956
-txt2ebook-0.1.43.dist-info/METADATA,sha256=4goYA7aZ6gZzuYld_RJe4_Sjo2t26m7GmVHsXmVouds,6777
-txt2ebook-0.1.43.dist-info/WHEEL,sha256=vVCvjcmxuUltf8cYhJ0sJMRDLr1XsPuxEId8YDzbyCY,88
-txt2ebook-0.1.43.dist-info/entry_points.txt,sha256=IQHyIIhd0MHjSSRVC1a6tMeIoLus8D06KHL_cumvEbg,83
-txt2ebook-0.1.43.dist-info/RECORD,,
+txt2ebook-0.1.45.dist-info/LICENSE.md,sha256=tGtFDwxWTjuR9syrJoSv1Hiffd2u8Tu8cYClfrXS_YU,31956
+txt2ebook-0.1.45.dist-info/METADATA,sha256=55vO3r0I_whQ1Soha4rbdHm5F5JZBBInRQZttNDKf3s,6575
+txt2ebook-0.1.45.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
+txt2ebook-0.1.45.dist-info/entry_points.txt,sha256=IQHyIIhd0MHjSSRVC1a6tMeIoLus8D06KHL_cumvEbg,83
+txt2ebook-0.1.45.dist-info/RECORD,,

{txt2ebook-0.1.43.dist-info → txt2ebook-0.1.45.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.4.0
+Generator: poetry-core 1.6.1
 Root-Is-Purelib: true
 Tag: py3-none-any