Merge pull request #4 from sudoskys/dev

Fix underline supports, fix `\(`, add some intro

README.md

@@ -25,6 +25,30 @@ or if you use `pdm`:
 pdm add telegramify-markdown
 ```
 
+## Supported Features
+
+- [x] Headings (1-6)
+- [x] Links [text](url)
+- [x] Images ![alt]
+- [x] Lists (Ordered, Unordered)
+- [x] Tables |-|-|
+- [x] Horizontal Rule ----
+- [x] *Text* **Styles**
+- [x] __Underline__
+- [x] Code Blocks
+- [x] `Inline Code`
+- [x] Block Quotes
+- [x] ~~Strikethrough~~
+- [ ] Task Lists
+- [ ] ~Strikethrough~
+- [ ] ||Spoiler||
+- [ ] Tg Emoji
+- [ ] Tg User At
+
+> [!NOTE]
+> Since mistletoe doesn't parse TODO and Spoiler, we can't apply it.
+~Strikethrough~ is incorrect, even if it comes from official documentation, please use ~~Strikethrough~~ format.
+
 ## Use case
 
 ````python3
@@ -34,37 +58,34 @@ from telegramify_markdown.customize import markdown_symbol
 markdown_symbol.head_level_1 = "📌"  # If you want, Customizing the head level 1 symbol
 markdown_symbol.link = "🔗"  # If you want, Customizing the link symbol
 md = """
-# 一级标题 `c!ode` # 一级标题 `code`
-[Link!AA](https://www.example.com)
-
-[key!]: https://www.google.com "a title!"
-
-[这是!链接2][asd!asd](https://www.example.com)
-[rttt]()
-![PIC](https://www.example.com/image.jpg)
-1. Order!ed
-   1. Order!ed sub
-- Unord*-.ered
+'\_', '\*', '\[', '\]', '\(', '\)', '\~', '\`', '\>', '\#', '\+', '\-', '\=', '\|', '\{', '\}', '\.', '\!'
+_ , * , [ , ] , ( , ) , ~ , ` , > , # , + , - , = , | , { , } , . , !
+**bold text**
+*bold text*
+_italic text_
+__underline__
+~no valid strikethrough~
+~~strikethrough~~
+||spoiler||
+*bold _italic bold ~~italic bold strikethrough ||italic bold strikethrough spoiler||~~ __underline italic bold___ bold*
+__underline italic bold__
+[link](https://www.google.com)
+- [ ] Uncompleted task list item
+- [x] Completed task list item
+> Quote
+```python
+print("Hello, World!")
+```
+This is `inline code`
+1. First ordered list item
+2. Another item
+    - Unordered sub-list.
+1. Actual numbers don't matter, just that it's a number
 """
 converted = telegramify_markdown.convert(md)
 print(converted)
 ````
 
 output as follows:
 
-```markdown
-*📌 一级标题 `c\!ode` \# 一级标题 `code`*
-[Link\!AA](https://www\.example\.com)
-
-🔗[a title\!](https://www\.google\.com)
-
-\[这是\!链接2\][asd\!asd](https://www\.example\.com)
-[rttt]()
-🖼[PIC](https://www\.example\.com/image\.jpg)
-1\. Order\!ed
-1\. Order\!ed sub
-⦁ Unord\*\-\.ered
-```
-
-> Note: Telegram Server automatically processes the double of `\`(`\\`) again (even after escaping), which is beyond the
-> control of us.
+![.github/result.png](.github/result.png)

playground/exp1.md

@@ -2,36 +2,40 @@
 key: value
 ---
 
-# 一级标题 `c!ode` # 一级标题 `code`
+\(c!ode\)
 
-## 二级标题
+\# Heading Level 1 `c!ode`
 
-### 三级标题
+# Heading Level 1 `c!ode`
+
+## Heading Level 2
+
+### Heading Level 3
 
 Header
 ======
 
     included as literal
     1231asdasd
 
-**这是粗!体文本**
-*这是斜!体文本*
-~~这是删!除线文本~~
+**Bold text**
+*Italic text*
+~~Strikethrough text~~
 
-> 这是引用!文本
+> Blockquote text
 
-`这是内联!代码\\\\`
+`Inline code`
 
-\\\/\111`sad`
+\\/\\111`sad`
 
 ```
 
-这是代码块!
+Code block
 
 ```
 
 ```python
-# 这是带有语言指定的代码块
+# Code block with specified language
 print("Hello, World!")
 ```
 
@@ -42,29 +46,50 @@ print("Hello, World!")
 
 1. numbered item
 
-[key!]: https://www.google.com "a title!"
-
-<p>some text</p>
+[some text](https://www.example.com)
 
-[这是链!接](https://www.example.com)
-
-[这是!链接2][asd!asd](https://www.example.com)
+[some text2][asd!asd](https://www.example.com)
 [rttt]()
-[这是链接3][asdasd2]
+[some text3][asdasd2]
 
-![这是图片](https://www.example.com/image.jpg)
+![Image](https://www.example.com/image.jpg)
 
 <https://www.google.com>
 
 ---
-这是水平线
-
-内置的 **加粗** 和 *斜体* 文本
-
-| 表头  | 表头  |
-|-----|-----|
-| 单元格 | 单元格 |
-| 单元格 | 单元格 |
-
-- [ ] 这是未完成的任务列表项
-- [x] 这是已完成的任务列表项
+Horizontal Rule
+
+**Bold** and *Italic* text
+
+| Header | Header |
+|--------|--------|
+| Cell   | Cell   |
+| Cell   | Cell   |
+
+- [ ] Uncompleted task list item
+- [x] Completed task list item
+
+In all other places characters '_', '*', '[', ']', '(', ')', '~', '`', '>', '#', '+', '-', '=', '|', '{', '}', '.', '!' must be escaped with the preceding character '\'.
+In all other places characters '\_', '\*', '\[', '\]', '\(', '\)', '\~', '\`', '\>', '\#', '\+', '\-', '\=', '\|', '\{', '\}', '\.', '\!' must be escaped with the preceding character '\'.
+
+*bold \*text*
+_italic \*text_
+__underline__
+~strikethrough~
+||spoiler||
+*bold _italic bold ~italic bold strikethrough ||italic bold strikethrough spoiler||~ __underline italic bold___ bold*
+[inline URL](http://www.example.com/)
+[inline mention of a user](tg://user?id=123456789)
+![👍](tg://emoji?id=5368324170671202286)
+`inline fixed-width code`
+```
+pre-formatted fixed-width code block
+```
+```lua
+pre-formatted fixed-width code block written in the Python programming language
+```
+>Block quotation started
+>Block quotation continued
+>The last line of the block quotation**
+>The second block quotation started right after the previous\r
+>The third block quotation started right after the previous

playground/show_send.py

@@ -0,0 +1,43 @@
+import os
+
+from dotenv import load_dotenv
+from telebot import TeleBot
+
+import telegramify_markdown
+
+md = """
+'\_', '\*', '\[', '\]', '\(', '\)', '\~', '\`', '\>', '\#', '\+', '\-', '\=', '\|', '\{', '\}', '\.', '\!'
+_ , * , [ , ] , ( , ) , ~ , ` , > , # , + , - , = , | , { , } , . , !
+**bold text**
+*bold text*
+_italic text_
+__underline__
+~no valid strikethrough~
+~~strikethrough~~
+||spoiler||
+*bold _italic bold ~~italic bold strikethrough ||italic bold strikethrough spoiler||~~ __underline italic bold___ bold*
+__underline italic bold__
+[link](https://www.google.com)
+- [ ] Uncompleted task list item
+- [x] Completed task list item
+> Quote
+```python
+print("Hello, World!")
+```
+This is `inline code`
+1. First ordered list item
+2. Another item
+    - Unordered sub-list.
+1. Actual numbers don't matter, just that it's a number
+"""
+converted = telegramify_markdown.convert(md)
+print(converted)
+load_dotenv()
+telegram_bot_token = os.getenv("TELEGRAM_BOT_TOKEN", None)
+chat_id = os.getenv("TELEGRAM_CHAT_ID", None)
+bot = TeleBot(telegram_bot_token)
+bot.send_message(
+    chat_id,
+    converted,
+    parse_mode="MarkdownV2"
+)

playground/telegram_exp.py

@@ -2,6 +2,7 @@
 
 
 def ignore(a):
+    print(a)
     pass
 
 
@@ -29,3 +30,5 @@ def ignore(a):
 """>Hello, World\!"""
 ignore(formatting.escape_markdown("Hello, World!"))
 """Hello, World\!"""
+ignore(formatting.escape_markdown("\(Hello, World!)"))
+"""Hello, World\!"""

playground/use_case.py

@@ -4,17 +4,8 @@
 markdown_symbol.head_level_1 = "📌"  # If you want, Customizing the head level 1 symbol
 markdown_symbol.link = "🔗"  # If you want, Customizing the link symbol
 md = """
-# 一级标题 `c!ode` # 一级标题 `code`
-[Link!AA](https://www.example.com)
-
-[key!]: https://www.google.com "a title!"
-
-[这是!链接2][asd!asd](https://www.example.com)
-[rttt]()
-![PIC](https://www.example.com/image.jpg)
-1. Order!ed
-   1. Order!ed sub
-- Unord*-.ered
+*bold _italic bold ~italic bold strikethrough ||italic bold strikethrough spoiler||~ __underline italic bold___ bold*
+~strikethrough~
 """
 converted = telegramify_markdown.convert(md)
 print(converted)

pyproject.toml

@@ -1,12 +1,12 @@
 [project]
 name = "telegramify-markdown"
-version = "0.1.2"
+version = "0.1.3"
 description = "Convert Markdown to a format usable by Telegram."
 authors = [
     { name = "sudoskys", email = "coldlando@hotmail.com" },
 ]
 dependencies = [
-    "mistletoe>=1.3.0",
+    "mistletoe==1.3.0",
     "pytelegrambotapi>=4.16.1",
     "emoji>=2.10.1",
 ]

src/telegramify_markdown/__init__.py

@@ -1,4 +1,3 @@
-import os
 from typing import Union
 
 import mistletoe
@@ -10,16 +9,24 @@
 from .render import TelegramMarkdownRenderer
 
 
+def markdownify(text: str):
+    # '_', '*', '[', ']', '(', ')', '~', '`', '>', '#', '+', '-', '=', '|', '{', '}', '.', '!'
+    # if text in ["_", "*", "[", "]", "(", ")", "~", "`", ">", "#", "+", "-", "=", "|", "{", "}", ".", "!"]:
+    #     return text
+    return formatting.escape_markdown(text)
+
+
 def _update_text(token: Union[SpanToken, BlockToken]):
     """Update the text contents of a span token and its children.
     `InlineCode` tokens are left unchanged."""
     if isinstance(token, ThematicBreak):
         token.line = formatting.escape_markdown("————————")
+        pass
     elif isinstance(token, LinkReferenceDefinition):
         pass
     else:
         assert hasattr(token, "content"), f"Token {token} has no content attribute"
-        token.content = formatting.escape_markdown(token.content)
+        token.content = markdownify(token.content)
 
 
 def _update_block(token: BlockToken):

src/telegramify_markdown/render.py

@@ -3,6 +3,7 @@
 from mistletoe import block_token, span_token
 from mistletoe.markdown_renderer import MarkdownRenderer, LinkReferenceDefinition, Fragment
 from telebot import formatting
+
 from .customize import markdown_symbol
 
 
@@ -64,11 +65,14 @@ def render_setext_heading(
         yield formatting.escape_markdown("——" * 5)
 
     def render_emphasis(self, token: span_token.Emphasis) -> Iterable[Fragment]:
-        token.delimiter = "_"
         return super().render_emphasis(token)
 
     def render_strong(self, token: span_token.Strong) -> Iterable[Fragment]:
-        return self.embed_span(Fragment(token.delimiter * 1), token.children)
+        # Telegram strong: *text* but __text__ for emphasis, so we need to check the delimiter
+        if token.delimiter == "*":
+            return self.embed_span(Fragment(token.delimiter * 1), token.children)
+        # __
+        return self.embed_span(Fragment(token.delimiter * 2), token.children)
 
     def render_strikethrough(
             self, token: span_token.Strikethrough
@@ -129,6 +133,13 @@ def render_link_or_image(
     def render_auto_link(self, token: span_token.AutoLink) -> Iterable[Fragment]:
         yield Fragment(formatting.escape_markdown("<") + token.children[0].content + formatting.escape_markdown(">"))
 
+    def render_escape_sequence(
+            self, token: span_token.EscapeSequence
+    ) -> Iterable[Fragment]:
+        # 渲染转义字符
+        # because the escape_markdown already happened in the parser, we can skip it here.
+        yield Fragment("" + token.children[0].content)
+
     def render_table(
             self, token: block_token.Table, max_line_length: int
     ) -> Iterable[str]: