chatgpt-md-converter 0.1.1__tar.gz → 0.1.2__tar.gz

{chatgpt_md_converter-0.1.1 → chatgpt_md_converter-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: chatgpt_md_converter
-Version: 0.1.1
+Version: 0.1.2
 Summary: A package for converting markdown to HTML for chat Telegram bots
 Home-page: https://github.com/Latand/formatter-chatgpt-telegram
 Author: Kostiantyn Kriuchkov

{chatgpt_md_converter-0.1.1 → chatgpt_md_converter-0.1.2}/chatgpt_md_converter/converters.py

@@ -16,6 +16,7 @@ def split_by_tag(out_text: str, md_tag: str, html_tag: str) -> str:
     Splits the text by markdown tag and replaces it with the specified HTML tag.
     """
     tag_pattern = re.compile(
-        r"{}(.*?){}".format(re.escape(md_tag), re.escape(md_tag)), re.DOTALL
+        r"(?<!\w){}(.*?){}(?!\w)".format(re.escape(md_tag), re.escape(md_tag)),
+        re.DOTALL,
     )
     return tag_pattern.sub(r"<{}>\1</{}>".format(html_tag, html_tag), out_text)

{chatgpt_md_converter-0.1.1 → chatgpt_md_converter-0.1.2}/chatgpt_md_converter/formatters.py

@@ -1,9 +1,6 @@
-import re
-
-
 def combine_blockquotes(text: str) -> str:
     """
-    Combines multiline blockquotes into a single blockquote.
+    Combines multiline blockquotes into a single blockquote while keeping the \n characters.
     """
     lines = text.split("\n")
     combined_lines = []
@@ -17,7 +14,7 @@ def combine_blockquotes(text: str) -> str:
         else:
             if in_blockquote:
                 combined_lines.append(
-                    "<blockquote>" + " ".join(blockquote_lines) + "</blockquote>"
+                    "<blockquote>" + "\n".join(blockquote_lines) + "</blockquote>"
                 )
                 blockquote_lines = []
                 in_blockquote = False
@@ -25,7 +22,7 @@ def combine_blockquotes(text: str) -> str:
 
     if in_blockquote:
         combined_lines.append(
-            "<blockquote>" + " ".join(blockquote_lines) + "</blockquote>"
+            "<blockquote>" + "\n".join(blockquote_lines) + "</blockquote>"
         )
 
     return "\n".join(combined_lines)

{chatgpt_md_converter-0.1.1 → chatgpt_md_converter-0.1.2}/chatgpt_md_converter/telegram_formatter.py

@@ -26,6 +26,7 @@ def telegram_format(text: str) -> str:
 
     # Nested Bold and Italic
     output = re.sub(r"\*\*\*(.*?)\*\*\*", r"<b><i>\1</i></b>", output)
+    output = re.sub(r"\_\_\_(.*?)\_\_\_", r"<u><i>\1</i></u>", output)
 
     # Process markdown formatting tags (bold, underline, italic, strikethrough)
     # and convert them to their respective HTML tags
@@ -39,14 +40,14 @@ def telegram_format(text: str) -> str:
     output = re.sub(r"【[^】]+】", "", output)
 
     # Convert links
-    output = re.sub(r"\[(.*?)\]\((.*?)\)", r'<a href="\2">\1</a>', output)
-
-    # Convert lists
-    output = re.sub(r"^\s*[\-\*] (.+)", r"• \1", output, flags=re.MULTILINE)
+    output = re.sub(r"!?\[(.*?)\]\((.*?)\)", r'<a href="\2">\1</a>', output)
 
     # Convert headings
     output = re.sub(r"^\s*#+ (.+)", r"<b>\1</b>", output, flags=re.MULTILINE)
 
+    # Convert unordered lists, preserving indentation
+    output = re.sub(r"^(\s*)[\-\*] (.+)", r"\1• \2", output, flags=re.MULTILINE)
+
     # Step 4: Reinsert the converted HTML code blocks
     output = reinsert_code_blocks(output, code_blocks)
 

{chatgpt_md_converter-0.1.1 → chatgpt_md_converter-0.1.2}/chatgpt_md_converter.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: chatgpt_md_converter
-Version: 0.1.1
+Version: 0.1.2
 Summary: A package for converting markdown to HTML for chat Telegram bots
 Home-page: https://github.com/Latand/formatter-chatgpt-telegram
 Author: Kostiantyn Kriuchkov

{chatgpt_md_converter-0.1.1 → chatgpt_md_converter-0.1.2}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup
 
 setup(
     name="chatgpt_md_converter",
-    version="0.1.1",
+    version="0.1.2",
     author="Kostiantyn Kriuchkov",
     author_email="latand666@gmail.com",
     description="A package for converting markdown to HTML for chat Telegram bots",

{chatgpt_md_converter-0.1.1 → chatgpt_md_converter-0.1.2}/tests/test_parser.py

@@ -254,3 +254,145 @@ def test_combined_formatting_with_lists():
     assert (
         output.strip() == expected_output.strip()
     ), "Failed handling combined formatting with lists"
+
+
+def test_md_large_example():
+    input_text = """
+1. **Headings:**
+# H1 Heading
+## H2 Heading
+### H3 Heading
+#### H4 Heading
+##### H5 Heading
+###### H6 Heading
+
+2. **Emphasis:**
+
+*Italic text* or _Italic text_
+
+**Bold text** or __Underline text__
+
+***Bold and italic text*** or ___Underline and italic text___
+
+3. **Lists:**
+   - **Unordered List:**
+
+   - Item 1
+   - Item 2
+     - Subitem 1
+     - Subitem 2
+   
+   - **Ordered List:**
+
+   1. First item
+   2. Second item
+      1. Subitem 1
+      2. Subitem 2
+
+4. **Links:**
+
+[OpenAI](https://www.openai.com)
+
+5. **Images:**
+
+![Alt text for image](URL_to_image)
+![Alt text for image](URL_to_імедж)
+
+6. **Blockquotes:**
+
+> This is a blockquote.
+> It can span multiple lines.
+
+7. **Inline Code:**
+
+Here is some `inline code`.
+
+8. **Code Blocks:**
+
+```python
+def example_function():
+    print("Hello World")
+```
+
+9. **Tables:**
+
+| Header 1 | Header 2 |
+|----------|----------|
+| Row 1 Col 1 | Row 1 Col 2 |
+| Row 2 Col 1 | Row 2 Col 2 |
+
+10. **Horizontal Rule:**
+
+---
+"""
+    expected_output = """
+1. <b>Headings:</b>
+<b>H1 Heading</b>
+<b>H2 Heading</b>
+<b>H3 Heading</b>
+<b>H4 Heading</b>
+<b>H5 Heading</b>
+<b>H6 Heading</b>
+
+2. <b>Emphasis:</b>
+
+<i>Italic text</i> or <i>Italic text</i>
+
+<b>Bold text</b> or <u>Underline text</u>
+
+<b><i>Bold and italic text</i></b> or <u><i>Underline and italic text</i></u>
+
+3. <b>Lists:</b>
+   • <b>Unordered List:</b>
+
+   • Item 1
+   • Item 2
+     • Subitem 1
+     • Subitem 2
+   
+   • <b>Ordered List:</b>
+
+   1. First item
+   2. Second item
+      1. Subitem 1
+      2. Subitem 2
+
+4. <b>Links:</b>
+
+<a href="https://www.openai.com">OpenAI</a>
+
+5. <b>Images:</b>
+
+<a href="URL_to_image">Alt text for image</a>
+<a href="URL_to_імедж">Alt text for image</a>
+
+6. <b>Blockquotes:</b>
+
+<blockquote>This is a blockquote.
+It can span multiple lines.</blockquote>
+
+7. <b>Inline Code:</b>
+
+Here is some <code>inline code</code>.
+
+8. <b>Code Blocks:</b>
+
+<pre><code class="language-python">def example_function():
+    print("Hello World")
+</code></pre>
+
+9. <b>Tables:</b>
+
+| Header 1 | Header 2 |
+|----------|----------|
+| Row 1 Col 1 | Row 1 Col 2 |
+| Row 2 Col 1 | Row 2 Col 2 |
+
+10. <b>Horizontal Rule:</b>
+
+---
+"""
+    output = telegram_format(input_text)
+    assert (
+        output.strip() == expected_output.strip()
+    ), "Failed handling large markdown example"