pyhtml2md 1.6.1__tar.gz → 1.6.4__tar.gz

{pyhtml2md-1.6.1 → pyhtml2md-1.6.4}/.github/workflows/wheels.yml

@@ -41,7 +41,8 @@ jobs:
 
     - uses: pypa/cibuildwheel@v2.19.1
       env:
-        CIBW_ARCHS_MACOS: auto universal2
+        CIBW_ARCHS_MACOS: "auto universal2"
+        CIBW_SKIP: "{cp36-*, cp37-*}" # Skip Python 3.6/3.7
 
     - name: Verify clean directory
       run: git diff --exit-code

{pyhtml2md-1.6.1 → pyhtml2md-1.6.4}/CHANGELOG.md

@@ -2,6 +2,15 @@
 
 [TOC]
 
+## 1.6.4
+- Fix handling of `<br>` tags outside of paragraphs (`<p>`)
+
+## 1.6.3
+- Update python dependencies, hopefully fixes (#133)
+
+## 1.6.2
+- Fix HTML entities not converted (see #131)
+
 ## 1.6.0
 
 - Add option for soft line break

{pyhtml2md-1.6.1 → pyhtml2md-1.6.4}/CMakeLists.txt

@@ -1,5 +1,5 @@
 cmake_minimum_required(VERSION 3.8)
-project(html2md VERSION 1.6.1 LANGUAGES CXX)
+project(html2md VERSION 1.6.4 LANGUAGES CXX)
 
 set(PROJECT_HOMEPAGE_URL "https://tim-gromeyer.github.io/html2md/")
 set(html2md_HOMEPAGE_URL "${PROJECT_HOMEPAGE_URL}")

{pyhtml2md-1.6.1 → pyhtml2md-1.6.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyhtml2md
-Version: 1.6.1
+Version: 1.6.4
 Summary: Transform your HTML into clean, easy-to-read markdown with pyhtml2md.
 Keywords: html,markdown,html-to-markdown,python3,cpp17,cpp-library,html2markdown,html2md
 Author-Email: Tim Gromeyer <sakul8826@gmail.com>

{pyhtml2md-1.6.1 → pyhtml2md-1.6.4}/pyproject.toml

@@ -11,7 +11,7 @@ description = "Transform your HTML into clean, easy-to-read markdown with pyhtml
 readme = "python/README.md"
 requires-python = ">=3.7"
 license = { text = "MIT" }
-version = "1.6.1"
+version = "1.6.4"
 classifiers = [
     "Intended Audience :: Developers",
     "License :: OSI Approved :: MIT License",

{pyhtml2md-1.6.1 → pyhtml2md-1.6.4}/src/html2md.cpp

@@ -155,9 +155,9 @@ void Converter::CleanUpMarkdown() {
   ReplaceAll(&md_, """, '"');
   ReplaceAll(&md_, "&lt;", "<");
   ReplaceAll(&md_, "&gt;", ">");
-  ReplaceAll(&html_, "&amp;", '&');
-  ReplaceAll(&html_, "&nbsp;", ' ');
-  ReplaceAll(&html_, "&rarr;", "→");
+  ReplaceAll(&md_, "&amp;", '&');
+  ReplaceAll(&md_, "&nbsp;", ' ');
+  ReplaceAll(&md_, "&rarr;", "→");
 
   ReplaceAll(&md_, "\t\t  ", "\t\t");
 }
@@ -620,7 +620,7 @@ void Converter::TagBreak::OnHasLeftOpeningTag(Converter *c) {
     c->appendToMd(Repeat("  ", c->index_li));
   } else if (c->is_in_table_) {
     c->appendToMd("<br>");
-  } else if (!c->is_in_p_) {
+  } else if (!c->is_in_p_ && !c->prev_tag_.empty()) {
     c->appendToMd("\n<br>\n\n");
   } else if (c->md_.length() > 0)
     c->appendToMd("  \n");

{pyhtml2md-1.6.1 → pyhtml2md-1.6.4}/tests/test_advanced.py

@@ -55,6 +55,28 @@ def test_complex_formatting():
     assert "1. Numbered one" in result
     assert "2. Numbered two" in result
 
+def test_line_breaks():
+    # Test br outside paragraphs
+    assert "Text  \nText2" in pyhtml2md.convert("Text<br>Text2")
+    
+    # Test br inside paragraphs
+    assert "Line 1  \nLine 2" in pyhtml2md.convert("<p>Line 1<br>Line 2</p>")
+    
+    # Test br with bullet points in paragraph
+    assert "Primary Colors:  \n• Red  \n• Blue  \n• Yellow" in pyhtml2md.convert("<p>Primary Colors:<br>• Red<br>• Blue<br>• Yellow</p>")
+
+    # Test soft line break settings
+    html = "A very long line of text that should be wrapped according to the soft break and hard break settings"
+    options = pyhtml2md.Options()
+    options.splitLines = True
+    options.softBreak = 20
+    options.hardBreak = 30
+
+    converter = pyhtml2md.Converter(html, options)
+    result = converter.convert()
+    lines = result.split('\n')
+    assert any(len(line) <= 30 for line in lines)
+
 def test_table_formatting():
     html = """
     <table>
@@ -68,21 +90,8 @@ def test_table_formatting():
     result = converter.convert()
 
     assert "|" in result
-    # assert "Header 1" in result  # BUG: The generated table is wrong
     assert "Data 1" in result
 
-def test_line_breaks():
-    html = "A very long line of text that should be wrapped according to the soft break and hard break settings"
-    options = pyhtml2md.Options()
-    options.splitLines = True
-    options.softBreak = 20
-    options.hardBreak = 30
-
-    converter = pyhtml2md.Converter(html, options)
-    result = converter.convert()
-    lines = result.split('\n')
-    assert any(len(line) <= 30 for line in lines)
-
 def test_error_handling():
     # Test with malformed HTML
     html = "<p>Unclosed paragraph"
@@ -106,6 +115,18 @@ def test_special_characters():
     assert '"characters"' in result
     assert "&" in result
 
+def test_html_entities():
+    html = """
+    <p>&quot;Double quotes&quot; &lt;less than&gt; &gt;greater than&lt; &amp; ampersand &nbsp; non-breaking space &rarr; right arrow</p>
+    """
+    result = pyhtml2md.convert(html)
+    assert '"Double quotes"' in result
+    assert "<less than>" in result
+    assert ">greater than<" in result
+    assert "& ampersand" in result
+    assert " non-breaking space" in result
+    assert "→ right arrow" in result
+
 def test_nested_structures():
     html = """
     <blockquote>
@@ -122,4 +143,4 @@ def test_nested_structures():
     assert "**list**" in result
 
 if __name__ == "__main__":
-    pytest.main([__file__])
+    pytest.main([__file__])