From 7ba8431c86c77bc03bbb5f3b5ffbc581e1e9e46e Mon Sep 17 00:00:00 2001
From: Gregory Anders <8965202+gpanders@users.noreply.github.com>
Date: Tue, 16 Jan 2024 11:13:43 -0600
Subject: [PATCH] Ignore <p> tags in table rows (#354)

Closes #198
Co-authored-by: Alireza Savand <591113+Alir3z4@users.noreply.github.com>
---
 ChangeLog.rst           |  2 ++
 html2text/__init__.py   |  2 ++
 test/no_p_in_table.html | 12 ++++++++++++
 test/no_p_in_table.md   | 15 +++++++++++++++
 4 files changed, 31 insertions(+)
 create mode 100644 test/no_p_in_table.html
 create mode 100644 test/no_p_in_table.md
diff --git a/ChangeLog.rst b/ChangeLog.rst
index caf2f78..b648fe4 100644
--- a/ChangeLog.rst
+++ b/ChangeLog.rst
@@ -8,6 +8,8 @@ UNRELEASED
 * Fix extra line breaks inside html link text (between '[' and ']')
 * Fix #344: indent ``<ul>`` inside ``<ol>`` three spaces instead of two to comply with CommonMark, GFM, etc.
 * Fix #324: unnecessary spaces around ``<b>``, ``<em>``, and ``strike`` tags.
+* Don't wrap tables by default and add a ``--wrap-tables`` config option.
+* Feature #198: Ignore ``<p>`` tags inside table rows.
 * Don't wrap tables by default and add a ``--wrap-tables`` config option
 * Remove support for Python ≤ 3.5. Now requires Python 3.6+.
 * Support for Python 3.10.
diff --git a/html2text/__init__.py b/html2text/__init__.py
index 89b98a1..ae4e154 100644
--- a/html2text/__init__.py
+++ b/html2text/__init__.py
@@ -367,6 +367,8 @@ def handle_tag(
                     self.soft_br()
             elif self.astack:
                 pass
+            elif self.split_next_td:
+                pass
             else:
                 self.p()
 
diff --git a/test/no_p_in_table.html b/test/no_p_in_table.html
new file mode 100644
index 0000000..73c1bb8
--- /dev/null
+++ b/test/no_p_in_table.html
@@ -0,0 +1,12 @@
+<!DOCTYPE html> <html>
+    <head lang="en"> <meta charset="UTF-8"> <title></title> </head>
+    <body> <h1>This is a test document</h1> With some text, <code>code</code>, <b>bolds</b> and <i>italics</i>.  <h2>This is second header</h2> <p style="display: none">Displaynone text</p> 
+    <table>
+        <tr> <th>Header 1</th> <th>Header 2</th> <th>Header 3</th> </tr>
+        <tr> <td><p>Content 1</p></td> <td><p>2</p></td> <td><img src="http://lorempixel.com/200/200" alt="200"/> Image!</td> </tr>
+        <tr> <td><p>Content 1 longer</p></td> <td><p>Content 2</p></td> <td><p>blah</p></td> </tr>
+        <tr> <td><p>Content </p></td> <td><p>Content 2</p></td> <td><p>blah</p></td> </tr>
+        <tr> <td><p>t </p></td> <td><p>Content 2</p></td> <td><p>blah blah blah</p></td> </tr>
+    </table>
+
+  </body> </html>
diff --git a/test/no_p_in_table.md b/test/no_p_in_table.md
new file mode 100644
index 0000000..f22449e
--- /dev/null
+++ b/test/no_p_in_table.md
@@ -0,0 +1,15 @@
+# This is a test document
+
+With some text, `code`, **bolds** and _italics_.
+
+## This is second header
+
+Displaynone text
+
+Header 1 | Header 2 | Header 3  
+---|---|---  
+Content 1 | 2 | ![200](http://lorempixel.com/200/200) Image!  
+Content 1 longer | Content 2 | blah  
+Content  | Content 2 | blah  
+t  | Content 2 | blah blah blah
+

Header 1	Header 2	Header 3
Content 1	2	Image!
Content 1 longer	Content 2	blah
Content	Content 2	blah
t	Content 2	blah blah blah