From 283a27a0af4c70d91695a146b7a6cbc82dc28098 Mon Sep 17 00:00:00 2001
From: Leonard Richardson <leonardr@segfault.org>
Date: Mon, 11 Oct 2021 16:37:41 -0400
Subject: Added special string classes, RubyParenthesisString and
 RubyTextString,   to make it possible to treat ruby text specially in
 get_text() calls.   [bug=1941980]

---
 bs4/tests/test_navigablestring.py | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'bs4/tests/test_navigablestring.py')

diff --git a/bs4/tests/test_navigablestring.py b/bs4/tests/test_navigablestring.py
index 2b76392..649acc0 100644
--- a/bs4/tests/test_navigablestring.py
+++ b/bs4/tests/test_navigablestring.py
@@ -6,6 +6,8 @@ from bs4.element import (
     Declaration,
     Doctype,
     NavigableString,
+    RubyParenthesisString,
+    RubyTextString,
     Script,
     Stylesheet,
     TemplateString,
@@ -128,3 +130,15 @@ class TestNavigableStringSubclasses(SoupTest):
         soup = self.soup(markup)
         assert markup == soup.template.encode("utf8")
 
+    def test_ruby_strings(self):
+        markup = "<ruby>漢 <rp>(</rp><rt>kan</rt><rp>)</rp> 字 <rp>(</rp><rt>ji</rt><rp>)</rp></ruby>"
+        soup = self.soup(markup)
+        assert isinstance(soup.rp.string, RubyParenthesisString)
+        assert isinstance(soup.rt.string, RubyTextString)
+
+        # Just as a demo, here's what this means for get_text usage.
+        assert "漢字" == soup.get_text(strip=True)
+        assert "漢(kan)字(ji)" == soup.get_text(
+            strip=True,
+            types=(NavigableString, RubyTextString, RubyParenthesisString)
+        )
-- 
cgit v1.2.3