From b30f4636a2acc36e69de79b09e77fd91d02f2017 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E2=80=9CKevin?= <kvnzavalza@hotmail.com>
Date: Thu, 2 Oct 2025 18:13:14 -0600
Subject: [PATCH 1/2] fix(clean): exclude text inside elements with class
 "star-pagination" add test case

---
 eyecite/clean.py       | 4 +++-
 tests/test_FindTest.py | 9 ++++++++-
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/eyecite/clean.py b/eyecite/clean.py
index d0fc1c5..11c6237 100644
--- a/eyecite/clean.py
+++ b/eyecite/clean.py
@@ -51,7 +51,9 @@ def html(html_content: str) -> str:
             parent::link |
             parent::head |
             parent::page-number |
-            parent::script)]"""
+            parent::script |
+            parent::*[@class="star-pagination"]
+            )]"""
     )
     return " ".join(text)
 
diff --git a/tests/test_FindTest.py b/tests/test_FindTest.py
index 13bfe01..6c05d00 100644
--- a/tests/test_FindTest.py
+++ b/tests/test_FindTest.py
@@ -828,7 +828,14 @@ def test_find_citations(self):
             # Fix for index error when searching for case name
             ("<p>State v. Luna-Benitez (S53965). Alternative writ issued, dismissed, 342 Or 255</p>",
             [case_citation(volume="342", reporter="Or", page="255")],
-            {'clean_steps': ['html', 'inline_whitespace']})
+            {'clean_steps': ['html', 'inline_whitespace']}),
+            # Test remove text with star-pagination class
+            ("<p>The somewhat similar cases of <i>Crane</i> v. <i>Hyde Park,</i> 135 <span class=\"star-pagination\">*355</span> Mass. 147, and <i>Mahoning County</i> v. <i>Young,</i> 16 U.S. App. 253, also cited by the defendant, likewise turned upon a question of forfeiture for breach of a condition subsequent in a deed to a municipal corporation.</p>",
+             [case_citation(volume="135", reporter="Mass.", page="147",
+                            metadata={"plaintiff": "Crane",
+                                      "defendant": "Hyde Park"}
+                            )],
+             {'clean_steps': ['html', 'inline_whitespace']})
         )
 
         # fmt: on

From 10c42daeb3ed12425e7e26d2808a6076f0da87bc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E2=80=9CKevin?= <kvnzavalza@hotmail.com>
Date: Thu, 2 Oct 2025 18:22:28 -0600
Subject: [PATCH 2/2] fix(clean): update CHANGES.md

---
 CHANGES.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/CHANGES.md b/CHANGES.md
index 8e4ab05..800c66f 100644
--- a/CHANGES.md
+++ b/CHANGES.md
@@ -12,6 +12,7 @@ Changes:
 
 Fixes:
 - Modifies rendering of AhocorasickTokenizer parameter in API docs II
+- Removed star-pagination markers from extracted text #293
 
 ## Current