From e6ea7e97f44b3fef48cf524f505c10df2675084b Mon Sep 17 00:00:00 2001
From: ryanwdale <ryanwdale@gmail.com>
Date: Fri, 23 Apr 2021 20:39:13 -0700
Subject: [PATCH] fix(clean): escape apostrophes in code exported by clean_dupl

---
 dataprep/clean/clean_duplication_utils.py | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/dataprep/clean/clean_duplication_utils.py b/dataprep/clean/clean_duplication_utils.py
index 2139ed6ef..cb2bbb26a 100644
--- a/dataprep/clean/clean_duplication_utils.py
+++ b/dataprep/clean/clean_duplication_utils.py
@@ -219,9 +219,13 @@ def _create_replace_calls(
         df_name, col = self._df_name, f"'{self._col}'"
         replace_calls = []
         for idx, cluster in enumerate(cluster_page):
-            cluster_repr = f"'{new_values[idx]}'"
             if do_merge[idx]:
-                cluster_vals = [f"'{val}'" for val, _ in cluster if f"'{val}'" != cluster_repr]
+                # create the string that all the values in the cluster will be set to
+                cluster_repr = new_values[idx].replace("'", "\\'")
+                cluster_repr = f"'{cluster_repr}'"
+                # create the strings to be replaced
+                cluster_vals = [val.replace("'", "\\'") for val, _ in cluster]
+                cluster_vals = [f"'{val}'" for val in cluster_vals if f"'{val}'" != cluster_repr]
                 code = (
                     f"{df_name}[{col}] = {df_name}[{col}].replace"
                     f"([{', '.join(cluster_vals)}], {cluster_repr})"