diff --git a/stl/inc/__msvc_format_ucd_tables.hpp b/stl/inc/__msvc_format_ucd_tables.hpp
index 5f0d7161b2..61159396c0 100644
--- a/stl/inc/__msvc_format_ucd_tables.hpp
+++ b/stl/inc/__msvc_format_ucd_tables.hpp
@@ -4,7 +4,7 @@
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 
 // WARNING, this entire header is generated by
-// tools/unicode_properties_parse/grapheme_break_property_data_gen.py
+// tools/unicode_properties_parse/unicode_properties_data_gen.py
 // DO NOT MODIFY!
 
 // UNICODE, INC. LICENSE AGREEMENT - DATA FILES AND SOFTWARE
@@ -112,7 +112,7 @@ struct _Unicode_property_data {
 // The enums containing the values for the properties are also generated, in order to ensure they match
 // up correctly with how we're parsing them.
 //
-// All sets of data tables are generated by tools/unicode_properties_parse/grapheme_break_property_data_gen.py in the
+// All sets of data tables are generated by tools/unicode_properties_parse/unicode_properties_data_gen.py in the
 // https://github.com/microsoft/stl repository.
 //
 // The data format is a set of arrays for each character property. The first is an array of uint32_t encoding
diff --git a/tools/unicode_properties_parse/download_unicode_data_files.py b/tools/unicode_properties_parse/download_unicode_data_files.py
new file mode 100644
index 0000000000..bf5c587fd1
--- /dev/null
+++ b/tools/unicode_properties_parse/download_unicode_data_files.py
@@ -0,0 +1,23 @@
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+
+from urllib.request import urlretrieve
+
+
+Unicode_data_files = {
+    "DerivedCoreProperties.txt": "https://www.unicode.org/Public/UCD/latest/ucd/DerivedCoreProperties.txt",
+    "DerivedGeneralCategory.txt": "https://www.unicode.org/Public/UCD/latest/ucd/extracted/DerivedGeneralCategory.txt",
+    "EastAsianWidth.txt": "https://www.unicode.org/Public/UCD/latest/ucd/EastAsianWidth.txt",
+    "GraphemeBreakProperty.txt": "https://www.unicode.org/Public/UCD/latest/ucd/auxiliary/GraphemeBreakProperty.txt",
+    "GraphemeBreakTest.txt": "https://www.unicode.org/Public/UCD/latest/ucd/auxiliary/GraphemeBreakTest.txt",
+    "emoji-data.txt": "https://www.unicode.org/Public/UCD/latest/ucd/emoji/emoji-data.txt",
+}
+
+def download_unicode_data_files():
+    for filename, url in Unicode_data_files.items():
+        print(f"downloading {filename} from {url}")
+        urlretrieve(url, filename)
+
+
+if __name__ == "__main__":
+    download_unicode_data_files()
diff --git a/tools/unicode_properties_parse/grapheme_break_test_data_gen.py b/tools/unicode_properties_parse/grapheme_break_test_data_gen.py
index c7f85bac60..196f199c5b 100644
--- a/tools/unicode_properties_parse/grapheme_break_test_data_gen.py
+++ b/tools/unicode_properties_parse/grapheme_break_test_data_gen.py
@@ -91,7 +91,7 @@ def line_to_cpp_data_line_utf8(line: BreakTestItem) -> str:
 
 
 """
-Generate test data from "GraphemeBreakText.txt"
+Generate test data from "GraphemeBreakTest.txt"
 This file can be downloaded from: https://www.unicode.org/Public/UCD/latest/ucd/auxiliary/GraphemeBreakTest.txt
 This script looks for GraphemeBreakTest.txt in same directory as this script
 """
diff --git a/tools/unicode_properties_parse/grapheme_break_property_data_gen.py b/tools/unicode_properties_parse/unicode_properties_data_gen.py
similarity index 96%
rename from tools/unicode_properties_parse/grapheme_break_property_data_gen.py
rename to tools/unicode_properties_parse/unicode_properties_data_gen.py
index d330700495..706471c7f0 100644
--- a/tools/unicode_properties_parse/grapheme_break_property_data_gen.py
+++ b/tools/unicode_properties_parse/unicode_properties_data_gen.py
@@ -92,7 +92,7 @@ def compact_property_ranges(input: list[PropertyRange]) -> list[PropertyRange]:
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 
 // WARNING, this entire header is generated by
-// tools/unicode_properties_parse/grapheme_break_property_data_gen.py
+// tools/unicode_properties_parse/unicode_properties_data_gen.py
 // DO NOT MODIFY!
 
 // UNICODE, INC. LICENSE AGREEMENT - DATA FILES AND SOFTWARE
@@ -201,7 +201,7 @@ def compact_property_ranges(input: list[PropertyRange]) -> list[PropertyRange]:
 // The enums containing the values for the properties are also generated, in order to ensure they match
 // up correctly with how we're parsing them.
 //
-// All sets of data tables are generated by tools/unicode_properties_parse/grapheme_break_property_data_gen.py in the
+// All sets of data tables are generated by tools/unicode_properties_parse/unicode_properties_data_gen.py in the
 // https://github.com/microsoft/stl repository.
 //
 // The data format is a set of arrays for each character property. The first is an array of uint32_t encoding