merge with dev

Signed-off-by: Isaac Milarsky <imilarsky@gmail.com>

README.md

@@ -170,6 +170,14 @@ the American public, but you are also welcome to submit anonymously.
 
 For more information about our Security, Vulnerability, and Responsible Disclosure Policies, see [SECURITY.md](SECURITY.md).
 
+### Software Bill of Materials (SBOM)
+
+A Software Bill of Materials (SBOM) is a formal record containing the details and supply chain relationships of various components used in building software.
+
+In the spirit of [Executive Order 14028 - Improving the Nation’s Cyber Security](https://www.gsa.gov/technology/it-contract-vehicles-and-purchasing-programs/information-technology-category/it-security/executive-order-14028), a SBOM for this repository is provided here: https://github.com/DSACMS/dedupliFHIR/network/dependencies.
+
+For more information and resources about SBOMs, visit: https://www.cisa.gov/sbom.
+
 ## Public domain
 
 This project is in the public domain within the United States, and copyright and related rights in the work worldwide are waived through the [CC0 1.0 Universal public domain dedication](https://creativecommons.org/publicdomain/zero/1.0/) as indicated in our [LICENSE](LICENSE).

cli/deduplifhirLib/normalization.py

@@ -4,6 +4,7 @@
 import re
 from dateutil import parser as date_parser
 from dateutil.parser import ParserError
+from text_to_num import alpha2digit
 
 NAME_ABBREVIATION_SYMBOLS = {
     ' jr ': 'junior',
@@ -307,6 +308,10 @@ def normalize_addr_text(input_text):
     """
     text_copy = input_text
     #text_copy = british_to_american(text_copy) not needed
+    try:
+        text_copy = alpha2digit(text_copy,"en")
+    except ValueError:
+        ...
     text_copy = remove_non_alphanum(text_copy)
     print(text_copy)
     text_copy = replace_abbreviations(text_copy.lower())
@@ -318,9 +323,12 @@ def normalize_addr_text(input_text):
     NAME_TEXT = "Greene,Jacquleine"
     print(normalize_name_text(NAME_TEXT))
 
-    PLACE_TEXT = "7805 Kartina Motorawy Apt. 313,Taylorstad,New Hampshire"
+    PLACE_TEXT = "7805 Kartina Motorawy Apt. three hundred thirteen ,Taylorstad,New Hampshire"
 
     print(normalize_addr_text(PLACE_TEXT))
 
     DATE_TEXT = "December 10, 1999"
     print(normalize_date_text(DATE_TEXT))
+
+    NUM_TEXT = "I have one hundred twenty three apples and forty-five oranges. Valetnine"
+    print(alpha2digit(NUM_TEXT,'en'))

pyproject.toml

@@ -16,6 +16,7 @@ openpyxl = "^3.1.2"
 lxml = "^5.2.2"
 pyarrow = "^16.1.0"
 python-dateutil = "^2.9.0.post0"
+text2num = "^2.5.1"
 
 [tool.poetry.dev-dependencies]
 black = "^24.4.2"