Reworked Language Normalization logic and some fixes

Author: jessbryte

Pipfile

@@ -10,6 +10,7 @@ GitPython = "*"
 google-api-python-client = "*"
 h11 = ">=0.16.0"  # Ensure dependency is secure
 internetarchive = ">=5.5.1"
+iso639-lang = "*"
 jupyterlab = ">=3.6.7"
 matplotlib = "*"
 numpy = "*"
@@ -19,7 +20,6 @@ pillow = ">=11.3.0"  # Ensure dependency is secure
 Pyarrow = "*"
 Pygments = "*"
 python-dotenv = "*"
-python-iso639 = "*"
 requests = ">=2.31.0"
 seaborn = "*"
 urllib3 = ">=2.5.0"

Pipfile.lock

@@ -5,6 +5,7 @@
 "https://creativecommons.org/licenses/by-nc-sa/4.0","CC BY-NC-SA 4.0"
 "https://creativecommons.org/licenses/by-nd/4.0","CC BY-ND 4.0"
 "https://creativecommons.org/licenses/by-sa/4.0","CC BY-SA 4.0"
+"https://creativecommons.org/publicdomain/certification/1.0/us","CC PUBLIC DOMAIN 1.0 US"
 "https://creativecommons.org/publicdomain/mark/1.0","PDM 1.0"
 "https://creativecommons.org/publicdomain/zero/1.0","CC0 1.0"
 "https://creativecommons.org/licenses/by/3.0","CC BY 3.0"
@@ -648,6 +649,6 @@
 "https://creativecommons.org/licenses/nd-nc/1.0/nl","CC ND-NC 1.0 NL"
 "https://creativecommons.org/licenses/sa/1.0/nl","CC SA 1.0 NL"
 "https://creativecommons.org/licenses/nc-sampling+/1.0/tw","CC NC-SAMPLING+ 1.0 TW"
-"https://creativecommons.org/licenses/sampling/1.0/tw","CC SAMPLING 1.0 TW"
+"https://creativecommons.org/licenses/sampling/1.0/tw","CC CERTIFICATION 1.0 US
 "https://creativecommons.org/licenses/sampling+/1.0/tw","CC SAMPLING+ 1.0 TW"
 "https://creativecommons.org/licenses/publicdomain","CC PUBLICDOMAIN"