added pii redactor

Signed-off-by: Maroun Touma <touma@us.ibm.com>

transforms/packaging/python/Makefile

@@ -15,8 +15,11 @@ PACKAGING_RUN_TIME=python
 
 #Excluded List
 # ./code/malware
-# ./language/pii_redactor
 # ./universal/html2parquet
+# ./universal/profiler      # Missing implementation 
+# ./universal/fdedup 	    # Missing implementation
+#  code/repo_level_ordering # Missing implementation
+
 
 TRANSFORMS_NAMES = code/code_quality \
 	    	code/code2parquet \
@@ -26,6 +29,7 @@ TRANSFORMS_NAMES = code/code_quality \
 		language/doc_quality \
 		language/lang_id \
 		language/pdf2parquet \
+		language/pii_redactor \
 		language/text_encoder \
 		universal/ededup \
 		universal/filter \

transforms/packaging/python/requirements.transforms.python.txt

@@ -3,15 +3,13 @@ bs4==0.0.2
 #docling 1.9.0 depends on docling-parse<2.0.0 and >=1.1.3
 #pdf2parquet depends on docling-parse==1.0.0
 #docling 1.8.5 depends on docling-parse<2.0.0 and >=1.1.3
-docling-parse>=1.0.0,
+#docling-parse>=1.0.0,
 # language/doc_chunk has conflict dependencies with pdf2parquet that need to be resolved
 # doc_chunk depends on docling>=1.8.2,<2.0.0
 # pdf2parquet depends on docling==1.7.0
 #docling==1.7.0,
-docling>=1.8.2,<2.0.0,
-llama-index-core>=0.11.1,<0.12.0,
-docling-core>=1.1.2,<2.0.0,
-quackling==0.1.1,
+docling==1.8.5,
+quackling==0.4.0,
 # quackling will pull 
 #  docling>=1.8.2,<2.0.0 
 #  llama-index-core<0.12.0,>=0.11.1
@@ -29,4 +27,10 @@ scancode-toolkit==32.1.0 ; platform_system != 'Darwin'
 sentence-transformers==3.0.1
 transformers==4.38.2
 xxhash==3.4.1
+# PII-redactor
+presidio-analyzer>=2.2.355
+presidio-anonymizer>=2.2.355
+flair>=0.14.0
+pandas>=2.2.2
+
 

transforms/packaging/ray/Makefile

@@ -27,6 +27,7 @@ TRANSFORMS_NAMES = code/proglang_select \
 	language/doc_quality \
 	language/lang_id \
 	language/text_encoder \
+	language/pii_redactor \
 	language/pdf2parquet \
 	universal/fdedup \
 	universal/tokenization \