From 927b91951820ce3793baad174f0898ca01705191 Mon Sep 17 00:00:00 2001
From: dionjoshualobo <23h13.joshua@sjec.ac.in>
Date: Fri, 7 Nov 2025 08:35:37 +0530
Subject: [PATCH 1/3] Updated gitignore and requirements

---
 .gitignore       | 1 +
 requirements.txt | 8 +++++++-
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/.gitignore b/.gitignore
index d6f6a5a..e13f817 100644
--- a/.gitignore
+++ b/.gitignore
@@ -5,6 +5,7 @@ __pycache__/
 *.so
 .Python
 build/
+output
 develop-eggs/
 dist/
 downloads/
diff --git a/requirements.txt b/requirements.txt
index d7778da..e69a34b 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -3,4 +3,10 @@ pandas>=2.0.0
 numpy>=1.24.0
 scikit-learn>=1.3.0
 python-dateutil>=2.8.0
-setuptools>=65.0.0
\ No newline at end of file
+setuptools>=65.0.0
+
+# PII Detection and Anonymization (for cleaning.py)
+presidio-analyzer>=2.2.0
+presidio-anonymizer>=2.2.0
+spacy>=3.7.0
+# Download spaCy model with: python -m spacy download en_core_web_sm
\ No newline at end of file

From f1af97f7c9bafacb353a6986e8d3a68d1c9d37e9 Mon Sep 17 00:00:00 2001
From: Chaithz <chaithanyakulal22@gmail.com>
Date: Fri, 7 Nov 2025 09:30:45 +0530
Subject: [PATCH 2/3] feat: csv generator

---
 discovery/main.py | 169 +++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 146 insertions(+), 23 deletions(-)

diff --git a/discovery/main.py b/discovery/main.py
index 03715b2..96fa8e7 100644
--- a/discovery/main.py
+++ b/discovery/main.py
@@ -1,44 +1,167 @@
 import csv
 import re
 from pathlib import Path
+from collections import Counter
+from datetime import datetime
 
-ROOT = Path("../../archiv/Data/Politics")
+ROOT = Path("../Data/Politics")
 
-email_re = re.compile(r"[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+")
-phone_re = re.compile(r"(?:\+?\d{1,3}[-.\s]?)?(?:\(?\d{2,4}\)?[-.\s]?)?\d{3,4}[-.\s]?\d{3,4}")
-ssn_re = re.compile(r"\b\d{3}[-\s]?\d{2}[-\s]?\d{4}\b")
-uuid_re = re.compile(r"\b[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{12}\b")
-pan_re = re.compile(r"\b[A-Z]{5}\d{4}[A-Z]\b")
-iban_re = re.compile(r"\b[A-Z]{2}\d{2}[A-Z0-9]{1,30}\b")
+# Try to import spaCy, fall back to basic extraction if not available
+try:
+    import spacy
+    nlp = spacy.load("en_core_web_sm")
+    USE_SPACY = True
+except:
+    USE_SPACY = False
 
+# Regex patterns for deterministic detection
 patterns = {
-    "EMAIL": email_re,
-    "PHONE": phone_re,
-    "SSN": ssn_re,
-    "UUID": uuid_re,
-    "PAN": pan_re,
-    "IBAN": iban_re,
+    "EMAIL": re.compile(r"[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+"),
+    "PHONE": re.compile(r"(?:\+?\d{1,3}[-.\s]?)?(?:\(?\d{2,4}\)?[-.\s]?)?\d{3,4}[-.\s]?\d{3,4}"),
+    "UUID": re.compile(r"\b[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{12}\b"),
+    "IBAN": re.compile(r"\b[A-Z]{2}\d{2}[A-Z0-9]{1,30}\b"),
+    "DATE": re.compile(r"\b\d{1,2}[/-]\d{1,2}[/-]\d{2,4}\b|\b\d{4}[/-]\d{1,2}[/-]\d{1,2}\b|(?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)[a-z]* \d{1,2},? \d{4}"),
+    "URL": re.compile(r"https?://[^\s]+"),
+    "SSN": re.compile(r"\b\d{3}-\d{2}-\d{4}\b"),
 }
 
 def find_entities(text):
-    found = []
+    """Extract entities using regex patterns."""
+    found = {}
     for label, pattern in patterns.items():
-        for m in pattern.finditer(text):
-            found.append(f"{label}: {m.group(0)}")
+        matches = pattern.findall(text)
+        if matches:
+            found[label] = list(set(matches))[:5]  # Limit to 5 per type
     return found
 
-with open("discovery_dataset.csv", "w", newline="", encoding="utf-8") as csvfile:
-    writer = csv.writer(csvfile)
-    writer.writerow(["filename", "text", "detected_entities"])
+def extract_with_spacy(text):
+    """Extract named entities using spaCy."""
+    if not USE_SPACY:
+        return {}, {}, {}
+    
+    doc = nlp(text[:10000])  # Limit text length for performance
+    
+    persons = []
+    orgs = []
+    locations = []
+    
+    for ent in doc.ents:
+        if ent.label_ == "PERSON":
+            persons.append(ent.text)
+        elif ent.label_ == "ORG":
+            orgs.append(ent.text)
+        elif ent.label_ in ["GPE", "LOC"]:
+            locations.append(ent.text)
+    
+    # Return most common entities
+    return (
+        dict(Counter(persons).most_common(5)),
+        dict(Counter(orgs).most_common(5)),
+        dict(Counter(locations).most_common(5))
+    )
 
+def extract_metadata(text, filename):
+    """Extract basic metadata from text."""
+    metadata = {
+        "char_count": len(text),
+        "word_count": len(text.split()),
+        "line_count": text.count('\n') + 1,
+        "file_extension": Path(filename).suffix,
+    }
+    return metadata
+
+def detect_content_type(text):
+    """Heuristic content type detection."""
+    text_lower = text.lower()
+    
+    # Check for common document types
+    if any(word in text_lower[:1000] for word in ['dear', 'sincerely', 'regards']):
+        return "letter"
+    elif any(word in text_lower[:500] for word in ['article', 'section', 'amendment']):
+        return "legal"
+    elif any(word in text_lower[:500] for word in ['press release', 'for immediate release']):
+        return "press_release"
+    elif re.search(r'^\s*#', text[:100], re.MULTILINE):
+        return "markdown"
+    elif '<html' in text_lower[:200]:
+        return "html"
+    else:
+        return "unknown"
+
+# Define fieldnames
+fieldnames = [
+    "filename", "file_extension", "char_count", "word_count", "line_count",
+    "content_type", "text_preview",
+    "EMAIL", "PHONE", "UUID", "IBAN", "DATE", "URL", "SSN",
+    "persons", "organizations", "locations"
+]
+
+print("Processing files...")
+with open("discovery_dataset.csv", "w", newline="", encoding="utf-8") as csvfile:
+    writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
+    writer.writeheader()
+    
+    file_count = 0
     for path in ROOT.rglob("*"):
         if not path.is_file():
             continue
+        
+        # Skip binary files
+        if path.suffix.lower() in ['.exe', '.dll', '.so', '.dylib', '.bin', '.jpg', '.png', '.gif', '.pdf']:
+            continue
+        
         try:
             text = path.read_text(encoding="utf-8", errors="ignore")
-        except Exception:
+        except Exception as e:
+            print(f"  Error reading {path.name}: {e}")
             continue
-
+        
+        if not text.strip():
+            continue
+        
+        file_count += 1
+        if file_count % 10 == 0:
+            print(f"Processed {file_count} files...")
+        
+        # Initialize row
+        row = {"filename": str(path.relative_to(ROOT.parent))}
+        
+        # Extract metadata
+        metadata = extract_metadata(text, path.name)
+        row.update(metadata)
+        
+        # Detect content type
+        row["content_type"] = detect_content_type(text)
+        row["text_preview"] = text[:500].replace('\n', ' ').replace('\r', ' ')
+        
+        # Extract entities with regex
         entities = find_entities(text)
-        if text.strip():  # skip empty
-            writer.writerow([str(path), text[:5000], "; ".join(entities)])  # limit length if huge
+        for key, values in entities.items():
+            row[key] = "; ".join(values) if values else ""
+        
+        # Fill in missing pattern fields
+        for pattern_key in ["EMAIL", "PHONE", "UUID", "IBAN", "DATE", "URL", "SSN"]:
+            if pattern_key not in row:
+                row[pattern_key] = ""
+        
+        # Extract named entities with spaCy
+        if USE_SPACY:
+            persons, orgs, locs = extract_with_spacy(text)
+            row["persons"] = "; ".join([f"{k}({v})" for k, v in persons.items()])
+            row["organizations"] = "; ".join([f"{k}({v})" for k, v in orgs.items()])
+            row["locations"] = "; ".join([f"{k}({v})" for k, v in locs.items()])
+        else:
+            row["persons"] = ""
+            row["organizations"] = ""
+            row["locations"] = ""
+        
+        writer.writerow(row)
+
+print(f"\nComplete! Processed {file_count} files.")
+print(f"Output: discovery_dataset.csv")
+
+# Print summary statistics
+if file_count > 0:
+    print("\nTo install spaCy for better entity extraction:")
+    print("  pip install spacy")
+    print("  python -m spacy download en_core_web_sm")
\ No newline at end of file

From 8ead47d54daa05e167e7db58abc5412bb3fcd920 Mon Sep 17 00:00:00 2001
From: Chaithz <chaithanyakulal22@gmail.com>
Date: Fri, 7 Nov 2025 09:32:16 +0530
Subject: [PATCH 3/3] ignore data dir

---
 .gitignore | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/.gitignore b/.gitignore
index d6f6a5a..a637d67 100644
--- a/.gitignore
+++ b/.gitignore
@@ -56,4 +56,6 @@ reports/*.pdf
 
 # Data (keep demo dataset)
 *.csv
-!Datasets/loan_data.csv
\ No newline at end of file
+!Datasets/loan_data.csv
+
+Data
\ No newline at end of file