From 5c1d8d9ce5eb0f91376bbb844f2fb4d91700e566 Mon Sep 17 00:00:00 2001
From: Rohit kumar <rohittourister@gmail.com>
Date: Tue, 9 Jan 2024 20:56:23 +0530
Subject: [PATCH] Added text module to connect with other programms, so that
 they can import it

---
 hawk_scanner/commands/text.py | 47 +++++++++++++++++++++++++++++++++++
 hawk_scanner/main.py          | 43 +++++++++++++++++++++++++-------
 setup.py                      |  2 +-
 3 files changed, 82 insertions(+), 10 deletions(-)
 create mode 100644 hawk_scanner/commands/text.py

diff --git a/hawk_scanner/commands/text.py b/hawk_scanner/commands/text.py
new file mode 100644
index 0000000..8781c83
--- /dev/null
+++ b/hawk_scanner/commands/text.py
@@ -0,0 +1,47 @@
+from hawk_scanner.internals import system
+from rich.console import Console
+
+console = Console()
+
+def check_data_patterns(value, patterns, profile_name):
+    value_str = str(value)
+    matches = system.match_strings(value_str)
+    results = []
+    if matches:
+        for match in matches:
+            results.append({
+                'pattern_name': match['pattern_name'],
+                'matches': match['matches'],
+                'sample_text': match['sample_text'],
+                'profile': profile_name,
+                'data_source': 'text'
+            })
+    return results
+
+def execute(args, programmatic=False):
+    results = []
+    system.print_info(f"Running Checks for Simple text")
+    connections = system.get_connection()
+    patterns = system.get_fingerprint_file()
+    
+    if not programmatic:
+        if 'sources' in connections:
+            sources_config = connections['sources']
+            text_config = sources_config.get('text')
+
+            if text_config:
+                for key, config in text_config.items():
+                    text = config.get('text', None)
+                    results += check_data_patterns(text, patterns, key)
+            else:
+                system.print_error("No text connection details found in connection.yml")
+        else:
+            system.print_error("No 'sources' section found in connection.yml")
+    else:
+        text = args.get('text', None)
+        results += check_data_patterns(text, patterns, 'text')
+    return results
+
+# Example usage
+if __name__ == "__main__":
+    execute(None)
diff --git a/hawk_scanner/main.py b/hawk_scanner/main.py
index 720e2ef..029bcfc 100644
--- a/hawk_scanner/main.py
+++ b/hawk_scanner/main.py
@@ -21,7 +21,7 @@ def clear_screen():
 console = Console()
 
 ## Now separate the results by data_source
-data_sources = ['s3', 'mysql', 'redis', 'firebase', 'gcs', 'fs', 'postgresql', 'mongodb', 'slack', 'couchdb', 'gdrive', 'gdrive_workspace']
+data_sources = ['s3', 'mysql', 'redis', 'firebase', 'gcs', 'fs', 'postgresql', 'mongodb', 'slack', 'couchdb', 'gdrive', 'gdrive_workspace', 'text']
 
 def load_command_module(command):
     try:
@@ -71,13 +71,16 @@ def main():
         grouped_results[data_source].append(result)
     
     if args.json:
-        with open(args.json, 'w') as file:
-            #file_path = file_path.replace('-runtime.pdf', '')
-            if 'gdrive_workspace' in grouped_results:
-                for result in grouped_results['gdrive_workspace']:
-                    result['file_name'] = result['file_name'].replace('-runtime.pdf', '')
-                
-            file.write(json.dumps(grouped_results, indent=4))
+        if args.json != '':
+            with open(args.json, 'w') as file:
+                #file_path = file_path.replace('-runtime.pdf', '')
+                if 'gdrive_workspace' in grouped_results:
+                    for result in grouped_results['gdrive_workspace']:
+                        result['file_name'] = result['file_name'].replace('-runtime.pdf', '')
+                    
+                file.write(json.dumps(grouped_results, indent=4))
+        else:
+            print(json.dumps(grouped_results, indent=4))
         system.print_success(f"Results saved to {args.json}")
         sys.exit(0)
     panel = Panel(Text("Now, lets look at findings!", justify="center"))
@@ -109,7 +112,6 @@ def main():
         elif group == 'gdrive_workspace':
             table.add_column("File Name")
             table.add_column("User")
-
         table.add_column("Pattern Name")
         table.add_column("Total Exposed")
         table.add_column("Exposed Values")
@@ -455,6 +457,29 @@ def main():
                     exposed_values=records_mini
                 )
                 
+                system.SlackNotify(AlertMsg)
+            elif group == 'text':
+                table.add_row(
+                    str(i),
+                    result['profile'],
+                    result['pattern_name'],
+                    str(len(result['matches'])),
+                    records_mini,
+                    result['sample_text'],
+                )
+                AlertMsg = """
+                *** PII Or Secret Found ***
+                Data Source: Text - {vulnerable_profile}
+                Pattern Name: {pattern_name}
+                Total Exposed: {total_exposed}
+                Exposed Values: {exposed_values}
+                """.format(
+                    vulnerable_profile=result['profile'],
+                    pattern_name=result['pattern_name'],
+                    total_exposed=str(len(result['matches'])),
+                    exposed_values=records_mini
+                )
+                
                 system.SlackNotify(AlertMsg)
             else:
                 # Handle other cases or do nothing for unsupported groups
diff --git a/setup.py b/setup.py
index 6d04828..3e9c387 100644
--- a/setup.py
+++ b/setup.py
@@ -1,4 +1,4 @@
-VERSION = "0.3.7"
+VERSION = "0.3.8"
 
 from setuptools import setup, find_packages