New field added client-secret for Azure client secret ID.

docs/gh_pages/docs/entityclassifier.md

@@ -31,6 +31,7 @@ Below is the list of `entities` supported by Pebblo -
 1. RSA Private Key
 1. Google Account Private Key
 1. Github Fine Grained Token
+1. Azure Client Secret Key
 
 
 User can get details of classified entities for their loader source files in Pebblo report.  

pebblo/entity_classifier/README.md

@@ -25,6 +25,7 @@ And following Secret Entities:
 10. RSA Private Key
 11. Google Account Private Key
 12. Github Fine Grained Token
+13. Azure Client Secret Key
 
 ## How to use
 Entity Classifier

pebblo/entity_classifier/utils/config.py

@@ -11,7 +11,7 @@
     "aws-access-key": ["aws_access_key", "aws_key", "access", "id", "api"],
     "aws-secret-key": ["aws_secret_key", "secret"],
     "azure-key-id": ["azure_key", "azure_key_id", "azure_id", "key"],
-    "azure-client-secret": ["azure_client_secret", "client", "secret"],
+    "azure-client-secret": ["azure_client_secret", "client-secret", "client_secret"],
     "google-api-key": ["google_api_key", "google_key", "google"],
 }
 

pebblo/entity_classifier/utils/regex_pattern.py

@@ -12,6 +12,6 @@
     "aws-access-key": r"""\b((?:AKIA|ABIA|ACCA|ASIA)[0-9A-Z]{16})\b""",
     "aws-secret-key": r"""\b([A-Za-z0-9+/]{40})[ \r\n'"\x60]""",
     "azure-key-id": r"""(?i)(%s).{0,20}([a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})""",
-    "azure-client-secret": r"""\b(?i)(%s).{0,20}([a-z0-9_\.\-~]{34})\b""",
+    "azure-client-secret": r"""\b[a-fA-F0-9]{8}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{12}\b""",
     "google-api-key": r"""\bAIza[0-9A-Za-z\-_]{35}\b""",
 }

tests/entity_classifier/mock_response.py

@@ -1,28 +1,27 @@
 mock_input_text1_anonymize_snippet_true = """
-<PERSON>'s SSN is <US_SSN>.
+Sachin's SSN is <US_SSN>.
 ITIN number <US_ITIN>
 His AWS Access Key is: <AWS_ACCESS_KEY>.
-And <PERSON> is: <GITHUB_TOKEN>
+And Github Token is: <GITHUB_TOKEN>
 """
 
 mock_input_text2_anonymize_snippet_true = """
 Content
-"<PERSON> board on <DATE_TIME> announced an interim dividend of Re 1 per equity share of the face value of Rs 2 each, i.e., a 50 per cent payout for <DATE_TIME> along with financial results for the <DATE_TIME> period of the company for <DATE_TIME>."
-"<PERSON> reminded the board of the scheduled retreat coming up in <DATE_TIME>, and provided a drafted retreat schedule. The board provided feedback on the agenda and the consensus was that, outside of making a few minor changes, the committee should move forward as planned. No board action required."
+"Wipros board on Friday, January 12 announced an interim dividend of Re 1 per equity share of the face value of Rs 2 each, i.e., a 50 per cent payout for the current financial year along with financial results for the October-December period of the company for the financial year ending March 2024."
+"Roberts reminded the board of the scheduled retreat coming up in three months, and provided a drafted retreat schedule. The board provided feedback on the agenda and the consensus was that, outside of making a few minor changes, the committee should move forward as planned. No board action required."
 "Claims: An adaptive pacing system for implantable cardiac devices, comprising a pulse generator, multiple sensing electrodes, a microprocessor-based control unit, a wireless communication module, and memory for dynamically adjusting pacing parameters based on real-time physiological data.  The system of claim 1, wherein the adaptive pacing algorithms include rate-responsive pacing based on physical activity.  The system of claim 1, further comprising an external monitoring system for remote data access and modification of pacing parameters."
-"<PERSON>'s SSN is <US_SSN>. His passport ID is 5484880UA.  
-<PERSON>'s driver's license number is <NRP>.  
-<PERSON>'s bank account number is 70048841700216300.  
-His <NRP> express credit card number is <CREDIT_CARD>.  
-His UK IBAN Code is <IBAN_CODE>.  
-ITIN number <US_ITIN>. 
-Azure client secret : c4cb6f91-15a7-4e6d-a824-abcdef012345.  
-AWS Access Key is: <AWS_ACCESS_KEY> 
-AWS Secret Key is : <AWS_SECRET_KEY>
-Github Token is: <GITHUB_TOKEN> 
-Google API key: <PERSON><PERSON> is: <SLACK_TOKEN> 
-Azure Client Secret - c4cb6f91-15a7-4e6d-a824-abcdef012345 
-<PERSON> - <SLACK_TOKEN> 
+"Sachin's SSN is <US_SSN>. His passport ID is 5484880UA.
+Sachin's driver's license number is <US_DRIVER_LICENSE>.
+Sachin's bank account number is <US_BANK_NUMBER>.
+His American express credit card number is <CREDIT_CARD>.
+His UK IBAN Code is <IBAN_CODE>.
+ITIN number <US_ITIN>.
+AWS Access Key is: <AWS_ACCESS_KEY>
+AWS Secret Key is : <AWS_SECRET_KEY>Github Token is: <GITHUB_TOKEN>
+Google API key: zaCELgL0imfnc8mVLWwsAawjYr4Rx-Af50DDqtlx
+Slack Token is: <SLACK_TOKEN>
+Slack Token - <SLACK_TOKEN>
 Google API key- KLzaSyB_tWrbmfWx8g2bzL7Vhq7znuTUn0JPKmY"
-IP Address - <IP_ADDRESS>
+My IP Address - <IP_ADDRESS>
+Azure client_secret is <AZURE_CLIENT_SECRET>
 """

tests/entity_classifier/test_data.py

@@ -10,26 +10,51 @@
 "Wipros board on Friday, January 12 announced an interim dividend of Re 1 per equity share of the face value of Rs 2 each, i.e., a 50 per cent payout for the current financial year along with financial results for the October-December period of the company for the financial year ending March 2024."
 "Roberts reminded the board of the scheduled retreat coming up in three months, and provided a drafted retreat schedule. The board provided feedback on the agenda and the consensus was that, outside of making a few minor changes, the committee should move forward as planned. No board action required."
 "Claims: An adaptive pacing system for implantable cardiac devices, comprising a pulse generator, multiple sensing electrodes, a microprocessor-based control unit, a wireless communication module, and memory for dynamically adjusting pacing parameters based on real-time physiological data.  The system of claim 1, wherein the adaptive pacing algorithms include rate-responsive pacing based on physical activity.  The system of claim 1, further comprising an external monitoring system for remote data access and modification of pacing parameters."
-"Sachin's SSN is 222-85-4836. His passport ID is 5484880UA.  
-Sachin's driver's license number is S9998888.  
-Sachin's bank account number is 70048841700216300.  
-His American express credit card number is 371449635398431.  
-His UK IBAN Code is AZ96AZEJ00000000001234567890.  
-ITIN number 993-77 0690. 
-Azure client secret : c4cb6f91-15a7-4e6d-a824-abcdef012345.  
-AWS Access Key is: AKIAQIPT4PDORIRTV6PH 
-AWS Secret Key is : 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 
-Github Token is: ghp_hgu657yiujgwfrtigu3ver238765tyuhygvtrder6t7gyvhbuy5e676578976tyghy76578uygfyfgcyturtdf 
-Google API key: zaCELgL0imfnc8mVLWwsAawjYr4Rx-Af50DDqtlx 
-Slack Token is: xoxp-7676545380258-uygh 
-Azure Client Secret - c4cb6f91-15a7-4e6d-a824-abcdef012345 
-Slack Token - xoxb-3204014939555-4519358291237-TTIf0243T8YFSAGEVr1wBrWE 
+"Sachin's SSN is 222-85-4836. His passport ID is 5484880UA.
+Sachin's driver's license number is S9998888.
+Sachin's bank account number is 70048841700216300.
+His American express credit card number is 371449635398431.
+His UK IBAN Code is AZ96AZEJ00000000001234567890.
+ITIN number 993-77 0690.
+AWS Access Key is: AKIAQIPT4PDORIRTV6PH
+AWS Secret Key is : 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
+Github Token is: ghp_hgu657yiujgwfrtigu3ver238765tyuhygvtrder6t7gyvhbuy5e676578976tyghy76578uygfyfgcyturtdf
+Google API key: zaCELgL0imfnc8mVLWwsAawjYr4Rx-Af50DDqtlx
+Slack Token is: xoxp-7676545380258-uygh
+Slack Token - xoxb-3204014939555-4519358291237-TTIf0243T8YFSAGEVr1wBrWE
 Google API key- KLzaSyB_tWrbmfWx8g2bzL7Vhq7znuTUn0JPKmY"
-My IP Address - 10.55.60.61 
+My IP Address - 10.55.60.61
+Azure client_secret is de1d4a2d-d9fa-44f1-84bb-4f73c004afda
 """
 
 negative_data = """
 Sachin's SSN is 222-85.
 His AWS Access Key is: AKIPT4PDORIRTV6PH.
 And Github Token is: ghpu657yiujgwfrtigu3ver238765tyuhygvtrder6t7gyvhbuy5e676578976tyghy76578uygfyfgcyturtdf
 """
+
+tf_test_data = """
+variable "client_secret" {
+}
+
+# We strongly recommend using the required_providers block to set the
+# Azure Provider source and version being used
+terraform {
+  required_providers {
+    azurerm = {
+      source  = "hashicorp/azurerm"
+      version = "~> 4.x"
+    }
+  }
+}
+
+# Configure the Microsoft Azure Provider
+provider "azurerm" {
+  features {}
+
+  client_id       = "00000000-0000-0000-0000-000000000000"
+  client_secret   = "1131a1fc-8cee-4f3c-9b2f-6808f66f72a4"
+  tenant_id       = "10000000-0000-0000-0000-000000000000"
+  subscription_id = "20000000-0000-0000-0000-000000000000"
+}
+"""