Merge pull request #30 from YuriMB/substring_support

Added substring support for field actions
ppomes · Aug 23, 2024 · d1f3494 · d1f3494
2 parents 0233826 + 85bd320
commit d1f3494
Show file tree

Hide file tree

Showing 6 changed files with 75 additions and 1 deletion.
diff --git a/main/configparser.y b/main/configparser.y
@@ -91,7 +91,7 @@ static bool is_valid_json_path(const char *path);
 /* 
  * Flex tokens
  */
-%token SECRET STATS TABLES YES NO FIXEDNULL FIXED FIXEDQUOTED FIXEDUNQUOTED TEXTHASH EMAILHASH INTHASH TRUNCATE KEY APPENDKEY PREPENDKEY EQ LEFT RIGHT PYPATH PYSCRIPT PYDEF JSON PATH SEPARATEDBY
+%token SECRET STATS TABLES YES NO FIXEDNULL FIXED FIXEDQUOTED FIXEDUNQUOTED TEXTHASH EMAILHASH INTHASH TRUNCATE KEY APPENDKEY PREPENDKEY EQ LEFT RIGHT PYPATH PYSCRIPT PYDEF JSON PATH SEPARATEDBY SUBSTRING
 %token <strval> STRING IDENTIFIER
 %token <shortval> LENGTH
 
@@ -204,6 +204,8 @@ fieldaction:
   emailhash separated |
   inthash |
   inthash separated |
+  substring |
+  substring separated |
   key |
   appendkey |
   prependkey |
@@ -256,6 +258,13 @@ inthash:
                     workinfos.type = AM_INTHASH;
                     workinfos.len=(unsigned short)$2;
                  }
+
+substring:
+  SUBSTRING LENGTH {
+                    workinfos.type = AM_SUBSTRING;
+                    workinfos.len=(unsigned short)$2;
+                  }
+
 key:
   KEY {
         workinfos.type = AM_KEY;

diff --git a/main/configscanner.l b/main/configscanner.l
@@ -60,6 +60,7 @@ fixed                   { return FIXED; }
 texthash                { return TEXTHASH; }
 emailhash               { return EMAILHASH; }
 inthash                 { return INTHASH; }
+substring		{ return SUBSTRING; }
 truncate                { return TRUNCATE; }
 key                     { return KEY; }
 appendkey               { return APPENDKEY; }

diff --git a/main/myanon.c b/main/myanon.c
@@ -200,6 +200,11 @@ anonymized_res_st anonymize_token(bool quoted, anon_base_st *config, char *token
         res_st.len = MIN(SHA256_DIGEST_SIZE, config->len);
         make_readable_hash((unsigned char *)worktoken, worktokenlen, &res_st, '1', '9');
         break;
+    case AM_SUBSTRING:
+        res_st.len = MIN(worktokenlen, config->len);
+        DEBUG_MSG("%d, %d, %d", worktokenlen, config->len, res_st.len)
+        mystrcpy((char *)&(res_st.data[0]), worktoken, res_st.len + 1);
+        break;
 
 #ifdef HAVE_PYTHON
     case AM_PY:

diff --git a/main/myanon.h b/main/myanon.h
@@ -103,6 +103,7 @@ typedef enum anon_type
     AM_KEY,
     AM_APPENDKEY,
     AM_PREPENDKEY,
+    AM_SUBSTRING,
     AM_JSON,
 #ifdef HAVE_PYTHON
     AM_PY,

diff --git a/tests/test_substring.conf b/tests/test_substring.conf
@@ -0,0 +1,9 @@
+# Config file for test1.sql
+secret = 'lapin'
+stats  = 'no'
+
+tables = {
+   `minimal_table` = {
+     `minimal_col`      = substring 5
+    }
+}
diff --git a/tests/test_substring.sql b/tests/test_substring.sql
@@ -0,0 +1,49 @@
+-- MySQL dump 10.13  Distrib 8.3.0, for macos14.2 (arm64)
+--
+-- Host: 127.0.0.1    Database: minimal
+-- ------------------------------------------------------
+-- Server version	8.3.0
+
+/*!40101 SET @OLD_CHARACTER_SET_CLIENT=@@CHARACTER_SET_CLIENT */;
+/*!40101 SET @OLD_CHARACTER_SET_RESULTS=@@CHARACTER_SET_RESULTS */;
+/*!40101 SET @OLD_COLLATION_CONNECTION=@@COLLATION_CONNECTION */;
+/*!50503 SET NAMES utf8mb4 */;
+/*!40103 SET @OLD_TIME_ZONE=@@TIME_ZONE */;
+/*!40103 SET TIME_ZONE='+00:00' */;
+/*!40014 SET @OLD_UNIQUE_CHECKS=@@UNIQUE_CHECKS, UNIQUE_CHECKS=0 */;
+/*!40014 SET @OLD_FOREIGN_KEY_CHECKS=@@FOREIGN_KEY_CHECKS, FOREIGN_KEY_CHECKS=0 */;
+/*!40101 SET @OLD_SQL_MODE=@@SQL_MODE, SQL_MODE='NO_AUTO_VALUE_ON_ZERO' */;
+/*!40111 SET @OLD_SQL_NOTES=@@SQL_NOTES, SQL_NOTES=0 */;
+
+--
+-- Table structure for table `minimal_table`
+--
+
+DROP TABLE IF EXISTS `minimal_table`;
+/*!40101 SET @saved_cs_client     = @@character_set_client */;
+/*!50503 SET character_set_client = utf8mb4 */;
+CREATE TABLE `minimal_table` (
+  `minimal_col` varchar(1024) DEFAULT NULL
+) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_0900_ai_ci;
+/*!40101 SET character_set_client = @saved_cs_client */;
+
+--
+-- Dumping data for table `minimal_table`
+--
+
+LOCK TABLES `minimal_table` WRITE;
+/*!40000 ALTER TABLE `minimal_table` DISABLE KEYS */;
+INSERT INTO `minimal_table` VALUES ('minimaal zo veel'),('🥳');
+/*!40000 ALTER TABLE `minimal_table` ENABLE KEYS */;
+UNLOCK TABLES;
+/*!40103 SET TIME_ZONE=@OLD_TIME_ZONE */;
+
+/*!40101 SET SQL_MODE=@OLD_SQL_MODE */;
+/*!40014 SET FOREIGN_KEY_CHECKS=@OLD_FOREIGN_KEY_CHECKS */;
+/*!40014 SET UNIQUE_CHECKS=@OLD_UNIQUE_CHECKS */;
+/*!40101 SET CHARACTER_SET_CLIENT=@OLD_CHARACTER_SET_CLIENT */;
+/*!40101 SET CHARACTER_SET_RESULTS=@OLD_CHARACTER_SET_RESULTS */;
+/*!40101 SET COLLATION_CONNECTION=@OLD_COLLATION_CONNECTION */;
+/*!40111 SET SQL_NOTES=@OLD_SQL_NOTES */;
+
+-- Dump completed on 2024-08-13 15:47:46