feature: string pattern anonymizer that fetches data from other anonymizers

Author: pounard

CHANGELOG.md

@@ -1,8 +1,12 @@
 # Changelog
 
+## Next
+
+* [feature] 🌟 String pattern anonymizer, build complex strings by fetching values from other anonymizers.
+
 ## 2.0.3
 
-* [FIX] Fix anonymization for MySQL version >=8.0 but <8.0.29 (#220).
+* [fix] Fix anonymization for MySQL version >=8.0 but <8.0.29 (#220).
 * [doc] Fix connection string examples (#219).
 
 ## 2.0.2

docs/content/anonymization/core-anonymizers.md

@@ -13,6 +13,7 @@ This page list all *Anonymizers* provided by *DbToolsBundle*.
 <!--@include: ./core-anonymizers/constant.md-->
 <!--@include: ./core-anonymizers/md5.md-->
 <!--@include: ./core-anonymizers/string.md-->
+<!--@include: ./core-anonymizers/pattern.md-->
 <!--@include: ./core-anonymizers/lastname.md-->
 <!--@include: ./core-anonymizers/firstname.md-->
 <!--@include: ./core-anonymizers/lorem-ipsum.md-->

docs/content/anonymization/core-anonymizers/pattern.md

@@ -0,0 +1,83 @@
+## String pattern
+
+Anonymize by building text values using other anonymizers to fill holes in text.
+
+### String range
+
+By adding `[MIN,MAX]` anywhere in your text, it will be replaced by a random integer
+in the given range. For example `"I want [7-111] apples"`.
+
+You can use negative integers such as `[-10,10]` or even a fully negative integer
+range `[-127,-34]`.
+
+### Single value from another anonymizer
+
+By adding `{ANONYMIZER}` anywhere in your text, it will be replaced by a random value
+given by the anonymizer. For example `"My email address is {email}, what's your ?"`.
+
+:::warning
+The target anonymizer must not be a column anonymizer.
+:::
+
+### Column value from another anonymizer
+
+By adding `{ANONYMIZER:COLUMN}` anywhere in your text, it will be replaced by a random
+value for the named column given by the anonymizer. For example, `"The country I live into is {address:country}."`.
+
+If you use more than one column of the same anonymizer in the same text value, the same
+generated row from the target anonymizer will be used. For example, this text will give
+a consistent result: `"The country I live in {address:locality} in {address:country}."`.
+
+:::warning
+The target anonymizer must be a column anonymizer.
+:::
+
+### Usage
+
+@@@ standalone docker
+
+```yaml [YAML]
+# db_tools.config.yaml
+anonymization:
+    default:
+        customer:
+            biography:
+                anonymizer: pattern
+                options: {value: '{firstname} {lastname} lives in {address:locality} in {address:country}, he has [2,7] cats.'}
+  #...
+```
+
+@@@
+@@@ symfony
+
+::: code-group
+```php [Attribute]
+namespace App\Entity;
+
+use Doctrine\ORM\Mapping as ORM;
+use MakinaCorpus\DbToolsBundle\Attribute\Anonymize;
+
+#[ORM\Entity()]
+#[ORM\Table(name: 'customer')]
+class Customer
+{
+    // ...
+
+    #[ORM\Column]
+    #[Anonymize(type: 'pattern', options: ['value' => '{firstname} {lastname} lives in {address:locality} in {address:country}, he has [2,7] cats.'])] // [!code ++]
+    private ?string $biography = null;
+}
+```
+
+```yml [YAML]
+# config/anonymization.yaml
+
+customer:
+    biography:
+        anonymizer: pattern
+        options: {value: '{firstname} {lastname} lives in {address:locality} in {address:country}, he has [2,7] cats.'}
+#...
+```
+:::
+
+@@@

src/Anonymization/Anonymizer/AbstractMultipleColumnAnonymizer.php

@@ -15,6 +15,7 @@
 abstract class AbstractMultipleColumnAnonymizer extends AbstractTableAnonymizer
 {
     private ?string $sampleTableName = null;
+    private ?string $joinAlias = null;
 
     /**
      * Get column names.
@@ -81,16 +82,30 @@ public function initialize(): void
     #[\Override]
     public function anonymize(Update $update): void
     {
-        $columns = $this->getColumnNames();
+        $columnOptions = $this->getColumnOptions();
 
-        if (0 >= $this->options->count()) {
-            throw new \InvalidArgumentException(\sprintf(
-                "Options are empty. You should at least give one of those: %s",
-                \implode(', ', $columns)
-            ));
+        $expr = $update->expression();
+
+        $joinAlias = $this->addJoinToQuery($update);
+
+        foreach ($columnOptions as $column) {
+            $update->set(
+                $this->options->get($column),
+                $expr->column($column, $joinAlias)
+            );
+        }
+    }
+
+    /**
+     * Add sample table join to query and return its alias.
+     */
+    public function addJoinToQuery(Update $update): string
+    {
+        if ($this->joinAlias) {
+            return $this->joinAlias;
         }
 
-        $columnOptions = \array_filter($columns, fn ($column) => $this->options->has($column));
+        $columnOptions = $this->getColumnOptions();
 
         $expr = $update->expression();
 
@@ -130,12 +145,22 @@ public function anonymize(Update $update): void
             $joinAlias
         );
 
-        foreach ($columnOptions as $column) {
-            $update->set(
-                $this->options->get($column),
-                $expr->column($column, $joinAlias)
-            );
+        return $this->joinAlias = $joinAlias;
+    }
+
+    /** @return array<string> */
+    private function getColumnOptions(): array
+    {
+        $columns = $this->getColumnNames();
+
+        if (0 >= $this->options->count()) {
+            throw new \InvalidArgumentException(\sprintf(
+                "Options are empty. You should at least give one of those: %s",
+                \implode(', ', $columns)
+            ));
         }
+
+        return \array_filter($columns, fn ($column) => $this->options->has($column));
     }
 
     #[\Override]
@@ -149,6 +174,7 @@ public function clean(): void
                 ->dropTable($this->sampleTableName)
                 ->commit()
             ;
+            $this->sampleTableName = $this->joinAlias = null;
         }
     }
 }

src/Anonymization/Anonymizer/AnonymizerRegistry.php

@@ -27,6 +27,7 @@ class AnonymizerRegistry
         Core\NullAnonymizer::class,
         Core\PasswordAnonymizer::class,
         Core\StringAnonymizer::class,
+        Core\StringPatternAnonymizer::class,
     ];
 
     /** @var array<string, string> */
@@ -71,7 +72,14 @@ public function createAnonymizer(
     ): AbstractAnonymizer {
         $className = $this->getAnonymizerClass($name);
 
-        return new $className($config->table, $config->targetName, $databaseSession, $options);
+        $ret = new $className($config->table, $config->targetName, $databaseSession, $options);
+        \assert($ret instanceof AbstractAnonymizer);
+
+        if ($ret instanceof WithAnonymizerRegistry) {
+            $ret->setAnonymizerRegistry($this);
+        }
+
+        return $ret;
     }
 
     /**