Remove entry object from column statistics

.github/CODEOWNERS

@@ -0,0 +1 @@
+* @norberttech

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,4 +1,8 @@
-<!-- Bellow section will be used to automatically generate changelog, please do not modify HTML code structure -->
+<!-- 
+    Below section will be used to automatically generate changelog, please do not modify HTML code structure
+    DO NOT REMOVE that HTML STRUCTURE, INSTEAD ADD YOUR CHANGES INSIDE THE LISTS 
+    PULL REQUESTS WITHOUT CHANGELOG CAN'T BE MERGED 
+-->
 <h2>Change Log</h2>
 <div id="change-log">
   <h4>Added</h4>

src/cli/src/Flow/CLI/Formatter/PipelineReportFormatter.php

@@ -53,7 +53,7 @@ public function format() : void
             foreach ($columnsStatistics->all() as $columnStatistics) {
                 $normalizedColumnStatistics[] = [
                     'name' => $columnStatistics->name(),
-                    'type' => $columnStatistics->type()->toString(),
+                    'type' => $schema ? $schema->get($columnStatistics->reference())->type()->toString() : 'N/A',
                     'nulls_count' => $valueFormatter->format($columnStatistics->nullCount()),
                     'distinct_count' => $valueFormatter->format($columnStatistics->distinctCount()),
                     'min' => $valueFormatter->format($columnStatistics->min()),

src/cli/tests/Flow/CLI/Tests/Integration/FileAnalyzeCommandTest.php

@@ -54,7 +54,7 @@ public function test_read_rows_csv() : void
 │ order_id   │ uuid                                                          │ 0     │ 5               │ -                         │ -                         │ -          │ -          │ -                  │ -                  │
 │ created_at │ datetime                                                      │ 0     │ 5               │ 2024-02-23T19:18:53+00:00 │ 2024-06-17T19:24:49+00:00 │ -          │ -          │ -                  │ -                  │
 │ updated_at │ datetime                                                      │ 0     │ 5               │ 2024-02-23T19:18:53+00:00 │ 2024-06-17T19:24:49+00:00 │ -          │ -          │ -                  │ -                  │
-│ discount   │ float                                                         │ 2     │ 3               │ 12.45                     │ 47.10                     │ -          │ -          │ -                  │ -                  │
+│ discount   │ ?float                                                        │ 2     │ 3               │ 12.45                     │ 47.10                     │ -          │ -          │ -                  │ -                  │
 │ address    │ map<string, string>                                           │ 0     │ 5               │ -                         │ -                         │ -          │ -          │ 4                  │ 4                  │
 │ notes      │ list<string>                                                  │ 0     │ 5               │ -                         │ -                         │ -          │ -          │ 1                  │ 5                  │
 │ items      │ list<structure{sku: string, quantity: integer, price: float}> │ 0     │ 5               │ -                         │ -                         │ -          │ -          │ 2                  │ 4                  │
@@ -67,4 +67,49 @@ public function test_read_rows_csv() : void
 
         self::assertStringContainsString("Execution Time", $tester->getDisplay());
     }
+
+    public function test_read_rows_csv_without_schema() : void
+    {
+        $application = new Application();
+        $application->add(new FileAnalyzeCommand());
+        $tester = new CommandTester($application->get('file:analyze'));
+
+        $tester->execute(['input-file' => __DIR__ . '/Fixtures/orders.csv', '--input-file-limit' => 5, '--stats-columns' => true]);
+
+        $tester->assertCommandIsSuccessful();
+
+        self::assertStringContainsString(
+            <<<'OUTPUT'
+Analyzing File
+==============
+
+ [INFO] File path: orders.csv
+OUTPUT,
+            $tester->getDisplay()
+        );
+
+        self::assertStringContainsString(
+            <<<'OUTPUT'
+Columns
+-------
+
+┌────────────┬──────┬───────┬─────────────────┬───────────────────────────┬───────────────────────────┬────────────┬────────────┬────────────────────┬────────────────────┐
+│ Name       │ Type │ Nulls │ Distinct Values │ Min                       │ Max                       │ Min Length │ Max Length │ Min Elements Count │ Max Elements Count │
+├────────────┼──────┼───────┼─────────────────┼───────────────────────────┼───────────────────────────┼────────────┼────────────┼────────────────────┼────────────────────┤
+│ order_id   │ N/A  │ 0     │ 5               │ -                         │ -                         │ -          │ -          │ -                  │ -                  │
+│ created_at │ N/A  │ 0     │ 5               │ 2024-02-23T19:18:53+00:00 │ 2024-06-17T19:24:49+00:00 │ -          │ -          │ -                  │ -                  │
+│ updated_at │ N/A  │ 0     │ 5               │ 2024-02-23T19:18:53+00:00 │ 2024-06-17T19:24:49+00:00 │ -          │ -          │ -                  │ -                  │
+│ discount   │ N/A  │ 2     │ 3               │ 12.45                     │ 47.10                     │ -          │ -          │ -                  │ -                  │
+│ address    │ N/A  │ 0     │ 5               │ -                         │ -                         │ -          │ -          │ 4                  │ 4                  │
+│ notes      │ N/A  │ 0     │ 5               │ -                         │ -                         │ -          │ -          │ 1                  │ 5                  │
+│ items      │ N/A  │ 0     │ 5               │ -                         │ -                         │ -          │ -          │ 2                  │ 4                  │
+└────────────┴──────┴───────┴─────────────────┴───────────────────────────┴───────────────────────────┴────────────┴────────────┴────────────────────┴────────────────────┘
+OUTPUT,
+            $tester->getDisplay()
+        );
+
+        self::assertStringContainsString("Analyzed Rows", $tester->getDisplay());
+
+        self::assertStringContainsString("Execution Time", $tester->getDisplay());
+    }
 }

src/core/etl/src/Flow/ETL/Dataset/Statistics/Column.php

@@ -4,8 +4,7 @@
 
 namespace Flow\ETL\Dataset\Statistics;
 
-use Flow\ETL\PHP\Type\Type;
-use Flow\ETL\Row\Entry;
+use Flow\ETL\Row\{Entry, Reference};
 
 final class Column
 {
@@ -25,23 +24,26 @@ final class Column
 
     private int $nullsCount = 0;
 
+    private readonly Reference $reference;
+
     /**
      * @param Entry<mixed, mixed> $entry
      *
      * @throws \JsonException
      */
-    public function __construct(public readonly Entry $entry)
+    public function __construct(Entry $entry)
     {
+        $this->reference = $entry->ref();
         $this->distinctCounter = new DistinctCounter();
-        $this->calculate($this->entry);
+        $this->calculate($entry);
     }
 
     /**
      * @param Entry<mixed, mixed> $entry
      */
     public function calculate(Entry $entry) : void
     {
-        if (!$entry->is($this->entry->name())) {
+        if (!$this->reference->is($entry->ref())) {
             return;
         }
 
@@ -134,19 +136,16 @@ public function minLength() : ?int
 
     public function name() : string
     {
-        return $this->entry->name();
+        return $this->reference->name();
     }
 
     public function nullCount() : int
     {
         return $this->nullsCount;
     }
 
-    /**
-     * @return Type<mixed>
-     */
-    public function type() : Type
+    public function reference() : Reference
     {
-        return $this->entry->type();
+        return $this->reference;
     }
 }