Initial experiments using the new Database query logic with Condition…

…al Statistical Functions (#1880)

- Refactoring of the Statistical Conditional functions (`AVERAGEIF()`, `AVERAGEIFS()`, `COUNTIF()`, `COUNTIFS()`, `MAXIFS()` and `MINIFS()` to use the new Database functions codebase.
- Extended unit testing
- Fix handling for null values
- Fixes to wildcard text searches

There's still scope for further improvements to memory usage and performance; but for now the code is stable with all unit tests passing

CHANGELOG.md

@@ -9,8 +9,9 @@ and this project adheres to [Semantic Versioning](https://semver.org).
 
 ### Added
 
+- Implementation of the Excel `AVERAGEIFS()` functions as part of a restructuring of Database functions and Conditional Statistical functions.
 - Support for date values and percentages in query parameters for Database functions, and the IF expressions in functions like COUNTIF() and AVERAGEIF(). [#1875](https://github.com/PHPOffice/PhpSpreadsheet/pull/1875)
-- Support for booleans, and for wildcard text search in query parameters for Database functions. [#1876](https://github.com/PHPOffice/PhpSpreadsheet/pull/1876)
+- Support for booleans, and for wildcard text search in query parameters for Database functions, and the IF expressions in functions like COUNTIF() and AVERAGEIF(). [#1876](https://github.com/PHPOffice/PhpSpreadsheet/pull/1876)
 - Implemented DataBar for conditional formatting in Xlsx, providing read/write and creation of (type, value, direction, fills, border, axis position, color settings) as DataBar options in Excel. [#1754](https://github.com/PHPOffice/PhpSpreadsheet/pull/1754)
 - Alignment for ODS Writer [#1796](https://github.com/PHPOffice/PhpSpreadsheet/issues/1796)
 - Basic implementation of the PERMUTATIONA() Statistical Function

src/PhpSpreadsheet/Calculation/Calculation.php

@@ -343,12 +343,12 @@ class Calculation
         ],
         'AVERAGEIF' => [
             'category' => Category::CATEGORY_STATISTICAL,
-            'functionCall' => [Statistical::class, 'AVERAGEIF'],
+            'functionCall' => [Statistical\Conditional::class, 'AVERAGEIF'],
             'argumentCount' => '2,3',
         ],
         'AVERAGEIFS' => [
             'category' => Category::CATEGORY_STATISTICAL,
-            'functionCall' => [Functions::class, 'DUMMY'],
+            'functionCall' => [Statistical\Conditional::class, 'AVERAGEIFS'],
             'argumentCount' => '3+',
         ],
         'BAHTTEXT' => [
@@ -639,12 +639,12 @@ class Calculation
         ],
         'COUNTIF' => [
             'category' => Category::CATEGORY_STATISTICAL,
-            'functionCall' => [Statistical::class, 'COUNTIF'],
+            'functionCall' => [Statistical\Conditional::class, 'COUNTIF'],
             'argumentCount' => '2',
         ],
         'COUNTIFS' => [
             'category' => Category::CATEGORY_STATISTICAL,
-            'functionCall' => [Statistical::class, 'COUNTIFS'],
+            'functionCall' => [Statistical\Conditional::class, 'COUNTIFS'],
             'argumentCount' => '2+',
         ],
         'COUPDAYBS' => [
@@ -1630,7 +1630,7 @@ class Calculation
         ],
         'MAXIFS' => [
             'category' => Category::CATEGORY_STATISTICAL,
-            'functionCall' => [Statistical::class, 'MAXIFS'],
+            'functionCall' => [Statistical\Conditional::class, 'MAXIFS'],
             'argumentCount' => '3+',
         ],
         'MDETERM' => [
@@ -1675,7 +1675,7 @@ class Calculation
         ],
         'MINIFS' => [
             'category' => Category::CATEGORY_STATISTICAL,
-            'functionCall' => [Statistical::class, 'MINIFS'],
+            'functionCall' => [Statistical\Conditional::class, 'MINIFS'],
             'argumentCount' => '3+',
         ],
         'MINUTE' => [

src/PhpSpreadsheet/Calculation/Database.php

@@ -34,7 +34,7 @@ class Database
      *                                        the column label in which you specify a condition for the
      *                                        column.
      *
-     * @return float|string
+     * @return null|float|string
      */
     public static function DAVERAGE($database, $field, $criteria)
     {

src/PhpSpreadsheet/Calculation/Database/DAverage.php

@@ -29,7 +29,7 @@ class DAverage extends DatabaseAbstract
      *                              the column label in which you specify a condition for the
      *                              column.
      *
-     * @return float|string
+     * @return null|float|string
      */
     public static function evaluate($database, $field, $criteria)
     {

src/PhpSpreadsheet/Calculation/Database/DCountA.php

@@ -36,7 +36,7 @@ public static function evaluate($database, $field, $criteria)
         $field = self::fieldExtract($database, $field);
 
         return Statistical::COUNTA(
-            self::getFilteredColumn($database, $field, $criteria)
+            self::getFilteredColumn($database, $field ?? 0, $criteria)
         );
     }
 }

src/PhpSpreadsheet/Calculation/Database/DGet.php

@@ -44,6 +44,8 @@ public static function evaluate($database, $field, $criteria)
             return Functions::NAN();
         }
 
-        return $columnData[0];
+        $row = array_pop($columnData);
+
+        return array_pop($row);
     }
 }

src/PhpSpreadsheet/Calculation/Database/DatabaseAbstract.php

@@ -25,19 +25,20 @@ abstract public static function evaluate($database, $field, $criteria);
      *                                        represents the position of the column within the list: 1 for
      *                                        the first column, 2 for the second column, and so on.
      */
-    protected static function fieldExtract(array $database, $field): ?string
+    protected static function fieldExtract(array $database, $field): ?int
     {
         $field = strtoupper(Functions::flattenSingleValue($field));
-        $fieldNames = array_map('strtoupper', array_shift($database));
+        if ($field === '') {
+            return null;
+        }
 
+        $fieldNames = array_map('strtoupper', array_shift($database));
         if (is_numeric($field)) {
-            $keys = array_keys($fieldNames);
-
-            return $keys[$field - 1];
+            return ((int) $field) - 1;
         }
-        $key = array_search($field, $fieldNames);
+        $key = array_search($field, array_values($fieldNames), true);
 
-        return $key ?: null;
+        return ($key !== false) ? (int) $key : null;
     }
 
     /**
@@ -70,14 +71,19 @@ protected static function filter(array $database, array $criteria): array
         return self::executeQuery($database, $query, $criteriaNames, $fieldNames);
     }
 
-    protected static function getFilteredColumn(array $database, $field, array $criteria): array
+    protected static function getFilteredColumn(array $database, ?int $field, array $criteria): array
     {
         //    reduce the database to a set of rows that match all the criteria
         $database = self::filter($database, $criteria);
+        $defaultReturnColumnValue = ($field === null) ? 1 : null;
+
         //    extract an array of values for the requested column
         $columnData = [];
-        foreach ($database as $row) {
-            $columnData[] = ($field !== null) ? $row[$field] : true;
+        foreach ($database as $rowKey => $row) {
+            $keys = array_keys($row);
+            $key = $keys[$field] ?? null;
+            $columnKey = $key ?? 'A';
+            $columnData[$rowKey][$columnKey] = $row[$key] ?? $defaultReturnColumnValue;
         }
 
         return $columnData;

src/PhpSpreadsheet/Calculation/Internal/WildcardMatch.php

@@ -5,9 +5,9 @@
 class WildcardMatch
 {
     private const SEARCH_SET = [
-        '/([^~])(\*)/ui',
+        '/(?<!~)\*/ui',
         '/~\*/ui',
-        '/([^~])(\?)/ui',
+        '/(?<!~)\?/ui',
         '/~\?/ui',
     ];
 
@@ -20,6 +20,11 @@ class WildcardMatch
 
     public static function wildcard(string $wildcard): string
     {
+        // Preg Escape the wildcard, but protecting the Excel * and ? search characters
+        $wildcard = str_replace(['*', '?'], [0x1A, 0x1B], $wildcard);
+        $wildcard = preg_quote($wildcard);
+        $wildcard = str_replace([0x1A, 0x1B], ['*', '?'], $wildcard);
+
         return preg_replace(self::SEARCH_SET, self::REPLACEMENT_SET, $wildcard);
     }
 
@@ -29,6 +34,6 @@ public static function compare($value, string $wildcard): bool
             return true;
         }
 
-        return (bool) preg_match("/{$wildcard}/ui", $value);
+        return (bool) preg_match("/^{$wildcard}\$/mui", $value);
     }
 }

src/PhpSpreadsheet/Calculation/MathTrig.php

@@ -1281,7 +1281,7 @@ public static function SUM(...$args)
     /**
      * SUMIF.
      *
-     * Counts the number of cells that contain numbers within the list of arguments
+     * Totals the values of cells that contain numbers within the list of arguments
      *
      * Excel Function:
      *        SUMIF(value1[,value2[, ...]],condition)
@@ -1327,7 +1327,7 @@ public static function SUMIF($aArgs, $condition, $sumArgs = [])
     /**
      * SUMIFS.
      *
-     *    Counts the number of cells that contain numbers within the list of arguments
+     *    Totals the values of cells that contain numbers within the list of arguments
      *
      *    Excel Function:
      *        SUMIFS(value1[,value2[, ...]],condition)