Added better support for XML types into Flow (#474)

* Added better support for XML types into Flow * adjustments after code review
flow-php · Sep 6, 2023 · 57666bf · 57666bf
1 parent 8c704b1
commit 57666bf
Show file tree

Hide file tree

Showing 31 changed files with 1,145 additions and 406 deletions.
diff --git a/.php-cs-fixer.php b/.php-cs-fixer.php
diff --git a/composer.lock b/composer.lock
diff --git a/examples/data/salaries.xml b/examples/data/salaries.xml
@@ -0,0 +1,104 @@
+<Salaries>
+    <Month name="January">
+        <Department name="HR">
+            <TotalSalary>71883</TotalSalary>
+        </Department>
+        <Department name="Engineering">
+            <TotalSalary>192644</TotalSalary>
+        </Department>
+        <Department name="Finance">
+            <TotalSalary>174187</TotalSalary>
+        </Department>
+        <Department name="Marketing">
+            <TotalSalary>179932</TotalSalary>
+        </Department>
+        <Department name="Sales">
+            <TotalSalary>52056</TotalSalary>
+        </Department>
+    </Month>
+    <Month name="February">
+        <Department name="HR">
+            <TotalSalary>102342</TotalSalary>
+        </Department>
+        <Department name="Engineering">
+            <TotalSalary>111102</TotalSalary>
+        </Department>
+        <Department name="Finance">
+            <TotalSalary>81938</TotalSalary>
+        </Department>
+        <Department name="Marketing">
+            <TotalSalary>132202</TotalSalary>
+        </Department>
+        <Department name="Sales">
+            <TotalSalary>173225</TotalSalary>
+        </Department>
+    </Month>
+    <Month name="March">
+        <Department name="HR">
+            <TotalSalary>79619</TotalSalary>
+        </Department>
+        <Department name="Engineering">
+            <TotalSalary>99387</TotalSalary>
+        </Department>
+        <Department name="Finance">
+            <TotalSalary>198847</TotalSalary>
+        </Department>
+        <Department name="Marketing">
+            <TotalSalary>50550</TotalSalary>
+        </Department>
+        <Department name="Sales">
+            <TotalSalary>98212</TotalSalary>
+        </Department>
+    </Month>
+    <Month name="April">
+        <Department name="HR">
+            <TotalSalary>69721</TotalSalary>
+        </Department>
+        <Department name="Engineering">
+            <TotalSalary>151826</TotalSalary>
+        </Department>
+        <Department name="Finance">
+            <TotalSalary>158168</TotalSalary>
+        </Department>
+        <Department name="Marketing">
+            <TotalSalary>111872</TotalSalary>
+        </Department>
+        <Department name="Sales">
+            <TotalSalary>172334</TotalSalary>
+        </Department>
+    </Month>
+    <Month name="May">
+        <Department name="HR">
+            <TotalSalary>174220</TotalSalary>
+        </Department>
+        <Department name="Engineering">
+            <TotalSalary>164086</TotalSalary>
+        </Department>
+        <Department name="Finance">
+            <TotalSalary>104257</TotalSalary>
+        </Department>
+        <Department name="Marketing">
+            <TotalSalary>105817</TotalSalary>
+        </Department>
+        <Department name="Sales">
+            <TotalSalary>145490</TotalSalary>
+        </Department>
+    </Month>
+    <Month name="June">
+        <Department name="HR">
+            <TotalSalary>127383</TotalSalary>
+        </Department>
+        <Department name="Engineering">
+            <TotalSalary>52592</TotalSalary>
+        </Department>
+        <Department name="Finance">
+            <TotalSalary>71732</TotalSalary>
+        </Department>
+        <Department name="Marketing">
+            <TotalSalary>165083</TotalSalary>
+        </Department>
+        <Department name="Sales">
+            <TotalSalary>85138</TotalSalary>
+        </Department>
+    </Month>
+</Salaries>
diff --git a/examples/data/simple_items.xml b/examples/data/simple_items.xml
@@ -0,0 +1,10 @@
+<root>
+    <items>
+        <item><id>1</id></item>
+        <item><id>2</id></item>
+        <item><id>3</id></item>
+        <item><id>4</id></item>
+        <item><id>5</id></item>
+        <item><id>6</id></item>
+    </items>
+</root>
diff --git a/examples/topics/types/xml/reading.php b/examples/topics/types/xml/reading.php
@@ -0,0 +1,16 @@
+<?php
+
+declare(strict_types=1);
+
+use Flow\ETL\DSL\To;
+use Flow\ETL\DSL\XML;
+use Flow\ETL\Flow;
+
+require __DIR__ . '/../../../bootstrap.php';
+
+print "Reading XML dataset...\n";
+
+(new Flow())
+    ->read(XML::from(__FLOW_DATA__ . '/simple_items.xml', 'root/items/item'))
+    ->write(To::output(false))
+    ->run();
diff --git a/examples/topics/types/xml/salaries.php b/examples/topics/types/xml/salaries.php
@@ -0,0 +1,29 @@
+<?php
+
+declare(strict_types=1);
+
+use function Flow\ETL\DSL\ref;
+use Flow\ETL\DSL\To;
+use Flow\ETL\DSL\XML;
+use Flow\ETL\Flow;
+use Flow\ETL\GroupBy\Aggregation;
+
+require __DIR__ . '/../../../bootstrap.php';
+
+print "Reading XML dataset...\n";
+
+(new Flow())
+    ->read(XML::from(__FLOW_DATA__ . '/salaries.xml'))
+    ->withEntry('months', ref('row')->xpath('/Salaries/Month'))
+    ->withEntry('month', ref('months')->expand())
+    ->withEntry('month_name', ref('month')->domNodeAttribute('name'))
+    ->withEntry('departments', ref('month')->xpath('/Month/Department'))
+    ->withEntry('department', ref('departments')->expand())
+    ->withEntry('department_name', ref('department')->domNodeAttribute('name'))
+    ->withEntry('department_salary', ref('department')->xpath('/Department/TotalSalary')->domNodeValue())
+    ->drop('row', 'months', 'month', 'departments', 'department')
+    ->groupBy(ref('month_name'))
+    ->aggregate(Aggregation::sum(ref('department_salary')))
+    ->rename('department_salary_sum', 'total_monthly_salaries')
+    ->write(To::output(false))
+    ->run();