[Excel] Add a new Excel Adapter with an extractor (#1643)

Add a new Excel Adapter with an extractor

Author: stloyd

.github/workflows/monorepo-split.yml

@@ -55,8 +55,8 @@ jobs:
             split_repository: 'etl-adapter-doctrine'
           - local_path: 'src/adapter/etl-adapter-elasticsearch'
             split_repository: 'etl-adapter-elasticsearch'
-          - local_path: 'src/adapter/etl-adapter-meilisearch'
-            split_repository: 'etl-adapter-meilisearch'
+          - local_path: 'src/adapter/etl-adapter-excel'
+            split_repository: 'etl-adapter-excel'
           - local_path: 'src/adapter/etl-adapter-google-sheet'
             split_repository: 'etl-adapter-google-sheet'
           - local_path: 'src/adapter/etl-adapter-http'
@@ -65,6 +65,8 @@ jobs:
             split_repository: 'etl-adapter-json'
           - local_path: 'src/adapter/etl-adapter-logger'
             split_repository: 'etl-adapter-logger'
+          - local_path: 'src/adapter/etl-adapter-meilisearch'
+            split_repository: 'etl-adapter-meilisearch'
           - local_path: 'src/adapter/etl-adapter-parquet'
             split_repository: 'etl-adapter-parquet'
           - local_path: 'src/adapter/etl-adapter-text'

.github/workflows/test-suite.yml

@@ -223,6 +223,9 @@ jobs:
       - name: "Test - Adapter - Elasticsearch"
         run: "composer test:adapter:elasticsearch"
 
+      - name: "Test - Adapter - Excel"
+        run: "composer test:adapter:excel"
+
       - name: "Test - Adapter - Google Sheet"
         run: "composer test:adapter:google-sheet"
 

composer.json

@@ -30,6 +30,7 @@
         "halaxa/json-machine": "^1.1",
         "meilisearch/meilisearch-php": "^1.11",
         "monolog/monolog": "^2.0||^3.0",
+        "openspout/openspout": "^4.0",
         "packaged/thrift": "^0.15.0",
         "php-http/discovery": "^1.0",
         "psr/clock": "^1.0",
@@ -70,6 +71,7 @@
         "flow-php/etl-adapter-csv": "self.version",
         "flow-php/etl-adapter-doctrine": "self.version",
         "flow-php/etl-adapter-elasticsearch": "self.version",
+        "flow-php/etl-adapter-excel": "self.version",
         "flow-php/etl-adapter-filesystem": "self.version",
         "flow-php/etl-adapter-google-sheet": "self.version",
         "flow-php/etl-adapter-http": "self.version",
@@ -101,6 +103,7 @@
                 "src/adapter/etl-adapter-csv/src/Flow",
                 "src/adapter/etl-adapter-doctrine/src/Flow",
                 "src/adapter/etl-adapter-elasticsearch/src/Flow",
+                "src/adapter/etl-adapter-excel/src/Flow",
                 "src/adapter/etl-adapter-google-sheet/src/Flow",
                 "src/adapter/etl-adapter-http/src/Flow",
                 "src/adapter/etl-adapter-json/src/Flow",
@@ -139,6 +142,7 @@
             "src/adapter/etl-adapter-csv/src/Flow/ETL/Adapter/CSV/functions.php",
             "src/adapter/etl-adapter-doctrine/src/Flow/ETL/Adapter/Doctrine/functions.php",
             "src/adapter/etl-adapter-elasticsearch/src/Flow/ETL/Adapter/Elasticsearch/functions.php",
+            "src/adapter/etl-adapter-excel/src/Flow/ETL/Adapter/Excel/DSL/functions.php",
             "src/adapter/etl-adapter-google-sheet/src/Flow/ETL/Adapter/GoogleSheet/functions.php",
             "src/adapter/etl-adapter-json/src/Flow/ETL/Adapter/JSON/functions.php",
             "src/adapter/etl-adapter-meilisearch/src/Flow/ETL/Adapter/Meilisearch/functions.php",
@@ -168,6 +172,7 @@
                 "src/adapter/etl-adapter-csv/tests/Flow",
                 "src/adapter/etl-adapter-doctrine/tests/Flow",
                 "src/adapter/etl-adapter-elasticsearch/tests/Flow",
+                "src/adapter/etl-adapter-excel/tests/Flow",
                 "src/adapter/etl-adapter-google-sheet/tests/Flow",
                 "src/adapter/etl-adapter-http/tests/Flow",
                 "src/adapter/etl-adapter-json/tests/Flow",
@@ -240,6 +245,7 @@
             "@test:adapter:csv",
             "@test:adapter:doctrine",
             "@test:adapter:elasticsearch",
+            "@test:adapter:excel",
             "@test:adapter:google-sheet",
             "@test:adapter:http",
             "@test:adapter:json",
@@ -314,6 +320,10 @@
             "tools/phpunit/vendor/bin/phpunit --testsuite=adapter-elasticsearch-unit --log-junit ./var/phpunit/logs/adapter-elasticsearch-unit.junit.xml --coverage-clover=./var/phpunit/coverage/clover/adapter-elasticsearch-unit.coverage.xml --coverage-html=./var/phpunit/coverage/html/adapter-elasticsearch-unit",
             "tools/phpunit/vendor/bin/phpunit --testsuite=adapter-elasticsearch-integration --log-junit ./var/phpunit/logs/adapter-elasticsearch-integration.junit.xml --coverage-clover=./var/phpunit/coverage/clover/adapter-elasticsearch-integration.coverage.xml --coverage-html=./var/phpunit/coverage/html/adapter-elasticsearch-integration"
         ],
+        "test:adapter:excel": [
+            "tools/phpunit/vendor/bin/phpunit --testsuite=adapter-excel-unit --log-junit ./var/phpunit/logs/adapter-excel-unit.junit.xml --coverage-clover=./var/phpunit/coverage/clover/adapter-excel-unit.coverage.xml --coverage-html=./var/phpunit/coverage/html/adapter-excel-unit",
+            "tools/phpunit/vendor/bin/phpunit --testsuite=adapter-excel-integration --log-junit ./var/phpunit/logs/adapter-excel-integration.junit.xml --coverage-clover=./var/phpunit/coverage/clover/adapter-excel-integration.coverage.xml --coverage-html=./var/phpunit/coverage/html/adapter-excel-integration"
+        ],
         "test:adapter:google-sheet": [
             "tools/phpunit/vendor/bin/phpunit --testsuite=adapter-google-sheet-unit --log-junit ./var/phpunit/logs/adapter-google-sheet-unit.junit.xml --coverage-clover=./var/phpunit/coverage/clover/adapter-google-sheet-unit.coverage.xml --coverage-html=./var/phpunit/coverage/html/adapter-google-sheet-unit",
             "tools/phpunit/vendor/bin/phpunit --testsuite=adapter-google-sheet-integration --log-junit ./var/phpunit/coverage/clover/adapter-google-sheet-integration.junit.xml --coverage-clover=./var/phpunit/coverage/clover/adapter-google-sheet-integration.coverage.xml --coverage-html=./var/phpunit/coverage/html/adapter-google-sheet-integration"
@@ -416,6 +426,7 @@
             "./tools/phpdocumentor/vendor/bin/phpdoc --config=./phpdoc/adapter.csv.xml",
             "./tools/phpdocumentor/vendor/bin/phpdoc --config=./phpdoc/adapter.doctrine.xml",
             "./tools/phpdocumentor/vendor/bin/phpdoc --config=./phpdoc/adapter.elasticsearch.xml",
+            "./tools/phpdocumentor/vendor/bin/phpdoc --config=./phpdoc/adapter.excel.xml",
             "./tools/phpdocumentor/vendor/bin/phpdoc --config=./phpdoc/adapter.google-sheet.xml",
             "./tools/phpdocumentor/vendor/bin/phpdoc --config=./phpdoc/adapter.http.xml",
             "./tools/phpdocumentor/vendor/bin/phpdoc --config=./phpdoc/adapter.json.xml",

composer.lock

@@ -0,0 +1,64 @@
+# Excel Adapter 
+
+- [⬅️️ Back](../../introduction.md)
+- [📚API Reference](/documentation/api/adapter/excel)
+- [📁Files](/documentation/api/adapter/excel/indices/files.html)
+
+Flow PHP's Adapter Excel is a comprehensive library engineered to enable smooth interactions with Excel
+within your ETL (Extract, Transform, Load) workflows. This adapter is indispensable for developers looking to seamlessly
+extract from or load data into Excel, ensuring a coherent and reliable data transformation journey. By
+leveraging the Adapter Excel library, developers can utilize a robust set of features designed for precise
+interaction with Excel, simplifying complex data transformations and enhancing data processing efficiency. The
+Adapter Excel library encapsulates a wide range of functionalities, providing a streamlined API for managing
+Excel tasks, which is essential in modern data processing and transformation scenarios. This library reflects
+Flow PHP's dedication to offering versatile and effective data processing solutions, making it an optimal choice for
+developers dealing with Excel in large-scale and data-intensive projects. With Flow PHP's Adapter Excel,
+managing Excel data within your ETL workflows becomes a more simplified and efficient task, perfectly aligning
+with the robust and adaptable nature of the Flow PHP ecosystem.
+
+## Installation
+
+``` 
+composer require flow-php/etl-adapter-excel:~--FLOW_PHP_VERSION--
+```
+
+## Extractor
+
+```php
+<?php
+
+$rows = data_frame()
+    ->read(from_excel('path/to/your/excel.xlsx'))
+    ->fetch();
+```
+
+```php
+<?php
+
+$rows = data_frame()
+    ->read(from_excel('path/to/your/excel.ods'))
+    ->fetch();
+```
+
+```php
+<?php
+
+$rows = data_frame()
+    ->read(
+        from_excel('path/to/your/excel.xlsx')
+            ->withSheetName('Sheet name')
+    )
+    ->fetch();
+```
+
+```php
+<?php
+
+$rows = data_frame()
+    ->read(
+        from_excel('path/to/your/excel.xlsx')
+            ->withHeaders(false)
+            ->withOffset(5)
+    )
+    ->fetch();
+```

documentation/components/adapters/excel.md

@@ -39,7 +39,7 @@ $rows = (new Flow())
 
 > :warning: Heads up, TextLoader expects rows to have single entry in order to properly write them into file.
 
-```php 
+```php
 <?php
 
 use Flow\ETL\DSL\Text;