Add --recursive mode for folders, update docs, improve headings parsing

See
#14
#13
#12
#11

DOCUMENTATION.md

@@ -1,7 +1,7 @@
 # Installation
 - Clone this project
 - Run `composer install`
-- test the console app: `php bin/console.php --help`
+- test the console app: `php bin/gsheet-to-xml.php --help`
 
 __Note__ Make sure you're using at least PHP 7.1
 
@@ -11,15 +11,18 @@ See: [How to: Google API Setup](https://github.com/forikal-uk/xml-authoring-libr
 
 
 # Usage
-`php bin/console.php forikal:gsheet-to-xml {URL} [--credentials=client_secret.json]`
+`php bin/gsheet-to-xml.php {URL} [--credentials=client_secret.json] [--recursive]`
 
 `{URL}` should be either Drive or Sheets URL in one of following formats
 - https://drive.google.com/drive/folders/xxxxxxxxxx-xxxxxxxxx-xxxxxxxxxxxx
 - https://docs.google.com/spreadsheets/d/xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx/edit
 
-`--credentials` is optional parameter that specifies path to the credentials file with Google secret. Path
+`-c, --credentials` is optional parameter that specifies path to the credentials file with Google secret. Path
 must be relative to the directory you're calling the script from.
 
+`-r, --recursive` if the Google Drive entity is a Google Drive folder, this option specifies whether or not to recurse 
+through sub-directories to find sheets.
+
 # Behavior
 
 - Empty rows are skipped without notice.

src/Application/Service/GoogleDriveFolderReadService.php

@@ -8,6 +8,9 @@
 
 class GoogleDriveFolderReadService
 {
+    const FOLDER_MIME_TYPE = 'application/vnd.google-apps.folder';
+    const SPREADSHEET_MIME_TYPE = 'application/vnd.google-apps.spreadsheet';
+
     /** @var Google_Client */
     private $client;
 
@@ -16,7 +19,7 @@ public function __construct(Google_Client $client)
         $this->client = $client;
     }
 
-    public function listSpreaadsheetsInFolder($folderId)
+    public function listSpreaadsheetsInFolder($folderId, bool $recursive)
     {
         $service = new Google_Service_Drive($this->client);
 
@@ -27,7 +30,7 @@ public function listSpreaadsheetsInFolder($folderId)
         // In the Drive API, a folder is essentially a file — one identified by the special
         // folder MIME type application/vnd.google-apps.folder
         $mimeType = $file->getMimeType();
-        if ('application/vnd.google-apps.folder' !== $mimeType) {
+        if (self::FOLDER_MIME_TYPE !== $mimeType) {
             throw new \Exception("File with ID $folderId is not Google Drive Folder");
         }
 
@@ -40,7 +43,14 @@ public function listSpreaadsheetsInFolder($folderId)
         $fileIds = [];
         /** @var Google_Service_Drive_DriveFile $childrenFile */
         foreach ($files as $childrenFile) {
-            if ('application/vnd.google-apps.spreadsheet' !== $childrenFile->getMimeType()) {
+
+            if (self::FOLDER_MIME_TYPE === $childrenFile->getMimeType() && true === $recursive) {
+                $subfolderSpreadsheets = $this->listSpreaadsheetsInFolder($childrenFile->getId(), true);
+                $fileIds = array_merge($fileIds, $subfolderSpreadsheets);
+                continue;
+            }
+
+            if (self::SPREADSHEET_MIME_TYPE !== $childrenFile->getMimeType()) {
                 continue;
             }
 

src/Application/Service/GoogleDriveProcessService.php

@@ -26,14 +26,14 @@ public function __construct(
         $this->xmlSerializer = $xmlSerializer;
     }
 
-    public function process($url)
+    public function process(string $url, bool $recursive)
     {
         if ($this->isSpreadsheet($url)) {
             return $this->processSpreadsheet($url);
         }
 
         if ($this->isFolder($url)) {
-            return $this->processFolder($url);
+            return $this->processFolder($url, $recursive);
         }
 
         throw new Exception('URL is not either Google Spreadsheet nor Google Drive Folder');
@@ -103,7 +103,7 @@ public function processSpreadsheet(string $url): string
         return $xml;
     }
 
-    public function processFolder(string $url)
+    public function processFolder(string $url, bool $recursive)
     {
         $folderId = $this->parseFolderIdFromUrl($url);
         if (true === empty($folderId)) {
@@ -112,12 +112,11 @@ public function processFolder(string $url)
 
         $client = $this->makeClient();
         $driveService = new GoogleDriveFolderReadService($client);
-        $spreadsheetFileIds = $driveService->listSpreaadsheetsInFolder($folderId);
+        $spreadsheetFileIds = $driveService->listSpreaadsheetsInFolder($folderId, $recursive);
 
         /**
          * Each Google Sheet tab represents one of these: <Product><Inventory>...data here..</Inventory></Product>.
          */
-
         $spreadsheetService = new GoogleSpreadsheetReadService($client);
         $inventories = [];
         foreach ($spreadsheetFileIds as $spreadsheetFileId) {

src/Application/Service/GoogleSpreadsheetReadService.php

@@ -95,8 +95,12 @@ private function combineSheetDataWithHeadings(array $data): array
                 continue;
             }
 
-            // First non-empty row are headings
-            if (true === empty($headings)) {
+            // Skip non-headings rows until we find headings
+            if (true === empty($headings) && false === $this->isHeadingsRow($row)) {
+                continue;
+            }
+
+            if (true === empty($headings) && true === $this->isHeadingsRow($row)) {
                 $headings = $row;
                 continue;
             }
@@ -127,4 +131,32 @@ private function isEmptyRow(?array $row): bool
 
         return false;
     }
+
+    private function isHeadingsRow(?array $row): bool
+    {
+        if (true === empty($row)) {
+            return false;
+        }
+
+        $firstCellValue = $row[0] ?? null;
+        if (true === empty($firstCellValue)) {
+            return false;
+        }
+
+        $headingValues = [
+            'Name',
+            'KNumberExists',
+            'KNumber',
+            'Quantity',
+            'AlternativeNumber',
+            'Purpose',
+            'PurposeOther',
+        ];
+
+        if (true === in_array(trim($firstCellValue), $headingValues)) {
+            return true;
+        }
+
+        return false;
+    }
 }

src/Application/Service/XmlSerializer.php

@@ -22,8 +22,8 @@ private function buildInventoryElement(DOMDocument $dom, Inventory $inventory)
     {
         $inventoryXmlElement = $dom->createElement('Inventory');
         $inventoryXmlElement->setAttribute('src-sheet', $inventory->getSpreadsheetName());
-        $inventoryXmlElement->setAttribute('src-sheet-url', $inventory->getSpreadsheetUrl());
         $inventoryXmlElement->setAttribute('src-tab', $inventory->getSheetName());
+        $inventoryXmlElement->setAttribute('src-sheet-url', $inventory->getSpreadsheetUrl());
 
         /** @var StockItem $stockItem */
         foreach ($inventory->getStockItems() as $stockItem) {

src/Command/GsheetToXmlCommand.php

@@ -31,12 +31,19 @@ protected function configure()
                 InputOption::VALUE_OPTIONAL,
                 'Path to the Google credentials JSON relative to the current working directory',
                 'client_secret.json'
+            )
+            ->addOption(
+                'recursive',
+                'r',
+                InputOption::VALUE_NONE,
+                'if the Google Drive entity is a Google Drive folder, this option specifies whether or not to recurse through sub-directories to find sheets.'
             );
     }
 
     protected function execute(InputInterface $input, OutputInterface $output)
     {
         $url = $input->getArgument('drive-url');
+        $recursive = $input->getOption('recursive');
 
         $credentialsPath = $input->getOption('credentials');
         $credentialsPath = getcwd() . '/' . ltrim($credentialsPath, '/');
@@ -49,7 +56,8 @@ protected function execute(InputInterface $input, OutputInterface $output)
         $inventoryFactory = new InventoryFactory();
 
         $service = new GoogleDriveProcessService($credentialsPath, $inventoryFactory, $serializer);
-        $xml = $service->process($url);
+        $xml = $service->process($url, $recursive
+        );
         $output->writeln($xml);
     }
 }

tests/Forikal/GsheetXml/Test/InventoryXmlSerializationTest.php

@@ -53,7 +53,7 @@ public function testSingleInventory()
 <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
 <Products>
   <Product>
-    <Inventory src-sheet="Spreadsheet x" src-sheet-url="https://docs.google.com/spreadsheets/d/xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx/edit" src-tab="Sheet 1">
+    <Inventory src-sheet="Spreadsheet x" src-tab="Sheet 1" src-sheet-url="https://docs.google.com/spreadsheets/d/xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx/edit">
       <StockItem>
         <KNumberExists>true</KNumberExists>
         <KNumber>111111</KNumber>