export the data to Excel

README.md

@@ -1,4 +1,13 @@
 # MAXQDA HTML to Ecel
 The aim of this project is to create a propper excel-file from the html output of the paraphrases.
 
-The project does not need a database.
+The project does not need a database-server. It is able to work ith SQLite.
+
+## stack
+- Laravel 8
+- spatie/simple-excel
+- PHP 8.1
+- SQLite
+
+## Licence
+This package is free to use as stated by the [LICENCE.md](LICENSE.md) under the MIT License, but you can [buy me a coffee](https://www.buymeacoffee.com/redFreak) if you want :D.

app/Console/Commands/ExcelExportCommand.php

@@ -0,0 +1,249 @@
+<?php
+
+namespace App\Console\Commands;
+
+use App\Models\Editor;
+use App\Models\Interview;
+use App\Models\Paraphrase;
+use Box\Spout\Common\Entity\Style\Style;
+use Carbon\Carbon;
+use Illuminate\Console\Command;
+use Illuminate\Database\Eloquent\Collection as EloquentCollection;
+use Illuminate\Support\Collection as SupportCollection;
+use Iterator;
+use OpenSpout\Common\Entity\Style\Color;
+use OpenSpout\Writer\Common\Creator\Style\StyleBuilder;
+use Spatie\SimpleExcel\SimpleExcelWriter;
+use Str;
+
+class ExcelExportCommand extends Command
+{
+    /**
+     * The name and signature of the console command.
+     *
+     * @var string
+     */
+    protected $signature = 'maxqda:export';
+
+    /**
+     * The console command description.
+     *
+     * @var string
+     */
+    protected $description = 'Exports the paraphrases into an Excel-file (imported by mayqda:import)';
+
+    /**
+     * Execute the console command.
+     *
+     * @return int
+     */
+    public function handle()
+    {
+        // prepare our Excel-file
+        $now = new Carbon();
+        $simpleExcelWriter = SimpleExcelWriter::create(
+            storage_path('exports/export_'. Str::slug($now->toDateTimeString()) . '.xlsx')
+        );
+        $writer = $simpleExcelWriter->getWriter();
+
+        // set header style
+        /** @var Style $style */
+        $style = (new StyleBuilder())
+            ->setFontBold()
+            ->setFontColor(Color::BLACK)
+            ->setShouldWrapText()
+            ->setBackgroundColor(Color::LIGHT_BLUE)
+            ->build();
+        $simpleExcelWriter->setHeaderStyle($style);
+
+        $interviews = Interview::all();
+        $interview_last = $interviews->last();
+
+        $interviews->each(function (Interview $interview) use ($writer, $simpleExcelWriter, $interview_last) {
+            // set the interview name as sheet name
+            $writer->getCurrentSheet()->setName($interview->id);
+
+            // collect and sort the data
+            $editors = $interview->editors->unique();
+            $paraphrasesByEditor = $this->getParaphrasesByEditors($editors, $interview);
+
+            // write the paraphrases to the sheet
+            $row = 1;
+            $editorIterators = $this->getEditorIterators($paraphrasesByEditor);
+            // add rows
+            do {
+                if (!$this->isLoopContinued($editorIterators)) break;
+
+                $rowData = $this->getRowData($row, $editors, $editorIterators);
+                $simpleExcelWriter->addRow($rowData);
+
+                ++$row;
+            } while (true);
+
+            if (!$interview->is($interview_last)) {
+                $writer->addNewSheetAndMakeItCurrent();
+            }
+        });
+
+        return Command::SUCCESS;
+    }
+
+    /**
+     * Sort the paraphrases by editor and within by position (12-45 (id: 42) < 12-43 (6) < 12 (12) < 12 (18))
+     *
+     * @param  EloquentCollection  $editors
+     * @param  Interview  $interview
+     *
+     * @return SupportCollection
+     */
+    private function getParaphrasesByEditors(EloquentCollection $editors, Interview $interview): SupportCollection
+    {
+        return $editors->mapWithKeys(
+            fn($editor) => [
+                $editor->name => $interview->paraphrases->where('editor_id', $editor->id)->sortBy(function (
+                    Paraphrase $paraphrase
+                ) {
+                    // sort order should be 12-47 before 12-46 before 12, but all with 12 in order of reading it to the db
+                    $sortKey = Str::padLeft($paraphrase->position_start, 6, 0);
+                    $sortKey .= ($paraphrase->position_start === $paraphrase->position_end ? 999999 : Str::padLeft($paraphrase->position_end,
+                        6, 0));
+
+                    return $sortKey.Str::padLeft($paraphrase->id, 6, 0);
+                })
+            ]
+        );
+    }
+
+    /**
+     * @param  SupportCollection  $paraphrasesByEditor
+     *
+     * @return SupportCollection
+     */
+    private function getEditorIterators(SupportCollection $paraphrasesByEditor): SupportCollection
+    {
+        $editorIterators = new SupportCollection();
+        $paraphrasesByEditor->each(function (EloquentCollection $paraphrases, string $editorName) use (&$editorIterators
+        ) {
+            // make sure we iterate form the beginning and add the iterator
+            $iterator = $paraphrases->getIterator();
+//            $iterator->rewind();
+            $editorIterators->add(
+                $iterator
+            );
+        });
+
+        return $editorIterators;
+    }/**
+ * @param  int  $row
+ * @param  EloquentCollection  $editors
+ * @param  SupportCollection  $editorIterators
+ *
+ * @return array
+ */
+    private function getRowData(int $row, EloquentCollection $editors, SupportCollection $editorIterators): array
+    {
+        $rowData = [
+            '#' => $row,
+        ];
+
+        // collect the current paraphrases
+        $currentParaphrases = $this->getCurrentParaphrases($editors, $editorIterators);
+
+        // get the minimum start position
+        $positionStart = $currentParaphrases
+            ->min(fn(?Paraphrase $paraphrase) => $paraphrase?->position_start ?? 999999);
+        // get the maximum end position
+        $positionEnd = $currentParaphrases
+            ->where('position_start', '=', $positionStart)
+            ->max(fn(?Paraphrase $paraphrase) => $paraphrase->position_end);
+
+        // write the cells per editor
+        $editors->each(function (Editor $editor, int $editor_index) use (
+            &$editorIterators,
+            $currentParaphrases,
+            $positionStart,
+            $positionEnd,
+            &$rowData
+        ) {
+            $rowData = $this->getParaphraseCells($currentParaphrases, $editor_index, $positionStart, $positionEnd,
+                $editor, $editorIterators, $rowData);
+        });
+        $rowData['pos.'] = ($positionStart === $positionEnd ? $positionStart : $positionStart.' - '.$positionEnd);
+        $rowData['final paraphrase'] = '';
+        $rowData['parent encoding'] = '';
+        $rowData['category'] = '';
+
+        return $rowData;
+    }
+
+    /**
+     * @param  SupportCollection  $editorIterators
+     *
+     * @return bool
+     */
+    private function isLoopContinued(SupportCollection $editorIterators): bool
+    {
+        $continueLoop = false;
+        $editorIterators->each(function (Iterator $editorIterator) use (&$continueLoop) {
+            $continueLoop = $continueLoop || $editorIterator->valid();
+        });
+
+        return $continueLoop;
+    }
+
+    /**
+     * @param  EloquentCollection  $editors
+     * @param  SupportCollection  $editorIterators
+     *
+     * @return EloquentCollection
+     */
+    private function getCurrentParaphrases(
+        EloquentCollection $editors,
+        SupportCollection $editorIterators
+    ): EloquentCollection {
+        $currentParaphrases = new EloquentCollection();
+        $editors->each(
+            fn(
+                Editor $editor,
+                int $editor_index
+            ) => $currentParaphrases->add($editorIterators->get($editor_index)->current())
+        );
+
+        return $currentParaphrases;
+    }
+
+    /**
+     * @param  EloquentCollection  $currentParaphrases
+     * @param  int  $editor_index
+     * @param  mixed  $positionStart
+     * @param  mixed  $positionEnd
+     * @param  Editor  $editor
+     * @param  SupportCollection  $editorIterators
+     * @param  array  $rowData
+     *
+     * @return array
+     */
+    private function getParaphraseCells(
+        EloquentCollection $currentParaphrases,
+        int $editor_index,
+        mixed $positionStart,
+        mixed $positionEnd,
+        Editor $editor,
+        SupportCollection $editorIterators,
+        array $rowData
+    ): array {
+        /** @var Paraphrase $paraphrase */
+        $paraphrase = $currentParaphrases->get($editor_index);
+        if ($paraphrase?->position_start === $positionStart && $paraphrase->position_end === $positionEnd) {
+            // write the data
+            $rowData[$editor->name] = $paraphrase->paraphrase;
+            // and advance the iterator
+            $editorIterators->get($editor_index)->next();
+        } else {
+            // write an empty cell
+            $rowData[$editor->name] = '-';
+        }
+
+        return $rowData;
+    }
+}

app/Models/Editor.php

@@ -26,6 +26,6 @@ public function paraphrases()
 
     public function interviews()
     {
-        return $this->hasManyThrough(Interview::class, Paraphrase::class);
+        return $this->belongsToMany(Interview::class, 'paraphrases');
     }
 }

app/Models/Interview.php

@@ -26,6 +26,6 @@ public function paraphrases()
 
     public function editors()
     {
-        return $this->hasManyThrough(Editor::class, Paraphrase::class);
+        return $this->belongsToMany(Editor::class, 'paraphrases');
     }
 }

composer.json

@@ -9,7 +9,8 @@
         "guzzlehttp/guzzle": "^7.2",
         "laravel/framework": "^9.19",
         "laravel/sanctum": "^3.0",
-        "laravel/tinker": "^2.7"
+        "laravel/tinker": "^2.7",
+        "spatie/simple-excel": "^2.3"
     },
     "require-dev": {
         "roave/security-advisories": "dev-latest",