feat: Ingest authentic Grade 10 Math Unit 1 with complete LaTeX equations and full derivations

This commit is contained in:
Hamza-Ayed
2026-08-29 03:32:37 +03:00
parent 39cf087488
commit eb94f6ff77
7 changed files with 368 additions and 23 deletions
@@ -0,0 +1,112 @@
<?php
require_once __DIR__ . '/../app/bootstrap.php';
use App\Services\CurriculumService;
/**
* Intelligent Markdown Curriculum Parser
* Splits a complete textbook markdown into units, lessons, outcomes, and resources.
*/
function parseAndIngestTextbookMarkdown(string $rawMarkdown, array $metadata = []): array
{
$lines = explode("\n", $rawMarkdown);
$gradeName = $metadata['grade_name'] ?? 'الصف العاشر';
$gradeKey = $metadata['grade_key'] ?? 'grade_10';
$subName = $metadata['subject_name'] ?? 'الرياضيات';
$subKey = $metadata['subject_key'] ?? 'math_10';
$semName = $metadata['semester_name'] ?? 'الفصل الدراسي الأول';
$semKey = $metadata['semester_key'] ?? 'semester_1';
$units = [];
$currentUnit = null;
$currentLesson = null;
$lessonBuffer = [];
$flushLesson = function() use (&$currentUnit, &$currentLesson, &$lessonBuffer) {
if ($currentUnit && $currentLesson) {
$content = trim(implode("\n", $lessonBuffer));
if (!empty($content)) {
$currentLesson['markdown_content'] = $content;
$currentUnit['lessons'][] = $currentLesson;
}
$currentLesson = null;
$lessonBuffer = [];
}
};
$flushUnit = function() use (&$units, &$currentUnit, $flushLesson) {
$flushLesson();
if ($currentUnit && !empty($currentUnit['lessons'])) {
$units[] = $currentUnit;
$currentUnit = null;
}
};
$unitCounter = 0;
$lessonCounter = 0;
foreach ($lines as $line) {
$trimmed = trim($line);
// Detect Unit (# UNIT or # الوحدة)
if (preg_match('/^#\s+(UNIT|الوحدة)\s*([0-9\-\:A-Za-z\s]+)(.*)$/ui', $trimmed, $m) || preg_match('/^#\s+([A-Za-z0-9\s]+(?:SPOT|SKILLS|REFERENCE|LIST))/ui', $trimmed, $m2)) {
$flushUnit();
$unitCounter++;
$unitTitle = trim(preg_replace('/^#\s+/u', '', $trimmed));
$unitKey = sprintf('unit_%02d', $unitCounter);
$currentUnit = [
'unit_key' => $unitKey,
'unit_name' => $unitTitle,
'lessons' => []
];
$lessonCounter = 0;
continue;
}
// Detect Lesson (## Lesson or ## الدرس or ## معمل or ## )
if (preg_match('/^##\s+(Lesson|الدرس|قسم|المحطة|قواعد|تمارين|معمل)\s*([0-9\-\:A-Za-z\s]+)(.*)$/ui', $trimmed, $m) || (preg_match('/^##\s+(.+)$/u', $trimmed, $mAlt) && $currentUnit)) {
$flushLesson();
$lessonCounter++;
$lessonTitle = trim(preg_replace('/^##\s+/u', '', $trimmed));
$lesId = sprintf('lesson_%02d', $lessonCounter);
if (!$currentUnit) {
$unitCounter++;
$currentUnit = [
'unit_key' => sprintf('unit_%02d', $unitCounter),
'unit_name' => 'الوحدة الأولى: المعادلات',
'lessons' => []
];
}
$currentLesson = [
'lesson_id' => $lesId,
'title' => $lessonTitle,
'outcomes' => [$lessonTitle]
];
$lessonBuffer = [$trimmed];
continue;
}
if ($currentLesson) {
$lessonBuffer[] = $line;
}
}
$flushUnit();
$extracted = [
'grade_name' => $gradeName,
'grade_key' => $gradeKey,
'subject_name' => $subName,
'subject_key' => $subKey,
'semester_name' => $semName,
'semester_key' => $semKey,
'units' => $units
];
return CurriculumService::mergeExtractedCurriculum($extracted);
}