commit pertama

2026-11-02 10:34:22 +07:00
commit c8f8ce04c4
13 changed files with 318 additions and 0 deletions
@@ -0,0 +1,84 @@
+"""
+Lab 1 - Eksperimen Chunking (15 menit)
+Hanya butuh library pypdf:   pip install pypdf
+
+Cara jalankan (pilih salah satu):
+    python lab_1.py                                  -> otomatis pakai PDF pertama di folder dokumen/
+    python lab_1.py dokumen/panduan_akademik.pdf     -> pakai PDF tertentu
+    python lab_1.py dokumen/panduan_akademik.pdf --overlap 0.2
+"""
+
+import argparse
+import random
+import re
+from pathlib import Path
+
+from pypdf import PdfReader
+
+UKURAN_LIST = [500, 1000, 1500]
+
+
+def baca_pdf(path):
+    """Baca seluruh teks dari satu file PDF."""
+    reader = PdfReader(str(path))
+    halaman = [(p.extract_text() or "") for p in reader.pages]
+    teks = "\n".join(halaman)
+    return re.sub(r"[ \t]+", " ", teks).strip()
+
+
+def potong(teks, ukuran=1000, overlap=0.15):
+    """Potong teks jadi chunk berukuran `ukuran` karakter dengan overlap (0-1)."""
+    langkah = max(1, int(ukuran * (1 - overlap)))
+    chunks = []
+    for mulai in range(0, len(teks), langkah):
+        potongan = teks[mulai:mulai + ukuran].strip()
+        if potongan:
+            chunks.append(potongan)
+        if mulai + ukuran >= len(teks):
+            break
+    return chunks
+
+
+def cari_pdf_default():
+    daftar = sorted(Path("dokumen").glob("*.pdf"))
+    if not daftar:
+        raise SystemExit("Tidak ada PDF di folder dokumen/. Taruh PDF di sana atau tulis path-nya.")
+    return daftar[0]
+
+
+def main():
+    p = argparse.ArgumentParser(description="Lab 1: eksperimen chunking")
+    p.add_argument("pdf", nargs="?", help="Path PDF (kosongkan untuk pakai PDF pertama di dokumen/)")
+    p.add_argument("--overlap", type=float, default=0.15, help="Overlap 0.10 - 0.20 (default 0.15)")
+    args = p.parse_args()
+
+    path = Path(args.pdf) if args.pdf else cari_pdf_default()
+    print(f"File: {path}\n")
+
+    # 1. Baca PDF, cetak 500 karakter pertama
+    teks = baca_pdf(path)
+    print(f"=== 1. Hasil baca PDF ({len(teks)} karakter total) ===")
+    print(teks[:500])
+
+    # 2. Potong dengan tiga ukuran, catat jumlah chunk
+    print("\n=== 2. Jumlah chunk per pengaturan ===")
+    hasil = {}
+    for ukuran in UKURAN_LIST:
+        chunks = potong(teks, ukuran, args.overlap)
+        hasil[ukuran] = chunks
+        print(f"  ukuran={ukuran:<5} overlap={args.overlap:.0%}  ->  {len(chunks)} chunk")
+
+    # 3. Lihat 3 chunk acak tiap ukuran
+    print("\n=== 3. Tiga chunk acak per ukuran (terpotong di tengah kalimat/tabel?) ===")
+    for ukuran, chunks in hasil.items():
+        print(f"\n--- ukuran {ukuran} ---")
+        for c in random.sample(chunks, min(3, len(chunks))):
+            awal_rapi = c[0].isupper() or c[0].isdigit()
+            akhir_rapi = c[-1] in ".!?:"
+            print(f"[awal rapi: {awal_rapi} | akhir rapi: {akhir_rapi}]")
+            print(c)
+            print("." * 40)
+
+
+if __name__ == "__main__":
+    main()