add reader mpk

services/upload_file/read_mpk/reader_mpk.py

@@ -0,0 +1,72 @@
+import os
+import tempfile
+import json
+from io import BytesIO
+import geopandas as gpd
+from py7zr import SevenZipFile
+import pyogrio
+
+
+def find_data_source(extract_dir: str):
+    """
+    Cari data sumber (.gdb atau .shp) di dalam folder hasil ekstrak.
+    """
+    for root, dirs, _ in os.walk(extract_dir):
+        for d in dirs:
+            if d.lower().endswith(".gdb"):
+                return os.path.join(root, d)
+
+    for root, _, files in os.walk(extract_dir):
+        for f in files:
+            if f.lower().endswith(".shp"):
+                return os.path.join(root, f)
+
+    raise ValueError("Tidak ditemukan data source yang didukung (.gdb atau .shp).")
+
+
+def get_main_layer(gdb_path: str):
+    """
+    Ambil nama layer utama dari geodatabase (.gdb).
+    """
+    try:
+        layers = pyogrio.list_layers(gdb_path)
+        for layer in layers:
+            if not layer[0].lower().endswith("__attach"):
+                return layer[0]
+        if layers:
+            return layers[0][0]
+        raise ValueError(f"Tidak ada layer utama yang valid di {gdb_path}")
+    except Exception as e:
+        raise ValueError(f"Gagal membaca daftar layer GDB: {e}")
+
+
+def read_mpk(path: str):
+    mpk_bytes = None
+    with open(path, "rb") as f:
+        mpk_bytes = f.read()
+        
+    if not mpk_bytes:
+        raise ValueError("File MPK kosong atau tidak valid.")
+
+    with tempfile.TemporaryDirectory() as tempdir:
+        try:
+            with SevenZipFile(BytesIO(mpk_bytes), mode="r") as z:
+                z.extractall(path=tempdir)
+        except Exception as e:
+            raise ValueError(f"File MPK rusak atau tidak valid: {e}")
+
+        src_path = find_data_source(tempdir)
+
+        if src_path.lower().endswith(".gdb"):
+            layer_name = get_main_layer(src_path)
+            gdf = gpd.read_file(src_path, layer=layer_name)
+        else:
+            gdf = gpd.read_file(src_path)
+
+        if gdf.crs is None:
+            raise ValueError("CRS tidak terdeteksi. Pastikan file memiliki informasi proyeksi (.prj).")
+
+        gdf = gdf.to_crs(epsg=4326)
+
+        print(f"[INFO] Berhasil membaca {len(gdf)} fitur")
+        return gdf

services/upload_file/read_pdf/reader_pdf.py

@@ -173,8 +173,12 @@ def parse_page_selection(selectedPage: str, total_pages: int):
 def read_pdf(path: str, page: str):
     pdf_path = path
     selectedPage = None
-    if page == '' or None:
+    # if page == '' or None:
+    #     selectedPage = "1"
+    if not page:
         selectedPage = "1"
+    else:
+        selectedPage = page
     tables_data = [] 
     with pdfplumber.open(pdf_path) as pdf:
         total_pages = len(pdf.pages)

services/upload_file/upload.py

@@ -11,6 +11,7 @@ from core.config import UPLOAD_FOLDER, MAX_FILE_MB, VALID_WKT_PREFIXES
 from services.upload_file.read_csv.reader_csv import read_csv
 from services.upload_file.read_shp.reader_shp import read_shp
 from services.upload_file.read_gdb.reader_gdb import read_gdb
+from services.upload_file.read_mpk.reader_mpk import read_mpk
 from services.upload_file.read_pdf.reader_pdf import convert_df, read_pdf
 from services.upload_file.geom_detector.geometry_detector import detect_and_build_geometry
 from services.upload_file.geom_detector.geometry_detector import attach_polygon_geometry_auto
@@ -156,7 +157,7 @@ async def handle_upload_file(file: UploadFile = File(...), page: Optional[str] =
     contents = await file.read()
     size_mb = len(contents) / (1024*1024)
     if size_mb > MAX_FILE_MB:
-        raise HTTPException(status_code=413, detail="File too large")
+        raise HTTPException(status_code=413, detail="Ukuran File Terlalu Besar")
     tmp_path = UPLOAD_FOLDER / fname
     with open(tmp_path, "wb") as f:
         f.write(contents)
@@ -168,6 +169,8 @@ async def handle_upload_file(file: UploadFile = File(...), page: Optional[str] =
             df = read_csv(str(tmp_path))
         elif ext == ".xlsx":
             df = read_csv(str(tmp_path), sheet)
+        elif ext == ".mpk":
+            df = read_mpk(str(tmp_path))
         elif ext == ".pdf":
             tbl = read_pdf(tmp_path, page)
             if len(tbl) == 0: