From bd1f6263ca57f67d063da7bfb1abd07382bcc1ad Mon Sep 17 00:00:00 2001
From: dmsanhrProject <dmsanhrproject@gmail.com>
Date: Thu, 30 Oct 2025 11:12:57 +0700
Subject: [PATCH] cleaning reader_pdf

---
 .DS_Store              | Bin 6148 -> 6148 bytes
 services/reader_pdf.py |  24 +-----------------------
 2 files changed, 1 insertion(+), 23 deletions(-)

diff --git a/.DS_Store b/.DS_Store
index 23ffbc084973f348acd719362eb32dd03072ef05..02daf350c3ae76dd0bbb5a1e8ae6e51b038e63cb 100644
GIT binary patch
delta 98
zcmZoMXfc@JFU-Zjz`)4BAi%(onp9p~kd%|3v{{g2B{M%rf|VheArXi(7*Z#Tur_cQ
n8X4&*n3|YRp2KP{jwD$YT$GoSpO+3YYcmfEKl5gGj=%f>9KaRz

delta 48
zcmZoMXfc@JFUrBdz`)4BAi&_6lb@WFlb;0S3v3qTSkBDIvH1rJKl8+fH=Efx{_+C=
D4j~M;

diff --git a/services/reader_pdf.py b/services/reader_pdf.py
index a5a5241..5001744 100644
--- a/services/reader_pdf.py
+++ b/services/reader_pdf.py
@@ -77,10 +77,6 @@ def merge_multiline_header(header_rows):
         val = str(val).replace('\n', ' ').strip()
         final_header.append(val)
     final_header = [v for v in final_header if v not in ['', None]]
-    
-    # header_string = ' | '.join(final_header)
-    # return header_string
-
     return final_header
 
 
@@ -177,22 +173,12 @@ def read_pdf(path: str):
         for i, raw_body in enumerate(body_only):
             con_body = [[cell for cell in row if cell not in (None, '')] for row in raw_body]
             cleaned = cleaning_column(clean_header[i], [con_body])
-            # clean_body.append(con_body)
             clean_body.append(cleaned[0])
 
-        # print(clean_header)
-        # print(clean_body)
-
         parsed = []
-        # for cols, rows in zip(clean_header, clean_body):
-        #     parsed.append({
-        #         "title": "",
-        #         "columns": cols,
-        #         "rows": rows
-        #     })
         for i, (cols, rows) in enumerate(zip(clean_header, clean_body), start=1):
             parsed.append({
-                "title": str(i),  # bisa juga f"Table {i}" kalau mau format tertentu
+                "title": str(i),
                 "columns": cols,
                 "rows": rows
             })
@@ -206,28 +192,20 @@ def read_pdf(path: str):
 
 
 def convert_df(payload):
-    # Validasi dasar
-    print(f'payload {payload}')
-    
-    # Cek apakah keys ada
     if "columns" not in payload or "rows" not in payload:
         raise ValueError("Payload tidak memiliki key 'columns' atau 'rows'.")
     
-    # Pastikan columns dan rows berupa list
     if not isinstance(payload["columns"], list):
         raise TypeError("'columns' harus berupa list.")
     if not isinstance(payload["rows"], list):
         raise TypeError("'rows' harus berupa list.")
     
-    # Pastikan setiap baris punya jumlah kolom yang sama
     for i, row in enumerate(payload["rows"]):
         if len(row) != len(payload["columns"]):
             raise ValueError(f"Jumlah elemen di baris ke-{i} tidak sesuai jumlah kolom.")
     
-    # Konversi menjadi DataFrame
     df = pd.DataFrame(payload["rows"], columns=payload["columns"])
     
-    # Tambahkan atribut title kalau ada
     if "title" in payload:
         df.attrs["title"] = payload["title"]