z230

60 DXA.py

@@ -0,0 +1,130 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+"""
+Report: DXA requisitions (Medicus → Dropbox)
+--------------------------------------------
+- Selects all histdoc records for year 2025 containing "DXA"
+- Finds matching PDF files in Dropbox (by rod_cis + "dxa" in name)
+- Outputs Excel report: datum, idpaci, rod_cis, prijmeni, jmeno, file
+"""
+
+import os
+import firebirdsql as fb
+import pandas as pd
+from pathlib import Path
+from datetime import datetime
+
+# ================== CONFIGURATION ==================
+FDB_PATH = r"z:\Medicus 3\data\MEDICUS.FDB"
+DOC_DIR = Path(r"U:\Dropbox\Ordinace\Dokumentace_zpracovaná")
+EXPORT_DIR = Path(r"U:\Dropbox\!!!Days\Downloads Z230")
+
+timestamp = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
+xlsx_path = EXPORT_DIR / f"{timestamp}_DXA_report.xlsx"
+
+# ================== DATABASE QUERY ==================
+conn = fb.connect(
+    host="192.168.1.4",
+    port=3050,
+    database=FDB_PATH,
+    user="SYSDBA",
+    password="masterkey",
+    charset="WIN1250",
+)
+
+sql = """
+SELECT
+    h.datum,
+    h.idpaci,
+    k.rodcis,
+    k.prijmeni,
+    k.jmeno,
+    (
+        SELECT LIST(
+            CAST(dd.datose AS DATE) || ':' || dd.kod, ', '
+        )
+        FROM dokladd dd
+        WHERE dd.rodcis = k.rodcis
+          AND EXTRACT(YEAR FROM dd.datose) = 2025
+          AND dd.kod STARTING WITH '1132'
+    ) AS vykony_1132_2025
+
+FROM histdoc h
+JOIN kar k ON h.idpaci = k.idpac
+WHERE EXTRACT(YEAR FROM h.datum) = 2025
+  AND h.data CONTAINING 'dxa'
+ORDER BY h.datum DESC
+"""
+
+
+df = pd.read_sql(sql, conn)
+conn.close()
+
+# ================== REMOVE DUPLICATES AND SORT ==================
+# Convert to datetime → drop duplicates → keep newest per patient → sort descending
+df["DATUM"] = pd.to_datetime(df["DATUM"], errors="coerce")
+
+# Drop duplicates, keep the newest by date
+df = (
+    df.sort_values("DATUM", ascending=False)
+      .drop_duplicates(subset="RODCIS", keep="first")
+      .sort_values("DATUM", ascending=False)
+      .reset_index(drop=True)
+)
+
+# Convert to pure date (no time portion)
+df["DATUM"] = df["DATUM"].dt.date
+
+# ================== FIND MATCHING PDF FILES ==================
+def find_dxa_file(rod_cis: str) -> str:
+    """Return first matching DXA file for given rod_cis or ''."""
+    if not rod_cis:
+        return ""
+    rod_cis = rod_cis.strip()
+
+    # Case-insensitive search for files like "1234567890 [DXA] something.pdf"
+    for file in DOC_DIR.iterdir():
+        name = file.name.lower()
+        if (
+            file.suffix.lower() == ".pdf"
+            and name.startswith(rod_cis.lower())
+            and "[dxa]" in name
+        ):
+            return file.name
+    return ""
+
+
+df["FILE"] = df["RODCIS"].apply(find_dxa_file)
+
+# ================== EXPORT TO EXCEL ==================
+with pd.ExcelWriter(xlsx_path, engine="openpyxl") as writer:
+    df.to_excel(writer, index=False, sheet_name="DXA")
+    ws = writer.sheets["DXA"]
+
+    # Format header
+    from openpyxl.styles import Font, Alignment, PatternFill, Border, Side
+    header_fill = PatternFill(start_color="FFFF00", end_color="FFFF00", fill_type="solid")
+    for cell in ws[1]:
+        cell.font = Font(bold=True, color="000000")
+        cell.alignment = Alignment(horizontal="center", vertical="center")
+        cell.fill = header_fill
+
+    # Auto column width
+    from openpyxl.utils import get_column_letter
+    for col in ws.columns:
+        col_letter = get_column_letter(col[0].column)
+        max_len = max(len(str(cell.value)) if cell.value else 0 for cell in col)
+        ws.column_dimensions[col_letter].width = min(max_len + 2, 80)
+
+    # Borders
+    thin = Side(border_style="thin", color="000000")
+    border = Border(top=thin, left=thin, right=thin, bottom=thin)
+    for row in ws.iter_rows(min_row=1, max_row=ws.max_row,
+                            min_col=1, max_col=ws.max_column):
+        for cell in row:
+            cell.border = border
+
+print(f"✅ Report created: {xlsx_path}")
+print(f"📂 Source folder scanned: {DOC_DIR}")
+print(f"🩻 {df['FILE'].astype(bool).sum()} matching DXA PDFs found")