reporty/50 Dekurs.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

"""
Export DEKURS records from Medicus Firebird DB into Excel.
- Includes only last 2 months from current date
- RTF text decoded and cleaned (Excel-safe, preserved newlines)
- Výkony of the same day concatenated into 'VYKONY DNE'
- Příjmení + Jméno merged into 'PACIENT'
- Proper column order and naming
- Bright yellow header, thin black borders, auto column widths
- Timestamped Excel filename
"""

import re
import pandas as pd
import firebirdsql as fb
from datetime import datetime, timedelta
from pathlib import Path
from striprtf.striprtf import rtf_to_text
from openpyxl.styles import Font, Alignment, PatternFill, Border, Side
from openpyxl.utils import get_column_letter
from Functions import get_medicus_connection

# ================== CONFIGURATION ==================
FDB_PATH = r"z:\Medicus 3\data\MEDICUS.FDB"
EXPORT_DIR = Path(r"u:\Dropbox\!!!Days\Downloads Z230")

# calculate last 2 months dynamically (now set to 10 days for testing)
DATE_FROM = (datetime.now() - timedelta(days=10)).strftime("%Y-%m-%d")

timestamp = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
xlsx_path = EXPORT_DIR / f"{timestamp}_Dekurz (poslední rok).xlsx"

# ================== FIREBIRD CONNECTION ==================
conn = get_medicus_connection()

def query_df(sql, params=None):
    cur = conn.cursor()
    cur.execute(sql, params or ())
    rows = cur.fetchall()
    cols = [d[0].strip() for d in cur.description]
    return pd.DataFrame(rows, columns=cols)

# ================== QUERY ==================
sql = f"""
SELECT
    d.id,
    k.prijmeni,
    k.jmeno,
    k.rodcis,
    u.zkratka,
    d.datum,
    d.dekurs,
    (
        SELECT LIST(dd.kod, ', ')
        FROM dokladd dd
        WHERE dd.rodcis = k.rodcis
          AND CAST(dd.datose AS DATE) = CAST(d.datum AS DATE)
    ) AS vykony_dne
FROM dekurs d
JOIN kar k ON d.idpac = k.idpac
JOIN uzivatel u ON d.iduzi = u.iduzi
WHERE d.datum >= DATE '{DATE_FROM}'
ORDER BY d.datum DESC
"""

df = query_df(sql)
conn.close()

# ================== DATA CLEANING ==================
def safe_rtf_to_text(x):
    if isinstance(x, str) and x.strip():
        try:
            return rtf_to_text(x)
        except Exception:
            return x
    return ""

df["DEKURS"] = df["DEKURS"].apply(safe_rtf_to_text)

# --- Normalize and clean newlines ---
df["DEKURS"] = (
    df["DEKURS"]
    .replace(r"(\r\n|\r|\n)+", "\n", regex=True)  # unify newlines
    .replace(r"\n{2,}", "\n", regex=True)         # collapse multiple blank lines
    .str.strip()                                  # trim leading/trailing blanks
)

# --- Remove invalid control characters ---
df.replace({r"[\ud800-\udfff\x00-\x08\x0B-\x0C\x0E-\x1F\x7F]+": ""}, regex=True, inplace=True)

# --- Merge patient name ---
df["PACIENT"] = df["PRIJMENI"].fillna("") + ", " + df["JMENO"].fillna("")
df.drop(columns=["PRIJMENI", "JMENO"], inplace=True)

# --- Rename and format columns ---
df.rename(columns={"ZKRATKA": "LEKAR", "VYKONY_DNE": "VYKONY DNE"}, inplace=True)
df["DATUM"] = pd.to_datetime(df["DATUM"], errors="coerce").dt.date
df.drop(columns=[c for c in df.columns if "ASCII" in c.upper()], inplace=True, errors="ignore")

desired_order = ["DATUM", "RODCIS", "PACIENT", "LEKAR", "VYKONY DNE", "DEKURS"]
df = df[[c for c in desired_order if c in df.columns]]

# ================== CLEANUP OLD FILES ==================
for old_file in EXPORT_DIR.glob("*Dekurz (poslední rok)*.xlsx"):
    try:
        old_file.unlink()
        print(f"🧹 Deleted old file: {old_file.name}")
    except Exception as e:
        print(f"⚠️ Could not delete {old_file.name}: {e}")

# ================== EXPORT TO EXCEL ==================
with pd.ExcelWriter(xlsx_path, engine="openpyxl") as writer:
    df.to_excel(writer, index=False, sheet_name="Dekurz")
    ws = writer.sheets["Dekurz"]
    ws.freeze_panes = "F2" #zamčení prvního řádku a sloupců A:F
    # ----- Bright yellow header -----
    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

    # ----- Format Datum column -----
    for cell in ws["A"][1:]:
        if hasattr(cell.value, "date"):
            cell.value = cell.value.date()
        cell.number_format = "DD.MM.YYYY"

    # ----- Vertical centering for key columns -----
    vertically_centered = {"DATUM", "RODCIS", "PACIENT", "LEKAR", "VYKONY DNE"}
    for row in ws.iter_rows(min_row=2, max_row=ws.max_row):
        for cell in row:
            header = ws.cell(row=1, column=cell.column).value
            if header in vertically_centered:
                align = cell.alignment
                cell.alignment = Alignment(
                    horizontal=align.horizontal or "left",
                    vertical="center",
                    wrap_text=align.wrap_text
                )
            elif isinstance(cell.value, str) and "\n" in cell.value:
                cell.alignment = Alignment(wrap_text=True, vertical="top")

    # ----- Column widths -----
    for col in ws.columns:
        header = col[0].value
        col_letter = get_column_letter(col[0].column)
        if header and "DEKURS" in str(header).upper():
            ws.column_dimensions[col_letter].width = 110
        else:
            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)

    # ----- Thin black 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"✅ Export hotov: {xlsx_path}")
print(f"📅 Dotaz zahrnuje data od: {DATE_FROM}")