Files
thechart/src/export_manager.py
T

435 lines
17 KiB
Python

"""
Export Manager for TheChart Application
Handles exporting data and graphs to various formats:
- CSV data to JSON, XML
- Graphs to PDF (with data tables)
"""
import contextlib
import json
import logging
import os
from datetime import datetime
from pathlib import Path
from typing import Any
from xml.dom import minidom
from xml.etree.ElementTree import Element, SubElement, tostring
import pandas as pd
from reportlab.lib import colors
from reportlab.lib.pagesizes import A4, landscape
from reportlab.lib.styles import ParagraphStyle, getSampleStyleSheet
from reportlab.lib.units import inch
from reportlab.platypus import (
Image,
PageBreak,
Paragraph,
SimpleDocTemplate,
Spacer,
Table,
TableStyle,
)
from data_manager import DataManager
from graph_manager import GraphManager
from medicine_manager import MedicineManager
from pathology_manager import PathologyManager
class ExportManager:
"""Handle data and graph export operations."""
def __init__(
self,
data_manager: DataManager,
graph_manager: GraphManager,
medicine_manager: MedicineManager,
pathology_manager: PathologyManager,
logger: logging.Logger,
) -> None:
self.data_manager = data_manager
self.graph_manager = graph_manager
self.medicine_manager = medicine_manager
self.pathology_manager = pathology_manager
self.logger = logger
def export_data_to_json(self, export_path: str) -> bool:
"""Export CSV data to JSON format."""
try:
df = self.data_manager.load_data()
if df.empty:
self.logger.warning("No data to export")
return False
# Convert DataFrame to dictionary with better structure
export_data = {
"metadata": {
"export_date": datetime.now().isoformat(),
"total_entries": len(df),
"date_range": {
"start": df["date"].min() if not df.empty else None,
"end": df["date"].max() if not df.empty else None,
},
"pathologies": list(self.pathology_manager.get_pathology_keys()),
"medicines": list(self.medicine_manager.get_medicine_keys()),
},
"entries": df.to_dict(orient="records"),
}
with open(export_path, "w", encoding="utf-8") as f:
json.dump(export_data, f, indent=2, ensure_ascii=False)
self.logger.info(f"Data exported to JSON: {export_path}")
return True
except Exception as e:
self.logger.error(f"Error exporting to JSON: {str(e)}")
return False
def export_data_to_xml(self, export_path: str) -> bool:
"""Export CSV data to XML format."""
try:
df = self.data_manager.load_data()
if df.empty:
self.logger.warning("No data to export")
return False
# Create root element
root = Element("thechart_data")
# Add metadata
metadata = SubElement(root, "metadata")
SubElement(metadata, "export_date").text = datetime.now().isoformat()
SubElement(metadata, "total_entries").text = str(len(df))
# Date range
date_range = SubElement(metadata, "date_range")
SubElement(date_range, "start").text = (
df["date"].min() if not df.empty else ""
)
SubElement(date_range, "end").text = (
df["date"].max() if not df.empty else ""
)
# Pathologies
pathologies = SubElement(metadata, "pathologies")
for pathology in self.pathology_manager.get_pathology_keys():
SubElement(pathologies, "pathology").text = pathology
# Medicines
medicines = SubElement(metadata, "medicines")
for medicine in self.medicine_manager.get_medicine_keys():
SubElement(medicines, "medicine").text = medicine
# Add entries
entries = SubElement(root, "entries")
for _, row in df.iterrows():
entry = SubElement(entries, "entry")
for column, value in row.items():
elem = SubElement(entry, column.replace(" ", "_"))
elem.text = str(value) if pd.notna(value) else ""
# Pretty print XML
rough_string = tostring(root, "utf-8")
reparsed = minidom.parseString(rough_string)
pretty_xml = reparsed.toprettyxml(indent=" ")
with open(export_path, "w", encoding="utf-8") as f:
f.write(pretty_xml)
self.logger.info(f"Data exported to XML: {export_path}")
return True
except Exception as e:
self.logger.error(f"Error exporting to XML: {str(e)}")
return False
def _save_graph_as_image(self, temp_dir: Path) -> str | None:
"""Save current graph as temporary image for PDF inclusion."""
try:
# Check if graph manager exists
if self.graph_manager is None:
self.logger.warning("No graph manager available for export")
return None
# Check if graph manager and figure exist
if not hasattr(self.graph_manager, "fig") or self.graph_manager.fig is None:
self.logger.warning("No graph figure available for export")
return None
# Ensure graph is up to date with current data
df = self.data_manager.load_data()
if not df.empty:
self.graph_manager.update_graph(df)
else:
self.logger.warning("No data available to update graph for export")
return None
# Ensure temp directory exists
temp_dir.mkdir(parents=True, exist_ok=True)
temp_image_path = temp_dir / "graph.png"
# Save the current figure
self.graph_manager.fig.savefig(
str(temp_image_path),
dpi=150,
bbox_inches="tight",
facecolor="white",
edgecolor="none",
)
# Ensure the figure data is properly flushed to disk
import matplotlib.pyplot as plt
plt.draw()
plt.pause(0.01) # Small pause to ensure file is written
# Verify the file was actually created and has content
if not temp_image_path.exists():
self.logger.error(
f"Graph image file was not created: {temp_image_path}"
)
return None
if temp_image_path.stat().st_size == 0:
self.logger.error(f"Graph image file is empty: {temp_image_path}")
return None
self.logger.info(f"Graph image saved successfully: {temp_image_path}")
return str(temp_image_path)
except Exception as e:
self.logger.error(f"Error saving graph image: {str(e)}")
return None
def export_to_pdf(self, export_path: str, include_graph: bool = True) -> bool:
"""Export data and optionally graph to PDF format."""
try:
df = self.data_manager.load_data()
# Create PDF document in landscape format for better table/graph display
doc = SimpleDocTemplate(
export_path,
pagesize=landscape(A4),
rightMargin=72,
leftMargin=72,
topMargin=72,
bottomMargin=18,
)
# Get styles
styles = getSampleStyleSheet()
title_style = ParagraphStyle(
"CustomTitle",
parent=styles["Heading1"],
fontSize=18,
spaceAfter=30,
textColor=colors.darkblue,
)
story = []
# Title
story.append(Paragraph("TheChart - Medication Tracker Export", title_style))
story.append(Spacer(1, 20))
# Export metadata
export_info = [
f"Export Date: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}",
f"Total Entries: {len(df) if not df.empty else 0}",
]
if not df.empty:
export_info.extend(
[
f"Date Range: {df['date'].min()} to {df['date'].max()}",
(
"Pathologies: "
+ ", ".join(self.pathology_manager.get_pathology_keys())
),
(
"Medicines: "
+ ", ".join(self.medicine_manager.get_medicine_keys())
),
]
)
for info in export_info:
story.append(Paragraph(info, styles["Normal"]))
story.append(Spacer(1, 20))
# Include graph if requested and available
if include_graph:
temp_dir = Path(export_path).parent / "temp_export"
graph_path = None
try:
graph_path = self._save_graph_as_image(temp_dir)
if graph_path and os.path.exists(graph_path):
# Add page break before graph for full page display
story.append(PageBreak())
story.append(
Paragraph("Data Visualization", styles["Heading2"])
)
story.append(Spacer(1, 20))
# Full page graph - maintain proportions while maximizing size
# Let ReportLab scale proportionally to fit landscape page
img = Image(graph_path, width=9 * inch, height=5.4 * inch)
story.append(img)
else:
# Graph not available, add a note instead
story.append(PageBreak())
story.append(
Paragraph("Data Visualization", styles["Heading2"])
)
story.append(Spacer(1, 10))
story.append(
Paragraph(
"Graph not available - no data to visualize or graph "
"not generated yet.",
styles["Normal"],
)
)
except Exception as e:
self.logger.error(f"Error including graph in PDF: {str(e)}")
# Add error note instead of failing completely
story.append(PageBreak())
story.append(Paragraph("Data Visualization", styles["Heading2"]))
story.append(Spacer(1, 10))
story.append(
Paragraph(
f"Graph could not be included: {str(e)}", styles["Normal"]
)
)
# Add data table if we have data
if not df.empty:
# Start table on new page
story.append(PageBreak())
story.append(Paragraph("Data Table", styles["Heading2"]))
story.append(Spacer(1, 20))
# Prepare table data - include all columns for full display
display_columns = ["date"]
for pathology_key in self.pathology_manager.get_pathology_keys():
display_columns.append(pathology_key)
for medicine_key in self.medicine_manager.get_medicine_keys():
display_columns.append(medicine_key)
display_columns.append("note")
# Filter dataframe to display columns that exist
available_columns = [
col for col in display_columns if col in df.columns
]
display_df = df[available_columns].copy()
# Don't truncate notes - landscape format has full width
# Keep notes as-is for complete data visibility
# Convert to table data
table_data = [available_columns] # Headers
for _, row in display_df.iterrows():
table_data.append(
[str(val) if pd.notna(val) else "" for val in row]
)
# Calculate optimal column widths for landscape format
col_widths = []
for col in available_columns:
if col == "date":
col_widths.append(1.0 * inch) # Fixed width for dates
elif col == "note":
col_widths.append(3.5 * inch) # Wider for notes
elif col in self.pathology_manager.get_pathology_keys():
col_widths.append(0.8 * inch) # Narrow for pathology scores
elif col in self.medicine_manager.get_medicine_keys():
col_widths.append(0.8 * inch) # Narrow for medicine status
else:
col_widths.append(1.0 * inch) # Default width
# Create table with specified column widths and better styling
table = Table(table_data, colWidths=col_widths, repeatRows=1)
table.setStyle(
TableStyle(
[
("BACKGROUND", (0, 0), (-1, 0), colors.grey),
("TEXTCOLOR", (0, 0), (-1, 0), colors.whitesmoke),
# Left align for better readability
("ALIGN", (0, 0), (-1, -1), "LEFT"),
("FONTNAME", (0, 0), (-1, 0), "Helvetica-Bold"),
("FONTSIZE", (0, 0), (-1, 0), 10),
# Add more padding for better readability
("LEFTPADDING", (0, 0), (-1, -1), 8),
("RIGHTPADDING", (0, 0), (-1, -1), 8),
("TOPPADDING", (0, 0), (-1, -1), 6),
("BOTTOMPADDING", (0, 0), (-1, -1), 6),
("BACKGROUND", (0, 1), (-1, -1), colors.beige),
("FONTNAME", (0, 1), (-1, -1), "Helvetica"),
# Slightly larger font for better readability
("FONTSIZE", (0, 1), (-1, -1), 9),
("GRID", (0, 0), (-1, -1), 1, colors.black),
("VALIGN", (0, 0), (-1, -1), "TOP"),
("WORDWRAP", (0, 0), (-1, -1), True),
# Alternating row colors for better visual separation
(
"ROWBACKGROUNDS",
(0, 1),
(-1, -1),
[colors.beige, colors.lightgrey],
),
]
)
)
story.append(table)
else:
story.append(PageBreak())
story.append(
Paragraph("No data available to export.", styles["Normal"])
)
# Build PDF
doc.build(story)
# Clean up temporary image file after PDF is built
if include_graph:
temp_dir = Path(export_path).parent / "temp_export"
if graph_path and os.path.exists(graph_path):
try:
os.remove(graph_path)
self.logger.debug(f"Cleaned up temporary image: {graph_path}")
except OSError as e:
self.logger.warning(f"Could not remove temp image: {e}")
# Clean up temp directory if empty
if temp_dir.exists():
with contextlib.suppress(OSError):
temp_dir.rmdir()
self.logger.info(f"Data exported to PDF: {export_path}")
return True
except Exception as e:
self.logger.error(f"Error exporting to PDF: {str(e)}")
return False
def get_export_info(self) -> dict[str, Any]:
"""Get information about available data for export."""
df = self.data_manager.load_data()
return {
"total_entries": len(df) if not df.empty else 0,
"date_range": {
"start": df["date"].min() if not df.empty else None,
"end": df["date"].max() if not df.empty else None,
},
"pathologies": list(self.pathology_manager.get_pathology_keys()),
"medicines": list(self.medicine_manager.get_medicine_keys()),
"has_data": not df.empty,
}