DGN to Excel Conversion

Business Case

Problem Statement

DGN files are common in infrastructure and civil engineering:

• Transportation and highway design
• Bridge and tunnel projects
• Utility networks
• Rail infrastructure

Extracting structured data from DGN files for analysis and reporting can be challenging.

Solution

Convert DGN files to structured Excel databases, supporting both v7 and v8 formats.

Business Value

• Infrastructure support - Civil engineering focused
• Legacy format support - V7 and V8 DGN files
• Data extraction - Levels, cells, text, geometry
• Batch processing - Process multiple files
• Structured output - Excel format for analysis

Technical Implementation

CLI Syntax

DgnExporter.exe <input_dgn>

Supported Versions

Output Format

Examples

# Basic conversion
DgnExporter.exe "C:\Projects\Bridge.dgn"

# Batch processing
for /R "C:\Infrastructure" %f in (*.dgn) do DgnExporter.exe "%f"

# PowerShell batch
Get-ChildItem "C:\Projects\*.dgn" -Recurse | ForEach-Object {
    & "C:\DDC\DgnExporter.exe" $_.FullName
}

Python Integration

import subprocess
import pandas as pd
from pathlib import Path
from typing import List, Optional, Dict, Any
from dataclasses import dataclass
from enum import Enum


class DGNElementType(Enum):
    """DGN element types."""
    CELL_HEADER = 2
    LINE = 3
    LINE_STRING = 4
    SHAPE = 6
    TEXT_NODE = 7
    CURVE = 11
    COMPLEX_CHAIN = 12
    COMPLEX_SHAPE = 14
    ELLIPSE = 15
    ARC = 16
    TEXT = 17
    SURFACE = 18
    SOLID = 19
    BSPLINE_CURVE = 21
    POINT_STRING = 22
    DIMENSION = 33
    SHARED_CELL = 35


@dataclass
class DGNElement:
    """Represents a DGN element."""
    element_id: int
    element_type: int
    type_name: str
    level: int
    color: int
    weight: int
    style: int

    # Geometry
    range_low_x: Optional[float] = None
    range_low_y: Optional[float] = None
    range_low_z: Optional[float] = None
    range_high_x: Optional[float] = None
    range_high_y: Optional[float] = None
    range_high_z: Optional[float] = None

    # Cell/Text specific
    cell_name: Optional[str] = None
    text_content: Optional[str] = None


@dataclass
class DGNLevel:
    """Represents a DGN level."""
    number: int
    name: str
    is_displayed: bool
    is_frozen: bool
    element_count: int


class DGNExporter:
    """DGN to Excel converter using DDC DgnExporter CLI."""

    def __init__(self, exporter_path: str = "DgnExporter.exe"):
        self.exporter = Path(exporter_path)
        if not self.exporter.exists():
            raise FileNotFoundError(f"DgnExporter not found: {exporter_path}")

    def convert(self, dgn_file: str) -> Path:
        """Convert DGN file to Excel."""
        dgn_path = Path(dgn_file)
        if not dgn_path.exists():
            raise FileNotFoundError(f"DGN file not found: {dgn_file}")

        cmd = [str(self.exporter), str(dgn_path)]
        result = subprocess.run(cmd, capture_output=True, text=True)

        if result.returncode != 0:
            raise RuntimeError(f"Export failed: {result.stderr}")

        return dgn_path.with_suffix('.xlsx')

    def batch_convert(self, folder: str,
                      include_subfolders: bool = True) -> List[Dict[str, Any]]:
        """Convert all DGN files in folder."""
        folder_path = Path(folder)
        pattern = "**/*.dgn" if include_subfolders else "*.dgn"

        results = []
        for dgn_file in folder_path.glob(pattern):
            try:
                output = self.convert(str(dgn_file))
                results.append({
                    'input': str(dgn_file),
                    'output': str(output),
                    'status': 'success'
                })
                print(f"✓ Converted: {dgn_file.name}")
            except Exception as e:
                results.append({
                    'input': str(dgn_file),
                    'output': None,
                    'status': 'failed',
                    'error': str(e)
                })
                print(f"✗ Failed: {dgn_file.name} - {e}")

        return results

    def read_elements(self, xlsx_file: str) -> pd.DataFrame:
        """Read converted Excel as DataFrame."""
        return pd.read_excel(xlsx_file, sheet_name="Elements")

    def get_levels(self, xlsx_file: str) -> pd.DataFrame:
        """Get level summary."""
        df = self.read_elements(xlsx_file)

        if 'Level' not in df.columns:
            raise ValueError("Level column not found")

        summary = df.groupby('Level').agg({
            'ElementId': 'count'
        }).reset_index()
        summary.columns = ['Level', 'Element_Count']
        return summary.sort_values('Level')

    def get_element_types(self, xlsx_file: str) -> pd.DataFrame:
        """Get element type statistics."""
        df = self.read_elements(xlsx_file)

        type_col = 'ElementType' if 'ElementType' in df.columns else 'Type'
        if type_col not in df.columns:
            return pd.DataFrame()

        summary = df.groupby(type_col).agg({
            'ElementId': 'count'
        }).reset_index()
        summary.columns = ['Element_Type', 'Count']
        return summary.sort_values('Count', ascending=False)

    def get_cells(self, xlsx_file: str) -> pd.DataFrame:
        """Get cell references (similar to blocks in DWG)."""
        df = self.read_elements(xlsx_file)

        # Filter to cell elements
        cells = df[df['ElementType'].isin([2, 35])]  # CELL_HEADER, SHARED_CELL

        if cells.empty or 'CellName' not in cells.columns:
            return pd.DataFrame(columns=['Cell_Name', 'Count'])

        summary = cells.groupby('CellName').agg({
            'ElementId': 'count'
        }).reset_index()
        summary.columns = ['Cell_Name', 'Count']
        return summary.sort_values('Count', ascending=False)

    def get_text_content(self, xlsx_file: str) -> pd.DataFrame:
        """Extract all text from DGN."""
        df = self.read_elements(xlsx_file)

        # Filter to text elements
        text_types = [7, 17]  # TEXT_NODE, TEXT
        texts = df[df['ElementType'].isin(text_types)]

        if 'TextContent' in texts.columns:
            return texts[['ElementId', 'Level', 'TextContent']].copy()
        return texts[['ElementId', 'Level']].copy()

    def get_statistics(self, xlsx_file: str) -> Dict[str, Any]:
        """Get comprehensive DGN statistics."""
        df = self.read_elements(xlsx_file)

        stats = {
            'total_elements': len(df),
            'levels_used': df['Level'].nunique() if 'Level' in df.columns else 0,
            'element_types': df['ElementType'].nunique() if 'ElementType' in df.columns else 0
        }

        # Calculate extents
        for coord in ['X', 'Y', 'Z']:
            low_col = f'RangeLow{coord}'
            high_col = f'RangeHigh{coord}'
            if low_col in df.columns and high_col in df.columns:
                stats[f'min_{coord.lower()}'] = df[low_col].min()
                stats[f'max_{coord.lower()}'] = df[high_col].max()

        return stats


class DGNAnalyzer:
    """Advanced DGN analysis for infrastructure projects."""

    def __init__(self, exporter: DGNExporter):
        self.exporter = exporter

    def analyze_infrastructure(self, dgn_file: str) -> Dict[str, Any]:
        """Analyze DGN for infrastructure elements."""
        xlsx = self.exporter.convert(dgn_file)
        df = self.exporter.read_elements(str(xlsx))

        analysis = {
            'file': dgn_file,
            'statistics': self.exporter.get_statistics(str(xlsx)),
            'levels': self.exporter.get_levels(str(xlsx)).to_dict('rec