\r

JSON Parser for Construction Data\r

\r

Overview\r

Construction systems increasingly use JSON for data exchange - from IoT sensors to BIM metadata exports. This skill handles parsing, validation, and flattening of JSON structures.\r \r

Python Implementation\r

\r

import json\r
import pandas as pd\r
from typing import Dict, Any, List, Optional, Union\r
from dataclasses import dataclass\r
from pathlib import Path\r
\r
\r
@dataclass\r
class JSONParseResult:\r
    """Result of JSON parsing operation."""\r
    success: bool\r
    data: Any\r
    errors: List[str]\r
    record_count: int\r
\r
\r
class ConstructionJSONParser:\r
    """Parse JSON data from construction sources."""\r
\r
    def __init__(self):\r
        self.errors: List[str] = []\r
\r
    def parse_file(self, file_path: str) -> JSONParseResult:\r
        """Parse JSON from file."""\r
        try:\r
            with open(file_path, 'r', encoding='utf-8') as f:\r
                data = json.load(f)\r
            return JSONParseResult(True, data, [], self._count_records(data))\r
        except json.JSONDecodeError as e:\r
            return JSONParseResult(False, None, [f"JSON Error: {e}"], 0)\r
        except Exception as e:\r
            return JSONParseResult(False, None, [str(e)], 0)\r
\r
    def parse_string(self, json_string: str) -> JSONParseResult:\r
        """Parse JSON from string."""\r
        try:\r
            data = json.loads(json_string)\r
            return JSONParseResult(True, data, [], self._count_records(data))\r
        except json.JSONDecodeError as e:\r
            return JSONParseResult(False, None, [f"JSON Error: {e}"], 0)\r
\r
    def _count_records(self, data: Any) -> int:\r
        """Count records in data."""\r
        if isinstance(data, list):\r
            return len(data)\r
        elif isinstance(data, dict):\r
            return 1\r
        return 0\r
\r
    def flatten_json(self, data: Dict, prefix: str = '') -> Dict[str, Any]:\r
        """Flatten nested JSON to single-level dict."""\r
        flat = {}\r
        for key, value in data.items():\r
            new_key = f"{prefix}_{key}" if prefix else key\r
\r
            if isinstance(value, dict):\r
                flat.update(self.flatten_json(value, new_key))\r
            elif isinstance(value, list):\r
                if all(isinstance(i, (str, int, float, bool, type(None))) for i in value):\r
                    flat[new_key] = value\r
                else:\r
                    for i, item in enumerate(value):\r
                        if isinstance(item, dict):\r
                            flat.update(self.flatten_json(item, f"{new_key}_{i}"))\r
                        else:\r
                            flat[f"{new_key}_{i}"] = item\r
            else:\r
                flat[new_key] = value\r
        return flat\r
\r
    def to_dataframe(self, data: Union[List[Dict], Dict]) -> pd.DataFrame:\r
        """Convert JSON data to DataFrame."""\r
        if isinstance(data, list):\r
            flat_records = [self.flatten_json(r) if isinstance(r, dict) else {'value': r} for r in data]\r
            return pd.DataFrame(flat_records)\r
        elif isinstance(data, dict):\r
            if all(isinstance(v, list) for v in data.values()):\r
                # Dict of lists - columnar format\r
                return pd.DataFrame(data)\r
            else:\r
                flat = self.flatten_json(data)\r
                return pd.DataFrame([flat])\r
        return pd.DataFrame()\r
\r
    def extract_elements(self, data: Dict, path: str) -> List[Any]:\r
        """Extract elements using dot notation path."""\r
        parts = path.split('.')\r
        current = data\r
\r
        for part in parts:\r
            if isinstance(current, dict) and part in current:\r
                current = current[part]\r
            elif isinstance(current, list) and part.isdigit():\r
                current = current[int(part)]\r
            else:\r
                return []\r
\r
        return current if isinstance(current, list) else [current]\r
\r
    def validate_schema(self, data: Dict,\r
                        required_fields: List[str]) -> Dict[str, Any]:\r
        """Validate JSON against required fields."""\r
        flat = self.flatten_json(data)\r
        missing = [f for f in required_fields if f not in flat]\r
        present = [f for f in required_fields if f in flat]\r
\r
        return {\r
            'valid': len(missing) == 0,\r
            'missing_fields': missing,\r
            'present_fields': present,\r
            'completeness': len(present) / len(required_fields) * 100\r
        }\r
\r
\r
# BIM JSON Parser\r
class BIMJSONParser(ConstructionJSONParser):\r
    """Specialized parser for BIM JSON exports."""\r
\r
    def parse_bim_elements(self, data: Dict) -> pd.DataFrame:\r
        """Parse BIM elements from JSON export."""\r
        elements = []\r
\r
        # Common BIM JSON structures\r
        if 'elements' in data:\r
            elements = data['elements']\r
        elif 'objects' in data:\r
            elements = data['objects']\r
        elif 'entities' in data:\r
            elements = data['entities']\r
        elif isinstance(data, list):\r
            elements = data\r
\r
        if not elements:\r
            return pd.DataFrame()\r
\r
        # Flatten each element\r
        flat_elements = []\r
        for elem in elements:\r
            if isinstance(elem, dict):\r
                flat = self.flatten_json(elem)\r
                flat_elements.append(flat)\r
\r
        return pd.DataFrame(flat_elements)\r
\r
    def extract_properties(self, element: Dict) -> Dict[str, Any]:\r
        """Extract properties from BIM element."""\r
        props = {}\r
\r
        # Common property locations in BIM JSON\r
        for key in ['properties', 'params', 'parameters', 'attributes']:\r
            if key in element and isinstance(element[key], dict):\r
                props.update(element[key])\r
\r
        return props\r
\r
\r
# IoT JSON Parser\r
class IoTJSONParser(ConstructionJSONParser):\r
    """Parser for IoT sensor data."""\r
\r
    def parse_sensor_reading(self, data: Dict) -> Dict[str, Any]:\r
        """Parse single sensor reading."""\r
        return {\r
            'sensor_id': data.get('sensor_id') or data.get('id'),\r
            'timestamp': data.get('timestamp') or data.get('time'),\r
            'value': data.get('value') or data.get('reading'),\r
            'unit': data.get('unit', ''),\r
            'location': data.get('location', '')\r
        }\r
\r
    def parse_sensor_batch(self, data: List[Dict]) -> pd.DataFrame:\r
        """Parse batch of sensor readings."""\r
        readings = [self.parse_sensor_reading(r) for r in data]\r
        return pd.DataFrame(readings)\r
```\r
\r
## Quick Start\r
\r
```python\r
parser = ConstructionJSONParser()\r
\r
# Parse from file\r
result = parser.parse_file("bim_export.json")\r
if result.success:\r
    df = parser.to_dataframe(result.data)\r
    print(f"Loaded {len(df)} records")\r
\r
# Flatten nested JSON\r
flat = parser.flatten_json(result.data)\r
\r
# Extract specific path\r
elements = parser.extract_elements(result.data, "project.building.floors")\r
```\r
\r
## Common Use Cases\r
\r
### 1. BIM Metadata\r
```python\r
bim_parser = BIMJSONParser()\r
result = bim_parser.parse_file("revit_export.json")\r
elements = bim_parser.parse_bim_elements(result.data)\r
```\r
\r
### 2. IoT Sensors\r
```python\r
iot_parser = IoTJSONParser()\r
readings = iot_parser.parse_sensor_batch(sensor_data)\r
```\r
\r
### 3. API Response\r
```python\r
parser = ConstructionJSONParser()\r
result = parser.parse_string(api_response)\r
df = parser.to_dataframe(result.data)\r
```\r
\r
## Resources\r
- **DDC Book**: Chapter 2.1 - Semi-structured Data\r