CSV Handler for Construction Data

Overview

CSV is the universal exchange format in construction - from scheduling exports to cost databases. This skill handles encoding issues, delimiter detection, and data cleaning.

Python Implementation

import pandas as pd
import csv
from typing import Dict, Any, List, Optional, Tuple
from pathlib import Path
from dataclasses import dataclass
import chardet


@dataclass
class CSVProfile:
    """Profile of CSV file."""
    encoding: str
    delimiter: str
    has_header: bool
    row_count: int
    column_count: int
    columns: List[str]


class ConstructionCSVHandler:
    """Handle CSV files from construction software."""

    COMMON_DELIMITERS = [',', ';', '\t', '|']
    COMMON_ENCODINGS = ['utf-8', 'utf-8-sig', 'latin-1', 'cp1252', 'iso-8859-1']

    def __init__(self):
        self.last_profile: Optional[CSVProfile] = None

    def detect_encoding(self, file_path: str) -> str:
        """Detect file encoding."""
        with open(file_path, 'rb') as f:
            raw = f.read(10000)
        result = chardet.detect(raw)
        return result.get('encoding', 'utf-8') or 'utf-8'

    def detect_delimiter(self, file_path: str, encoding: str) -> str:
        """Detect CSV delimiter."""
        with open(file_path, 'r', encoding=encoding, errors='replace') as f:
            sample = f.read(5000)

        # Count occurrences
        counts = {d: sample.count(d) for d in self.COMMON_DELIMITERS}

        # Return most common that appears consistently
        if counts:
            return max(counts, key=counts.get)
        return ','

    def profile_csv(self, file_path: str) -> CSVProfile:
        """Profile CSV file."""
        encoding = self.detect_encoding(file_path)
        delimiter = self.detect_delimiter(file_path, encoding)

        # Read sample
        df = pd.read_csv(file_path, encoding=encoding, delimiter=delimiter,
                         nrows=10, on_bad_lines='skip')

        has_header = not df.columns[0].replace('.', '').replace('-', '').isdigit()

        # Full row count
        with open(file_path, 'r', encoding=encoding, errors='replace') as f:
            row_count = sum(1 for _ in f) - (1 if has_header else 0)

        profile = CSVProfile(
            encoding=encoding,
            delimiter=delimiter,
            has_header=has_header,
            row_count=row_count,
            column_count=len(df.columns),
            columns=list(df.columns)
        )
        self.last_profile = profile
        return profile

    def read_csv(self, file_path: str,
                 encoding: Optional[str] = None,
                 delimiter: Optional[str] = None,
                 clean: bool = True) -> pd.DataFrame:
        """Read CSV with auto-detection."""

        # Auto-detect if not provided
        if encoding is None:
            encoding = self.detect_encoding(file_path)
        if...