pandas_util

pandas_util.py

import io
import re

import pandas as pd


def _prepare_pipe_separated_str(str_input):
    substitutions = [
        ('^ *', ''),  # Remove leading spaces
        (' *$', ''),  # Remove trailing spaces
        (r' *\| *', '|'),  # Remove spaces between columns
    ]
    if all(line.lstrip().startswith('|') and line.rstrip().endswith('|') for line in str_input.strip().split('\n')):
        substitutions.extend([
            (r'^\|', ''),  # Remove redundant leading delimiter
            (r'\|$', ''),  # Remove redundant trailing delimiter
        ])
    for pattern, replacement in substitutions:
        str_input = re.sub(pattern, replacement, str_input, flags=re.MULTILINE)
    return str_input


def read_pipe_separated_str(str_input):
    """Read a Pandas object from a pipe-separated table contained within a string.

    Example:
        | odcd_wacs | cs_wacs | automation_eligible |
        |           |         | True                |
        |           | 0       | False               |
        |           | 576     | True                |
        | 300       | 600     | True                |

    The leading and trailing pipes are optional, but if one is present, so must be the other.

    In PyCharm, the "Pipe Table Formatter" plugin has a "Format" feature that can be used to neatly format a table.
    """
    str_input = _prepare_pipe_separated_str(str_input)
    return pd.read_csv(io.StringIO(str_input), sep='|')