generate_bolts_yml.py

generate_bolts_yml.py

from pathlib import Path
from pprint import pprint

def find_nth_overlapping(haystack, needle, n=1):
    start = haystack.find(needle)
    while start >= 0 and n > 1:
        start = haystack.find(needle, start+1)
        n -= 1
    return start

def process_table_data(table_data, x_split=1):
    lines = table_data.splitlines()
    test_spaces_amount = lines[0].strip().count(' ')
    output_lines = []
    for line in lines:
        line = line.strip()
        # print(line, '___', line.count('x'))
        if x_split > 0:
            if line.count('x') == x_split:
                previous_line_part = line[:find_nth_overlapping(line, 'x', x_split) +2]
            else:
                line = previous_line_part + line

        # print(f'previous line: {previous_line_part}')            
        output_lines.append(line.split())
        current_spaces_count = line.count(' ')

        if current_spaces_count != test_spaces_amount:
            raise Exception(f'Line: {line} have {current_spaces_count} spaces. First line had {test_spaces_amount} spaces.\nFirst line: {lines[0]}')
    return output_lines


def check_final_data(headers, value_types, output_lines):
    # print(len(headers), len(value_types), len(output_lines[0]))
    assert len(headers) == len(value_types) and len(value_types) == len(output_lines[0]), 'Headers, value_types and columns of data should be consistent.'
    assert len(headers) == len((set(headers))), f"Headers shouldn't have duplicates. Duplicates: {[i for i in set(headers) if headers.count(i) > 1]}"


# US C Type
def get_us_c_type_data():
    headers = [
        "type", "h", "b", "tw", "tf", "sf", "r1", "r2"
    ]
    value_types = [
        "", "in", "in", "in", "in", "%", "in", "in"
    ]

    table_data = """C15X50	15.0	3.72	0.716	0.650 16.67 0.719	0.185
    C15X40	15.0	3.52	0.520	0.650 16.67 0.7	0.195
    C15X33.9	15.0	3.40	0.400	0.650 16.67 0.688	0.2
    C12X30	12.0	3.17	0.510	0.501 16.67 0.54	0.129
    C12X25	12.0	3.05	0.387	0.501 16.67 0.527	0.135
    C12X20.7	12.0	2.94	0.282	0.501 16.67 0.517	0.14
    C10X30	10.0	3.03	0.673	0.436 16.67 0.508	0.1
    C10X25	10.0	2.89	0.526	0.436 16.67 0.493	0.106
    C10X20	10.0	2.74	0.379	0.436 16.67 0.479	0.113
    C10X15.3	10.0	2.60	0.240	0.436 16.67 0.465	0.12
    C9X20	9.00	2.65	0.448	0.413 16.67 0.529	0.105
    C9X15	9.00	2.49	0.285	0.413 16.67 0.512	0.112
    C9X13.4	9.00	2.43	0.233	0.413 16.67 0.508	0.115
    C8X18.75	8.00	2.53	0.487	0.390 16.67 0.502	0.098
    C8X13.75	8.00	2.34	0.303	0.390 16.67 0.484	0.106
    C8X11.5	8.00	2.26	0.220	0.390 16.67 0.476	0.11
    C7X14.75	7.00	2.30	0.419	0.366 16.67 0.465	0.095
    C7X12.25	7.00	2.19	0.314	0.366 16.67 0.455	0.1
    C7X9.8	7.00	2.09	0.210	0.366 16.67 0.444	0.105
    C6X13	6.00	2.16	0.437	0.343 16.67 0.435	0.089
    C6X10.5	6.00	2.03	0.314	0.343 16.67 0.424	0.095
    C6X8.2	6.00	1.92	0.200	0.343 16.67 0.412	0.1
    C5X9	5.00	1.89	0.325	0.320 16.67 0.392	0.089
    C5X6.7	5.00	1.75	0.190	0.320 16.67 0.379	0.095
    C4X7.25	4.00	1.72	0.321	0.296 16.67 0.437	0.083
    C4X6.25	4.00	1.65	0.247	0.296 16.67 0.429	0.086
    C4X5.4	4.00	1.58	0.184	0.296 16.67 0.424	0.09
    C4X4.5	4.00	1.52	0.125	0.296 16.67 0.418	0.092
    C3X6	3.00	1.60	0.356	0.273 16.67 0.409	0.076
    C3X5	3.00	1.50	0.258	0.273 16.67 0.4	0.081
    C3X4.1	3.00	1.41	0.170	0.273 16.67 0.391	0.085
    C3X3.5	3.00	1.37	0.132	0.273 16.67 0.387	0.087"""

    output_lines = process_table_data(table_data, x_split=0)
    check_final_data(headers, value_types, output_lines)
    headers_filter = headers[1:]

    return output_lines, headers, headers_filter
# ===============================================

# profile_path, profile_data, data_headers, headers_filter
profiles_data = [
    ('data/profile_c/cbeam_c_imp.yaml', *get_us_c_type_data()),
]

def get_yaml_line(element_name, element_data, name_width=25, data_width=10):
    element_data_str =  ','.join([str(i).rjust(data_width) for i in element_data])
    line = f'{(element_name+":").ljust(name_width)} [{element_data_str} ]\n'
    return line

def get_yaml_header(element_name, element_data, name_width=25, data_width=10):
    element_data_str =  ' '.join([str(i).rjust(data_width) for i in element_data])
    line = f'{("#"+element_name+":").ljust(name_width)} [{element_data_str} ]\n'
    return line

base_path = Path(__file__).parent

for profile_data in profiles_data:
    print(f'Processing {profile_data[0]}')
    profile_path, profile_data, data_headers, headers_filter = profile_data
    data_indices = [i for i in range(len(data_headers)) if data_headers[i] in headers_filter]
    
    # sort data the same way as headers
    data_indices = sorted(data_indices, key=lambda x: headers_filter.index(data_headers[x]))
    assert len(data_indices) == len(headers_filter), "Amount of data columns the expected amount (header_filter)"

    profile_path = base_path / Path(profile_path)
    profile_path.parent.mkdir(exist_ok=True, parents=True)

    lines = []
    lines.append(get_yaml_header('type', headers_filter))
    for data_row in profile_data:
        profile_type = data_row[0]
        yml_data = [data_row[i] for i in data_indices]
        line = get_yaml_line(profile_type, yml_data)
        lines.append(line)

    def all_lines_have_the_space_at(char_i):
        return all(line[char_i] == ' ' for line in lines)
    
    def remove_character_from_lines(char_i):
        for i in range(len(lines)):
            line = lines[i]
            lines[i] = line[:char_i] + line[char_i+1:]

    # clean up unnecessary spaces
    char_i = -1
    while True:
        if char_i >= len(lines[0]) - 1:
            break

        char_i += 1
        cur_char = lines[0][char_i]

        if cur_char != ' ':
            continue

        if not all_lines_have_the_space_at(char_i):
            continue

        char_i += 1
        while all_lines_have_the_space_at(char_i):
            remove_character_from_lines(char_i)

    with open(profile_path, 'w') as file_output:
        for line in lines:
            file_output.write(line)