Parse all languages as specified by TK Speakeasy

ruby_reader.py

# this script is assumed to live in the directory https://github.com/typekit/speakeasy/tree/master/data
import os
import re


def get_code_points(language_file):
    with open(language_file, 'r') as f:
        raw_data = f.read().splitlines()
    split_index = raw_data.index('---') + 5
    data = raw_data[split_index:]
    code_points = []

    for line in data:
        if line.startswith('-'):
            rx_range = re.match(r'- !ruby/range (\d*)\.\.(\d*)', line)
            rx_codepoint = re.match(r'- (\d*)', line)
            if rx_range:
                range_start = int(rx_range.group(1))
                range_end = int(rx_range.group(2)) + 1
                code_points.extend(range(range_start, range_end))
            elif rx_codepoint:
                cp = int(rx_codepoint.group(1))
                code_points.append(cp)
            # else:
            #     print(line)
    return(sorted(code_points))


lang_dict = {}
for filename in os.listdir(os.curdir):
    if os.path.splitext(filename)[-1] is '':
        lang_dict[filename] = ''.join(
            chr(code_point) for code_point in get_code_points(filename))


# print(lang_dict.items())
print(lang_dict)