Parser/clear_data.py

import re

'''
Use normalize_molar_ratios() to turn the original ratios to required format.
For example: [0.5,0.5,0.5,0.5] -> [0.25,0.25,0.25,0.25]
'''
def normalize_molar_ratios(ratios):
    normalized_ratios = list()
    ele_sum = sum(ratios)
    for ele in ratios:
        ele = float(ele / ele_sum)
        normalized_ratios.append(ele)
    return normalized_ratios


'''
Turn the original alloy string to every element and corresponding content(without normalization).
For example: 'Ag2Cu3C' -> result_ele = ['Ag','Cu','C'], result__num = ['2','3','1']
'''
def clean_row(row: str):
    #result_ele = re.split(r'[^a-zA-Z]+', row)
    result_ele = []

    ## The list s contains all of the elements in an alloy.
    s = list(''.join(ch for ch in row if ch.isalpha()))

    ## Get the list of result_ele.
    for i in range(len(s)-1):
        # In terms of the
        if s[i].isupper() and s[i+1].islower():
            element = str(s[i]+s[i+1])
            # print(element)
            result_ele.append(element)
        if s[i].isupper() and s[i+1].isupper():
            element = str(s[i])
            # print(element)
            result_ele.append(element)

    if len(s)!=0:
        ## The last element is an element which is only one letter, for example 'C', add it to the result_ele.
        if s[-1].isupper():
            element = str(s[-1])
            result_ele.append(element)
    # print("Elements: ", result_ele)

    ## Get the list of result__num
    row_list = list(row)
    # print(row_list)
    num_list = row_list.copy()
    index = 1
    for i in range(len(num_list)-1):
        # print(num_list[i])
        ## In terms of the situation "AgAl0.5" and "CAg0.5", add '1' in the middle of elements.
        if num_list[i].islower() and num_list[i+1].isupper():
            row_list.insert(i+index,str(1))
            index+=1
            # num_list.append(str(1))
        if num_list[i].isupper() and num_list[i+1].isupper():
            row_list.insert(i+index,str(1))
            index+=1
            # row_list.append(str(1))
        # elif row_list[i].is
    if row_list[-1].isalpha():
        row_list.append(str(1))
        # print("New row: "+ "".join(row_list))

    result_num = re.findall(r'-?\d+\.?\d*e?-?\d*?', "".join(row_list))
    # print(result_num)
    result__num = list()
    for i in result_num:
        float_ratio = float(i)
        result__num.append(float_ratio)
    #     print("Ratios: " + str(result__num))
    #     # print("Dictionary Format: " + str(ele_dic))
    # print("Element：" + str(result_ele))
    # print("Content" + str(result_num))
    # print("---------------------------")

    return result_ele, result__num