正则表达式读取数据（七巧板）

之前的“七巧板”题使用split()读取.xml文件中的数据，现在改用正则表达式读取

 

代码：

import re
import copy

# get colours and coordinates
def available_coloured_pieces_orig(file_name):
    # get all coordinates from file
    coloured_pieces = []  # store coordinates
    line = file_name.readline()
    while line:
        line_tmp = copy.deepcopy(line)  # deepcopy for using split() function
        line_tmp_split = line_tmp.split()
        if len(line_tmp_split) > 0 and line_tmp_split[0] == "<path":
            shape = [int(s) for s in line_tmp_split if s.isdigit()]  # <class 'list'>: [30, 20, 110, 20, 110, 120, 30, 120]
            shape_color = []  # <class 'list'>: ["red", (30, 20), (110, 20), (110, 120), (30, 120)]
            shape_color.append(line_tmp.split('"')[-2])
            for i in range(len(shape))[::2]:
                point = (shape[i], shape[i+1])
                shape_color.append(point)
            coloured_pieces.append(shape_color)  # store each shape's coordinates
        line = file_name.readline()

    return coloured_pieces


# regular_expression
def available_coloured_pieces(file_name):
    coloured_pieces = []  # store coordinates
    # shape_color = []
    line = file_name.readline()
    info_pattern = '<path([\d\D]*)/>'
    point_pattern = ' (\d+)'
    color_pattern = '"(\w+)"'
    while line:
        line_info = re.findall(info_pattern, line)
        if line_info:
            line_point = re.findall(point_pattern, line_info[0])
            line_color = re.findall(color_pattern, line_info[0])
            shape_color = []
            # shape_color.clear()
            shape_color.append(line_color[0])
            for i in range(len(line_point))[::2]:
                point = (int(line_point[i]), int(line_point[i + 1]))
                shape_color.append(point)

            coloured_pieces.append(shape_color)

        line = file_name.readline()


    return coloured_pieces


file = open('tangram_A_1_a.xml')
coloured_pieces_orig = available_coloured_pieces_orig(file)

file = open('tangram_A_1_a.xml')
coloured_pieces = available_coloured_pieces(file)

print(coloured_pieces == coloured_pieces_orig)

注：文中若使用初始定义的shape_color=[]，并使用shape_color.clear()和coloured_pieces.append(shape_color)会出错，因为append进去的是索引值，因此之后改变shape_color的内容，coloured_pieces中之前append进去的shape_color也会跟着改变。