• 转义非字母数字的字符，转义结果为预定义字符串codepoint2name[]

def qstr_escape(qst):
    def esc_char(m):
        c = ord(m.group(0))
        try:
            name = codepoint2name[c]
        except KeyError:
            name = "0x%02x" % c
        return "_" + name + "_"

    return re.sub(r"[^A-Za-z0-9_]", esc_char, qst)

• 生成静态qstr列表

def parse_input_headers(infiles):
    qcfgs = {}
    qstrs = {}

    # add static qstrs
    for qstr in static_qstr_list:
        # work out the corresponding qstr name
        ident = qstr_escape(qstr)

        # don't add duplicates
        assert ident not in qstrs

        # add the qstr to the list, with order number to retain original order in file
        order = len(qstrs) - 300000
        qstrs[ident] = (order, ident, qstr)
        print(qstrs[ident])

执行结果

• 生成输入文件的qstr列表，带去重机制

# 主要做两件事：提取QCFG配置的长度字节数和哈希字节数，提取Q描述的qstr字符串
# read the qstrs in from the input files
    for infile in infiles:
        with open(infile, "rt") as f:
            for line in f:
                line = line.strip()

                # is this a config line?
                match = re.match(r"^QCFG\((.+), (.+)\)", line)
                if match:
                    value = match.group(2)
                    if value[0] == "(" and value[-1] == ")":
                        # strip parenthesis from config value
                        value = value[1:-1]
                    qcfgs[match.group(1)] = value
                    continue

                # is this a QSTR line?
                match = re.match(r"^Q\((.*)\)$", line)
                if not match:
                    continue

                # get the qstr value
                qstr = match.group(1)

                # special cases to specify control characters
                if qstr == "\\n":
                    qstr = "\n"
                elif qstr == "\\r\\n":
                    qstr = "\r\n"

                # work out the corresponding qstr name
                ident = qstr_escape(qstr)

                # don't add duplicates
                if ident in qstrs:
                    continue

                # add the qstr to the list, with order number to retain original order in file
                order = len(qstrs)
                # but put special method names like __add__ at the top of list, so
                # that their id's fit into a byte
                if ident == "":
                    # Sort empty qstr above all still
                    order = -200000
                elif ident == "__dir__":
                    # Put __dir__ after empty qstr for builtin dir() to work
                    order = -190000
                elif ident.startswith("__"):
                    order -= 100000
                qstrs[ident] = (order, ident, qstr)

• 生成QSTR表的输入文件示例

• 将生成的QSTR表定位到文件

上述问题解决：输入 bash 回车，然后再次执行生成

• 修改脚本使输出格式符合代码运行要求

def make_bytes(cfg_bytes_len, cfg_bytes_hash, qstr):
    qbytes = bytes_cons(qstr, "utf8")
    qlen = len(qbytes)
    qhash = compute_hash(qbytes, cfg_bytes_hash)
    if qlen >= (1 << (8 * cfg_bytes_len)):
        print("qstr is too long:", qstr)
        assert False
    qdata = escape_bytes(qstr, qbytes)
    # return '%d, %d, "%s"' % (qhash, qlen, qdata)
    return '"\\x%02x\\x%02x\\x%02x" "%s"' % (qhash >> 8, qhash & 0xFF, qlen, qdata)


def print_qstr_data(qcfgs, qstrs):
    # get config variables
    cfg_bytes_len = int(qcfgs["BYTES_IN_LEN"])
    cfg_bytes_hash = int(qcfgs["BYTES_IN_HASH"])

    # print out the starter of the generated C header file
    print("// This file was automatically generated by makeqstrdata.py")
    print("")

    # add NULL qstr with no hash or data
    # print('QDEF(MP_QSTRnull, 0, 0, "")')
    print('QDEF(MP_QSTRnull, "\\x00\\x00\\x00" "")')

    # go through each qstr and print it out
    # sorted(object,  key=lambda  变量：变量[维数] )：对qstrs按第一维数据进行由小到大排序
    for order, ident, qstr in sorted(qstrs.values(), key=lambda x: x[0]):
        qbytes = make_bytes(cfg_bytes_len, cfg_bytes_hash, qstr)
        print("QDEF(MP_QSTR_%s, %s)" % (ident, qbytes))