使用python将值插入到JS脚本中

Question

我正在解析存储在目录中的JS文件，以获取tags中的值。在使用regex在tags中找到相关值后，我希望将这些值移到一个名为controls的新节下。我已经能够使用下面的脚本在controls变量中获得所需的值：

def parse_sigs(target_folder):    
    try:
        count = 0

        for root, dir, files in os.walk(target_folder):
            for file in files:
                file_extension = os.path.splitext(file)[1]
                if file_extension.lower() == ".js":
                    print(file)
                    filename = os.path.join(root, file)
                    print(f'Processing : {filename}')

                    with open(filename, "r") as f_in:
                        data = f_in.read()
                    data = re.search(r"\btags\s*:\s*(\[.*?\])", data, flags=re.S)
                    if data:
                        data = literal_eval(data.group(1))
                        #print(type(data)
                        cregex = re.compile(r".*\-.*\-.*[\.|\-].*")
                        controls = list(filter(cregex.match, data))
                            
                        count +=1
                        print(controls)
        print(count)
    except Exception as e:
        print(f"Error in Processing  {filename} Skipping -- ")  
        print(e)  

我想不出一种将controls列表作为一个新字段插入JS文件并更新它的方法。它应该出现在tags字段之后。

JS文件示例如下：

var fs = require('fs');
var path = require('path')
const remediation = fs.readFileSync(path.resolve(__dirname, '../sig/file.md'), 'utf-8')

module.exports = {
  status: "ENABLED",
  sig: {
    name: "iam",
    tags: [
        "aws",
        "iam",
        "compliance",
        "chg-02.1",
        "AWS-CIS-v1.4",
        "AWS-CIS-v1.4-1.12",
        "AWS-CIS-v1.4-1.14",
        "SOC-2",
        "SOC-2-CC6.8",
        "NIST-800-53rev5",
        "NIST-800-53rev5-CM-3(1)"
    ],
    result: "A.id, A.name",
    result_header: [
      "account_id",
      "account_name",
    ],
    primary_resource: "user_arn",
  },
  expected: {
   "all":
    [
      {
        user_name: "2506"
      }
    ]
  }
};

我的最终目标是创建一个JS文件，其tags和新添加的controls部分如下所示：

    tags: [
        "aws",
        "iam",
        "compliance",
        "chg-02.1",
        "AWS-CIS-v1.4",
        "SOC-2",
        "NIST-800-53rev5"
    ],

controls: [
        "AWS-CIS-v1.4-1.12",
        "AWS-CIS-v1.4-1.14",
        "NIST-800-53rev5-CM-3(1)",
        "SOC-2-CC6.8",
    ],

编辑:能够让它使用@Dev提供的解决方案。唯一不合适的是关闭]。是否有一种方法可以将结束括号正确地缩进？

    tags: [
        "aws",
        "docdb",
        "kms",
        "configuration-check",
],
 controls: [
        "SOC-2-CC6.1",
        "NIST-800-53rev5-SC-12"
]

Answer 1

您可以提取这些标记并使用包jsonnet将它们转换为JSON，然后使用regex对它们进行迭代，然后构建一个字符串来替换原始标记，如下所示：

import json
import os
import re
import _jsonnet


def parse_sigs(target_folder):
    
    count = 0
    cregex = re.compile(r".*-.*-.*[.|\-].*")
    for root, _, files in os.walk(target_folder):
        for file in files:
            file_extension = os.path.splitext(file)[1]

            if file_extension.lower() == ".js":
                new_tags = []
                controls = []
                # pint(file)

                filename = os.path.join(root, file)
                print(f'Processing : {filename}')
                try:
                    with open(filename, "r") as f_in:
                        data = f_in.read()
                        snippet = re.findall(r'module.exports = (.*);', data, flags=re.S)[0]
                    json_data = json.loads(_jsonnet.evaluate_snippet('snippet', snippet))

                    # print(json.dumps(json_data['sig']['tags'], indent=4))
                    for tag in json_data['sig']['tags']:
                        if re.match(cregex, tag):
                            controls.append(tag)
                        else:
                            new_tags.append(tag)
                    new_string = f"tags: {json.dumps(new_tags, indent=8)},\n controls: {json.dumps(controls, indent=8)}"

                    data = re.sub(r'tags: \[(.*?)]', new_string, data, flags=re.S)
                    
                    if data:
                        print(data)
                        count += 1
                    print(count)
                    
                except Exception as e:
                    print(f"Error in Processing  {filename} Skipping -- ")
                    print(e)


parse_sigs('./')

产出：

Processing : ./test.js
var fs = require('fs');
var path = require('path')
const remediation = fs.readFileSync(path.resolve(__dirname, '../sig/file.md'), 'utf-8')

module.exports = {
  status: "ENABLED",
  sig: {
    name: "iam",
    tags: [
        "aws",
        "iam",
        "compliance",
        "chg-02.1",
        "SOC-2",
        "NIST-800-53rev5"
],
 controls: [
        "AWS-CIS-v1.4",
        "AWS-CIS-v1.4-1.12",
        "AWS-CIS-v1.4-1.14",
        "SOC-2-CC6.8",
        "NIST-800-53rev5-CM-3(1)"
],
    result: "A.id, A.name",
    result_header: [
      "account_id",
      "account_name",
    ],
    primary_resource: "user_arn",
  },
  expected: {
   "all":
    [
      {
        user_name: "2506"
      }
    ]
  }
};


1

用格式更新：

import json
import os
import re
import _jsonnet
import jsbeautifier


opts = jsbeautifier.default_options()
opts.indent_size = 2
opts.space_in_empty_paren = True


def parse_sigs(target_folder):
    count = 0
    cregex = re.compile(r".*-.*-.*[.|\-].*")
    for root, _, files in os.walk(target_folder):
        for file in files:
            file_extension = os.path.splitext(file)[1]

            if file_extension.lower() == ".js":
                new_tags = []
                controls = []
                # pint(file)

                filename = os.path.join(root, file)
                print(f'Processing : {filename}')
                try:
                    with open(filename, "r") as f_in:
                        data = f_in.read()
                        snippet = re.findall(r'module.exports = (.*);', data, flags=re.S)[0]
                    json_data = json.loads(_jsonnet.evaluate_snippet('snippet', snippet))

                    # print(json.dumps(json_data['sig']['tags'], indent=4))
                    for tag in json_data['sig']['tags']:
                        if re.match(cregex, tag):
                            controls.append(tag)
                        else:
                            new_tags.append(tag)
                    new_string = f"tags: {json.dumps(new_tags, indent=8)},\n controls: {json.dumps(controls, indent=8)}"

                    data = re.sub(r'tags: \[(.*?)]', new_string, data, flags=re.S)

                    data = jsbeautifier.beautify(data, opts)

                    if data:
                        print(data)
                        count += 1
                    print(count)

                except Exception as e:
                    print(f"Error in Processing  {filename} Skipping -- ")
                    print(e)


parse_sigs('./')