使用Regex提取数据

Question

我制作的正则表达式从 opts.taskDetails.order_details 中获取项目列表。

我想优化正则表达式/任何其他更好的正则表达式以获取以下数据，如上图所示。 （可以是1个项目列表，也可以是多个）。

除了获取项目详细信息外，我还想获取以下 opts.taskDetails.order_details 中的获取项目列表后剩下的数据。

Tipo de papa: -\nPapa Amarilla Tumbay S/0.00\n Adicional : - Quesp cheddar S/0.00\n Agrega Bebida: - Fanta 400 ml S/0.00\n
Salsas: - Mayonesa S/0.00\n - Ketchup S/0.00\n - Golf S/0.00\n - Guacamole S/0.00\n - Ají S/0.00\n - Tártara S/0.00\n - Mayo-aji S/0.00\n

代码

var opts = {
      "items": [{
        "mail_parser_label": "order_details",
        "label": "order_details",
        "data_type": "Table",
        "app_side": "0",
        "required": 0,
        "value": 1,
        "data": {
          "head": [{
            "mail_parser_label": "Detalle",
            "label": "Detalle",
            "type": "text",
            "arth": " ",
            "id": 0,
            "show": 1,
            "app_side": 0,
            "required": 0
          }, {
            "mail_parser_label": "Cantidad",
            "label": "Cantidad",
            "type": "text",
            "arth": " ",
            "id": 1,
            "show": 1,
            "app_side": 0,
            "required": 0
          }, {
            "mail_parser_label": "Unidad",
            "label": "Unidad",
            "type": "text",
            "arth": " ",
            "id": 2,
            "show": 1,
            "app_side": 0,
            "required": 0
          }, {
            "mail_parser_label": "Total",
            "label": "Total",
            "type": "text",
            "arth": " ",
            "id": 2,
            "show": 1,
            "app_side": 0,
            "required": 0
          }],
          "other": [],
          "body": []
        },
        "template_id": "NUEVO_PEDIDO",
        "appCheck": true
      }],
      "taskDetails": {
      "order_details":"Detalle\n Unidad\n Cantidad\n Total\n     Triple Insomnio Especial   S/37.90 1  S/37.90   Insomnio Especial  \nS/212 S/23.12 *Tipo de papa:*  - Papa Amarilla Tumbay S/0.00\n     *Adicional :*  - Quesp cheddar S/0.00\n     *Agrega Bebida:*  - Fanta 400 ml S/0.00\n     *Salsas:*  - Mayonesa S/0.00\n - Ketchup S/0.00\n - Golf S/0.00\n - Guacamole S/0.00\n - Ají S/0.00\n - Tártara S/0.00\n - Mayo-aji S/0.00\n       "
      
    }
}
    
    var items = opts.items;
    var taskDetails = opts.taskDetails;
    for (var p = 0; p < items.length; p++) {
      var parameter = items[p];
      if (parameter.mail_parser_label == "order_details") {
        var str = taskDetails.order_details.toString().replace(/[ ]+/g, ' ');
        var itemPatternFull = str.match(/[A-Za-z0-9 ]*S\/\d{1,}[.]*\d*\s+\d{1,}\s+S\/\d{1,}[.]*\d*/g);
        var itemPattern = itemPatternFull ? itemPatternFull.toString().match(/S\/\d{1,}[.]*\d*\s+\d{1,}\s+S\/\d{1,}[.]*\d*/g) : [];
        var details = itemPatternFull ? itemPatternFull.toString().replace(/S\/\d{1,}[.]*\d*\s+\d{1,}\s+S\/\d{1,}[.]*\d*/g, '').toString().split(',') : [];
        var itemPatternLength = str.match(/S\/\d{1,}[.]*\d*\s+\d{1,}\s+S\/\d{1,}[.]*\d*/g).length;
        var itemPattern = str.match(/S\/\d{1,}[.]*\d*\s+\d{1,}\s+S\/\d{1,}[.]*\d*/g);
        var itemPatternArray = itemPattern.toString().replace(',', ' ').split(' ');
        str = str.split(' ');
    
    
    
        var count = 0;
        if (itemPatternArray.length < str.length && details.length == itemPatternArray.length / 3) {
          for (columnIndex = 0; columnIndex < itemPatternArray.length; columnIndex++) {
            if (columnIndex % 3 == 0) {
              parameter.data.body.push({
                "val": details[count].trim(),
                "id": count + columnIndex,
                "head": "Dettalle"
              });
              count++;
            }
            parameter.data.body.push({
              "val": itemPatternArray[columnIndex].replace(/S\//, ''),
              "id": columnIndex + count,
              "head": str[(columnIndex % 3) + 1] ? str[(columnIndex % 3) + 1].toString().replace('\n', '') : str[(columnIndex % 3) + 1]
            });
          }
        }
      } else {
        parameter.data = taskDetails[parameter.mail_parser_label].toString().trim().replace(/[\s+\n]/g, ' ');
      }
    }
    console.log("ITEMS", parameter.data.body)

Answer 1

这里是regex，用于切碎order_details，并在末尾提取其余部分。

我使用一个rx来获取标题，项目和其他内容。然后另一个使用g标志来解析项目。您可以在正则表达式中进行更多验证，或者将匹配项解析为数字，但您应该明白这一点。关键是两阶段解析。

我将结果放入order对象中。您可以简单地将其映射到所需的任何内容。显示与其他代码隔离的正则表达式和解决方案更加容易。

var order_details = `Detalle\n Unidad\n Cantidad\n Total\n Triple Insomnio Especial S/37.90 1 S/37.90 Insomnio Especial \nS/23.12 1 S/23.12 Tipo de papa: - Papa Amarilla Tumbay S/0.00\n Adicional : - Quesp cheddar S/0.00\n Agrega Bebida: - Fanta 400 ml S/0.00\n Salsas: - Mayonesa S/0.00\n - Ketchup S/0.00\n - Golf S/0.00\n - Guacamole S/0.00\n - Ají S/0.00\n - Tártara S/0.00\n - Mayo-aji S/0.00\n " `

var order_details2 = `Detalle\n Unidad\n Cantidad\n Total\n Combo Cheese Burger para 2 S/39.90 1 S/39.90 Salsas primera: -\nGolf S/0.00\n Elige tu bebida: - Coca Cola 500ml S/0.00\n Elige tu bebida: - Coca Cola 500ml S/0.00\n Verduras primera : - Cebolla blanca S/0.00\n - Tomate S/0.00\n - Lechuga S/0.00\n Salsas segunda : - Golf S/0.00\n - Tártara S/0.00\n Verduras segunda : - Cebolla blanca S/0.00\n - Tomate S/0.00\n - Lechuga S/0.00\n Porción de papa : - Papa Regular S/0.00\n`

function parse(string) {
  // header, items, and tipo
  var rxItems = /Detalle\n Unidad\n Cantidad\n\ Total\n\s*([^:]+)(([^:]+:[\s\S]*)) /

  // single item line
  var rxItem = /s*(.*?)\s+(S\/.*?)\s+(\d+)\s+(S\/.*?)/g

  var order = {
    items: [],
    other: null
  }

  var mParts = rxItems.exec(string)
  var items = mParts[1]
  order.other = mParts[2]

  var mItem = rxItem.exec(items)
  while (mItem) {
    var detalle = mItem[1]
    var unidad = mItem[2]
    var cantidad = mItem[3]
    var total = mItem[4]
    let item = {
      detalle,
      unidad,
      cantidad,
      total
    }
    order.items.push(item)
    mItem = rxItem.exec(items)
  }
  console.log(order)
}

parse(order_details)
parse(order_details2)