将字符串解析为时间，但未知布局。

huangapple
go评论147阅读模式
英文:

Parsing string to time with unknown layout

问题

我有一个csv文件，想要读取：

  1. 表头名称
  2. 字段类型

所以，我写了以下代码：

  1. package main
  3. import (
  4. 	"encoding/csv"
  5. 	"fmt"
  6. 	"os"
  7. 	"log"
  8. 	"reflect"
  9. 	"strconv"
  10. )
  12. func main() {
  13. 	filePath := "./file.csv"
  14. 	headerNames := make(map[int]string)
  15. 	headerTypes := make(map[int]string)
  16. 	// 加载csv文件
  17. 	f, _ := os.Open(filePath)
  18. 	// 创建一个新的读取器
  19. 	r := csv.NewReader(f)
  20. 	// 只读取第一行
  21. 	header, err := r.Read()
  22. 	checkError("发生其他错误", err)
  24. 	// 添加映射：列/属性名称 --> 记录索引
  25. 	for i, v := range header {
  26. 		headerNames[i] = v
  27. 	}
  29. 	// 读取第二行
  30. 	record, err := r.Read()
  31. 	checkError("发生其他错误", err)
  32. 	// 检查记录字段类型
  33. 	for i, v := range record {
  34. 		var value interface{}
  35. 		if value, err = strconv.Atoi(v); err != nil {
  36. 			if value, err = strconv.ParseFloat(v, 64); err != nil {
  37. 				if value, err = strconv.ParseBool(v); err != nil {
  38. 					if value, err = strconv.ParseBool(v); err != nil { // <== 如何处理未知布局的情况
  39. 						// 值是字符串
  40. 						headerTypes[i] = "string"
  41. 						value = v
  42. 						fmt.Println(reflect.TypeOf(value), reflect.ValueOf(value))
  43. 					} else {
  44. 						// 值是时间戳
  45. 						headerTypes[i] = "time"
  46. 						fmt.Println(reflect.TypeOf(value), reflect.ValueOf(value))
  47. 					}
  48. 				} else {
  49. 					// 值是布尔型
  50. 					headerTypes[i] = "bool"
  51. 					fmt.Println(reflect.TypeOf(value), reflect.ValueOf(value))
  52. 				}
  53. 			} else {
  54. 				// 值是浮点型
  55. 				headerTypes[i] = "float"
  56. 				fmt.Println(reflect.TypeOf(value), reflect.ValueOf(value))
  57. 			}
  58. 		} else {
  59. 			// 值是整型
  60. 			headerTypes[i] = "int"
  61. 			fmt.Println(reflect.TypeOf(value), reflect.ValueOf(value))
  62. 		}
  63. 	}
  65. 	for i, _ := range header {
  66. 		fmt.Printf("表头: %v \t类型: %v\n", headerNames[i], headerTypes[i])
  67. 	}
  68. }
  70. func checkError(message string, err error) {
  71. 	// 错误日志记录
  72. 	if err != nil {
  73. 		log.Fatal(message, err)
  74. 	}
  75. }

使用以下csv文件：

  1. name,age,developer
  2. "Hasan","46.4","true"

我得到的输出结果是：

  1. 表头: name       类型: string
  2. 表头: age        类型: float
  3. 表头: developer  类型: bool

输出结果是正确的。

我无法做到的是检查字段是否为字符串，因为我不知道字段的布局。

我知道可以根据https://go.dev/src/time/format.go中所述的格式将字符串解析为时间，并且可以构建一个自定义解析器，例如：

  1.     test, err := fmtdate.Parse("MM/DD/YYYY", "10/15/1983")
  2.     if err != nil {
  3.         panic(err)
  4.     }

但是，这只适用于我知道布局的情况下。

所以，我再次的问题是，如果我不知道布局，我应该如何解析时间，或者我应该做些什么才能解析时间？

英文:

I'm having a csv file, and want to read:

  1. Header names
  2. Fields types

So, I wrote the below:

  1. package main
  3. import (
  4. 	"encoding/csv"
  5. 	"fmt"
  6. 	"os"
  7.     "log"
  8. 	"reflect"
  9. 	"strconv"
  10. )
  12. func main() {
  13. 	filePath := "./file.csv"
  14. 	headerNames := make(map[int]string)
  15. 	headerTypes := make(map[int]string)
  16. 	// Load a csv file.
  17. 	f, _ := os.Open(filePath)
  18. 	// Create a new reader.
  19. 	r := csv.NewReader(f)
  20. 	// Read first row only
  21. 	header, err := r.Read()
  22. 	checkError("Some other error occurred", err)
  24. 	// Add mapping: Column/property name --> record index
  25. 	for i, v := range header {
  26. 		headerNames[i] = v
  27. 	}
  29. 	// Read second row
  30. 	record, err := r.Read()
  31. 	checkError("Some other error occurred", err)
  32. 	// Check record fields types
  33. 	for i, v := range record {
  34. 		var value interface{}
  35. 		if value, err = strconv.Atoi(v); err != nil {
  36. 			if value, err = strconv.ParseFloat(v, 64); err != nil {
  37. 				if value, err = strconv.ParseBool(v); err != nil {
  38. 					if value, err = strconv.ParseBool(v); err != nil { // <== How to do this with unknown layout
  39. 						// Value is a string
  40. 						headerTypes[i] = "string"
  41. 						value = v
  42. 						fmt.Println(reflect.TypeOf(value), reflect.ValueOf(value))
  43. 					} else {
  44. 						// Value is a timestamp
  45. 						headerTypes[i] = "time"
  46. 						fmt.Println(reflect.TypeOf(value), reflect.ValueOf(value))
  47. 					}
  48. 				} else {
  49. 					// Value is a bool
  50. 					headerTypes[i] = "bool"
  51. 					fmt.Println(reflect.TypeOf(value), reflect.ValueOf(value))
  52. 				}
  53. 			} else {
  54. 				// Value is a float
  55. 				headerTypes[i] = "float"
  56. 				fmt.Println(reflect.TypeOf(value), reflect.ValueOf(value))
  57. 			}
  58. 		} else {
  59. 			// Value is an int
  60. 			headerTypes[i] = "int"
  61. 			fmt.Println(reflect.TypeOf(value), reflect.ValueOf(value))
  62. 		}
  63. 	}
  65. 	for i, _ := range header {
  66. 		fmt.Printf("Header: %v \tis\t %v\n", headerNames[i], headerTypes[i])
  67. 	}
  68. }
  70. func checkError(message string, err error) {
  71. 	// Error Logging
  72. 	if err != nil {
  73. 		log.Fatal(message, err)
  74. 	}
  75. }

And with csv file as:

  1. name,age,developer
  2. "Hasan","46.4","true"

I got an output as:

  1. Header: name       is  string
  2. Header: age        is  float
  3. Header: developer  is  bool

The output is correct.

The thing that I could not do is the one is checking if the field is string as I do not know what layout the field could be.

I aware I can pasre string to time as per the format stated at https://go.dev/src/time/format.go, and can build a custom parser, something like:

  1.     test, err := fmtdate.Parse("MM/DD/YYYY", "10/15/1983")
  2.     if err != nil {
  3.         panic(err)
  4.     }

But this will work only (as per my knowledge) if I know the layout?

So, again my question is, how can I parse time, or what shall I do to be able to parse it, if I do not know the layout?

答案1

得分: 0

感谢Burak的评论，我通过使用这个包找到了解决方案：github.com/araddon/dateparse

  2. // 普通解析。与time.Parse()相同的时区规则
  3. t, err := dateparse.ParseAny("3/1/2014")
  5. // 严格解析，对于模糊的mm/dd和dd/mm日期会返回错误
  6. t, err := dateparse.ParseStrict("3/1/2014")
  7. > 返回错误
  9. // 返回表示解析给定日期时间的布局的字符串
  10. layout, err := dateparse.ParseFormat("May 8, 2009 5:57:51 PM")
  11. > "Jan 2, 2006 3:04:05 PM"
英文:

Thanks to the comment by Burak, I found the solution by using this package: github.com/araddon/dateparse

  2. // Normal parse.  Equivalent Timezone rules as time.Parse()
  3. t, err := dateparse.ParseAny("3/1/2014")
  5. // Parse Strict, error on ambigous mm/dd vs dd/mm dates
  6. t, err := dateparse.ParseStrict("3/1/2014")
  7. > returns error 
  9. // Return a string that represents the layout to parse the given date-time.
  10. layout, err := dateparse.ParseFormat("May 8, 2009 5:57:51 PM")
  11. > "Jan 2, 2006 3:04:05 PM"

huangapple
  • 本文由 发表于 2022年7月25日 21:18:32
  • 转载请务必保留本文链接：https://go.coder-hub.com/73109905.html
  • go
匿名

发表评论

匿名网友

:?: :razz: :sad: :evil: :!: :smile: :oops: :grin: :eek: :shock: :???: :cool: :lol: :mad: :twisted: :roll: :wink: :idea: :arrow: :neutral: :cry: :mrgreen:

确定