jy-data-extract/src/main_test.go

package main

import (
	"fmt"
	"jy/admin/track"
	"jy/clear"
	"jy/extract"
	. "jy/mongodbutil"
	"log"
	"os"
	"regexp"
	"strconv"
	"strings"
	"testing"
	"time"
)

func Test_han(t *testing.T) {
	str := `[\u4e00-\u9fa5]` //"[\u4e00-\u9fa5]"
	//var rg = regexp.MustCompile(`[\u4e00-\u9fa5]`)会出错
	if strings.Contains(str, "\\u") {
		pattern, _ := strconv.Unquote(`"` + str + `"`)
		log.Println(pattern)
	}
	var rg = regexp.MustCompile(str)
	fmt.Println(rg.MatchString(str))
	os.Exit(0)
}
func Test_task(t *testing.T) {
	Mgo = MgoFactory(1, 3, 120, "192.168.3.207:27082", "extract_kf")
	//extract.StartExtractTaskId("5b8f804025e29a290415aee1")5c528686698414055c47b115
	extract.StartExtractTestTask("5b8f804025e29a290415aee1", "5a53966e40d2d9bbe8f7d30a", "1", "mxs_v2", "mxs_v2")
	//extract.StartExtractTestTask("5c3d75c96984142998eb00e1", "5c2a3d28a5cb26b9b76144dd", "100", "mxs_v3", "mxs_v3")
	time.Sleep(5 * time.Second)
}
func Test_extractcity(t *testing.T) {
	Mgo = MgoFactory(1, 3, 120, "192.168.3.207:27082", "extract_kf")
	extract.InitDFA2()
	//查询采购单位信息
	extract.FindBuyer()
}
func Test_reg(t *testing.T) {
	context := `sfsa.`
	reg := regexp.MustCompile(`(勘察|设计|设备|项目|标段|工程|监理|范围|分包|月|日|天|[,，\.。、：:“”‘’"])`)
	//reg := regexp.MustCompile(`[\\p{Han}]`)
	tmp := reg.MatchString(context)
	log.Println(tmp)
}

func Test_reg1(t *testing.T) {
	context := `sss<input  name="AgentCode" size="30" maxsize="50" value="91370800688271668P" class="textbox">
    dfdf<input type="hidden" name="AgentCode" size="30" maxsize="50" value="tttt" class="textbox"></input>`
	reg := regexp.MustCompile(`<\s*input.*value=['"](.[^'"]+).+>`)
	tmp := reg.ReplaceAllString(context, "$1")
	log.Println(tmp)
}

func Test_paths(t *testing.T) {
	Mgo = MgoFactory(1, 3, 120, "192.168.3.207:27082", "extract_v3")
	tracks := track.GetTrackPath("5b8dd276a5cb26b9b7faaa7c", "projectname", "rack_v3", "result_v3")
	for code, v := range tracks {
		if tmp, ok := v.([]map[string]interface{}); ok {
			for k, v := range tmp {
				if k == 0 {
					log.Println(v)
				} else {
					log.Println(code, v["code"], v["value"])
				}
			}
		}
		break
	}
}

func Test_clear(t *testing.T) {
	text := clear.OtherClean("winner", "宁夏泷泽医疗器械有限公司（地址：银川市兴庆区绿地214商城D区7号楼317房）")
	log.Println(text)
}

func Test_reg3(t *testing.T) {
	text := []rune("(法撒旦法士大夫发的发)生(的]发的法旦法士大夫三发的)")
	for i := 1; i <= 2; i++ {
		if len(text) > 0 {
			text = gl(i, text)
		}
	}
	log.Println("finish--", string(text))
}
func gl(i int, text []rune) []rune {
	pairedIndex := make(map[int]int)
	surplusMax := -1  //记录多余的反符号最大值
	positiveMax := -1 //记录多余的正符号最大值
	removeLength := 0
	nb := 0
	//na := 0
	length := len(text)
	allSymbol := "[（(\\[【{｛〔<《）)\\]】}｝〕>》]"
	allReg := regexp.MustCompile(allSymbol)
	symmetricMap := map[string]string{
		"]": "[",
		")": "(",
		"】": "【",
		"}": "{",
	}
	symbolIndex := map[string][]int{} //记录符号和当前索引位置
	//log.Println(string(text))
	for index, t := range text {
		now := allReg.FindString(string(t))
		if len(now) > 0 { //匹配到符号
			if index == 0 {
				if symmetricMap[now] != "" { //去除第一个反符号
					text = text[1:len(text)]
				} else if len(now) > 0 { //第一个是正符号，记录索引位置
					tmpArr := []int{index}
					symbolIndex[now] = tmpArr
				}
			} else {
				if symmetricMap[now] != "" { //反向符号，找出对称的正向符号
					fdSymbol := symmetricMap[now] //正向符号
					tmp := symbolIndex[fdSymbol]
					if len(tmp) == 0 { //多出来的反向符号,记录最大值
						//log.Println("多余反向符号----", now)
						if index > surplusMax {
							surplusMax = index
						}
					} else {
						nowIndex := tmp[len(tmp)-1]              //索引位置
						symbolIndex[fdSymbol] = tmp[:len(tmp)-1] //匹配索引位置后，删除之前的记录
						if len(symbolIndex[fdSymbol]) == 0 {
							delete(symbolIndex, fdSymbol)
						}
						//将成对的符号的index记录，
						if index == length-1 {
							pairedIndex[index] = nowIndex
						}
						pairedIndex[nowIndex] = index
					}
				} else { //正向符号,加入symbolIndex记录索引
					tmpArr := []int{}
					if len(symbolIndex[now]) > 0 { //有该符号的索引位置
						tmpArr = symbolIndex[now]
						tmpArr = append(tmpArr, index)
					} else { //没有该符号的索引位置
						tmpArr = []int{index}
					}
					symbolIndex[now] = tmpArr
				}
			}
		}
	}

	if len(symbolIndex) != 0 { //多余的正符号索引位置
		for _, arr := range symbolIndex {
			for j, l := range arr {
				if j == 0 && l == 0 {
					text = text[1:] //删除text开头的正向符号
					removeLength = 1
					nb = nb + 1
				}
				if positiveMax < l { //记录最大正向索引
					positiveMax = l
				}
			}
		}
	}
	firstOpposite := pairedIndex[0]
	if firstOpposite != 0 { //第一个正符号对应反符号的位置
		text = text[firstOpposite+1:]
		removeLength = firstOpposite + 1
		nb = nb + removeLength
	}
	lastOpposite := pairedIndex[length-1] //最后一个符号
	if lastOpposite > 0 {                 //有对称的正向符号,删除其中间内容
		//na = length - lastOpposite
		text = text[:lastOpposite-removeLength]
	} else if surplusMax == length-1 { //没有对称，只删除最后一个反符号
		text = text[:length-1-removeLength]
		//na = na + 1
	}
	//有多余反向符号，删除之前部分 surplusMax所有多余反向符号的最大索引
	if surplusMax != -1 && surplusMax > firstOpposite && surplusMax < length-1 {
		if (lastOpposite > 0 && surplusMax < lastOpposite) || (lastOpposite == 0) { //发发发发发发}发(发发发发发发)
			text = text[surplusMax-nb+1:]
			nb = surplusMax + 1
		}
	}
	//多余正符号删除之后部分（优先删除反符号之前部分）//（发发{发发）发发发发发发发发发发发发发发发（发{发）
	if positiveMax != -1 && positiveMax != 0 && positiveMax > surplusMax && positiveMax > firstOpposite { ////发发发发发发]发发{
		if (lastOpposite > 0 && positiveMax < lastOpposite) || (lastOpposite == 0) { //发发发发发发发发{发发发发发（发发）
			text = text[:positiveMax-nb]
		}
	}
	log.Println(string(text))
	return text
}