library(stringr)
library(openxlsx)
#load Name list

NameInformation<-read.xlsx("data/名单_20160308.xlsx",sheet = 1,colNames = TRUE)
str(NameInformation)
NameList<-NameInformation$姓名
NameList<-str_trim(NameList)
#read E-mail name
EmailName<-dir("data/第一次考勤/信件打包")

查看缺勤人员名单

###########################
## check in email received time   ###
# get email content
 
EmailContent<-lapply(EmailName,function(x){
  readLines(con<-file(paste0("data/第一次考勤/信件打包/",x),encoding = 'UTF-8'))
})

# get date and time
EmailDate<-lapply(EmailContent,function(x){
  date_vec<-str_subset(x,"Date: Wed, 2 Mar 2016")
  date<-str_sub(date_vec,start = 7, end = 30)
  return(date)
})


# format conveting
## windows 下有问题，linux下没问题
EmailDate<-lapply(EmailDate,function(x){
  strptime(x,"%a, %d %b %Y %I:%M:%S")
})

EmailDate<-unlist(EmailDate)

提取名字

########################################33
## exteact name on the subject     ##

NameOnSubject<-lapply(EmailName,function(x){
  ExtractName<-str_extract(x,NameList)
  ## 有的同学没有选课也发了邮件，或者不小心下载了垃圾邮件
  if(sum(is.na(ExtractName))==51){
    return(NA)
  }
  else{
    Name<- ExtractName[!is.na(ExtractName)]
    return(Name)
  }
})

### combine Date and name
NameOnSubject<-unlist(NameOnSubject)

EmailData<-data.frame(CheckTime= EmailDate,NameOnSubject = NameOnSubject,stringsAsFactors = FALSE)

#先去掉名字为NA的邮件
EmailData<-EmailData[!is.na(EmailData$NameOnSubject),]

# 有的同学手抖，发了几封邮件,需要去重
EmailData<-EmailData[!duplicated(EmailData[,"NameOnSubject"]),]

View(EmailData)
str(EmailData)

合并数据集

CheckInNameList<-data.frame(Name = NameInformation$姓名,CheckInStatus = ExistStatus)
str(CheckInNameList)
# merge namelist and the EmailData
CheckInNameData<-merge(x = CheckInNameList, y = EmailData, by.x = "Name",
      by.y = "NameOnSubject",all = TRUE,all.x = TRUE )

library(DT)
datatable(CheckInNameData)