Match by name

breachdata<-readLines("/Users/jjw6286/Downloads/CSR_databreach/Namesfirm.csv")

allsymble<-unique(data[,1:3])


library(stringdist)
matchfirmwithsymbles<-function(input, allsymble){
    section<-unlist(strsplit(input,","))
    ID<-section[1]
    time<-unlist(strsplit(as.matrix(section[2]),"/"))
    day<-time[2]
    month<-time[1]
    year<-paste("20",time[3], sep="")
    firmname<-as.matrix(paste(section[3:length(section)],collapse=" "))
    listdist<-stringdist(firmname,allsymble[,1],method="qgram")
    match<-allsymble[which(listdist==min(listdist))[1],]
    dist<-listdist[which(listdist==min(listdist))[1]]                      
    output<-data.frame(day)
    output<-cbind(output,month,year,firmname,match,dist,ID)
    
}
results<-lapply(breachdata[2:length(breachdata)],matchfirmwithsymbles, allsymble)
library(data.table)
results<-rbindlist(results)


#handclean
write.table(results,file="/Users/jjw6286/Downloads/CSR_databreach/publicdatabreach.csv", sep=",",row.names=FALSE)