sample_text <-
c("811310 Commercial and Industrial Machinery and"
, "7692 Welding Repair"
, "Equipment (except Automotive and" # non-digit pattern (1/2)
, "Electronic) Repair and Maintenance" # non-digit pattern (2/2)
, "811310 Commercial and Industrial Machinery and"
, "7694 Armature Rewinding Shops"
, "Equipment (except Automotive and" # non-digit pattern (1/2)
, "Electronic) Repair and Maintenance" # non-digit pattern (2/2)
, "811310 Commercial and Industrial Machinery and"
, "7699 Repair Services, Nec"
, "Equipment (except Automotive and" # non-digit pattern (1/2)
, "Electronic) Repair and Maintenance" # non-digit pattern (2/2)
, "811411 Home and Garden Equipment Repair and"
, "7699 Repair Services, Nec"
, "Maintenance" # non-digit pattern (1/1)
, "811412 Appliance Repair and Maintenance"
, "7623 Refrigeration Service and Repair"
, "811412 Appliance Repair and Maintenance"
, "7629 Electrical Repair Shops"
, "811412 Appliance Repair and Maintenance"
, "7699 Repair Services, Nec")
x <- c()
for(i in sample_text){
if(grepl("^\\D*$",i)) {
x[length(x)-1] <- paste(x[length(x)-1], i)
} else {
x <- c(x, i) #append
}
}
x
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