Shell Programming and Scripting

hai wafam cherol makha palli adubu madu ma yaakhidre haikhre tamlakle .
mahak aroiba yaahip tankhi hai machagi matamda saramba gatetu kaikhere mahakkisu aroiba yaahip tankhi hai  haikhre .

-0.9725326      arna thamlamba nongchup santhong gani -0.014587925
-0.9777407      tainaba amanba yamna uningdraba  -0.014587925
-0.9700631      aeroplane adu indira parktara ama     -0.014587925
-1.2438936      mahakki aroiba yaahip tankhi hai -0.014587925
-0.97742474     aroiba yaahip tankhi hai hairi    -0.014587925
-1.391722       hai wafam cherolna makha palli     -0.6328273
-2.922845       hai wafam cherolduna makha palli -0.1190167
-2.915667       hai wafam cherolsina makha palli  -0.5702463
-2.927181       hai wafam paochena makha palli  -0.1963889
-2.925497       hai wafam khangnaduna   -0.6328273
-2.855543       hai wafam ngasigi 
-2.926619       hai wafam thamkharabani
-1.635051       hai wafam thamlamle    -0.4567362
-1.078001       hai wafam thamlamli    -0.8960688
-1.023442       adubu madu makhada yaakhidre haikhre -0.1234433
-1.432234       adubu madu makha yaakhidre haikhre  -0.5432345
-1.1278934      changangei air fieldda hongdok pikhraga   -0.014587925
-0.9567379      nupa machagi matamda saramba gatetu     -0.014587925
-0.5984392      machagi matamda saramba gatetu kaire       -0.014587925
-1.250842       leiriba aduda santri khara thamkhre        -0.014587925

hai wafam paochena makha palli adubu madu makha yaakhidre haikhre tamlakle.
mahakki aroiba yaahip tankhi hai nupa machagi matamda saramba gatetu mahakki aroiba yaahip tankhi hai haikhre

awk  '

NR==FNR {if (5 == split ($2, T, " ")) PAT[$2]=$1
         next
        }

        {for (j=0; j<NF; j+=5)  {TMP = ""
                                 MIN = 1E100
                                 for (p in PAT) {CNT=0
                                                 split(p, X, " ")
                                                 for (i=1+j; i<=5+j; i++)
                                                    for (k=1; k<=5; k++) if ($i == X[k]) CNT++
                                                 if (CNT >= 4 && PAT[p] < MIN)  {MIN=PAT[p]
                                                                                 TMP=p
                                                                                }
                                                }
                                 if (TMP)        printf "%s ", TMP
                                 else            printf "%s %s %s %s %s ", $(j+1), $(j+2), $(j+3),P $(j+4), $(j+5)
                                }
         printf "\n"
        }
' FS="\t" OFS="\t" SEARCH.txt  FS=" " INPUT.txt
hai wafam paochena makha palli adubu madu makha yaakhidre haikhre tamlakle .    
mahakki aroiba yaahip tankhi hai nupa machagi matamda saramba gatetu mahakki aroiba yaahip tankhi hai haikhre .

awk ' NR==FNR  {sub (/| /, "\t");  if (5 == split ($2, T, " ")) PAT[$2]=$1
         next
}