Shell Programming and Scripting

cat <data_file.txt> | uniq > <output_file>.txt

bash-3.2$ uniq -c sarattdnewdruggene.txt >sarattdnewdruggene3.txt
bash-3.2$ cat <sarattdnewdruggene.txt> | uniq > <sarattdnewdruggene4>.txt
bash: syntax error near unexpected token `|'
bash-3.2$ cat <sarattdnewdruggene.txt> | uniq > <sarattdnewdruggene4.txt>
bash: syntax error near unexpected token `|'
bash-3.2$ cat <sarattdnewdruggene.txt> | uniq | <sarattdnewdruggene4.txt>
bash: syntax error near unexpected token `|'
bash-3.2$ cat <sarattdnewdruggene.txt> | uniq  <sarattdnewdruggene4.txt>
bash: syntax error near unexpected token `|'
bash-3.2$ cat <sarattdnewdruggene.txt>  uniq  <sarattdnewdruggene4.txt>
bash: syntax error near unexpected token `newline'
bash-3.2$

cat sarattdnewdruggene.txt | uniq > sarattdnewdruggene4.txt

CHRM1 P11229 Pirenzepine DAP000492 Peptic ulcer disease Approved T2D
CHRM1 P11229 Glycopyrrolate DAP001116 Anesthetic Approved T2D
CHRM1 P11229 Clidinium DAP001117 Abdominal/stomach pain Approved T2D
CHRM1 P11229 Dicyclomine DAP001118 Irritable bowel syndrome Approved T2D
CHRM1 P11229 Ethopropazine DAP001119 Parkinson's disease Approved T2D
CHRM1 P11229 Cycrimine DAP001120 Parkinson's disease Approved T2D
CHRM1 P11229 Benztropine DAP001121 Parkinson's disease Approved T2D
CHRM1 P11229 Trihexyphenidyl DAP001122 Parkinson's disease Approved T2D
CHRM1 P11229 Propantheline DAP001123 Excessive sweating (hyperhidrosis) Approved T2D
CHRM1 P11229 Oxyphenonium DAP001124 Spasm Approved T2D
CHRM1 P11229 Biperiden DAP001125 Parkinson's disease Approved T2D
CHRM1 P11229 Talsaclidine isomer DCL000268 Alzheimer's disease Discontinued T2D
CHRM1 P11229 Sabcomeline hydrochloride DCL000279 Cardiovascular diseases Phase IIa T2D
CHRM1 P11229 Talsaclidine fumarate DCL000303 Alzheimer's disease Discontinued T2D
CHRM1 P11229 Xanomeline tartrate DCL000328 Alzheimer's disease Phase II T2D
CHRM1 P11229 GSK573719 DCL000381 Chronic Obstructive Pulmonary Disease (COPD) Phase II T2D
CHRM1 P11229 GSK961081 DCL000397 Chronic Obstructive Pulmonary Disease (COPD) Phase II completed T2D
CHRM1 P11229 GSK1034702 DCL000402 Schizophrenia, Dementia Phase I completed T2D
CHRM1 P11229 Darotropium DCL000514 COPD Suspended in Phase II in GSK 2009 Report T2D
CHRM1 P11229 Darotropium + 642444 DCL000515 COPD Phase III T2D
CHRM1 P11229 Revatropate DCL000957 Chronic obstructive pulmonary disease Discontinued in Phase I T2D
FLT1 P17948 Sorafenib DAP000006 Advanced renal cell carcinoma Launched CAD
FLT1 P17948 Sorafenib DAP000006 Hepatocellular carcinoma, NSCLC, melanoma Phase III CAD
FLT1 P17948 Sorafenib DAP000006 Myelodyspalstic syndrome, AML, head & neck cancer, breast, colon, ovarian, pancreatic cancer Phase II CAD
FLT1 P17948 Ranibizumab DAP001260 Age-related macular degeneration Approved CAD
FLT1 P17948 Ranibizumab DAP001260 Diabetic macular edema and retinal vein occlusion Phase III CAD

CHRM1 P11229 Pirenzepine DAP000492 Peptic ulcer disease Approved T2D
Glycopyrrolate DAP001116 Anesthetic Approved T2D
Clidinium DAP001117 Abdominal/stomach pain Approved T2D
Dicyclomine DAP001118 Irritable bowel syndrome Approved T2D
Ethopropazine DAP001119 Parkinson's disease Approved T2D
Cycrimine DAP001120 Parkinson's disease Approved T2D
Benztropine DAP001121 Parkinson's disease Approved T2D
Trihexyphenidyl DAP001122 Parkinson's disease Approved T2D
Propantheline DAP001123 Excessive sweating (hyperhidrosis) Approved T2D
Oxyphenonium DAP001124 Spasm Approved T2D
Biperiden DAP001125 Parkinson's disease Approved T2D
Talsaclidine isomer DCL000268 Alzheimer's disease Discontinued T2D
Sabcomeline hydrochloride DCL000279 Cardiovascular diseases Phase IIa T2D
Talsaclidine fumarate DCL000303 Alzheimer's disease Discontinued T2D
Xanomeline tartrate DCL000328 Alzheimer's disease Phase II T2D
GSK573719 DCL000381 Chronic Obstructive Pulmonary Disease (COPD) Phase II T2D
GSK961081 DCL000397 Chronic Obstructive Pulmonary Disease (COPD) Phase II completed T2D
GSK1034702 DCL000402 Schizophrenia, Dementia Phase I completed T2D
Darotropium DCL000514 COPD Suspended in Phase II in GSK 2009 Report T2D
+ 642444 DCL000515 COPD Phase III T2D
Revatropate DCL000957 Chronic obstructive pulmonary disease Discontinued in Phase I T2D
FLT1 P17948 Sorafenib DAP000006 Advanced renal cell carcinoma Launched CAD
Hepatocellular carcinoma, NSCLC, melanoma Phase III CAD
Myelodyspalstic syndrome, AML, head & neck cancer, breast, colon, ovarian, pancreatic cancer Phase II CAD
Ranibizumab DAP001260 Age-related macular degeneration Approved CAD
Diabetic macular edema and retinal vein occlusion Phase III CAD

#!/usr/bin/python

import sys

if len(sys.argv) < 2:
        print "usage:",sys.argv[0],"<file_path>"
        sys.exit(69)

f = open(sys.argv[1], 'r')
lines = f.readlines()

count = 0
index = 0

for item in lines:
        if count != 0:
                left  = lines[count].split()    
                right = lines[count-1].split()

                while left[index] == right[index]:
                        index += 1

                print ' '.join(left[index:])
                index = 0
        else:
                print lines[count].rstrip() 

        count += 1