Question

I have two files

File1:

IdName1 Info1 Info2 Info3   #Info: from program1 for name1  #Info: from program2 for name1
IdName2 Info1 Info2 Info3   #Info: from program1 for name2  #Info: from program2 for name2
IdName4 Info1 Info2 Info3   #Info: from program1 for name4  
IdName3 Info1 Info2 Info3   #Info: from program1 for name3  #Info: from program2 for name3

File2:

# ProgramInfo
# Query: IdName1 Info1 Info2 Info3
# DatabaseInfo
# FiledInfo
line1
line2
# ProgramInfo
# Query: IdName2 Info1 Info2 Info3
# DatabaseInfo
# FiledInfo
# ProgramInfo
# Query: IdName4 Info1 Info2 Info3
# DatabaseInfo
# FiledInfo
line1
line2
line3
line4

Now I need to check if “IdName1 Info1 Info2 Info3” is in File2 after “#Query: ” and if it is I need to split up the iformation from that line in File1 and
insert it in File2 before the corresponding “# ProgramInfo” line. The out put file should look like this:

OutputFile:

# IdName1 Info1 Info2 Info3
# Info: from program1 for name1 
# Info: from program2 for name1
# ProgramInfo
# Query: IdName1 Info1 Info2 Info3
# DatabaseInfo
# FiledInfo
line1
line2
# IdName2 Info1 Info2 Info3 
# Info: from program1 for name2 
# Info: from program2 for name2
# ProgramInfo
# Query: IdName2 Info1 Info2 Info3
# DatabaseInfo
# FiledInfo
# IdName4 Info1 Info2 Info3 
# Info: from program1 for name4 
# ProgramInfo
# Query: IdName4 Info1 Info2 Info3
# DatabaseInfo
# FiledInfo
line1
line2
line3
line4

My question is now, how do I add the corresponding three lines into File2, I have been trying something like this:

import sys
def programs_info_comb(fileName1, fileName2):
    my_file1 = open(fileName1, "r")
    my_line1=my_file1.readlines()
    my_file2 = open(fileName2, "r")
    my_line2=my_file2.readlines() 
    for line1 in my_line1: 
        (name1, info1, info2)= line1.strip().split("\t")
        for line2 in my_line2:
            if line2.startswith("# Q"):
                name2 = line2[9:-1]
                if name1 == name2:
                    #### here Im lost how to tell where I want those next two lines to be printed
                    print "#"+" "+name1
                    print info1
                    print info2
    my_file1.close
    my_file2.close
if __name__== "__main__":
    programs_info_comb(sys.argv[1], sys.argv[2])

There is probably a better easier way to this, all help will be gratefully accepted
Thank you for your time
Daeja

Answer 1

import sys
def programs_info_comb(fileName1, fileName2):
    my_file1 = open(fileName1, "r")
    my_line1=my_file1.readlines()
    my_file1.close()

    my_file2 = open(fileName2, "r")
    my_line2=my_file2.readlines() 
    my_file2.close()

    # load file1 into a dict for lookup later
    infoFor = dict()
    for line1 in my_line1: 
        parts = line1.strip().split("\t")
        infoFor[parts[0]] = parts[1:] 

    # iterate over line numbers to be able to refer previous line numbers
    for line2 in range(len(my_line2)):
        if my_line2[line2].startswith("# Q"):
            name2 = my_line2[line2][9:-1]
            # lookup
            if infoFor.has_key(name2):
                print '# ' + name2
        for info in infoFor[name2]:
                    print info
            # print programinfo and query lines
                print my_line2[line2-1],
                print my_line2[line2],
    # skip program info always
        elif my_line2[line2].startswith("# ProgramInfo"):
            pass
    # otherwise just print as is
        else:
            print my_line2[line2],

if __name__== "__main__":
    programs_info_comb(sys.argv[1], sys.argv[2])

I have loaded file1 into a dictionary for lookup later and sent the output to stdout. Before sending the output I’ve checked the type of line I’m on and output accordingly.

Here’s the o/p :-

C:\>python st.py f1.txt f2.txt
# IdName1 Info1 Info2 Info3
#Info: from program1 for name1
#Info: from program2 for name1
# ProgramInfo
# Query: IdName1 Info1 Info2 Info3
# DatabaseInfo
# FiledInfo
line1
line2
# IdName2 Info1 Info2 Info3
#Info: from program1 for name2
#Info: from program2 for name2
# ProgramInfo
# Query: IdName2 Info1 Info2 Info3
# DatabaseInfo
# FiledInfo
# IdName4 Info1 Info2 Info3
#Info: from program1 for name4
# ProgramInfo
# Query: IdName4 Info1 Info2 Info3
# DatabaseInfo
# FiledInfo
line1
line2
line3
line4