Replacing a number(ID) in the file with another number(ID)

**bvdet** · Jan 1 '08, 04:13 PM

The following is a separate application for replacing the ID numbers in a data file.
[code=Python]def replaceID2(file List, idDict, *args):
pattkey = re.compile('|'. join([r'\b(%s)' % item for item in args]))
for i, line in enumerate(fileL ist):
m = pattkey.match(l ine)
if m:
try:
mnum = pattnum.search( line)
id = int(mnum.group( 0))
if id in idDict:
s = str(idDict[id])
fileList[i] = '%s%s%s' % (line[:mnum.start()], s, \
line[mnum.start()+le n(s):])
except:
print 'No valid ID number found.'
return fileList

if __name__ == '__main__':
fn = 'sample_data'
pointID = {1:86010101,2:8 6010102,3:86010 103,4:86010104, \
5:86010106,6:96 010104,7:860101 10,8:86010201,\
9:86010115,3280 504:96010403}
curveID = {1:10001101,2:1 0001102,3:10001 103,4:10001104, \
6:10001106}
fileList = open(fn).readli nes()
replaceID2(file List, curveID, *['Line', 'Rect', 'Tria'])
replaceID2(file List, pointID, *['Point',])
f = open('sample_da ta1', 'w')
f.write(''.join (fileList))
f.close()[/code]

**psbasha** · Jan 6 '08, 06:04 AM

Originally posted by bvdet

The following is a separate application for replacing the ID numbers in a data file.
[code=Python]def replaceID2(file List, idDict, *args):
pattkey = re.compile('|'. join([r'\b(%s)' % item for item in args]))
for i, line in enumerate(fileL ist):
m = pattkey.match(l ine)
if m:
try:
mnum = pattnum.search( line)
id = int(mnum.group( 0))
if id in idDict:
s = str(idDict[id])
fileList[i] = '%s%s%s' % (line[:mnum.start()], s, \
line[mnum.start()+le n(s):])
except:
print 'No valid ID number found.'
return fileList

if __name__ == '__main__':
fn = 'sample_data'
pointID = {1:86010101,2:8 6010102,3:86010 103,4:86010104, \
5:86010106,6:96 010104,7:860101 10,8:86010201,\
9:86010115,3280 504:96010403}
curveID = {1:10001101,2:1 0001102,3:10001 103,4:10001104, \
6:10001106}
fileList = open(fn).readli nes()
replaceID2(file List, curveID, *['Line', 'Rect', 'Tria'])
replaceID2(file List, pointID, *['Point',])
f = open('sample_da ta1', 'w')
f.write(''.join (fileList))
f.close()[/code]

The numbers whose IDs are not to be replaced are not written in correct format to the output file

Code:

Data

#Input data
Rect    10000000	10000000200000007000000060000000
Rect    20000000	20000000300000008000000070000000
Rect    30000000	30000000400000009000000080000000
Tria    40000000	400000005000000090000000

Point   10000000	0.      0.      0.
Point   20000000	5.      0.      0.
Point   30000000	10.     0.      0.
Point   40000000	15.     0.      0.
Point   50000000	20.     0.      0.
Point   60000000	0.      5.      0.
Point   70000000	5.      5.      0.
Point   80000000	10.     5.      0.
Point   90000000	15.     5.      0.

#Outpu file data ( Incorrect output data)

Rect    10000000	10000000200000007000000060000000
Rect    20000000	20000000300000008000000070000000
Rect    30000000	30000000400000009000000080000000
Tria    40000000	400000005000000090000000

Point   10000000	0.      0.      0.
Point   20000000	5.      0.      0.
Point   30000000	10.     0.      0.
Point   40000000	15.     0.      0.
Point   50000000	20.     0.      0.
Point   60000000	0.      5.      0.
Point   70000000	5.      5.      0.
Point   80000000	10.     5.      0.
Point   90000000	15.     5.      0.

**psbasha** · Jan 6 '08, 06:11 AM

Originally posted by psbasha

The numbers whose IDs are not to be replaced are not written in correct format to the output file

Code:

Data

#Input data
Rect    10000000	10000000200000007000000060000000
Rect    20000000	20000000300000008000000070000000
Rect    30000000	30000000400000009000000080000000
Tria    40000000	400000005000000090000000

Point   10000000	0.      0.      0.
Point   20000000	5.      0.      0.
Point   30000000	10.     0.      0.
Point   40000000	15.     0.      0.
Point   50000000	20.     0.      0.
Point   60000000	0.      5.      0.
Point   70000000	5.      5.      0.
Point   80000000	10.     5.      0.
Point   90000000	15.     5.      0.

#Outpu file data ( Incorrect output data)

Rect    10000000	10000000200000007000000060000000
Rect    20000000	20000000300000008000000070000000
Rect    30000000	30000000400000009000000080000000
Tria    40000000	400000005000000090000000

Point   10000000	0.      0.      0.
Point   20000000	5.      0.      0.
Point   30000000	10.     0.      0.
Point   40000000	15.     0.      0.
Point   50000000	20.     0.      0.
Point   60000000	0.      5.      0.
Point   70000000	5.      5.      0.
Point   80000000	10.     5.      0.
Point   90000000	15.     5.      0.

Ignore the above posting it was incorrect data in th einput file.

**psbasha** · Jan 6 '08, 06:22 AM

Originally posted by bvdet

The following is a separate application for replacing the ID numbers in a data file.
[code=Python]def replaceID2(file List, idDict, *args):
pattkey = re.compile('|'. join([r'\b(%s)' % item for item in args]))
for i, line in enumerate(fileL ist):
m = pattkey.match(l ine)
if m:
try:
mnum = pattnum.search( line)
id = int(mnum.group( 0))
if id in idDict:
s = str(idDict[id])
fileList[i] = '%s%s%s' % (line[:mnum.start()], s, \
line[mnum.start()+le n(s):])
except:
print 'No valid ID number found.'
return fileList

if __name__ == '__main__':
fn = 'sample_data'
pointID = {1:86010101,2:8 6010102,3:86010 103,4:86010104, \
5:86010106,6:96 010104,7:860101 10,8:86010201,\
9:86010115,3280 504:96010403}
curveID = {1:10001101,2:1 0001102,3:10001 103,4:10001104, \
6:10001106}
fileList = open(fn).readli nes()
replaceID2(file List, curveID, *['Line', 'Rect', 'Tria'])
replaceID2(file List, pointID, *['Point',])
f = open('sample_da ta1', 'w')
f.write(''.join (fileList)
f.close()[/code]

I dont want the Curves or Points data to be written to the output file, if we dont want to replace the ID's

The ouput should looks like below.Comments can be removed

Code:

Output
START
COLOR RED
LINETYPE SOLID
END
PLine   1        6      1.5     9.375   .001    .001
Line    90010102 1      8601010186010102    
Rect    90010103 1      860101018601010286010103860101004
PRect*  4               11              15              16
*       10              11              0.3
Rect*   90010104        1               86010104        86010103
*       86010102        86010101               0.
Othr*   1               1               5               6
*       10              11              0.              0.
*       10              11              0.              1.0
Oth1*   1               1               5               6
*       10              11              0.              0.
*       10              11              0.              1.0
*       10              11              0.              1.0
*       10              11              0.              1.0
 
Point   86010101               0.0     0.0     0.0
Point   86010102               1.0     0.0     0.0
Point*  86010103                       0.0             2.0
*       0.0
Point  *86010104       0               1.28286145E+03  1.28286145E+03
*       -2.01004501E+02

**ghostdog74** · Jan 6 '08, 06:45 AM

@OP, you should pay bv for doing your work.

**bvdet** · Jan 6 '08, 03:15 PM

Originally posted by psbasha

I dont want the Curves or Points data to be written to the output file, if we dont want to replace the ID's

The ouput should looks like below.Comments can be removed

Code:

Output
START
COLOR RED
LINETYPE SOLID
END
PLine   1        6      1.5     9.375   .001    .001
Line    90010102 1      8601010186010102    
Rect    90010103 1      860101018601010286010103860101004
PRect*  4               11              15              16
*       10              11              0.3
Rect*   90010104        1               86010104        86010103
*       86010102        86010101               0.
Othr*   1               1               5               6
*       10              11              0.              0.
*       10              11              0.              1.0
Oth1*   1               1               5               6
*       10              11              0.              0.
*       10              11              0.              1.0
*       10              11              0.              1.0
*       10              11              0.              1.0
 
Point   86010101               0.0     0.0     0.0
Point   86010102               1.0     0.0     0.0
Point*  86010103                       0.0             2.0
*       0.0
Point  *86010104       0               1.28286145E+03  1.28286145E+03
*       -2.01004501E+02

You need to make an effort to help yourself, instead of asking me to program for you. I suggest that you create a filter function that removes the unwanted lines from fileList before writing to disc. Please post back your solution. I have my own projects to work on.

**psbasha** · Jan 7 '08, 12:27 AM

Originally posted by bvdet

You need to make an effort to help yourself, instead of asking me to program for you. I suggest that you create a filter function that removes the unwanted lines from fileList before writing to disc. Please post back your solution. I have my own projects to work on.

Here is the solution:

Code:

Filter
def filter_numberIDs(fileList, idDict, *args):
    astreikFlag = False
    notNumFlag = False
        
    pattkey = re.compile('|'.join([r'\b(%s)' % item for item in args]))    
    iLen = len(fileList)
    fileList1 = []
    for i in range(0,iLen):    
        line = fileList[i]
        if line.startswith('$'):
            pass            
        else:
            m = pattkey.match(line)
            if m:
                try:
                    mnum = pattnum.search(line)
                    id = int(mnum.group(0))
                    if id not in idDict.values():                         
                        #astreikFlag = False
                        if '*' in line:
                            astreikFlag = False                            
                        else:
                            pass
                        notNumFlag = True
                    else:
                        if not astreikFlag:
                            fileList1.append(line)                            
                            if '*' in line:
                                astreikFlag = True                                
                            else:
                                astreikFlag = False
                        notNumFlag = False
                except:
                    pass
            else:
                if astreikFlag:
                    fileList1.append(line)
                    astreikFlag = False                
                    
                else:
                    if not astreikFlag and not notNumFlag:
                        fileList1.append(line)
                    notNumFlag = False
    return fileList1
    
if __name__ == '__main__':
    fn = 'sample4.txt'
    pointID = {1:86010101,2:86010102,3:86010103,4:86010104,\
               5:86010106,6:96010104,7:86010110,8:86010201,\
               9:86010115,3280504:96010403}
    curveID = {1:10001101,2:10001102,3:10001103,4:10001104,\
               6:10001106}
    fileList = open(fn).readlines()
    replaceID2(fileList, curveID, *['Line', 'Rect', 'Tria'])
    replaceID2(fileList, pointID, *['Point',])
    newFileList = []

    newFileList = filter_numberIDs(fileList, curveID, *['Line', 'Rect', 'Tria'])
    newFileList = filter_numberIDs(newFileList, pointID, *['Point'])
    
        
    f = open('sample_data1.txt', 'w')
    f.write(''.join(newFileList))
    f.close()

Let me know whether this code can be made more modular.

Thanks
PSB

**psbasha** · Jan 7 '08, 06:23 AM

BV,

Please let me know your suggestion on this code

Thanks
PSB