Convert a LaTeX master file into a flatten LaTeX with all the files included

master2single.py

#!/usr/bin/env python
# Author: Timo Korthals <[email protected]>
# Template by https://gist.github.com/restrepo/4207109
# Function:
#  Convert a master latex file
#  into a single document by including hierarchically
#  automatically all the LaTeX documents 
#  which are arguments of 
#  \include, \input, or \import
#  ignoring any \includeonly

import sys
import re
import tempfile
import filecmp
from shutil import copyfile

def exitMsg():
    sys.exit('USAGE: %s masterfile.tex flattenfile.tex [-v] [-c]\n'
             '        masterfile.tex      : Input file\n'
             '        flattenfile.tex     : Flattened file\n'
             '        -v                  : Verbose mode\n'
             '        -c                  : Remove all comments' %sys.argv[0])
    return

def flatten(masterfile, flattenfile, verbose):
    filetex=open(masterfile,'r')
    texlist=filetex.readlines()
    finaltex=open(flattenfile,'w')
    for i in texlist:
        if re.match('(\s)*\\\\input{',i)!=None or re.match('(\s)*\\\\include{',i)!=None or re.match('(\s)*\\\\import{',i)!=None: 
            if verbose==True:
                print('Command: '+i[:-1])
            # Remove trailing comments which might taint the following processing
            command=i.split('%')[0]
            filename=command.split('{')[-1].split('}')[0]
            # Check for expansion
            if filename[-3:]!='tex': 
                filename=filename+'tex'
            # Check for root if command is '\import'
            dirname='./'
            if i.find(r'\import{')==0: 
                dirname=dirname+i.split('{')[-2].split('}')[0]+'/'
            filename=dirname+filename
            if verbose==True:
                print('Import: '+filename)
            includetex=open(filename,'r')
            finaltex.write(includetex.read())
            finaltex.write('\n')
        elif i.find(r'\includeonly{')==0:
            finaltex.write(i.replace(r'\includeonly{',r'%\includeonly{'))
        else:
            finaltex.write(i)
    filetex.close()
    finaltex.close()
    return

# Check for files
if len(sys.argv)>=3:
    masterfile=sys.argv[1]
    flattenfile=sys.argv[2]
else:
    exitMsg()

# Check for switches
verbose=False
comment=False
if len(sys.argv)>3:
    for x in sys.argv[3:]:
        if x=='-v':
            verbose=True
        elif x=='-c': 
            comment=True
        else:
            exitMsg()

# Start flattening
print('Start flattening')
fileIn=masterfile
fileOut=tempfile.NamedTemporaryFile().name
while True:
    if verbose==True:
        print('Process '+fileIn+' > '+fileOut)
    flatten(fileIn, fileOut, verbose)
    if filecmp.cmp(fileIn, fileOut)==True:
        break
    fileIn=fileOut
    fileOut=tempfile.NamedTemporaryFile().name


# Remove all comments and produce final output file
if comment==True:
    print('Remove comments')
    filetex=open(fileOut,'r')
    texlist=filetex.readlines()
    finaltex=open(flattenfile,'w')
    for i in texlist:
        if re.match('(\s)*%',i)!=None:       # match all lines which are just comments
            continue
        elif re.search('[^\\\\-]%',i)!=None: # match all comments after commands, but not '\%'
            finaltex.write(i[0:re.search('[^\\\\-]%',i).start(0)+1]+'\n')
        else:
            finaltex.write(i)
    filetex.close()
    finaltex.close()
else:
    copyfile(fileOut, flattenfile)

print(flattenfile+' produced')

Hint: Line 39 should be filename=filename+'.tex' (the dot is missing)