Mass string replace in python?

Question

Say I have a string that looks like this:

str = \"The &yquick &cbrown &bfox &Yjumps over the &ulazy dog\"

You\'ll notic

Answer 1

Here is the C Extensions Approach for python

const char *dvals[]={
    //"0-64
    "","","","","","","","","","",
    "","","","","","","","","","",
    "","","","","","","","","","",
    "","","","","","","","","","",
    "","","","","","","","","","",
    "","","","","","","","","","",
    "","","","","",
    //A-Z
    "","","","","",
    "","","","","",
    "","","","","",
    "","","","","",
    "","","","","33",
    "",
    //
    "","","","","","",
    //a-z
    "","32","31","","",
    "","","","","",
    "","","","","",
    "","","","","",
    "34","","","","30",
    ""
};

int dsub(char*d,char*s){
    char *ofs=d;
    do{
        if(*s=='&' && s[1]<='z' && *dvals[s[1]]){

            //\033[0;
            *d++='\\',*d++='0',*d++='3',*d++='3',*d++='[',*d++='0',*d++=';';

            //consider as fixed 2 digits
            *d++=dvals[s[1]][0];
            *d++=dvals[s[1]][1];

            *d++='m';

            s++; //skip

        //non &,invalid, unused (&) ampersand sequences will go here.
        }else *d++=*s;

    }while(*s++);

    return d-ofs-1;
}

Python codes I have tested

from mylib import *
import time

start=time.time()

instr="The &yquick &cbrown &bfox &Yjumps over the &ulazy dog, skip &Unknown.\n"*100000
x=dsub(instr)

end=time.time()

print "time taken",end-start,",input str length",len(x)
print "first few lines"
print x[:1100]

Results

time taken 0.140000104904 ,input str length 11000000
first few lines
The \033[0;30mquick \033[0;31mbrown \033[0;32mfox \033[0;33mjumps over the \033[0;34mlazy dog, skip &Unknown.
The \033[0;30mquick \033[0;31mbrown \033[0;32mfox \033[0;33mjumps over the \033[0;34mlazy dog, skip &Unknown.
The \033[0;30mquick \033[0;31mbrown \033[0;32mfox \033[0;33mjumps over the \033[0;34mlazy dog, skip &Unknown.
The \033[0;30mquick \033[0;31mbrown \033[0;32mfox \033[0;33mjumps over the \033[0;34mlazy dog, skip &Unknown.
The \033[0;30mquick \033[0;31mbrown \033[0;32mfox \033[0;33mjumps over the \033[0;34mlazy dog, skip &Unknown.
The \033[0;30mquick \033[0;31mbrown \033[0;32mfox \033[0;33mjumps over the \033[0;34mlazy dog, skip &Unknown.
The \033[0;30mquick \033[0;31mbrown \033[0;32mfox \033[0;33mjumps over the \033[0;34mlazy dog, skip &Unknown.
The \033[0;30mquick \033[0;31mbrown \033[0;32mfox \033[0;33mjumps over the \033[0;34mlazy dog, skip &Unknown.
The \033[0;30mquick \033[0;31mbrown \033[0;32mfox \033[0;33mjumps over the \033[0;34mlazy dog, skip &Unknown.
The \033[0;30mquick \033[0;31mbrown \033[0;32mfox \033[0;33mjumps over the \033[0;34mlazy dog, skip &Unknown.

Its suppose to able to run at O(n), and Only took 160 ms (avg) for 11 MB string in My Mobile Celeron 1.6 GHz PC

It will also skip unknown characters as is, for example &Unknown will return as is

Let me know If you have any problem with compiling, bugs, etc...