Fast enough way to move a directory tree in Python?

Question

Assuming this directory tree is a reasonable size: say an open source project such as Twisted or Python, what is the fastest way to traverse and iterate over the absolute path of all files / directories inside this directory?

I want to do this from Python. os.path.walk is slow. So I tried ls -lR and the -fi tree . For a project with approximately 8337 files (including tmp, pyc, test, .svn files):

$ time tree -fi > /dev/null 

real    0m0.170s
user    0m0.044s
sys     0m0.123s

$ time ls -lR > /dev/null 

real    0m0.292s
user    0m0.138s
sys     0m0.152s

$ time find . > /dev/null 

real    0m0.074s
user    0m0.017s
sys     0m0.056s
$

treeIt turns out faster than ls -lR(although ls -Rfaster than tree, but it does not give full paths). findis the fastest.

- / ? Windows 32- tree.exe ls.exe, .

1: find

2. ?... CD, Pushd ... , (, , , , ). , (, "CD GRAI LXML" "CD/Src pypm///LXML" ). , cd , , , . . http://github.com/srid/pf

Answer 1

pf , os.path.walk . , 3 , . Kernighan Pike, , :

/* spname:  return correctly spelled filename */
/*
 * spname(oldname, newname)  char *oldname, *newname;
 *  returns -1 if no reasonable match to oldname,
 *           0 if exact match,
 *           1 if corrected.
 *  stores corrected name in newname.
 */

#include <sys/types.h>
#include <sys/dir.h>

spname(oldname, newname)
    char *oldname, *newname;
{
    char *p, guess[DIRSIZ+1], best[DIRSIZ+1];
    char *new = newname, *old = oldname;

    for (;;) {
        while (*old == '/') /* skip slashes */
            *new++ = *old++;
        *new = '\0';
        if (*old == '\0')   /* exact or corrected */
            return strcmp(oldname,newname) != 0;
        p = guess;  /* copy next component into guess */
        for ( ; *old != '/' && *old != '\0'; old++)
            if (p < guess+DIRSIZ)
                *p++ = *old;
        *p = '\0';
        if (mindist(newname, guess, best) >= 3)
            return -1;  /* hopeless */
        for (p = best; *new = *p++; ) /* add to end */
            new++;                    /* of newname */
    }
}

mindist(dir, guess, best)   /* search dir for guess */
    char *dir, *guess, *best;
{
    /* set best, return distance 0..3 */
    int d, nd, fd;
    struct {
        ino_t ino;
        char  name[DIRSIZ+1];   /* 1 more than in dir.h */
    } nbuf;

    nbuf.name[DIRSIZ] = '\0';   /* +1 for terminal '\0' */
    if (dir[0] == '\0')     /* current directory */
        dir = ".";
    d = 3;  /* minimum distance */
    if ((fd=open(dir, 0)) == -1)
        return d;
    while (read(fd,(char *) &nbuf,sizeof(struct direct)) > 0)
        if (nbuf.ino) {
            nd = spdist(nbuf.name, guess);
            if (nd <= d && nd != 3) {
                strcpy(best, nbuf.name);
                d = nd;
                if (d == 0)     /* exact match */
                    break;
            }
        }
    close(fd);
    return d;
}

/* spdist:  return distance between two names */
/*
 *  very rough spelling metric:
 *  0 if the strings are identical
 *  1 if two chars are transposed
 *  2 if one char wrong, added or deleted
 *  3 otherwise
 */

#define EQ(s,t) (strcmp(s,t) == 0)

spdist(s, t)
    char *s, *t;
{
    while (*s++ == *t)
        if (*t++ == '\0')
            return 0;       /* exact match */
    if (*--s) {
        if (*t) {
            if (s[1] && t[1] && *s == t[1] 
              && *t == s[1] && EQ(s+2, t+2))
                return 1;   /* transposition */
            if (EQ(s+1, t+1))
                return 2;   /* 1 char mismatch */
        }
        if (EQ(s+1, t))
            return 2;       /* extra character */
    }
    if (*t && EQ(s, t+1))
        return 2;           /* missing character */
    return 3;
}

: , ANSI C, ISO C POSIX , . , .

Answer 2

, find, , ? , os.path.walk , , 16k-. , 0,68 1,9 Python.

, C, 75% , . 25% Python . ?

Answer 3

, , "os.walk". , , os.path.walk, .

, , , .

Answer 4

Although I doubt that you have several read heads, here is how you can go through several million files (we did 10M + in a few minutes).

https://github.com/hpc/purger/blob/master/src/treewalk/treewalk.c