Created
October 13, 2010 19:11
-
-
Save dchud/624671 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import grp | |
import mimetypes | |
from optparse import OptionParser | |
import os | |
from pprint import pprint | |
import pwd | |
from stat import * | |
import sys | |
import time | |
import solr | |
SOLR_URL = 'http://127.0.0.1:8983/solr' | |
solr_conn = solr.SolrConnection(SOLR_URL) | |
def utc_time(secs): | |
return time.strftime('%Y-%m-%dT%H:%M:%SZ', time.gmtime(secs)) | |
needs_commit = False | |
def handle_file(path, filename, verbose): | |
global needs_commit | |
full_name = os.path.join(path, filename) | |
if verbose: | |
print 'HANDLE:', path | |
mode, ino, dev, nlink, uid, gid, \ | |
size, atime, mtime, ctime = os.lstat(full_name) | |
d = {} | |
d['fullname'] = path + '/' + filename | |
d['path'] = path | |
d['filename'] = filename | |
root, ext = os.path.splitext(filename) | |
d['base'] = root | |
d['extension'] = ext[1:] # skip the dot! | |
d['accessdt'] = utc_time(atime) | |
d['editdt'] = utc_time(mtime) | |
d['createdt'] = utc_time(ctime) | |
d['perms'] = mode # FIXME | |
d['size'] = size | |
d['owner'] = pwd.getpwuid(uid)[0] | |
d['group'] = grp.getgrgid(gid)[0] | |
d['mimetype'] = mimetypes.guess_type(full_name)[0] | |
if verbose: | |
pprint(d) | |
solr_conn.add(**d) | |
# commit every 10 secs or so | |
if needs_commit: | |
if int(time.time()) % 10 == 0: | |
print '\n\n\tCOMMIT\n' | |
solr_conn.commit() | |
needs_commit = False | |
else: | |
needs_commit = True | |
return d | |
def walk(path, verbose=False): | |
if verbose: | |
print path | |
for root, dirs, files in os.walk(path, topdown=True): | |
for filename in files: | |
if verbose: | |
print 'file:', filename | |
handle_file(os.path.join(path, root), filename, verbose) | |
for dirname in dirs: | |
if verbose: | |
print 'dir:', dirname | |
walk(os.path.join(path, root, dirname), verbose) | |
def main(): | |
usage = 'usage: %prog [options] PATH1 [PATH2 PATH3 ...]' | |
parser = OptionParser(usage=usage) | |
parser.add_option('-v', '--verbose', action='store_true', | |
dest='verbose', default=False, help='show verbose status') | |
options, args = parser.parse_args() | |
for path in args: | |
walk(path, options.verbose) | |
solr_conn.commit() | |
sys.exit() | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment