isoboroff

#!/usr/bin/env python2.7

import os
import random
import sys
import argparse

parser = argparse.ArgumentParser(description = 'Print random lines from a file')
parser.add_argument('-n', dest='sample_size', type=int, help='number of lines to sample', default=100)
parser.add_argument('files', nargs=argparse.REMAINDER, help='files to read from')

isoboroff

I had a large index job crash at about doc 75M.  This is with CDH4.6.  I could not list the /solr/overseer/queue directory in ZK because it had millions of entries.

Here are the steps I followed to avoid a re-index:
1. Shut down all solr-servers and zookeeper-servers
2. Run zookeeper-server-initialize --force --myid X on each ZK server.  This should result in an empty ZK space.
3. solrctl --init
4. hadoop mv /solr/the-collection /hold
5. Restart solr-server instances
6. solrctl instancedir --create ... # re-upload the config info
7. solrctl collection --create # with the same number of nodes, repls, as before

isoboroff

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

/**
 * Usage: rm_all <dir-name>
 * From lkml...
 */

#define u32 unsigned int

isoboroff

// getTrueName.c
// 
// DESCRIPTION
//   Resolve HFS and HFS+ aliased files (and soft links), and return the
//   name of the "Original" or actual file. Directories have a "/"
//   appended. The error number returned is 255 on error, 0 if the file
//   was an alias, or 1 if the argument given was not an alias
// 
// BUILD INSTRUCTIONS
//   gcc-3.3 -o getTrueName -framework Carbon getTrueName.c 

isoboroff

#!/usr/bin/env python3

import json
import argparse
import re

# source files from https://github.com/bpb27/trump_tweet_data_archive
# Removes URLs since M-x cookie-doctor gets confused by them

argparser = argparse.ArgumentParser(description='Convert from JSON array of condensed tweets to cookie format')

isoboroff

#!/usr/bin/env python3
if __name__ == "__main__":
    import json
    import argparse
    import spacy
    import dateparser
    import signal
    from contextlib import contextmanager
    from tqdm import tqdm
    

isoboroff

from django.conf import settings
from django.core.files.storage import FileSystemStorage
from django.core.files.base import File
from django.utils.deconstruct import deconstructible

from git import Repo
import io

@deconstructible
class VersionedStorage(FileSystemStorage):

isoboroff

from django.core.management.base import BaseCommand, CommandError
from django.utils.crypto import get_random_string

class Command(BaseCommand):
    help='''Generate a secret key the same way Django does.  
    You will need to install it either in settings.py for dev or externally for production
    '''

    def add_arguments(self, parser):
        parser.add_argument('-l', '--length', type=int, default=50)

isoboroff

#!/usr/bin/env python3

from elasticsearch import Elasticsearch, TransportError
import argparse
import re
import sys

ap = argparse.ArgumentParser(description='Do a baseline run against an Elasticsearch index')
ap.add_argument('--host', default='localhost', help='Elasticsearch host')
ap.add_argument('--port', default=9200, help='Elasticsearch port')

isoboroff

    <script src="moment.min.js"></script>
    <script src="moment-timezone-with-data-10-year-range.js"></script>
    <script>
      const my_zone = moment.tz.guess(true);

      // Set up timezone selector with all the zones.
      // The user's current guessed zone is selected.
      const sel = document.querySelector('select.timezone');
      moment.tz.names().forEach( zone => {
        option = document.createElement('option');