djszemiako

#!/usr/bin/env bash
set -euo pipefail

if [ $# -ne 1 ]; then
    echo "Usage: $(basename "$0") <source>"
    echo "Example: $(basename "$0") 'bucket/path/to/data'"
    echo "         $(basename "$0") 'gs://bucket/path/to/data'"
    exit 1
fi

djszemiako

import pandas as pd
from datetime import datetime
from itertools import combinations
from math import comb
from sys import argv
from time import monotonic
from typing import List


MAX_FAMILY_TOKENS = 6

djszemiako

import pandas as pd
from datetime import datetime
from rapidfuzz.process import extractOne
from string_grouper import match_strings, group_similar_strings
from sys import argv
from time import monotonic
from uuid import uuid4


class Constants:

djszemiako

# Make sure the source index is actually open
POST /source_index/_open

# Put the source index in read-only mode
PUT /source_index/_settings
{
  "settings": {
    "index.blocks.write": "true"
  }
}