libpostal/src/libpostal_data

#!/bin/sh

set -e

if [ "$#" -lt 3 ]; then
    echo "Usage: ./libpostal_data [upload|download] [base|geodb] data_dir"
    exit 1
fi

LIBPOSTAL_S3_BUCKET_NAME="libpostal"
LIBPOSTAL_S3_KEY="s3://$LIBPOSTAL_S3_BUCKET_NAME"
LIBPOSTAL_S3_BUCKET_URL="http://$LIBPOSTAL_S3_BUCKET_NAME.s3.amazonaws.com"
LIBPOSTAL_DATA_FILE="libpostal_data.tar.gz"
LIBPOSTAL_GEODB_FILE="geodb.tar.gz"
LIBPOSTAL_PARSER_FILE="parser.tar.gz"
LIBPOSTAL_LANG_CLASS_FILE="language_classifier.tar.gz"

COMMAND=$1
FILE=$2
LIBPOSTAL_DATA_DIR=$3

mkdir -p $LIBPOSTAL_DATA_DIR

LIBPOSTAL_DATA_UPDATED_PATH=$LIBPOSTAL_DATA_DIR/last_updated
LIBPOSTAL_GEO_UPDATED_PATH=$LIBPOSTAL_DATA_DIR/last_updated_geo
LIBPOSTAL_PARSER_UPDATED_PATH=$LIBPOSTAL_DATA_DIR/last_updated_parser
LIBPOSTAL_LANG_CLASS_UPDATED_PATH=$LIBPOSTAL_DATA_DIR/last_updated_language_classifier

BASIC_MODULE_DIRS="address_expansions numex transliteration"
GEODB_MODULE_DIR=geodb
PARSER_MODULE_DIR=address_parser
LANGUAGE_CLASSIFIER_MODULE_DIR=language_classifier

export LC_ALL=C

EPOCH_DATE="Jan  1 00:00:00 1970"

MB=$((1024*1024))
CHUNK_SIZE=$((64*$MB))

LARGE_FILE_SIZE=$((CHUNK_SIZE*2))


NUM_WORKERS=10

kill_background_processes() {
    jobs -p | xargs kill;
    exit
}

trap kill_background_processes INT

PART_MSG='echo "Downloading part $1: filename=$5, offset=$2, max=$3"'
PART_CURL='curl $4 --silent -H"Range:bytes=$2-$3" --retry 3 --retry-delay 2 -o $5'
DOWNLOAD_PART="$PART_MSG;$PART_CURL"


download_multipart() {
    url=$1
    filename=$2
    size=$3

    num_chunks=$((size/CHUNK_SIZE))
    echo "Downloading multipart: $url, size=$size, num_chunks=$num_chunks"
    offset=0
    i=0
    while [ $i -lt $num_chunks ]; do
        i=$((i+1))
        part_filename="$filename.$i"
        if [ $i -lt $num_chunks ]; then
            max=$((offset+CHUNK_SIZE-1));
        else
            max=$size;
        fi;
        printf "%s\0%s\0%s\0%s\0%s\0" "$i" "$offset" "$max" "$url" "$part_filename"
        offset=$((offset+CHUNK_SIZE))
    done | xargs -0 -n 5 -P $NUM_WORKERS sh -c "$DOWNLOAD_PART" --

    > $local_path

    i=0
    while [ $i -lt $num_chunks ]; do
        i=$((i+1))
        part_filename="$filename.$i"
        cat $part_filename >> $local_path
        rm $part_filename
    done;

}


download_file() {
    updated_path=$1
    data_dir=$2
    filename=$3
    name=$4

    local_path=$data_dir/$filename

    if [ ! -e $updated_path ]; then
        echo "$EPOCH_DATE" > $updated_path;
    fi;

    echo "Checking for new libpostal $name..."

    url=$LIBPOSTAL_S3_BUCKET_URL/$filename

    if [ $(curl -sI $url -z "$(cat $updated_path)" --remote-time -w %{http_code} -o /dev/null | grep "^200$") ]; then
        echo "New libpostal $name available"
        content_length=$(curl -I $url 2> /dev/null | awk '/^Content-Length:/ { print $2 }' | tr -d '[[:space:]]')

        if [ $content_length -ge $LARGE_FILE_SIZE ]; then
            download_multipart $url $local_path $content_length
        else
            curl $url --retry 3 --retry-delay 2 -o $local_path
        fi

        if date -ur . >/dev/null 2>&1; then
            echo $(date -d "$(date -d "@$(date -ur $local_path +%s)") + 1 second") > $updated_path;
        elif stat -f %Sm . >/dev/null 2>&1; then
            echo $(date -r $(stat -f %m $local_path) -v+1S) > $updated_path;
        fi;
        tar -xvzf $local_path -C $data_dir;
        rm $local_path;
    else
        echo "libpostal $name up to date"
    fi
}

if [ $COMMAND = "download" ]; then
    mkdir -p $LIBPOSTAL_DATA_DIR

    if [ $FILE = "base" ] || [ $FILE = "all" ]; then
        download_file $LIBPOSTAL_DATA_UPDATED_PATH $LIBPOSTAL_DATA_DIR $LIBPOSTAL_DATA_FILE "data file"
    fi
    if [ $FILE = "geodb" ] || [ $FILE = "all" ]; then
        download_file $LIBPOSTAL_GEO_UPDATED_PATH $LIBPOSTAL_DATA_DIR $LIBPOSTAL_GEODB_FILE "geodb data file"
    fi
    if [ $FILE = "parser" ] || [ $FILE = "all" ]; then
        download_file $LIBPOSTAL_PARSER_UPDATED_PATH $LIBPOSTAL_DATA_DIR $LIBPOSTAL_PARSER_FILE "parser data file"
    fi
    if [ $FILE = "language_classifier" ] || [ $FILE = "all" ]; then
        download_file $LIBPOSTAL_LANG_CLASS_UPDATED_PATH $LIBPOSTAL_DATA_DIR $LIBPOSTAL_LANG_CLASS_FILE "language classifier data file"
    fi

elif [ $COMMAND = "upload" ]; then

    if [ $FILE = "base" ] || [ $FILE = "all" ]; then
        tar -C $LIBPOSTAL_DATA_DIR -cvzf $LIBPOSTAL_DATA_DIR/$LIBPOSTAL_DATA_FILE $BASIC_MODULE_DIRS
        aws s3 cp --acl=public-read $LIBPOSTAL_DATA_DIR/$LIBPOSTAL_DATA_FILE $LIBPOSTAL_S3_KEY
    fi

    if [ $FILE = "geodb" ] || [ $FILE = "all" ]; then
        tar -C $LIBPOSTAL_DATA_DIR -cvzf $LIBPOSTAL_DATA_DIR/$LIBPOSTAL_GEODB_FILE $GEODB_MODULE_DIR
        aws s3 cp --acl=public-read $LIBPOSTAL_DATA_DIR/$LIBPOSTAL_GEODB_FILE $LIBPOSTAL_S3_KEY
    fi

    if [ $FILE = "parser" ] || [ $FILE = "all" ]; then
        tar -C $LIBPOSTAL_DATA_DIR -cvzf $LIBPOSTAL_DATA_DIR/$LIBPOSTAL_PARSER_FILE $PARSER_MODULE_DIR
        aws s3 cp --acl=public-read $LIBPOSTAL_DATA_DIR/$LIBPOSTAL_PARSER_FILE $LIBPOSTAL_S3_KEY
    fi

    if [ $FILE = "language_classifier" ] || [ $FILE = "all" ]; then
        tar -C $LIBPOSTAL_DATA_DIR -cvzf $LIBPOSTAL_DATA_DIR/$LIBPOSTAL_LANG_CLASS_FILE $LANGUAGE_CLASSIFIER_MODULE_DIR
        aws s3 cp --acl=public-read $LIBPOSTAL_DATA_DIR/$LIBPOSTAL_LANG_CLASS_FILE $LIBPOSTAL_S3_KEY
    fi

else
    echo "Invalid command: $COMMAND"
    exit 1
fi