[build] Adding libpostal_data script for downloading data from S3, Makefile uses that now as part of the all-local target. Can be run periodically after install

This commit is contained in:
Al
2015-09-28 17:26:11 -04:00
parent f29f2f091b
commit abfa744d59
3 changed files with 72 additions and 49 deletions

61
src/libpostal_data Executable file
View File

@@ -0,0 +1,61 @@
#!/usr/bin/env bash
if [ "$#" -ne 2 ]; then
echo "Usage: ./libpostal_data [upload|download] data_dir"
fi
LIBPOSTAL_S3_BUCKET_NAME="libpostal"
LIBPOSTAL_S3_KEY="s3://$LIBPOSTAL_S3_BUCKET_NAME"
LIBPOSTAL_S3_BUCKET_URL="http://$LIBPOSTAL_S3_BUCKET_NAME.s3.amazonaws.com"
LIBPOSTAL_DATA_FILE="libpostal_data.tar.gz"
COMMAND=$1
LIBPOSTAL_DATA_DIR=$2
LIBPOSTAL_DATA_UPDATED_PATH=$LIBPOSTAL_DATA_DIR/last_updated
BASIC_MODULE_DIRS=(address_expansins numex transliteration)
EPOCH_DATE="Jan 1 00:00:00 1970"
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..."
if [ $(curl $LIBPOSTAL_S3_BUCKET_URL/$filename -z "$(cat $updated_path)" --silent --remote-time -o $local_path -w %{http_code}) = "200" ]; then
echo "New libpostal $name available"
if date -r . >/dev/null 2>&1; then
echo $(date -d "$(date -d "@$(date -r $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
download_file $LIBPOSTAL_DATA_UPDATED_PATH $LIBPOSTAL_DATA_DIR $LIBPOSTAL_DATA_FILE "data file"
elif [ $COMMAND = "upload" ]; 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
else
echo "Invalid command: $COMMAND"
exit 1
fi