Show all characters used in Prague public transit stop_names, headsigns and route_short_names

gtfs_character_check.sh

#!/usr/bin/env bash	

# Download static GTFS for Prague PID and show all used characters in stop_names, trip_headsigns and, route_short_names
# Require: curl, unzip and duckdb

GTFS_PID_URL='https://data.pid.cz/PID_GTFS.zip'
GTFS_ZIP_FILEMAME='pid_gtfs.zip'
GTFS_DIRNAME='pid_gtfs'

# check for file GTFS_ZIP_FILEMAME
 if [[ ! -e "$GTFS_ZIP_FILEMAME" ]]; then
	curl "$GTFS_PID_URL" --output "$GTFS_ZIP_FILEMAME"
 fi

# check for directory GTFS_DIRNAME
if [[ ! -d "$GTFS_DIRNAME" ]]; then 
	unzip pid_gtfs.zip -d "$GTFS_DIRNAME"
fi

cd "$GTFS_DIRNAME"

duckdb -csv -noheader -c "SELECT stop_name FROM read_csv_auto('stops.txt')" | grep -o . | sort | uniq | tr -d '\n'
echo
# "&()+,-./0123456789=ABCDEFGHIJKLMNOPRSTUVWXYZabcdefghijklmnopqrstuvwxyzÁÚáéíóöúüýČčĎďěňŘřŠšťůŽž

duckdb -csv -noheader -c "SELECT trip_headsign FROM read_csv_auto('trips.txt')" | grep -o . | sort | uniq | tr -d '\n'
echo
# "&(),-./1ABCDEFGHIJKLMNOPRSTUVWYZabcdefghijklmnopqrstuvxyzÁÖÚáéíóúüýČčĎďěňŘřŠšťůŽž✈

duckdb -csv -noheader -c "SELECT route_short_name FROM read_csv_auto('routes.txt')" | grep -o . | sort | uniq | tr -d '\n'
echo
# "0123456789ABCDEHKLMNOPRSTUVXYceilrÍŠ