catlog  [node=localhost]  [date=today]   # 打印CSV日志到标准输出
pglog                                    # 从标准输入灌入CSVLOG
pglog12                                  # 灌入PG12格式的CSVLOG
pglog13                                  # 灌入PG13格式的CSVLOG
pglog14                                  # 灌入PG14格式的CSVLOG (=pglog)

catlog | pglog                       # 分析当前节点当日的日志
catlog node-1 '2021-07-15' | pglog   # 分析node-1在2021-07-15的csvlog

catlog | pglog                       # 分析当前节点当日的日志
catlog node-1 '2021-07-15' | pglog   # 分析node-1在2021-07-15的csvlog

git clone https://github.com/Vonng/isd.git; cd isd;

# the default PGURL for pigsty's meta database, change that accordingly
export PGURL=postgres://dbuser_dba:DBUser.DBA@127.0.0.1:5432/meta?sslmode=disable
psql "${PGURL}" -c 'SELECT 1'  # check if connection is ok

make sql              # setup postgres schema on target database

make reload-station   # equivalent to get-station + load-station

make get-parser       # download parser binary from github, you can just build with: make build
make reload-daily     # download and reload latest daily data and re-calculates monthly/yearly data

make get-stable       # download stable isd.daily dataset from Github
make load-stable      # load downloaded stable isd.daily dataset into database

make reload           # reload-station + reload-daily

bin/get-daily  2022                   # get daily observation summary of a specific year (1900-2023)
bin/load-daily "${PGURL}" 2022    # load daily data of a specific year 

bin/get-hourly  2022                  # get hourly observation record of a specific year (1900-2023)
bin/load-hourly "${PGURL}" 2022   # load hourly data of a specific year 

CREATE TABLE isd.station
(
    station    VARCHAR(12) PRIMARY KEY,
    usaf       VARCHAR(6) GENERATED ALWAYS AS (substring(station, 1, 6)) STORED,
    wban       VARCHAR(5) GENERATED ALWAYS AS (substring(station, 7, 5)) STORED,
    name       VARCHAR(32),
    country    VARCHAR(2),
    province   VARCHAR(2),
    icao       VARCHAR(4),
    location   GEOMETRY(POINT),
    longitude  NUMERIC GENERATED ALWAYS AS (Round(ST_X(location)::NUMERIC, 6)) STORED,
    latitude   NUMERIC GENERATED ALWAYS AS (Round(ST_Y(location)::NUMERIC, 6)) STORED,
    elevation  NUMERIC,
    period     daterange,
    begin_date DATE GENERATED ALWAYS AS (lower(period)) STORED,
    end_date   DATE GENERATED ALWAYS AS (upper(period)) STORED
);

CREATE TABLE IF NOT EXISTS isd.daily
(
    station     VARCHAR(12) NOT NULL, -- station number 6USAF+5WBAN
    ts          DATE        NOT NULL, -- observation date
    -- temperature & dew point
    temp_mean   NUMERIC(3, 1),        -- mean temperature ℃
    temp_min    NUMERIC(3, 1),        -- min temperature ℃
    temp_max    NUMERIC(3, 1),        -- max temperature ℃
    dewp_mean   NUMERIC(3, 1),        -- mean dew point ℃
    -- pressure
    slp_mean    NUMERIC(5, 1),        -- sea level pressure (hPa)
    stp_mean    NUMERIC(5, 1),        -- station pressure (hPa)
    -- visible distance
    vis_mean    NUMERIC(6),           -- visible distance (m)
    -- wind speed
    wdsp_mean   NUMERIC(4, 1),        -- average wind speed (m/s)
    wdsp_max    NUMERIC(4, 1),        -- max wind speed (m/s)
    gust        NUMERIC(4, 1),        -- max wind gust (m/s) 
    -- precipitation / snow depth
    prcp_mean   NUMERIC(5, 1),        -- precipitation (mm)
    prcp        NUMERIC(5, 1),        -- rectified precipitation (mm)
    sndp        NuMERIC(5, 1),        -- snow depth (mm)
    -- FRSHTT (Fog/Rain/Snow/Hail/Thunder/Tornado)
    is_foggy    BOOLEAN,              -- (F)og
    is_rainy    BOOLEAN,              -- (R)ain or Drizzle
    is_snowy    BOOLEAN,              -- (S)now or pellets
    is_hail     BOOLEAN,              -- (H)ail
    is_thunder  BOOLEAN,              -- (T)hunder
    is_tornado  BOOLEAN,              -- (T)ornado or Funnel Cloud
    -- record count
    temp_count  SMALLINT,             -- record count for temp
    dewp_count  SMALLINT,             -- record count for dew point
    slp_count   SMALLINT,             -- record count for sea level pressure
    stp_count   SMALLINT,             -- record count for station pressure
    wdsp_count  SMALLINT,             -- record count for wind speed
    visib_count SMALLINT,             -- record count for visible distance
    -- temp marks
    temp_min_f  BOOLEAN,              -- aggregate min temperature
    temp_max_f  BOOLEAN,              -- aggregate max temperature
    prcp_flag   CHAR,                 -- precipitation flag: ABCDEFGHI
    PRIMARY KEY (station, ts)
); -- PARTITION BY RANGE (ts);

NAME
        isd -- Intergrated Surface Dataset Parser

SYNOPSIS
        isd daily   [-i <input|stdin>] [-o <output|stout>] [-v]
        isd hourly  [-i <input|stdin>] [-o <output|stout>] [-v] [-d raw|ts-first|hour-first]

DESCRIPTION
        The isd program takes noaa isd daily/hourly raw tarball data as input.
        and generate parsed data in csv format as output. Works in pipe mode

        cat data/daily/2023.tar.gz | bin/isd daily -v | psql ${PGURL} -AXtwqc "COPY isd.daily FROM STDIN CSV;" 

        isd daily  -v -i data/daily/2023.tar.gz  | psql ${PGURL} -AXtwqc "COPY isd.daily FROM STDIN CSV;"
        isd hourly -v -i data/hourly/2023.tar.gz | psql ${PGURL} -AXtwqc "COPY isd.hourly FROM STDIN CSV;"

OPTIONS
        -i  <input>     input file, stdin by default
        -o  <output>    output file, stdout by default
        -p  <profpath>  pprof file path, enable if specified
        -d              de-duplicate rows for hourly dataset (raw, ts-first, hour-first)
        -v              verbose mode
        -h              print help

make            # 如果本地数据可用
make all        # 完整安装，从WHO官网下载数据
makd reload     # 重新下载并加载最新数据 

make reload     # download latest data and pour it again
make ui         # install grafana dashboards
make sql        # install database schemas
make download   # download latest data
make load       # load downloaded data into database
make reload     # download latest data and pour it into database