Northern-Thailand-Ping-River-Monitor/rust/collector/src/config.rs

//! Configuration from the same environment / `.env` file as the Python app,
//! so both services can share `/opt/thailand-water-monitor/.env`.

use anyhow::{Context, Result, bail};
use std::env;
use std::path::PathBuf;

pub const RID_API_URL: &str =
    "https://hyd-app-db.rid.go.th/webservice/getGroupHourlyWaterLevelReportAllHL.ashx";
pub const HII_API_BASE: &str = "https://api-v3.thaiwater.net/api/v1/thaiwater30/public";
pub const RID_DAMS_URL: &str = "https://app.rid.go.th/reservoir/api/dams";
pub const OPENMETEO_URL: &str = "https://api.open-meteo.com/v1/forecast";
/// The RID endpoint serves the same JSON to any client; keep the UA the
/// Python collector has used for years.
pub const USER_AGENT: &str = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 \
     (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36";

#[derive(Clone, Debug)]
pub struct Config {
    pub database_url: String,
    pub rid_api_url: String,
    pub hii_api_base: String,
    pub dams_url: String,
    pub openmeteo_url: String,
    pub hii_enabled: bool,
    pub dams_enabled: bool,
    pub rain_enabled: bool,
    pub hii_basin_code: i64,
    /// RID is polled this many minutes past each hour.
    pub poll_offset_minutes: u32,
    /// While the current hour is not published yet, retry this often.
    pub retry_minutes: u32,
    /// Days of RID holes re-fetched at startup (0 = off).
    pub gap_fill_days_on_start: u32,
    pub station_config_path: PathBuf,
    /// Status JSON read by the Python API's /scraping/status.
    pub status_file: Option<PathBuf>,
}

fn var(name: &str) -> Option<String> {
    env::var(name)
        .ok()
        .map(|v| v.trim().to_string())
        .filter(|v| !v.is_empty())
}

fn flag(name: &str, default: bool) -> bool {
    var(name).map_or(default, |v| {
        matches!(v.to_lowercase().as_str(), "1" | "true" | "yes")
    })
}

fn number<T: std::str::FromStr>(name: &str, default: T) -> Result<T>
where
    T::Err: std::fmt::Display,
{
    match var(name) {
        None => Ok(default),
        Some(v) => v.parse().map_err(|e| anyhow::anyhow!("{name}={v:?}: {e}")),
    }
}

/// Percent-encode everything outside RFC 3986 "unreserved" (as Python's
/// `urllib.parse.quote(password, safe="")`).
fn encode_userinfo(s: &str) -> String {
    s.bytes()
        .map(|b| match b {
            b'A'..=b'Z' | b'a'..=b'z' | b'0'..=b'9' | b'-' | b'.' | b'_' | b'~' => {
                (b as char).to_string()
            }
            _ => format!("%{b:02X}"),
        })
        .collect()
}

/// SQLAlchemy URLs carry a driver suffix (`postgresql+psycopg2://`) that
/// sqlx does not understand.
pub fn normalize_database_url(url: &str) -> String {
    match url.split_once("://") {
        Some((scheme, rest))
            if scheme.starts_with("postgresql") || scheme.starts_with("postgres") =>
        {
            format!("postgres://{rest}")
        }
        _ => url.to_string(),
    }
}

impl Config {
    pub fn from_env() -> Result<Self> {
        let database_url = match var("POSTGRES_CONNECTION_STRING") {
            Some(url) => normalize_database_url(&url),
            None => {
                let password = var("POSTGRES_PASSWORD")
                    .context("POSTGRES_CONNECTION_STRING or POSTGRES_PASSWORD must be set")?;
                format!(
                    "postgres://{}:{}@{}:{}/{}",
                    encode_userinfo(&var("POSTGRES_USER").unwrap_or_else(|| "postgres".into())),
                    encode_userinfo(&password),
                    var("POSTGRES_HOST").unwrap_or_else(|| "localhost".into()),
                    var("POSTGRES_PORT").unwrap_or_else(|| "5432".into()),
                    var("POSTGRES_DB").unwrap_or_else(|| "water_monitoring".into()),
                )
            }
        };
        if let Some(db_type) = var("DB_TYPE")
            && db_type != "postgresql"
        {
            bail!("ping-collector supports PostgreSQL only (DB_TYPE={db_type})");
        }
        let cfg = Config {
            database_url,
            rid_api_url: var("RID_API_URL").unwrap_or_else(|| RID_API_URL.into()),
            hii_api_base: var("HII_API_BASE").unwrap_or_else(|| HII_API_BASE.into()),
            dams_url: var("RID_DAMS_URL").unwrap_or_else(|| RID_DAMS_URL.into()),
            openmeteo_url: var("OPENMETEO_URL").unwrap_or_else(|| OPENMETEO_URL.into()),
            hii_enabled: flag("ENABLE_HII_COLLECTION", true),
            dams_enabled: flag("ENABLE_RESERVOIR_COLLECTION", true),
            rain_enabled: flag("ENABLE_RAIN_COLLECTION", true),
            hii_basin_code: number("HII_BASIN_CODE", 6)?,
            poll_offset_minutes: number("RID_POLL_OFFSET_MINUTES", 5)?,
            retry_minutes: number("RID_RETRY_MINUTES", 10)?,
            gap_fill_days_on_start: number("GAP_FILL_DAYS_ON_START", 14)?,
            station_config_path: var("STATION_CONFIG_PATH")
                .unwrap_or_else(|| "stations.json".into())
                .into(),
            status_file: var("SCRAPING_STATUS_FILE").map(PathBuf::from),
        };
        if cfg.poll_offset_minutes >= 60 {
            bail!("RID_POLL_OFFSET_MINUTES must be between 0 and 59");
        }
        if cfg.retry_minutes == 0 {
            bail!("RID_RETRY_MINUTES must be positive");
        }
        Ok(cfg)
    }

    /// The URL with the password masked, for logs.
    pub fn redacted_database_url(&self) -> String {
        match (self.database_url.find("://"), self.database_url.rfind('@')) {
            (Some(s), Some(at)) if at > s => {
                let creds = &self.database_url[s + 3..at];
                let user = creds.split(':').next().unwrap_or("");
                format!(
                    "{}{user}:***{}",
                    &self.database_url[..s + 3],
                    &self.database_url[at..]
                )
            }
            _ => self.database_url.clone(),
        }
    }
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn sqlalchemy_urls_are_normalized() {
        assert_eq!(
            normalize_database_url("postgresql+psycopg2://u:p@h:5432/db"),
            "postgres://u:p@h:5432/db"
        );
        assert_eq!(
            normalize_database_url("postgresql://u@h/db"),
            "postgres://u@h/db"
        );
    }

    #[test]
    fn passwords_are_percent_encoded() {
        assert_eq!(encode_userinfo("p@ss:w/rd"), "p%40ss%3Aw%2Frd");
    }
}