feat(commands): Add convenient names for read-data-subset n/m (#328)

This PR adds convenience names for the `-read-data-subset=n/m` option
which allow for more easy regular check runs which cover the whole
repository data over a given period.

E.g. it allows to daily run `check --read-data
--read-data-subset=daily/month` which covers the repository once run at
every day of any month. Before, this requirement needed scripting to set
`n` to the number of the current day within the month and `m` to the
total count of days in the current month.

For `n`, it is now allowed to use
- `hourly`
- `daily`
- `weekly`
- `monthly`
- `yearly`
which is replaced by an index corresponding to the date/time the `check`
command is called.

For `m`, it is now allowed to use
- `day`
- `week`
- `month`
- `year`
which is depending on `n` replaced by the total count of
hours/days/weeks/months within the current entity. Moreover
`month_hours`, `month_days`, `year_hours`, `year_days` which work
independent from `n`.

Co-authored-by: simonsan <[email protected]>

crates/core/src/commands/check.rs

@@ -1,11 +1,13 @@
 //! `check` subcommand
 use std::{
     collections::{BTreeSet, HashMap},
+    fmt::Debug,
     str::FromStr,
 };
 
 use bytes::Bytes;
 use bytesize::ByteSize;
+use chrono::{Datelike, Local, NaiveDateTime, Timelike};
 use derive_setters::Setters;
 use log::{debug, error, warn};
 use rand::{prelude::SliceRandom, thread_rng, Rng};
@@ -95,6 +97,47 @@ impl ReadSubsetOption {
     }
 }
 
+/// parses n/m inclding named settings depending on current date
+fn parse_n_m(now: NaiveDateTime, n_in: &str, m_in: &str) -> Result<(u32, u32), CommandErrorKind> {
+    let is_leap_year = |dt: NaiveDateTime| {
+        let year = dt.year();
+        year % 4 == 0 && (year % 25 != 0 || year % 16 == 0)
+    };
+
+    let days_of_month = |dt: NaiveDateTime| match dt.month() {
+        1 | 3 | 5 | 7 | 8 | 10 | 12 => 31,
+        4 | 6 | 9 | 11 => 30,
+        2 if is_leap_year(dt) => 29,
+        2 => 28,
+        _ => panic!("invalid month, should not happen"),
+    };
+
+    let days_of_year = |dt: NaiveDateTime| if is_leap_year(dt) { 366 } else { 365 };
+
+    let n = match n_in {
+        "hourly" => now.ordinal0() * 24 + now.hour(),
+        "daily" => now.ordinal0(),
+        "weekly" => now.iso_week().week0(),
+        "monthly" => now.month0(),
+        n => n.parse()?,
+    };
+
+    let m = match (n_in, m_in) {
+        ("hourly", "day") => 24,
+        ("hourly", "week") => 24 * 7,
+        ("hourly", "month") | (_, "month_hours") => 24 * days_of_month(now),
+        ("hourly", "year") | (_, "year_hours") => 24 * days_of_year(now),
+        ("daily", "week") => 7,
+        ("daily", "month") | (_, "month_days") => days_of_month(now),
+        ("daily", "year") | (_, "year_days") => days_of_year(now),
+        ("weekly", "month") => 4,
+        ("weekly", "year") => 52,
+        ("monthly", "year") => 12,
+        (_, m) => m.parse()?,
+    };
+    Ok((n % m, m))
+}
+
 impl FromStr for ReadSubsetOption {
     type Err = CommandErrorKind;
     fn from_str(s: &str) -> Result<Self, Self::Err> {
@@ -104,8 +147,8 @@ impl FromStr for ReadSubsetOption {
             // try to read percentage
             Self::Percentage(p.parse()?)
         } else if let Some((n, m)) = s.split_once('/') {
-            // try to read n/m
-            Self::IdSubSet((n.parse()?, m.parse()?))
+            let now = Local::now().naive_local();
+            Self::IdSubSet(parse_n_m(now, n, m)?)
         } else {
             Self::Size(
                 ByteSize::from_str(s)
@@ -131,8 +174,11 @@ pub struct CheckOptions {
     #[cfg_attr(feature = "clap", clap(long))]
     pub read_data: bool,
 
-    /// Read and check pack files
-    #[cfg_attr(feature = "clap", clap(long, default_value = "all"))]
+    /// Read only a subset of the data. Allowed values: "all", "n/m" for specific part, "x%" or a size for a random subset.
+    #[cfg_attr(
+        feature = "clap",
+        clap(long, default_value = "all", requires = "read_data")
+    )]
     pub read_data_subset: ReadSubsetOption,
 }
 
@@ -221,6 +267,7 @@ pub(crate) fn check_repository<P: ProgressBars, S: Open>(
             .into_iter()
             .filter(|p| packs.contains(&p.id));
 
+        debug!("using read-data-subset {:?}", opts.read_data_subset);
         let packs = opts.read_data_subset.apply(packs);
 
         repo.warm_up_wait(packs.iter().map(|pack| pack.id))?;
@@ -721,6 +768,47 @@ mod tests {
         assert_ron_snapshot!(s, ids);
     }
 
+    #[rstest]
+    #[case("5", "12")]
+    #[case("29", "28")]
+    #[case("15", "month_hours")]
+    #[case("4", "month_days")]
+    #[case("hourly", "day")]
+    #[case("hourly", "week")]
+    #[case("hourly", "month")]
+    #[case("hourly", "year")]
+    #[case("hourly", "20")]
+    #[case("daily", "week")]
+    #[case("daily", "month")]
+    #[case("daily", "year")]
+    #[case("daily", "15")]
+    #[case("weekly", "month")]
+    #[case("weekly", "year")]
+    #[case("weekly", "10")]
+    #[case("monthly", "year")]
+    #[case("monthly", "5")]
+    fn test_parse_n_m(#[case] n: &str, #[case] m: &str) {
+        let now: NaiveDateTime = "2024-10-11T12:00:00".parse().unwrap();
+        let res = parse_n_m(now, n, m).unwrap();
+        let now: NaiveDateTime = "2024-10-11T13:00:00".parse().unwrap();
+        let res_1h = parse_n_m(now, n, m).unwrap();
+        let now: NaiveDateTime = "2024-10-12T12:00:00".parse().unwrap();
+        let res_1d = parse_n_m(now, n, m).unwrap();
+        let now: NaiveDateTime = "2024-10-18T12:00:00".parse().unwrap();
+        let res_1w = parse_n_m(now, n, m).unwrap();
+        let now: NaiveDateTime = "2024-11-11T12:00:00".parse().unwrap();
+        let res_1m = parse_n_m(now, n, m).unwrap();
+        let now: NaiveDateTime = "2025-10-11T12:00:00".parse().unwrap();
+        let res_1y = parse_n_m(now, n, m).unwrap();
+        let now: NaiveDateTime = "2020-02-02T12:00:00".parse().unwrap();
+        let res2 = parse_n_m(now, n, m).unwrap();
+
+        assert_ron_snapshot!(
+            format!("n_m_{n}_{m}"),
+            (res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)
+        );
+    }
+
     fn test_read_subset_n_m() {
         let test_packs = test_packs(&mut thread_rng());
         let mut all_packs: BTreeSet<_> = test_packs.iter().map(|pack| pack.id).collect();

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_15_month_hours.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((15, 744), (15, 744), (15, 744), (15, 744), (15, 720), (15, 744), (15, 696))

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_29_28.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((1, 28), (1, 28), (1, 28), (1, 28), (1, 28), (1, 28), (1, 28))

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_4_month_days.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((4, 31), (4, 31), (4, 31), (4, 31), (4, 30), (4, 31), (4, 29))

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_5_12.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((5, 12), (5, 12), (5, 12), (5, 12), (5, 12), (5, 12), (5, 12))

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_daily_15.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((14, 15), (14, 15), (0, 15), (6, 15), (0, 15), (13, 15), (2, 15))

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_daily_month.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((5, 31), (5, 31), (6, 31), (12, 31), (15, 30), (4, 31), (3, 29))

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_daily_week.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((4, 7), (4, 7), (5, 7), (4, 7), (0, 7), (3, 7), (4, 7))

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_daily_year.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((284, 366), (284, 366), (285, 366), (291, 366), (315, 366), (283, 365), (32, 366))

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_hourly_20.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((8, 20), (9, 20), (12, 20), (16, 20), (12, 20), (4, 20), (0, 20))

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_hourly_day.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((12, 24), (13, 24), (12, 24), (12, 24), (12, 24), (12, 24), (12, 24))

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_hourly_month.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((132, 744), (133, 744), (156, 744), (300, 744), (372, 720), (108, 744), (84, 696))

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_hourly_week.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((108, 168), (109, 168), (132, 168), (108, 168), (12, 168), (84, 168), (108, 168))

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_hourly_year.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((6828, 8784), (6829, 8784), (6852, 8784), (6996, 8784), (7572, 8784), (6804, 8760), (780, 8784))

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_monthly_5.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((4, 5), (4, 5), (4, 5), (4, 5), (0, 5), (4, 5), (1, 5))

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_monthly_year.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((9, 12), (9, 12), (9, 12), (9, 12), (10, 12), (9, 12), (1, 12))

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_weekly_10.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((0, 10), (0, 10), (0, 10), (1, 10), (5, 10), (0, 10), (4, 10))

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_weekly_month.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((0, 4), (0, 4), (0, 4), (1, 4), (1, 4), (0, 4), (0, 4))

crates/core/src/commands/snapshots/rustic_core__commands__check__tests__n_m_weekly_year.snap

@@ -0,0 +1,5 @@
+---
+source: crates/core/src/commands/check.rs
+expression: "(res, res_1h, res_1d, res_1w, res_1m, res_1y, res2)"
+---
+((40, 52), (40, 52), (40, 52), (41, 52), (45, 52), (40, 52), (4, 52))