feat(stitched): Implement a simple REPL for testing stitched ordering

This commit is contained in:
Ginger 2026-01-22 14:55:08 -05:00
parent 4da955438e
commit 4a6295e374
No known key found for this signature in database
6 changed files with 269 additions and 94 deletions

41
Cargo.lock generated
View file

@ -935,6 +935,15 @@ version = "0.7.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c3e64b0cc0439b12df2fa678eae89a1c56a529fd067a9115f7827f1fffd22b32"
[[package]]
name = "clipboard-win"
version = "5.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bde03770d3df201d4fb868f2c9c59e66a3e4e2bd06692a0fe701e7103c7e84d4"
dependencies = [
"error-code",
]
[[package]]
name = "cmake"
version = "0.1.57"
@ -1820,6 +1829,12 @@ dependencies = [
"windows-sys 0.61.2",
]
[[package]]
name = "error-code"
version = "3.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dea2df4cf52843e0452895c455a1a2cfbb842a1e7329671acf418fdc53ed4c59"
[[package]]
name = "event-listener"
version = "5.3.1"
@ -4613,6 +4628,25 @@ version = "1.0.22"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b39cdef0fa800fc44525c84ccb54a029961a8215f9619753635a9c0d2538d46d"
[[package]]
name = "rustyline"
version = "17.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e902948a25149d50edc1a8e0141aad50f54e22ba83ff988cf8f7c9ef07f50564"
dependencies = [
"bitflags",
"cfg-if",
"clipboard-win",
"libc",
"log",
"memchr",
"nix",
"unicode-segmentation",
"unicode-width 0.2.2",
"utf8parse",
"windows-sys 0.60.2",
]
[[package]]
name = "rustyline-async"
version = "0.4.6"
@ -5142,6 +5176,7 @@ dependencies = [
"indexmap",
"itertools 0.14.0",
"peg",
"rustyline",
]
[[package]]
@ -5905,6 +5940,12 @@ version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"
[[package]]
name = "utf8parse"
version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
[[package]]
name = "uuid"
version = "1.19.0"

View file

@ -16,3 +16,4 @@ itertools.workspace = true
[dev-dependencies]
peg = "0.8.5"
rustyline = { version = "17.0.2", default-features = false }

View file

@ -0,0 +1,90 @@
use std::collections::HashSet;
use rustyline::{DefaultEditor, Result, error::ReadlineError};
use stitcher::{Batch, EventEdges, Stitcher, memory_backend::MemoryStitcherBackend};
const BANNER: &str = "
stitched ordering test repl
- append an event by typing its name: `A`
- to add prev events type an arrow and then space-separated event names: `A --> B C D`
- use `/reset` to clear the ordering
Ctrl-D to exit, Ctrl-C to clear input
"
.trim_ascii();
enum Command<'line> {
AppendEvents(EventEdges<'line>),
ResetOrder,
}
peg::parser! {
// partially copied from the test case parser
grammar command_parser() for str {
/// Parse whitespace.
rule _ -> () = quiet! { $([' '])* {} }
/// Parse empty lines and comments.
rule newline() -> () = quiet! { (("#" [^'\n']*)? "\n")+ {} }
/// Parse an event ID.
rule event_id() -> &'input str
= quiet! { id:$([char if char.is_ascii_alphanumeric() || ['_', '-'].contains(&char)]+) { id } }
/ expected!("event id")
/// Parse an event and its prev events.
rule event() -> (&'input str, HashSet<&'input str>)
= id:event_id() prev_events:(_ "-->" _ id:(event_id() ++ _) { id })? {
(id, prev_events.into_iter().flatten().collect())
}
pub rule command() -> Command<'input> =
"/reset" { Command::ResetOrder }
/ events:event() ++ newline() { Command::AppendEvents(events.into_iter().collect()) }
}
}
fn main() -> Result<()> {
let mut backend = MemoryStitcherBackend::default();
let mut reader = DefaultEditor::new()?;
println!("{BANNER}");
loop {
match reader.readline("> ") {
| Ok(line) => match command_parser::command(&line) {
| Ok(Command::AppendEvents(events)) => {
let batch = Batch::from_edges(&events);
let stitcher = Stitcher::new(&backend);
let updates = stitcher.stitch(&batch);
for update in &updates.gap_updates {
println!("update to gap {}:", update.key);
println!(" new gap contents: {:?}", update.gap);
println!(" inserted items: {:?}", update.inserted_items);
}
println!("new items: {:?}", &updates.new_items);
println!("events added to gaps: {:?}", &updates.events_added_to_gaps);
backend.extend(updates);
println!("\norder: {backend:?}");
},
| Ok(Command::ResetOrder) => {
backend.clear();
println!("order cleared.");
},
| Err(parse_error) => {
println!("parse error!! {parse_error}");
},
},
| Err(ReadlineError::Interrupted) => {
println!("interrupt");
},
| Err(ReadlineError::Eof) => {
println!("goodbye :3");
break Ok(());
},
| Err(err) => break Err(err),
}
}
}

View file

@ -0,0 +1,130 @@
use std::{
fmt::Debug,
sync::atomic::{AtomicU64, Ordering},
};
use crate::{Gap, OrderUpdates, StitchedItem, StitcherBackend};
/// A version of [`StitchedItem`] which owns event IDs.
#[derive(Debug)]
enum MemoryStitcherItem {
Event(String),
Gap(Gap),
}
impl From<StitchedItem<'_>> for MemoryStitcherItem {
fn from(value: StitchedItem) -> Self {
match value {
| StitchedItem::Event(id) => MemoryStitcherItem::Event(id.to_string()),
| StitchedItem::Gap(gap) => MemoryStitcherItem::Gap(gap),
}
}
}
impl<'id> From<&'id MemoryStitcherItem> for StitchedItem<'id> {
fn from(value: &'id MemoryStitcherItem) -> Self {
match value {
| MemoryStitcherItem::Event(id) => StitchedItem::Event(id),
| MemoryStitcherItem::Gap(gap) => StitchedItem::Gap(gap.clone()),
}
}
}
/// A stitcher backend which holds a stitched ordering in RAM.
#[derive(Default)]
pub struct MemoryStitcherBackend {
items: Vec<(u64, MemoryStitcherItem)>,
counter: AtomicU64,
}
impl MemoryStitcherBackend {
fn next_id(&self) -> u64 { self.counter.fetch_add(1, Ordering::Relaxed) }
/// Extend this ordering with new updates.
pub fn extend(&mut self, results: OrderUpdates<'_, <Self as StitcherBackend>::Key>) {
for update in results.gap_updates {
let Some(gap_index) = self.items.iter().position(|(key, _)| *key == update.key)
else {
panic!("bad update key {}", update.key);
};
let insertion_index = if update.gap.is_empty() {
self.items.remove(gap_index);
gap_index
} else {
match self.items.get_mut(gap_index) {
| Some((_, MemoryStitcherItem::Gap(gap))) => {
*gap = update.gap;
},
| Some((key, other)) => {
panic!("expected item with key {key} to be a gap, it was {other:?}");
},
| None => unreachable!("we just checked that this index is valid"),
}
gap_index.checked_add(1).expect(
"should never allocate usize::MAX ids. what kind of test are you running",
)
};
let to_insert: Vec<_> = update
.inserted_items
.into_iter()
.map(|item| (self.next_id(), item.into()))
.collect();
self.items
.splice(insertion_index..insertion_index, to_insert.into_iter())
.for_each(drop);
}
let new_items: Vec<_> = results
.new_items
.into_iter()
.map(|item| (self.next_id(), item.into()))
.collect();
self.items.extend(new_items);
}
/// Iterate over the items in this ordering.
pub fn iter(&self) -> impl Iterator<Item = StitchedItem<'_>> {
self.items.iter().map(|(_, item)| item.into())
}
/// Clear this ordering.
pub fn clear(&mut self) { self.items.clear(); }
}
impl StitcherBackend for MemoryStitcherBackend {
type Key = u64;
fn find_matching_gaps<'a>(
&'a self,
events: impl Iterator<Item = &'a str>,
) -> impl Iterator<Item = (Self::Key, Gap)> {
// nobody cares about test suite performance right
let mut gaps = vec![];
for event in events {
for (key, item) in &self.items {
if let MemoryStitcherItem::Gap(gap) = item
&& gap.contains(event)
{
gaps.push((*key, gap.clone()));
}
}
}
gaps.into_iter()
}
fn event_exists<'a>(&'a self, event: &'a str) -> bool {
self.items
.iter()
.any(|item| matches!(&item.1, MemoryStitcherItem::Event(id) if event == id))
}
}
impl Debug for MemoryStitcherBackend {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.debug_list().entries(self.iter()).finish()
}
}

View file

@ -3,8 +3,10 @@ use std::{cmp::Ordering, collections::HashSet};
use indexmap::IndexMap;
pub mod algorithm;
pub mod memory_backend;
#[cfg(test)]
mod test;
pub use algorithm::*;
/// A gap in the stitched order.

View file

@ -1,101 +1,12 @@
use std::sync::atomic::{AtomicU64, Ordering};
use itertools::Itertools;
use super::{algorithm::*, *};
use crate::memory_backend::MemoryStitcherBackend;
mod parser;
/// A stitcher backend which holds a stitched ordering in RAM.
#[derive(Default)]
struct TestStitcherBackend<'id> {
items: Vec<(u64, StitchedItem<'id>)>,
counter: AtomicU64,
}
impl<'id> TestStitcherBackend<'id> {
fn next_id(&self) -> u64 { self.counter.fetch_add(1, Ordering::Relaxed) }
fn extend(&mut self, results: OrderUpdates<'id, <Self as StitcherBackend>::Key>) {
for update in results.gap_updates {
let Some(gap_index) = self.items.iter().position(|(key, _)| *key == update.key)
else {
panic!("bad update key {}", update.key);
};
let insertion_index = if update.gap.is_empty() {
self.items.remove(gap_index);
gap_index
} else {
match self.items.get_mut(gap_index) {
| Some((_, StitchedItem::Gap(gap))) => {
*gap = update.gap;
},
| Some((key, other)) => {
panic!("expected item with key {key} to be a gap, it was {other:?}");
},
| None => unreachable!("we just checked that this index is valid"),
}
gap_index.checked_add(1).expect(
"should never allocate usize::MAX ids. what kind of test are you running",
)
};
let to_insert: Vec<_> = update
.inserted_items
.into_iter()
.map(|item| (self.next_id(), item))
.collect();
self.items
.splice(insertion_index..insertion_index, to_insert.into_iter())
.for_each(drop);
}
let new_items: Vec<_> = results
.new_items
.into_iter()
.map(|item| (self.next_id(), item))
.collect();
self.items.extend(new_items);
}
fn iter(&self) -> impl Iterator<Item = &StitchedItem<'id>> {
self.items.iter().map(|(_, item)| item)
}
}
impl StitcherBackend for TestStitcherBackend<'_> {
type Key = u64;
fn find_matching_gaps<'a>(
&'a self,
events: impl Iterator<Item = &'a str>,
) -> impl Iterator<Item = (Self::Key, Gap)> {
// nobody cares about test suite performance right
let mut gaps = vec![];
for event in events {
for (key, item) in &self.items {
if let StitchedItem::Gap(gap) = item
&& gap.contains(event)
{
gaps.push((*key, gap.clone()));
}
}
}
gaps.into_iter()
}
fn event_exists<'a>(&'a self, event: &'a str) -> bool {
self.items
.iter()
.any(|item| matches!(item.1, StitchedItem::Event(id) if event == id))
}
}
fn run_testcase(testcase: parser::TestCase<'_>) {
let mut backend = TestStitcherBackend::default();
let mut backend = MemoryStitcherBackend::default();
for (index, phase) in testcase.into_iter().enumerate() {
let stitcher = Stitcher::new(&backend);
@ -107,7 +18,7 @@ fn run_testcase(testcase: parser::TestCase<'_>) {
for update in &updates.gap_updates {
println!("update to gap {}:", update.key);
println!(" new gap contents: {:?}", update.gap);
println!(" new items: {:?}", update.inserted_items);
println!(" inserted items: {:?}", update.inserted_items);
}
println!("expected new items: {:?}", &phase.order.new_items);
@ -134,9 +45,9 @@ fn run_testcase(testcase: parser::TestCase<'_>) {
}
backend.extend(updates);
println!("extended ordering: {:?}", backend.items);
println!("extended ordering: {:?}", backend);
for (expected, actual) in phase.order.iter().zip_eq(backend.iter()) {
for (expected, ref actual) in phase.order.iter().zip_eq(backend.iter()) {
assert_eq!(
expected, actual,
"bad item in order, expected {expected:?} but got {actual:?}",