Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Implement DeduplicationStrategy::RetainBaseLanguages #4836

Merged
merged 4 commits into from
Apr 24, 2024
Merged

Implement DeduplicationStrategy::RetainBaseLanguages #4836

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3f6b28c
Implement `DeduplicationStrategy::RetainBaseLanguages`
jedel1043 Apr 23, 2024
1c71a0d
Add tests
jedel1043 Apr 23, 2024
166dbec
Rename utility function
jedel1043 Apr 23, 2024
4dcdc7e
Remove unnecessary variable
jedel1043 Apr 23, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions provider/datagen/src/bin/icu4x-datagen.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -303,6 +303,7 @@ enum Fallback {
#[derive(Copy, Clone, PartialEq, Eq, PartialOrd, Ord, ValueEnum, Debug)]
enum DeduplicationStrategy {
Maximal,
RetainBaseLanguages,
None,
}

Expand Down Expand Up @@ -532,6 +533,9 @@ fn main() -> eyre::Result<()> {
}
(Some(x), _, false) => match x {
DeduplicationStrategy::Maximal => Some(icu_datagen::DeduplicationStrategy::Maximal),
DeduplicationStrategy::RetainBaseLanguages => {
Some(icu_datagen::DeduplicationStrategy::RetainBaseLanguages)
}
DeduplicationStrategy::None => Some(icu_datagen::DeduplicationStrategy::None),
},
(None, fallback_mode, false) => match fallback_mode {
Expand Down
132 changes: 84 additions & 48 deletions provider/datagen/src/driver.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,12 +68,9 @@ pub enum RuntimeFallbackLocation {
pub enum DeduplicationStrategy {
/// Removes from the lookup table any locale whose parent maps to the same data.
Maximal,
// TODO(#58): Add `RetainBaseLanguages`
/*
/// Removes from the lookup table any locale whose parent maps to the same data, except if
/// the parent is `und`.
RetainBaseLanguages,
*/
/// Keeps all selected locales in the lookup table.
None,
}
Expand Down Expand Up @@ -635,8 +632,8 @@ impl DatagenDriver {
},
match deduplication_strategy {
DeduplicationStrategy::Maximal => "maximal deduplication",
// TODO(#58): Add `RetainBaseLanguages`
// DeduplicationStrategy::RetainBaseLanguages => "deduplication retaining base languages",
DeduplicationStrategy::RetainBaseLanguages =>
"deduplication retaining base languages",
DeduplicationStrategy::None => "no deduplication",
},
sorted_locales
Expand Down Expand Up @@ -748,8 +745,6 @@ impl DatagenDriver {
)?;

let (slowest_duration, slowest_locale) = match deduplication_strategy {
// TODO(#58): Add `RetainBaseLanguages`
// DeduplicationStrategy::RetainBaseLanguages => todo!(),
DeduplicationStrategy::Maximal => {
let payloads = locales_to_export
.into_par_iter()
Expand All @@ -760,48 +755,19 @@ impl DatagenDriver {
})
.collect::<Result<HashMap<_, _>, _>>()?;
let fallbacker = fallbacker.as_ref().map_err(|e| *e)?;
let fallbacker_with_config = fallbacker.for_config(key.fallback_config());
payloads
.iter()
.try_for_each(|(locale, (payload, _duration))| {
let mut iter = fallbacker_with_config.fallback_for(locale.clone());
while !iter.get().is_und() {
iter.step();
if let Some((inherited_payload, _duration)) =
payloads.get(iter.get())
{
if inherited_payload == payload {
// Found a match: don't need to write anything
log::trace!(
"Deduplicating {key}/{locale} (inherits from {})",
iter.get()
);
return Ok(());
} else {
// Not a match: we must include this
break;
}
}
}
// Did not find a match: export this payload
sink.put_payload(key, locale, payload).map_err(|e| {
e.with_req(
key,
DataRequest {
locale,
metadata: Default::default(),
},
)
})
})?;

// Slowest locale calculation:
payloads
.iter()
.map(|(locale, (_payload, duration))| {
(*duration, locale.write_to_string().into_owned())
deduplicate_locales::<true>(key, &payloads, fallbacker, sink)?
}
DeduplicationStrategy::RetainBaseLanguages => {
let payloads = locales_to_export
.into_par_iter()
.filter_map(|locale| {
let instant2 = Instant::now();
load_with_fallback(key, &locale)
.map(|r| r.map(|payload| (locale, (payload, instant2.elapsed()))))
})
.max()
.collect::<Result<HashMap<_, _>, _>>()?;
let fallbacker = fallbacker.as_ref().map_err(|e| *e)?;
deduplicate_locales::<false>(key, &payloads, fallbacker, sink)?
}
DeduplicationStrategy::None => locales_to_export
.into_par_iter()
Expand Down Expand Up @@ -1068,6 +1034,76 @@ fn select_locales_for_key(
Ok(result)
}

fn deduplicate_locales<const MAXIMAL: bool>(
jedel1043 marked this conversation as resolved.
Show resolved Hide resolved
key: DataKey,
payloads: &HashMap<DataLocale, (DataPayload<ExportMarker>, Duration)>,
fallbacker: &LocaleFallbacker,
sink: &dyn DataExporter,
) -> Result<Option<(Duration, String)>, DataError> {
let fallbacker_with_config = fallbacker.for_config(key.fallback_config());
payloads
.iter()
.try_for_each(|(locale, (payload, _duration))| {
// Always export `und`. This prevents calling `step` on an empty locale.
if locale.is_und() {
return sink.put_payload(key, locale, payload).map_err(|e| {
e.with_req(
key,
DataRequest {
locale,
metadata: Default::default(),
},
)
});
}
let mut iter = fallbacker_with_config.fallback_for(locale.clone());
loop {
if !MAXIMAL {
// To retain base languages, preemptively step to the
// parent locale. This should retain the locale if
// the next parent is `und`.
iter.step();
}
if iter.get().is_und() {
break;
}
if MAXIMAL {
iter.step();
}

if let Some((inherited_payload, _duration)) = payloads.get(iter.get()) {
if inherited_payload == payload {
// Found a match: don't need to write anything
log::trace!(
"Deduplicating {key}/{locale} (inherits from {})",
iter.get()
);
return Ok(());
} else {
// Not a match: we must include this
break;
}
}
}
// Did not find a match: export this payload
sink.put_payload(key, locale, payload).map_err(|e| {
e.with_req(
key,
DataRequest {
locale,
metadata: Default::default(),
},
)
})
})?;

// Slowest locale calculation:
Ok(payloads
.iter()
.map(|(locale, (_payload, duration))| (*duration, locale.write_to_string().into_owned()))
.max())
}

struct DisplayDuration(pub Duration);

impl fmt::Display for DisplayDuration {
Expand Down
Loading
Loading