Preserve engine type profile cohorts

This commit is contained in:
Jan Petykiewicz 2026-04-21 23:24:49 -07:00
commit f67629069c
3 changed files with 71 additions and 1 deletions

View file

@ -170,10 +170,15 @@ pub struct EngineTypesInspectionReport {
pub car_side_view_resource_pk4_missing_counts: BTreeMap<String, usize>,
pub car_auxiliary_stem_counts: BTreeMap<String, usize>,
pub car_auxiliary_stem_relation_counts: BTreeMap<String, usize>,
pub car_auxiliary_stem_distinct_pair_counts: BTreeMap<String, usize>,
pub internal_ne_profile_pk4_match_count: usize,
pub internal_ne_profile_pk4_missing_count: usize,
pub locomotive_pair_internal_ne_profile_pk4_match_count: usize,
pub locomotive_pair_internal_ne_profile_pk4_missing_count: usize,
pub matched_prefix_internal_ne_profile_pk4_match_count: usize,
pub matched_prefix_internal_ne_profile_pk4_missing_count: usize,
pub unmatched_display_internal_ne_profile_pk4_match_count: usize,
pub unmatched_display_internal_ne_profile_pk4_missing_count: usize,
pub internal_ne_profile_texture_size_counts: BTreeMap<String, usize>,
pub internal_ne_profile_horizontal_scale_modifier_counts: BTreeMap<String, usize>,
pub internal_ne_profile_max_percent_of_interface_vram_counts: BTreeMap<String, usize>,
@ -423,6 +428,11 @@ pub fn inspect_engine_types_dir(
.iter()
.filter_map(classify_car_auxiliary_stem_relation),
);
let car_auxiliary_stem_distinct_pair_counts = count_owned_values(
family_entries
.iter()
.filter_map(distinct_car_auxiliary_stem_pair_label),
);
let lco_companion_stem_counts = count_named_values(
family_entries
.iter()
@ -450,6 +460,42 @@ pub fn inspect_engine_types_dir(
&& family.internal_ne_profile_found_in_pk4 == Some(false)
})
.count();
let matched_prefix_internal_ne_profile_pk4_match_count = family_entries
.iter()
.filter(|family| {
family.has_matched_locomotive_pair
&& family.internal_ne_profile_found_in_pk4 == Some(true)
&& !UNMATCHED_LOCOMOTIVE_DISPLAY_NAMES
.contains(&family.primary_display_name.as_deref().unwrap_or(""))
})
.count();
let matched_prefix_internal_ne_profile_pk4_missing_count = family_entries
.iter()
.filter(|family| {
family.has_matched_locomotive_pair
&& family.internal_ne_profile_found_in_pk4 == Some(false)
&& !UNMATCHED_LOCOMOTIVE_DISPLAY_NAMES
.contains(&family.primary_display_name.as_deref().unwrap_or(""))
})
.count();
let unmatched_display_internal_ne_profile_pk4_match_count = family_entries
.iter()
.filter(|family| {
family.has_matched_locomotive_pair
&& family.internal_ne_profile_found_in_pk4 == Some(true)
&& UNMATCHED_LOCOMOTIVE_DISPLAY_NAMES
.contains(&family.primary_display_name.as_deref().unwrap_or(""))
})
.count();
let unmatched_display_internal_ne_profile_pk4_missing_count = family_entries
.iter()
.filter(|family| {
family.has_matched_locomotive_pair
&& family.internal_ne_profile_found_in_pk4 == Some(false)
&& UNMATCHED_LOCOMOTIVE_DISPLAY_NAMES
.contains(&family.primary_display_name.as_deref().unwrap_or(""))
})
.count();
let internal_ne_profile_texture_size_counts = side_view_imb_pk4_lookup
.as_ref()
.map(|lookup| lookup.internal_ne_profile_texture_size_counts.clone())
@ -549,10 +595,15 @@ pub fn inspect_engine_types_dir(
car_side_view_resource_pk4_missing_counts,
car_auxiliary_stem_counts,
car_auxiliary_stem_relation_counts,
car_auxiliary_stem_distinct_pair_counts,
internal_ne_profile_pk4_match_count,
internal_ne_profile_pk4_missing_count,
locomotive_pair_internal_ne_profile_pk4_match_count,
locomotive_pair_internal_ne_profile_pk4_missing_count,
matched_prefix_internal_ne_profile_pk4_match_count,
matched_prefix_internal_ne_profile_pk4_missing_count,
unmatched_display_internal_ne_profile_pk4_match_count,
unmatched_display_internal_ne_profile_pk4_missing_count,
internal_ne_profile_texture_size_counts,
internal_ne_profile_horizontal_scale_modifier_counts,
internal_ne_profile_max_percent_of_interface_vram_counts,
@ -933,6 +984,16 @@ fn classify_car_auxiliary_stem_relation(family: &EngineTypeFamilyEntry) -> Optio
Some("distinct_auxiliary_stem".to_string())
}
fn distinct_car_auxiliary_stem_pair_label(family: &EngineTypeFamilyEntry) -> Option<String> {
(classify_car_auxiliary_stem_relation(family)?.as_str() == "distinct_auxiliary_stem")
.then_some(())?;
Some(format!(
"{} -> {}",
family.internal_stem.as_deref()?,
family.auxiliary_stem.as_deref()?
))
}
fn strip_terminal_role_letter(value: &str) -> Option<&str> {
let last = value.chars().last()?;
matches!(last, 'L' | 'T' | 'l' | 't').then(|| {

View file

@ -12,11 +12,12 @@ This file is the short active queue for the current runtime and reverse-engineer
- The active static parser head is now the `engine_types` semantics frontier.
The repo now has structural inspectors for `.car`, `.lco`, `.cgo`, and `.cct`, but the binary side is still only partially semantic: the checked 1.05 corpus grounds `.car` fixed strings at `0x0c / 0x48 / 0x84` plus a second fixed stem slot at `0xa2` and a side-view resource name at `0xc0`, while `.lco` carries a stable primary stem at `0x04` and only conditional companion/body slots at `0x0c` and `0x12` when the leading stem slot is padded.
The checked 1.05 corpus now also splits `.car` auxiliary stems into `126` direct matches, `14` role-neutral roots, and only `5` truly distinct cases, while `.cgo` collapses into five stable scalar ladders instead of arbitrary floats.
The checked 1.05 corpus now also splits `.car` auxiliary stems into `126` direct matches, `14` role-neutral roots, and only `5` truly distinct cases, with those five exact internal-to-auxiliary pairs now preserved directly in the report surface, while `.cgo` collapses into five stable scalar ladders instead of arbitrary floats.
The early `.lco` lane block is now partially partitioned too: only offsets `0x20`, `0x34`, `0x38`, `0x3c`, `0x44`, `0x48`, and `0x54` behave like low-cardinality buckets, while the other early lanes still look high-variance.
The side-view resource path is now grounded into `Data/2D/rt3_2IMB.PK4`, and the `.imb` parser now decodes shipped comment-suffixed numeric rows plus `_NE` profile fields such as `HorizontalScaleModifier` and `ImageWHScaled`.
The checked PK4 linkage split is now explicit too: `132 / 145` side-view resource names resolve directly, but the remaining `13` are the missing `CarSideView_3.imb` cohort and that hole exists in both checked installs, while `43 / 145` derived `{internal_stem}_NE.imb` names resolve and all of those hits belong to matched locomotive pairs.
The packaged profile metadata is stable enough to summarize: `CarSideView_1` is `512x512` at `0.04` VRAM, `CarSideView_2` is `512x256` at `0.02`, and every packaged `_NE` profile is `512x128` with `HorizontalScaleModifier = 0.75` and `MaxPercentOfInterfaceVRAM = 0.09`.
The `_NE` split is now aligned with the locomotive display census too: all `43` packaged `_NE` hits live inside the grounded display prefix, and all `5` unmatched display-tail families are still missing packaged `_NE` profiles.
The next honest static work is to keep promoting those fixed lanes into stable parser fields, explain the five remaining distinct auxiliary-stem cases, and decide how far the `.cgo` ladders plus the low-cardinality `.lco` lanes can be grounded without overclaiming semantics.
Preserved checked parser detail now lives in [EngineTypes parser semantics](rehost-queue/engine-types-parser-semantics-2026-04-21.md).
Preserved checked format inventory detail now lives in [RT3 format inventory](rehost-queue/format-inventory-2026-04-21.md).

View file

@ -71,6 +71,12 @@ first `.car` / `.lco` / `.cgo` / `.cct` inspector pass landed.
- `CarSideView_2.imb`: `512x256`, `MaxPercentOfInterfaceVRAM = 0.02`
- every packaged `_NE.imb` profile: `512x128`, `HorizontalScaleModifier = 0.75`,
`MaxPercentOfInterfaceVRAM = 0.09`, and `ImageWHScaled` present
- The `_NE` profile split is now tied back to the locomotive display census:
- `43` matched locomotive display-prefix families resolve `{internal_stem}_NE.imb`
- `18` matched display-prefix families still do not resolve `{internal_stem}_NE.imb`
- `0` unmatched display-tail families resolve `{internal_stem}_NE.imb`
- all `5` unmatched display-tail families (`242 A1`, `Class 460`, `Class A1`, `Class P8`,
`Class QJ`) are missing packaged `_NE` profiles
## What The Current Parser Now Owns
@ -81,6 +87,7 @@ first `.car` / `.lco` / `.cgo` / `.cct` inspector pass landed.
- auxiliary stem slot
- side-view resource name
- auxiliary-stem relation counts across the shipped corpus
- exact distinct auxiliary-stem pair counts
- PK4-backed side-view resource resolution status
- derived `{internal_stem}_NE.imb` resolution status
- `.lco`
@ -102,6 +109,7 @@ first `.car` / `.lco` / `.cgo` / `.cct` inspector pass landed.
- `rt3_2IMB.PK4` link surface
- packaged side-view profile summaries for `CarSideView_*`
- packaged `_NE.imb` texture-size and scalar-family counts
- packaged `_NE.imb` match counts split by grounded display prefix vs unmatched display tail
## Remaining Static Questions