feat(taxonomy): add rust sidecar compact surface pipeline

This commit is contained in:
2026-03-12 15:23:10 -04:00
parent f2c25fb9c6
commit 58061af006
84 changed files with 19350 additions and 265 deletions

View File

@@ -0,0 +1,249 @@
use anyhow::{anyhow, Context, Result};
use serde::Deserialize;
use std::env;
use std::fs;
use std::collections::HashMap;
use std::path::PathBuf;
use crate::pack_selector::FiscalPack;
#[derive(Debug, Deserialize, Clone)]
pub struct SurfacePackFile {
pub version: String,
pub pack: String,
pub surfaces: Vec<SurfaceDefinition>,
}
#[derive(Debug, Deserialize, Clone)]
pub struct SurfaceDefinition {
pub surface_key: String,
pub statement: String,
pub label: String,
pub category: String,
pub order: i64,
pub unit: String,
pub rollup_policy: String,
pub allowed_source_concepts: Vec<String>,
pub allowed_authoritative_concepts: Vec<String>,
pub formula_fallback: Option<serde_json::Value>,
pub detail_grouping_policy: String,
pub materiality_policy: String,
}
#[derive(Debug, Deserialize, Clone)]
pub struct CrosswalkFile {
pub version: String,
pub regime: String,
pub mappings: std::collections::HashMap<String, CrosswalkMapping>,
}
#[derive(Debug, Deserialize, Clone)]
pub struct CrosswalkMapping {
pub surface_key: String,
pub authoritative_concept_key: String,
}
#[derive(Debug, Deserialize, Clone)]
pub struct KpiPackFile {
pub version: String,
pub pack: String,
pub kpis: Vec<KpiDefinition>,
}
#[derive(Debug, Deserialize, Clone)]
pub struct KpiDefinition {
pub key: String,
pub label: String,
pub unit: String,
}
#[derive(Debug, Deserialize, Clone)]
pub struct UniversalIncomeFile {
pub version: String,
pub rows: Vec<UniversalIncomeDefinition>,
}
#[derive(Debug, Deserialize, Clone)]
pub struct UniversalIncomeDefinition {
pub key: String,
pub statement: String,
pub label: String,
pub category: String,
pub order: i64,
pub unit: String,
}
#[derive(Debug, Deserialize, Clone)]
pub struct IncomeBridgeFile {
pub version: String,
pub pack: String,
pub rows: HashMap<String, IncomeBridgeRow>,
}
#[derive(Debug, Deserialize, Clone, Default)]
pub struct IncomeBridgeComponents {
#[serde(default)]
pub positive: Vec<String>,
#[serde(default)]
pub negative: Vec<String>,
}
#[derive(Debug, Deserialize, Clone, Default)]
pub struct IncomeBridgeConceptGroups {
#[serde(default)]
pub positive: Vec<IncomeBridgeConceptGroup>,
#[serde(default)]
pub negative: Vec<IncomeBridgeConceptGroup>,
}
#[derive(Debug, Deserialize, Clone)]
pub struct IncomeBridgeConceptGroup {
pub name: String,
pub concepts: Vec<String>,
}
#[derive(Debug, Deserialize, Clone)]
pub struct IncomeBridgeRow {
#[serde(default)]
pub direct_authoritative_concepts: Vec<String>,
#[serde(default)]
pub direct_source_concepts: Vec<String>,
#[serde(default)]
pub component_surfaces: IncomeBridgeComponents,
#[serde(default)]
pub component_concept_groups: IncomeBridgeConceptGroups,
pub formula: String,
#[serde(default)]
pub not_meaningful_for_pack: bool,
#[serde(default)]
pub warning_codes_when_used: Vec<String>,
}
pub fn resolve_taxonomy_dir() -> Result<PathBuf> {
let mut candidates = Vec::new();
if let Some(value) = env::var("FISCAL_TAXONOMY_DIR")
.ok()
.map(|value| value.trim().to_string())
.filter(|value| !value.is_empty())
{
candidates.push(PathBuf::from(value));
}
if let Ok(current_dir) = env::current_dir() {
candidates.push(current_dir.join("rust").join("taxonomy"));
candidates.push(current_dir.join("taxonomy"));
}
candidates.push(PathBuf::from(env!("CARGO_MANIFEST_DIR")).join("../taxonomy"));
if let Ok(executable) = env::current_exe() {
if let Some(parent) = executable.parent() {
candidates.push(parent.join("../rust/taxonomy"));
candidates.push(parent.join("../taxonomy"));
}
}
candidates
.into_iter()
.find(|path| path.is_dir())
.ok_or_else(|| anyhow!("taxonomy resolution failed: unable to locate runtime taxonomy directory"))
}
pub fn load_surface_pack(pack: FiscalPack) -> Result<SurfacePackFile> {
let taxonomy_dir = resolve_taxonomy_dir()?;
let path = taxonomy_dir
.join("fiscal")
.join("v1")
.join(format!("{}.surface.json", pack.as_str()));
let raw = fs::read_to_string(&path)
.with_context(|| format!("taxonomy resolution failed: unable to read {}", path.display()))?;
let file = serde_json::from_str::<SurfacePackFile>(&raw)
.with_context(|| format!("taxonomy resolution failed: unable to parse {}", path.display()))?;
let _ = (&file.version, &file.pack);
Ok(file)
}
pub fn load_crosswalk(regime: &str) -> Result<Option<CrosswalkFile>> {
let file_name = match regime {
"us-gaap" => "us-gaap.json",
"ifrs-full" => "ifrs.json",
_ => return Ok(None),
};
let taxonomy_dir = resolve_taxonomy_dir()?;
let path = taxonomy_dir.join("crosswalk").join(file_name);
let raw = fs::read_to_string(&path)
.with_context(|| format!("taxonomy resolution failed: unable to read {}", path.display()))?;
let file = serde_json::from_str::<CrosswalkFile>(&raw)
.with_context(|| format!("taxonomy resolution failed: unable to parse {}", path.display()))?;
let _ = (&file.version, &file.regime);
Ok(Some(file))
}
pub fn load_kpi_pack(pack: FiscalPack) -> Result<KpiPackFile> {
let taxonomy_dir = resolve_taxonomy_dir()?;
let path = taxonomy_dir
.join("fiscal")
.join("v1")
.join("kpis")
.join(format!("{}.kpis.json", pack.as_str()));
let raw = fs::read_to_string(&path)
.with_context(|| format!("taxonomy resolution failed: unable to read {}", path.display()))?;
let file = serde_json::from_str::<KpiPackFile>(&raw)
.with_context(|| format!("taxonomy resolution failed: unable to parse {}", path.display()))?;
let _ = (&file.version, &file.pack);
Ok(file)
}
pub fn load_universal_income_definitions() -> Result<UniversalIncomeFile> {
let taxonomy_dir = resolve_taxonomy_dir()?;
let path = taxonomy_dir
.join("fiscal")
.join("v1")
.join("universal_income.surface.json");
let raw = fs::read_to_string(&path)
.with_context(|| format!("taxonomy resolution failed: unable to read {}", path.display()))?;
let file = serde_json::from_str::<UniversalIncomeFile>(&raw)
.with_context(|| format!("taxonomy resolution failed: unable to parse {}", path.display()))?;
let _ = &file.version;
Ok(file)
}
pub fn load_income_bridge(pack: FiscalPack) -> Result<IncomeBridgeFile> {
let taxonomy_dir = resolve_taxonomy_dir()?;
let path = taxonomy_dir
.join("fiscal")
.join("v1")
.join(format!("{}.income-bridge.json", pack.as_str()));
let raw = fs::read_to_string(&path)
.with_context(|| format!("taxonomy resolution failed: unable to read {}", path.display()))?;
let file = serde_json::from_str::<IncomeBridgeFile>(&raw)
.with_context(|| format!("taxonomy resolution failed: unable to parse {}", path.display()))?;
let _ = (&file.version, &file.pack);
Ok(file)
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn resolves_taxonomy_dir_and_loads_core_pack() {
let taxonomy_dir = resolve_taxonomy_dir().expect("taxonomy dir should resolve during tests");
assert!(taxonomy_dir.exists());
let surface_pack = load_surface_pack(FiscalPack::Core).expect("core surface pack should load");
assert_eq!(surface_pack.pack, "core");
assert!(!surface_pack.surfaces.is_empty());
let kpi_pack = load_kpi_pack(FiscalPack::Core).expect("core kpi pack should load");
assert_eq!(kpi_pack.pack, "core");
let universal_income = load_universal_income_definitions().expect("universal income config should load");
assert!(!universal_income.rows.is_empty());
let core_bridge = load_income_bridge(FiscalPack::Core).expect("core bridge should load");
assert_eq!(core_bridge.pack, "core");
}
}