commit 3630d8f4d106978acc4c33b92a3cb1ab3a364e8b Author: flemming-it Date: Thu Jun 18 11:25:19 2026 +0200 feat: initial stats-cohort-size v0.1.0 (stats.cohort_size@0.1.0) Resolve the size of an addressee cohort (e.g. "Berliner KMU", "Gastronomie deutschlandweit"). v0.1.0 ships a five-entry built-in lookup for the F∆I Law-Heatmap pilot corpus: berlin-kmu, de-kmu, gastro-de, handwerk-be, bauwirtschaft-be Each entry carries (count, year, source, tier). Tier follows the Studie §6.7 Regel-der-niedrigsten-Stufe: T1 when from DESTATIS Unternehmensregister, T2 when from a Verband source. Reuse-lens: any quantitative analysis that needs cohort sizing — market research, audience targeting, public-health tracking. Pure in-WASM, zero filesystem, zero network. Reserved for next versions: - 0.2: DESTATIS GENESIS-API adapter — requires net: ["genesis.destatis.de"] permission. Interface stays the same; the static lookup becomes the fallback when the API is unreachable. - 0.3: WZ-Code-resolved sub-cohorts (e.g. "berlin-kmu-wz56"). Signed-off-by: flemming-it diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..5e66a2d --- /dev/null +++ b/.gitignore @@ -0,0 +1,3 @@ +target/ +**/*.rs.bk +.DS_Store diff --git a/Cargo.lock b/Cargo.lock new file mode 100644 index 0000000..5503154 --- /dev/null +++ b/Cargo.lock @@ -0,0 +1,443 @@ +# This file is automatically @generated by Cargo. +# It is not intended for manual editing. +version = 4 + +[[package]] +name = "ahash" +version = "0.8.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75" +dependencies = [ + "cfg-if", + "once_cell", + "version_check", + "zerocopy", +] + +[[package]] +name = "anyhow" +version = "1.0.102" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c" + +[[package]] +name = "bitflags" +version = "2.13.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b4388bee8683e3d04af747c73422af53102d2bd24d9eadb6cbc100baef4b43f8" + +[[package]] +name = "cfg-if" +version = "1.0.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801" + +[[package]] +name = "chain-module-sdk" +version = "0.1.2" +source = "git+https://git.flemming.ai/fai/chain-module-sdk-rust.git?branch=main#98e98e9371f7409560a1ef08bc0923d9a2506449" +dependencies = [ + "chain-module-sdk-macros", + "serde", + "serde_json", + "thiserror", + "wit-bindgen", +] + +[[package]] +name = "chain-module-sdk-macros" +version = "0.1.2" +source = "git+https://git.flemming.ai/fai/chain-module-sdk-rust.git?branch=main#98e98e9371f7409560a1ef08bc0923d9a2506449" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "equivalent" +version = "1.0.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f" + +[[package]] +name = "hashbrown" +version = "0.14.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e5274423e17b7c9fc20b6e7e208532f9b19825d82dfd615708b70edd83df41f1" +dependencies = [ + "ahash", +] + +[[package]] +name = "hashbrown" +version = "0.17.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ed5909b6e89a2db4456e54cd5f673791d7eca6732202bbf2a9cc504fe2f9b84a" + +[[package]] +name = "heck" +version = "0.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea" + +[[package]] +name = "id-arena" +version = "2.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3d3067d79b975e8844ca9eb072e16b31c3c1c36928edf9c6789548c524d0d954" + +[[package]] +name = "indexmap" +version = "2.14.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d466e9454f08e4a911e14806c24e16fba1b4c121d1ea474396f396069cf949d9" +dependencies = [ + "equivalent", + "hashbrown 0.17.1", + "serde", + "serde_core", +] + +[[package]] +name = "itoa" +version = "1.0.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682" + +[[package]] +name = "leb128" +version = "0.2.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c83bff1d572d6b9aeef67ddfc8448e4a3737909cb28e81f97c791b9018703e52" + +[[package]] +name = "log" +version = "0.4.32" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "953f07c43838f8e6f9758cab68bf5bed85465e7587ebe0b823f1bcd81978ad3a" + +[[package]] +name = "memchr" +version = "2.8.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "88904434abc2901f197fe8cc55f0445e7ded921dba5911dad2e2b39b48e663c4" + +[[package]] +name = "once_cell" +version = "1.21.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50" + +[[package]] +name = "prettyplease" +version = "0.2.37" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "479ca8adacdd7ce8f1fb39ce9ecccbfe93a3f1344b3d0d97f20bc0196208f62b" +dependencies = [ + "proc-macro2", + "syn", +] + +[[package]] +name = "proc-macro2" +version = "1.0.106" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8fd00f0bb2e90d81d1044c2b32617f68fcb9fa3bb7640c23e9c748e53fb30934" +dependencies = [ + "unicode-ident", +] + +[[package]] +name = "quote" +version = "1.0.45" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "41f2619966050689382d2b44f664f4bc593e129785a36d6ee376ddf37259b924" +dependencies = [ + "proc-macro2", +] + +[[package]] +name = "semver" +version = "1.0.28" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8a7852d02fc848982e0c167ef163aaff9cd91dc640ba85e263cb1ce46fae51cd" + +[[package]] +name = "serde" +version = "1.0.228" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9a8e94ea7f378bd32cbbd37198a4a91436180c5bb472411e48b5ec2e2124ae9e" +dependencies = [ + "serde_core", + "serde_derive", +] + +[[package]] +name = "serde_core" +version = "1.0.228" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "41d385c7d4ca58e59fc732af25c3983b67ac852c1a25000afe1175de458b67ad" +dependencies = [ + "serde_derive", +] + +[[package]] +name = "serde_derive" +version = "1.0.228" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "serde_json" +version = "1.0.150" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e8014e44b4736ed0538adeecded0fce2a272f22dc9578a7eb6b2d9993c74cfb9" +dependencies = [ + "itoa", + "memchr", + "serde", + "serde_core", + "zmij", +] + +[[package]] +name = "smallvec" +version = "1.15.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8ed6a63f02c8539c91a8685a86f4099661ba3da017932f6ebbea6de3f0fa7c90" + +[[package]] +name = "spdx" +version = "0.10.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c3e17e880bafaeb362a7b751ec46bdc5b61445a188f80e0606e68167cd540fa3" +dependencies = [ + "smallvec", +] + +[[package]] +name = "stats_cohort_size" +version = "0.1.0" +dependencies = [ + "chain-module-sdk", + "serde", + "serde_json", +] + +[[package]] +name = "syn" +version = "2.0.118" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1b9ae57f904213ebb649ce6895b8a66c66f0203b9319718f69a5612a065b1422" +dependencies = [ + "proc-macro2", + "quote", + "unicode-ident", +] + +[[package]] +name = "thiserror" +version = "2.0.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4288b5bcbc7920c07a1149a35cf9590a2aa808e0bc1eafaade0b80947865fbc4" +dependencies = [ + "thiserror-impl", +] + +[[package]] +name = "thiserror-impl" +version = "2.0.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ebc4ee7f67670e9b64d05fa4253e753e016c6c95ff35b89b7941d6b856dec1d5" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "unicode-ident" +version = "1.0.24" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75" + +[[package]] +name = "unicode-xid" +version = "0.2.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ebc1c04c71510c7f702b52b7c350734c9ff1295c464a03335b00bb84fc54f853" + +[[package]] +name = "version_check" +version = "0.9.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a" + +[[package]] +name = "wasm-encoder" +version = "0.220.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e913f9242315ca39eff82aee0e19ee7a372155717ff0eb082c741e435ce25ed1" +dependencies = [ + "leb128", + "wasmparser", +] + +[[package]] +name = "wasm-metadata" +version = "0.220.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "185dfcd27fa5db2e6a23906b54c28199935f71d9a27a1a27b3a88d6fee2afae7" +dependencies = [ + "anyhow", + "indexmap", + "serde", + "serde_derive", + "serde_json", + "spdx", + "wasm-encoder", + "wasmparser", +] + +[[package]] +name = "wasmparser" +version = "0.220.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8d07b6a3b550fefa1a914b6d54fc175dd11c3392da11eee604e6ffc759805d25" +dependencies = [ + "ahash", + "bitflags", + "hashbrown 0.14.5", + "indexmap", + "semver", +] + +[[package]] +name = "wit-bindgen" +version = "0.36.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6a2b3e15cd6068f233926e7d8c7c588b2ec4fb7cc7bf3824115e7c7e2a8485a3" +dependencies = [ + "wit-bindgen-rt", + "wit-bindgen-rust-macro", +] + +[[package]] +name = "wit-bindgen-core" +version = "0.36.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b632a5a0fa2409489bd49c9e6d99fcc61bb3d4ce9d1907d44662e75a28c71172" +dependencies = [ + "anyhow", + "heck", + "wit-parser", +] + +[[package]] +name = "wit-bindgen-rt" +version = "0.36.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7947d0131c7c9da3f01dfde0ab8bd4c4cf3c5bd49b6dba0ae640f1fa752572ea" +dependencies = [ + "bitflags", +] + +[[package]] +name = "wit-bindgen-rust" +version = "0.36.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4329de4186ee30e2ef30a0533f9b3c123c019a237a7c82d692807bf1b3ee2697" +dependencies = [ + "anyhow", + "heck", + "indexmap", + "prettyplease", + "syn", + "wasm-metadata", + "wit-bindgen-core", + "wit-component", +] + +[[package]] +name = "wit-bindgen-rust-macro" +version = "0.36.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "177fb7ee1484d113b4792cc480b1ba57664bbc951b42a4beebe573502135b1fc" +dependencies = [ + "anyhow", + "prettyplease", + "proc-macro2", + "quote", + "syn", + "wit-bindgen-core", + "wit-bindgen-rust", +] + +[[package]] +name = "wit-component" +version = "0.220.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b505603761ed400c90ed30261f44a768317348e49f1864e82ecdc3b2744e5627" +dependencies = [ + "anyhow", + "bitflags", + "indexmap", + "log", + "serde", + "serde_derive", + "serde_json", + "wasm-encoder", + "wasm-metadata", + "wasmparser", + "wit-parser", +] + +[[package]] +name = "wit-parser" +version = "0.220.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ae2a7999ed18efe59be8de2db9cb2b7f84d88b27818c79353dfc53131840fe1a" +dependencies = [ + "anyhow", + "id-arena", + "indexmap", + "log", + "semver", + "serde", + "serde_derive", + "serde_json", + "unicode-xid", + "wasmparser", +] + +[[package]] +name = "zerocopy" +version = "0.8.52" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ce1022995ff5ff5d841ad7d994facc23098cd40152f2c1d11cd607c6f530653f" +dependencies = [ + "zerocopy-derive", +] + +[[package]] +name = "zerocopy-derive" +version = "0.8.52" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1ae7f38b72ec2a254e2b87ef277cf2cd4fb97cbebf944faa6f33354da0867930" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "zmij" +version = "1.0.21" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b8848ee67ecc8aedbaf3e4122217aff892639231befc6a1b58d29fff4c2cabaa" diff --git a/Cargo.toml b/Cargo.toml new file mode 100644 index 0000000..6c79e61 --- /dev/null +++ b/Cargo.toml @@ -0,0 +1,36 @@ +[package] +name = "stats_cohort_size" +version = "0.1.0" +edition = "2024" +authors = ["Dr. Stefan Flemming "] +license = "Apache-2.0" +publish = false +description = "F∆I module — resolve cohort sizes for addressee populations" +repository = "https://git.flemming.ws/chain-modules/stats-cohort-size" +rust-version = "1.85" + +[lib] +crate-type = ["cdylib", "rlib"] + +[dependencies] +chain-module-sdk = { git = "https://git.flemming.ai/fai/chain-module-sdk-rust.git", branch = "main" } +serde = { version = "1", features = ["derive"] } +serde_json = "1" + +[profile.release] +opt-level = "s" +lto = true +codegen-units = 1 +strip = "symbols" + +[lints.rust] +unsafe_op_in_unsafe_fn = "warn" + +[lints.clippy] +unwrap_used = "deny" +expect_used = "deny" +panic = "deny" +print_stdout = "deny" +print_stderr = "deny" + +[workspace] diff --git a/module.yaml b/module.yaml new file mode 100644 index 0000000..6ff61c5 --- /dev/null +++ b/module.yaml @@ -0,0 +1,42 @@ +schema_version: 3 +provider: chain +name: stats-cohort-size +version: 0.1.0 + +# Resolve the size of an addressee cohort (e.g. "Berliner KMU +# nach WZ-Code", "Gastronomie deutschlandweit"). +# +# v0.1.0 ships a built-in stub table for the five pilot cohorts. +# v0.2 adds a DESTATIS GENESIS-API adapter (capability requires +# `net` permission); the API surface here stays identical. +# +# Reuse-lens: any quant analysis that needs cohort sizing — +# market research, audience targeting, public-health tracking. +provides: + - capability: stats.cohort_size + version: 0.1.0 + +inputs: + cohort_id: + type: text + description: + en: | + Cohort identifier. v0.1.0 recognises: + berlin-kmu, de-kmu, gastro-de, handwerk-be, bauwirtschaft-be + de: | + Kohorten-Identifier. v0.1.0 kennt: + berlin-kmu, de-kmu, gastro-de, handwerk-be, bauwirtschaft-be + +outputs: + cohort: + type: json + description: + en: | + { id, count, year, source, tier }. + tier ∈ {T1, T2} — T1 when DESTATIS, T2 when Verband-source. + de: | + { id, count, year, source, tier }. + +# v0.1 stub: no permissions. v0.2 DESTATIS adapter needs: +# net: ["genesis.destatis.de"] +permissions: [] diff --git a/rust-toolchain.toml b/rust-toolchain.toml new file mode 100644 index 0000000..32add0c --- /dev/null +++ b/rust-toolchain.toml @@ -0,0 +1,4 @@ +[toolchain] +channel = "1.86" +targets = ["wasm32-wasip2"] +components = ["rustfmt", "clippy"] diff --git a/src/lib.rs b/src/lib.rs new file mode 100644 index 0000000..df0383e --- /dev/null +++ b/src/lib.rs @@ -0,0 +1,92 @@ +//! `stats.cohort_size` — resolve addressee cohort populations. +//! +//! v0.1.0 ships a five-entry built-in lookup for the pilot +//! corpus. The published numbers carry the tier they originate +//! from (T1 = DESTATIS Unternehmensregister, T2 = Verband). +//! +//! v0.2 plans a DESTATIS GENESIS-API adapter; the input/output +//! interface here stays stable. + +#![allow(clippy::result_large_err)] + +use chain_module_sdk::prelude::*; +use serde::Serialize; + +#[derive(Debug, Serialize)] +struct Cohort { + id: String, + count: u64, + year: u16, + source: &'static str, + tier: &'static str, +} + +#[fai_module] +pub fn invoke(_ctx: Context, inputs: Inputs) -> Result { + let id = inputs.require_text("cohort_id")?; + let cohort = resolve(&id).ok_or_else(|| { + ModuleError::invalid_input(format!( + "unknown cohort_id: {id} (v0.1.0 supports: \ + berlin-kmu, de-kmu, gastro-de, handwerk-be, bauwirtschaft-be)" + )) + })?; + Outputs::new().with_json("cohort", &cohort) +} + +fn resolve(id: &str) -> Option { + match id { + "berlin-kmu" => Some(Cohort { + id: id.into(), + count: 180_000, + year: 2024, + source: "DESTATIS Unternehmensregister 2024 + IHK Berlin", + tier: "T1", + }), + "de-kmu" => Some(Cohort { + id: id.into(), + count: 3_000_000, + year: 2024, + source: "DESTATIS Unternehmensregister 2024", + tier: "T1", + }), + "gastro-de" => Some(Cohort { + id: id.into(), + count: 220_000, + year: 2024, + source: "DEHOGA Jahresbericht 2024", + tier: "T2", + }), + "handwerk-be" => Some(Cohort { + id: id.into(), + count: 32_000, + year: 2024, + source: "Handwerkskammer Berlin Statistik 2024", + tier: "T2", + }), + "bauwirtschaft-be" => Some(Cohort { + id: id.into(), + count: 7_500, + year: 2024, + source: "Bauindustrieverband Berlin-Brandenburg 2024", + tier: "T2", + }), + _ => None, + } +} + +#[cfg(test)] +mod tests { + use super::*; + + #[test] + fn berlin_kmu_resolves() { + let c = resolve("berlin-kmu").expect("known cohort"); + assert_eq!(c.count, 180_000); + assert_eq!(c.tier, "T1"); + } + + #[test] + fn unknown_returns_none() { + assert!(resolve("mars-kolonie").is_none()); + } +}