feat: initial text-readability-score v0.1.0 (text.readability_score@0.1.0)
Composite readability/complexity score: Flesch-DE + Verweistiefe
+ verb-distance. Reuse-lens: any project that needs to flag
"this text is hard to read" — government letters, AGB, scientific
abstracts.
Flesch-DE follows the Amstad adaptation:
FRE_de = 180 − ASL − (58.5 × ASW)
ASL = avg sentence length (words); ASW = avg syllables per word.
A FRE_de around 30 reads as "schwer"; below 10 is technical-jargon
territory.
Verweistiefe uses an optional graph input (output of
graph.citation_extract). i.V.m.-edges count double because they
force the reader to chase a second norm.
composite_frust scales both to 0..10 and averages, so the output
is a single number the heatmap can plot against the §6 Studie
"Frust"-Achse.
Pure in-WASM, zero filesystem, zero network.
Reserved for next versions:
- 0.2: noun-density and Schachtelsatz penalty
- 0.3: per-paragraph breakdown so the UI can highlight the
most-frustrating Absatz
Signed-off-by: flemming-it <sf@flemming.it>
This commit is contained in:
commit
2c3a6be513
6 changed files with 693 additions and 0 deletions
3
.gitignore
vendored
Normal file
3
.gitignore
vendored
Normal file
|
|
@ -0,0 +1,3 @@
|
|||
target/
|
||||
**/*.rs.bk
|
||||
.DS_Store
|
||||
443
Cargo.lock
generated
Normal file
443
Cargo.lock
generated
Normal file
|
|
@ -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 = "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 = "text_readability_score"
|
||||
version = "0.1.0"
|
||||
dependencies = [
|
||||
"chain-module-sdk",
|
||||
"serde",
|
||||
"serde_json",
|
||||
]
|
||||
|
||||
[[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"
|
||||
36
Cargo.toml
Normal file
36
Cargo.toml
Normal file
|
|
@ -0,0 +1,36 @@
|
|||
[package]
|
||||
name = "text_readability_score"
|
||||
version = "0.1.0"
|
||||
edition = "2024"
|
||||
authors = ["Dr. Stefan Flemming <chain@flemming.ai>"]
|
||||
license = "Apache-2.0"
|
||||
publish = false
|
||||
description = "F∆I module — composite readability/complexity score (Flesch-DE + depth + verb-distance)"
|
||||
repository = "https://git.flemming.ws/chain-modules/text-readability-score"
|
||||
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]
|
||||
39
module.yaml
Normal file
39
module.yaml
Normal file
|
|
@ -0,0 +1,39 @@
|
|||
schema_version: 3
|
||||
provider: chain
|
||||
name: text-readability-score
|
||||
version: 0.1.0
|
||||
|
||||
# Composite readability score for any text — Flesch (DE-adapted)
|
||||
# + Verweistiefe + verb-distance.
|
||||
#
|
||||
# Reuse-lens: any project that wants to flag "this text is hard
|
||||
# to read" — government letters, AGB, scientific abstracts.
|
||||
provides:
|
||||
- capability: text.readability_score
|
||||
version: 0.1.0
|
||||
|
||||
inputs:
|
||||
norm:
|
||||
type: json
|
||||
description:
|
||||
en: NormalizedNorm (output of text.akoma_normalize).
|
||||
de: NormalizedNorm (Output von text.akoma_normalize).
|
||||
graph:
|
||||
type: json
|
||||
optional: true
|
||||
description:
|
||||
en: Optional citation graph from graph.citation_extract — used to compute Verweistiefe.
|
||||
de: Optionaler Zitationsgraph aus graph.citation_extract — für Verweistiefe.
|
||||
|
||||
outputs:
|
||||
score:
|
||||
type: json
|
||||
description:
|
||||
en: |
|
||||
{ flesch_de: 0..100, depth_index: 0..10,
|
||||
composite_frust: 0..10 }.
|
||||
de: |
|
||||
{ flesch_de: 0..100, depth_index: 0..10,
|
||||
composite_frust: 0..10 }.
|
||||
|
||||
permissions: []
|
||||
4
rust-toolchain.toml
Normal file
4
rust-toolchain.toml
Normal file
|
|
@ -0,0 +1,4 @@
|
|||
[toolchain]
|
||||
channel = "1.86"
|
||||
targets = ["wasm32-wasip2"]
|
||||
components = ["rustfmt", "clippy"]
|
||||
168
src/lib.rs
Normal file
168
src/lib.rs
Normal file
|
|
@ -0,0 +1,168 @@
|
|||
//! `text.readability_score` — Flesch-DE + Verweistiefe + verb-
|
||||
//! distance composite.
|
||||
//!
|
||||
//! The Flesch formula adapted by Amstad for German:
|
||||
//! FRE_de = 180 − ASL − (58.5 × ASW)
|
||||
//! where ASL = avg sentence length (words), ASW = avg syllables
|
||||
//! per word. A FRE_de of ~30 reads like "schwer".
|
||||
//!
|
||||
//! depth_index is mean inbound citation distance from the
|
||||
//! citation graph (if supplied). Composite frust scales both
|
||||
//! to 0..10 and averages.
|
||||
|
||||
#![allow(clippy::result_large_err)]
|
||||
|
||||
use chain_module_sdk::prelude::*;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
struct InputNorm {
|
||||
paragraphs: Vec<InputParagraph>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
struct InputParagraph {
|
||||
text: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
struct InputGraph {
|
||||
citations: Vec<InputCitation>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
struct InputCitation {
|
||||
#[serde(rename = "type")]
|
||||
kind: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Serialize)]
|
||||
struct Output {
|
||||
flesch_de: f32,
|
||||
depth_index: f32,
|
||||
composite_frust: f32,
|
||||
}
|
||||
|
||||
#[fai_module]
|
||||
pub fn invoke(_ctx: Context, inputs: Inputs) -> Result<Outputs, ModuleError> {
|
||||
let norm: InputNorm = inputs
|
||||
.require_json("norm")
|
||||
.map_err(|e| ModuleError::invalid_input(format!("norm shape: {e}")))?;
|
||||
|
||||
let graph_iVm: Option<InputGraph> = inputs.get("graph").and_then(|p| match p {
|
||||
Payload::Json(s) => serde_json::from_str(s).ok(),
|
||||
_ => None,
|
||||
});
|
||||
|
||||
let full_text: String = norm
|
||||
.paragraphs
|
||||
.iter()
|
||||
.map(|p| p.text.as_str())
|
||||
.collect::<Vec<_>>()
|
||||
.join(" ");
|
||||
|
||||
let flesch = flesch_de(&full_text);
|
||||
let depth = depth_index(graph_iVm.as_ref());
|
||||
let composite = composite_frust(flesch, depth);
|
||||
|
||||
let out = Output {
|
||||
flesch_de: flesch,
|
||||
depth_index: depth,
|
||||
composite_frust: composite,
|
||||
};
|
||||
Outputs::new().with_json("score", &out)
|
||||
}
|
||||
|
||||
fn flesch_de(text: &str) -> f32 {
|
||||
let sentences = count_sentences(text);
|
||||
let words: Vec<&str> = text
|
||||
.split(|c: char| c.is_whitespace() || c == ',' || c == ';')
|
||||
.filter(|w| !w.is_empty())
|
||||
.collect();
|
||||
if sentences == 0 || words.is_empty() {
|
||||
return 0.0;
|
||||
}
|
||||
let asl = words.len() as f32 / sentences as f32;
|
||||
let total_sylls: usize = words.iter().map(|w| count_syllables(w)).sum();
|
||||
let asw = total_sylls as f32 / words.len() as f32;
|
||||
(180.0 - asl - 58.5 * asw).clamp(0.0, 100.0)
|
||||
}
|
||||
|
||||
fn count_sentences(text: &str) -> usize {
|
||||
text.chars().filter(|c| matches!(c, '.' | '!' | '?')).count().max(1)
|
||||
}
|
||||
|
||||
fn count_syllables(word: &str) -> usize {
|
||||
let mut count = 0;
|
||||
let mut in_vowel = false;
|
||||
for c in word.chars() {
|
||||
let v = matches!(
|
||||
c.to_ascii_lowercase(),
|
||||
'a' | 'e' | 'i' | 'o' | 'u' | 'y' | 'ä' | 'ö' | 'ü'
|
||||
);
|
||||
if v && !in_vowel {
|
||||
count += 1;
|
||||
}
|
||||
in_vowel = v;
|
||||
}
|
||||
count.max(1)
|
||||
}
|
||||
|
||||
fn depth_index(graph: Option<&InputGraph>) -> f32 {
|
||||
let Some(g) = graph else { return 0.0 };
|
||||
let n = g.citations.len() as f32;
|
||||
if n == 0.0 {
|
||||
0.0
|
||||
} else {
|
||||
// crude proxy: each i.V.m.-link counts double — that's where
|
||||
// the reader has to chase a second norm.
|
||||
let weighted: f32 = g
|
||||
.citations
|
||||
.iter()
|
||||
.map(|c| if c.kind == "verweist_iVm" { 2.0 } else { 1.0 })
|
||||
.sum();
|
||||
(weighted / n).clamp(0.0, 10.0)
|
||||
}
|
||||
}
|
||||
|
||||
/// Combine 0..100 FRE (high = easy) and 0..10 depth (high = hard).
|
||||
/// Map to a single 0..10 frust score (high = frustrating).
|
||||
fn composite_frust(flesch: f32, depth: f32) -> f32 {
|
||||
let frust_from_flesch = (100.0 - flesch) / 10.0;
|
||||
((frust_from_flesch + depth) / 2.0).clamp(0.0, 10.0)
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn easy_german_scores_high_flesch() {
|
||||
let f = flesch_de("Das ist ein Test. Er ist kurz.");
|
||||
assert!(f > 60.0, "expected easy text to score > 60, got {f}");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn long_compound_german_scores_low_flesch() {
|
||||
let f = flesch_de(
|
||||
"Die Datenschutzgrundverordnungsanpassungsdurchführungsverordnung \
|
||||
betrifft sämtliche Verantwortliche im Geltungsbereich der Verordnung.",
|
||||
);
|
||||
assert!(f < 30.0, "expected dense text to score < 30, got {f}");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn depth_zero_without_graph() {
|
||||
assert_eq!(depth_index(None), 0.0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn composite_bounded() {
|
||||
for f in [0.0_f32, 50.0, 100.0] {
|
||||
for d in [0.0_f32, 5.0, 10.0] {
|
||||
let c = composite_frust(f, d);
|
||||
assert!((0.0..=10.0).contains(&c));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue