Compare commits
No commits in common. "2375dd6aa8efc7cf6ee518901bb1466f6ce506c4" and "37e39c26ee3d2a668626154017404bdb32d0fb50" have entirely different histories.
2375dd6aa8
...
37e39c26ee
3 changed files with 8 additions and 88 deletions
|
|
@ -1,66 +0,0 @@
|
||||||
name: CI
|
|
||||||
|
|
||||||
on:
|
|
||||||
push:
|
|
||||||
branches: [main]
|
|
||||||
pull_request:
|
|
||||||
branches: [main]
|
|
||||||
|
|
||||||
env:
|
|
||||||
CARGO_TERM_COLOR: always
|
|
||||||
RUSTFLAGS: "-D warnings"
|
|
||||||
RUST_TOOLCHAIN: "1.86"
|
|
||||||
CARGO_NET_GIT_FETCH_WITH_CLI: "true"
|
|
||||||
|
|
||||||
jobs:
|
|
||||||
ci:
|
|
||||||
name: Linux x86_64 (Forgejo)
|
|
||||||
runs-on: ubuntu-latest
|
|
||||||
steps:
|
|
||||||
- name: Checkout text-deontic-extract via external URL
|
|
||||||
run: |
|
|
||||||
set -eu
|
|
||||||
mkdir -p "$GITHUB_WORKSPACE"
|
|
||||||
cd "$GITHUB_WORKSPACE"
|
|
||||||
git init -q
|
|
||||||
git remote add origin \
|
|
||||||
"https://x-access-token:${GITHUB_TOKEN}@git.flemming.ws/${GITHUB_REPOSITORY}.git"
|
|
||||||
git fetch --depth=1 origin "$GITHUB_SHA"
|
|
||||||
git checkout -q FETCH_HEAD
|
|
||||||
|
|
||||||
- name: Configure git URL rewrite for SDK fetch
|
|
||||||
env:
|
|
||||||
SDK_PAT: ${{ secrets.MODULE_SDK_PAT }}
|
|
||||||
run: |
|
|
||||||
git config --global \
|
|
||||||
"url.https://x-access-token:${SDK_PAT}@git.flemming.ws/.insteadOf" \
|
|
||||||
"https://git.flemming.ws/"
|
|
||||||
|
|
||||||
- name: Install system dependencies
|
|
||||||
run: |
|
|
||||||
apt-get update -qq
|
|
||||||
apt-get install -y --no-install-recommends \
|
|
||||||
curl ca-certificates build-essential pkg-config libssl-dev git
|
|
||||||
|
|
||||||
- name: Install Rust toolchain
|
|
||||||
run: |
|
|
||||||
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs \
|
|
||||||
| sh -s -- -y --profile minimal \
|
|
||||||
--default-toolchain "$RUST_TOOLCHAIN" \
|
|
||||||
--target wasm32-wasip2 --component rustfmt --component clippy
|
|
||||||
echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
|
|
||||||
|
|
||||||
- name: Cargo fmt --check
|
|
||||||
run: cargo fmt --all -- --check
|
|
||||||
|
|
||||||
- name: Cargo clippy
|
|
||||||
run: cargo clippy --all-targets -- -D warnings
|
|
||||||
|
|
||||||
- name: Cargo build (host)
|
|
||||||
run: cargo build --all-targets
|
|
||||||
|
|
||||||
- name: Cargo test (host)
|
|
||||||
run: cargo test --all-targets
|
|
||||||
|
|
||||||
- name: Cargo build (wasm32-wasip2)
|
|
||||||
run: cargo build --release --target wasm32-wasip2
|
|
||||||
BIN
module.wasm
BIN
module.wasm
Binary file not shown.
30
src/lib.rs
30
src/lib.rs
|
|
@ -22,7 +22,6 @@ use serde::{Deserialize, Serialize};
|
||||||
|
|
||||||
#[derive(Debug, Deserialize)]
|
#[derive(Debug, Deserialize)]
|
||||||
struct InputNorm {
|
struct InputNorm {
|
||||||
#[allow(dead_code)]
|
|
||||||
eli: Option<String>,
|
eli: Option<String>,
|
||||||
jurabk: Option<String>,
|
jurabk: Option<String>,
|
||||||
paragraph: Option<String>,
|
paragraph: Option<String>,
|
||||||
|
|
@ -91,10 +90,7 @@ pub fn invoke(_ctx: Context, inputs: Inputs) -> Result<Outputs, ModuleError> {
|
||||||
} else {
|
} else {
|
||||||
duties.iter().map(|d| d.confidence).sum::<f32>() / duties.len() as f32
|
duties.iter().map(|d| d.confidence).sum::<f32>() / duties.len() as f32
|
||||||
};
|
};
|
||||||
let out = Output {
|
let out = Output { duties, avg_confidence: avg };
|
||||||
duties,
|
|
||||||
avg_confidence: avg,
|
|
||||||
};
|
|
||||||
Outputs::new().with_json("duties", &out)
|
Outputs::new().with_json("duties", &out)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
@ -106,11 +102,7 @@ fn compile_patterns() -> Result<Vec<(&'static str, f32, Regex)>, ModuleError> {
|
||||||
(MOD_OBLIGATION, 0.85, r"\bsind\s+verpflichtet\b"),
|
(MOD_OBLIGATION, 0.85, r"\bsind\s+verpflichtet\b"),
|
||||||
(MOD_OBLIGATION, 0.80, r"\b(?:ist|sind)\s+anzuzeigen\b"),
|
(MOD_OBLIGATION, 0.80, r"\b(?:ist|sind)\s+anzuzeigen\b"),
|
||||||
(MOD_OBLIGATION, 0.80, r"\baufzuzeichnen\b"),
|
(MOD_OBLIGATION, 0.80, r"\baufzuzeichnen\b"),
|
||||||
(
|
(MOD_OBLIGATION, 0.80, r"\b(?:muss|müssen)\s+\w+\s+(?:eingehalten|gef[uü]hrt|gemeldet|nachgewiesen)\b"),
|
||||||
MOD_OBLIGATION,
|
|
||||||
0.80,
|
|
||||||
r"\b(?:muss|müssen)\s+\w+\s+(?:eingehalten|gef[uü]hrt|gemeldet|nachgewiesen)\b",
|
|
||||||
),
|
|
||||||
(MOD_PROHIBITION, 0.85, r"\bdarf\s+(?:nicht|kein)\b"),
|
(MOD_PROHIBITION, 0.85, r"\bdarf\s+(?:nicht|kein)\b"),
|
||||||
(MOD_PROHIBITION, 0.85, r"\bd[uü]rfen\s+(?:nicht|kein)\b"),
|
(MOD_PROHIBITION, 0.85, r"\bd[uü]rfen\s+(?:nicht|kein)\b"),
|
||||||
(MOD_PROHIBITION, 0.85, r"\b(?:ist|sind)\s+untersagt\b"),
|
(MOD_PROHIBITION, 0.85, r"\b(?:ist|sind)\s+untersagt\b"),
|
||||||
|
|
@ -121,15 +113,16 @@ fn compile_patterns() -> Result<Vec<(&'static str, f32, Regex)>, ModuleError> {
|
||||||
];
|
];
|
||||||
let mut out = Vec::with_capacity(raw.len());
|
let mut out = Vec::with_capacity(raw.len());
|
||||||
for (m, c, src) in raw {
|
for (m, c, src) in raw {
|
||||||
let re = Regex::new(src)
|
let re = Regex::new(src).map_err(|e| {
|
||||||
.map_err(|e| ModuleError::invalid_input(format!("internal regex compile: {e}")))?;
|
ModuleError::invalid_input(format!("internal regex compile: {e}"))
|
||||||
|
})?;
|
||||||
out.push((m, c, re));
|
out.push((m, c, re));
|
||||||
}
|
}
|
||||||
Ok(out)
|
Ok(out)
|
||||||
}
|
}
|
||||||
|
|
||||||
fn split_sentences(text: &str) -> Vec<&str> {
|
fn split_sentences(text: &str) -> Vec<&str> {
|
||||||
text.split_terminator(['.', ';', '\n'])
|
text.split_terminator(|c: char| c == '.' || c == ';' || c == '\n')
|
||||||
.map(str::trim)
|
.map(str::trim)
|
||||||
.filter(|s| !s.is_empty() && s.len() > 4)
|
.filter(|s| !s.is_empty() && s.len() > 4)
|
||||||
.collect()
|
.collect()
|
||||||
|
|
@ -137,7 +130,6 @@ fn split_sentences(text: &str) -> Vec<&str> {
|
||||||
|
|
||||||
#[cfg(test)]
|
#[cfg(test)]
|
||||||
mod tests {
|
mod tests {
|
||||||
#![allow(clippy::unwrap_used, clippy::expect_used, clippy::panic)]
|
|
||||||
use super::*;
|
use super::*;
|
||||||
|
|
||||||
fn norm(paragraphs: Vec<(&str, &str)>) -> serde_json::Value {
|
fn norm(paragraphs: Vec<(&str, &str)>) -> serde_json::Value {
|
||||||
|
|
@ -177,10 +169,7 @@ mod tests {
|
||||||
} else {
|
} else {
|
||||||
duties.iter().map(|d| d.confidence).sum::<f32>() / duties.len() as f32
|
duties.iter().map(|d| d.confidence).sum::<f32>() / duties.len() as f32
|
||||||
};
|
};
|
||||||
Output {
|
Output { duties, avg_confidence: avg }
|
||||||
duties,
|
|
||||||
avg_confidence: avg,
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
|
||||||
#[test]
|
#[test]
|
||||||
|
|
@ -204,10 +193,7 @@ mod tests {
|
||||||
|
|
||||||
#[test]
|
#[test]
|
||||||
fn no_duty_means_zero_avg() {
|
fn no_duty_means_zero_avg() {
|
||||||
let result = extract(norm(vec![(
|
let result = extract(norm(vec![("(1)", "Dieser Satz enthält nichts Deontisches.")]));
|
||||||
"(1)",
|
|
||||||
"Dieser Satz enthält nichts Deontisches.",
|
|
||||||
)]));
|
|
||||||
assert_eq!(result.duties.len(), 0);
|
assert_eq!(result.duties.len(), 0);
|
||||||
assert_eq!(result.avg_confidence, 0.0);
|
assert_eq!(result.avg_confidence, 0.0);
|
||||||
}
|
}
|
||||||
|
|
|
||||||
Loading…
Add table
Add a link
Reference in a new issue