feat: Alpha-ID-SE corpus parser with code normalization
This commit is contained in:
+43
-1
@@ -1 +1,43 @@
|
||||
// implemented in a later task
|
||||
use crate::model::{AlphaIdEntry, AppError};
|
||||
|
||||
/// Normalize an ICD code field by removing classification marks.
|
||||
pub fn normalize_code(raw: &str) -> String {
|
||||
raw.trim().trim_end_matches(['+', '*', '!']).trim().to_string()
|
||||
}
|
||||
|
||||
pub fn parse_line(line: &str) -> Option<AlphaIdEntry> {
|
||||
let f: Vec<&str> = line.split('|').collect();
|
||||
if f.len() < 8 { return None; }
|
||||
Some(AlphaIdEntry {
|
||||
valid: f[0].trim() == "1",
|
||||
alpha_id: f[1].trim().to_string(),
|
||||
icd_primary: normalize_code(f[2]),
|
||||
icd_star: normalize_code(f[3]),
|
||||
icd_addon: normalize_code(f[4]),
|
||||
icd_primary2: normalize_code(f[5]),
|
||||
orpha: f[6].trim().to_string(),
|
||||
text: f[7].trim().to_string(),
|
||||
})
|
||||
}
|
||||
|
||||
pub fn load(path: &str) -> Result<Vec<AlphaIdEntry>, AppError> {
|
||||
let raw = std::fs::read_to_string(path)
|
||||
.map_err(|e| AppError::Io(format!("{path}: {e}")))?;
|
||||
let entries: Vec<AlphaIdEntry> = raw
|
||||
.lines()
|
||||
.filter(|l| !l.trim().is_empty())
|
||||
.filter_map(parse_line)
|
||||
.collect();
|
||||
if entries.is_empty() {
|
||||
return Err(AppError::Parse(format!("no entries parsed from {path}")));
|
||||
}
|
||||
Ok(entries)
|
||||
}
|
||||
|
||||
/// The primary ICD code a matched entry contributes (falls back to star/addon).
|
||||
pub fn primary_code(e: &AlphaIdEntry) -> Option<&str> {
|
||||
for c in [&e.icd_primary, &e.icd_primary2, &e.icd_star, &e.icd_addon] {
|
||||
if !c.is_empty() { return Some(c); }
|
||||
}
|
||||
None
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user