From 27d51448643cb104cdb42a6c04b1660d02b0e262 Mon Sep 17 00:00:00 2001
From: Brummel <mould@mycelium.de>
Date: Mon, 18 May 2026 16:38:21 +0200
Subject: [PATCH] feat: dictation segmentation on blank lines

---
 src/segment.rs         | 21 ++++++++++++++++++++-
 tests/segment_tests.rs | 22 ++++++++++++++++++++++
 2 files changed, 42 insertions(+), 1 deletion(-)
 create mode 100644 tests/segment_tests.rs

diff --git a/src/segment.rs b/src/segment.rs
index 4b0fd9d..8cd36fd 100644
--- a/src/segment.rs
+++ b/src/segment.rs
@@ -1 +1,20 @@
-// implemented in a later task
+/// Split a dictation into Befund segments on Markdown paragraph
+/// breaks (one or more blank lines). Trims each segment; drops empties.
+pub fn split_segments(dictation: &str) -> Vec<String> {
+    let mut segments = Vec::new();
+    let mut current: Vec<&str> = Vec::new();
+    for line in dictation.lines() {
+        if line.trim().is_empty() {
+            if !current.is_empty() {
+                segments.push(current.join("\n").trim().to_string());
+                current.clear();
+            }
+        } else {
+            current.push(line);
+        }
+    }
+    if !current.is_empty() {
+        segments.push(current.join("\n").trim().to_string());
+    }
+    segments.into_iter().filter(|s| !s.is_empty()).collect()
+}
diff --git a/tests/segment_tests.rs b/tests/segment_tests.rs
new file mode 100644
index 0000000..564f8c6
--- /dev/null
+++ b/tests/segment_tests.rs
@@ -0,0 +1,22 @@
+use alpha_id::segment::split_segments;
+
+#[test]
+fn splits_on_blank_lines() {
+    let d = "Befund eins\nmit Zeile zwei\n\nBefund zwei\n\n\nBefund drei\n";
+    let segs = split_segments(d);
+    assert_eq!(segs, vec![
+        "Befund eins\nmit Zeile zwei".to_string(),
+        "Befund zwei".to_string(),
+        "Befund drei".to_string(),
+    ]);
+}
+
+#[test]
+fn single_segment_when_no_blank_line() {
+    assert_eq!(split_segments("nur ein Befund"), vec!["nur ein Befund".to_string()]);
+}
+
+#[test]
+fn empty_input_yields_no_segments() {
+    assert!(split_segments("   \n\n").is_empty());
+}