fix(kon): normalise British English table, single-pass whitespace collapse, byte-index safety
- Normalise BRITISH_REPLACEMENTS: remove baked-in \b from entries so all entries are plain base words; the function adds boundaries uniformly - Replace O(n*m) while-loop double-space removal with single-pass collapse - Add debug_assert! documenting ASCII assumption for byte-indexed suffix slicing - Expand llm_client.rs module-level doc comment - Run cargo fmt on ai-formatting crate Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -31,10 +31,7 @@ impl FormatMode {
|
||||
|
||||
/// Apply all post-processing steps to a list of segments.
|
||||
/// Modifies segments in place. Composed from individual pure functions.
|
||||
pub fn post_process_segments(
|
||||
segments: &mut Vec<Segment>,
|
||||
options: &PostProcessOptions,
|
||||
) {
|
||||
pub fn post_process_segments(segments: &mut Vec<Segment>, options: &PostProcessOptions) {
|
||||
if options.anti_hallucination {
|
||||
segments.retain(|seg| !rule_based::is_hallucination(&seg.text));
|
||||
}
|
||||
@@ -55,8 +52,7 @@ pub fn post_process_segments(
|
||||
for i in (1..segments.len()).rev() {
|
||||
let gap = segments[i].start - segments[i - 1].end;
|
||||
if gap > SMART_PARAGRAPH_GAP_SECS {
|
||||
segments[i].text =
|
||||
format!("\n\n{}", segments[i].text.trim_start());
|
||||
segments[i].text = format!("\n\n{}", segments[i].text.trim_start());
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user