goosedump 0.2.1

Coding agent context data browser
// SPDX-License-Identifier: LGPL-2.1-or-later
// Copyright (C) Jarkko Sakkinen 2026

use crate::display;
use crate::message::{ConversationMessage, SearchHit};
use crate::text;
use regex::Regex;
use std::collections::HashMap;

const BM25_K1: f64 = 1.5;
const BM25_B: f64 = 0.75;
const PROXIMITY_FACTOR: f64 = 2.0;

#[allow(clippy::cast_precision_loss)]
fn usize_as_f64(value: usize) -> f64 {
    value as f64
}

#[allow(clippy::cast_precision_loss)]
fn fuzzy_score_as_f64(value: isize) -> f64 {
    value as f64
}

fn build_fuzzy_hit(msg: &ConversationMessage, query: &str) -> Option<SearchHit> {
    let searchable = display::searchable_text(msg);
    let m = sublime_fuzzy::best_match(query, &searchable)?;
    let role = msg.role_label();
    let snippet = fuzzy_snippet(&searchable, m.matched_indices().next().copied(), 2);
    let files = display::message_files(msg);
    Some(SearchHit {
        entry_id: msg.entry_id.clone(),
        score: fuzzy_score_as_f64(m.score()),
        role,
        text: snippet,
        files,
    })
}

fn fuzzy_snippet(text: &str, first_match: Option<usize>, context_lines: usize) -> String {
    let Some(pos) = first_match else {
        return text::clip(text, 200);
    };
    let lines: Vec<&str> = text.split('\n').collect();
    let mut char_count = 0;
    for (i, line) in lines.iter().enumerate() {
        char_count += line.len() + 1;
        if char_count > pos {
            return line_snippet_at(&lines, i, context_lines);
        }
    }
    text::clip(text, 200)
}

fn line_snippet_at(lines: &[&str], match_idx: usize, context_lines: usize) -> String {
    let start = match_idx.saturating_sub(context_lines);
    let end = (match_idx + context_lines + 1).min(lines.len());
    let mut out = Vec::new();

    if start > 0 {
        out.push(format!("...({start} lines above)"));
    }
    for line in &lines[start..end] {
        out.push(line.to_string());
    }
    if end < lines.len() {
        out.push(format!("...({} lines below)", lines.len() - end));
    }
    out.join("\n")
}

fn min_span_all(positions: &[Vec<usize>]) -> usize {
    let mut all: Vec<(usize, usize)> = Vec::new();
    for (term_idx, pos_list) in positions.iter().enumerate() {
        for &pos in pos_list {
            all.push((pos, term_idx));
        }
    }
    all.sort_by_key(|(pos, _)| *pos);

    let num_terms = positions.len();
    let mut counts = vec![0usize; num_terms];
    let mut matched = 0;
    let mut left = 0;
    let mut min_span = usize::MAX;

    for right in 0..all.len() {
        let term_idx = all[right].1;
        if counts[term_idx] == 0 {
            matched += 1;
        }
        counts[term_idx] += 1;

        while matched == num_terms {
            let span = all[right].0 - all[left].0 + 1;
            min_span = min_span.min(span);

            let left_term = all[left].1;
            counts[left_term] -= 1;
            if counts[left_term] == 0 {
                matched -= 1;
            }
            left += 1;
        }
    }

    min_span
}

fn adjacent_fallback(
    messages: &[ConversationMessage],
    tokenized: &[Vec<String>],
    terms: &[String],
    page: usize,
    page_size: usize,
) -> (Vec<SearchHit>, usize) {
    let hits: Vec<SearchHit> = tokenized
        .iter()
        .enumerate()
        .filter_map(|(i, msg_words)| {
            let word_set: std::collections::HashSet<&str> =
                msg_words.iter().map(std::string::String::as_str).collect();
            let matching_pairs = terms
                .windows(2)
                .filter(|pair| {
                    word_set.contains(pair[0].as_str()) && word_set.contains(pair[1].as_str())
                })
                .count();
            if matching_pairs == 0 {
                return None;
            }
            let msg = &messages[i];
            let role = msg.role_label();
            let searchable = display::searchable_text(msg);
            let snippet = text::line_snippet_terms(&searchable, terms, 2);
            let files = display::message_files(msg);
            Some(SearchHit {
                entry_id: msg.entry_id.clone(),
                score: usize_as_f64(matching_pairs),
                role,
                text: snippet,
                files,
            })
        })
        .collect();

    sort_and_page(hits, page, page_size)
}

fn build_regex_hit(msg: &ConversationMessage, regex: &Regex) -> Option<SearchHit> {
    let searchable = display::searchable_text(msg);
    let match_count = regex.find_iter(&searchable).count();
    if match_count == 0 {
        return None;
    }
    let role = msg.role_label();
    let snippet = text::line_snippet_regex(&searchable, regex, 2);
    let files = display::message_files(msg);
    Some(SearchHit {
        entry_id: msg.entry_id.clone(),
        score: usize_as_f64(match_count),
        role,
        text: snippet,
        files,
    })
}

fn sort_and_page(
    mut hits: Vec<SearchHit>,
    page: usize,
    page_size: usize,
) -> (Vec<SearchHit>, usize) {
    hits.sort_by(|a, b| {
        b.score
            .partial_cmp(&a.score)
            .unwrap_or(std::cmp::Ordering::Equal)
    });
    let total = hits.len();
    let start = (page.saturating_sub(1)) * page_size;
    if start >= total {
        return (Vec::new(), total);
    }
    (
        hits[start..std::cmp::min(start + page_size, total)].to_vec(),
        total,
    )
}

pub fn grep(messages: &[ConversationMessage], pattern: &str) -> Vec<SearchHit> {
    let Some(regex) = text::make_regex(pattern) else {
        return Vec::new();
    };
    messages
        .iter()
        .filter_map(|msg| build_regex_hit(msg, &regex))
        .collect()
}

pub fn query(
    messages: &[ConversationMessage],
    query_str: &str,
    page: usize,
    page_size: usize,
) -> (Vec<SearchHit>, usize) {
    if text::looks_like_regex(query_str) {
        let hits: Vec<SearchHit> = messages
            .iter()
            .filter_map(|msg| build_fuzzy_hit(msg, query_str))
            .collect();
        sort_and_page(hits, page, page_size)
    } else {
        let words = text::split_words(query_str);
        let terms: Vec<String> = words
            .into_iter()
            .filter(|w| w.len() > 1 && !text::is_stop_word(w))
            .collect();

        if terms.is_empty() {
            return (Vec::new(), 0);
        }

        let n = usize_as_f64(messages.len());
        let mut df: HashMap<String, usize> = HashMap::new();
        let mut tokenized: Vec<Vec<String>> = Vec::with_capacity(messages.len());
        let mut doc_lengths: Vec<usize> = Vec::with_capacity(messages.len());
        let mut total_words: usize = 0;

        for msg in messages {
            let searchable = display::searchable_text(msg);
            let msg_words: Vec<String> = text::split_words(&searchable)
                .into_iter()
                .map(|w| w.to_ascii_lowercase())
                .collect();

            let dl = msg_words.len();
            doc_lengths.push(dl);
            total_words += dl;

            let word_set: std::collections::HashSet<&str> =
                msg_words.iter().map(std::string::String::as_str).collect();
            for term in &terms {
                if word_set.contains(term.as_str()) {
                    *df.entry(term.clone()).or_insert(0) += 1;
                }
            }
            tokenized.push(msg_words);
        }

        let avgdl = if n > 0.0 {
            usize_as_f64(total_words) / n
        } else {
            0.0
        };

        let hits: Vec<SearchHit> = messages
            .iter()
            .enumerate()
            .filter_map(|(i, msg)| {
                let msg_words = &tokenized[i];
                let dl = usize_as_f64(doc_lengths[i]);
                let len_norm = 1.0 - BM25_B + BM25_B * (dl / avgdl.max(1.0));

                let mut score = 0.0;
                let mut term_positions: Vec<Vec<usize>> = Vec::with_capacity(terms.len());

                for term in &terms {
                    let positions: Vec<usize> = msg_words
                        .iter()
                        .enumerate()
                        .filter(|(_, w)| w.as_str() == term)
                        .map(|(i, _)| i)
                        .collect();
                    let tf = positions.len();
                    if tf == 0 {
                        continue;
                    }
                    term_positions.push(positions);
                    let df_val = usize_as_f64(*df.get(term).unwrap_or(&1));
                    let idf = ((n - df_val + 0.5) / (df_val + 0.5)).ln() + 1.0;
                    let tf = usize_as_f64(tf);
                    let tf_score = (tf * (BM25_K1 + 1.0)) / (tf + BM25_K1 * len_norm);
                    score += idf * tf_score;
                }

                if score > 0.0 && term_positions.len() > 1 {
                    let min_span = min_span_all(&term_positions).max(1);
                    score *= 1.0 + PROXIMITY_FACTOR / (1.0 + usize_as_f64(min_span));
                }

                if score == 0.0 {
                    return None;
                }

                let role = msg.role_label();

                let searchable = display::searchable_text(msg);
                let snippet = text::line_snippet_terms(&searchable, &terms, 2);
                let files = display::message_files(msg);

                Some(SearchHit {
                    entry_id: msg.entry_id.clone(),
                    score,
                    role,
                    text: snippet,
                    files,
                })
            })
            .collect();

        let (hits, total) = sort_and_page(hits, page, page_size);
        if hits.is_empty() && total == 0 && terms.len() >= 2 {
            return adjacent_fallback(messages, &tokenized, &terms, page, page_size);
        }
        (hits, total)
    }
}