Files
gitlore/src/documents/extractor/discussions.rs

217 lines
7.6 KiB
Rust

pub fn extract_discussion_document(
conn: &Connection,
discussion_id: i64,
) -> Result<Option<DocumentData>> {
let disc_row = conn.query_row(
"SELECT d.id, d.noteable_type, d.issue_id, d.merge_request_id,
p.path_with_namespace, p.id AS project_id
FROM discussions d
JOIN projects p ON p.id = d.project_id
WHERE d.id = ?1",
rusqlite::params![discussion_id],
|row| {
Ok((
row.get::<_, i64>(0)?,
row.get::<_, String>(1)?,
row.get::<_, Option<i64>>(2)?,
row.get::<_, Option<i64>>(3)?,
row.get::<_, String>(4)?,
row.get::<_, i64>(5)?,
))
},
);
let (id, noteable_type, issue_id, merge_request_id, path_with_namespace, project_id) =
match disc_row {
Ok(r) => r,
Err(rusqlite::Error::QueryReturnedNoRows) => return Ok(None),
Err(e) => return Err(e.into()),
};
let (_parent_iid, parent_title, parent_web_url, parent_type_prefix, labels) =
match noteable_type.as_str() {
"Issue" => {
let parent_id = match issue_id {
Some(pid) => pid,
None => return Ok(None),
};
let parent = conn.query_row(
"SELECT i.iid, i.title, i.web_url FROM issues i WHERE i.id = ?1",
rusqlite::params![parent_id],
|row| {
Ok((
row.get::<_, i64>(0)?,
row.get::<_, Option<String>>(1)?,
row.get::<_, Option<String>>(2)?,
))
},
);
let (iid, title, web_url) = match parent {
Ok(r) => r,
Err(rusqlite::Error::QueryReturnedNoRows) => return Ok(None),
Err(e) => return Err(e.into()),
};
let mut label_stmt = conn.prepare_cached(
"SELECT l.name FROM issue_labels il
JOIN labels l ON l.id = il.label_id
WHERE il.issue_id = ?1
ORDER BY l.name",
)?;
let labels: Vec<String> = label_stmt
.query_map(rusqlite::params![parent_id], |row| row.get(0))?
.collect::<std::result::Result<Vec<_>, _>>()?;
(iid, title, web_url, format!("Issue #{}", iid), labels)
}
"MergeRequest" => {
let parent_id = match merge_request_id {
Some(pid) => pid,
None => return Ok(None),
};
let parent = conn.query_row(
"SELECT m.iid, m.title, m.web_url FROM merge_requests m WHERE m.id = ?1",
rusqlite::params![parent_id],
|row| {
Ok((
row.get::<_, i64>(0)?,
row.get::<_, Option<String>>(1)?,
row.get::<_, Option<String>>(2)?,
))
},
);
let (iid, title, web_url) = match parent {
Ok(r) => r,
Err(rusqlite::Error::QueryReturnedNoRows) => return Ok(None),
Err(e) => return Err(e.into()),
};
let mut label_stmt = conn.prepare_cached(
"SELECT l.name FROM mr_labels ml
JOIN labels l ON l.id = ml.label_id
WHERE ml.merge_request_id = ?1
ORDER BY l.name",
)?;
let labels: Vec<String> = label_stmt
.query_map(rusqlite::params![parent_id], |row| row.get(0))?
.collect::<std::result::Result<Vec<_>, _>>()?;
(iid, title, web_url, format!("MR !{}", iid), labels)
}
_ => return Ok(None),
};
let mut note_stmt = conn.prepare_cached(
"SELECT n.author_username, n.body, n.created_at, n.gitlab_id,
n.note_type, n.position_old_path, n.position_new_path
FROM notes n
WHERE n.discussion_id = ?1 AND n.is_system = 0
ORDER BY n.created_at ASC, n.id ASC",
)?;
struct NoteRow {
author: Option<String>,
body: Option<String>,
created_at: i64,
gitlab_id: i64,
old_path: Option<String>,
new_path: Option<String>,
}
let notes: Vec<NoteRow> = note_stmt
.query_map(rusqlite::params![id], |row| {
Ok(NoteRow {
author: row.get(0)?,
body: row.get(1)?,
created_at: row.get(2)?,
gitlab_id: row.get(3)?,
old_path: row.get(5)?,
new_path: row.get(6)?,
})
})?
.collect::<std::result::Result<Vec<_>, _>>()?;
if notes.is_empty() {
return Ok(None);
}
let mut path_set = BTreeSet::new();
for note in &notes {
if let Some(ref p) = note.old_path
&& !p.is_empty()
{
path_set.insert(p.clone());
}
if let Some(ref p) = note.new_path
&& !p.is_empty()
{
path_set.insert(p.clone());
}
}
let paths: Vec<String> = path_set.into_iter().collect();
let first_note_gitlab_id = notes[0].gitlab_id;
let url = parent_web_url
.as_ref()
.map(|wu| format!("{}#note_{}", wu, first_note_gitlab_id));
let author_username = notes[0].author.clone();
let display_title = parent_title.as_deref().unwrap_or("(untitled)");
let labels_json = serde_json::to_string(&labels).unwrap_or_else(|_| "[]".to_string());
let paths_json = serde_json::to_string(&paths).unwrap_or_else(|_| "[]".to_string());
let mut content = format!(
"[[Discussion]] {}: {}\nProject: {}\n",
parent_type_prefix, display_title, path_with_namespace
);
if let Some(ref u) = url {
let _ = writeln!(content, "URL: {}", u);
}
let _ = writeln!(content, "Labels: {}", labels_json);
if !paths.is_empty() {
let _ = writeln!(content, "Files: {}", paths_json);
}
let note_contents: Vec<NoteContent> = notes
.iter()
.map(|note| NoteContent {
author: note.author.as_deref().unwrap_or("unknown").to_string(),
date: format_date(note.created_at),
body: note.body.as_deref().unwrap_or("").to_string(),
})
.collect();
let header_len = content.len() + "\n--- Thread ---\n\n".len();
let thread_budget = MAX_DISCUSSION_BYTES.saturating_sub(header_len);
let thread_result = truncate_discussion(&note_contents, thread_budget);
content.push_str("\n--- Thread ---\n\n");
content.push_str(&thread_result.content);
let created_at = notes[0].created_at;
let updated_at = notes.last().map(|n| n.created_at).unwrap_or(created_at);
let content_hash = compute_content_hash(&content);
let labels_hash = compute_list_hash(&labels);
let paths_hash = compute_list_hash(&paths);
Ok(Some(DocumentData {
source_type: SourceType::Discussion,
source_id: id,
project_id,
author_username,
labels,
paths,
labels_hash,
paths_hash,
created_at,
updated_at,
url,
title: None,
content_text: content,
content_hash,
is_truncated: thread_result.is_truncated,
truncated_reason: thread_result.reason.map(|r| r.as_str().to_string()),
}))
}