Skip to content

fix(cli): sanitize query to prevent fts5 errors #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
lmntrixace wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix(cli): sanitize query to prevent fts5 errors #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion crates/ctxgraph-cli/src/commands/query.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,10 @@ pub fn run(
_source: Option<String>,
) -> ctxgraph::Result<()> {
let graph = open_graph()?;
let results = graph.search(&text, limit)?;

let safe_query = super::query_universal::sanitize_query(&text);

let results = graph.search(&safe_query, limit)?;

if results.is_empty() {
println!("No results found for '{text}'");
Expand Down
46 changes: 18 additions & 28 deletions crates/ctxgraph-cli/src/commands/query_universal.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -170,20 +170,7 @@ pub fn run(query_text: String, limit: usize) -> ctxgraph::Result<()> {
}

// ── Stage 3: fallback fused search ───────────────────────────
// FTS5 doesn't like punctuation. Strip everything except word chars.
let safe_query: String = query_text
.chars()
.map(|c| {
if c.is_alphanumeric() || c == ' ' || c == '_' {
c
} else {
' '
}
})
.collect::<String>()
.split_whitespace()
.collect::<Vec<_>>()
.join(" ");
let safe_query = sanitize_query(&query_text);

println!("\n FALLBACK fused search results:");
let entity_hits = graph.search_entities(&safe_query, limit.min(10))?;
Expand Down Expand Up @@ -300,20 +287,7 @@ fn split_verb_entity(
}

fn exact_entity_lookup(graph: &ctxgraph::Graph, name: &str) -> ctxgraph::Result<Option<Entity>> {
// Strip punctuation for FTS5 compatibility
let safe: String = name
.chars()
.map(|c| {
if c.is_alphanumeric() || c == ' ' || c == '_' {
c
} else {
' '
}
})
.collect::<String>()
.split_whitespace()
.collect::<Vec<_>>()
.join(" ");
let safe = sanitize_query(name);
if safe.is_empty() {
return Ok(None);
}
Expand All @@ -328,6 +302,22 @@ fn exact_entity_lookup(graph: &ctxgraph::Graph, name: &str) -> ctxgraph::Result<
Ok(None)
}

/// Sanitize a query string for FTS5 by stripping non-alphanumeric characters.
pub fn sanitize_query(text: &str) -> String {
text.chars()
.map(|c| {
if c.is_alphanumeric() || c == ' ' || c == '_' {
c
} else {
' '
}
})
.collect::<String>()
.split_whitespace()
.collect::<Vec<_>>()
.join(" ")
}

fn is_pure_stopwords(s: &str) -> bool {
const STOP: &[&str] = &[
"what", "who", "where", "when", "why", "how", "the", "a", "an", "is", "are", "was", "were",
Expand Down