Skip to content

LightCraft: An open-source non-destructive photo editor written by scratch in pure Rust

Merge main into feat/1449-people-search; people and quotes go through text_matches (#2099)

Arekatla Nishanth Chowdary3a6e7d0b9bc5
diff --cc crates/catalog/src/query.rs
index f98a083ef,7625c9ab6..a94421369
--- a/crates/catalog/src/query.rs
+++ b/crates/catalog/src/query.rs
@@@ -135,46 -135,15 +135,46 @@@ fn shuffle_rank(seed: u64, id: PhotoId
mix64(mix64(seed) ^ id.0)
}
+ /// What [`Filter::prepare`] works out once for a pass over many photos.
+ pub(crate) struct Prepared {
+ root: Option<String>,
+ only: Option<std::collections::HashSet<PhotoId>>,
+ }
+
+/// The tokens of a search text: split at whitespace, except inside double quotes, so
+/// `person:"Jane Doe"` is one token (issue #1449). An unclosed quote runs to the end of the text; a
+/// backslash is an ordinary character. One pass over the text, nothing allocated.
+fn search_tokens(text: &str) -> impl Iterator<Item = &str> {
+ let mut rest = text;
+ std::iter::from_fn(move || {
+ rest = rest.trim_start();
+ if rest.is_empty() {
+ return None;
+ }
+ let mut quoted = false;
+ let end = rest
+ .char_indices()
+ .find(|&(_, c)| {
+ quoted ^= c == '"';
+ !quoted && c.is_whitespace()
+ })
+ .map_or(rest.len(), |(i, _)| i);
+ let (tok, tail) = rest.split_at(end);
+ rest = tail;
+ Some(tok)
+ })
+}
+
+/// `s` without the double quotes around it (a missing closing quote is allowed).
+fn unquote(s: &str) -> &str {
+ s.strip_prefix('"').map_or(s, |inner| inner.strip_suffix('"').unwrap_or(inner))
+}
+
- /// What [`Filter::prepare`] works out once for a pass over many photos.
- pub(crate) struct Prepared {
- root: Option<String>,
- only: Option<std::collections::HashSet<PhotoId>>,
- }
-
fn token_matches(p: &Photo, tok: &str) -> bool {
let t = tok.to_lowercase();
- if let Some((field, val)) = t.split_once(':') {
+ // a token that starts with a quote is a phrase, even with a colon in it
- if let Some((field, val)) = t.split_once(':').filter(|_| !t.starts_with('"')) {
- let val = unquote(val);
++ if let Some((field, quoted)) = t.split_once(':').filter(|_| !t.starts_with('"')) {
++ let val = unquote(quoted);
let num = |s: &str| -> Option<(char, f64)> {
let (op, rest) = match s.chars().next()? {
c @ ('>' | '<' | '=') => (c, &s[1..]),
@@@ -204,14 -180,18 +211,22 @@@
"date" => p.captured.as_deref().is_some_and(|c| c.starts_with(val)),
"copy" | "virtual" => (val == "true" || val == "yes") == p.copy_of.is_some(),
"name" | "file" => p.file_name.to_lowercase().contains(val),
- _ => false,
- // Not a known field: the colon is part of a plain word ("10:30", "Re:").
++ // Not a known field: the colon is part of a plain word ("10:30", "Re:"), its value unquoted
++ // (`re:"a b"` is the text `re:a b`).
++ _ if val.len() != quoted.len() => text_matches(p, &format!("{field}:{val}")),
+ _ => text_matches(p, &t),
};
}
- let t = unquote(&t);
- text_matches(p, &t)
++ text_matches(p, unquote(&t))
+ }
+
+ /// Whether the lower-cased word `t` is in the file name, title, caption, camera, lens, location,
-/// format or a keyword of `p`.
++/// format, a keyword or the name of a person (a named face) of `p`.
+ fn text_matches(p: &Photo, t: &str) -> bool {
let hay = [&p.file_name, &p.meta.title, &p.meta.caption, &p.meta.camera, &p.meta.lens, &p.meta.location, &p.format];
- hay.iter().any(|h| h.to_lowercase().contains(t)) || p.meta.keywords.iter().any(|k| k.to_lowercase().contains(t))
+ hay.iter().any(|h| h.to_lowercase().contains(t))
+ || p.meta.keywords.iter().any(|k| k.to_lowercase().contains(t))
+ || p.people().iter().any(|n| n.to_lowercase().contains(t))
}
/// Whether `p` has a named face region called `name` (case-insensitive).
diff --cc crates/catalog/src/tests.rs
index 401d62020,a32b5acf5..f8b72dad8
--- a/crates/catalog/src/tests.rs
+++ b/crates/catalog/src/tests.rs
@@@ -794,68 -836,6 +836,71 @@@ fn cmp_name_ignores_case_without_alloca
assert_eq!(cmp_name("a", "ab"), Less);
}
+/// Search Photos finds named people in free text, and a quoted value keeps a name of several words
+/// together: `person:"Jane Doe"` (issue #1449). Malformed quotes narrow the result or change nothing.
+#[test]
+fn search_text_finds_people_and_quoted_values() {
+ use lightcraft_meta::{Rect, Region, RegionKind};
+ let region = |name: &str, kind: RegionKind| Region {
+ rect: Rect { x0: 0.4, y0: 0.4, x1: 0.6, y1: 0.6 },
+ kind,
+ name: Some(name.to_string()),
+ description: None,
+ };
+ let mut c = Catalog::new();
+ let mut add = |name: &str, regions: Vec<Region>, keywords: &[&str]| {
+ let id = c.alloc_photo_id();
+ let mut p = Photo::new(id, Source::Demo { scene: 1 }, name, "JPEG", 6000, 4000, "2026-09-30T10:00:00");
+ p.meta.regions = regions;
+ p.meta.keywords = keywords.iter().map(|k| k.to_string()).collect();
+ c.apply(Op::AddPhoto { photo: Box::new(p) }).unwrap();
+ id
+ };
+ let jane = add("a.jpg", vec![region("Jane Doe", RegionKind::Face), region("Rex", RegionKind::Pet)], &[]);
+ let both = add("b.jpg", vec![region("Jane Roe", RegionKind::Face), region("John Doe", RegionKind::Face)], &[]);
+ let zoe = add("c.jpg", vec![region("Zoë Ångström", RegionKind::Face)], &["New York"]);
- let none = add("d.jpg", vec![], &["york minster"]);
++ let none = add("lunch 10:30 am.jpg", vec![], &["york minster"]);
+ let q = |text: &str| {
+ let mut ids = c.query(&Filter { text: text.into(), ..Default::default() }, &Sort::default());
+ ids.sort();
+ ids
+ };
+
+ // free text: a person's name, any case, any part of it; pets are not people
+ assert_eq!(q("jane"), vec![jane, both]);
+ assert_eq!(q("DOE"), vec![jane, both]);
+ assert_eq!(q("ångström"), vec![zoe]);
+ assert!(q("rex").is_empty(), "a pet is not a person");
+ // words are still ANDed: b.jpg has a Jane and a Doe, a quoted phrase asks for them together
+ assert_eq!(q("jane doe"), vec![jane, both]);
+ assert_eq!(q("\"jane doe\""), vec![jane]);
+
+ // fielded: the exact name, of several words when quoted
+ assert_eq!(q("person:\"Jane Doe\""), vec![jane]);
+ assert_eq!(q("who:\"jane roe\""), vec![both]);
+ assert_eq!(q("person:\"Zoë Ångström\""), vec![zoe]);
+ assert!(q("person:jane").is_empty(), "person: is the whole name, as before");
+ assert!(q("person:Jane Doe").is_empty(), "unquoted, the second word is its own token, as before");
+ assert_eq!(q("keyword:\"new york\""), vec![zoe], "other fields take quoted values too");
+ assert_eq!(q("person:\"Jane Doe\" a.jpg"), vec![jane], "tokens after a quoted one still count");
+
+ // malformed input never widens the match and never panics
+ assert_eq!(q("person:\"Jane Doe"), vec![jane], "an unclosed quote runs to the end");
+ assert!(q("person:\"Jane Doe a.jpg").is_empty(), "…and takes the rest of the text with it");
+ assert!(q("person:\"\"").is_empty());
+ assert!(q("person:").is_empty());
+ assert_eq!(q("\""), vec![jane, both, zoe, none], "a lone quote is an empty phrase, like an empty search");
+ assert_eq!(q("\"\" jane"), vec![jane, both]);
+ assert!(q("\"jane:doe\"").is_empty(), "a quoted phrase is free text even with a colon");
++ // an unknown field is plain text, its quoted value unquoted (#2099): `10:"30 am"` is the text `10:30 am`
++ assert_eq!(q("10:\"30 am\""), vec![none]);
++ assert!(q("10:\"30 pm\"").is_empty());
+ assert!(q("jane\\\"").is_empty(), "a backslash is an ordinary character");
+ let long = format!("person:\"{}", "é ".repeat(50_000));
+ assert!(q(&long).is_empty());
+ assert_eq!(q(" \t jane \u{3000} "), vec![jane, both], "any whitespace separates tokens");
+}
+
/// What the catalog remembers of its latest ops: which photos each changed and what of them, as long as that can be
/// said photo by photo.
#[test]