extract used CSS variables from CSS files

We will track CSS files while traversing the folder structure, but don't
extract any normal candidates from these CSS files. We will also not
include these files into any of the returned globs.

We will just run the CSS extractor on these CSS files, and every time we
find a CSS variable, we will verify whether it was used or not.

For now, "using", just means if it is used inside of `var(…)`.

crates/oxide/src/extractor/mod.rs

@@ -1,5 +1,6 @@
 use crate::cursor;
 use crate::extractor::machine::Span;
+use bstr::ByteSlice;
 use candidate_machine::CandidateMachine;
 use css_variable_machine::CssVariableMachine;
 use machine::{Machine, MachineState};
@@ -139,6 +140,41 @@ impl<'a> Extractor<'a> {
 
         extracted
     }
+
+    pub fn extract_css_variables_from_css_files(&mut self) -> Vec<Extracted<'a>> {
+        let mut extracted = Vec::with_capacity(100);
+
+        let len = self.cursor.input.len();
+
+        let cursor = &mut self.cursor.clone();
+        while cursor.pos < len {
+            if cursor.curr.is_ascii_whitespace() {
+                cursor.advance();
+                continue;
+            }
+
+            if let MachineState::Done(span) = self.css_variable_machine.next(cursor) {
+                // We are only interested in variables that are used, not defined. Therefore we
+                // need to ensure that the variable is prefixed with `var(`.
+                if span.start < 4 {
+                    cursor.advance();
+                    continue;
+                }
+
+                let slice_before = Span::new(span.start - 4, span.start - 1);
+                if !slice_before.slice(self.cursor.input).starts_with(b"var(") {
+                    cursor.advance();
+                    continue;
+                }
+
+                extracted.push(Extracted::CssVariable(span.slice(self.cursor.input)));
+            }
+
+            cursor.advance();
+        }
+
+        extracted
+    }
 }
 
 // Extract sub-candidates from a given range.

crates/oxide/src/scanner/mod.rs

@@ -215,11 +215,25 @@ impl Scanner {
     fn extract_candidates(&mut self) -> Vec<String> {
         let changed_content = self.changed_content.drain(..).collect::<Vec<_>>();
 
-        let candidates = parse_all_blobs(read_all_files(changed_content));
+        // Extract all candidates from the changed content
+        let mut new_candidates = parse_all_blobs(read_all_files(changed_content));
+
+        // Extract all CSS variables from the CSS files
+        let css_files = self.css_files.drain(..).collect::<Vec<_>>();
+        if !css_files.is_empty() {
+            let css_variables = extract_css_variables(read_all_files(
+                css_files
+                    .into_iter()
+                    .map(|file| ChangedContent::File(file, "css".into()))
+                    .collect(),
+            ));
+
+            new_candidates.extend(css_variables);
+        }
 
         // Only compute the new candidates and ignore the ones we already have. This is for
         // subsequent calls to prevent serializing the entire set of candidates every time.
-        let mut new_candidates = candidates
+        let mut new_candidates = new_candidates
             .into_par_iter()
             .filter(|candidate| !self.candidates.contains(candidate))
             .collect::<Vec<_>>();
@@ -411,6 +425,44 @@ fn read_all_files(changed_content: Vec<ChangedContent>) -> Vec<Vec<u8>> {
         .collect()
 }
 
+#[tracing::instrument(skip_all)]
+fn extract_css_variables(blobs: Vec<Vec<u8>>) -> Vec<String> {
+    let mut result: Vec<_> = blobs
+        .par_iter()
+        .flat_map(|blob| blob.par_split(|x| *x == b'\n'))
+        .filter_map(|blob| {
+            if blob.is_empty() {
+                return None;
+            }
+
+            let extracted =
+                crate::extractor::Extractor::new(blob).extract_css_variables_from_css_files();
+            if extracted.is_empty() {
+                return None;
+            }
+
+            Some(FxHashSet::from_iter(extracted.into_iter().map(
+                |x| match x {
+                    Extracted::CssVariable(bytes) => bytes,
+                    _ => &[],
+                },
+            )))
+        })
+        .reduce(Default::default, |mut a, b| {
+            a.extend(b);
+            a
+        })
+        .into_iter()
+        .map(|s| unsafe { String::from_utf8_unchecked(s.to_vec()) })
+        .collect();
+
+    // SAFETY: Unstable sort is faster and in this scenario it's also safe because we are
+    //         guaranteed to have unique candidates.
+    result.par_sort_unstable();
+
+    result
+}
+
 #[tracing::instrument(skip_all)]
 fn parse_all_blobs(blobs: Vec<Vec<u8>>) -> Vec<String> {
     let mut result: Vec<_> = blobs

crates/oxide/tests/scanner.rs

@@ -1735,4 +1735,39 @@ mod scanner {
 
         assert_eq!(candidates, vec!["content-['abcd/xyz.html']"]);
     }
+
+    #[test]
+    fn test_extract_used_css_variables_from_css() {
+        let dir = tempdir().unwrap().into_path();
+        create_files_in(
+            &dir,
+            &[
+                (
+                    "src/index.css",
+                    r#"
+                        @theme {
+                            --color-red: #ff0000; /* Not used, so don't extract */
+                            --color-green: #00ff00; /* Not used, so don't extract */
+                        }
+
+                        .button {
+                            color: var(--color-red); /* Used, so extract */
+                        }
+                    "#,
+                ),
+                ("src/used-at-start.css", "var(--color-used-at-start)"),
+                // Here to verify that we don't crash when trying to find `var(` in front of the
+                // variable.
+                ("src/defined-at-start.css", "--color-defined-at-start: red;"),
+            ],
+        );
+
+        let mut scanner = Scanner::new(vec![public_source_entry_from_pattern(
+            dir.clone(),
+            "@source './'",
+        )]);
+        let candidates = scanner.scan();
+
+        assert_eq!(candidates, vec!["--color-red", "--color-used-at-start"]);
+    }
 }