Struct ContentHashedIndex 

pub struct ContentHashedIndex {
    pub duplicates_found: usize,
    pub unique_items: usize,
    /* private fields */
}

Content-hashed index for deduplication of code units.

Used to avoid indexing identical code multiple times. The index normalizes whitespace before hashing, so code with different formatting but identical content will be detected as duplicates.

Examples

use go_brrr::semantic::ContentHashedIndex;

let mut index = ContentHashedIndex::new();

// First occurrence is added
assert!(index.add("def foo(): pass", "src/a.py", "foo", 10));

// Identical content is detected as duplicate
assert!(!index.add("def foo(): pass", "src/b.py", "foo", 20));

// Check stats
let (unique, duplicates) = index.stats();
assert_eq!(unique, 1);
assert_eq!(duplicates, 1);

Fields

duplicates_found: usize

Number of duplicate items detected

unique_items: usize

Number of unique items indexed

Implementations

impl ContentHashedIndex

pub fn new() -> Self

Create a new empty content-hashed index.

pub fn check_duplicate(&self, content: &str) -> Option<&CodeLocation>

Check if content is a duplicate, returning the original location if so.

Arguments

• content - Code content to check

Returns

Some(&CodeLocation) if this content was already seen, None otherwise.

pub fn add( &mut self, content: &str, file: &str, function_name: &str, line: usize, ) -> bool

Add content to the index.

Arguments

• content - Code content to add
• file - Source file path
• function_name - Name of the function or code unit
• line - Line number (1-indexed)

Returns

true if this is new content (was added), false if duplicate (was not added).

pub fn stats(&self) -> (usize, usize)

Get deduplication statistics.

Returns

Tuple of (unique_items, duplicates_found).

pub fn len(&self) -> usize

Get the number of unique items in the index.

pub fn is_empty(&self) -> bool

Check if the index is empty.

pub fn clear(&mut self)

Clear the index and reset statistics.

pub fn dedup_ratio(&self) -> f64

Get the deduplication ratio (duplicates / total).

Returns 0.0 if no items have been processed.

Trait Implementations

impl Clone for ContentHashedIndex

fn clone(&self) -> ContentHashedIndex

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ContentHashedIndex

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for ContentHashedIndex

fn default() -> ContentHashedIndex

Returns the “default value” for a type.