func (c *Chunker) ProcessFile(filePath string) ([]Chunk, error) {
    fileSize := getFileSize(filePath)
    numWorkers := 4
    chunkChan := make(chan Chunk, 100)
    var wg sync.WaitGroup
    sectionSize := fileSize / int64(numWorkers)

    for i := 0; i < numWorkers; i++ {
        start := int64(i) * sectionSize
        end := start + sectionSize
        if i == numWorkers-1 {
            end = fileSize
        }
        wg.Add(1)
        go c.processSection(filePath, start, end, chunkChan)
    }

    go func() {
        wg.Wait()
        close(chunkChan)
    }()

    var chunks []Chunk
    for chunk := range chunkChan {
        chunks = append(chunks, chunk)
    }
    return chunks, nil
}

type Fingerprint struct {
    SimHash     uint64
    VecSketches []int
}

func Hash(content []byte) Fingerprint {
    vector := toVector(string(content))
    return Fingerprint{
        SimHash:     simHash(string(content)),
        VecSketches: vectorSketches(vector, 10),
    }
}

type Index struct {
    Entries    map[uint64]IndexEntry
    LSHBuckets map[int][]IndexEntry
    mu         sync.RWMutex
}

func (idx *Index) AddEntry(fp simhash.Fingerprint, offset int64) {
    idx.mu.Lock()
    defer idx.mu.Unlock()
    idx.Entries[fp.SimHash] = IndexEntry{Fingerprint: fp, Offsets: []int64{offset}}
    bucketKey := fp.VecSketches[0]
    idx.LSHBuckets[bucketKey] = append(idx.LSHBuckets[bucketKey], entry)
}

./textindex -c index -i large_text.txt -s 4096 -o index.idx
./textindex -c lookup -i index.idx -h 3eff1b2c98a6
./textindex -c compare -i doc1.txt -i2 doc2.txt -o report.txt
./textindex -c fuzzy -i testdata.idx -h $HASH -threshold 0.8