Function build_reverse_index

src/semantic/semantic.c:1207–1268

Build reverse index: token_id → list of (doc_id, position) pairs. * SEQUENTIAL (fast: just pointer arithmetic + flat array fill). */

/* Build reverse index: token_id → list of (doc_id, position) pairs.
 * SEQUENTIAL (fast: just pointer arithmetic + flat array fill). */
static reverse_index_t *build_reverse_index(cbm_sem_corpus_t *corpus) {
    reverse_index_t *rev = calloc(SKIP_ONE, sizeof(reverse_index_t));
    if (!rev) {
        return NULL;
    }
    /* Phase A: count occurrences per token */
    int *counts = calloc((size_t)corpus->entry_count + SKIP_ONE, sizeof(int));
    if (!counts) {
        free(rev);
        return NULL;
    }
    long total = 0;
    for (int d = 0; d < corpus->doc_count; d++) {
        int *ids = corpus->doc_token_ids[d];
        int len = corpus->doc_token_counts[d];
        for (int i = 0; i < len; i++) {
            int tid = ids[i];
            if (tid >= 0 && tid < corpus->entry_count) {
                counts[tid]++;
                total++;
            }
        }
    }
    /* Phase B: exclusive prefix sum → offsets[] */
    rev->offsets = malloc(((size_t)corpus->entry_count + SKIP_ONE) * sizeof(int));
    if (!rev->offsets) {
        free(counts);
        free(rev);
        return NULL;
    }
    int running = 0;
    for (int t = 0; t < corpus->entry_count; t++) {
        rev->offsets[t] = running;
        running += counts[t];
        counts[t] = 0; /* reuse as per-token fill cursor */
    }
    rev->offsets[corpus->entry_count] = running;
    /* Phase C: fill flat array. Ensure allocation size > 0 even for empty
     * corpora (avoids malloc(0) which is implementation-defined). */
    size_t flat_bytes = (total > 0 ? (size_t)total : SKIP_ONE) * sizeof(cooccur_pos_t);
    rev->flat = malloc(flat_bytes);
    if (!rev->flat) {
        free(rev->offsets);
        free(counts);
        free(rev);
        return NULL;
    }
    for (int d = 0; d < corpus->doc_count; d++) {
        int *ids = corpus->doc_token_ids[d];
        int len = corpus->doc_token_counts[d];
        for (int i = 0; i < len; i++) {
            int tid = ids[i];
            if (tid >= 0 && tid < corpus->entry_count) {
                int slot = rev->offsets[tid] + counts[tid]++;
                rev->flat[slot].doc_id = (int32_t)d;
                rev->flat[slot].pos = (int32_t)i;
            }
        }