diff --git a/diffcore-rename.c b/diffcore-rename.c index a215421a9c..2a8fcd5292 100644 --- a/diffcore-rename.c +++ b/diffcore-rename.c @@ -9,63 +9,48 @@ #include "hashmap.h" #include "progress.h" #include "promisor-remote.h" +#include "strmap.h" /* Table of rename/copy destinations */ static struct diff_rename_dst { - struct diff_filespec *two; - struct diff_filepair *pair; + struct diff_filepair *p; + struct diff_filespec *filespec_to_free; + int is_rename; /* false -> just a create; true -> rename or copy */ } *rename_dst; static int rename_dst_nr, rename_dst_alloc; +/* Mapping from break source pathname to break destination index */ +static struct strintmap *break_idx = NULL; -static int find_rename_dst(struct diff_filespec *two) +static struct diff_rename_dst *locate_rename_dst(struct diff_filepair *p) { - int first, last; - - first = 0; - last = rename_dst_nr; - while (last > first) { - int next = first + ((last - first) >> 1); - struct diff_rename_dst *dst = &(rename_dst[next]); - int cmp = strcmp(two->path, dst->two->path); - if (!cmp) - return next; - if (cmp < 0) { - last = next; - continue; - } - first = next+1; - } - return -first - 1; -} - -static struct diff_rename_dst *locate_rename_dst(struct diff_filespec *two) -{ - int ofs = find_rename_dst(two); - return ofs < 0 ? NULL : &rename_dst[ofs]; + /* Lookup by p->ONE->path */ + int idx = break_idx ? strintmap_get(break_idx, p->one->path) : -1; + return (idx == -1) ? NULL : &rename_dst[idx]; } /* * Returns 0 on success, -1 if we found a duplicate. */ -static int add_rename_dst(struct diff_filespec *two) +static int add_rename_dst(struct diff_filepair *p) { - int first = find_rename_dst(two); - - if (first >= 0) + /* + * If we have multiple entries at the same path in the destination + * tree (an invalid tree, to be sure), turn off rename detection + * entirely. Once upon a time, diffcore-rename had double free() + * issues due to such duplicate paths, resulting in segfaults. See + * commit 4d6be03b95 ("diffcore-rename: avoid processing duplicate + * destinations", 2015-02-26). + */ + if (rename_dst_nr > 0 && + !strcmp(rename_dst[rename_dst_nr-1].p->two->path, p->two->path)) return -1; - first = -first - 1; - /* insert to make it at "first" */ ALLOC_GROW(rename_dst, rename_dst_nr + 1, rename_dst_alloc); + rename_dst[rename_dst_nr].p = p; + rename_dst[rename_dst_nr].filespec_to_free = NULL; + rename_dst[rename_dst_nr].is_rename = 0; rename_dst_nr++; - if (first < rename_dst_nr) - MOVE_ARRAY(rename_dst + first + 1, rename_dst + first, - rename_dst_nr - first - 1); - rename_dst[first].two = alloc_filespec(two->path); - fill_filespec(rename_dst[first].two, &two->oid, two->oid_valid, - two->mode); - rename_dst[first].pair = NULL; return 0; } @@ -89,6 +74,14 @@ static void register_rename_src(struct diff_filepair *p) !strcmp(rename_src[rename_src_nr-1].p->one->path, p->one->path)) return; + if (p->broken_pair) { + if (!break_idx) { + break_idx = xmalloc(sizeof(*break_idx)); + strintmap_init(break_idx, -1); + } + strintmap_set(break_idx, p->one->path, rename_dst_nr); + } + ALLOC_GROW(rename_src, rename_src_nr + 1, rename_src_alloc); rename_src[rename_src_nr].p = p; rename_src[rename_src_nr].score = p->score; @@ -128,14 +121,14 @@ static void prefetch(void *prefetch_options) struct oid_array to_fetch = OID_ARRAY_INIT; for (i = 0; i < rename_dst_nr; i++) { - if (rename_dst[i].pair) + if (rename_dst[i].p->renamed_pair) /* * The loop in diffcore_rename() will not need these * blobs, so skip prefetching. */ continue; /* already found exact match */ diff_add_if_missing(options->repo, &to_fetch, - rename_dst[i].two); + rename_dst[i].p->two); } for (i = 0; i < rename_src_nr; i++) { if (options->skip_unmodified && @@ -245,26 +238,24 @@ static int estimate_similarity(struct repository *r, static void record_rename_pair(int dst_index, int src_index, int score) { - struct diff_filespec *src, *dst; - struct diff_filepair *dp; + struct diff_filepair *src = rename_src[src_index].p; + struct diff_filepair *dst = rename_dst[dst_index].p; - if (rename_dst[dst_index].pair) + if (dst->renamed_pair) die("internal error: dst already matched."); - src = rename_src[src_index].p->one; - src->rename_used++; - src->count++; + src->one->rename_used++; + src->one->count++; - dst = rename_dst[dst_index].two; - dst->count++; + rename_dst[dst_index].filespec_to_free = dst->one; + rename_dst[dst_index].is_rename = 1; - dp = diff_queue(NULL, src, dst); - dp->renamed_pair = 1; - if (!strcmp(src->path, dst->path)) - dp->score = rename_src[src_index].score; + dst->one = src->one; + dst->renamed_pair = 1; + if (!strcmp(dst->one->path, dst->two->path)) + dst->score = rename_src[src_index].score; else - dp->score = score; - rename_dst[dst_index].pair = dp; + dst->score = score; } /* @@ -310,7 +301,7 @@ static int find_identical_files(struct hashmap *srcs, struct diff_options *options) { int renames = 0; - struct diff_filespec *target = rename_dst[dst_index].two; + struct diff_filespec *target = rename_dst[dst_index].p->two; struct file_similarity *p, *best = NULL; int i = 100, best_score = -1; unsigned int hash = hash_filespec(options->repo, target); @@ -476,7 +467,7 @@ static int find_renames(struct diff_score *mx, int dst_cnt, int minimum_score, i (mx[i].score < minimum_score)) break; /* there is no more usable pair. */ dst = &rename_dst[mx[i].dst]; - if (dst->pair) + if (dst->is_rename) continue; /* already done, either exact or fuzzy. */ if (!copies && rename_src[mx[i].src].p->one->rename_used) continue; @@ -511,7 +502,7 @@ void diffcore_rename(struct diff_options *options) else if (!options->flags.rename_empty && is_empty_blob_oid(&p->two->oid)) continue; - else if (add_rename_dst(p->two) < 0) { + else if (add_rename_dst(p) < 0) { warning("skipping rename detection, detected" " duplicate destination '%s'", p->two->path); @@ -586,10 +577,10 @@ void diffcore_rename(struct diff_options *options) mx = xcalloc(st_mult(NUM_CANDIDATE_PER_DST, num_destinations), sizeof(*mx)); for (dst_cnt = i = 0; i < rename_dst_nr; i++) { - struct diff_filespec *two = rename_dst[i].two; + struct diff_filespec *two = rename_dst[i].p->two; struct diff_score *m; - if (rename_dst[i].pair) + if (rename_dst[i].is_rename) continue; /* dealt with exact match already. */ m = &mx[dst_cnt * NUM_CANDIDATE_PER_DST]; @@ -646,22 +637,8 @@ void diffcore_rename(struct diff_options *options) diff_q(&outq, p); } else if (!DIFF_FILE_VALID(p->one) && DIFF_FILE_VALID(p->two)) { - /* - * Creation - * - * We would output this create record if it has - * not been turned into a rename/copy already. - */ - struct diff_rename_dst *dst = locate_rename_dst(p->two); - if (dst && dst->pair) { - diff_q(&outq, dst->pair); - pair_to_free = p; - } - else - /* no matching rename/copy source, so - * record this as a creation. - */ - diff_q(&outq, p); + /* Creation */ + diff_q(&outq, p); } else if (DIFF_FILE_VALID(p->one) && !DIFF_FILE_VALID(p->two)) { /* @@ -682,8 +659,10 @@ void diffcore_rename(struct diff_options *options) */ if (DIFF_PAIR_BROKEN(p)) { /* broken delete */ - struct diff_rename_dst *dst = locate_rename_dst(p->one); - if (dst && dst->pair) + struct diff_rename_dst *dst = locate_rename_dst(p); + if (!dst) + BUG("tracking failed somehow; failed to find associated dst for broken pair"); + if (dst->is_rename) /* counterpart is now rename/copy */ pair_to_free = p; } @@ -693,16 +672,14 @@ void diffcore_rename(struct diff_options *options) pair_to_free = p; } - if (pair_to_free) - ; - else + if (!pair_to_free) diff_q(&outq, p); } else if (!diff_unmodified_pair(p)) /* all the usual ones need to be kept */ diff_q(&outq, p); else - /* no need to keep unmodified pairs */ + /* no need to keep unmodified pairs; FIXME: remove earlier? */ pair_to_free = p; if (pair_to_free) @@ -715,11 +692,16 @@ void diffcore_rename(struct diff_options *options) diff_debug_queue("done collapsing", q); for (i = 0; i < rename_dst_nr; i++) - free_filespec(rename_dst[i].two); + if (rename_dst[i].filespec_to_free) + free_filespec(rename_dst[i].filespec_to_free); FREE_AND_NULL(rename_dst); rename_dst_nr = rename_dst_alloc = 0; FREE_AND_NULL(rename_src); rename_src_nr = rename_src_alloc = 0; + if (break_idx) { + strintmap_clear(break_idx); + FREE_AND_NULL(break_idx); + } return; }