X-Git-Url: https://git.octo.it/?p=git.git;a=blobdiff_plain;f=diffcore-rename.c;h=d57e8656cdcf1b999df30c01d3a8a042bc3ebb75;hp=ffd126af0d2cd3539e0f186e83c7671132758e6b;hb=HEAD;hpb=6be65bbc958e8d7c57bc81ae7035119b8b1afbab diff --git a/diffcore-rename.c b/diffcore-rename.c index ffd126af..d57e8656 100644 --- a/diffcore-rename.c +++ b/diffcore-rename.c @@ -4,8 +4,6 @@ #include "cache.h" #include "diff.h" #include "diffcore.h" -#include "delta.h" -#include "count-delta.h" /* Table of rename/copy destinations */ @@ -56,12 +54,14 @@ static struct diff_rename_dst *locate_rename_dst(struct diff_filespec *two, /* Table of rename/copy src files */ static struct diff_rename_src { struct diff_filespec *one; + unsigned short score; /* to remember the break score */ unsigned src_path_left : 1; } *rename_src; static int rename_src_nr, rename_src_alloc; static struct diff_rename_src *register_rename_src(struct diff_filespec *one, - int src_path_left) + int src_path_left, + unsigned short score) { int first, last; @@ -91,6 +91,7 @@ static struct diff_rename_src *register_rename_src(struct diff_filespec *one, memmove(rename_src + first + 1, rename_src + first, (rename_src_nr - first - 1) * sizeof(*rename_src)); rename_src[first].one = one; + rename_src[first].score = score; rename_src[first].src_path_left = src_path_left; return &(rename_src[first]); } @@ -135,8 +136,7 @@ static int estimate_similarity(struct diff_filespec *src, * match than anything else; the destination does not even * call into this function in that case. */ - void *delta; - unsigned long delta_size, base_size, src_copied, literal_added; + unsigned long max_size, delta_size, base_size, src_copied, literal_added; unsigned long delta_limit; int score; @@ -147,9 +147,9 @@ static int estimate_similarity(struct diff_filespec *src, if (!S_ISREG(src->mode) || !S_ISREG(dst->mode)) return 0; - delta_size = ((src->size < dst->size) ? - (dst->size - src->size) : (src->size - dst->size)); + max_size = ((src->size > dst->size) ? src->size : dst->size); base_size = ((src->size < dst->size) ? src->size : dst->size); + delta_size = max_size - base_size; /* We would not consider edits that change the file size so * drastically. delta_size must be smaller than @@ -165,42 +165,22 @@ static int estimate_similarity(struct diff_filespec *src, if (diff_populate_filespec(src, 0) || diff_populate_filespec(dst, 0)) return 0; /* error but caught downstream */ + delta_limit = base_size * (MAX_SCORE-minimum_score) / MAX_SCORE; - delta = diff_delta(src->data, src->size, - dst->data, dst->size, - &delta_size, delta_limit); - if (!delta) - /* If delta_limit is exceeded, we have too much differences */ + if (diffcore_count_changes(src->data, src->size, + dst->data, dst->size, + &src->cnt_data, &dst->cnt_data, + delta_limit, + &src_copied, &literal_added)) return 0; - /* A delta that has a lot of literal additions would have - * big delta_size no matter what else it does. + /* How similar are they? + * what percentage of material in dst are from source? */ - if (base_size * (MAX_SCORE-minimum_score) < delta_size * MAX_SCORE) { - free(delta); - return 0; - } - - /* Estimate the edit size by interpreting delta. */ - if (count_delta(delta, delta_size, &src_copied, &literal_added)) { - free(delta); - return 0; - } - free(delta); - - /* Extent of damage */ - if (src->size + literal_added < src_copied) - delta_size = 0; + if (!dst->size) + score = 0; /* should not happen */ else - delta_size = (src->size - src_copied) + literal_added; - - /* - * Now we will give some score to it. 100% edit gets 0 points - * and 0% edit gets MAX_SCORE points. - */ - score = MAX_SCORE - (MAX_SCORE * delta_size / base_size); - if (score < 0) return 0; - if (MAX_SCORE < score) return MAX_SCORE; + score = src_copied * MAX_SCORE / max_size; return score; } @@ -221,7 +201,10 @@ static void record_rename_pair(int dst_index, int src_index, int score) fill_filespec(two, dst->sha1, dst->mode); dp = diff_queue(NULL, one, two); - dp->score = score; + if (!strcmp(src->path, dst->path)) + dp->score = rename_src[src_index].score; + else + dp->score = score; dp->source_stays = rename_src[src_index].src_path_left; rename_dst[dst_index].pair = dp; } @@ -279,10 +262,10 @@ void diffcore_rename(struct diff_options *options) * that means the source actually stays. */ int stays = (p->broken_pair && !p->score); - register_rename_src(p->one, stays); + register_rename_src(p->one, stays, p->score); } else if (detect_rename == DIFF_DETECT_COPY) - register_rename_src(p->one, 1); + register_rename_src(p->one, 1, p->score); } if (rename_dst_nr == 0 || rename_src_nr == 0 || (0 < rename_limit && rename_limit < rename_dst_nr)) @@ -328,6 +311,8 @@ void diffcore_rename(struct diff_options *options) m->score = estimate_similarity(one, two, minimum_score); } + /* We do not need the text anymore */ + diff_free_filespec_data(two); dst_cnt++; } /* cost matrix sorted by most to least similar pair */