1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-11-18 06:54:55 +01:00

Merge branch 'fk/blame' into next

* fk/blame:
  git-blame, take 2
  Merge part of 'lt/rev-list' into 'fk/blame'
This commit is contained in:
Junio C Hamano 2006-03-02 21:15:56 -08:00
commit 262cc77dab

746
blame.c
View file

@ -1,4 +1,10 @@
/*
* Copyright (C) 2006, Fredrik Kuivinen <freku045@student.liu.se>
*/
#include <assert.h> #include <assert.h>
#include <time.h>
#include <sys/time.h>
#include "cache.h" #include "cache.h"
#include "refs.h" #include "refs.h"
@ -7,436 +13,550 @@
#include "tree.h" #include "tree.h"
#include "blob.h" #include "blob.h"
#include "diff.h" #include "diff.h"
#include "revision.h"
#define DEBUG 0 #define DEBUG 0
struct commit** blame_lines; struct commit **blame_lines;
int num_blame_lines; int num_blame_lines;
struct util_info struct util_info {
{ int *line_map;
int* line_map; unsigned char sha1[20]; /* blob sha, not commit! */
int num_lines; char *buf;
unsigned char sha1[20]; /* blob sha, not commit! */ unsigned long size;
char* buf; int num_lines;
unsigned long size;
// const char* path; // const char* path;
}; };
struct chunk struct chunk {
{ int off1, len1; // ---
int off1, len1; // --- int off2, len2; // +++
int off2, len2; // +++
}; };
struct patch struct patch {
{ struct chunk *chunks;
struct chunk* chunks; int num;
int num;
}; };
static void get_blob(struct commit* commit); static void get_blob(struct commit *commit);
int num_get_patch = 0; /* Only used for statistics */
int num_commits = 0; static int num_get_patch = 0;
static int num_commits = 0;
static int patch_time = 0;
struct patch* get_patch(struct commit* commit, struct commit* other) #define TEMPFILE_PATH_LEN 60
static struct patch *get_patch(struct commit *commit, struct commit *other)
{ {
struct patch* ret = xmalloc(sizeof(struct patch)); struct patch *ret;
ret->chunks = NULL; struct util_info *info_c = (struct util_info *)commit->object.util;
ret->num = 0; struct util_info *info_o = (struct util_info *)other->object.util;
char tmp_path1[TEMPFILE_PATH_LEN], tmp_path2[TEMPFILE_PATH_LEN];
char diff_cmd[TEMPFILE_PATH_LEN*2 + 20];
struct timeval tv_start, tv_end;
int fd;
FILE *fin;
char buf[1024];
struct util_info* info_c = (struct util_info*) commit->object.util; ret = xmalloc(sizeof(struct patch));
struct util_info* info_o = (struct util_info*) other->object.util; ret->chunks = NULL;
ret->num = 0;
if(!memcmp(info_c->sha1, info_o->sha1, 20)) get_blob(commit);
return ret; get_blob(other);
get_blob(commit); gettimeofday(&tv_start, NULL);
get_blob(other);
FILE* fout = fopen("/tmp/git-blame-tmp1", "w"); fd = git_mkstemp(tmp_path1, TEMPFILE_PATH_LEN, "git-blame-XXXXXX");
if(!fout) if (fd < 0)
die("fopen tmp1 failed: %s", strerror(errno)); die("unable to create temp-file: %s", strerror(errno));
if(fwrite(info_c->buf, info_c->size, 1, fout) != 1) if (xwrite(fd, info_c->buf, info_c->size) != info_c->size)
die("fwrite 1 failed: %s", strerror(errno)); die("write failed: %s", strerror(errno));
fclose(fout); close(fd);
fout = fopen("/tmp/git-blame-tmp2", "w"); fd = git_mkstemp(tmp_path2, TEMPFILE_PATH_LEN, "git-blame-XXXXXX");
if(!fout) if (fd < 0)
die("fopen tmp2 failed: %s", strerror(errno)); die("unable to create temp-file: %s", strerror(errno));
if(fwrite(info_o->buf, info_o->size, 1, fout) != 1) if (xwrite(fd, info_o->buf, info_o->size) != info_o->size)
die("fwrite 2 failed: %s", strerror(errno)); die("write failed: %s", strerror(errno));
fclose(fout); close(fd);
FILE* fin = popen("diff -u0 /tmp/git-blame-tmp1 /tmp/git-blame-tmp2", "r"); sprintf(diff_cmd, "diff -u0 %s %s", tmp_path1, tmp_path2);
if(!fin) fin = popen(diff_cmd, "r");
die("popen failed: %s", strerror(errno)); if (!fin)
die("popen failed: %s", strerror(errno));
char buf[1024]; while (fgets(buf, sizeof(buf), fin)) {
while(fgets(buf, sizeof(buf), fin)) { struct chunk *chunk;
if(buf[0] != '@' || buf[1] != '@') char *start, *sp;
continue;
if(DEBUG) if (buf[0] != '@' || buf[1] != '@')
printf("chunk line: %s", buf); continue;
ret->num++;
ret->chunks = xrealloc(ret->chunks, sizeof(struct chunk)*ret->num);
struct chunk* chunk = &ret->chunks[ret->num-1];
assert(!strncmp(buf, "@@ -", 4)); if (DEBUG)
printf("chunk line: %s", buf);
ret->num++;
ret->chunks = xrealloc(ret->chunks,
sizeof(struct chunk) * ret->num);
chunk = &ret->chunks[ret->num - 1];
char* start = buf+4; assert(!strncmp(buf, "@@ -", 4));
char* sp = index(start, ' ');
*sp = '\0';
if(index(start, ',')) {
int ret = sscanf(start, "%d,%d", &chunk->off1, &chunk->len1);
assert(ret == 2);
} else {
int ret = sscanf(start, "%d", &chunk->off1);
assert(ret == 1);
chunk->len1 = 1;
}
*sp = ' ';
start = sp+1; start = buf + 4;
sp = index(start, ' '); sp = index(start, ' ');
*sp = '\0'; *sp = '\0';
if(index(start, ',')) { if (index(start, ',')) {
int ret = sscanf(start, "%d,%d", &chunk->off2, &chunk->len2); int ret =
assert(ret == 2); sscanf(start, "%d,%d", &chunk->off1, &chunk->len1);
} else { assert(ret == 2);
int ret = sscanf(start, "%d", &chunk->off2); } else {
assert(ret == 1); int ret = sscanf(start, "%d", &chunk->off1);
chunk->len2 = 1; assert(ret == 1);
} chunk->len1 = 1;
*sp = ' '; }
*sp = ' ';
if(chunk->off1 > 0) start = sp + 1;
chunk->off1 -= 1; sp = index(start, ' ');
if(chunk->off2 > 0) *sp = '\0';
chunk->off2 -= 1; if (index(start, ',')) {
int ret =
sscanf(start, "%d,%d", &chunk->off2, &chunk->len2);
assert(ret == 2);
} else {
int ret = sscanf(start, "%d", &chunk->off2);
assert(ret == 1);
chunk->len2 = 1;
}
*sp = ' ';
assert(chunk->off1 >= 0); if (chunk->len1 == 0)
assert(chunk->off2 >= 0); chunk->off1++;
} if (chunk->len2 == 0)
fclose(fin); chunk->off2++;
num_get_patch++; if (chunk->off1 > 0)
return ret; chunk->off1--;
if (chunk->off2 > 0)
chunk->off2--;
assert(chunk->off1 >= 0);
assert(chunk->off2 >= 0);
}
pclose(fin);
unlink(tmp_path1);
unlink(tmp_path2);
gettimeofday(&tv_end, NULL);
patch_time += 1000000 * (tv_end.tv_sec - tv_start.tv_sec) +
tv_end.tv_usec - tv_start.tv_usec;
num_get_patch++;
return ret;
} }
void free_patch(struct patch* p) static void free_patch(struct patch *p)
{ {
free(p->chunks); free(p->chunks);
free(p); free(p);
} }
static int get_blob_sha1_internal(unsigned char *sha1, const char *base, int baselen, static int get_blob_sha1_internal(unsigned char *sha1, const char *base,
const char *pathname, unsigned mode, int stage); int baselen, const char *pathname,
unsigned mode, int stage);
static unsigned char blob_sha1[20]; static unsigned char blob_sha1[20];
static int get_blob_sha1(struct tree* t, const char* pathname, unsigned char* sha1) static int get_blob_sha1(struct tree *t, const char *pathname,
unsigned char *sha1)
{ {
const char *pathspec[2]; int i;
pathspec[0] = pathname; const char *pathspec[2];
pathspec[1] = NULL; pathspec[0] = pathname;
memset(blob_sha1, 0, sizeof(blob_sha1)); pathspec[1] = NULL;
read_tree_recursive(t, "", 0, 0, pathspec, get_blob_sha1_internal); memset(blob_sha1, 0, sizeof(blob_sha1));
read_tree_recursive(t, "", 0, 0, pathspec, get_blob_sha1_internal);
int i; for (i = 0; i < 20; i++) {
for(i = 0; i < 20; i++) { if (blob_sha1[i] != 0)
if(blob_sha1[i] != 0) break;
break; }
}
if(i == 20) if (i == 20)
return -1; return -1;
memcpy(sha1, blob_sha1, 20); memcpy(sha1, blob_sha1, 20);
return 0; return 0;
} }
static int get_blob_sha1_internal(unsigned char *sha1, const char *base, int baselen, static int get_blob_sha1_internal(unsigned char *sha1, const char *base,
const char *pathname, unsigned mode, int stage) int baselen, const char *pathname,
unsigned mode, int stage)
{ {
// printf("Got blob: %s base: '%s' baselen: %d pathname: '%s' mode: %o stage: %d\n", if (S_ISDIR(mode))
// sha1_to_hex(sha1), base, baselen, pathname, mode, stage); return READ_TREE_RECURSIVE;
if(S_ISDIR(mode)) memcpy(blob_sha1, sha1, 20);
return READ_TREE_RECURSIVE; return -1;
memcpy(blob_sha1, sha1, 20);
return -1;
} }
static void get_blob(struct commit* commit) static void get_blob(struct commit *commit)
{ {
struct util_info* info = commit->object.util; struct util_info *info = commit->object.util;
char type[20]; char type[20];
if(info->buf) if (info->buf)
return; return;
info->buf = read_sha1_file(info->sha1, type, &info->size); info->buf = read_sha1_file(info->sha1, type, &info->size);
assert(!strcmp(type, "blob"));
assert(!strcmp(type, "blob"));
} }
void print_patch(struct patch* p) /* For debugging only */
static void print_patch(struct patch *p)
{ {
printf("Num chunks: %d\n", p->num); int i;
int i; printf("Num chunks: %d\n", p->num);
for(i = 0; i < p->num; i++) { for (i = 0; i < p->num; i++) {
printf("%d,%d %d,%d\n", p->chunks[i].off1, p->chunks[i].len1, p->chunks[i].off2, p->chunks[i].len2); printf("%d,%d %d,%d\n", p->chunks[i].off1, p->chunks[i].len1,
} p->chunks[i].off2, p->chunks[i].len2);
}
} }
/* For debugging only */
static void print_map(struct commit *cmit, struct commit *other)
{
struct util_info *util = cmit->object.util;
struct util_info *util2 = other->object.util;
int i;
int max =
util->num_lines >
util2->num_lines ? util->num_lines : util2->num_lines;
int num;
for (i = 0; i < max; i++) {
printf("i: %d ", i);
num = -1;
if (i < util->num_lines) {
num = util->line_map[i];
printf("%d\t", num);
} else
printf("\t");
if (i < util2->num_lines) {
int num2 = util2->line_map[i];
printf("%d\t", num2);
if (num != -1 && num2 != num)
printf("---");
} else
printf("\t");
printf("\n");
}
}
// p is a patch from commit to other. // p is a patch from commit to other.
void fill_line_map(struct commit* commit, struct commit* other, struct patch* p) static void fill_line_map(struct commit *commit, struct commit *other,
struct patch *p)
{ {
int num_lines = ((struct util_info*) commit->object.util)->num_lines; struct util_info *util = commit->object.util;
int* line_map = ((struct util_info*) commit->object.util)->line_map; struct util_info *util2 = other->object.util;
int num_lines2 = ((struct util_info*) other->object.util)->num_lines; int *map = util->line_map;
int* line_map2 = ((struct util_info*) other->object.util)->line_map; int *map2 = util2->line_map;
int cur_chunk = 0; int cur_chunk = 0;
int i1, i2; int i1, i2;
if(p->num && DEBUG) if (p->num && DEBUG)
print_patch(p); print_patch(p);
for(i1 = 0; i1 < num_lines; i1++) if (DEBUG)
line_map[i1] = -1; printf("num lines 1: %d num lines 2: %d\n", util->num_lines,
util2->num_lines);
if(DEBUG) for (i1 = 0, i2 = 0; i1 < util->num_lines; i1++, i2++) {
printf("num lines 1: %d num lines 2: %d\n", num_lines, num_lines2); struct chunk *chunk = NULL;
if (cur_chunk < p->num)
chunk = &p->chunks[cur_chunk];
for(i1 = 0, i2 = 0; i1 < num_lines; i1++, i2++) { if (chunk && chunk->off1 == i1) {
if(DEBUG > 1) if (DEBUG && i2 != chunk->off2)
printf("%d %d\n", i1, i2); printf("i2: %d off2: %d\n", i2, chunk->off2);
if(i2 >= num_lines2) assert(i2 == chunk->off2);
break;
line_map[i1] = line_map2[i2]; i1--;
i2--;
if (chunk->len1 > 0)
i1 += chunk->len1;
struct chunk* chunk = NULL; if (chunk->len2 > 0)
if(cur_chunk < p->num) i2 += chunk->len2;
chunk = &p->chunks[cur_chunk];
if(chunk && chunk->off1 == i1) { cur_chunk++;
i2 = chunk->off2; } else {
if (i2 >= util2->num_lines)
break;
if(chunk->len1 > 0) if (map[i1] != map2[i2] && map[i1] != -1) {
i1 += chunk->len1-1; if (DEBUG)
if(chunk->len2 > 0) printf("map: i1: %d %d %p i2: %d %d %p\n",
i2 += chunk->len2-1; i1, map[i1],
cur_chunk++; i1 != -1 ? blame_lines[map[i1]] : NULL,
} i2, map2[i2],
} i2 != -1 ? blame_lines[map2[i2]] : NULL);
if (map2[i2] != -1 &&
blame_lines[map[i1]] &&
!blame_lines[map2[i2]])
map[i1] = map2[i2];
}
if (map[i1] == -1 && map2[i2] != -1)
map[i1] = map2[i2];
}
if (DEBUG > 1)
printf("l1: %d l2: %d i1: %d i2: %d\n",
map[i1], map2[i2], i1, i2);
}
} }
int map_line(struct commit* commit, int line) static int map_line(struct commit *commit, int line)
{ {
struct util_info* info = commit->object.util; struct util_info *info = commit->object.util;
assert(line >= 0 && line < info->num_lines); assert(line >= 0 && line < info->num_lines);
return info->line_map[line]; return info->line_map[line];
} }
int fill_util_info(struct commit* commit, const char* path) static int fill_util_info(struct commit *commit, const char *path)
{ {
if(commit->object.util) struct util_info *util;
return 0; if (commit->object.util)
return 0;
struct util_info* util = xmalloc(sizeof(struct util_info)); util = xmalloc(sizeof(struct util_info));
util->buf = NULL;
util->size = 0;
util->num_lines = -1;
util->line_map = NULL;
commit->object.util = util; if (get_blob_sha1(commit->tree, path, util->sha1)) {
free(util);
if(get_blob_sha1(commit->tree, path, util->sha1)) return 1;
return -1; } else {
util->buf = NULL;
return 0; util->size = 0;
util->line_map = NULL;
util->num_lines = -1;
commit->object.util = util;
return 0;
}
} }
void alloc_line_map(struct commit* commit) static void alloc_line_map(struct commit *commit)
{ {
struct util_info* util = commit->object.util; struct util_info *util = commit->object.util;
int i;
if(util->line_map) if (util->line_map)
return; return;
get_blob(commit); get_blob(commit);
int i; util->num_lines = 0;
util->num_lines = 0; for (i = 0; i < util->size; i++) {
for(i = 0; i < util->size; i++) { if (util->buf[i] == '\n')
if(util->buf[i] == '\n') util->num_lines++;
util->num_lines++; }
} if(util->buf[util->size - 1] != '\n')
util->line_map = xmalloc(sizeof(int)*util->num_lines); util->num_lines++;
util->line_map = xmalloc(sizeof(int) * util->num_lines);
for (i = 0; i < util->num_lines; i++)
util->line_map[i] = -1;
} }
void copy_line_map(struct commit* dst, struct commit* src) static void init_first_commit(struct commit* commit, const char* filename)
{ {
struct util_info* u_dst = dst->object.util; struct util_info* util;
struct util_info* u_src = src->object.util; int i;
u_dst->line_map = u_src->line_map; if (fill_util_info(commit, filename))
u_dst->num_lines = u_src->num_lines; die("fill_util_info failed");
u_dst->buf = u_src->buf;
u_dst->size = u_src->size; alloc_line_map(commit);
util = commit->object.util;
num_blame_lines = util->num_lines;
for (i = 0; i < num_blame_lines; i++)
util->line_map[i] = i;
} }
void process_commits(struct commit_list* list, const char* path)
static void process_commits(struct rev_info *rev, const char *path,
struct commit** initial)
{ {
int i; int i;
struct util_info* util;
int lines_left;
int *blame_p;
int *new_lines;
int new_lines_len;
while(list) { struct commit* commit = get_revision(rev);
struct commit* commit = pop_commit(&list); assert(commit);
struct commit_list* parents; init_first_commit(commit, path);
struct util_info* info;
info = commit->object.util; util = commit->object.util;
num_commits++; num_blame_lines = util->num_lines;
if(DEBUG) blame_lines = xmalloc(sizeof(struct commit *) * num_blame_lines);
printf("\nProcessing commit: %d %s\n", num_commits, sha1_to_hex(commit->object.sha1)); for (i = 0; i < num_blame_lines; i++)
for(parents = commit->parents; blame_lines[i] = NULL;
parents != NULL; parents = parents->next) {
struct commit* parent = parents->item;
if(parse_commit(parent) < 0) lines_left = num_blame_lines;
die("parse_commit error"); blame_p = xmalloc(sizeof(int) * num_blame_lines);
new_lines = xmalloc(sizeof(int) * num_blame_lines);
do {
struct commit_list *parents;
int num_parents;
struct util_info *util;
if(DEBUG) if (DEBUG)
printf("parent: %s\n", sha1_to_hex(parent->object.sha1)); printf("\nProcessing commit: %d %s\n", num_commits,
sha1_to_hex(commit->object.sha1));
if(fill_util_info(parent, path)) if (lines_left == 0)
continue; return;
// Temporarily assign everything to the parent. num_commits++;
int num_blame = 0; memset(blame_p, 0, sizeof(int) * num_blame_lines);
for(i = 0; i < num_blame_lines; i++) { new_lines_len = 0;
if(blame_lines[i] == commit) { num_parents = 0;
num_blame++; for (parents = commit->parents;
blame_lines[i] = parent; parents != NULL; parents = parents->next)
} num_parents++;
}
if(num_blame == 0) if(num_parents == 0)
continue; *initial = commit;
struct patch* patch = get_patch(parent, commit); if(fill_util_info(commit, path))
if(patch->num == 0) { continue;
copy_line_map(parent, commit);
} else {
alloc_line_map(parent);
fill_line_map(parent, commit, patch);
}
for(i = 0; i < patch->num; i++) { alloc_line_map(commit);
int l; util = commit->object.util;
for(l = 0; l < patch->chunks[i].len2; l++) {
int mapped_line = map_line(commit, patch->chunks[i].off2 + l);
if(mapped_line != -1 && blame_lines[mapped_line] == parent)
blame_lines[mapped_line] = commit;
}
}
free_patch(patch);
}
}
}
#define SEEN 1 for (parents = commit->parents;
struct commit_list* get_commit_list(struct commit* commit, const char* pathname) parents != NULL; parents = parents->next) {
{ struct commit *parent = parents->item;
struct commit_list* ret = NULL; struct patch *patch;
struct commit_list* process = NULL;
unsigned char sha1[20];
commit_list_insert(commit, &process); if (parse_commit(parent) < 0)
die("parse_commit error");
while(process) { if (DEBUG)
struct commit* com = pop_commit(&process); printf("parent: %s\n",
if(com->object.flags & SEEN) sha1_to_hex(parent->object.sha1));
continue;
com->object.flags |= SEEN; if(fill_util_info(parent, path)) {
commit_list_insert(com, &ret); num_parents--;
struct commit_list* parents; continue;
}
parse_commit(com); patch = get_patch(parent, commit);
alloc_line_map(parent);
fill_line_map(parent, commit, patch);
for(parents = com->parents; for (i = 0; i < patch->num; i++) {
parents != NULL; parents = parents->next) { int l;
struct commit* parent = parents->item; for (l = 0; l < patch->chunks[i].len2; l++) {
int mapped_line =
map_line(commit, patch->chunks[i].off2 + l);
if (mapped_line != -1) {
blame_p[mapped_line]++;
if (blame_p[mapped_line] == num_parents)
new_lines[new_lines_len++] = mapped_line;
}
}
}
free_patch(patch);
}
parse_commit(parent); if (DEBUG)
printf("parents: %d\n", num_parents);
if(!get_blob_sha1(parent->tree, pathname, sha1)) for (i = 0; i < new_lines_len; i++) {
commit_list_insert(parent, &process); int mapped_line = new_lines[i];
} if (blame_lines[mapped_line] == NULL) {
} blame_lines[mapped_line] = commit;
lines_left--;
return ret; if (DEBUG)
printf("blame: mapped: %d i: %d\n",
mapped_line, i);
}
}
} while ((commit = get_revision(rev)) != NULL);
} }
int main(int argc, const char **argv) int main(int argc, const char **argv)
{ {
unsigned char sha1[20]; int i;
struct commit *commit; struct commit *initial = NULL;
const char* filename; unsigned char sha1[20];
int i; const char* filename;
int num_args;
const char* args[10];
struct rev_info rev;
setup_git_directory(); setup_git_directory();
if (argc != 3) if (argc != 3)
die("Usage: blame commit-ish file"); die("Usage: blame commit-ish file");
if (get_sha1(argv[1], sha1))
die("get_sha1 failed");
commit = lookup_commit_reference(sha1);
filename = argv[2];
struct commit_list* list = get_commit_list(commit, filename);
sort_in_topological_order(&list, 1);
if(fill_util_info(commit, filename)) {
printf("%s not found in %s\n", filename, argv[1]);
return 0;
}
alloc_line_map(commit);
struct util_info* util = commit->object.util;
num_blame_lines = util->num_lines;
blame_lines = xmalloc(sizeof(struct commit*)*num_blame_lines);
for(i = 0; i < num_blame_lines; i++) { filename = argv[2];
blame_lines[i] = commit;
((struct util_info*) commit->object.util)->line_map[i] = i; {
} struct commit* commit;
if (get_sha1(argv[1], sha1))
die("get_sha1 failed");
commit = lookup_commit_reference(sha1);
process_commits(list, filename); if (fill_util_info(commit, filename)) {
printf("%s not found in %s\n", filename, argv[1]);
return 1;
}
}
for(i = 0; i < num_blame_lines; i++) { num_args = 0;
printf("%d %s\n", i+1-1, sha1_to_hex(blame_lines[i]->object.sha1)); args[num_args++] = NULL;
// printf("%d %s\n", i+1-1, find_unique_abbrev(blame_lines[i]->object.sha1, 6)); args[num_args++] = "--topo-order";
} args[num_args++] = "--remove-empty";
args[num_args++] = argv[1];
args[num_args++] = "--";
args[num_args++] = filename;
args[num_args] = NULL;
if(DEBUG) { setup_revisions(num_args, args, &rev, "HEAD");
printf("num get patch: %d\n", num_get_patch); prepare_revision_walk(&rev);
printf("num commits: %d\n", num_commits); process_commits(&rev, filename, &initial);
}
return 0; for (i = 0; i < num_blame_lines; i++) {
struct commit *c = blame_lines[i];
if (!c)
c = initial;
printf("%d %.8s\n", i, sha1_to_hex(c->object.sha1));
// printf("%d %s\n", i, find_unique_abbrev(blame_lines[i]->object.sha1, 6));
}
if (DEBUG) {
printf("num get patch: %d\n", num_get_patch);
printf("num commits: %d\n", num_commits);
printf("patch time: %f\n", patch_time / 1000000.0);
printf("initial: %s\n", sha1_to_hex(initial->object.sha1));
}
return 0;
} }