--- /dev/null
+#include <assert.h>
+
+#include "cache.h"
+#include "refs.h"
+#include "tag.h"
+#include "commit.h"
+#include "tree.h"
+#include "blob.h"
+#include "epoch.h"
+#include "diff.h"
+
+#define DEBUG 0
+
+struct commit** blame_lines;
+int num_blame_lines;
+
+struct util_info
+{
+ int* line_map;
+ int num_lines;
+ unsigned char sha1[20]; /* blob sha, not commit! */
+ char* buf;
+ unsigned long size;
+// const char* path;
+};
+
+struct chunk
+{
+ int off1, len1; // ---
+ int off2, len2; // +++
+};
+
+struct patch
+{
+ struct chunk* chunks;
+ int num;
+};
+
+static void get_blob(struct commit* commit);
+
+int num_get_patch = 0;
+int num_commits = 0;
+
+struct patch* get_patch(struct commit* commit, struct commit* other)
+{
+ struct patch* ret = xmalloc(sizeof(struct patch));
+ ret->chunks = NULL;
+ ret->num = 0;
+
+ struct util_info* info_c = (struct util_info*) commit->object.util;
+ struct util_info* info_o = (struct util_info*) other->object.util;
+
+ if(!memcmp(info_c->sha1, info_o->sha1, 20))
+ return ret;
+
+ get_blob(commit);
+ get_blob(other);
+
+ FILE* fout = fopen("/tmp/git-blame-tmp1", "w");
+ if(!fout)
+ die("fopen tmp1 failed: %s", strerror(errno));
+
+ if(fwrite(info_c->buf, info_c->size, 1, fout) != 1)
+ die("fwrite 1 failed: %s", strerror(errno));
+ fclose(fout);
+
+ fout = fopen("/tmp/git-blame-tmp2", "w");
+ if(!fout)
+ die("fopen tmp2 failed: %s", strerror(errno));
+
+ if(fwrite(info_o->buf, info_o->size, 1, fout) != 1)
+ die("fwrite 2 failed: %s", strerror(errno));
+ fclose(fout);
+
+ FILE* fin = popen("diff -u0 /tmp/git-blame-tmp1 /tmp/git-blame-tmp2", "r");
+ if(!fin)
+ die("popen failed: %s", strerror(errno));
+
+ char buf[1024];
+ while(fgets(buf, sizeof(buf), fin)) {
+ if(buf[0] != '@' || buf[1] != '@')
+ continue;
+
+ if(DEBUG)
+ printf("chunk line: %s", buf);
+ ret->num++;
+ ret->chunks = xrealloc(ret->chunks, sizeof(struct chunk)*ret->num);
+ struct chunk* chunk = &ret->chunks[ret->num-1];
+
+ assert(!strncmp(buf, "@@ -", 4));
+
+ char* start = 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;
+ sp = index(start, ' ');
+ *sp = '\0';
+ 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 = ' ';
+
+ if(chunk->off1 > 0)
+ chunk->off1 -= 1;
+ if(chunk->off2 > 0)
+ chunk->off2 -= 1;
+
+ assert(chunk->off1 >= 0);
+ assert(chunk->off2 >= 0);
+ }
+ fclose(fin);
+
+ num_get_patch++;
+ return ret;
+}
+
+void free_patch(struct patch* p)
+{
+ free(p->chunks);
+ free(p);
+}
+
+static int get_blob_sha1_internal(unsigned char *sha1, const char *base, int baselen,
+ const char *pathname, unsigned mode, int stage);
+
+
+static unsigned char blob_sha1[20];
+static int get_blob_sha1(struct tree* t, const char* pathname, unsigned char* sha1)
+{
+ const char *pathspec[2];
+ pathspec[0] = pathname;
+ pathspec[1] = NULL;
+ 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++) {
+ if(blob_sha1[i] != 0)
+ break;
+ }
+
+ if(i == 20)
+ return -1;
+
+ memcpy(sha1, blob_sha1, 20);
+ return 0;
+}
+
+static int get_blob_sha1_internal(unsigned char *sha1, const char *base, int baselen,
+ const char *pathname, unsigned mode, int stage)
+{
+// printf("Got blob: %s base: '%s' baselen: %d pathname: '%s' mode: %o stage: %d\n",
+// sha1_to_hex(sha1), base, baselen, pathname, mode, stage);
+
+ if(S_ISDIR(mode))
+ return READ_TREE_RECURSIVE;
+
+ memcpy(blob_sha1, sha1, 20);
+ return -1;
+}
+
+static void get_blob(struct commit* commit)
+{
+ struct util_info* info = commit->object.util;
+ char type[20];
+
+ if(info->buf)
+ return;
+
+ info->buf = read_sha1_file(info->sha1, type, &info->size);
+ assert(!strcmp(type, "blob"));
+}
+
+void print_patch(struct patch* p)
+{
+ printf("Num chunks: %d\n", p->num);
+ int 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);
+ }
+}
+
+
+// p is a patch from commit to other.
+void fill_line_map(struct commit* commit, struct commit* other, struct patch* p)
+{
+ int num_lines = ((struct util_info*) commit->object.util)->num_lines;
+ int* line_map = ((struct util_info*) commit->object.util)->line_map;
+ int num_lines2 = ((struct util_info*) other->object.util)->num_lines;
+ int* line_map2 = ((struct util_info*) other->object.util)->line_map;
+ int cur_chunk = 0;
+ int i1, i2;
+
+ if(p->num && DEBUG)
+ print_patch(p);
+
+ for(i1 = 0; i1 < num_lines; i1++)
+ line_map[i1] = -1;
+
+ if(DEBUG)
+ printf("num lines 1: %d num lines 2: %d\n", num_lines, num_lines2);
+
+ for(i1 = 0, i2 = 0; i1 < num_lines; i1++, i2++) {
+ if(DEBUG > 1)
+ printf("%d %d\n", i1, i2);
+
+ if(i2 >= num_lines2)
+ break;
+
+ line_map[i1] = line_map2[i2];
+
+ struct chunk* chunk = NULL;
+ if(cur_chunk < p->num)
+ chunk = &p->chunks[cur_chunk];
+
+ if(chunk && chunk->off1 == i1) {
+ i2 = chunk->off2;
+
+ if(chunk->len1 > 0)
+ i1 += chunk->len1-1;
+ if(chunk->len2 > 0)
+ i2 += chunk->len2-1;
+ cur_chunk++;
+ }
+ }
+}
+
+int map_line(struct commit* commit, int line)
+{
+ struct util_info* info = commit->object.util;
+ assert(line >= 0 && line < info->num_lines);
+ return info->line_map[line];
+}
+
+int fill_util_info(struct commit* commit, const char* path)
+{
+ if(commit->object.util)
+ return 0;
+
+ 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))
+ return -1;
+
+ return 0;
+}
+
+void alloc_line_map(struct commit* commit)
+{
+ struct util_info* util = commit->object.util;
+
+ if(util->line_map)
+ return;
+
+ get_blob(commit);
+
+ int i;
+ util->num_lines = 0;
+ for(i = 0; i < util->size; i++) {
+ if(util->buf[i] == '\n')
+ util->num_lines++;
+ }
+ util->line_map = xmalloc(sizeof(int)*util->num_lines);
+}
+
+void copy_line_map(struct commit* dst, struct commit* src)
+{
+ struct util_info* u_dst = dst->object.util;
+ struct util_info* u_src = src->object.util;
+
+ u_dst->line_map = u_src->line_map;
+ u_dst->num_lines = u_src->num_lines;
+ u_dst->buf = u_src->buf;
+ u_dst->size = u_src->size;
+}
+
+void process_commits(struct commit_list* list, const char* path)
+{
+ int i;
+
+ while(list) {
+ struct commit* commit = pop_commit(&list);
+ struct commit_list* parents;
+ struct util_info* info;
+
+ info = commit->object.util;
+ num_commits++;
+ if(DEBUG)
+ printf("\nProcessing commit: %d %s\n", num_commits, sha1_to_hex(commit->object.sha1));
+ for(parents = commit->parents;
+ parents != NULL; parents = parents->next) {
+ struct commit* parent = parents->item;
+
+ if(parse_commit(parent) < 0)
+ die("parse_commit error");
+
+ if(DEBUG)
+ printf("parent: %s\n", sha1_to_hex(parent->object.sha1));
+
+ if(fill_util_info(parent, path))
+ continue;
+
+ // Temporarily assign everything to the parent.
+ int num_blame = 0;
+ for(i = 0; i < num_blame_lines; i++) {
+ if(blame_lines[i] == commit) {
+ num_blame++;
+ blame_lines[i] = parent;
+ }
+ }
+
+ if(num_blame == 0)
+ continue;
+
+ struct patch* patch = get_patch(parent, commit);
+ if(patch->num == 0) {
+ copy_line_map(parent, commit);
+ } else {
+ alloc_line_map(parent);
+ fill_line_map(parent, commit, patch);
+ }
+
+ for(i = 0; i < patch->num; i++) {
+ int l;
+ 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
+struct commit_list* get_commit_list(struct commit* commit, const char* pathname)
+{
+ struct commit_list* ret = NULL;
+ struct commit_list* process = NULL;
+ unsigned char sha1[20];
+
+ commit_list_insert(commit, &process);
+
+ while(process) {
+ struct commit* com = pop_commit(&process);
+ if(com->object.flags & SEEN)
+ continue;
+
+ com->object.flags |= SEEN;
+ commit_list_insert(com, &ret);
+ struct commit_list* parents;
+
+ parse_commit(com);
+
+ for(parents = com->parents;
+ parents != NULL; parents = parents->next) {
+ struct commit* parent = parents->item;
+
+ parse_commit(parent);
+
+ if(!get_blob_sha1(parent->tree, pathname, sha1))
+ commit_list_insert(parent, &process);
+ }
+ }
+
+ return ret;
+}
+
+int main(int argc, const char **argv)
+{
+ unsigned char sha1[20];
+ struct commit *commit;
+ const char* filename;
+ int i;
+
+ setup_git_directory();
+
+ if (argc != 3)
+ 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++) {
+ blame_lines[i] = commit;
+
+ ((struct util_info*) commit->object.util)->line_map[i] = i;
+ }
+
+ process_commits(list, filename);
+
+ for(i = 0; i < num_blame_lines; i++) {
+ printf("%d %s\n", i+1-1, sha1_to_hex(blame_lines[i]->object.sha1));
+// printf("%d %s\n", i+1-1, 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);
+ }
+
+ return 0;
+}
*/
#include <stdlib.h>
+#include <string.h>
+#include <zlib.h>
#include "delta.h"
-#include "zlib.h"
/* block size: min = 16, max = 64k, power of 2 */
#define MIN(a, b) ((a) < (b) ? (a) : (b))
#define GR_PRIME 0x9e370001
-#define HASH(v, b) (((unsigned int)(v) * GR_PRIME) >> (32 - (b)))
-
-static unsigned int hashbits(unsigned int size)
-{
- unsigned int val = 1, bits = 0;
- while (val < size && bits < 32) {
- val <<= 1;
- bits++;
- }
- return bits ? bits: 1;
-}
-
-typedef struct s_chanode {
- struct s_chanode *next;
- int icurr;
-} chanode_t;
-
-typedef struct s_chastore {
- int isize, nsize;
- chanode_t *ancur;
-} chastore_t;
-
-static void cha_init(chastore_t *cha, int isize, int icount)
-{
- cha->isize = isize;
- cha->nsize = icount * isize;
- cha->ancur = NULL;
-}
-
-static void *cha_alloc(chastore_t *cha)
-{
- chanode_t *ancur;
- void *data;
+#define HASH(v, shift) (((unsigned int)(v) * GR_PRIME) >> (shift))
- ancur = cha->ancur;
- if (!ancur || ancur->icurr == cha->nsize) {
- ancur = malloc(sizeof(chanode_t) + cha->nsize);
- if (!ancur)
- return NULL;
- ancur->icurr = 0;
- ancur->next = cha->ancur;
- cha->ancur = ancur;
- }
-
- data = (void *)ancur + sizeof(chanode_t) + ancur->icurr;
- ancur->icurr += cha->isize;
- return data;
-}
-
-static void cha_free(chastore_t *cha)
-{
- chanode_t *cur = cha->ancur;
- while (cur) {
- chanode_t *tmp = cur;
- cur = cur->next;
- free(tmp);
- }
-}
-
-typedef struct s_bdrecord {
- struct s_bdrecord *next;
- unsigned int fp;
+struct index {
const unsigned char *ptr;
-} bdrecord_t;
-
-typedef struct s_bdfile {
- chastore_t cha;
- unsigned int fphbits;
- bdrecord_t **fphash;
-} bdfile_t;
+ unsigned int val;
+ struct index *next;
+};
-static int delta_prepare(const unsigned char *buf, int bufsize, bdfile_t *bdf)
+static struct index ** delta_index(const unsigned char *buf,
+ unsigned long bufsize,
+ unsigned int *hash_shift)
{
- unsigned int fphbits;
- int i, hsize;
- const unsigned char *data, *top;
- bdrecord_t *brec;
- bdrecord_t **fphash;
-
- fphbits = hashbits(bufsize / BLK_SIZE + 1);
- hsize = 1 << fphbits;
- fphash = malloc(hsize * sizeof(bdrecord_t *));
- if (!fphash)
- return -1;
- for (i = 0; i < hsize; i++)
- fphash[i] = NULL;
- cha_init(&bdf->cha, sizeof(bdrecord_t), hsize / 4 + 1);
-
- top = buf + bufsize;
- data = buf + (bufsize / BLK_SIZE) * BLK_SIZE;
- if (data == top)
+ unsigned int hsize, hshift, entries, blksize, i;
+ const unsigned char *data;
+ struct index *entry, **hash;
+ void *mem;
+
+ /* determine index hash size */
+ entries = (bufsize + BLK_SIZE - 1) / BLK_SIZE;
+ hsize = entries / 4;
+ for (i = 4; (1 << i) < hsize && i < 16; i++);
+ hsize = 1 << i;
+ hshift = 32 - i;
+ *hash_shift = hshift;
+
+ /* allocate lookup index */
+ mem = malloc(hsize * sizeof(*hash) + entries * sizeof(*entry));
+ if (!mem)
+ return NULL;
+ hash = mem;
+ entry = mem + hsize * sizeof(*hash);
+ memset(hash, 0, hsize * sizeof(*hash));
+
+ /* then populate it */
+ data = buf + entries * BLK_SIZE - BLK_SIZE;
+ blksize = bufsize - (data - buf);
+ while (data >= buf) {
+ unsigned int val = adler32(0, data, blksize);
+ i = HASH(val, hshift);
+ entry->ptr = data;
+ entry->val = val;
+ entry->next = hash[i];
+ hash[i] = entry++;
+ blksize = BLK_SIZE;
data -= BLK_SIZE;
+ }
- for ( ; data >= buf; data -= BLK_SIZE) {
- brec = cha_alloc(&bdf->cha);
- if (!brec) {
- cha_free(&bdf->cha);
- free(fphash);
- return -1;
- }
- brec->fp = adler32(0, data, MIN(BLK_SIZE, top - data));
- brec->ptr = data;
- i = HASH(brec->fp, fphbits);
- brec->next = fphash[i];
- fphash[i] = brec;
- }
-
- bdf->fphbits = fphbits;
- bdf->fphash = fphash;
-
- return 0;
-}
-
-static void delta_cleanup(bdfile_t *bdf)
-{
- free(bdf->fphash);
- cha_free(&bdf->cha);
+ return hash;
}
+/* provide the size of the copy opcode given the block offset and size */
#define COPYOP_SIZE(o, s) \
(!!(o & 0xff) + !!(o & 0xff00) + !!(o & 0xff0000) + !!(o & 0xff000000) + \
!!(s & 0xff) + !!(s & 0xff00) + 1)
+/* the maximum size for any opcode */
+#define MAX_OP_SIZE COPYOP_SIZE(0xffffffff, 0xffffffff)
+
void *diff_delta(void *from_buf, unsigned long from_size,
void *to_buf, unsigned long to_size,
unsigned long *delta_size,
unsigned long max_size)
{
- int i, outpos, outsize, inscnt, csize, msize, moff;
- unsigned int fp;
- const unsigned char *ref_data, *ref_top, *data, *top, *ptr1, *ptr2;
- unsigned char *out, *orig;
- bdrecord_t *brec;
- bdfile_t bdf;
+ unsigned int i, outpos, outsize, inscnt, hash_shift;
+ const unsigned char *ref_data, *ref_top, *data, *top;
+ unsigned char *out;
+ struct index *entry, **hash;
- if (!from_size || !to_size || delta_prepare(from_buf, from_size, &bdf))
+ if (!from_size || !to_size)
+ return NULL;
+ hash = delta_index(from_buf, from_size, &hash_shift);
+ if (!hash)
return NULL;
-
+
outpos = 0;
outsize = 8192;
+ if (max_size && outsize >= max_size)
+ outsize = max_size + MAX_OP_SIZE + 1;
out = malloc(outsize);
if (!out) {
- delta_cleanup(&bdf);
+ free(hash);
return NULL;
}
}
inscnt = 0;
- moff = 0;
- while (data < top) {
- msize = 0;
- fp = adler32(0, data, MIN(top - data, BLK_SIZE));
- i = HASH(fp, bdf.fphbits);
- for (brec = bdf.fphash[i]; brec; brec = brec->next) {
- if (brec->fp == fp) {
- csize = ref_top - brec->ptr;
- if (csize > top - data)
- csize = top - data;
- for (ptr1 = brec->ptr, ptr2 = data;
- csize && *ptr1 == *ptr2;
- csize--, ptr1++, ptr2++);
- csize = ptr1 - brec->ptr;
- if (csize > msize) {
- moff = brec->ptr - ref_data;
- msize = csize;
- if (msize >= 0x10000) {
- msize = 0x10000;
- break;
- }
+ while (data < top) {
+ unsigned int moff = 0, msize = 0;
+ unsigned int blksize = MIN(top - data, BLK_SIZE);
+ unsigned int val = adler32(0, data, blksize);
+ i = HASH(val, hash_shift);
+ for (entry = hash[i]; entry; entry = entry->next) {
+ const unsigned char *ref = entry->ptr;
+ const unsigned char *src = data;
+ unsigned int ref_size = ref_top - ref;
+ if (entry->val != val)
+ continue;
+ if (ref_size > top - src)
+ ref_size = top - src;
+ while (ref_size && *src++ == *ref) {
+ ref++;
+ ref_size--;
+ }
+ ref_size = ref - entry->ptr;
+ if (ref_size > msize) {
+ /* this is our best match so far */
+ moff = entry->ptr - ref_data;
+ msize = ref_size;
+ if (msize >= 0x10000) {
+ msize = 0x10000;
+ break;
}
}
}
inscnt = 0;
}
} else {
+ unsigned char *op;
+
if (inscnt) {
out[outpos - inscnt - 1] = inscnt;
inscnt = 0;
}
data += msize;
- orig = out + outpos++;
+ op = out + outpos++;
i = 0x80;
if (moff & 0xff) { out[outpos++] = moff; i |= 0x01; }
msize >>= 8;
if (msize & 0xff) { out[outpos++] = msize; i |= 0x20; }
- *orig = i;
- }
-
- if (max_size && outpos > max_size) {
- free(out);
- delta_cleanup(&bdf);
- return NULL;
+ *op = i;
}
- /* next time around the largest possible output is 1 + 4 + 3 */
- if (outpos > outsize - 8) {
+ if (outpos >= outsize - MAX_OP_SIZE) {
void *tmp = out;
outsize = outsize * 3 / 2;
- out = realloc(out, outsize);
+ if (max_size && outsize >= max_size)
+ outsize = max_size + MAX_OP_SIZE + 1;
+ if (max_size && outpos > max_size)
+ out = NULL;
+ else
+ out = realloc(out, outsize);
if (!out) {
free(tmp);
- delta_cleanup(&bdf);
+ free(hash);
return NULL;
}
}
if (inscnt)
out[outpos - inscnt - 1] = inscnt;
- delta_cleanup(&bdf);
+ free(hash);
*delta_size = outpos;
return out;
}