diff --git a/builtin-blame.c b/builtin-blame.c
index 1a752b95bb32578cd3ecb69153b55f605b8bfdc3..35471fc2615992451c8c5b51a346fe171029b572 100644 (file)
--- a/builtin-blame.c
+++ b/builtin-blame.c
#include "quote.h"
#include "xdiff-interface.h"
#include "cache-tree.h"
#include "quote.h"
#include "xdiff-interface.h"
#include "cache-tree.h"
+#include "path-list.h"
+#include "mailmap.h"
static char blame_usage[] =
static char blame_usage[] =
-"git-blame [-c] [-l] [-t] [-f] [-n] [-p] [-L n,m] [-S <revs-file>] [-M] [-C] [-C] [--contents <filename>] [--incremental] [commit] [--] file\n"
-" -c, --compatibility Use the same output mode as git-annotate (Default: off)\n"
+"git-blame [-c] [-b] [-l] [--root] [-t] [-f] [-n] [-s] [-p] [-L n,m] [-S <revs-file>] [-M] [-C] [-C] [--contents <filename>] [--incremental] [commit] [--] file\n"
+" -c Use the same output mode as git-annotate (Default: off)\n"
" -b Show blank SHA-1 for boundary commits (Default: off)\n"
" -b Show blank SHA-1 for boundary commits (Default: off)\n"
-" -l, --long Show long commit SHA1 (Default: off)\n"
+" -l Show long commit SHA1 (Default: off)\n"
" --root Do not treat root commits as boundaries (Default: off)\n"
" --root Do not treat root commits as boundaries (Default: off)\n"
-" -t, --time Show raw timestamp (Default: off)\n"
+" -t Show raw timestamp (Default: off)\n"
" -f, --show-name Show original filename (Default: auto)\n"
" -n, --show-number Show original linenumber (Default: off)\n"
" -f, --show-name Show original filename (Default: auto)\n"
" -n, --show-number Show original linenumber (Default: off)\n"
+" -s Suppress author name and timestamp (Default: off)\n"
" -p, --porcelain Show in a format designed for machine consumption\n"
" -L n,m Process only line range n,m, counting from 1\n"
" -M, -C Find line movements within and across files\n"
" -p, --porcelain Show in a format designed for machine consumption\n"
" -L n,m Process only line range n,m, counting from 1\n"
" -M, -C Find line movements within and across files\n"
static int blank_boundary;
static int incremental;
static int cmd_is_annotate;
static int blank_boundary;
static int incremental;
static int cmd_is_annotate;
+static struct path_list mailmap;
#ifndef DEBUG
#define DEBUG 0
#ifndef DEBUG
#define DEBUG 0
#define PICKAXE_BLAME_MOVE 01
#define PICKAXE_BLAME_COPY 02
#define PICKAXE_BLAME_COPY_HARDER 04
#define PICKAXE_BLAME_MOVE 01
#define PICKAXE_BLAME_COPY 02
#define PICKAXE_BLAME_COPY_HARDER 04
+#define PICKAXE_BLAME_COPY_HARDEST 010
/*
* blame for a blame_entry with score lower than these thresholds
/*
* blame for a blame_entry with score lower than these thresholds
static char *fill_origin_blob(struct origin *o, mmfile_t *file)
{
if (!o->file.ptr) {
static char *fill_origin_blob(struct origin *o, mmfile_t *file)
{
if (!o->file.ptr) {
- char type[10];
+ enum object_type type;
num_read_blob++;
num_read_blob++;
- file->ptr = read_sha1_file(o->blob_sha1, type,
+ file->ptr = read_sha1_file(o->blob_sha1, &type,
(unsigned long *)(&(file->size)));
o->file = *file;
}
(unsigned long *)(&(file->size)));
o->file = *file;
}
int *lineno;
};
int *lineno;
};
-static int cmp_suspect(struct origin *a, struct origin *b)
+static inline int same_suspect(struct origin *a, struct origin *b)
{
{
- int cmp = hashcmp(a->commit->object.sha1, b->commit->object.sha1);
- if (cmp)
- return cmp;
- return strcmp(a->path, b->path);
+ if (a == b)
+ return 1;
+ if (a->commit != b->commit)
+ return 0;
+ return !strcmp(a->path, b->path);
}
}
-#define cmp_suspect(a, b) ( ((a)==(b)) ? 0 : cmp_suspect(a,b) )
-
static void sanity_check_refcnt(struct scoreboard *);
/*
static void sanity_check_refcnt(struct scoreboard *);
/*
struct blame_entry *ent, *next;
for (ent = sb->ent; ent && (next = ent->next); ent = next) {
struct blame_entry *ent, *next;
for (ent = sb->ent; ent && (next = ent->next); ent = next) {
- if (!cmp_suspect(ent->suspect, next->suspect) &&
+ if (same_suspect(ent->suspect, next->suspect) &&
ent->guilty == next->guilty &&
ent->s_lno + ent->num_lines == next->s_lno) {
ent->num_lines += next->num_lines;
ent->guilty == next->guilty &&
ent->s_lno + ent->num_lines == next->s_lno) {
ent->num_lines += next->num_lines;
static int fill_blob_sha1(struct origin *origin)
{
unsigned mode;
static int fill_blob_sha1(struct origin *origin)
{
unsigned mode;
- char type[10];
if (!is_null_sha1(origin->blob_sha1))
return 0;
if (!is_null_sha1(origin->blob_sha1))
return 0;
origin->path,
origin->blob_sha1, &mode))
goto error_out;
origin->path,
origin->blob_sha1, &mode))
goto error_out;
- if (sha1_object_info(origin->blob_sha1, type, NULL) ||
- strcmp(type, blob_type))
+ if (sha1_object_info(origin->blob_sha1, NULL) != OBJ_BLOB)
goto error_out;
return 0;
error_out:
goto error_out;
return 0;
error_out:
int last_in_target = -1;
for (e = sb->ent; e; e = e->next) {
int last_in_target = -1;
for (e = sb->ent; e; e = e->next) {
- if (e->guilty || cmp_suspect(e->suspect, target))
+ if (e->guilty || !same_suspect(e->suspect, target))
continue;
if (last_in_target < e->s_lno + e->num_lines)
last_in_target = e->s_lno + e->num_lines;
continue;
if (last_in_target < e->s_lno + e->num_lines)
last_in_target = e->s_lno + e->num_lines;
struct blame_entry *e;
for (e = sb->ent; e; e = e->next) {
struct blame_entry *e;
for (e = sb->ent; e; e = e->next) {
- if (e->guilty || cmp_suspect(e->suspect, target))
+ if (e->guilty || !same_suspect(e->suspect, target))
continue;
if (same <= e->s_lno)
continue;
continue;
if (same <= e->s_lno)
continue;
memcpy(best_so_far, this, sizeof(struct blame_entry [3]));
}
memcpy(best_so_far, this, sizeof(struct blame_entry [3]));
}
+/*
+ * We are looking at a part of the final image represented by
+ * ent (tlno and same are offset by ent->s_lno).
+ * tlno is where we are looking at in the final image.
+ * up to (but not including) same match preimage.
+ * plno is where we are looking at in the preimage.
+ *
+ * <-------------- final image ---------------------->
+ * <------ent------>
+ * ^tlno ^same
+ * <---------preimage----->
+ * ^plno
+ *
+ * All line numbers are 0-based.
+ */
+static void handle_split(struct scoreboard *sb,
+ struct blame_entry *ent,
+ int tlno, int plno, int same,
+ struct origin *parent,
+ struct blame_entry *split)
+{
+ if (ent->num_lines <= tlno)
+ return;
+ if (tlno < same) {
+ struct blame_entry this[3];
+ tlno += ent->s_lno;
+ same += ent->s_lno;
+ split_overlap(this, ent, tlno, plno, same, parent);
+ copy_split_if_better(sb, split, this);
+ decref_split(this);
+ }
+}
+
/*
* Find the lines from parent that are the same as ent so that
* we can pass blames to it. file_p has the blob contents for
/*
* Find the lines from parent that are the same as ent so that
* we can pass blames to it. file_p has the blob contents for
patch = compare_buffer(file_p, &file_o, 1);
patch = compare_buffer(file_p, &file_o, 1);
+ /*
+ * file_o is a part of final image we are annotating.
+ * file_p partially may match that image.
+ */
memset(split, 0, sizeof(struct blame_entry [3]));
plno = tlno = 0;
for (i = 0; i < patch->num; i++) {
struct chunk *chunk = &patch->chunks[i];
memset(split, 0, sizeof(struct blame_entry [3]));
plno = tlno = 0;
for (i = 0; i < patch->num; i++) {
struct chunk *chunk = &patch->chunks[i];
- /* tlno to chunk->same are the same as ent */
- if (ent->num_lines <= tlno)
- break;
- if (tlno < chunk->same) {
- struct blame_entry this[3];
- split_overlap(this, ent,
- tlno + ent->s_lno, plno,
- chunk->same + ent->s_lno,
- parent);
- copy_split_if_better(sb, split, this);
- decref_split(this);
- }
+ handle_split(sb, ent, tlno, plno, chunk->same, parent, split);
plno = chunk->p_next;
tlno = chunk->t_next;
}
plno = chunk->p_next;
tlno = chunk->t_next;
}
+ /* remainder, if any, all match the preimage */
+ handle_split(sb, ent, tlno, plno, ent->num_lines, parent, split);
free_patch(patch);
}
free_patch(patch);
}
while (made_progress) {
made_progress = 0;
for (e = sb->ent; e; e = e->next) {
while (made_progress) {
made_progress = 0;
for (e = sb->ent; e; e = e->next) {
- if (e->guilty || cmp_suspect(e->suspect, target))
+ if (e->guilty || !same_suspect(e->suspect, target))
continue;
find_copy_in_blob(sb, e, parent, split, &file_p);
if (split[1].suspect &&
continue;
find_copy_in_blob(sb, e, parent, split, &file_p);
if (split[1].suspect &&
struct blame_list *blame_list = NULL;
for (e = sb->ent, num_ents = 0; e; e = e->next)
struct blame_list *blame_list = NULL;
for (e = sb->ent, num_ents = 0; e; e = e->next)
- if (!e->guilty && !cmp_suspect(e->suspect, target))
+ if (!e->guilty && same_suspect(e->suspect, target))
num_ents++;
if (num_ents) {
blame_list = xcalloc(num_ents, sizeof(struct blame_list));
for (e = sb->ent, i = 0; e; e = e->next)
num_ents++;
if (num_ents) {
blame_list = xcalloc(num_ents, sizeof(struct blame_list));
for (e = sb->ent, i = 0; e; e = e->next)
- if (!e->guilty && !cmp_suspect(e->suspect, target))
+ if (!e->guilty && same_suspect(e->suspect, target))
blame_list[i++].ent = e;
}
*num_ents_p = num_ents;
blame_list[i++].ent = e;
}
*num_ents_p = num_ents;
* and this code needs to be after diff_setup_done(), which
* usually makes find-copies-harder imply copy detection.
*/
* and this code needs to be after diff_setup_done(), which
* usually makes find-copies-harder imply copy detection.
*/
- if ((opt & PICKAXE_BLAME_COPY_HARDER) &&
- (!porigin || strcmp(target->path, porigin->path)))
+ if ((opt & PICKAXE_BLAME_COPY_HARDEST)
+ || ((opt & PICKAXE_BLAME_COPY_HARDER)
+ && (!porigin || strcmp(target->path, porigin->path))))
diff_opts.find_copies_harder = 1;
if (is_null_sha1(target->commit->object.sha1))
diff_opts.find_copies_harder = 1;
if (is_null_sha1(target->commit->object.sha1))
origin->file.ptr = NULL;
}
for (e = sb->ent; e; e = e->next) {
origin->file.ptr = NULL;
}
for (e = sb->ent; e; e = e->next) {
- if (cmp_suspect(e->suspect, origin))
+ if (!same_suspect(e->suspect, origin))
continue;
origin_incref(porigin);
origin_decref(e->suspect);
continue;
origin_incref(porigin);
origin_decref(e->suspect);
@@ -1246,29 +1277,29 @@ static void pass_blame(struct scoreboard *sb, struct origin *origin, int opt)
*/
struct commit_info
{
*/
struct commit_info
{
- char *author;
- char *author_mail;
+ const char *author;
+ const char *author_mail;
unsigned long author_time;
unsigned long author_time;
- char *author_tz;
+ const char *author_tz;
/* filled only when asked for details */
/* filled only when asked for details */
- char *committer;
- char *committer_mail;
+ const char *committer;
+ const char *committer_mail;
unsigned long committer_time;
unsigned long committer_time;
- char *committer_tz;
+ const char *committer_tz;
- char *summary;
+ const char *summary;
};
/*
* Parse author/committer line in the commit object buffer
*/
static void get_ac_line(const char *inbuf, const char *what,
};
/*
* Parse author/committer line in the commit object buffer
*/
static void get_ac_line(const char *inbuf, const char *what,
- int bufsz, char *person, char **mail,
- unsigned long *time, char **tz)
+ int bufsz, char *person, const char **mail,
+ unsigned long *time, const char **tz)
{
{
- int len;
- char *tmp, *endp;
+ int len, tzlen, maillen;
+ char *tmp, *endp, *timepos;
tmp = strstr(inbuf, what);
if (!tmp)
tmp = strstr(inbuf, what);
if (!tmp)
if (bufsz <= len) {
error_out:
/* Ugh */
if (bufsz <= len) {
error_out:
/* Ugh */
- person = *mail = *tz = "(unknown)";
+ *mail = *tz = "(unknown)";
*time = 0;
return;
}
*time = 0;
return;
}
while (*tmp != ' ')
tmp--;
*tz = tmp+1;
while (*tmp != ' ')
tmp--;
*tz = tmp+1;
+ tzlen = (person+len)-(tmp+1);
*tmp = 0;
while (*tmp != ' ')
tmp--;
*time = strtoul(tmp, NULL, 10);
*tmp = 0;
while (*tmp != ' ')
tmp--;
*time = strtoul(tmp, NULL, 10);
+ timepos = tmp;
*tmp = 0;
while (*tmp != ' ')
tmp--;
*mail = tmp + 1;
*tmp = 0;
*tmp = 0;
while (*tmp != ' ')
tmp--;
*mail = tmp + 1;
*tmp = 0;
+ maillen = timepos - tmp;
+
+ if (!mailmap.nr)
+ return;
+
+ /*
+ * mailmap expansion may make the name longer.
+ * make room by pushing stuff down.
+ */
+ tmp = person + bufsz - (tzlen + 1);
+ memmove(tmp, *tz, tzlen);
+ tmp[tzlen] = 0;
+ *tz = tmp;
+
+ tmp = tmp - (maillen + 1);
+ memmove(tmp, *mail, maillen);
+ tmp[maillen] = 0;
+ *mail = tmp;
+
+ /*
+ * Now, convert e-mail using mailmap
+ */
+ map_email(&mailmap, tmp + 1, person, tmp-person-1);
}
static void get_commit_info(struct commit *commit,
}
static void get_commit_info(struct commit *commit,
* we now need to populate them for output.
*/
if (!commit->buffer) {
* we now need to populate them for output.
*/
if (!commit->buffer) {
- char type[20];
+ enum object_type type;
unsigned long size;
commit->buffer =
unsigned long size;
commit->buffer =
- read_sha1_file(commit->object.sha1, type, &size);
+ read_sha1_file(commit->object.sha1, &type, &size);
}
ret->author = author_buf;
get_ac_line(commit->buffer, "\nauthor ",
}
ret->author = author_buf;
get_ac_line(commit->buffer, "\nauthor ",
@@ -1445,7 +1501,7 @@ static void assign_blame(struct scoreboard *sb, struct rev_info *revs, int opt)
/* Take responsibility for the remaining entries */
for (ent = sb->ent; ent; ent = ent->next)
/* Take responsibility for the remaining entries */
for (ent = sb->ent; ent; ent = ent->next)
- if (!cmp_suspect(ent->suspect, suspect))
+ if (same_suspect(ent->suspect, suspect))
found_guilty_entry(ent);
origin_decref(suspect);
found_guilty_entry(ent);
origin_decref(suspect);
#define OUTPUT_SHOW_NAME 020
#define OUTPUT_SHOW_NUMBER 040
#define OUTPUT_SHOW_SCORE 0100
#define OUTPUT_SHOW_NAME 020
#define OUTPUT_SHOW_NUMBER 040
#define OUTPUT_SHOW_SCORE 0100
+#define OUTPUT_NO_AUTHOR 0200
static void emit_porcelain(struct scoreboard *sb, struct blame_entry *ent)
{
static void emit_porcelain(struct scoreboard *sb, struct blame_entry *ent)
{
@@ -1580,10 +1637,15 @@ static void emit_other(struct scoreboard *sb, struct blame_entry *ent, int opt)
if (opt & OUTPUT_SHOW_NUMBER)
printf(" %*d", max_orig_digits,
ent->s_lno + 1 + cnt);
if (opt & OUTPUT_SHOW_NUMBER)
printf(" %*d", max_orig_digits,
ent->s_lno + 1 + cnt);
- printf(" (%-*.*s %10s %*d) ",
- longest_author, longest_author, ci.author,
- format_time(ci.author_time, ci.author_tz,
- show_raw_time),
+
+ if (!(opt & OUTPUT_NO_AUTHOR))
+ printf(" (%-*.*s %10s",
+ longest_author, longest_author,
+ ci.author,
+ format_time(ci.author_time,
+ ci.author_tz,
+ show_raw_time));
+ printf(" %*d) ",
max_digits, ent->lno + 1 + cnt);
}
do {
max_digits, ent->lno + 1 + cnt);
}
do {
@@ -1965,7 +2027,7 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con
die("Cannot lstat %s", path);
read_from = path;
}
die("Cannot lstat %s", path);
read_from = path;
}
- fin_size = st.st_size;
+ fin_size = xsize_t(st.st_size);
buf = xmalloc(fin_size+1);
mode = canon_mode(st.st_mode);
switch (st.st_mode & S_IFMT) {
buf = xmalloc(fin_size+1);
mode = canon_mode(st.st_mode);
switch (st.st_mode & S_IFMT) {
@@ -2006,7 +2068,7 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con
buf[fin_size] = 0;
origin->file.ptr = buf;
origin->file.size = fin_size;
buf[fin_size] = 0;
origin->file.ptr = buf;
origin->file.size = fin_size;
- pretend_sha1_file(buf, fin_size, blob_type, origin->blob_sha1);
+ pretend_sha1_file(buf, fin_size, OBJ_BLOB, origin->blob_sha1);
commit->util = origin;
/*
commit->util = origin;
/*
@@ -2044,7 +2106,7 @@ static struct commit *fake_working_tree_commit(const char *path, const char *con
commit->buffer = xmalloc(400);
ident = fmt_ident("Not Committed Yet", "not.committed.yet", NULL, 0);
commit->buffer = xmalloc(400);
ident = fmt_ident("Not Committed Yet", "not.committed.yet", NULL, 0);
- sprintf(commit->buffer,
+ snprintf(commit->buffer, 400,
"tree 0000000000000000000000000000000000000000\n"
"parent %s\n"
"author %s\n"
"tree 0000000000000000000000000000000000000000\n"
"parent %s\n"
"author %s\n"
int i, seen_dashdash, unk, opt;
long bottom, top, lno;
int output_option = 0;
int i, seen_dashdash, unk, opt;
long bottom, top, lno;
int output_option = 0;
+ int show_stats = 0;
const char *revs_file = NULL;
const char *final_commit_name = NULL;
const char *revs_file = NULL;
const char *final_commit_name = NULL;
- char type[10];
+ enum object_type type;
const char *bottomtop = NULL;
const char *contents_from = NULL;
const char *bottomtop = NULL;
const char *contents_from = NULL;
blank_boundary = 1;
else if (!strcmp("--root", arg))
show_root = 1;
blank_boundary = 1;
else if (!strcmp("--root", arg))
show_root = 1;
+ else if (!strcmp(arg, "--show-stats"))
+ show_stats = 1;
else if (!strcmp("-c", arg))
output_option |= OUTPUT_ANNOTATE_COMPAT;
else if (!strcmp("-t", arg))
output_option |= OUTPUT_RAW_TIMESTAMP;
else if (!strcmp("-l", arg))
output_option |= OUTPUT_LONG_OBJECT_NAME;
else if (!strcmp("-c", arg))
output_option |= OUTPUT_ANNOTATE_COMPAT;
else if (!strcmp("-t", arg))
output_option |= OUTPUT_RAW_TIMESTAMP;
else if (!strcmp("-l", arg))
output_option |= OUTPUT_LONG_OBJECT_NAME;
+ else if (!strcmp("-s", arg))
+ output_option |= OUTPUT_NO_AUTHOR;
else if (!strcmp("-S", arg) && ++i < argc)
revs_file = argv[i];
else if (!strcmp("-S", arg) && ++i < argc)
revs_file = argv[i];
- else if (!strncmp("-M", arg, 2)) {
+ else if (!prefixcmp(arg, "-M")) {
opt |= PICKAXE_BLAME_MOVE;
blame_move_score = parse_score(arg+2);
}
opt |= PICKAXE_BLAME_MOVE;
blame_move_score = parse_score(arg+2);
}
- else if (!strncmp("-C", arg, 2)) {
+ else if (!prefixcmp(arg, "-C")) {
+ /*
+ * -C enables copy from removed files;
+ * -C -C enables copy from existing files, but only
+ * when blaming a new file;
+ * -C -C -C enables copy from existing files for
+ * everybody
+ */
+ if (opt & PICKAXE_BLAME_COPY_HARDER)
+ opt |= PICKAXE_BLAME_COPY_HARDEST;
if (opt & PICKAXE_BLAME_COPY)
opt |= PICKAXE_BLAME_COPY_HARDER;
opt |= PICKAXE_BLAME_COPY | PICKAXE_BLAME_MOVE;
blame_copy_score = parse_score(arg+2);
}
if (opt & PICKAXE_BLAME_COPY)
opt |= PICKAXE_BLAME_COPY_HARDER;
opt |= PICKAXE_BLAME_COPY | PICKAXE_BLAME_MOVE;
blame_copy_score = parse_score(arg+2);
}
- else if (!strncmp("-L", arg, 2)) {
+ else if (!prefixcmp(arg, "-L")) {
if (!arg[2]) {
if (++i >= argc)
usage(blame_usage);
if (!arg[2]) {
if (++i >= argc)
usage(blame_usage);
if (fill_blob_sha1(o))
die("no such path %s in %s", path, final_commit_name);
if (fill_blob_sha1(o))
die("no such path %s in %s", path, final_commit_name);
- sb.final_buf = read_sha1_file(o->blob_sha1, type,
+ sb.final_buf = read_sha1_file(o->blob_sha1, &type,
&sb.final_buf_size);
}
num_read_blob++;
&sb.final_buf_size);
}
num_read_blob++;
die("reading graft file %s failed: %s",
revs_file, strerror(errno));
die("reading graft file %s failed: %s",
revs_file, strerror(errno));
+ read_mailmap(&mailmap, ".mailmap", NULL);
+
assign_blame(&sb, &revs, opt);
if (incremental)
assign_blame(&sb, &revs, opt);
if (incremental)
ent = e;
}
ent = e;
}
- if (DEBUG) {
+ if (show_stats) {
printf("num read blob: %d\n", num_read_blob);
printf("num get patch: %d\n", num_get_patch);
printf("num commits: %d\n", num_commits);
printf("num read blob: %d\n", num_read_blob);
printf("num get patch: %d\n", num_get_patch);
printf("num commits: %d\n", num_commits);