#include "quote.h"
#include "xdiff-interface.h"
#include "cache-tree.h"
+#include "string-list.h"
+#include "mailmap.h"
+#include "parse-options.h"
-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"
-" -b Show blank SHA-1 for boundary commits (Default: off)\n"
-" -l, --long Show long commit SHA1 (Default: off)\n"
-" --root Do not treat root commits as boundaries (Default: off)\n"
-" -t, --time Show raw timestamp (Default: off)\n"
-" -f, --show-name Show original filename (Default: auto)\n"
-" -n, --show-number Show original linenumber (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"
-" --incremental Show blame entries as we find them, incrementally\n"
-" --contents file Use <file>'s contents as the final image\n"
-" -S revs-file Use revisions from revs-file instead of calling git-rev-list\n";
+static char blame_usage[] = "git blame [options] [rev-opts] [rev] [--] file";
+
+static const char *blame_opt_usage[] = {
+ blame_usage,
+ "",
+ "[rev-opts] are documented in git-rev-list(1)",
+ NULL
+};
static int longest_file;
static int longest_author;
static int max_digits;
static int max_score_digits;
static int show_root;
+static int reverse;
static int blank_boundary;
static int incremental;
static int cmd_is_annotate;
+static int xdl_opts = XDF_NEED_MINIMAL;
+static struct string_list mailmap;
#ifndef DEBUG
#define DEBUG 0
#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
* Given an origin, prepare mmfile_t structure to be used by the
* diff machinery
*/
-static char *fill_origin_blob(struct origin *o, mmfile_t *file)
+static void fill_origin_blob(struct origin *o, mmfile_t *file)
{
if (!o->file.ptr) {
- char type[10];
+ enum object_type type;
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)));
+ if (!file->ptr)
+ die("Cannot read blob %s for path %s",
+ sha1_to_hex(o->blob_sha1),
+ o->path);
o->file = *file;
}
else
*file = o->file;
- return file->ptr;
}
/*
static void origin_decref(struct origin *o)
{
if (o && --o->refcnt <= 0) {
- if (o->file.ptr)
- free(o->file.ptr);
- memset(o, 0, sizeof(*o));
+ free(o->file.ptr);
free(o);
}
}
+static void drop_origin_blob(struct origin *o)
+{
+ if (o->file.ptr) {
+ free(o->file.ptr);
+ o->file.ptr = NULL;
+ }
+}
+
/*
* Each group of lines is described by a blame_entry; it can be split
* as we pass blame to the parents. They form a linked list in the
*/
char guilty;
+ /* true if the entry has been scanned for copies in the current parent
+ */
+ char scanned;
+
/* the line number of the first line of this group in the
* suspect's file; internally all line numbers are 0 based.
*/
struct scoreboard {
/* the final commit (i.e. where we started digging from) */
struct commit *final;
-
+ struct rev_info *revs;
const char *path;
/*
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 *);
/*
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;
static int fill_blob_sha1(struct origin *origin)
{
unsigned mode;
- char type[10];
if (!is_null_sha1(origin->blob_sha1))
return 0;
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:
* same and diff-tree is fairly efficient about this.
*/
diff_setup(&diff_opts);
- diff_opts.recursive = 1;
+ DIFF_OPT_SET(&diff_opts, RECURSIVE);
diff_opts.detect_rename = 0;
diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;
paths[0] = origin->path;
}
}
diff_flush(&diff_opts);
+ diff_tree_release_paths(&diff_opts);
if (porigin) {
/*
* Create a freestanding copy that is not part of
const char *paths[2];
diff_setup(&diff_opts);
- diff_opts.recursive = 1;
+ DIFF_OPT_SET(&diff_opts, RECURSIVE);
diff_opts.detect_rename = DIFF_DETECT_RENAME;
diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;
diff_opts.single_follow = origin->path;
}
}
diff_flush(&diff_opts);
+ diff_tree_release_paths(&diff_opts);
return porigin;
}
xdemitconf_t xecfg;
xdemitcb_t ecb;
- xpp.flags = XDF_NEED_MINIMAL;
+ xpp.flags = xdl_opts;
+ memset(&xecfg, 0, sizeof(xecfg));
xecfg.ctxlen = context;
- xecfg.flags = 0;
ecb.outf = xdiff_outf;
ecb.priv = &state;
memset(&state, 0, sizeof(state));
state.ret->chunks = NULL;
state.ret->num = 0;
- xdl_diff(file_p, file_o, &xpp, &xecfg, &ecb);
+ xdi_diff(file_p, file_o, &xpp, &xecfg, &ecb);
if (state.ret->num) {
struct chunk *chunk;
/*
* src typically is on-stack; we want to copy the information in it to
- * an malloced blame_entry that is already on the linked list of the
+ * a malloced blame_entry that is already on the linked list of the
* scoreboard. The origin of dst loses a refcnt while the origin of src
* gains one.
*/
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;
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;
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
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];
- /* 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;
}
+ /* remainder, if any, all match the preimage */
+ handle_split(sb, ent, tlno, plno, ent->num_lines, parent, split);
free_patch(patch);
}
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) ||
+ ent_score(sb, e) < blame_move_score)
continue;
find_copy_in_blob(sb, e, parent, split, &file_p);
if (split[1].suspect &&
*/
static struct blame_list *setup_blame_list(struct scoreboard *sb,
struct origin *target,
+ int min_score,
int *num_ents_p)
{
struct blame_entry *e;
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->scanned && !e->guilty &&
+ same_suspect(e->suspect, target) &&
+ min_score < ent_score(sb, e))
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->scanned && !e->guilty &&
+ same_suspect(e->suspect, target) &&
+ min_score < ent_score(sb, e))
blame_list[i++].ent = e;
}
*num_ents_p = num_ents;
return blame_list;
}
+/*
+ * Reset the scanned status on all entries.
+ */
+static void reset_scanned_flag(struct scoreboard *sb)
+{
+ struct blame_entry *e;
+ for (e = sb->ent; e; e = e->next)
+ e->scanned = 0;
+}
+
/*
* For lines target is suspected for, see if we can find code movement
* across file boundary from the parent commit. porigin is the path
struct blame_list *blame_list;
int num_ents;
- blame_list = setup_blame_list(sb, target, &num_ents);
+ blame_list = setup_blame_list(sb, target, blame_copy_score, &num_ents);
if (!blame_list)
return 1; /* nothing remains for this target */
diff_setup(&diff_opts);
- diff_opts.recursive = 1;
+ DIFF_OPT_SET(&diff_opts, RECURSIVE);
diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;
paths[0] = NULL;
* 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)))
- diff_opts.find_copies_harder = 1;
+ if ((opt & PICKAXE_BLAME_COPY_HARDEST)
+ || ((opt & PICKAXE_BLAME_COPY_HARDER)
+ && (!porigin || strcmp(target->path, porigin->path))))
+ DIFF_OPT_SET(&diff_opts, FIND_COPIES_HARDER);
if (is_null_sha1(target->commit->object.sha1))
do_diff_cache(parent->tree->object.sha1, &diff_opts);
target->commit->tree->object.sha1,
"", &diff_opts);
- if (!diff_opts.find_copies_harder)
+ if (!DIFF_OPT_TST(&diff_opts, FIND_COPIES_HARDER))
diffcore_std(&diff_opts);
retval = 0;
split_blame(sb, split, blame_list[j].ent);
made_progress = 1;
}
+ else
+ blame_list[j].ent->scanned = 1;
decref_split(split);
}
free(blame_list);
if (!made_progress)
break;
- blame_list = setup_blame_list(sb, target, &num_ents);
+ blame_list = setup_blame_list(sb, target, blame_copy_score, &num_ents);
if (!blame_list) {
retval = 1;
break;
}
}
+ reset_scanned_flag(sb);
diff_flush(&diff_opts);
-
+ diff_tree_release_paths(&diff_opts);
return retval;
}
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);
}
}
-#define MAXPARENT 16
+/*
+ * We pass blame from the current commit to its parents. We keep saying
+ * "parent" (and "porigin"), but what we mean is to find scapegoat to
+ * exonerate ourselves.
+ */
+static struct commit_list *first_scapegoat(struct rev_info *revs, struct commit *commit)
+{
+ if (!reverse)
+ return commit->parents;
+ return lookup_decoration(&revs->children, &commit->object);
+}
+
+static int num_scapegoats(struct rev_info *revs, struct commit *commit)
+{
+ int cnt;
+ struct commit_list *l = first_scapegoat(revs, commit);
+ for (cnt = 0; l; l = l->next)
+ cnt++;
+ return cnt;
+}
+
+#define MAXSG 16
static void pass_blame(struct scoreboard *sb, struct origin *origin, int opt)
{
- int i, pass;
+ struct rev_info *revs = sb->revs;
+ int i, pass, num_sg;
struct commit *commit = origin->commit;
- struct commit_list *parent;
- struct origin *parent_origin[MAXPARENT], *porigin;
-
- memset(parent_origin, 0, sizeof(parent_origin));
+ struct commit_list *sg;
+ struct origin *sg_buf[MAXSG];
+ struct origin *porigin, **sg_origin = sg_buf;
+
+ num_sg = num_scapegoats(revs, commit);
+ if (!num_sg)
+ goto finish;
+ else if (num_sg < ARRAY_SIZE(sg_buf))
+ memset(sg_buf, 0, sizeof(sg_buf));
+ else
+ sg_origin = xcalloc(num_sg, sizeof(*sg_origin));
- /* The first pass looks for unrenamed path to optimize for
+ /*
+ * The first pass looks for unrenamed path to optimize for
* common cases, then we look for renames in the second pass.
*/
for (pass = 0; pass < 2; pass++) {
struct commit *, struct origin *);
find = pass ? find_rename : find_origin;
- for (i = 0, parent = commit->parents;
- i < MAXPARENT && parent;
- parent = parent->next, i++) {
- struct commit *p = parent->item;
+ for (i = 0, sg = first_scapegoat(revs, commit);
+ i < num_sg && sg;
+ sg = sg->next, i++) {
+ struct commit *p = sg->item;
int j, same;
- if (parent_origin[i])
+ if (sg_origin[i])
continue;
if (parse_commit(p))
continue;
goto finish;
}
for (j = same = 0; j < i; j++)
- if (parent_origin[j] &&
- !hashcmp(parent_origin[j]->blob_sha1,
+ if (sg_origin[j] &&
+ !hashcmp(sg_origin[j]->blob_sha1,
porigin->blob_sha1)) {
same = 1;
break;
}
if (!same)
- parent_origin[i] = porigin;
+ sg_origin[i] = porigin;
else
origin_decref(porigin);
}
}
num_commits++;
- for (i = 0, parent = commit->parents;
- i < MAXPARENT && parent;
- parent = parent->next, i++) {
- struct origin *porigin = parent_origin[i];
+ for (i = 0, sg = first_scapegoat(revs, commit);
+ i < num_sg && sg;
+ sg = sg->next, i++) {
+ struct origin *porigin = sg_origin[i];
if (!porigin)
continue;
if (pass_blame_to_parent(sb, origin, porigin))
* Optionally find moves in parents' files.
*/
if (opt & PICKAXE_BLAME_MOVE)
- for (i = 0, parent = commit->parents;
- i < MAXPARENT && parent;
- parent = parent->next, i++) {
- struct origin *porigin = parent_origin[i];
+ for (i = 0, sg = first_scapegoat(revs, commit);
+ i < num_sg && sg;
+ sg = sg->next, i++) {
+ struct origin *porigin = sg_origin[i];
if (!porigin)
continue;
if (find_move_in_parent(sb, origin, porigin))
* Optionally find copies from parents' files.
*/
if (opt & PICKAXE_BLAME_COPY)
- for (i = 0, parent = commit->parents;
- i < MAXPARENT && parent;
- parent = parent->next, i++) {
- struct origin *porigin = parent_origin[i];
- if (find_copy_in_parent(sb, origin, parent->item,
+ for (i = 0, sg = first_scapegoat(revs, commit);
+ i < num_sg && sg;
+ sg = sg->next, i++) {
+ struct origin *porigin = sg_origin[i];
+ if (find_copy_in_parent(sb, origin, sg->item,
porigin, opt))
goto finish;
}
finish:
- for (i = 0; i < MAXPARENT; i++)
- origin_decref(parent_origin[i]);
+ for (i = 0; i < num_sg; i++) {
+ if (sg_origin[i]) {
+ drop_origin_blob(sg_origin[i]);
+ origin_decref(sg_origin[i]);
+ }
+ }
+ drop_origin_blob(origin);
+ if (sg_buf != sg_origin)
+ free(sg_origin);
}
/*
*/
struct commit_info
{
- char *author;
- char *author_mail;
+ const char *author;
+ const char *author_mail;
unsigned long author_time;
- char *author_tz;
+ const char *author_tz;
/* filled only when asked for details */
- char *committer;
- char *committer_mail;
+ const char *committer;
+ const char *committer_mail;
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,
- 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)
if (bufsz <= len) {
error_out:
/* Ugh */
- person = *mail = *tz = "(unknown)";
+ *mail = *tz = "(unknown)";
*time = 0;
return;
}
while (*tmp != ' ')
tmp--;
*tz = tmp+1;
+ tzlen = (person+len)-(tmp+1);
*tmp = 0;
while (*tmp != ' ')
tmp--;
*time = strtoul(tmp, NULL, 10);
+ timepos = tmp;
*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,
* we now need to populate them for output.
*/
if (!commit->buffer) {
- char type[20];
+ enum object_type type;
unsigned long size;
commit->buffer =
- read_sha1_file(commit->object.sha1, type, &size);
+ read_sha1_file(commit->object.sha1, &type, &size);
+ if (!commit->buffer)
+ die("Cannot read commit %s",
+ sha1_to_hex(commit->object.sha1));
}
ret->author = author_buf;
get_ac_line(commit->buffer, "\nauthor ",
static void write_filename_info(const char *path)
{
printf("filename ");
- write_name_quoted(NULL, 0, path, 1, stdout);
- putchar('\n');
+ write_name_quoted(path, stdout, '\n');
}
/*
printf("boundary\n");
}
write_filename_info(suspect->path);
+ maybe_flush_or_die(stdout, "stdout");
}
}
* is still unknown, pick one blame_entry, and allow its current
* suspect to pass blames to its parents.
*/
-static void assign_blame(struct scoreboard *sb, struct rev_info *revs, int opt)
+static void assign_blame(struct scoreboard *sb, int opt)
{
+ struct rev_info *revs = sb->revs;
+
while (1) {
struct blame_entry *ent;
struct commit *commit;
commit = suspect->commit;
if (!commit->object.parsed)
parse_commit(commit);
- if (!(commit->object.flags & UNINTERESTING) &&
- !(revs->max_age != -1 && commit->date < revs->max_age))
+ if (reverse ||
+ (!(commit->object.flags & UNINTERESTING) &&
+ !(revs->max_age != -1 && commit->date < revs->max_age)))
pass_blame(sb, suspect, opt);
else {
commit->object.flags |= UNINTERESTING;
/* 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);
#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)
{
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 {
*/
static int lineno_width(int lines)
{
- int i, width;
+ int i, width;
- for (width = 1, i = 10; i <= lines + 1; width++)
- i *= 10;
- return width;
+ for (width = 1, i = 10; i <= lines + 1; width++)
+ i *= 10;
+ return width;
}
/*
* Used for the command line parsing; check if the path exists
* in the working tree.
*/
-static int has_path_in_work_tree(const char *path)
+static int has_string_in_work_tree(const char *path)
{
struct stat st;
return !lstat(path, &st);
static const char *add_prefix(const char *prefix, const char *path)
{
- if (!prefix || !prefix[0])
- return path;
- return prefix_path(prefix, strlen(prefix), path);
+ return prefix_path(prefix, prefix ? strlen(prefix) : 0, path);
}
/*
usage(blame_usage);
}
-static int git_blame_config(const char *var, const char *value)
+static int git_blame_config(const char *var, const char *value, void *cb)
{
if (!strcmp(var, "blame.showroot")) {
show_root = git_config_bool(var, value);
blank_boundary = git_config_bool(var, value);
return 0;
}
- return git_default_config(var, value);
+ return git_default_config(var, value, cb);
}
+/*
+ * Prepare a dummy commit that represents the work tree (or staged) item.
+ * Note that annotating work tree item never works in the reverse.
+ */
static struct commit *fake_working_tree_commit(const char *path, const char *contents_from)
{
struct commit *commit;
struct origin *origin;
unsigned char head_sha1[20];
- char *buf;
+ struct strbuf buf;
const char *ident;
- int fd;
time_t now;
- unsigned long fin_size;
int size, len;
struct cache_entry *ce;
unsigned mode;
origin = make_origin(commit, path);
+ strbuf_init(&buf, 0);
if (!contents_from || strcmp("-", contents_from)) {
struct stat st;
const char *read_from;
+ unsigned long fin_size;
if (contents_from) {
if (stat(contents_from, &st) < 0)
die("Cannot lstat %s", path);
read_from = path;
}
- fin_size = st.st_size;
- buf = xmalloc(fin_size+1);
+ fin_size = xsize_t(st.st_size);
mode = canon_mode(st.st_mode);
switch (st.st_mode & S_IFMT) {
case S_IFREG:
- fd = open(read_from, O_RDONLY);
- if (fd < 0)
- die("cannot open %s", read_from);
- if (read_in_full(fd, buf, fin_size) != fin_size)
- die("cannot read %s", read_from);
+ if (strbuf_read_file(&buf, read_from, st.st_size) != st.st_size)
+ die("cannot open or read %s", read_from);
break;
case S_IFLNK:
- if (readlink(read_from, buf, fin_size+1) != fin_size)
+ if (readlink(read_from, buf.buf, buf.alloc) != fin_size)
die("cannot readlink %s", read_from);
+ buf.len = fin_size;
break;
default:
die("unsupported file type %s", read_from);
else {
/* Reading from stdin */
contents_from = "standard input";
- buf = NULL;
- fin_size = 0;
mode = 0;
- while (1) {
- ssize_t cnt = 8192;
- buf = xrealloc(buf, fin_size + cnt);
- cnt = xread(0, buf + fin_size, cnt);
- if (cnt < 0)
- die("read error %s from stdin",
- strerror(errno));
- if (!cnt)
- break;
- fin_size += cnt;
- }
- buf = xrealloc(buf, fin_size + 1);
+ if (strbuf_read(&buf, 0, 0) < 0)
+ die("read error %s from stdin", strerror(errno));
}
- buf[fin_size] = 0;
- origin->file.ptr = buf;
- origin->file.size = fin_size;
- pretend_sha1_file(buf, fin_size, blob_type, origin->blob_sha1);
+ convert_to_git(path, buf.buf, buf.len, &buf, 0);
+ origin->file.ptr = buf.buf;
+ origin->file.size = buf.len;
+ pretend_sha1_file(buf.buf, buf.len, OBJ_BLOB, origin->blob_sha1);
commit->util = origin;
/*
if (!mode) {
int pos = cache_name_pos(path, len);
if (0 <= pos)
- mode = ntohl(active_cache[pos]->ce_mode);
+ mode = active_cache[pos]->ce_mode;
else
/* Let's not bother reading from HEAD tree */
mode = S_IFREG | 0644;
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"
return commit;
}
+static const char *prepare_final(struct scoreboard *sb)
+{
+ int i;
+ const char *final_commit_name = NULL;
+ struct rev_info *revs = sb->revs;
+
+ /*
+ * There must be one and only one positive commit in the
+ * revs->pending array.
+ */
+ for (i = 0; i < revs->pending.nr; i++) {
+ struct object *obj = revs->pending.objects[i].item;
+ if (obj->flags & UNINTERESTING)
+ continue;
+ while (obj->type == OBJ_TAG)
+ obj = deref_tag(obj, NULL, 0);
+ if (obj->type != OBJ_COMMIT)
+ die("Non commit %s?", revs->pending.objects[i].name);
+ if (sb->final)
+ die("More than one commit to dig from %s and %s?",
+ revs->pending.objects[i].name,
+ final_commit_name);
+ sb->final = (struct commit *) obj;
+ final_commit_name = revs->pending.objects[i].name;
+ }
+ return final_commit_name;
+}
+
+static const char *prepare_initial(struct scoreboard *sb)
+{
+ int i;
+ const char *final_commit_name = NULL;
+ struct rev_info *revs = sb->revs;
+
+ /*
+ * There must be one and only one negative commit, and it must be
+ * the boundary.
+ */
+ for (i = 0; i < revs->pending.nr; i++) {
+ struct object *obj = revs->pending.objects[i].item;
+ if (!(obj->flags & UNINTERESTING))
+ continue;
+ while (obj->type == OBJ_TAG)
+ obj = deref_tag(obj, NULL, 0);
+ if (obj->type != OBJ_COMMIT)
+ die("Non commit %s?", revs->pending.objects[i].name);
+ if (sb->final)
+ die("More than one commit to dig down to %s and %s?",
+ revs->pending.objects[i].name,
+ final_commit_name);
+ sb->final = (struct commit *) obj;
+ final_commit_name = revs->pending.objects[i].name;
+ }
+ if (!final_commit_name)
+ die("No commit to dig down to?");
+ return final_commit_name;
+}
+
+static int blame_copy_callback(const struct option *option, const char *arg, int unset)
+{
+ int *opt = option->value;
+
+ /*
+ * -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;
+
+ if (arg)
+ blame_copy_score = parse_score(arg);
+ return 0;
+}
+
+static int blame_move_callback(const struct option *option, const char *arg, int unset)
+{
+ int *opt = option->value;
+
+ *opt |= PICKAXE_BLAME_MOVE;
+
+ if (arg)
+ blame_move_score = parse_score(arg);
+ return 0;
+}
+
+static int blame_bottomtop_callback(const struct option *option, const char *arg, int unset)
+{
+ const char **bottomtop = option->value;
+ if (!arg)
+ return -1;
+ if (*bottomtop)
+ die("More than one '-L n,m' option given");
+ *bottomtop = arg;
+ return 0;
+}
+
int cmd_blame(int argc, const char **argv, const char *prefix)
{
struct rev_info revs;
struct scoreboard sb;
struct origin *o;
struct blame_entry *ent;
- int i, seen_dashdash, unk, opt;
- long bottom, top, lno;
- int output_option = 0;
- int show_stats = 0;
- const char *revs_file = NULL;
+ long dashdash_pos, bottom, top, lno;
const char *final_commit_name = NULL;
- char type[10];
- const char *bottomtop = NULL;
- const char *contents_from = NULL;
+ enum object_type type;
+
+ static const char *bottomtop = NULL;
+ static int output_option = 0, opt = 0;
+ static int show_stats = 0;
+ static const char *revs_file = NULL;
+ static const char *contents_from = NULL;
+ static const struct option options[] = {
+ OPT_BOOLEAN(0, "incremental", &incremental, "Show blame entries as we find them, incrementally"),
+ OPT_BOOLEAN('b', NULL, &blank_boundary, "Show blank SHA-1 for boundary commits (Default: off)"),
+ OPT_BOOLEAN(0, "root", &show_root, "Do not treat root commits as boundaries (Default: off)"),
+ OPT_BOOLEAN(0, "show-stats", &show_stats, "Show work cost statistics"),
+ OPT_BIT(0, "score-debug", &output_option, "Show output score for blame entries", OUTPUT_SHOW_SCORE),
+ OPT_BIT('f', "show-name", &output_option, "Show original filename (Default: auto)", OUTPUT_SHOW_NAME),
+ OPT_BIT('n', "show-number", &output_option, "Show original linenumber (Default: off)", OUTPUT_SHOW_NUMBER),
+ OPT_BIT('p', "porcelain", &output_option, "Show in a format designed for machine consumption", OUTPUT_PORCELAIN),
+ OPT_BIT('c', NULL, &output_option, "Use the same output mode as git-annotate (Default: off)", OUTPUT_ANNOTATE_COMPAT),
+ OPT_BIT('t', NULL, &output_option, "Show raw timestamp (Default: off)", OUTPUT_RAW_TIMESTAMP),
+ OPT_BIT('l', NULL, &output_option, "Show long commit SHA1 (Default: off)", OUTPUT_LONG_OBJECT_NAME),
+ OPT_BIT('s', NULL, &output_option, "Suppress author name and timestamp (Default: off)", OUTPUT_NO_AUTHOR),
+ OPT_BIT('w', NULL, &xdl_opts, "Ignore whitespace differences", XDF_IGNORE_WHITESPACE),
+ OPT_STRING('S', NULL, &revs_file, "file", "Use revisions from <file> instead of calling git-rev-list"),
+ OPT_STRING(0, "contents", &contents_from, "file", "Use <file>'s contents as the final image"),
+ { OPTION_CALLBACK, 'C', NULL, &opt, "score", "Find line copies within and across files", PARSE_OPT_OPTARG, blame_copy_callback },
+ { OPTION_CALLBACK, 'M', NULL, &opt, "score", "Find line movements within and across files", PARSE_OPT_OPTARG, blame_move_callback },
+ OPT_CALLBACK('L', NULL, &bottomtop, "n,m", "Process only line range n,m, counting from 1", blame_bottomtop_callback),
+ OPT_END()
+ };
+
+ struct parse_opt_ctx_t ctx;
cmd_is_annotate = !strcmp(argv[0], "annotate");
- git_config(git_blame_config);
+ git_config(git_blame_config, NULL);
+ init_revisions(&revs, NULL);
save_commit_buffer = 0;
-
- opt = 0;
- seen_dashdash = 0;
- for (unk = i = 1; i < argc; i++) {
- const char *arg = argv[i];
- if (*arg != '-')
- break;
- else if (!strcmp("-b", arg))
- 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("-S", arg) && ++i < argc)
- revs_file = argv[i];
- else if (!prefixcmp(arg, "-M")) {
- opt |= PICKAXE_BLAME_MOVE;
- blame_move_score = parse_score(arg+2);
- }
- else if (!prefixcmp(arg, "-C")) {
- 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 (!prefixcmp(arg, "-L")) {
- if (!arg[2]) {
- if (++i >= argc)
- usage(blame_usage);
- arg = argv[i];
- }
- else
- arg += 2;
- if (bottomtop)
- die("More than one '-L n,m' option given");
- bottomtop = arg;
+ dashdash_pos = 0;
+
+ parse_options_start(&ctx, argc, argv, PARSE_OPT_KEEP_DASHDASH |
+ PARSE_OPT_KEEP_ARGV0);
+ for (;;) {
+ switch (parse_options_step(&ctx, options, blame_opt_usage)) {
+ case PARSE_OPT_HELP:
+ exit(129);
+ case PARSE_OPT_DONE:
+ if (ctx.argv[0])
+ dashdash_pos = ctx.cpidx;
+ goto parse_done;
}
- else if (!strcmp("--contents", arg)) {
- if (++i >= argc)
- usage(blame_usage);
- contents_from = argv[i];
- }
- else if (!strcmp("--incremental", arg))
- incremental = 1;
- else if (!strcmp("--score-debug", arg))
- output_option |= OUTPUT_SHOW_SCORE;
- else if (!strcmp("-f", arg) ||
- !strcmp("--show-name", arg))
- output_option |= OUTPUT_SHOW_NAME;
- else if (!strcmp("-n", arg) ||
- !strcmp("--show-number", arg))
- output_option |= OUTPUT_SHOW_NUMBER;
- else if (!strcmp("-p", arg) ||
- !strcmp("--porcelain", arg))
- output_option |= OUTPUT_PORCELAIN;
- else if (!strcmp("--", arg)) {
- seen_dashdash = 1;
- i++;
- break;
+
+ if (!strcmp(ctx.argv[0], "--reverse")) {
+ ctx.argv[0] = "--children";
+ reverse = 1;
}
- else
- argv[unk++] = arg;
+ parse_revision_opt(&revs, &ctx, options, blame_opt_usage);
}
-
- if (!incremental)
- setup_pager();
+parse_done:
+ argc = parse_options_end(&ctx);
if (!blame_move_score)
blame_move_score = BLAME_DEFAULT_MOVE_SCORE;
*
* The remaining are:
*
- * (1) if seen_dashdash, its either
- * "-options -- <path>" or
- * "-options -- <path> <rev>".
- * but the latter is allowed only if there is no
- * options that we passed to revision machinery.
+ * (1) if dashdash_pos != 0, its either
+ * "blame [revisions] -- <path>" or
+ * "blame -- <path> <rev>"
*
- * (2) otherwise, we may have "--" somewhere later and
- * might be looking at the first one of multiple 'rev'
- * parameters (e.g. " master ^next ^maint -- path").
- * See if there is a dashdash first, and give the
- * arguments before that to revision machinery.
- * After that there must be one 'path'.
+ * (2) otherwise, its one of the two:
+ * "blame [revisions] <path>"
+ * "blame <path> <rev>"
*
- * (3) otherwise, its one of the three:
- * "-options <path> <rev>"
- * "-options <rev> <path>"
- * "-options <path>"
- * but again the first one is allowed only if
- * there is no options that we passed to revision
- * machinery.
+ * Note that we must strip out <path> from the arguments: we do not
+ * want the path pruning but we may want "bottom" processing.
*/
-
- if (seen_dashdash) {
- /* (1) */
- if (argc <= i)
- usage(blame_usage);
- path = add_prefix(prefix, argv[i]);
- if (i + 1 == argc - 1) {
- if (unk != 1)
- usage(blame_usage);
- argv[unk++] = argv[i + 1];
+ if (dashdash_pos) {
+ switch (argc - dashdash_pos - 1) {
+ case 2: /* (1b) */
+ if (argc != 4)
+ usage_with_options(blame_opt_usage, options);
+ /* reorder for the new way: <rev> -- <path> */
+ argv[1] = argv[3];
+ argv[3] = argv[2];
+ argv[2] = "--";
+ /* FALLTHROUGH */
+ case 1: /* (1a) */
+ path = add_prefix(prefix, argv[--argc]);
+ argv[argc] = NULL;
+ break;
+ default:
+ usage_with_options(blame_opt_usage, options);
}
- else if (i + 1 != argc)
- /* garbage at end */
- usage(blame_usage);
- }
- else {
- int j;
- for (j = i; !seen_dashdash && j < argc; j++)
- if (!strcmp(argv[j], "--"))
- seen_dashdash = j;
- if (seen_dashdash) {
- /* (2) */
- if (seen_dashdash + 1 != argc - 1)
- usage(blame_usage);
- path = add_prefix(prefix, argv[seen_dashdash + 1]);
- for (j = i; j < seen_dashdash; j++)
- argv[unk++] = argv[j];
+ } else {
+ if (argc < 2)
+ usage_with_options(blame_opt_usage, options);
+ path = add_prefix(prefix, argv[argc - 1]);
+ if (argc == 3 && !has_string_in_work_tree(path)) { /* (2b) */
+ path = add_prefix(prefix, argv[1]);
+ argv[1] = argv[2];
}
- else {
- /* (3) */
- if (argc <= i)
- usage(blame_usage);
- path = add_prefix(prefix, argv[i]);
- if (i + 1 == argc - 1) {
- final_commit_name = argv[i + 1];
-
- /* if (unk == 1) we could be getting
- * old-style
- */
- if (unk == 1 && !has_path_in_work_tree(path)) {
- path = add_prefix(prefix, argv[i + 1]);
- final_commit_name = argv[i];
- }
- }
- else if (i != argc - 1)
- usage(blame_usage); /* garbage at end */
+ argv[argc - 1] = "--";
- if (!has_path_in_work_tree(path))
- die("cannot stat path %s: %s",
- path, strerror(errno));
- }
+ setup_work_tree();
+ if (!has_string_in_work_tree(path))
+ die("cannot stat path %s: %s", path, strerror(errno));
}
- if (final_commit_name)
- argv[unk++] = final_commit_name;
-
- /*
- * Now we got rev and path. We do not want the path pruning
- * but we may want "bottom" processing.
- */
- argv[unk++] = "--"; /* terminate the rev name */
- argv[unk] = NULL;
-
- init_revisions(&revs, NULL);
- setup_revisions(unk, argv, &revs, NULL);
+ setup_revisions(argc, argv, &revs, NULL);
memset(&sb, 0, sizeof(sb));
- /*
- * There must be one and only one positive commit in the
- * revs->pending array.
- */
- for (i = 0; i < revs.pending.nr; i++) {
- struct object *obj = revs.pending.objects[i].item;
- if (obj->flags & UNINTERESTING)
- continue;
- while (obj->type == OBJ_TAG)
- obj = deref_tag(obj, NULL, 0);
- if (obj->type != OBJ_COMMIT)
- die("Non commit %s?",
- revs.pending.objects[i].name);
- if (sb.final)
- die("More than one commit to dig from %s and %s?",
- revs.pending.objects[i].name,
- final_commit_name);
- sb.final = (struct commit *) obj;
- final_commit_name = revs.pending.objects[i].name;
- }
+ sb.revs = &revs;
+ if (!reverse)
+ final_commit_name = prepare_final(&sb);
+ else if (contents_from)
+ die("--contents and --children do not blend well.");
+ else
+ final_commit_name = prepare_initial(&sb);
if (!sb.final) {
/*
* do not default to HEAD, but use the working tree
* or "--contents".
*/
+ setup_work_tree();
sb.final = fake_working_tree_commit(path, contents_from);
add_pending_object(&revs, &(sb.final->object), ":");
}
* bottom commits we would reach while traversing as
* uninteresting.
*/
- prepare_revision_walk(&revs);
+ if (prepare_revision_walk(&revs))
+ die("revision walk setup failed");
if (is_null_sha1(sb.final->object.sha1)) {
char *buf;
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);
+ if (!sb.final_buf)
+ die("Cannot read blob %s for path %s",
+ sha1_to_hex(o->blob_sha1),
+ path);
}
num_read_blob++;
lno = prepare_lines(&sb);
die("reading graft file %s failed: %s",
revs_file, strerror(errno));
- assign_blame(&sb, &revs, opt);
+ read_mailmap(&mailmap, ".mailmap", NULL);
+
+ if (!incremental)
+ setup_pager();
+
+ assign_blame(&sb, opt);
if (incremental)
return 0;