1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-05-07 12:46:12 +02:00
git/blame.h
Barret Rhoden 8934ac8c92 blame: add config options for the output of ignored or unblamable lines
When ignoring commits, the commit that is blamed might not be
responsible for the change, due to the inaccuracy of our heuristic.
Users might want to know when a particular line has a potentially
inaccurate blame.

Furthermore, guess_line_blames() may fail to find any parent commit for
a given line touched by an ignored commit.  Those 'unblamable' lines
remain blamed on an ignored commit.  Users might want to know if a line
is unblamable so that they do not spend time investigating a commit they
know is uninteresting.

This patch adds two config options to mark these two types of lines in
the output of blame.

The first option can identify ignored lines by specifying
blame.markIgnoredLines.  When this option is set, each blame line that
was blamed on a commit other than the ignored commit is marked with a
'?'.

For example:
	278b6158d6fdb (Barret Rhoden  2016-04-11 13:57:54 -0400 26)
appears as:
	?278b6158d6fd (Barret Rhoden  2016-04-11 13:57:54 -0400 26)

where the '?' is placed before the commit, and the hash has one fewer
characters.

Sometimes we are unable to even guess at what ancestor commit touched a
line.  These lines are 'unblamable.'  The second option,
blame.markUnblamableLines, will mark the line with '*'.

For example, say we ignore e5e8d36d04cbe, yet we are unable to blame
this line on another commit:
	e5e8d36d04cbe (Barret Rhoden  2016-04-11 13:57:54 -0400 26)
appears as:
	*e5e8d36d04cb (Barret Rhoden  2016-04-11 13:57:54 -0400 26)

When these config options are used together, every line touched by an
ignored commit will be marked with either a '?' or a '*'.

Signed-off-by: Barret Rhoden <brho@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2019-05-16 11:36:23 +09:00

187 lines
5.3 KiB
C

#ifndef BLAME_H
#define BLAME_H
#include "cache.h"
#include "commit.h"
#include "xdiff-interface.h"
#include "revision.h"
#include "prio-queue.h"
#include "diff.h"
#define PICKAXE_BLAME_MOVE 01
#define PICKAXE_BLAME_COPY 02
#define PICKAXE_BLAME_COPY_HARDER 04
#define PICKAXE_BLAME_COPY_HARDEST 010
#define BLAME_DEFAULT_MOVE_SCORE 20
#define BLAME_DEFAULT_COPY_SCORE 40
/*
* One blob in a commit that is being suspected
*/
struct blame_origin {
int refcnt;
/* Record preceding blame record for this blob */
struct blame_origin *previous;
/* origins are put in a list linked via `next' hanging off the
* corresponding commit's util field in order to make finding
* them fast. The presence in this chain does not count
* towards the origin's reference count. It is tempting to
* let it count as long as the commit is pending examination,
* but even under circumstances where the commit will be
* present multiple times in the priority queue of unexamined
* commits, processing the first instance will not leave any
* work requiring the origin data for the second instance. An
* interspersed commit changing that would have to be
* preexisting with a different ancestry and with the same
* commit date in order to wedge itself between two instances
* of the same commit in the priority queue _and_ produce
* blame entries relevant for it. While we don't want to let
* us get tripped up by this case, it certainly does not seem
* worth optimizing for.
*/
struct blame_origin *next;
struct commit *commit;
/* `suspects' contains blame entries that may be attributed to
* this origin's commit or to parent commits. When a commit
* is being processed, all suspects will be moved, either by
* assigning them to an origin in a different commit, or by
* shipping them to the scoreboard's ent list because they
* cannot be attributed to a different commit.
*/
struct blame_entry *suspects;
mmfile_t file;
struct object_id blob_oid;
unsigned mode;
/* guilty gets set when shipping any suspects to the final
* blame list instead of other commits
*/
char guilty;
char path[FLEX_ARRAY];
};
/*
* Each group of lines is described by a blame_entry; it can be split
* as we pass blame to the parents. They are arranged in linked lists
* kept as `suspects' of some unprocessed origin, or entered (when the
* blame origin has been finalized) into the scoreboard structure.
* While the scoreboard structure is only sorted at the end of
* processing (according to final image line number), the lists
* attached to an origin are sorted by the target line number.
*/
struct blame_entry {
struct blame_entry *next;
/* the first line of this group in the final image;
* internally all line numbers are 0 based.
*/
int lno;
/* how many lines this group has */
int num_lines;
/* the commit that introduced this group into the final image */
struct blame_origin *suspect;
/* the line number of the first line of this group in the
* suspect's file; internally all line numbers are 0 based.
*/
int s_lno;
/* how significant this entry is -- cached to avoid
* scanning the lines over and over.
*/
unsigned score;
int ignored;
int unblamable;
};
/*
* The current state of the blame assignment.
*/
struct blame_scoreboard {
/* the final commit (i.e. where we started digging from) */
struct commit *final;
/* Priority queue for commits with unassigned blame records */
struct prio_queue commits;
struct repository *repo;
struct rev_info *revs;
const char *path;
/*
* The contents in the final image.
* Used by many functions to obtain contents of the nth line,
* indexed with scoreboard.lineno[blame_entry.lno].
*/
const char *final_buf;
unsigned long final_buf_size;
/* linked list of blames */
struct blame_entry *ent;
struct oidset ignore_list;
/* look-up a line in the final buffer */
int num_lines;
int *lineno;
/* stats */
int num_read_blob;
int num_get_patch;
int num_commits;
/*
* blame for a blame_entry with score lower than these thresholds
* is not passed to the parent using move/copy logic.
*/
unsigned move_score;
unsigned copy_score;
/* use this file's contents as the final image */
const char *contents_from;
/* flags */
int reverse;
int show_root;
int xdl_opts;
int no_whole_file_rename;
int debug;
/* callbacks */
void(*on_sanity_fail)(struct blame_scoreboard *, int);
void(*found_guilty_entry)(struct blame_entry *, void *);
void *found_guilty_entry_data;
};
/*
* Origin is refcounted and usually we keep the blob contents to be
* reused.
*/
static inline struct blame_origin *blame_origin_incref(struct blame_origin *o)
{
if (o)
o->refcnt++;
return o;
}
void blame_origin_decref(struct blame_origin *o);
void blame_coalesce(struct blame_scoreboard *sb);
void blame_sort_final(struct blame_scoreboard *sb);
unsigned blame_entry_score(struct blame_scoreboard *sb, struct blame_entry *e);
void assign_blame(struct blame_scoreboard *sb, int opt);
const char *blame_nth_line(struct blame_scoreboard *sb, long lno);
void init_scoreboard(struct blame_scoreboard *sb);
void setup_scoreboard(struct blame_scoreboard *sb,
const char *path,
struct blame_origin **orig);
struct blame_entry *blame_entry_prepend(struct blame_entry *head,
long start, long end,
struct blame_origin *o);
extern struct blame_origin *get_blame_suspects(struct commit *commit);
#endif /* BLAME_H */