1
0
mirror of https://github.com/git/git.git synced 2024-11-19 04:43:58 +01:00
git/diff.h
Linus Torvalds 750f7b668f Finally implement "git log --follow"
Ok, I've really held off doing this too damn long, because I'm lazy, and I
was always hoping that somebody else would do it.

But no, people keep asking for it, but nobody actually did anything, so I
decided I might as well bite the bullet, and instead of telling people
they could add a "--follow" flag to "git log" to do what they want to do,
I decided that it looks like I just have to do it for them..

The code wasn't actually that complicated, in that the diffstat for this
patch literally says "70 insertions(+), 1 deletions(-)", but I will have
to admit that in order to get to this fairly simple patch, you did have to
know and understand the internal git diff generation machinery pretty
well, and had to really be able to follow how commit generation interacts
with generating patches and generating the log.

So I suspect that while I was right that it wasn't that hard, I might have
been expecting too much of random people - this patch does seem to be
firmly in the core "Linus or Junio" territory.

To make a long story short: I'm sorry for it taking so long until I just
did it.

I'm not going to guarantee that this works for everybody, but you really
can just look at the patch, and after the appropriate appreciative noises
("Ooh, aah") over how clever I am, you can then just notice that the code
itself isn't really that complicated.

All the real new code is in the new "try_to_follow_renames()" function. It
really isn't rocket science: we notice that the pathname we were looking
at went away, so we start a full tree diff and try to see if we can
instead make that pathname be a rename or a copy from some other previous
pathname. And if we can, we just continue, except we show *that*
particular diff, and ever after we use the _previous_ pathname.

One thing to look out for: the "rename detection" is considered to be a
singular event in the _linear_ "git log" output! That's what people want
to do, but I just wanted to point out that this patch is *not* carrying
around a "commit,pathname" kind of pair and it's *not* going to be able to
notice the file coming from multiple *different* files in earlier history.

IOW, if you use "git log --follow", then you get the stupid CVS/SVN kind
of "files have single identities" kind of semantics, and git log will just
pick the identity based on the normal move/copy heuristics _as_if_ the
history could be linearized.

Put another way: I think the model is broken, but given the broken model,
I think this patch does just about as well as you can do. If you have
merges with the same "file" having different filenames over the two
branches, git will just end up picking _one_ of the pathnames at the point
where the newer one goes away. It never looks at multiple pathnames in
parallel.

And if you understood all that, you probably didn't need it explained, and
if you didn't understand the above blathering, it doesn't really mtter to
you. What matters to you is that you can now do

	git log -p --follow builtin-rev-list.c

and it will find the point where the old "rev-list.c" got renamed to
"builtin-rev-list.c" and show it as such.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-22 23:37:11 -07:00

236 lines
7.0 KiB
C

/*
* Copyright (C) 2005 Junio C Hamano
*/
#ifndef DIFF_H
#define DIFF_H
#include "tree-walk.h"
struct rev_info;
struct diff_options;
struct diff_queue_struct;
typedef void (*change_fn_t)(struct diff_options *options,
unsigned old_mode, unsigned new_mode,
const unsigned char *old_sha1,
const unsigned char *new_sha1,
const char *base, const char *path);
typedef void (*add_remove_fn_t)(struct diff_options *options,
int addremove, unsigned mode,
const unsigned char *sha1,
const char *base, const char *path);
typedef void (*diff_format_fn_t)(struct diff_queue_struct *q,
struct diff_options *options, void *data);
#define DIFF_FORMAT_RAW 0x0001
#define DIFF_FORMAT_DIFFSTAT 0x0002
#define DIFF_FORMAT_NUMSTAT 0x0004
#define DIFF_FORMAT_SUMMARY 0x0008
#define DIFF_FORMAT_PATCH 0x0010
#define DIFF_FORMAT_SHORTSTAT 0x0020
/* These override all above */
#define DIFF_FORMAT_NAME 0x0100
#define DIFF_FORMAT_NAME_STATUS 0x0200
#define DIFF_FORMAT_CHECKDIFF 0x0400
/* Same as output_format = 0 but we know that -s flag was given
* and we should not give default value to output_format.
*/
#define DIFF_FORMAT_NO_OUTPUT 0x0800
#define DIFF_FORMAT_CALLBACK 0x1000
struct diff_options {
const char *filter;
const char *orderfile;
const char *pickaxe;
const char *single_follow;
unsigned recursive:1,
tree_in_recursive:1,
binary:1,
text:1,
full_index:1,
silent_on_remove:1,
find_copies_harder:1,
follow_renames:1,
color_diff:1,
color_diff_words:1,
has_changes:1,
quiet:1,
allow_external:1,
exit_with_status:1;
int context;
int break_opt;
int detect_rename;
int line_termination;
int output_format;
int pickaxe_opts;
int rename_score;
int reverse_diff;
int rename_limit;
int setup;
int abbrev;
const char *msg_sep;
const char *stat_sep;
long xdl_opts;
int stat_width;
int stat_name_width;
/* this is set by diffcore for DIFF_FORMAT_PATCH */
int found_changes;
int nr_paths;
const char **paths;
int *pathlens;
change_fn_t change;
add_remove_fn_t add_remove;
diff_format_fn_t format_callback;
void *format_callback_data;
};
enum color_diff {
DIFF_RESET = 0,
DIFF_PLAIN = 1,
DIFF_METAINFO = 2,
DIFF_FRAGINFO = 3,
DIFF_FILE_OLD = 4,
DIFF_FILE_NEW = 5,
DIFF_COMMIT = 6,
DIFF_WHITESPACE = 7,
};
const char *diff_get_color(int diff_use_color, enum color_diff ix);
extern const char mime_boundary_leader[];
extern void diff_tree_setup_paths(const char **paths, struct diff_options *);
extern void diff_tree_release_paths(struct diff_options *);
extern int diff_tree(struct tree_desc *t1, struct tree_desc *t2,
const char *base, struct diff_options *opt);
extern int diff_tree_sha1(const unsigned char *old, const unsigned char *new,
const char *base, struct diff_options *opt);
extern int diff_root_tree_sha1(const unsigned char *new, const char *base,
struct diff_options *opt);
struct combine_diff_path {
struct combine_diff_path *next;
int len;
char *path;
unsigned int mode;
unsigned char sha1[20];
struct combine_diff_parent {
char status;
unsigned int mode;
unsigned char sha1[20];
} parent[FLEX_ARRAY];
};
#define combine_diff_path_size(n, l) \
(sizeof(struct combine_diff_path) + \
sizeof(struct combine_diff_parent) * (n) + (l) + 1)
extern void show_combined_diff(struct combine_diff_path *elem, int num_parent,
int dense, struct rev_info *);
extern void diff_tree_combined(const unsigned char *sha1, const unsigned char parent[][20], int num_parent, int dense, struct rev_info *rev);
extern void diff_tree_combined_merge(const unsigned char *sha1, int, struct rev_info *);
extern void diff_addremove(struct diff_options *,
int addremove,
unsigned mode,
const unsigned char *sha1,
const char *base,
const char *path);
extern void diff_change(struct diff_options *,
unsigned mode1, unsigned mode2,
const unsigned char *sha1,
const unsigned char *sha2,
const char *base, const char *path);
extern void diff_unmerge(struct diff_options *,
const char *path,
unsigned mode,
const unsigned char *sha1);
#define DIFF_SETUP_REVERSE 1
#define DIFF_SETUP_USE_CACHE 2
#define DIFF_SETUP_USE_SIZE_CACHE 4
extern int git_diff_ui_config(const char *var, const char *value);
extern void diff_setup(struct diff_options *);
extern int diff_opt_parse(struct diff_options *, const char **, int);
extern int diff_setup_done(struct diff_options *);
#define DIFF_DETECT_RENAME 1
#define DIFF_DETECT_COPY 2
#define DIFF_PICKAXE_ALL 1
#define DIFF_PICKAXE_REGEX 2
extern void diffcore_std(struct diff_options *);
#define COMMON_DIFF_OPTIONS_HELP \
"\ncommon diff options:\n" \
" -z output diff-raw with lines terminated with NUL.\n" \
" -p output patch format.\n" \
" -u synonym for -p.\n" \
" --patch-with-raw\n" \
" output both a patch and the diff-raw format.\n" \
" --stat show diffstat instead of patch.\n" \
" --numstat show numeric diffstat instead of patch.\n" \
" --patch-with-stat\n" \
" output a patch and prepend its diffstat.\n" \
" --name-only show only names of changed files.\n" \
" --name-status show names and status of changed files.\n" \
" --full-index show full object name on index lines.\n" \
" --abbrev=<n> abbreviate object names in diff-tree header and diff-raw.\n" \
" -R swap input file pairs.\n" \
" -B detect complete rewrites.\n" \
" -M detect renames.\n" \
" -C detect copies.\n" \
" --find-copies-harder\n" \
" try unchanged files as candidate for copy detection.\n" \
" -l<n> limit rename attempts up to <n> paths.\n" \
" -O<file> reorder diffs according to the <file>.\n" \
" -S<string> find filepair whose only one side contains the string.\n" \
" --pickaxe-all\n" \
" show all files diff when -S is used and hit is found.\n" \
" -a --text treat all files as text.\n"
extern int diff_queue_is_empty(void);
extern void diff_flush(struct diff_options*);
/* diff-raw status letters */
#define DIFF_STATUS_ADDED 'A'
#define DIFF_STATUS_COPIED 'C'
#define DIFF_STATUS_DELETED 'D'
#define DIFF_STATUS_MODIFIED 'M'
#define DIFF_STATUS_RENAMED 'R'
#define DIFF_STATUS_TYPE_CHANGED 'T'
#define DIFF_STATUS_UNKNOWN 'X'
#define DIFF_STATUS_UNMERGED 'U'
/* these are not diff-raw status letters proper, but used by
* diffcore-filter insn to specify additional restrictions.
*/
#define DIFF_STATUS_FILTER_AON '*'
#define DIFF_STATUS_FILTER_BROKEN 'B'
extern const char *diff_unique_abbrev(const unsigned char *, int);
extern int run_diff_files(struct rev_info *revs, int silent_on_removed);
extern int setup_diff_no_index(struct rev_info *revs,
int argc, const char ** argv, int nongit, const char *prefix);
extern int run_diff_files_cmd(struct rev_info *revs, int argc, const char **argv);
extern int run_diff_index(struct rev_info *revs, int cached);
extern int do_diff_cache(const unsigned char *, struct diff_options *);
extern int diff_flush_patch_id(struct diff_options *, unsigned char *);
#endif /* DIFF_H */