git-commit-vandalism/commit.h

258 lines
8.5 KiB
C
Raw Normal View History

#ifndef COMMIT_H
#define COMMIT_H
#include "object.h"
#include "tree.h"
#include "strbuf.h"
#include "decorate.h"
#include "gpg-interface.h"
struct commit_list {
struct commit *item;
struct commit_list *next;
};
struct commit {
struct object object;
void *util;
unsigned int index;
unsigned long date;
struct commit_list *parents;
struct tree *tree;
char *buffer;
};
[PATCH] Avoid wasting memory in git-rev-list As pointed out on the list, git-rev-list can use a lot of memory. One low-hanging fruit is to free the commit buffer for commits that we parse. By default, parse_commit() will save away the buffer, since a lot of cases do want it, and re-reading it continually would be unnecessary. However, in many cases the buffer isn't actually necessary and saving it just wastes memory. We could just free the buffer ourselves, but especially in git-rev-list, we actually end up using the helper functions that automatically add parent commits to the commit lists, so we don't actually control the commit parsing directly. Instead, just make this behaviour of "parse_commit()" a global flag. Maybe this is a bit tasteless, but it's very simple, and it makes a noticable difference in memory usage. Before the change: [torvalds@g5 linux]$ /usr/bin/time git-rev-list v2.6.12..HEAD > /dev/null 0.26user 0.02system 0:00.28elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+3714minor)pagefaults 0swaps after the change: [torvalds@g5 linux]$ /usr/bin/time git-rev-list v2.6.12..HEAD > /dev/null 0.26user 0.00system 0:00.27elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k 0inputs+0outputs (0major+2433minor)pagefaults 0swaps note how the minor faults have decreased from 3714 pages to 2433 pages. That's all due to the fewer anonymous pages allocated to hold the comment buffers and their metadata. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2005-09-15 23:43:17 +02:00
extern int save_commit_buffer;
extern const char *commit_type;
/* While we can decorate any object with a name, it's only used for commits.. */
extern struct decoration name_decoration;
struct name_decoration {
struct name_decoration *next;
int type;
char name[1];
};
struct commit *lookup_commit(const unsigned char *sha1);
struct commit *lookup_commit_reference(const unsigned char *sha1);
struct commit *lookup_commit_reference_gently(const unsigned char *sha1,
int quiet);
struct commit *lookup_commit_reference_by_name(const char *name);
/*
* Look up object named by "sha1", dereference tag as necessary,
* get a commit and return it. If "sha1" does not dereference to
* a commit, use ref_name to report an error and die.
*/
struct commit *lookup_commit_or_die(const unsigned char *sha1, const char *ref_name);
int parse_commit_buffer(struct commit *item, const void *buffer, unsigned long size);
int parse_commit(struct commit *item);
/* Find beginning and length of commit subject. */
int find_commit_subject(const char *commit_buffer, const char **subject);
struct commit_list *commit_list_insert(struct commit *item,
struct commit_list **list);
struct commit_list **commit_list_append(struct commit *commit,
struct commit_list **next);
unsigned commit_list_count(const struct commit_list *l);
struct commit_list *commit_list_insert_by_date(struct commit *item,
struct commit_list **list);
void commit_list_sort_by_date(struct commit_list **list);
void free_commit_list(struct commit_list *list);
/* Commit formats */
enum cmit_fmt {
CMIT_FMT_RAW,
CMIT_FMT_MEDIUM,
CMIT_FMT_DEFAULT = CMIT_FMT_MEDIUM,
CMIT_FMT_SHORT,
CMIT_FMT_FULL,
CMIT_FMT_FULLER,
CMIT_FMT_ONELINE,
CMIT_FMT_EMAIL,
CMIT_FMT_USERFORMAT,
CMIT_FMT_UNSPECIFIED
};
struct pretty_print_context {
enum cmit_fmt fmt;
int abbrev;
const char *subject;
const char *after_subject;
int preserve_subject;
enum date_mode date_mode;
unsigned date_mode_explicit:1;
int need_8bit_cte;
char *notes_message;
struct reflog_walk_info *reflog_info;
const char *output_encoding;
struct string_list *mailmap;
int color;
};
struct userformat_want {
unsigned notes:1;
};
extern int has_non_ascii(const char *text);
struct rev_info; /* in revision.h, it circularly uses enum cmit_fmt */
extern char *logmsg_reencode(const struct commit *commit,
char **commit_encoding,
const char *output_encoding);
extern void logmsg_free(char *msg, const struct commit *commit);
extern void get_commit_format(const char *arg, struct rev_info *);
extern const char *format_subject(struct strbuf *sb, const char *msg,
const char *line_separator);
extern void userformat_find_requirements(const char *fmt, struct userformat_want *w);
extern void format_commit_message(const struct commit *commit,
const char *format, struct strbuf *sb,
const struct pretty_print_context *context);
extern void pretty_print_commit(const struct pretty_print_context *pp,
const struct commit *commit,
struct strbuf *sb);
extern void pp_commit_easy(enum cmit_fmt fmt, const struct commit *commit,
struct strbuf *sb);
void pp_user_info(const struct pretty_print_context *pp,
const char *what, struct strbuf *sb,
const char *line, const char *encoding);
void pp_title_line(const struct pretty_print_context *pp,
const char **msg_p,
struct strbuf *sb,
const char *encoding,
int need_8bit_cte);
void pp_remainder(const struct pretty_print_context *pp,
const char **msg_p,
struct strbuf *sb,
int indent);
/** Removes the first commit from a list sorted by date, and adds all
* of its parents.
**/
struct commit *pop_most_recent_commit(struct commit_list **list,
unsigned int mark);
[PATCH] Modify git-rev-list to linearise the commit history in merge order. This patch linearises the GIT commit history graph into merge order which is defined by invariants specified in Documentation/git-rev-list.txt. The linearisation produced by this patch is superior in an objective sense to that produced by the existing git-rev-list implementation in that the linearisation produced is guaranteed to have the minimum number of discontinuities, where a discontinuity is defined as an adjacent pair of commits in the output list which are not related in a direct child-parent relationship. With this patch a graph like this: a4 --- | \ \ | b4 | |/ | | a3 | | | | | a2 | | | | c3 | | | | | c2 | b3 | | | /| | b2 | | | c1 | | / | b1 a1 | | | a0 | | / root Sorts like this: = a4 | c3 | c2 | c1 ^ b4 | b3 | b2 | b1 ^ a3 | a2 | a1 | a0 = root Instead of this: = a4 | c3 ^ b4 | a3 ^ c2 ^ b3 ^ a2 ^ b2 ^ c1 ^ a1 ^ b1 ^ a0 = root A test script, t/t6000-rev-list.sh, includes a test which demonstrates that the linearisation produced by --merge-order has less discontinuities than the linearisation produced by git-rev-list without the --merge-order flag specified. To see this, do the following: cd t ./t6000-rev-list.sh cd trash cat actual-default-order cat actual-merge-order The existing behaviour of git-rev-list is preserved, by default. To obtain the modified behaviour, specify --merge-order or --merge-order --show-breaks on the command line. This version of the patch has been tested on the git repository and also on the linux-2.6 repository and has reasonable performance on both - ~50-100% slower than the original algorithm. This version of the patch has incorporated a functional equivalent of the Linus' output limiting algorithm into the merge-order algorithm itself. This operates per the notes associated with Linus' commit 337cb3fb8da45f10fe9a0c3cf571600f55ead2ce. This version has incorporated Linus' feedback regarding proposed changes to rev-list.c. (see: [PATCH] Factor out filtering in rev-list.c) This version has improved the way sort_first_epoch marks commits as uninteresting. For more details about this change, refer to Documentation/git-rev-list.txt and http://blackcubes.dyndns.org/epoch/. Signed-off-by: Jon Seymour <jon.seymour@gmail.com> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-06 17:39:40 +02:00
struct commit *pop_commit(struct commit_list **stack);
void clear_commit_marks(struct commit *commit, unsigned int mark);
void clear_commit_marks_many(int nr, struct commit **commit, unsigned int mark);
void clear_commit_marks_for_object_array(struct object_array *a, unsigned mark);
toposort: rename "lifo" field The primary invariant of sort_in_topological_order() is that a parent commit is not emitted until all children of it are. When traversing a forked history like this with "git log C E": A----B----C \ D----E we ensure that A is emitted after all of B, C, D, and E are done, B has to wait until C is done, and D has to wait until E is done. In some applications, however, we would further want to control how these child commits B, C, D and E on two parallel ancestry chains are shown. Most of the time, we would want to see C and B emitted together, and then E and D, and finally A (i.e. the --topo-order output). The "lifo" parameter of the sort_in_topological_order() function is used to control this behaviour. We start the traversal by knowing two commits, C and E. While keeping in mind that we also need to inspect E later, we pick C first to inspect, and we notice and record that B needs to be inspected. By structuring the "work to be done" set as a LIFO stack, we ensure that B is inspected next, before other in-flight commits we had known that we will need to inspect, e.g. E. When showing in --date-order, we would want to see commits ordered by timestamps, i.e. show C, E, B and D in this order before showing A, possibly mixing commits from two parallel histories together. When "lifo" parameter is set to false, the function keeps the "work to be done" set sorted in the date order to realize this semantics. After inspecting C, we add B to the "work to be done" set, but the next commit we inspect from the set is E which is newer than B. The name "lifo", however, is too strongly tied to the way how the function implements its behaviour, and does not describe what the behaviour _means_. Replace this field with an enum rev_sort_order, with two possible values: REV_SORT_IN_GRAPH_ORDER and REV_SORT_BY_COMMIT_DATE, and update the existing code. The mechanical replacement rule is: "lifo == 0" is equivalent to "sort_order == REV_SORT_BY_COMMIT_DATE" "lifo == 1" is equivalent to "sort_order == REV_SORT_IN_GRAPH_ORDER" Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-07 01:07:14 +02:00
enum rev_sort_order {
REV_SORT_IN_GRAPH_ORDER = 0,
REV_SORT_BY_COMMIT_DATE,
REV_SORT_BY_AUTHOR_DATE
toposort: rename "lifo" field The primary invariant of sort_in_topological_order() is that a parent commit is not emitted until all children of it are. When traversing a forked history like this with "git log C E": A----B----C \ D----E we ensure that A is emitted after all of B, C, D, and E are done, B has to wait until C is done, and D has to wait until E is done. In some applications, however, we would further want to control how these child commits B, C, D and E on two parallel ancestry chains are shown. Most of the time, we would want to see C and B emitted together, and then E and D, and finally A (i.e. the --topo-order output). The "lifo" parameter of the sort_in_topological_order() function is used to control this behaviour. We start the traversal by knowing two commits, C and E. While keeping in mind that we also need to inspect E later, we pick C first to inspect, and we notice and record that B needs to be inspected. By structuring the "work to be done" set as a LIFO stack, we ensure that B is inspected next, before other in-flight commits we had known that we will need to inspect, e.g. E. When showing in --date-order, we would want to see commits ordered by timestamps, i.e. show C, E, B and D in this order before showing A, possibly mixing commits from two parallel histories together. When "lifo" parameter is set to false, the function keeps the "work to be done" set sorted in the date order to realize this semantics. After inspecting C, we add B to the "work to be done" set, but the next commit we inspect from the set is E which is newer than B. The name "lifo", however, is too strongly tied to the way how the function implements its behaviour, and does not describe what the behaviour _means_. Replace this field with an enum rev_sort_order, with two possible values: REV_SORT_IN_GRAPH_ORDER and REV_SORT_BY_COMMIT_DATE, and update the existing code. The mechanical replacement rule is: "lifo == 0" is equivalent to "sort_order == REV_SORT_BY_COMMIT_DATE" "lifo == 1" is equivalent to "sort_order == REV_SORT_IN_GRAPH_ORDER" Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-07 01:07:14 +02:00
};
/*
* Performs an in-place topological sort of list supplied.
*
* invariant of resulting list is:
* a reachable from b => ord(b) < ord(a)
toposort: rename "lifo" field The primary invariant of sort_in_topological_order() is that a parent commit is not emitted until all children of it are. When traversing a forked history like this with "git log C E": A----B----C \ D----E we ensure that A is emitted after all of B, C, D, and E are done, B has to wait until C is done, and D has to wait until E is done. In some applications, however, we would further want to control how these child commits B, C, D and E on two parallel ancestry chains are shown. Most of the time, we would want to see C and B emitted together, and then E and D, and finally A (i.e. the --topo-order output). The "lifo" parameter of the sort_in_topological_order() function is used to control this behaviour. We start the traversal by knowing two commits, C and E. While keeping in mind that we also need to inspect E later, we pick C first to inspect, and we notice and record that B needs to be inspected. By structuring the "work to be done" set as a LIFO stack, we ensure that B is inspected next, before other in-flight commits we had known that we will need to inspect, e.g. E. When showing in --date-order, we would want to see commits ordered by timestamps, i.e. show C, E, B and D in this order before showing A, possibly mixing commits from two parallel histories together. When "lifo" parameter is set to false, the function keeps the "work to be done" set sorted in the date order to realize this semantics. After inspecting C, we add B to the "work to be done" set, but the next commit we inspect from the set is E which is newer than B. The name "lifo", however, is too strongly tied to the way how the function implements its behaviour, and does not describe what the behaviour _means_. Replace this field with an enum rev_sort_order, with two possible values: REV_SORT_IN_GRAPH_ORDER and REV_SORT_BY_COMMIT_DATE, and update the existing code. The mechanical replacement rule is: "lifo == 0" is equivalent to "sort_order == REV_SORT_BY_COMMIT_DATE" "lifo == 1" is equivalent to "sort_order == REV_SORT_IN_GRAPH_ORDER" Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-07 01:07:14 +02:00
* sort_order further specifies:
* REV_SORT_IN_GRAPH_ORDER: try to show a commit on a single-parent
* chain together.
* REV_SORT_BY_COMMIT_DATE: show eligible commits in committer-date order.
*/
toposort: rename "lifo" field The primary invariant of sort_in_topological_order() is that a parent commit is not emitted until all children of it are. When traversing a forked history like this with "git log C E": A----B----C \ D----E we ensure that A is emitted after all of B, C, D, and E are done, B has to wait until C is done, and D has to wait until E is done. In some applications, however, we would further want to control how these child commits B, C, D and E on two parallel ancestry chains are shown. Most of the time, we would want to see C and B emitted together, and then E and D, and finally A (i.e. the --topo-order output). The "lifo" parameter of the sort_in_topological_order() function is used to control this behaviour. We start the traversal by knowing two commits, C and E. While keeping in mind that we also need to inspect E later, we pick C first to inspect, and we notice and record that B needs to be inspected. By structuring the "work to be done" set as a LIFO stack, we ensure that B is inspected next, before other in-flight commits we had known that we will need to inspect, e.g. E. When showing in --date-order, we would want to see commits ordered by timestamps, i.e. show C, E, B and D in this order before showing A, possibly mixing commits from two parallel histories together. When "lifo" parameter is set to false, the function keeps the "work to be done" set sorted in the date order to realize this semantics. After inspecting C, we add B to the "work to be done" set, but the next commit we inspect from the set is E which is newer than B. The name "lifo", however, is too strongly tied to the way how the function implements its behaviour, and does not describe what the behaviour _means_. Replace this field with an enum rev_sort_order, with two possible values: REV_SORT_IN_GRAPH_ORDER and REV_SORT_BY_COMMIT_DATE, and update the existing code. The mechanical replacement rule is: "lifo == 0" is equivalent to "sort_order == REV_SORT_BY_COMMIT_DATE" "lifo == 1" is equivalent to "sort_order == REV_SORT_IN_GRAPH_ORDER" Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-06-07 01:07:14 +02:00
void sort_in_topological_order(struct commit_list **, enum rev_sort_order);
struct commit_graft {
unsigned char sha1[20];
int nr_parent; /* < 0 if shallow commit */
unsigned char parent[FLEX_ARRAY][20]; /* more */
};
typedef int (*each_commit_graft_fn)(const struct commit_graft *, void *);
struct commit_graft *read_graft_line(char *buf, int len);
int register_commit_graft(struct commit_graft *, int);
struct commit_graft *lookup_commit_graft(const unsigned char *sha1);
extern struct commit_list *get_merge_bases(struct commit *rev1, struct commit *rev2, int cleanup);
extern struct commit_list *get_merge_bases_many(struct commit *one, int n, struct commit **twos, int cleanup);
extern struct commit_list *get_octopus_merge_bases(struct commit_list *in);
/* largest positive number a signed 32-bit integer can contain */
#define INFINITE_DEPTH 0x7fffffff
extern int register_shallow(const unsigned char *sha1);
extern int unregister_shallow(const unsigned char *sha1);
extern int for_each_commit_graft(each_commit_graft_fn, void *);
extern int is_repository_shallow(void);
extern struct commit_list *get_shallow_commits(struct object_array *heads,
int depth, int shallow_flag, int not_shallow_flag);
extern void check_shallow_file_for_update(void);
extern void set_alternate_shallow_file(const char *path);
int is_descendant_of(struct commit *, struct commit_list *);
int in_merge_bases(struct commit *, struct commit *);
int in_merge_bases_many(struct commit *, int, struct commit **);
extern int interactive_add(int argc, const char **argv, const char *prefix, int patch);
extern int run_add_interactive(const char *revision, const char *patch_mode,
const char **pathspec);
static inline int single_parent(struct commit *commit)
{
return commit->parents && !commit->parents->next;
}
struct commit_list *reduce_heads(struct commit_list *heads);
struct commit_extra_header {
struct commit_extra_header *next;
char *key;
char *value;
size_t len;
};
extern void append_merge_tag_headers(struct commit_list *parents,
struct commit_extra_header ***tail);
extern int commit_tree(const struct strbuf *msg, unsigned char *tree,
struct commit_list *parents, unsigned char *ret,
commit: teach --gpg-sign option This uses the gpg-interface.[ch] to allow signing the commit, i.e. $ git commit --gpg-sign -m foo You need a passphrase to unlock the secret key for user: "Junio C Hamano <gitster@pobox.com>" 4096-bit RSA key, ID 96AFE6CB, created 2011-10-03 (main key ID 713660A7) [master 8457d13] foo 1 files changed, 1 insertions(+), 0 deletions(-) The lines of GPG detached signature are placed in a new multi-line header field, instead of tucking the signature block at the end of the commit log message text (similar to how signed tag is done), for multiple reasons: - The signature won't clutter output from "git log" and friends if it is in the extra header. If we place it at the end of the log message, we would need to teach "git log" and friends to strip the signature block with an option. - Teaching new versions of "git log" and "gitk" to optionally verify and show signatures is cleaner if we structurally know where the signature block is (instead of scanning in the commit log message). - The signature needs to be stripped upon various commit rewriting operations, e.g. rebase, filter-branch, etc. They all already ignore unknown headers, but if we place signature in the log message, all of these tools (and third-party tools) also need to learn how a signature block would look like. - When we added the optional encoding header, all the tools (both in tree and third-party) that acts on the raw commit object should have been fixed to ignore headers they do not understand, so it is not like that new header would be more likely to break than extra text in the commit. A commit made with the above sample sequence would look like this: $ git cat-file commit HEAD tree 3cd71d90e3db4136e5260ab54599791c4f883b9d parent b87755351a47b09cb27d6913e6e0e17e6254a4d4 author Junio C Hamano <gitster@pobox.com> 1317862251 -0700 committer Junio C Hamano <gitster@pobox.com> 1317862251 -0700 gpgsig -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.10 (GNU/Linux) iQIcBAABAgAGBQJOjPtrAAoJELC16IaWr+bL4TMP/RSe2Y/jYnCkds9unO5JEnfG ... =dt98 -----END PGP SIGNATURE----- foo but "git log" (unless you ask for it with --pretty=raw) output is not cluttered with the signature information. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-10-06 02:23:20 +02:00
const char *author, const char *sign_commit);
extern int commit_tree_extended(const struct strbuf *msg, unsigned char *tree,
struct commit_list *parents, unsigned char *ret,
commit: teach --gpg-sign option This uses the gpg-interface.[ch] to allow signing the commit, i.e. $ git commit --gpg-sign -m foo You need a passphrase to unlock the secret key for user: "Junio C Hamano <gitster@pobox.com>" 4096-bit RSA key, ID 96AFE6CB, created 2011-10-03 (main key ID 713660A7) [master 8457d13] foo 1 files changed, 1 insertions(+), 0 deletions(-) The lines of GPG detached signature are placed in a new multi-line header field, instead of tucking the signature block at the end of the commit log message text (similar to how signed tag is done), for multiple reasons: - The signature won't clutter output from "git log" and friends if it is in the extra header. If we place it at the end of the log message, we would need to teach "git log" and friends to strip the signature block with an option. - Teaching new versions of "git log" and "gitk" to optionally verify and show signatures is cleaner if we structurally know where the signature block is (instead of scanning in the commit log message). - The signature needs to be stripped upon various commit rewriting operations, e.g. rebase, filter-branch, etc. They all already ignore unknown headers, but if we place signature in the log message, all of these tools (and third-party tools) also need to learn how a signature block would look like. - When we added the optional encoding header, all the tools (both in tree and third-party) that acts on the raw commit object should have been fixed to ignore headers they do not understand, so it is not like that new header would be more likely to break than extra text in the commit. A commit made with the above sample sequence would look like this: $ git cat-file commit HEAD tree 3cd71d90e3db4136e5260ab54599791c4f883b9d parent b87755351a47b09cb27d6913e6e0e17e6254a4d4 author Junio C Hamano <gitster@pobox.com> 1317862251 -0700 committer Junio C Hamano <gitster@pobox.com> 1317862251 -0700 gpgsig -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.10 (GNU/Linux) iQIcBAABAgAGBQJOjPtrAAoJELC16IaWr+bL4TMP/RSe2Y/jYnCkds9unO5JEnfG ... =dt98 -----END PGP SIGNATURE----- foo but "git log" (unless you ask for it with --pretty=raw) output is not cluttered with the signature information. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-10-06 02:23:20 +02:00
const char *author, const char *sign_commit,
struct commit_extra_header *);
extern struct commit_extra_header *read_commit_extra_headers(struct commit *, const char **);
extern void free_commit_extra_headers(struct commit_extra_header *extra);
struct merge_remote_desc {
struct object *obj; /* the named object, could be a tag */
const char *name;
};
#define merge_remote_util(commit) ((struct merge_remote_desc *)((commit)->util))
/*
* Given "name" from the command line to merge, find the commit object
* and return it, while storing merge_remote_desc in its ->util field,
* to allow callers to tell if we are told to merge a tag.
*/
struct commit *get_merge_parent(const char *name);
extern int parse_signed_commit(const unsigned char *sha1,
struct strbuf *message, struct strbuf *signature);
extern void print_commit_list(struct commit_list *list,
const char *format_cur,
const char *format_last);
/*
* Check the signature of the given commit. The result of the check is stored
* in sig->check_result, 'G' for a good signature, 'U' for a good signature
* from an untrusted signer, 'B' for a bad signature and 'N' for no signature
* at all. This may allocate memory for sig->gpg_output, sig->gpg_status,
* sig->signer and sig->key.
*/
extern void check_commit_signature(const struct commit* commit, struct signature_check *sigc);
#endif /* COMMIT_H */