git/commit.h

385 lines
14 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"
#include "string-list.h"
#include "pretty.h"
#include "commit-slab.h"
#define COMMIT_NOT_FROM_GRAPH 0xFFFFFFFF
#define GENERATION_NUMBER_INFINITY 0xFFFFFFFF
#define GENERATION_NUMBER_MAX 0x3FFFFFFF
#define GENERATION_NUMBER_ZERO 0
struct commit_list {
struct commit *item;
struct commit_list *next;
};
/*
* The size of this struct matters in full repo walk operations like
* 'git clone' or 'git gc'. Consider using commit-slab to attach data
* to a commit instead of adding new fields here.
*/
struct commit {
struct object object;
timestamp_t date;
struct commit_list *parents;
/*
* If the commit is loaded from the commit-graph file, then this
* member may be NULL. Only access it through get_commit_tree()
* or get_commit_tree_oid().
*/
struct tree *maybe_tree;
uint32_t graph_pos;
uint32_t generation;
unsigned int index;
};
[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>
2005-09-16 05:43:17 +08:00
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.. */
struct name_decoration {
struct name_decoration *next;
int type;
char name[FLEX_ARRAY];
};
enum decoration_type {
DECORATION_NONE = 0,
DECORATION_REF_LOCAL,
DECORATION_REF_REMOTE,
DECORATION_REF_TAG,
DECORATION_REF_STASH,
DECORATION_REF_HEAD,
DECORATION_GRAFTED,
};
void add_name_decoration(enum decoration_type type, const char *name, struct object *obj);
const struct name_decoration *get_name_decoration(const struct object *obj);
struct commit *lookup_commit(struct repository *r, const struct object_id *oid);
struct commit *lookup_commit_reference(struct repository *r,
const struct object_id *oid);
struct commit *lookup_commit_reference_gently(struct repository *r,
const struct object_id *oid,
int quiet);
struct commit *lookup_commit_reference_by_name(const char *name);
/*
Convert lookup_commit* to struct object_id Convert lookup_commit, lookup_commit_or_die, lookup_commit_reference, and lookup_commit_reference_gently to take struct object_id arguments. Introduce a temporary in parse_object buffer in order to convert this function. This is required since in order to convert parse_object and parse_object_buffer, lookup_commit_reference_gently and lookup_commit_or_die would need to be converted. Not introducing a temporary would therefore require that lookup_commit_or_die take a struct object_id *, but lookup_commit would take unsigned char *, leaving a confusing and hard-to-use interface. parse_object_buffer will lose this temporary in a later patch. This commit was created with manual changes to commit.c, commit.h, and object.c, plus the following semantic patch: @@ expression E1, E2; @@ - lookup_commit_reference_gently(E1.hash, E2) + lookup_commit_reference_gently(&E1, E2) @@ expression E1, E2; @@ - lookup_commit_reference_gently(E1->hash, E2) + lookup_commit_reference_gently(E1, E2) @@ expression E1; @@ - lookup_commit_reference(E1.hash) + lookup_commit_reference(&E1) @@ expression E1; @@ - lookup_commit_reference(E1->hash) + lookup_commit_reference(E1) @@ expression E1; @@ - lookup_commit(E1.hash) + lookup_commit(&E1) @@ expression E1; @@ - lookup_commit(E1->hash) + lookup_commit(E1) @@ expression E1, E2; @@ - lookup_commit_or_die(E1.hash, E2) + lookup_commit_or_die(&E1, E2) @@ expression E1, E2; @@ - lookup_commit_or_die(E1->hash, E2) + lookup_commit_or_die(E1, E2) Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-07 06:10:10 +08:00
* Look up object named by "oid", dereference tag as necessary,
* get a commit and return it. If "oid" does not dereference to
* a commit, use ref_name to report an error and die.
*/
Convert lookup_commit* to struct object_id Convert lookup_commit, lookup_commit_or_die, lookup_commit_reference, and lookup_commit_reference_gently to take struct object_id arguments. Introduce a temporary in parse_object buffer in order to convert this function. This is required since in order to convert parse_object and parse_object_buffer, lookup_commit_reference_gently and lookup_commit_or_die would need to be converted. Not introducing a temporary would therefore require that lookup_commit_or_die take a struct object_id *, but lookup_commit would take unsigned char *, leaving a confusing and hard-to-use interface. parse_object_buffer will lose this temporary in a later patch. This commit was created with manual changes to commit.c, commit.h, and object.c, plus the following semantic patch: @@ expression E1, E2; @@ - lookup_commit_reference_gently(E1.hash, E2) + lookup_commit_reference_gently(&E1, E2) @@ expression E1, E2; @@ - lookup_commit_reference_gently(E1->hash, E2) + lookup_commit_reference_gently(E1, E2) @@ expression E1; @@ - lookup_commit_reference(E1.hash) + lookup_commit_reference(&E1) @@ expression E1; @@ - lookup_commit_reference(E1->hash) + lookup_commit_reference(E1) @@ expression E1; @@ - lookup_commit(E1.hash) + lookup_commit(&E1) @@ expression E1; @@ - lookup_commit(E1->hash) + lookup_commit(E1) @@ expression E1, E2; @@ - lookup_commit_or_die(E1.hash, E2) + lookup_commit_or_die(&E1, E2) @@ expression E1, E2; @@ - lookup_commit_or_die(E1->hash, E2) + lookup_commit_or_die(E1, E2) Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-07 06:10:10 +08:00
struct commit *lookup_commit_or_die(const struct object_id *oid, const char *ref_name);
int parse_commit_buffer(struct repository *r, struct commit *item, const void *buffer, unsigned long size, int check_graph);
int repo_parse_commit_internal(struct repository *r, struct commit *item,
int quiet_on_missing, int use_commit_graph);
int repo_parse_commit_gently(struct repository *r,
struct commit *item,
int quiet_on_missing);
static inline int repo_parse_commit(struct repository *r, struct commit *item)
{
return repo_parse_commit_gently(r, item, 0);
}
#ifndef NO_THE_REPOSITORY_COMPATIBILITY_MACROS
#define parse_commit_internal(item, quiet, use) repo_parse_commit_internal(the_repository, item, quiet, use)
#define parse_commit_gently(item, quiet) repo_parse_commit_gently(the_repository, item, quiet)
#define parse_commit(item) repo_parse_commit(the_repository, item)
#endif
void parse_commit_or_die(struct commit *item);
struct buffer_slab;
struct buffer_slab *allocate_commit_buffer_slab(void);
void free_commit_buffer_slab(struct buffer_slab *bs);
/*
* Associate an object buffer with the commit. The ownership of the
* memory is handed over to the commit, and must be free()-able.
*/
void set_commit_buffer(struct repository *r, struct commit *, void *buffer, unsigned long size);
/*
* Get any cached object buffer associated with the commit. Returns NULL
* if none. The resulting memory should not be freed.
*/
const void *get_cached_commit_buffer(struct repository *, const struct commit *, unsigned long *size);
/*
* Get the commit's object contents, either from cache or by reading the object
* from disk. The resulting memory should not be modified, and must be given
* to unuse_commit_buffer when the caller is done.
*/
const void *repo_get_commit_buffer(struct repository *r,
const struct commit *,
unsigned long *size);
#ifndef NO_THE_REPOSITORY_COMPATIBILITY_MACROS
#define get_commit_buffer(c, s) repo_get_commit_buffer(the_repository, c, s)
#endif
/*
* Tell the commit subsytem that we are done with a particular commit buffer.
* The commit and buffer should be the input and return value, respectively,
* from an earlier call to get_commit_buffer. The buffer may or may not be
* freed by this call; callers should not access the memory afterwards.
*/
void repo_unuse_commit_buffer(struct repository *r,
const struct commit *,
const void *buffer);
#ifndef NO_THE_REPOSITORY_COMPATIBILITY_MACROS
#define unuse_commit_buffer(c, b) repo_unuse_commit_buffer(the_repository, c, b)
#endif
/*
* Free any cached object buffer associated with the commit.
*/
void free_commit_buffer(struct parsed_object_pool *pool, struct commit *);
struct tree *get_commit_tree(const struct commit *);
struct object_id *get_commit_tree_oid(const struct commit *);
/*
* Release memory related to a commit, including the parent list and
* any cached object buffer.
*/
void release_commit_memory(struct parsed_object_pool *pool, struct commit *c);
/*
* Disassociate any cached object buffer from the commit, but do not free it.
* The buffer (or NULL, if none) is returned.
*/
const void *detach_commit_buffer(struct commit *, unsigned long *sizep);
/* 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);
log: use true parents for diff even when rewriting When using pathspec filtering in combination with diff-based log output, parent simplification happens before the diff is computed. The diff is therefore against the *simplified* parents. This works okay, arguably by accident, in the normal case: simplification reduces to one parent as long as the commit is TREESAME to it. So the simplified parent of any given commit must have the same tree contents on the filtered paths as its true (unfiltered) parent. However, --full-diff breaks this guarantee, and indeed gives pretty spectacular results when comparing the output of git log --graph --stat ... git log --graph --full-diff --stat ... (--graph internally kicks in parent simplification, much like --parents). To fix it, store a copy of the parent list before simplification (in a slab) whenever --full-diff is in effect. Then use the stored parents instead of the simplified ones in the commit display code paths. The latter do not actually check for --full-diff to avoid duplicated code; they just grab the original parents if save_parents() has not been called for this revision walk. For ordinary commits it should be obvious that this is the right thing to do. Merge commits are a bit subtle. Observe that with default simplification, merge simplification is an all-or-nothing decision: either the merge is TREESAME to one parent and disappears, or it is different from all parents and the parent list remains intact. Redundant parents are not pruned, so the existing code also shows them as a merge. So if we do show a merge commit, the parent list just consists of the rewrite result on each parent. Running, e.g., --cc on this in --full-diff mode is not very useful: if any commits were skipped, some hunks will disagree with all sides of the merge (with one side, because commits were skipped; with the others, because they didn't have those changes in the first place). This triggers --cc showing these hunks spuriously. Therefore I believe that even for merge commits it is better to show the diffs wrt. the original parents. Reported-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> Helped-by: Junio C Hamano <gitster@pobox.com> Helped-by: Ramsay Jones <ramsay@ramsay1.demon.co.uk> Signed-off-by: Thomas Rast <trast@inf.ethz.ch> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-08-01 04:13:20 +08:00
/* Shallow copy of the input list */
struct commit_list *copy_commit_list(struct commit_list *list);
void free_commit_list(struct commit_list *list);
struct rev_info; /* in revision.h, it circularly uses enum cmit_fmt */
int has_non_ascii(const char *text);
const char *logmsg_reencode(const struct commit *commit,
char **commit_encoding,
const char *output_encoding);
const char *repo_logmsg_reencode(struct repository *r,
const struct commit *commit,
char **commit_encoding,
const char *output_encoding);
#ifndef NO_THE_REPOSITORY_COMPATIBILITY_MACROS
#define logmsg_reencode(c, enc, out) repo_logmsg_reencode(the_repository, c, enc, out)
#endif
const char *skip_blank_lines(const char *msg);
/** 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 23:39:40 +08:00
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);
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 07:07:14 +08:00
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 07:07:14 +08:00
};
/*
* 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 07:07:14 +08:00
* 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 07:07:14 +08:00
void sort_in_topological_order(struct commit_list **, enum rev_sort_order);
struct commit_graft {
struct object_id oid;
int nr_parent; /* < 0 if shallow commit */
struct object_id parent[FLEX_ARRAY]; /* more */
};
typedef int (*each_commit_graft_fn)(const struct commit_graft *, void *);
struct commit_graft *read_graft_line(struct strbuf *line);
int register_commit_graft(struct repository *r, struct commit_graft *, int);
void prepare_commit_graft(struct repository *r);
struct commit_graft *lookup_commit_graft(struct repository *r, const struct object_id *oid);
struct commit *get_fork_point(const char *refname, struct commit *commit);
/* largest positive number a signed 32-bit integer can contain */
#define INFINITE_DEPTH 0x7fffffff
struct oid_array;
shallow.c: the 8 steps to select new commits for .git/shallow Suppose a fetch or push is requested between two shallow repositories (with no history deepening or shortening). A pack that contains necessary objects is transferred over together with .git/shallow of the sender. The receiver has to determine whether it needs to update .git/shallow if new refs needs new shallow comits. The rule here is avoid updating .git/shallow by default. But we don't want to waste the received pack. If the pack contains two refs, one needs new shallow commits installed in .git/shallow and one does not, we keep the latter and reject/warn about the former. Even if .git/shallow update is allowed, we only add shallow commits strictly necessary for the former ref (remember the sender can send more shallow commits than necessary) and pay attention not to accidentally cut the receiver history short (no history shortening is asked for) So the steps to figure out what ref need what new shallow commits are: 1. Split the sender shallow commit list into "ours" and "theirs" list by has_sha1_file. Those that exist in current repo in "ours", the remaining in "theirs". 2. Check the receiver .git/shallow, remove from "ours" the ones that also exist in .git/shallow. 3. Fetch the new pack. Either install or unpack it. 4. Do has_sha1_file on "theirs" list again. Drop the ones that fail has_sha1_file. Obviously the new pack does not need them. 5. If the pack is kept, remove from "ours" the ones that do not exist in the new pack. 6. Walk the new refs to answer the question "what shallow commits, both ours and theirs, are required in .git/shallow in order to add this ref?". Shallow commits not associated to any refs are removed from their respective list. 7. (*) Check reachability (from the current refs) of all remaining commits in "ours". Those reachable are removed. We do not want to cut any part of our (reachable) history. We only check up commits. True reachability test is done by check_everything_connected() at the end as usual. 8. Combine the final "ours" and "theirs" and add them all to .git/shallow. Install new refs. The case where some hook rejects some refs on a push is explained in more detail in the push patches. Of these steps, #6 and #7 are expensive. Both require walking through some commits, or in the worst case all commits. And we rather avoid them in at least common case, where the transferred pack does not contain any shallow commits that the sender advertises. Let's look at each scenario: 1) the sender has longer history than the receiver All shallow commits from the sender will be put into "theirs" list at step 1 because none of them exists in current repo. In the common case, "theirs" becomes empty at step 4 and exit early. 2) the sender has shorter history than the receiver All shallow commits from the sender are likely in "ours" list at step 1. In the common case, if the new pack is kept, we could empty "ours" and exit early at step 5. If the pack is not kept, we hit the expensive step 6 then exit after "ours" is emptied. There'll be only a handful of objects to walk in fast-forward case. If it's forced update, we may need to walk to the bottom. 3) the sender has same .git/shallow as the receiver This is similar to case 2 except that "ours" should be emptied at step 2 and exit early. A fetch after "clone --depth=X" is case 1. A fetch after "clone" (from a shallow repo) is case 3. Luckily they're cheap for the common case. A push from "clone --depth=X" falls into case 2, which is expensive. Some more work may be done at the sender/client side to avoid more work on the server side: if the transferred pack does not contain any shallow commits, send-pack should not send any shallow commits to the receive-pack, effectively turning it into a normal push and avoid all steps. This patch implements all steps except #3, already handled by fetch-pack and receive-pack, #6 and #7, which has their own patch due to their size. (*) in previous versions step 7 was put before step 3. I reorder it so that the common case that keeps the pack does not need to walk commits at all. In future if we implement faster commit reachability check (maybe with the help of pack bitmaps or commit cache), step 7 could become cheap and be moved up before 6 again. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-05 21:02:35 +08:00
struct ref;
int register_shallow(struct repository *r, const struct object_id *oid);
int unregister_shallow(const struct object_id *oid);
int for_each_commit_graft(each_commit_graft_fn, void *);
int is_repository_shallow(struct repository *r);
struct commit_list *get_shallow_commits(struct object_array *heads,
int depth, int shallow_flag, int not_shallow_flag);
struct commit_list *get_shallow_commits_by_rev_list(
shallow.c: implement a generic shallow boundary finder based on rev-list Instead of a custom commit walker like get_shallow_commits(), this new function uses rev-list to mark NOT_SHALLOW to all reachable commits, except borders. The definition of reachable is to be defined by the protocol later. This makes it more flexible to define shallow boundary. The way we find border is paint all reachable commits NOT_SHALLOW. Any of them that "touches" commits without NOT_SHALLOW flag are considered shallow (e.g. zero parents via grafting mechanism). Shallow commits and their true parents are all marked SHALLOW. Then NOT_SHALLOW is removed from shallow commits at the end. There is an interesting observation. With a generic walker, we can produce all kinds of shallow cutting. In the following graph, every commit but "x" is reachable. "b" is a parent of "a". x -- a -- o / / x -- c -- b -- o After this function is run, "a" and "c" are both considered shallow commits. After grafting occurs at the client side, what we see is a -- o / c -- b -- o Notice that because of grafting, "a" has zero parents, so "b" is no longer a parent of "a". This is unfortunate and may be solved in two ways. The first is change the way shallow grafting works and keep "a -- b" connection if "b" exists and always ends at shallow commits (iow, no loose ends). This is hard to detect, or at least not cheap to do. The second way is mark one "x" as shallow commit instead of "a" and produce this graph at client side: x -- a -- o / / c -- b -- o More commits, but simpler grafting rules. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-06-12 18:53:57 +08:00
int ac, const char **av, int shallow_flag, int not_shallow_flag);
void set_alternate_shallow_file(struct repository *r, const char *path, int override);
int write_shallow_commits(struct strbuf *out, int use_pack_protocol,
const struct oid_array *extra);
void setup_alternate_shallow(struct lock_file *shallow_lock,
const char **alternate_shallow_file,
const struct oid_array *extra);
const char *setup_temporary_shallow(const struct oid_array *extra);
void advertise_shallow_grafts(int);
shallow.c: the 8 steps to select new commits for .git/shallow Suppose a fetch or push is requested between two shallow repositories (with no history deepening or shortening). A pack that contains necessary objects is transferred over together with .git/shallow of the sender. The receiver has to determine whether it needs to update .git/shallow if new refs needs new shallow comits. The rule here is avoid updating .git/shallow by default. But we don't want to waste the received pack. If the pack contains two refs, one needs new shallow commits installed in .git/shallow and one does not, we keep the latter and reject/warn about the former. Even if .git/shallow update is allowed, we only add shallow commits strictly necessary for the former ref (remember the sender can send more shallow commits than necessary) and pay attention not to accidentally cut the receiver history short (no history shortening is asked for) So the steps to figure out what ref need what new shallow commits are: 1. Split the sender shallow commit list into "ours" and "theirs" list by has_sha1_file. Those that exist in current repo in "ours", the remaining in "theirs". 2. Check the receiver .git/shallow, remove from "ours" the ones that also exist in .git/shallow. 3. Fetch the new pack. Either install or unpack it. 4. Do has_sha1_file on "theirs" list again. Drop the ones that fail has_sha1_file. Obviously the new pack does not need them. 5. If the pack is kept, remove from "ours" the ones that do not exist in the new pack. 6. Walk the new refs to answer the question "what shallow commits, both ours and theirs, are required in .git/shallow in order to add this ref?". Shallow commits not associated to any refs are removed from their respective list. 7. (*) Check reachability (from the current refs) of all remaining commits in "ours". Those reachable are removed. We do not want to cut any part of our (reachable) history. We only check up commits. True reachability test is done by check_everything_connected() at the end as usual. 8. Combine the final "ours" and "theirs" and add them all to .git/shallow. Install new refs. The case where some hook rejects some refs on a push is explained in more detail in the push patches. Of these steps, #6 and #7 are expensive. Both require walking through some commits, or in the worst case all commits. And we rather avoid them in at least common case, where the transferred pack does not contain any shallow commits that the sender advertises. Let's look at each scenario: 1) the sender has longer history than the receiver All shallow commits from the sender will be put into "theirs" list at step 1 because none of them exists in current repo. In the common case, "theirs" becomes empty at step 4 and exit early. 2) the sender has shorter history than the receiver All shallow commits from the sender are likely in "ours" list at step 1. In the common case, if the new pack is kept, we could empty "ours" and exit early at step 5. If the pack is not kept, we hit the expensive step 6 then exit after "ours" is emptied. There'll be only a handful of objects to walk in fast-forward case. If it's forced update, we may need to walk to the bottom. 3) the sender has same .git/shallow as the receiver This is similar to case 2 except that "ours" should be emptied at step 2 and exit early. A fetch after "clone --depth=X" is case 1. A fetch after "clone" (from a shallow repo) is case 3. Luckily they're cheap for the common case. A push from "clone --depth=X" falls into case 2, which is expensive. Some more work may be done at the sender/client side to avoid more work on the server side: if the transferred pack does not contain any shallow commits, send-pack should not send any shallow commits to the receive-pack, effectively turning it into a normal push and avoid all steps. This patch implements all steps except #3, already handled by fetch-pack and receive-pack, #6 and #7, which has their own patch due to their size. (*) in previous versions step 7 was put before step 3. I reorder it so that the common case that keeps the pack does not need to walk commits at all. In future if we implement faster commit reachability check (maybe with the help of pack bitmaps or commit cache), step 7 could become cheap and be moved up before 6 again. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-05 21:02:35 +08:00
struct shallow_info {
struct oid_array *shallow;
shallow.c: the 8 steps to select new commits for .git/shallow Suppose a fetch or push is requested between two shallow repositories (with no history deepening or shortening). A pack that contains necessary objects is transferred over together with .git/shallow of the sender. The receiver has to determine whether it needs to update .git/shallow if new refs needs new shallow comits. The rule here is avoid updating .git/shallow by default. But we don't want to waste the received pack. If the pack contains two refs, one needs new shallow commits installed in .git/shallow and one does not, we keep the latter and reject/warn about the former. Even if .git/shallow update is allowed, we only add shallow commits strictly necessary for the former ref (remember the sender can send more shallow commits than necessary) and pay attention not to accidentally cut the receiver history short (no history shortening is asked for) So the steps to figure out what ref need what new shallow commits are: 1. Split the sender shallow commit list into "ours" and "theirs" list by has_sha1_file. Those that exist in current repo in "ours", the remaining in "theirs". 2. Check the receiver .git/shallow, remove from "ours" the ones that also exist in .git/shallow. 3. Fetch the new pack. Either install or unpack it. 4. Do has_sha1_file on "theirs" list again. Drop the ones that fail has_sha1_file. Obviously the new pack does not need them. 5. If the pack is kept, remove from "ours" the ones that do not exist in the new pack. 6. Walk the new refs to answer the question "what shallow commits, both ours and theirs, are required in .git/shallow in order to add this ref?". Shallow commits not associated to any refs are removed from their respective list. 7. (*) Check reachability (from the current refs) of all remaining commits in "ours". Those reachable are removed. We do not want to cut any part of our (reachable) history. We only check up commits. True reachability test is done by check_everything_connected() at the end as usual. 8. Combine the final "ours" and "theirs" and add them all to .git/shallow. Install new refs. The case where some hook rejects some refs on a push is explained in more detail in the push patches. Of these steps, #6 and #7 are expensive. Both require walking through some commits, or in the worst case all commits. And we rather avoid them in at least common case, where the transferred pack does not contain any shallow commits that the sender advertises. Let's look at each scenario: 1) the sender has longer history than the receiver All shallow commits from the sender will be put into "theirs" list at step 1 because none of them exists in current repo. In the common case, "theirs" becomes empty at step 4 and exit early. 2) the sender has shorter history than the receiver All shallow commits from the sender are likely in "ours" list at step 1. In the common case, if the new pack is kept, we could empty "ours" and exit early at step 5. If the pack is not kept, we hit the expensive step 6 then exit after "ours" is emptied. There'll be only a handful of objects to walk in fast-forward case. If it's forced update, we may need to walk to the bottom. 3) the sender has same .git/shallow as the receiver This is similar to case 2 except that "ours" should be emptied at step 2 and exit early. A fetch after "clone --depth=X" is case 1. A fetch after "clone" (from a shallow repo) is case 3. Luckily they're cheap for the common case. A push from "clone --depth=X" falls into case 2, which is expensive. Some more work may be done at the sender/client side to avoid more work on the server side: if the transferred pack does not contain any shallow commits, send-pack should not send any shallow commits to the receive-pack, effectively turning it into a normal push and avoid all steps. This patch implements all steps except #3, already handled by fetch-pack and receive-pack, #6 and #7, which has their own patch due to their size. (*) in previous versions step 7 was put before step 3. I reorder it so that the common case that keeps the pack does not need to walk commits at all. In future if we implement faster commit reachability check (maybe with the help of pack bitmaps or commit cache), step 7 could become cheap and be moved up before 6 again. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-05 21:02:35 +08:00
int *ours, nr_ours;
int *theirs, nr_theirs;
struct oid_array *ref;
/* for receive-pack */
uint32_t **used_shallow;
int *need_reachability_test;
int *reachable;
int *shallow_ref;
struct commit **commits;
int nr_commits;
shallow.c: the 8 steps to select new commits for .git/shallow Suppose a fetch or push is requested between two shallow repositories (with no history deepening or shortening). A pack that contains necessary objects is transferred over together with .git/shallow of the sender. The receiver has to determine whether it needs to update .git/shallow if new refs needs new shallow comits. The rule here is avoid updating .git/shallow by default. But we don't want to waste the received pack. If the pack contains two refs, one needs new shallow commits installed in .git/shallow and one does not, we keep the latter and reject/warn about the former. Even if .git/shallow update is allowed, we only add shallow commits strictly necessary for the former ref (remember the sender can send more shallow commits than necessary) and pay attention not to accidentally cut the receiver history short (no history shortening is asked for) So the steps to figure out what ref need what new shallow commits are: 1. Split the sender shallow commit list into "ours" and "theirs" list by has_sha1_file. Those that exist in current repo in "ours", the remaining in "theirs". 2. Check the receiver .git/shallow, remove from "ours" the ones that also exist in .git/shallow. 3. Fetch the new pack. Either install or unpack it. 4. Do has_sha1_file on "theirs" list again. Drop the ones that fail has_sha1_file. Obviously the new pack does not need them. 5. If the pack is kept, remove from "ours" the ones that do not exist in the new pack. 6. Walk the new refs to answer the question "what shallow commits, both ours and theirs, are required in .git/shallow in order to add this ref?". Shallow commits not associated to any refs are removed from their respective list. 7. (*) Check reachability (from the current refs) of all remaining commits in "ours". Those reachable are removed. We do not want to cut any part of our (reachable) history. We only check up commits. True reachability test is done by check_everything_connected() at the end as usual. 8. Combine the final "ours" and "theirs" and add them all to .git/shallow. Install new refs. The case where some hook rejects some refs on a push is explained in more detail in the push patches. Of these steps, #6 and #7 are expensive. Both require walking through some commits, or in the worst case all commits. And we rather avoid them in at least common case, where the transferred pack does not contain any shallow commits that the sender advertises. Let's look at each scenario: 1) the sender has longer history than the receiver All shallow commits from the sender will be put into "theirs" list at step 1 because none of them exists in current repo. In the common case, "theirs" becomes empty at step 4 and exit early. 2) the sender has shorter history than the receiver All shallow commits from the sender are likely in "ours" list at step 1. In the common case, if the new pack is kept, we could empty "ours" and exit early at step 5. If the pack is not kept, we hit the expensive step 6 then exit after "ours" is emptied. There'll be only a handful of objects to walk in fast-forward case. If it's forced update, we may need to walk to the bottom. 3) the sender has same .git/shallow as the receiver This is similar to case 2 except that "ours" should be emptied at step 2 and exit early. A fetch after "clone --depth=X" is case 1. A fetch after "clone" (from a shallow repo) is case 3. Luckily they're cheap for the common case. A push from "clone --depth=X" falls into case 2, which is expensive. Some more work may be done at the sender/client side to avoid more work on the server side: if the transferred pack does not contain any shallow commits, send-pack should not send any shallow commits to the receive-pack, effectively turning it into a normal push and avoid all steps. This patch implements all steps except #3, already handled by fetch-pack and receive-pack, #6 and #7, which has their own patch due to their size. (*) in previous versions step 7 was put before step 3. I reorder it so that the common case that keeps the pack does not need to walk commits at all. In future if we implement faster commit reachability check (maybe with the help of pack bitmaps or commit cache), step 7 could become cheap and be moved up before 6 again. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-12-05 21:02:35 +08:00
};
void prepare_shallow_info(struct shallow_info *, struct oid_array *);
void clear_shallow_info(struct shallow_info *);
void remove_nonexistent_theirs_shallow(struct shallow_info *);
void assign_shallow_commits_to_refs(struct shallow_info *info,
uint32_t **used,
int *ref_status);
int delayed_reachability_test(struct shallow_info *si, int c);
#define PRUNE_SHOW_ONLY 1
#define PRUNE_QUICK 2
void prune_shallow(unsigned options);
extern struct trace_key trace_shallow;
int interactive_add(int argc, const char **argv, const char *prefix, int patch);
int run_add_interactive(const char *revision, const char *patch_mode,
const struct pathspec *pathspec);
struct commit_extra_header {
struct commit_extra_header *next;
char *key;
char *value;
size_t len;
};
void append_merge_tag_headers(struct commit_list *parents,
struct commit_extra_header ***tail);
int commit_tree(const char *msg, size_t msg_len,
const struct object_id *tree,
struct commit_list *parents, struct object_id *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 08:23:20 +08:00
const char *author, const char *sign_commit);
int commit_tree_extended(const char *msg, size_t msg_len,
const struct object_id *tree,
struct commit_list *parents,
struct object_id *ret, const char *author,
const char *sign_commit,
struct commit_extra_header *);
struct commit_extra_header *read_commit_extra_headers(struct commit *, const char **);
void free_commit_extra_headers(struct commit_extra_header *extra);
/*
* Search the commit object contents given by "msg" for the header "key".
* Returns a pointer to the start of the header contents, or NULL. The length
* of the header, up to the first newline, is returned via out_len.
*
* Note that some headers (like mergetag) may be multi-line. It is the caller's
* responsibility to parse further in this case!
*/
const char *find_commit_header(const char *msg, const char *key,
size_t *out_len);
/* Find the end of the log message, the right place for a new trailer. */
size_t ignore_non_trailer(const char *buf, size_t len);
typedef int (*each_mergetag_fn)(struct commit *commit, struct commit_extra_header *extra,
void *cb_data);
int for_each_mergetag(each_mergetag_fn fn, struct commit *commit, void *data);
struct merge_remote_desc {
struct object *obj; /* the named object, could be a tag */
char name[FLEX_ARRAY];
};
struct merge_remote_desc *merge_remote_util(struct commit *);
void set_merge_remote_desc(struct commit *commit,
const char *name, struct object *obj);
/*
* 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);
int parse_signed_commit(const struct commit *commit,
struct strbuf *message, struct strbuf *signature);
int remove_signature(struct strbuf *buf);
/*
* 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.
*/
int check_commit_signature(const struct commit *commit, struct signature_check *sigc);
/* record author-date for each commit object */
struct author_date_slab;
void record_author_date(struct author_date_slab *author_date,
struct commit *commit);
int compare_commits_by_author_date(const void *a_, const void *b_, void *unused);
/*
* Verify a single commit with check_commit_signature() and die() if it is not
* a good signature. This isn't really suitable for general use, but is a
* helper to implement consistent logic for pull/merge --verify-signatures.
*/
void verify_merge_signature(struct commit *commit, int verbose);
int compare_commits_by_commit_date(const void *a_, const void *b_, void *unused);
int compare_commits_by_gen_then_commit_date(const void *a_, const void *b_, void *unused);
LAST_ARG_MUST_BE_NULL
extern int run_commit_hook(int editor_is_used, const char *index_file, const char *name, ...);
#endif /* COMMIT_H */