git-commit-vandalism/dir.h

229 lines
6.9 KiB
C
Raw Normal View History

#ifndef DIR_H
#define DIR_H
/* See Documentation/technical/api-directory-listing.txt */
#include "strbuf.h"
struct dir_entry {
unsigned int len;
char name[FLEX_ARRAY]; /* more */
};
#define EXC_FLAG_NODIR 1
#define EXC_FLAG_ENDSWITH 4
#define EXC_FLAG_MUSTBEDIR 8
#define EXC_FLAG_NEGATIVE 16
struct exclude {
/*
* This allows callers of last_exclude_matching() etc.
* to determine the origin of the matching pattern.
*/
struct exclude_list *el;
const char *pattern;
int patternlen;
int nowildcardlen;
const char *base;
int baselen;
int flags;
/*
* Counting starts from 1 for line numbers in ignore files,
* and from -1 decrementing for patterns from CLI args.
*/
int srcpos;
};
/*
* Each excludes file will be parsed into a fresh exclude_list which
* is appended to the relevant exclude_list_group (either EXC_DIRS or
* EXC_FILE). An exclude_list within the EXC_CMDL exclude_list_group
* can also be used to represent the list of --exclude values passed
* via CLI args.
*/
struct exclude_list {
int nr;
int alloc;
/* remember pointer to exclude file contents so we can free() */
char *filebuf;
/* origin of list, e.g. path to filename, or descriptive string */
const char *src;
struct exclude **excludes;
};
/*
* The contents of the per-directory exclude files are lazily read on
* demand and then cached in memory, one per exclude_stack struct, in
* order to avoid opening and parsing each one every time that
* directory is traversed.
*/
struct exclude_stack {
struct exclude_stack *prev; /* the struct exclude_stack for the parent directory */
int baselen;
int exclude_ix; /* index of exclude_list within EXC_DIRS exclude_list_group */
};
struct exclude_list_group {
int nr, alloc;
struct exclude_list *el;
};
struct dir_struct {
int nr, alloc;
int ignored_nr, ignored_alloc;
enum {
DIR_SHOW_IGNORED = 1<<0,
DIR_SHOW_OTHER_DIRECTORIES = 1<<1,
DIR_HIDE_EMPTY_DIRECTORIES = 1<<2,
DIR_NO_GITLINKS = 1<<3,
dir.c: git-status --ignored: don't scan the work tree twice 'git-status --ignored' still scans the work tree twice to collect untracked and ignored files, respectively. fill_directory / read_directory already supports collecting untracked and ignored files in a single directory scan. However, the DIR_COLLECT_IGNORED flag to enable this has some git-add specific side-effects (e.g. it doesn't recurse into ignored directories, so listing ignored files with --untracked=all doesn't work). The DIR_SHOW_IGNORED flag doesn't list untracked files and returns ignored files in dir_struct.entries[] (instead of dir_struct.ignored[] as DIR_COLLECT_IGNORED). DIR_SHOW_IGNORED is used all throughout git. We don't want to break the existing API, so lets introduce a new flag DIR_SHOW_IGNORED_TOO that lists untracked as well as ignored files similar to DIR_COLLECT_FILES, but will recurse into sub-directories based on the other flags as DIR_SHOW_IGNORED does. In dir.c::read_directory_recursive, add ignored files to either dir_struct.entries[] or dir_struct.ignored[] based on the flags. Also move the DIR_COLLECT_IGNORED case here so that filling result lists is in a common place. In wt-status.c::wt_status_collect_untracked, use the new flag and read results from dir_struct.ignored[]. Remove the extra fill_directory call. builtin/check-ignore.c doesn't call fill_directory, setting the git-add specific DIR_COLLECT_IGNORED flag has no effect here. Remove for clarity. Update API documentation to reflect the changes. Performance: with this patch, 'git-status --ignored' is typically as fast as 'git-status'. Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:15:03 +02:00
DIR_COLLECT_IGNORED = 1<<4,
ls-files -k: a directory only can be killed if the index has a non-directory "ls-files -o" and "ls-files -k" both traverse the working tree down to find either all untracked paths or those that will be "killed" (removed from the working tree to make room) when the paths recorded in the index are checked out. It is necessary to traverse the working tree fully when enumerating all the "other" paths, but when we are only interested in "killed" paths, we can take advantage of the fact that paths that do not overlap with entries in the index can never be killed. The treat_one_path() helper function, which is called during the recursive traversal, is the ideal place to implement an optimization. When we are looking at a directory P in the working tree, there are three cases: (1) P exists in the index. Everything inside the directory P in the working tree needs to go when P is checked out from the index. (2) P does not exist in the index, but there is P/Q in the index. We know P will stay a directory when we check out the contents of the index, but we do not know yet if there is a directory P/Q in the working tree to be killed, so we need to recurse. (3) P does not exist in the index, and there is no P/Q in the index to require P to be a directory, either. Only in this case, we know that everything inside P will not be killed without recursing. Note that this helper is called by treat_leading_path() that decides if we need to traverse only subdirectories of a single common leading directory, which is essential for this optimization to be correct. This caller checks each level of the leading path component from shallower directory to deeper ones, and that is what allows us to only check if the path appears in the index. If the call to treat_one_path() weren't there, given a path P/Q/R, the real traversal may start from directory P/Q/R, even when the index records P as a regular file, and we would end up having to check if any leading subpath in P/Q/R, e.g. P, appears in the index. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-08-15 21:13:46 +02:00
DIR_SHOW_IGNORED_TOO = 1<<5,
DIR_COLLECT_KILLED_ONLY = 1<<6
} flags;
struct dir_entry **entries;
struct dir_entry **ignored;
/* Exclude info */
const char *exclude_per_dir;
/*
* We maintain three groups of exclude pattern lists:
*
* EXC_CMDL lists patterns explicitly given on the command line.
* EXC_DIRS lists patterns obtained from per-directory ignore files.
* EXC_FILE lists patterns from fallback ignore files, e.g.
* - .git/info/exclude
* - core.excludesfile
*
* Each group contains multiple exclude lists, a single list
* per source.
*/
#define EXC_CMDL 0
#define EXC_DIRS 1
#define EXC_FILE 2
struct exclude_list_group exclude_list_group[3];
/*
* Temporary variables which are used during loading of the
* per-directory exclude lists.
*
* exclude_stack points to the top of the exclude_stack, and
* basebuf contains the full path to the current
dir.c: unify is_excluded and is_path_excluded APIs The is_excluded and is_path_excluded APIs are very similar, except for a few noteworthy differences: is_excluded doesn't handle ignored directories, results for paths within ignored directories are incorrect. This is probably based on the premise that recursive directory scans should stop at ignored directories, which is no longer true (in certain cases, read_directory_recursive currently calls is_excluded *and* is_path_excluded to get correct ignored state). is_excluded caches parsed .gitignore files of the last directory in struct dir_struct. If the directory changes, it finds a common parent directory and is very careful to drop only as much state as necessary. On the other hand, is_excluded will also read and parse .gitignore files in already ignored directories, which are completely irrelevant. is_path_excluded correctly handles ignored directories by checking if any component in the path is excluded. As it uses is_excluded internally, this unfortunately forces is_excluded to drop and re-read all .gitignore files, as there is no common parent directory for the root dir. is_path_excluded tracks state in a separate struct path_exclude_check, which is essentially a wrapper of dir_struct with two more fields. However, as is_path_excluded also modifies dir_struct, it is not possible to e.g. use multiple path_exclude_check structures with the same dir_struct in parallel. The additional structure just unnecessarily complicates the API. Teach is_excluded / prep_exclude about ignored directories: whenever entering a new directory, first check if the entire directory is excluded. Remember the excluded state in dir_struct. Don't traverse into already ignored directories (i.e. don't read irrelevant .gitignore files). Directories could also be excluded by exclude patterns specified on the command line or .git/info/exclude, so we cannot simply skip prep_exclude entirely if there's no .gitignore file name (dir_struct.exclude_per_dir). Move this check to just before actually reading the file. is_path_excluded is now equivalent to is_excluded, so we can simply redirect to it (the public API is cleaned up in the next patch). The performance impact of the additional ignored check per directory is hardly noticeable when reading directories recursively (e.g. 'git status'). However, performance of git commands using the is_path_excluded API (e.g. 'git ls-files --cached --ignored --exclude-standard') is greatly improved as this no longer re-reads .gitignore files on each call. Here's some performance data from the linux and WebKit repos (best of 10 runs on a Debian Linux on SSD, core.preloadIndex=true): | ls-files -ci | status | status --ignored | linux | WebKit | linux | WebKit | linux | WebKit -------+-------+--------+-------+--------+-------+--------- before | 0.506 | 6.539 | 0.212 | 1.555 | 0.323 | 2.541 after | 0.080 | 1.191 | 0.218 | 1.583 | 0.321 | 2.579 gain | 6.325 | 5.490 | 0.972 | 0.982 | 1.006 | 0.985 Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:12:14 +02:00
* (sub)directory in the traversal. Exclude points to the
* matching exclude struct if the directory is excluded.
*/
struct exclude_stack *exclude_stack;
dir.c: unify is_excluded and is_path_excluded APIs The is_excluded and is_path_excluded APIs are very similar, except for a few noteworthy differences: is_excluded doesn't handle ignored directories, results for paths within ignored directories are incorrect. This is probably based on the premise that recursive directory scans should stop at ignored directories, which is no longer true (in certain cases, read_directory_recursive currently calls is_excluded *and* is_path_excluded to get correct ignored state). is_excluded caches parsed .gitignore files of the last directory in struct dir_struct. If the directory changes, it finds a common parent directory and is very careful to drop only as much state as necessary. On the other hand, is_excluded will also read and parse .gitignore files in already ignored directories, which are completely irrelevant. is_path_excluded correctly handles ignored directories by checking if any component in the path is excluded. As it uses is_excluded internally, this unfortunately forces is_excluded to drop and re-read all .gitignore files, as there is no common parent directory for the root dir. is_path_excluded tracks state in a separate struct path_exclude_check, which is essentially a wrapper of dir_struct with two more fields. However, as is_path_excluded also modifies dir_struct, it is not possible to e.g. use multiple path_exclude_check structures with the same dir_struct in parallel. The additional structure just unnecessarily complicates the API. Teach is_excluded / prep_exclude about ignored directories: whenever entering a new directory, first check if the entire directory is excluded. Remember the excluded state in dir_struct. Don't traverse into already ignored directories (i.e. don't read irrelevant .gitignore files). Directories could also be excluded by exclude patterns specified on the command line or .git/info/exclude, so we cannot simply skip prep_exclude entirely if there's no .gitignore file name (dir_struct.exclude_per_dir). Move this check to just before actually reading the file. is_path_excluded is now equivalent to is_excluded, so we can simply redirect to it (the public API is cleaned up in the next patch). The performance impact of the additional ignored check per directory is hardly noticeable when reading directories recursively (e.g. 'git status'). However, performance of git commands using the is_path_excluded API (e.g. 'git ls-files --cached --ignored --exclude-standard') is greatly improved as this no longer re-reads .gitignore files on each call. Here's some performance data from the linux and WebKit repos (best of 10 runs on a Debian Linux on SSD, core.preloadIndex=true): | ls-files -ci | status | status --ignored | linux | WebKit | linux | WebKit | linux | WebKit -------+-------+--------+-------+--------+-------+--------- before | 0.506 | 6.539 | 0.212 | 1.555 | 0.323 | 2.541 after | 0.080 | 1.191 | 0.218 | 1.583 | 0.321 | 2.579 gain | 6.325 | 5.490 | 0.972 | 0.982 | 1.006 | 0.985 Signed-off-by: Karsten Blees <blees@dcon.de> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-04-15 21:12:14 +02:00
struct exclude *exclude;
struct strbuf basebuf;
};
/*
* The ordering of these constants is significant, with
* higher-numbered match types signifying "closer" (i.e. more
* specific) matches which will override lower-numbered match types
* when populating the seen[] array.
*/
#define MATCHED_RECURSIVELY 1
#define MATCHED_FNMATCH 2
#define MATCHED_EXACTLY 3
extern int simple_length(const char *match);
extern int no_wildcard(const char *string);
extern char *common_prefix(const struct pathspec *pathspec);
extern int match_pathspec(const struct pathspec *pathspec,
const char *name, int namelen,
int prefix, char *seen, int is_dir);
extern int within_depth(const char *name, int namelen, int depth, int max_depth);
extern int fill_directory(struct dir_struct *dir, const struct pathspec *pathspec);
extern int read_directory(struct dir_struct *, const char *path, int len, const struct pathspec *pathspec);
extern int is_excluded_from_list(const char *pathname, int pathlen, const char *basename,
int *dtype, struct exclude_list *el);
struct dir_entry *dir_add_ignored(struct dir_struct *dir, const char *pathname, int len);
/*
* these implement the matching logic for dir.c:excluded_from_list and
* attr.c:path_matches()
*/
extern int match_basename(const char *, int,
const char *, int, int, int);
extern int match_pathname(const char *, int,
const char *, int,
const char *, int, int, int);
extern struct exclude *last_exclude_matching(struct dir_struct *dir,
const char *name, int *dtype);
extern int is_excluded(struct dir_struct *dir, const char *name, int *dtype);
extern struct exclude_list *add_exclude_list(struct dir_struct *dir,
int group_type, const char *src);
extern int add_excludes_from_file_to_list(const char *fname, const char *base, int baselen,
struct exclude_list *el, int check_index);
extern void add_excludes_from_file(struct dir_struct *, const char *fname);
extern void parse_exclude_pattern(const char **string, int *patternlen, int *flags, int *nowildcardlen);
extern void add_exclude(const char *string, const char *base,
int baselen, struct exclude_list *el, int srcpos);
extern void clear_exclude_list(struct exclude_list *el);
extern void clear_directory(struct dir_struct *dir);
extern int file_exists(const char *);
extern int is_inside_dir(const char *dir);
extern int dir_inside_of(const char *subdir, const char *dir);
static inline int is_dot_or_dotdot(const char *name)
{
return (name[0] == '.' &&
(name[1] == '\0' ||
(name[1] == '.' && name[2] == '\0')));
}
extern int is_empty_dir(const char *dir);
core.excludesfile clean-up There are inconsistencies in the way commands currently handle the core.excludesfile configuration variable. The problem is the variable is too new to be noticed by anything other than git-add and git-status. * git-ls-files does not notice any of the "ignore" files by default, as it predates the standardized set of ignore files. The calling scripts established the convention to use .git/info/exclude, .gitignore, and later core.excludesfile. * git-add and git-status know about it because they call add_excludes_from_file() directly with their own notion of which standard set of ignore files to use. This is just a stupid duplication of code that need to be updated every time the definition of the standard set of ignore files is changed. * git-read-tree takes --exclude-per-directory=<gitignore>, not because the flexibility was needed. Again, this was because the option predates the standardization of the ignore files. * git-merge-recursive uses hardcoded per-directory .gitignore and nothing else. git-clean (scripted version) does not honor core.* because its call to underlying ls-files does not know about it. git-clean in C (parked in 'pu') doesn't either. We probably could change git-ls-files to use the standard set when no excludes are specified on the command line and ignore processing was asked, or something like that, but that will be a change in semantics and might break people's scripts in a subtle way. I am somewhat reluctant to make such a change. On the other hand, I think it makes perfect sense to fix git-read-tree, git-merge-recursive and git-clean to follow the same rule as other commands. I do not think of a valid use case to give an exclude-per-directory that is nonstandard to read-tree command, outside a "negative" test in the t1004 test script. This patch is the first step to untangle this mess. The next step would be to teach read-tree, merge-recursive and clean (in C) to use setup_standard_excludes(). Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-14 09:05:00 +01:00
extern void setup_standard_excludes(struct dir_struct *dir);
#define REMOVE_DIR_EMPTY_ONLY 01
#define REMOVE_DIR_KEEP_NESTED_GIT 02
#define REMOVE_DIR_KEEP_TOPLEVEL 04
extern int remove_dir_recursively(struct strbuf *path, int flag);
/* tries to remove the path with empty directories along it, ignores ENOENT */
extern int remove_path(const char *path);
extern int strcmp_icase(const char *a, const char *b);
extern int strncmp_icase(const char *a, const char *b, size_t count);
extern int fnmatch_icase(const char *pattern, const char *string, int flags);
/*
* The prefix part of pattern must not contains wildcards.
*/
struct pathspec_item;
extern int git_fnmatch(const struct pathspec_item *item,
const char *pattern, const char *string,
int prefix);
static inline int ce_path_match(const struct cache_entry *ce,
const struct pathspec *pathspec,
char *seen)
{
return match_pathspec(pathspec, ce->name, ce_namelen(ce), 0, seen,
S_ISDIR(ce->ce_mode) || S_ISGITLINK(ce->ce_mode));
}
static inline int dir_path_match(const struct dir_entry *ent,
const struct pathspec *pathspec,
int prefix, char *seen)
{
int has_trailing_dir = ent->len && ent->name[ent->len - 1] == '/';
int len = has_trailing_dir ? ent->len - 1 : ent->len;
return match_pathspec(pathspec, ent->name, len, prefix, seen,
has_trailing_dir);
}
#endif