Add virtual file system settings and hook proc

On index load, clear/set the skip worktree bits based on the virtual
file system data. Use virtual file system data to update skip-worktree
bit in unpack-trees. Use virtual file system data to exclude files and
folders not explicitly requested.

Signed-off-by: Ben Peart <[email protected]>

Author: benpeart

Documentation/config/core.txt

@@ -68,6 +68,14 @@ core.fsmonitor::
 	avoiding unnecessary processing of files that have not changed.
 	See the "fsmonitor-watchman" section of linkgit:githooks[5].
 
+core.virtualFilesystem::
+	If set, the value of this variable is used as a command which
+	will identify all files and directories that are present in
+	the working directory.  Git will only track and update files
+	listed in the virtual file system.  Using the virtual file system
+	will supersede the sparse-checkout settings which will be ignored.
+	See the "virtual file system" section of linkgit:githooks[6].
+
 core.trustctime::
 	If false, the ctime differences between the index and the
 	working tree are ignored; useful when the inode change time

Documentation/githooks.txt

@@ -492,6 +492,26 @@ This hook is invoked by `git-p4 submit`. It takes no parameters and nothing
 from standard input. Exiting with non-zero status from this script prevent
 `git-p4 submit` from launching. Run `git-p4 submit --help` for details.
 
+virtualFilesystem
+~~~~~~~~~~~~~~~~~~
+
+"Virtual File System" allows populating the working directory sparsely.
+The projection data is typically automatically generated by an external
+process.  Git will limit what files it checks for changes as well as which
+directories are checked for untracked files based on the path names given.
+Git will also only update those files listed in the projection.
+
+The hook is invoked when the configuration option core.virtualFilesystem
+is set.  It takes one argument, a version (currently 1).
+
+The hook should output to stdout the list of all files in the working
+directory that git should track.  The paths are relative to the root
+of the working directory and are separated by a single NUL.  Full paths
+('dir1/a.txt') as well as directories are supported (ie 'dir1/').
+
+The exit status determines whether git will use the data from the
+hook.  On error, git will abort the command with an error message.
+
 GIT
 ---
 Part of the linkgit:git[1] suite

Makefile

@@ -1016,6 +1016,7 @@ LIB_OBJS += utf8.o
 LIB_OBJS += varint.o
 LIB_OBJS += version.o
 LIB_OBJS += versioncmp.o
+LIB_OBJS += virtualfilesystem.o
 LIB_OBJS += walker.o
 LIB_OBJS += wildmatch.o
 LIB_OBJS += worktree.o

cache.h

@@ -886,6 +886,7 @@ extern char *git_replace_ref_base;
 extern int fsync_object_files;
 extern int core_preload_index;
 extern int core_apply_sparse_checkout;
+extern const char *core_virtualfilesystem;
 extern int core_gvfs;
 extern int precomposed_unicode;
 extern int protect_hfs;

config.c

@@ -1331,7 +1331,11 @@ static int git_default_core_config(const char *var, const char *value, void *cb)
 	}
 
 	if (!strcmp(var, "core.sparsecheckout")) {
-		core_apply_sparse_checkout = git_config_bool(var, value);
+		/* virtual file system relies on the sparse checkout logic so force it on */
+		if (core_virtualfilesystem)
+			core_apply_sparse_checkout = 1;
+		else
+			core_apply_sparse_checkout = git_config_bool(var, value);
 		return 0;
 	}
 
@@ -2312,6 +2316,23 @@ int git_config_get_fsmonitor(void)
 	return 0;
 }
 
+int git_config_get_virtualfilesystem(void)
+{
+	if (git_config_get_pathname("core.virtualfilesystem", &core_virtualfilesystem))
+		core_virtualfilesystem = getenv("GIT_VIRTUALFILESYSTEM_TEST");
+
+	if (core_virtualfilesystem && !*core_virtualfilesystem)
+		core_virtualfilesystem = NULL;
+
+	/* virtual file system relies on the sparse checkout logic so force it on */
+	if (core_virtualfilesystem) {
+		core_apply_sparse_checkout = 1;
+		return 1;
+	}
+
+	return 0;
+}
+
 int git_config_get_index_threads(int *dest)
 {
 	int is_bool, val;

config.h

@@ -251,6 +251,7 @@ extern int git_config_get_untracked_cache(void);
 extern int git_config_get_split_index(void);
 extern int git_config_get_max_percent_split_change(void);
 extern int git_config_get_fsmonitor(void);
+extern int git_config_get_virtualfilesystem(void);
 
 /* This dies if the configured or default date is in the future */
 extern int git_config_get_expiry(const char *key, const char **output);

dir.c

@@ -21,6 +21,7 @@
 #include "ewah/ewok.h"
 #include "fsmonitor.h"
 #include "submodule-config.h"
+#include "virtualfilesystem.h"
 
 /*
  * Tells read_directory_recursive how a file or directory should be treated.
@@ -1159,6 +1160,18 @@ int is_excluded_from_list(const char *pathname,
 			  struct exclude_list *el, struct index_state *istate)
 {
 	struct exclude *exclude;
+
+	/*
+	 * The virtual file system data is used to prevent git from traversing
+	 * any part of the tree that is not in the virtual file system.  Return
+	 * 1 to exclude the entry if it is not found in the virtual file system,
+	 * else fall through to the regular excludes logic as it may further exclude.
+	 */
+	if (*dtype == DT_UNKNOWN)
+		*dtype = get_dtype(NULL, istate, pathname, pathlen);
+	if (is_excluded_from_virtualfilesystem(pathname, pathlen, *dtype) > 0)
+		return 1;
+
 	exclude = last_exclude_matching_from_list(pathname, pathlen, basename,
 						  dtype, el, istate);
 	if (exclude)
@@ -1374,8 +1387,20 @@ struct exclude *last_exclude_matching(struct dir_struct *dir,
 int is_excluded(struct dir_struct *dir, struct index_state *istate,
 		const char *pathname, int *dtype_p)
 {
-	struct exclude *exclude =
-		last_exclude_matching(dir, istate, pathname, dtype_p);
+	struct exclude *exclude;
+
+	/*
+	 * The virtual file system data is used to prevent git from traversing
+	 * any part of the tree that is not in the virtual file system.  Return
+	 * 1 to exclude the entry if it is not found in the virtual file system,
+	 * else fall through to the regular excludes logic as it may further exclude.
+	 */
+	if (*dtype_p == DT_UNKNOWN)
+		*dtype_p = get_dtype(NULL, istate, pathname, strlen(pathname));
+	if (is_excluded_from_virtualfilesystem(pathname, strlen(pathname), *dtype_p) > 0)
+		return 1;
+
+	exclude = last_exclude_matching(dir, istate, pathname, dtype_p);
 	if (exclude)
 		return exclude->flags & EXC_FLAG_NEGATIVE ? 0 : 1;
 	return 0;
@@ -1728,6 +1753,9 @@ static enum path_treatment treat_one_path(struct dir_struct *dir,
 	if (dtype != DT_DIR && has_path_in_index)
 		return path_none;
 
+	if (is_excluded_from_virtualfilesystem(path->buf, path->len, dtype) > 0)
+		return path_excluded;
+
 	/*
 	 * When we are looking at a directory P in the working tree,
 	 * there are three cases:
@@ -2068,6 +2096,8 @@ static enum path_treatment read_directory_recursive(struct dir_struct *dir,
 		/* add the path to the appropriate result list */
 		switch (state) {
 		case path_excluded:
+			if (is_excluded_from_virtualfilesystem(path.buf, path.len, DT_DIR) > 0)
+				break;
 			if (dir->flags & DIR_SHOW_IGNORED)
 				dir_add_name(dir, istate, path.buf, path.len);
 			else if ((dir->flags & DIR_SHOW_IGNORED_TOO) ||

environment.c

@@ -70,6 +70,7 @@ char *notes_ref_name;
 int grafts_replace_parents = 1;
 int core_apply_sparse_checkout;
 int core_gvfs;
+const char *core_virtualfilesystem;
 int merge_log_config = -1;
 int precomposed_unicode = -1; /* see probe_utf8_pathname_composition() */
 unsigned long pack_size_limit_cfg;

read-cache.c

@@ -25,6 +25,7 @@
 #include "fsmonitor.h"
 #include "thread-utils.h"
 #include "progress.h"
+#include "virtualfilesystem.h"
 #include "gvfs.h"
 
 /* Mask for the name length in ce_flags in the on-disk index */
@@ -1897,6 +1898,7 @@ static void post_read_index_from(struct index_state *istate)
 	tweak_untracked_cache(istate);
 	tweak_split_index(istate);
 	tweak_fsmonitor(istate);
+	apply_virtualfilesystem(istate);
 }
 
 static size_t estimate_cache_size_from_compressed(unsigned int entries)