Merge branch 'mt/parallel-checkout-part-1'

Preparatory API changes for parallel checkout.

* mt/parallel-checkout-part-1:
  entry: add checkout_entry_ca() taking preloaded conv_attrs
  entry: move conv_attrs lookup up to checkout_entry()
  entry: extract update_ce_after_write() from write_entry()
  entry: make fstat_output() and read_blob_entry() public
  entry: extract a header file for entry.c functions
  convert: add classification for conv_attrs struct
  convert: add get_stream_filter_ca() variant
  convert: add [async_]convert_to_working_tree_ca() variants
  convert: make convert_attrs() and convert structs public

apply.c

@@ -21,6 +21,7 @@
 #include "quote.h"
 #include "rerere.h"
 #include "apply.h"
+#include "entry.h"
 
 struct gitdiff_data {
 	struct strbuf *root;

builtin/checkout-index.c

@@ -11,6 +11,7 @@
 #include "quote.h"
 #include "cache-tree.h"
 #include "parse-options.h"
+#include "entry.h"
 
 #define CHECKOUT_ALL 4
 static int nul_term_line;

builtin/checkout.c

@@ -26,6 +26,7 @@
 #include "unpack-trees.h"
 #include "wt-status.h"
 #include "xdiff-interface.h"
+#include "entry.h"
 
 static const char * const checkout_usage[] = {
 	N_("git checkout [<options>] <branch>"),

builtin/difftool.c

@@ -23,6 +23,7 @@
 #include "lockfile.h"
 #include "object-store.h"
 #include "dir.h"
+#include "entry.h"
 
 static int trust_exit_code;
 

builtin/stash.c

@@ -10,11 +10,13 @@
 #include "strvec.h"
 #include "run-command.h"
 #include "dir.h"
+#include "entry.h"
 #include "rerere.h"
 #include "revision.h"
 #include "log-tree.h"
 #include "diffcore.h"
 #include "exec-cmd.h"
+#include "entry.h"
 
 #define INCLUDE_ALL_FILES 2
 

cache.h

@@ -1621,30 +1621,6 @@ const char *show_ident_date(const struct ident_split *id,
  */
 int ident_cmp(const struct ident_split *, const struct ident_split *);
 
-struct checkout {
-	struct index_state *istate;
-	const char *base_dir;
-	int base_dir_len;
-	struct delayed_checkout *delayed_checkout;
-	struct checkout_metadata meta;
-	unsigned force:1,
-		 quiet:1,
-		 not_new:1,
-		 clone:1,
-		 refresh_cache:1;
-};
-#define CHECKOUT_INIT { NULL, "" }
-
-#define TEMPORARY_FILENAME_LENGTH 25
-int checkout_entry(struct cache_entry *ce, const struct checkout *state, char *topath, int *nr_checkouts);
-void enable_delayed_checkout(struct checkout *state);
-int finish_delayed_checkout(struct checkout *state, int *nr_checkouts);
-/*
- * Unlink the last component and schedule the leading directories for
- * removal, such that empty directories get removed.
- */
-void unlink_entry(const struct cache_entry *ce);
-
 struct cache_def {
 	struct strbuf path;
 	int flags;

convert.c

@@ -24,17 +24,6 @@
 #define CONVERT_STAT_BITS_TXT_CRLF  0x2
 #define CONVERT_STAT_BITS_BIN       0x4
 
-enum crlf_action {
-	CRLF_UNDEFINED,
-	CRLF_BINARY,
-	CRLF_TEXT,
-	CRLF_TEXT_INPUT,
-	CRLF_TEXT_CRLF,
-	CRLF_AUTO,
-	CRLF_AUTO_INPUT,
-	CRLF_AUTO_CRLF
-};
-
 struct text_stat {
 	/* NUL, CR, LF and CRLF counts */
 	unsigned nul, lonecr, lonelf, crlf;
@@ -172,7 +161,7 @@ static int text_eol_is_crlf(void)
 	return 0;
 }
 
-static enum eol output_eol(enum crlf_action crlf_action)
+static enum eol output_eol(enum convert_crlf_action crlf_action)
 {
 	switch (crlf_action) {
 	case CRLF_BINARY:
@@ -246,7 +235,7 @@ static int has_crlf_in_index(const struct index_state *istate, const char *path)
 }
 
 static int will_convert_lf_to_crlf(struct text_stat *stats,
-				   enum crlf_action crlf_action)
+				   enum convert_crlf_action crlf_action)
 {
 	if (output_eol(crlf_action) != EOL_CRLF)
 		return 0;
@@ -499,7 +488,7 @@ static int encode_to_worktree(const char *path, const char *src, size_t src_len,
 static int crlf_to_git(const struct index_state *istate,
 		       const char *path, const char *src, size_t len,
 		       struct strbuf *buf,
-		       enum crlf_action crlf_action, int conv_flags)
+		       enum convert_crlf_action crlf_action, int conv_flags)
 {
 	struct text_stat stats;
 	char *dst;
@@ -585,8 +574,8 @@ static int crlf_to_git(const struct index_state *istate,
 	return 1;
 }
 
-static int crlf_to_worktree(const char *src, size_t len,
-			    struct strbuf *buf, enum crlf_action crlf_action)
+static int crlf_to_worktree(const char *src, size_t len, struct strbuf *buf,
+			    enum convert_crlf_action crlf_action)
 {
 	char *to_free = NULL;
 	struct text_stat stats;
@@ -1247,7 +1236,7 @@ static const char *git_path_check_encoding(struct attr_check_item *check)
 	return value;
 }
 
-static enum crlf_action git_path_check_crlf(struct attr_check_item *check)
+static enum convert_crlf_action git_path_check_crlf(struct attr_check_item *check)
 {
 	const char *value = check->value;
 
@@ -1297,18 +1286,10 @@ static int git_path_check_ident(struct attr_check_item *check)
 	return !!ATTR_TRUE(value);
 }
 
-struct conv_attrs {
-	struct convert_driver *drv;
-	enum crlf_action attr_action; /* What attr says */
-	enum crlf_action crlf_action; /* When no attr is set, use core.autocrlf */
-	int ident;
-	const char *working_tree_encoding; /* Supported encoding or default encoding if NULL */
-};
-
 static struct attr_check *check;
 
-static void convert_attrs(const struct index_state *istate,
-			  struct conv_attrs *ca, const char *path)
+void convert_attrs(const struct index_state *istate,
+		   struct conv_attrs *ca, const char *path)
 {
 	struct attr_check_item *ccheck = NULL;
 
@@ -1465,19 +1446,16 @@ void convert_to_git_filter_fd(const struct index_state *istate,
 	ident_to_git(dst->buf, dst->len, dst, ca.ident);
 }
 
-static int convert_to_working_tree_internal(const struct index_state *istate,
-					    const char *path, const char *src,
-					    size_t len, struct strbuf *dst,
-					    int normalizing,
-					    const struct checkout_metadata *meta,
-					    struct delayed_checkout *dco)
+static int convert_to_working_tree_ca_internal(const struct conv_attrs *ca,
+					       const char *path, const char *src,
+					       size_t len, struct strbuf *dst,
+					       int normalizing,
+					       const struct checkout_metadata *meta,
+					       struct delayed_checkout *dco)
 {
 	int ret = 0, ret_filter = 0;
-	struct conv_attrs ca;
-
-	convert_attrs(istate, &ca, path);
 
-	ret |= ident_to_worktree(src, len, dst, ca.ident);
+	ret |= ident_to_worktree(src, len, dst, ca->ident);
 	if (ret) {
 		src = dst->buf;
 		len = dst->len;
@@ -1487,49 +1465,56 @@ static int convert_to_working_tree_internal(const struct index_state *istate,
 	 * is a smudge or process filter (even if the process filter doesn't
 	 * support smudge).  The filters might expect CRLFs.
 	 */
-	if ((ca.drv && (ca.drv->smudge || ca.drv->process)) || !normalizing) {
-		ret |= crlf_to_worktree(src, len, dst, ca.crlf_action);
+	if ((ca->drv && (ca->drv->smudge || ca->drv->process)) || !normalizing) {
+		ret |= crlf_to_worktree(src, len, dst, ca->crlf_action);
 		if (ret) {
 			src = dst->buf;
 			len = dst->len;
 		}
 	}
 
-	ret |= encode_to_worktree(path, src, len, dst, ca.working_tree_encoding);
+	ret |= encode_to_worktree(path, src, len, dst, ca->working_tree_encoding);
 	if (ret) {
 		src = dst->buf;
 		len = dst->len;
 	}
 
 	ret_filter = apply_filter(
-		path, src, len, -1, dst, ca.drv, CAP_SMUDGE, meta, dco);
-	if (!ret_filter && ca.drv && ca.drv->required)
-		die(_("%s: smudge filter %s failed"), path, ca.drv->name);
+		path, src, len, -1, dst, ca->drv, CAP_SMUDGE, meta, dco);
+	if (!ret_filter && ca->drv && ca->drv->required)
+		die(_("%s: smudge filter %s failed"), path, ca->drv->name);
 
 	return ret | ret_filter;
 }
 
-int async_convert_to_working_tree(const struct index_state *istate,
-				  const char *path, const char *src,
-				  size_t len, struct strbuf *dst,
-				  const struct checkout_metadata *meta,
-				  void *dco)
+int async_convert_to_working_tree_ca(const struct conv_attrs *ca,
+				     const char *path, const char *src,
+				     size_t len, struct strbuf *dst,
+				     const struct checkout_metadata *meta,
+				     void *dco)
 {
-	return convert_to_working_tree_internal(istate, path, src, len, dst, 0, meta, dco);
+	return convert_to_working_tree_ca_internal(ca, path, src, len, dst, 0,
+						   meta, dco);
 }
 
-int convert_to_working_tree(const struct index_state *istate,
-			    const char *path, const char *src,
-			    size_t len, struct strbuf *dst,
-			    const struct checkout_metadata *meta)
+int convert_to_working_tree_ca(const struct conv_attrs *ca,
+			       const char *path, const char *src,
+			       size_t len, struct strbuf *dst,
+			       const struct checkout_metadata *meta)
 {
-	return convert_to_working_tree_internal(istate, path, src, len, dst, 0, meta, NULL);
+	return convert_to_working_tree_ca_internal(ca, path, src, len, dst, 0,
+						   meta, NULL);
 }
 
 int renormalize_buffer(const struct index_state *istate, const char *path,
 		       const char *src, size_t len, struct strbuf *dst)
 {
-	int ret = convert_to_working_tree_internal(istate, path, src, len, dst, 1, NULL, NULL);
+	struct conv_attrs ca;
+	int ret;
+
+	convert_attrs(istate, &ca, path);
+	ret = convert_to_working_tree_ca_internal(&ca, path, src, len, dst, 1,
+						  NULL, NULL);
 	if (ret) {
 		src = dst->buf;
 		len = dst->len;
@@ -1956,41 +1941,41 @@ static struct stream_filter *ident_filter(const struct object_id *oid)
 }
 
 /*
- * Return an appropriately constructed filter for the path, or NULL if
+ * Return an appropriately constructed filter for the given ca, or NULL if
  * the contents cannot be filtered without reading the whole thing
  * in-core.
  *
  * Note that you would be crazy to set CRLF, smudge/clean or ident to a
  * large binary blob you would want us not to slurp into the memory!
  */
-struct stream_filter *get_stream_filter(const struct index_state *istate,
-					const char *path,
-					const struct object_id *oid)
+struct stream_filter *get_stream_filter_ca(const struct conv_attrs *ca,
+					   const struct object_id *oid)
 {
-	struct conv_attrs ca;
 	struct stream_filter *filter = NULL;
 
-	convert_attrs(istate, &ca, path);
-	if (ca.drv && (ca.drv->process || ca.drv->smudge || ca.drv->clean))
-		return NULL;
-
-	if (ca.working_tree_encoding)
+	if (classify_conv_attrs(ca) != CA_CLASS_STREAMABLE)
 		return NULL;
 
-	if (ca.crlf_action == CRLF_AUTO || ca.crlf_action == CRLF_AUTO_CRLF)
-		return NULL;
-
-	if (ca.ident)
+	if (ca->ident)
 		filter = ident_filter(oid);
 
-	if (output_eol(ca.crlf_action) == EOL_CRLF)
+	if (output_eol(ca->crlf_action) == EOL_CRLF)
 		filter = cascade_filter(filter, lf_to_crlf_filter());
 	else
 		filter = cascade_filter(filter, &null_filter_singleton);
 
 	return filter;
 }
 
+struct stream_filter *get_stream_filter(const struct index_state *istate,
+					const char *path,
+					const struct object_id *oid)
+{
+	struct conv_attrs ca;
+	convert_attrs(istate, &ca, path);
+	return get_stream_filter_ca(&ca, oid);
+}
+
 void free_stream_filter(struct stream_filter *filter)
 {
 	filter->vtbl->free(filter);
@@ -2024,3 +2009,21 @@ void clone_checkout_metadata(struct checkout_metadata *dst,
 	if (blob)
 		oidcpy(&dst->blob, blob);
 }
+
+enum conv_attrs_classification classify_conv_attrs(const struct conv_attrs *ca)
+{
+	if (ca->drv) {
+		if (ca->drv->process)
+			return CA_CLASS_INCORE_PROCESS;
+		if (ca->drv->smudge || ca->drv->clean)
+			return CA_CLASS_INCORE_FILTER;
+	}
+
+	if (ca->working_tree_encoding)
+		return CA_CLASS_INCORE;
+
+	if (ca->crlf_action == CRLF_AUTO || ca->crlf_action == CRLF_AUTO_CRLF)
+		return CA_CLASS_INCORE;
+
+	return CA_CLASS_STREAMABLE;
+}