X-Git-Url: http://review.tizen.org/git/?a=blobdiff_plain;f=convert.c;h=94ff8376492257782a1af5b3d2851ee8724c2edd;hb=a001ef91d93daca995b6f446c23e7213f43b588f;hp=f3bd3e93fb2ecf95413db3c53d7e686cd03d1e69;hpb=93c1ea80c67f3875c237bf649bb062fe8ad235a9;p=platform%2Fupstream%2Fgit.git

diff --git a/convert.c b/convert.c
index f3bd3e9..94ff837 100644
--- a/convert.c
+++ b/convert.c
@@ -1,8 +1,13 @@
 #include "cache.h"
+#include "config.h"
+#include "object-store.h"
 #include "attr.h"
 #include "run-command.h"
 #include "quote.h"
 #include "sigchain.h"
+#include "pkt-line.h"
+#include "sub-process.h"
+#include "utf8.h"
 
 /*
  * convert.c - convert a file when checking it out and checking it in.
@@ -13,18 +18,25 @@
  * translation when the "text" attribute or "auto_crlf" option is set.
  */
 
+/* Stat bits: When BIN is set, the txt bits are unset */
+#define CONVERT_STAT_BITS_TXT_LF    0x1
+#define CONVERT_STAT_BITS_TXT_CRLF  0x2
+#define CONVERT_STAT_BITS_BIN       0x4
+
 enum crlf_action {
-	CRLF_GUESS = -1,
-	CRLF_BINARY = 0,
+	CRLF_UNDEFINED,
+	CRLF_BINARY,
 	CRLF_TEXT,
-	CRLF_INPUT,
-	CRLF_CRLF,
-	CRLF_AUTO
+	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, cr, lf, crlf;
+	unsigned nul, lonecr, lonelf, crlf;
 
 	/* These are just approximations! */
 	unsigned printable, nonprintable;
@@ -39,13 +51,15 @@ static void gather_stats(const char *buf, unsigned long size, struct text_stat *
 	for (i = 0; i < size; i++) {
 		unsigned char c = buf[i];
 		if (c == '\r') {
-			stats->cr++;
-			if (i+1 < size && buf[i+1] == '\n')
+			if (i+1 < size && buf[i+1] == '\n') {
 				stats->crlf++;
+				i++;
+			} else
+				stats->lonecr++;
 			continue;
 		}
 		if (c == '\n') {
-			stats->lf++;
+			stats->lonelf++;
 			continue;
 		}
 		if (c == 127)
@@ -75,23 +89,85 @@ static void gather_stats(const char *buf, unsigned long size, struct text_stat *
 
 /*
  * The same heuristics as diff.c::mmfile_is_binary()
+ * We treat files with bare CR as binary
  */
-static int is_binary(unsigned long size, struct text_stat *stats)
+static int convert_is_binary(const struct text_stat *stats)
 {
-
+	if (stats->lonecr)
+		return 1;
 	if (stats->nul)
 		return 1;
 	if ((stats->printable >> 7) < stats->nonprintable)
 		return 1;
-	/*
-	 * Other heuristics? Average line length might be relevant,
-	 * as might LF vs CR vs CRLF counts..
-	 *
-	 * NOTE! It might be normal to have a low ratio of CRLF to LF
-	 * (somebody starts with a LF-only file and edits it with an editor
-	 * that adds CRLF only to lines that are added..). But do  we
-	 * want to support CR-only? Probably not.
-	 */
+	return 0;
+}
+
+static unsigned int gather_convert_stats(const char *data, unsigned long size)
+{
+	struct text_stat stats;
+	int ret = 0;
+	if (!data || !size)
+		return 0;
+	gather_stats(data, size, &stats);
+	if (convert_is_binary(&stats))
+		ret |= CONVERT_STAT_BITS_BIN;
+	if (stats.crlf)
+		ret |= CONVERT_STAT_BITS_TXT_CRLF;
+	if (stats.lonelf)
+		ret |=  CONVERT_STAT_BITS_TXT_LF;
+
+	return ret;
+}
+
+static const char *gather_convert_stats_ascii(const char *data, unsigned long size)
+{
+	unsigned int convert_stats = gather_convert_stats(data, size);
+
+	if (convert_stats & CONVERT_STAT_BITS_BIN)
+		return "-text";
+	switch (convert_stats) {
+	case CONVERT_STAT_BITS_TXT_LF:
+		return "lf";
+	case CONVERT_STAT_BITS_TXT_CRLF:
+		return "crlf";
+	case CONVERT_STAT_BITS_TXT_LF | CONVERT_STAT_BITS_TXT_CRLF:
+		return "mixed";
+	default:
+		return "none";
+	}
+}
+
+const char *get_cached_convert_stats_ascii(const struct index_state *istate,
+					   const char *path)
+{
+	const char *ret;
+	unsigned long sz;
+	void *data = read_blob_data_from_index(istate, path, &sz);
+	ret = gather_convert_stats_ascii(data, sz);
+	free(data);
+	return ret;
+}
+
+const char *get_wt_convert_stats_ascii(const char *path)
+{
+	const char *ret = "";
+	struct strbuf sb = STRBUF_INIT;
+	if (strbuf_read_file(&sb, path, 0) >= 0)
+		ret = gather_convert_stats_ascii(sb.buf, sb.len);
+	strbuf_release(&sb);
+	return ret;
+}
+
+static int text_eol_is_crlf(void)
+{
+	if (auto_crlf == AUTO_CRLF_TRUE)
+		return 1;
+	else if (auto_crlf == AUTO_CRLF_INPUT)
+		return 0;
+	if (core_eol == EOL_CRLF)
+		return 1;
+	if (core_eol == EOL_UNSET && EOL_NATIVE == EOL_CRLF)
+		return 1;
 	return 0;
 }
 
@@ -100,80 +176,341 @@ static enum eol output_eol(enum crlf_action crlf_action)
 	switch (crlf_action) {
 	case CRLF_BINARY:
 		return EOL_UNSET;
-	case CRLF_CRLF:
+	case CRLF_TEXT_CRLF:
 		return EOL_CRLF;
-	case CRLF_INPUT:
+	case CRLF_TEXT_INPUT:
+		return EOL_LF;
+	case CRLF_UNDEFINED:
+	case CRLF_AUTO_CRLF:
+		return EOL_CRLF;
+	case CRLF_AUTO_INPUT:
 		return EOL_LF;
-	case CRLF_GUESS:
-		if (!auto_crlf)
-			return EOL_UNSET;
-		/* fall through */
 	case CRLF_TEXT:
 	case CRLF_AUTO:
-		if (auto_crlf == AUTO_CRLF_TRUE)
-			return EOL_CRLF;
-		else if (auto_crlf == AUTO_CRLF_INPUT)
-			return EOL_LF;
-		else if (core_eol == EOL_UNSET)
-			return EOL_NATIVE;
+		/* fall through */
+		return text_eol_is_crlf() ? EOL_CRLF : EOL_LF;
 	}
+	warning(_("illegal crlf_action %d"), (int)crlf_action);
 	return core_eol;
 }
 
-static void check_safe_crlf(const char *path, enum crlf_action crlf_action,
-                            struct text_stat *stats, enum safe_crlf checksafe)
+static void check_global_conv_flags_eol(const char *path, enum crlf_action crlf_action,
+			    struct text_stat *old_stats, struct text_stat *new_stats,
+			    int conv_flags)
 {
-	if (!checksafe)
-		return;
-
-	if (output_eol(crlf_action) == EOL_LF) {
+	if (old_stats->crlf && !new_stats->crlf ) {
 		/*
-		 * CRLFs would not be restored by checkout:
-		 * check if we'd remove CRLFs
+		 * CRLFs would not be restored by checkout
 		 */
-		if (stats->crlf) {
-			if (checksafe == SAFE_CRLF_WARN)
-				warning("CRLF will be replaced by LF in %s.\nThe file will have its original line endings in your working directory.", path);
-			else /* i.e. SAFE_CRLF_FAIL */
-				die("CRLF would be replaced by LF in %s.", path);
-		}
-	} else if (output_eol(crlf_action) == EOL_CRLF) {
+		if (conv_flags & CONV_EOL_RNDTRP_DIE)
+			die(_("CRLF would be replaced by LF in %s"), path);
+		else if (conv_flags & CONV_EOL_RNDTRP_WARN)
+			warning(_("CRLF will be replaced by LF in %s.\n"
+				  "The file will have its original line"
+				  " endings in your working directory"), path);
+	} else if (old_stats->lonelf && !new_stats->lonelf ) {
 		/*
-		 * CRLFs would be added by checkout:
-		 * check if we have "naked" LFs
+		 * CRLFs would be added by checkout
 		 */
-		if (stats->lf != stats->crlf) {
-			if (checksafe == SAFE_CRLF_WARN)
-				warning("LF will be replaced by CRLF in %s.\nThe file will have its original line endings in your working directory.", path);
-			else /* i.e. SAFE_CRLF_FAIL */
-				die("LF would be replaced by CRLF in %s", path);
-		}
+		if (conv_flags & CONV_EOL_RNDTRP_DIE)
+			die(_("LF would be replaced by CRLF in %s"), path);
+		else if (conv_flags & CONV_EOL_RNDTRP_WARN)
+			warning(_("LF will be replaced by CRLF in %s.\n"
+				  "The file will have its original line"
+				  " endings in your working directory"), path);
 	}
 }
 
-static int has_cr_in_index(const char *path)
+static int has_crlf_in_index(const struct index_state *istate, const char *path)
 {
 	unsigned long sz;
 	void *data;
-	int has_cr;
+	const char *crp;
+	int has_crlf = 0;
 
-	data = read_blob_data_from_cache(path, &sz);
+	data = read_blob_data_from_index(istate, path, &sz);
 	if (!data)
 		return 0;
-	has_cr = memchr(data, '\r', sz) != NULL;
+
+	crp = memchr(data, '\r', sz);
+	if (crp) {
+		unsigned int ret_stats;
+		ret_stats = gather_convert_stats(data, sz);
+		if (!(ret_stats & CONVERT_STAT_BITS_BIN) &&
+		    (ret_stats & CONVERT_STAT_BITS_TXT_CRLF))
+			has_crlf = 1;
+	}
 	free(data);
-	return has_cr;
+	return has_crlf;
+}
+
+static int will_convert_lf_to_crlf(struct text_stat *stats,
+				   enum crlf_action crlf_action)
+{
+	if (output_eol(crlf_action) != EOL_CRLF)
+		return 0;
+	/* No "naked" LF? Nothing to convert, regardless. */
+	if (!stats->lonelf)
+		return 0;
+
+	if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
+		/* If we have any CR or CRLF line endings, we do not touch it */
+		/* This is the new safer autocrlf-handling */
+		if (stats->lonecr || stats->crlf)
+			return 0;
+
+		if (convert_is_binary(stats))
+			return 0;
+	}
+	return 1;
+
 }
 
-static int crlf_to_git(const char *path, const char *src, size_t len,
+static int validate_encoding(const char *path, const char *enc,
+		      const char *data, size_t len, int die_on_error)
+{
+	/* We only check for UTF here as UTF?? can be an alias for UTF-?? */
+	if (istarts_with(enc, "UTF")) {
+		/*
+		 * Check for detectable errors in UTF encodings
+		 */
+		if (has_prohibited_utf_bom(enc, data, len)) {
+			const char *error_msg = _(
+				"BOM is prohibited in '%s' if encoded as %s");
+			/*
+			 * This advice is shown for UTF-??BE and UTF-??LE encodings.
+			 * We cut off the last two characters of the encoding name
+			 * to generate the encoding name suitable for BOMs.
+			 */
+			const char *advise_msg = _(
+				"The file '%s' contains a byte order "
+				"mark (BOM). Please use UTF-%s as "
+				"working-tree-encoding.");
+			const char *stripped = NULL;
+			char *upper = xstrdup_toupper(enc);
+			upper[strlen(upper)-2] = '\0';
+			if (!skip_prefix(upper, "UTF-", &stripped))
+				skip_prefix(stripped, "UTF", &stripped);
+			advise(advise_msg, path, stripped);
+			free(upper);
+			if (die_on_error)
+				die(error_msg, path, enc);
+			else {
+				return error(error_msg, path, enc);
+			}
+
+		} else if (is_missing_required_utf_bom(enc, data, len)) {
+			const char *error_msg = _(
+				"BOM is required in '%s' if encoded as %s");
+			const char *advise_msg = _(
+				"The file '%s' is missing a byte order "
+				"mark (BOM). Please use UTF-%sBE or UTF-%sLE "
+				"(depending on the byte order) as "
+				"working-tree-encoding.");
+			const char *stripped = NULL;
+			char *upper = xstrdup_toupper(enc);
+			if (!skip_prefix(upper, "UTF-", &stripped))
+				skip_prefix(stripped, "UTF", &stripped);
+			advise(advise_msg, path, stripped, stripped);
+			free(upper);
+			if (die_on_error)
+				die(error_msg, path, enc);
+			else {
+				return error(error_msg, path, enc);
+			}
+		}
+
+	}
+	return 0;
+}
+
+static void trace_encoding(const char *context, const char *path,
+			   const char *encoding, const char *buf, size_t len)
+{
+	static struct trace_key coe = TRACE_KEY_INIT(WORKING_TREE_ENCODING);
+	struct strbuf trace = STRBUF_INIT;
+	int i;
+
+	strbuf_addf(&trace, "%s (%s, considered %s):\n", context, path, encoding);
+	for (i = 0; i < len && buf; ++i) {
+		strbuf_addf(
+			&trace, "| \033[2m%2i:\033[0m %2x \033[2m%c\033[0m%c",
+			i,
+			(unsigned char) buf[i],
+			(buf[i] > 32 && buf[i] < 127 ? buf[i] : ' '),
+			((i+1) % 8 && (i+1) < len ? ' ' : '\n')
+		);
+	}
+	strbuf_addchars(&trace, '\n', 1);
+
+	trace_strbuf(&coe, &trace);
+	strbuf_release(&trace);
+}
+
+static int check_roundtrip(const char *enc_name)
+{
+	/*
+	 * check_roundtrip_encoding contains a string of comma and/or
+	 * space separated encodings (eg. "UTF-16, ASCII, CP1125").
+	 * Search for the given encoding in that string.
+	 */
+	const char *found = strcasestr(check_roundtrip_encoding, enc_name);
+	const char *next;
+	int len;
+	if (!found)
+		return 0;
+	next = found + strlen(enc_name);
+	len = strlen(check_roundtrip_encoding);
+	return (found && (
+			/*
+			 * check that the found encoding is at the
+			 * beginning of check_roundtrip_encoding or
+			 * that it is prefixed with a space or comma
+			 */
+			found == check_roundtrip_encoding || (
+				(isspace(found[-1]) || found[-1] == ',')
+			)
+		) && (
+			/*
+			 * check that the found encoding is at the
+			 * end of check_roundtrip_encoding or
+			 * that it is suffixed with a space or comma
+			 */
+			next == check_roundtrip_encoding + len || (
+				next < check_roundtrip_encoding + len &&
+				(isspace(next[0]) || next[0] == ',')
+			)
+		));
+}
+
+static const char *default_encoding = "UTF-8";
+
+static int encode_to_git(const char *path, const char *src, size_t src_len,
+			 struct strbuf *buf, const char *enc, int conv_flags)
+{
+	char *dst;
+	size_t dst_len;
+	int die_on_error = conv_flags & CONV_WRITE_OBJECT;
+
+	/*
+	 * No encoding is specified or there is nothing to encode.
+	 * Tell the caller that the content was not modified.
+	 */
+	if (!enc || (src && !src_len))
+		return 0;
+
+	/*
+	 * Looks like we got called from "would_convert_to_git()".
+	 * This means Git wants to know if it would encode (= modify!)
+	 * the content. Let's answer with "yes", since an encoding was
+	 * specified.
+	 */
+	if (!buf && !src)
+		return 1;
+
+	if (validate_encoding(path, enc, src, src_len, die_on_error))
+		return 0;
+
+	trace_encoding("source", path, enc, src, src_len);
+	dst = reencode_string_len(src, src_len, default_encoding, enc,
+				  &dst_len);
+	if (!dst) {
+		/*
+		 * We could add the blob "as-is" to Git. However, on checkout
+		 * we would try to reencode to the original encoding. This
+		 * would fail and we would leave the user with a messed-up
+		 * working tree. Let's try to avoid this by screaming loud.
+		 */
+		const char* msg = _("failed to encode '%s' from %s to %s");
+		if (die_on_error)
+			die(msg, path, enc, default_encoding);
+		else {
+			error(msg, path, enc, default_encoding);
+			return 0;
+		}
+	}
+	trace_encoding("destination", path, default_encoding, dst, dst_len);
+
+	/*
+	 * UTF supports lossless conversion round tripping [1] and conversions
+	 * between UTF and other encodings are mostly round trip safe as
+	 * Unicode aims to be a superset of all other character encodings.
+	 * However, certain encodings (e.g. SHIFT-JIS) are known to have round
+	 * trip issues [2]. Check the round trip conversion for all encodings
+	 * listed in core.checkRoundtripEncoding.
+	 *
+	 * The round trip check is only performed if content is written to Git.
+	 * This ensures that no information is lost during conversion to/from
+	 * the internal UTF-8 representation.
+	 *
+	 * Please note, the code below is not tested because I was not able to
+	 * generate a faulty round trip without an iconv error. Iconv errors
+	 * are already caught above.
+	 *
+	 * [1] http://unicode.org/faq/utf_bom.html#gen2
+	 * [2] https://support.microsoft.com/en-us/help/170559/prb-conversion-problem-between-shift-jis-and-unicode
+	 */
+	if (die_on_error && check_roundtrip(enc)) {
+		char *re_src;
+		size_t re_src_len;
+
+		re_src = reencode_string_len(dst, dst_len,
+					     enc, default_encoding,
+					     &re_src_len);
+
+		trace_printf("Checking roundtrip encoding for %s...\n", enc);
+		trace_encoding("reencoded source", path, enc,
+			       re_src, re_src_len);
+
+		if (!re_src || src_len != re_src_len ||
+		    memcmp(src, re_src, src_len)) {
+			const char* msg = _("encoding '%s' from %s to %s and "
+					    "back is not the same");
+			die(msg, path, enc, default_encoding);
+		}
+
+		free(re_src);
+	}
+
+	strbuf_attach(buf, dst, dst_len, dst_len + 1);
+	return 1;
+}
+
+static int encode_to_worktree(const char *path, const char *src, size_t src_len,
+			      struct strbuf *buf, const char *enc)
+{
+	char *dst;
+	size_t dst_len;
+
+	/*
+	 * No encoding is specified or there is nothing to encode.
+	 * Tell the caller that the content was not modified.
+	 */
+	if (!enc || (src && !src_len))
+		return 0;
+
+	dst = reencode_string_len(src, src_len, enc, default_encoding,
+				  &dst_len);
+	if (!dst) {
+		error(_("failed to encode '%s' from %s to %s"),
+		      path, default_encoding, enc);
+		return 0;
+	}
+
+	strbuf_attach(buf, dst, dst_len, dst_len + 1);
+	return 1;
+}
+
+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, enum safe_crlf checksafe)
+		       enum crlf_action crlf_action, int conv_flags)
 {
 	struct text_stat stats;
 	char *dst;
+	int convert_crlf_into_lf;
 
 	if (crlf_action == CRLF_BINARY ||
-	    (crlf_action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE) ||
 	    (src && !len))
 		return 0;
 
@@ -185,36 +522,39 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
 		return 1;
 
 	gather_stats(src, len, &stats);
+	/* Optimization: No CRLF? Nothing to convert, regardless. */
+	convert_crlf_into_lf = !!stats.crlf;
 
-	if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) {
-		/*
-		 * We're currently not going to even try to convert stuff
-		 * that has bare CR characters. Does anybody do that crazy
-		 * stuff?
-		 */
-		if (stats.cr != stats.crlf)
+	if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
+		if (convert_is_binary(&stats))
 			return 0;
-
 		/*
-		 * And add some heuristics for binary vs text, of course...
+		 * If the file in the index has any CR in it, do not
+		 * convert.  This is the new safer autocrlf handling,
+		 * unless we want to renormalize in a merge or
+		 * cherry-pick.
 		 */
-		if (is_binary(len, &stats))
-			return 0;
-
-		if (crlf_action == CRLF_GUESS) {
-			/*
-			 * If the file in the index has any CR in it, do not convert.
-			 * This is the new safer autocrlf handling.
-			 */
-			if (has_cr_in_index(path))
-				return 0;
+		if ((!(conv_flags & CONV_EOL_RENORMALIZE)) &&
+		    has_crlf_in_index(istate, path))
+			convert_crlf_into_lf = 0;
+	}
+	if (((conv_flags & CONV_EOL_RNDTRP_WARN) ||
+	     ((conv_flags & CONV_EOL_RNDTRP_DIE) && len))) {
+		struct text_stat new_stats;
+		memcpy(&new_stats, &stats, sizeof(new_stats));
+		/* simulate "git add" */
+		if (convert_crlf_into_lf) {
+			new_stats.lonelf += new_stats.crlf;
+			new_stats.crlf = 0;
 		}
+		/* simulate "git checkout" */
+		if (will_convert_lf_to_crlf(&new_stats, crlf_action)) {
+			new_stats.crlf += new_stats.lonelf;
+			new_stats.lonelf = 0;
+		}
+		check_global_conv_flags_eol(path, crlf_action, &stats, &new_stats, conv_flags);
 	}
-
-	check_safe_crlf(path, crlf_action, &stats, checksafe);
-
-	/* Optimization: No CR? Nothing to convert, regardless. */
-	if (!stats.cr)
+	if (!convert_crlf_into_lf)
 		return 0;
 
 	/*
@@ -228,7 +568,7 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
 	if (strbuf_avail(buf) + buf->len < len)
 		strbuf_grow(buf, len - buf->len);
 	dst = buf->buf;
-	if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) {
+	if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
 		/*
 		 * If we guessed, we already know we rejected a file with
 		 * lone CR, and we can strip a CR without looking at what
@@ -250,7 +590,7 @@ static int crlf_to_git(const char *path, const char *src, size_t len,
 	return 1;
 }
 
-static int crlf_to_worktree(const char *path, const char *src, size_t len,
+static int crlf_to_worktree(const char *src, size_t len,
 			    struct strbuf *buf, enum crlf_action crlf_action)
 {
 	char *to_free = NULL;
@@ -260,36 +600,14 @@ static int crlf_to_worktree(const char *path, const char *src, size_t len,
 		return 0;
 
 	gather_stats(src, len, &stats);
-
-	/* No LF? Nothing to convert, regardless. */
-	if (!stats.lf)
+	if (!will_convert_lf_to_crlf(&stats, crlf_action))
 		return 0;
 
-	/* Was it already in CRLF format? */
-	if (stats.lf == stats.crlf)
-		return 0;
-
-	if (crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS) {
-		if (crlf_action == CRLF_GUESS) {
-			/* If we have any CR or CRLF line endings, we do not touch it */
-			/* This is the new safer autocrlf-handling */
-			if (stats.cr > 0 || stats.crlf > 0)
-				return 0;
-		}
-
-		/* If we have any bare CR characters, we're not going to touch it */
-		if (stats.cr != stats.crlf)
-			return 0;
-
-		if (is_binary(len, &stats))
-			return 0;
-	}
-
 	/* are we "faking" in place editing ? */
 	if (src == buf->buf)
 		to_free = strbuf_detach(buf, NULL);
 
-	strbuf_grow(buf, len + stats.lf - stats.crlf);
+	strbuf_grow(buf, len + stats.lonelf);
 	for (;;) {
 		const char *nl = memchr(src, '\n', len);
 		if (!nl)
@@ -350,8 +668,11 @@ static int filter_buffer_or_fd(int in, int out, void *data)
 	child_process.in = -1;
 	child_process.out = out;
 
-	if (start_command(&child_process))
-		return error("cannot fork to run external filter %s", params->cmd);
+	if (start_command(&child_process)) {
+		strbuf_release(&cmd);
+		return error(_("cannot fork to run external filter '%s'"),
+			     params->cmd);
+	}
 
 	sigchain_push(SIGPIPE, SIG_IGN);
 
@@ -369,20 +690,21 @@ static int filter_buffer_or_fd(int in, int out, void *data)
 	if (close(child_process.in))
 		write_err = 1;
 	if (write_err)
-		error("cannot feed the input to external filter %s", params->cmd);
+		error(_("cannot feed the input to external filter '%s'"),
+		      params->cmd);
 
 	sigchain_pop(SIGPIPE);
 
 	status = finish_command(&child_process);
 	if (status)
-		error("external filter %s failed %d", params->cmd, status);
+		error(_("external filter '%s' failed %d"), params->cmd, status);
 
 	strbuf_release(&cmd);
 	return (write_err || status);
 }
 
-static int apply_filter(const char *path, const char *src, size_t len, int fd,
-                        struct strbuf *dst, const char *cmd)
+static int apply_single_file_filter(const char *path, const char *src, size_t len, int fd,
+				    struct strbuf *dst, const char *cmd)
 {
 	/*
 	 * Create a pipeline to have the command filter the buffer's
@@ -390,17 +712,11 @@ static int apply_filter(const char *path, const char *src, size_t len, int fd,
 	 *
 	 * (child --> cmd) --> us
 	 */
-	int ret = 1;
+	int err = 0;
 	struct strbuf nbuf = STRBUF_INIT;
 	struct async async;
 	struct filter_params params;
 
-	if (!cmd)
-		return 0;
-
-	if (!dst)
-		return 1;
-
 	memset(&async, 0, sizeof(async));
 	async.proc = filter_buffer_or_fd;
 	async.data = &params;
@@ -415,24 +731,237 @@ static int apply_filter(const char *path, const char *src, size_t len, int fd,
 	if (start_async(&async))
 		return 0;	/* error was already reported */
 
-	if (strbuf_read(&nbuf, async.out, len) < 0) {
-		error("read from external filter %s failed", cmd);
-		ret = 0;
+	if (strbuf_read(&nbuf, async.out, 0) < 0) {
+		err = error(_("read from external filter '%s' failed"), cmd);
 	}
 	if (close(async.out)) {
-		error("read from external filter %s failed", cmd);
-		ret = 0;
+		err = error(_("read from external filter '%s' failed"), cmd);
 	}
 	if (finish_async(&async)) {
-		error("external filter %s failed", cmd);
-		ret = 0;
+		err = error(_("external filter '%s' failed"), cmd);
 	}
 
-	if (ret) {
+	if (!err) {
 		strbuf_swap(dst, &nbuf);
 	}
 	strbuf_release(&nbuf);
-	return ret;
+	return !err;
+}
+
+#define CAP_CLEAN    (1u<<0)
+#define CAP_SMUDGE   (1u<<1)
+#define CAP_DELAY    (1u<<2)
+
+struct cmd2process {
+	struct subprocess_entry subprocess; /* must be the first member! */
+	unsigned int supported_capabilities;
+};
+
+static int subprocess_map_initialized;
+static struct hashmap subprocess_map;
+
+static int start_multi_file_filter_fn(struct subprocess_entry *subprocess)
+{
+	static int versions[] = {2, 0};
+	static struct subprocess_capability capabilities[] = {
+		{ "clean",  CAP_CLEAN  },
+		{ "smudge", CAP_SMUDGE },
+		{ "delay",  CAP_DELAY  },
+		{ NULL, 0 }
+	};
+	struct cmd2process *entry = (struct cmd2process *)subprocess;
+	return subprocess_handshake(subprocess, "git-filter", versions, NULL,
+				    capabilities,
+				    &entry->supported_capabilities);
+}
+
+static void handle_filter_error(const struct strbuf *filter_status,
+				struct cmd2process *entry,
+				const unsigned int wanted_capability)
+{
+	if (!strcmp(filter_status->buf, "error"))
+		; /* The filter signaled a problem with the file. */
+	else if (!strcmp(filter_status->buf, "abort") && wanted_capability) {
+		/*
+		 * The filter signaled a permanent problem. Don't try to filter
+		 * files with the same command for the lifetime of the current
+		 * Git process.
+		 */
+		 entry->supported_capabilities &= ~wanted_capability;
+	} else {
+		/*
+		 * Something went wrong with the protocol filter.
+		 * Force shutdown and restart if another blob requires filtering.
+		 */
+		error(_("external filter '%s' failed"), entry->subprocess.cmd);
+		subprocess_stop(&subprocess_map, &entry->subprocess);
+		free(entry);
+	}
+}
+
+static int apply_multi_file_filter(const char *path, const char *src, size_t len,
+				   int fd, struct strbuf *dst, const char *cmd,
+				   const unsigned int wanted_capability,
+				   struct delayed_checkout *dco)
+{
+	int err;
+	int can_delay = 0;
+	struct cmd2process *entry;
+	struct child_process *process;
+	struct strbuf nbuf = STRBUF_INIT;
+	struct strbuf filter_status = STRBUF_INIT;
+	const char *filter_type;
+
+	if (!subprocess_map_initialized) {
+		subprocess_map_initialized = 1;
+		hashmap_init(&subprocess_map, cmd2process_cmp, NULL, 0);
+		entry = NULL;
+	} else {
+		entry = (struct cmd2process *)subprocess_find_entry(&subprocess_map, cmd);
+	}
+
+	fflush(NULL);
+
+	if (!entry) {
+		entry = xmalloc(sizeof(*entry));
+		entry->supported_capabilities = 0;
+
+		if (subprocess_start(&subprocess_map, &entry->subprocess, cmd, start_multi_file_filter_fn)) {
+			free(entry);
+			return 0;
+		}
+	}
+	process = &entry->subprocess.process;
+
+	if (!(entry->supported_capabilities & wanted_capability))
+		return 0;
+
+	if (wanted_capability & CAP_CLEAN)
+		filter_type = "clean";
+	else if (wanted_capability & CAP_SMUDGE)
+		filter_type = "smudge";
+	else
+		die(_("unexpected filter type"));
+
+	sigchain_push(SIGPIPE, SIG_IGN);
+
+	assert(strlen(filter_type) < LARGE_PACKET_DATA_MAX - strlen("command=\n"));
+	err = packet_write_fmt_gently(process->in, "command=%s\n", filter_type);
+	if (err)
+		goto done;
+
+	err = strlen(path) > LARGE_PACKET_DATA_MAX - strlen("pathname=\n");
+	if (err) {
+		error(_("path name too long for external filter"));
+		goto done;
+	}
+
+	err = packet_write_fmt_gently(process->in, "pathname=%s\n", path);
+	if (err)
+		goto done;
+
+	if ((entry->supported_capabilities & CAP_DELAY) &&
+	    dco && dco->state == CE_CAN_DELAY) {
+		can_delay = 1;
+		err = packet_write_fmt_gently(process->in, "can-delay=1\n");
+		if (err)
+			goto done;
+	}
+
+	err = packet_flush_gently(process->in);
+	if (err)
+		goto done;
+
+	if (fd >= 0)
+		err = write_packetized_from_fd(fd, process->in);
+	else
+		err = write_packetized_from_buf(src, len, process->in);
+	if (err)
+		goto done;
+
+	err = subprocess_read_status(process->out, &filter_status);
+	if (err)
+		goto done;
+
+	if (can_delay && !strcmp(filter_status.buf, "delayed")) {
+		string_list_insert(&dco->filters, cmd);
+		string_list_insert(&dco->paths, path);
+	} else {
+		/* The filter got the blob and wants to send us a response. */
+		err = strcmp(filter_status.buf, "success");
+		if (err)
+			goto done;
+
+		err = read_packetized_to_strbuf(process->out, &nbuf) < 0;
+		if (err)
+			goto done;
+
+		err = subprocess_read_status(process->out, &filter_status);
+		if (err)
+			goto done;
+
+		err = strcmp(filter_status.buf, "success");
+	}
+
+done:
+	sigchain_pop(SIGPIPE);
+
+	if (err)
+		handle_filter_error(&filter_status, entry, wanted_capability);
+	else
+		strbuf_swap(dst, &nbuf);
+	strbuf_release(&nbuf);
+	return !err;
+}
+
+
+int async_query_available_blobs(const char *cmd, struct string_list *available_paths)
+{
+	int err;
+	char *line;
+	struct cmd2process *entry;
+	struct child_process *process;
+	struct strbuf filter_status = STRBUF_INIT;
+
+	assert(subprocess_map_initialized);
+	entry = (struct cmd2process *)subprocess_find_entry(&subprocess_map, cmd);
+	if (!entry) {
+		error(_("external filter '%s' is not available anymore although "
+			"not all paths have been filtered"), cmd);
+		return 0;
+	}
+	process = &entry->subprocess.process;
+	sigchain_push(SIGPIPE, SIG_IGN);
+
+	err = packet_write_fmt_gently(
+		process->in, "command=list_available_blobs\n");
+	if (err)
+		goto done;
+
+	err = packet_flush_gently(process->in);
+	if (err)
+		goto done;
+
+	while ((line = packet_read_line(process->out, NULL))) {
+		const char *path;
+		if (skip_prefix(line, "pathname=", &path))
+			string_list_insert(available_paths, xstrdup(path));
+		else
+			; /* ignore unknown keys */
+	}
+
+	err = subprocess_read_status(process->out, &filter_status);
+	if (err)
+		goto done;
+
+	err = strcmp(filter_status.buf, "success");
+
+done:
+	sigchain_pop(SIGPIPE);
+
+	if (err)
+		handle_filter_error(&filter_status, entry, 0);
+	return !err;
 }
 
 static struct convert_driver {
@@ -440,9 +969,37 @@ static struct convert_driver {
 	struct convert_driver *next;
 	const char *smudge;
 	const char *clean;
+	const char *process;
 	int required;
 } *user_convert, **user_convert_tail;
 
+static int apply_filter(const char *path, const char *src, size_t len,
+			int fd, struct strbuf *dst, struct convert_driver *drv,
+			const unsigned int wanted_capability,
+			struct delayed_checkout *dco)
+{
+	const char *cmd = NULL;
+
+	if (!drv)
+		return 0;
+
+	if (!dst)
+		return 1;
+
+	if ((wanted_capability & CAP_CLEAN) && !drv->process && drv->clean)
+		cmd = drv->clean;
+	else if ((wanted_capability & CAP_SMUDGE) && !drv->process && drv->smudge)
+		cmd = drv->smudge;
+
+	if (cmd && *cmd)
+		return apply_single_file_filter(path, src, len, fd, dst, cmd);
+	else if (drv->process && *drv->process)
+		return apply_multi_file_filter(path, src, len, fd, dst,
+			drv->process, wanted_capability, dco);
+
+	return 0;
+}
+
 static int read_convert_config(const char *var, const char *value, void *cb)
 {
 	const char *key, *name;
@@ -480,6 +1037,9 @@ static int read_convert_config(const char *var, const char *value, void *cb)
 	if (!strcmp("clean", key))
 		return git_config_string(&drv->clean, var, value);
 
+	if (!strcmp("process", key))
+		return git_config_string(&drv->process, var, value);
+
 	if (!strcmp("required", key)) {
 		drv->required = git_config_bool(var, value);
 		return 0;
@@ -530,8 +1090,8 @@ static int count_ident(const char *cp, unsigned long size)
 	return cnt;
 }
 
-static int ident_to_git(const char *path, const char *src, size_t len,
-                        struct strbuf *buf, int ident)
+static int ident_to_git(const char *src, size_t len,
+			struct strbuf *buf, int ident)
 {
 	char *dst, *dollar;
 
@@ -574,10 +1134,10 @@ static int ident_to_git(const char *path, const char *src, size_t len,
 	return 1;
 }
 
-static int ident_to_worktree(const char *path, const char *src, size_t len,
-                             struct strbuf *buf, int ident)
+static int ident_to_worktree(const char *src, size_t len,
+			     struct strbuf *buf, int ident)
 {
-	unsigned char sha1[20];
+	struct object_id oid;
 	char *to_free = NULL, *dollar, *spc;
 	int cnt;
 
@@ -591,9 +1151,9 @@ static int ident_to_worktree(const char *path, const char *src, size_t len,
 	/* are we "faking" in place editing ? */
 	if (src == buf->buf)
 		to_free = strbuf_detach(buf, NULL);
-	hash_sha1_file(src, len, "blob", sha1);
+	hash_object_file(src, len, "blob", &oid);
 
-	strbuf_grow(buf, len + cnt * 43);
+	strbuf_grow(buf, len + cnt * (the_hash_algo->hexsz + 3));
 	for (;;) {
 		/* step 1: run to the next '$' */
 		dollar = memchr(src, '$', len);
@@ -648,7 +1208,7 @@ static int ident_to_worktree(const char *path, const char *src, size_t len,
 
 		/* step 4: substitute */
 		strbuf_addstr(buf, "Id: ");
-		strbuf_add(buf, sha1_to_hex(sha1), 40);
+		strbuf_addstr(buf, oid_to_hex(&oid));
 		strbuf_addstr(buf, " $");
 	}
 	strbuf_add(buf, src, len);
@@ -657,7 +1217,25 @@ static int ident_to_worktree(const char *path, const char *src, size_t len,
 	return 1;
 }
 
-static enum crlf_action git_path_check_crlf(const char *path, struct git_attr_check *check)
+static const char *git_path_check_encoding(struct attr_check_item *check)
+{
+	const char *value = check->value;
+
+	if (ATTR_UNSET(value) || !strlen(value))
+		return NULL;
+
+	if (ATTR_TRUE(value) || ATTR_FALSE(value)) {
+		die(_("true/false are no valid working-tree-encodings"));
+	}
+
+	/* Don't encode to the default encoding */
+	if (same_encoding(value, default_encoding))
+		return NULL;
+
+	return value;
+}
+
+static enum crlf_action git_path_check_crlf(struct attr_check_item *check)
 {
 	const char *value = check->value;
 
@@ -668,13 +1246,13 @@ static enum crlf_action git_path_check_crlf(const char *path, struct git_attr_ch
 	else if (ATTR_UNSET(value))
 		;
 	else if (!strcmp(value, "input"))
-		return CRLF_INPUT;
+		return CRLF_TEXT_INPUT;
 	else if (!strcmp(value, "auto"))
 		return CRLF_AUTO;
-	return CRLF_GUESS;
+	return CRLF_UNDEFINED;
 }
 
-static enum eol git_path_check_eol(const char *path, struct git_attr_check *check)
+static enum eol git_path_check_eol(struct attr_check_item *check)
 {
 	const char *value = check->value;
 
@@ -687,8 +1265,7 @@ static enum eol git_path_check_eol(const char *path, struct git_attr_check *chec
 	return EOL_UNSET;
 }
 
-static struct convert_driver *git_path_check_convert(const char *path,
-					     struct git_attr_check *check)
+static struct convert_driver *git_path_check_convert(struct attr_check_item *check)
 {
 	const char *value = check->value;
 	struct convert_driver *drv;
@@ -701,68 +1278,72 @@ static struct convert_driver *git_path_check_convert(const char *path,
 	return NULL;
 }
 
-static int git_path_check_ident(const char *path, struct git_attr_check *check)
+static int git_path_check_ident(struct attr_check_item *check)
 {
 	const char *value = check->value;
 
 	return !!ATTR_TRUE(value);
 }
 
-static enum crlf_action input_crlf_action(enum crlf_action text_attr, enum eol eol_attr)
-{
-	if (text_attr == CRLF_BINARY)
-		return CRLF_BINARY;
-	if (eol_attr == EOL_LF)
-		return CRLF_INPUT;
-	if (eol_attr == EOL_CRLF)
-		return CRLF_CRLF;
-	return text_attr;
-}
-
 struct conv_attrs {
 	struct convert_driver *drv;
-	enum crlf_action crlf_action;
-	enum eol eol_attr;
+	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 const char *conv_attr_name[] = {
-	"crlf", "ident", "filter", "eol", "text",
-};
-#define NUM_CONV_ATTRS ARRAY_SIZE(conv_attr_name)
-
-static void convert_attrs(struct conv_attrs *ca, const char *path)
+static void convert_attrs(const struct index_state *istate,
+			  struct conv_attrs *ca, const char *path)
 {
-	int i;
-	static struct git_attr_check ccheck[NUM_CONV_ATTRS];
+	static struct attr_check *check;
+	struct attr_check_item *ccheck = NULL;
 
-	if (!ccheck[0].attr) {
-		for (i = 0; i < NUM_CONV_ATTRS; i++)
-			ccheck[i].attr = git_attr(conv_attr_name[i]);
+	if (!check) {
+		check = attr_check_initl("crlf", "ident", "filter",
+					 "eol", "text", "working-tree-encoding",
+					 NULL);
 		user_convert_tail = &user_convert;
 		git_config(read_convert_config, NULL);
 	}
 
-	if (!git_check_attr(path, NUM_CONV_ATTRS, ccheck)) {
-		ca->crlf_action = git_path_check_crlf(path, ccheck + 4);
-		if (ca->crlf_action == CRLF_GUESS)
-			ca->crlf_action = git_path_check_crlf(path, ccheck + 0);
-		ca->ident = git_path_check_ident(path, ccheck + 1);
-		ca->drv = git_path_check_convert(path, ccheck + 2);
-		ca->eol_attr = git_path_check_eol(path, ccheck + 3);
-	} else {
-		ca->drv = NULL;
-		ca->crlf_action = CRLF_GUESS;
-		ca->eol_attr = EOL_UNSET;
-		ca->ident = 0;
+	git_check_attr(istate, path, check);
+	ccheck = check->items;
+	ca->crlf_action = git_path_check_crlf(ccheck + 4);
+	if (ca->crlf_action == CRLF_UNDEFINED)
+		ca->crlf_action = git_path_check_crlf(ccheck + 0);
+	ca->ident = git_path_check_ident(ccheck + 1);
+	ca->drv = git_path_check_convert(ccheck + 2);
+	if (ca->crlf_action != CRLF_BINARY) {
+		enum eol eol_attr = git_path_check_eol(ccheck + 3);
+		if (ca->crlf_action == CRLF_AUTO && eol_attr == EOL_LF)
+			ca->crlf_action = CRLF_AUTO_INPUT;
+		else if (ca->crlf_action == CRLF_AUTO && eol_attr == EOL_CRLF)
+			ca->crlf_action = CRLF_AUTO_CRLF;
+		else if (eol_attr == EOL_LF)
+			ca->crlf_action = CRLF_TEXT_INPUT;
+		else if (eol_attr == EOL_CRLF)
+			ca->crlf_action = CRLF_TEXT_CRLF;
 	}
+	ca->working_tree_encoding = git_path_check_encoding(ccheck + 5);
+
+	/* Save attr and make a decision for action */
+	ca->attr_action = ca->crlf_action;
+	if (ca->crlf_action == CRLF_TEXT)
+		ca->crlf_action = text_eol_is_crlf() ? CRLF_TEXT_CRLF : CRLF_TEXT_INPUT;
+	if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_FALSE)
+		ca->crlf_action = CRLF_BINARY;
+	if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_TRUE)
+		ca->crlf_action = CRLF_AUTO_CRLF;
+	if (ca->crlf_action == CRLF_UNDEFINED && auto_crlf == AUTO_CRLF_INPUT)
+		ca->crlf_action = CRLF_AUTO_INPUT;
 }
 
-int would_convert_to_git_filter_fd(const char *path)
+int would_convert_to_git_filter_fd(const struct index_state *istate, const char *path)
 {
 	struct conv_attrs ca;
 
-	convert_attrs(&ca, path);
+	convert_attrs(istate, &ca, path);
 	if (!ca.drv)
 		return 0;
 
@@ -774,110 +1355,153 @@ int would_convert_to_git_filter_fd(const char *path)
 	if (!ca.drv->required)
 		return 0;
 
-	return apply_filter(path, NULL, 0, -1, NULL, ca.drv->clean);
+	return apply_filter(path, NULL, 0, -1, NULL, ca.drv, CAP_CLEAN, NULL);
 }
 
-int convert_to_git(const char *path, const char *src, size_t len,
-                   struct strbuf *dst, enum safe_crlf checksafe)
+const char *get_convert_attr_ascii(const struct index_state *istate, const char *path)
 {
-	int ret = 0;
-	const char *filter = NULL;
-	int required = 0;
 	struct conv_attrs ca;
 
-	convert_attrs(&ca, path);
-	if (ca.drv) {
-		filter = ca.drv->clean;
-		required = ca.drv->required;
+	convert_attrs(istate, &ca, path);
+	switch (ca.attr_action) {
+	case CRLF_UNDEFINED:
+		return "";
+	case CRLF_BINARY:
+		return "-text";
+	case CRLF_TEXT:
+		return "text";
+	case CRLF_TEXT_INPUT:
+		return "text eol=lf";
+	case CRLF_TEXT_CRLF:
+		return "text eol=crlf";
+	case CRLF_AUTO:
+		return "text=auto";
+	case CRLF_AUTO_CRLF:
+		return "text=auto eol=crlf";
+	case CRLF_AUTO_INPUT:
+		return "text=auto eol=lf";
 	}
+	return "";
+}
 
-	ret |= apply_filter(path, src, len, -1, dst, filter);
-	if (!ret && required)
-		die("%s: clean filter '%s' failed", path, ca.drv->name);
+int convert_to_git(const struct index_state *istate,
+		   const char *path, const char *src, size_t len,
+		   struct strbuf *dst, int conv_flags)
+{
+	int ret = 0;
+	struct conv_attrs ca;
+
+	convert_attrs(istate, &ca, path);
+
+	ret |= apply_filter(path, src, len, -1, dst, ca.drv, CAP_CLEAN, NULL);
+	if (!ret && ca.drv && ca.drv->required)
+		die(_("%s: clean filter '%s' failed"), path, ca.drv->name);
 
 	if (ret && dst) {
 		src = dst->buf;
 		len = dst->len;
 	}
-	ca.crlf_action = input_crlf_action(ca.crlf_action, ca.eol_attr);
-	ret |= crlf_to_git(path, src, len, dst, ca.crlf_action, checksafe);
+
+	ret |= encode_to_git(path, src, len, dst, ca.working_tree_encoding, conv_flags);
 	if (ret && dst) {
 		src = dst->buf;
 		len = dst->len;
 	}
-	return ret | ident_to_git(path, src, len, dst, ca.ident);
+
+	if (!(conv_flags & CONV_EOL_KEEP_CRLF)) {
+		ret |= crlf_to_git(istate, path, src, len, dst, ca.crlf_action, conv_flags);
+		if (ret && dst) {
+			src = dst->buf;
+			len = dst->len;
+		}
+	}
+	return ret | ident_to_git(src, len, dst, ca.ident);
 }
 
-void convert_to_git_filter_fd(const char *path, int fd, struct strbuf *dst,
-			      enum safe_crlf checksafe)
+void convert_to_git_filter_fd(const struct index_state *istate,
+			      const char *path, int fd, struct strbuf *dst,
+			      int conv_flags)
 {
 	struct conv_attrs ca;
-	convert_attrs(&ca, path);
+	convert_attrs(istate, &ca, path);
 
 	assert(ca.drv);
-	assert(ca.drv->clean);
+	assert(ca.drv->clean || ca.drv->process);
 
-	if (!apply_filter(path, NULL, 0, fd, dst, ca.drv->clean))
-		die("%s: clean filter '%s' failed", path, ca.drv->name);
+	if (!apply_filter(path, NULL, 0, fd, dst, ca.drv, CAP_CLEAN, NULL))
+		die(_("%s: clean filter '%s' failed"), path, ca.drv->name);
 
-	ca.crlf_action = input_crlf_action(ca.crlf_action, ca.eol_attr);
-	crlf_to_git(path, dst->buf, dst->len, dst, ca.crlf_action, checksafe);
-	ident_to_git(path, dst->buf, dst->len, dst, ca.ident);
+	encode_to_git(path, dst->buf, dst->len, dst, ca.working_tree_encoding, conv_flags);
+	crlf_to_git(istate, path, dst->buf, dst->len, dst, ca.crlf_action, conv_flags);
+	ident_to_git(dst->buf, dst->len, dst, ca.ident);
 }
 
-static int convert_to_working_tree_internal(const char *path, const char *src,
+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)
+					    int normalizing, struct delayed_checkout *dco)
 {
 	int ret = 0, ret_filter = 0;
-	const char *filter = NULL;
-	int required = 0;
 	struct conv_attrs ca;
 
-	convert_attrs(&ca, path);
-	if (ca.drv) {
-		filter = ca.drv->smudge;
-		required = ca.drv->required;
-	}
+	convert_attrs(istate, &ca, path);
 
-	ret |= ident_to_worktree(path, src, len, dst, ca.ident);
+	ret |= ident_to_worktree(src, len, dst, ca.ident);
 	if (ret) {
 		src = dst->buf;
 		len = dst->len;
 	}
 	/*
 	 * CRLF conversion can be skipped if normalizing, unless there
-	 * is a smudge filter.  The filter might expect CRLFs.
+	 * is a smudge or process filter (even if the process filter doesn't
+	 * support smudge).  The filters might expect CRLFs.
 	 */
-	if (filter || !normalizing) {
-		ca.crlf_action = input_crlf_action(ca.crlf_action, ca.eol_attr);
-		ret |= crlf_to_worktree(path, 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_filter = apply_filter(path, src, len, -1, dst, filter);
-	if (!ret_filter && required)
-		die("%s: smudge filter %s failed", path, ca.drv->name);
+	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, dco);
+	if (!ret_filter && ca.drv && ca.drv->required)
+		die(_("%s: smudge filter %s failed"), path, ca.drv->name);
 
 	return ret | ret_filter;
 }
 
-int convert_to_working_tree(const char *path, const char *src, size_t len, struct strbuf *dst)
+int async_convert_to_working_tree(const struct index_state *istate,
+				  const char *path, const char *src,
+				  size_t len, struct strbuf *dst,
+				  void *dco)
+{
+	return convert_to_working_tree_internal(istate, path, src, len, dst, 0, dco);
+}
+
+int convert_to_working_tree(const struct index_state *istate,
+			    const char *path, const char *src,
+			    size_t len, struct strbuf *dst)
 {
-	return convert_to_working_tree_internal(path, src, len, dst, 0);
+	return convert_to_working_tree_internal(istate, path, src, len, dst, 0, NULL);
 }
 
-int renormalize_buffer(const char *path, const char *src, size_t len, struct strbuf *dst)
+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(path, src, len, dst, 1);
+	int ret = convert_to_working_tree_internal(istate, path, src, len, dst, 1, NULL);
 	if (ret) {
 		src = dst->buf;
 		len = dst->len;
 	}
-	return ret | convert_to_git(path, src, len, dst, SAFE_CRLF_FALSE);
+	return ret | convert_to_git(istate, path, src, len, dst, CONV_EOL_RENORMALIZE);
 }
 
 /*****************************************************************
@@ -1161,7 +1785,7 @@ struct ident_filter {
 	struct stream_filter filter;
 	struct strbuf left;
 	int state;
-	char ident[45]; /* ": x40 $" */
+	char ident[GIT_MAX_HEXSZ + 5]; /* ": x40 $" */
 };
 
 static int is_foreign_ident(const char *str)
@@ -1205,8 +1829,9 @@ static int ident_filter_fn(struct stream_filter *filter,
 		switch (ident->state) {
 		default:
 			strbuf_add(&ident->left, head, ident->state);
+			/* fallthrough */
 		case IDENT_SKIPPING:
-			/* fallthru */
+			/* fallthrough */
 		case IDENT_DRAINING:
 			ident_drain(ident, &output, osize_p);
 		}
@@ -1285,11 +1910,12 @@ static struct stream_filter_vtbl ident_vtbl = {
 	ident_free_fn,
 };
 
-static struct stream_filter *ident_filter(const unsigned char *sha1)
+static struct stream_filter *ident_filter(const struct object_id *oid)
 {
 	struct ident_filter *ident = xmalloc(sizeof(*ident));
 
-	sprintf(ident->ident, ": %s $", sha1_to_hex(sha1));
+	xsnprintf(ident->ident, sizeof(ident->ident),
+		  ": %s $", oid_to_hex(oid));
 	strbuf_init(&ident->left, 0);
 	ident->filter.vtbl = &ident_vtbl;
 	ident->state = 0;
@@ -1304,29 +1930,30 @@ static struct stream_filter *ident_filter(const unsigned char *sha1)
  * Note that you would be crazy to set CRLF, smuge/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 char *path, const unsigned char *sha1)
+struct stream_filter *get_stream_filter(const struct index_state *istate,
+					const char *path,
+					const struct object_id *oid)
 {
 	struct conv_attrs ca;
-	enum crlf_action crlf_action;
 	struct stream_filter *filter = NULL;
 
-	convert_attrs(&ca, path);
-
-	if (ca.drv && (ca.drv->smudge || ca.drv->clean))
-		return filter;
+	convert_attrs(istate, &ca, path);
+	if (ca.drv && (ca.drv->process || ca.drv->smudge || ca.drv->clean))
+		return NULL;
 
-	if (ca.ident)
-		filter = ident_filter(sha1);
+	if (ca.working_tree_encoding)
+		return NULL;
 
-	crlf_action = input_crlf_action(ca.crlf_action, ca.eol_attr);
+	if (ca.crlf_action == CRLF_AUTO || ca.crlf_action == CRLF_AUTO_CRLF)
+		return NULL;
 
-	if ((crlf_action == CRLF_BINARY) || (crlf_action == CRLF_INPUT) ||
-	    (crlf_action == CRLF_GUESS && auto_crlf == AUTO_CRLF_FALSE))
-		filter = cascade_filter(filter, &null_filter_singleton);
+	if (ca.ident)
+		filter = ident_filter(oid);
 
-	else if (output_eol(crlf_action) == EOL_CRLF &&
-		 !(crlf_action == CRLF_AUTO || crlf_action == CRLF_GUESS))
+	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;
 }