convert: add 'working-tree-encoding' attribute

Git recognizes files encoded with ASCII or one of its supersets (e.g.
UTF-8 or ISO-8859-1) as text files. All other encodings are usually
interpreted as binary and consequently built-in Git text processing
tools (e.g. 'git diff') as well as most Git web front ends do not
visualize the content.

Add an attribute to tell Git what encoding the user has defined for a
given file. If the content is added to the index, then Git reencodes
the content to a canonical UTF-8 representation. On checkout Git will
reverse this operation.

Signed-off-by: Lars Schneider <larsxschneider@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 112 insertions, 1 deletions

diff --git a/convert.c b/convert.c
index b976eb968c..21d5cb60da 100644
--- a/convert.c
+++ b/convert.c
@@ -7,6 +7,7 @@
 #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.
@@ -265,6 +266,78 @@ static int will_convert_lf_to_crlf(size_t len, struct text_stat *stats,
 
 }
 
+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;
+	int 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;
+
+	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;
+		}
+	}
+
+	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;
+	int 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,
@@ -978,6 +1051,24 @@ static int ident_to_worktree(const char *path, const char *src, size_t len,
 	return 1;
 }
 
+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;
@@ -1033,6 +1124,7 @@ struct conv_attrs {
 	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 void convert_attrs(struct conv_attrs *ca, const char *path)
@@ -1041,7 +1133,8 @@ static void convert_attrs(struct conv_attrs *ca, const char *path)
 
 	if (!check) {
 		check = attr_check_initl("crlf", "ident", "filter",
-					 "eol", "text", NULL);
+					 "eol", "text", "working-tree-encoding",
+					 NULL);
 		user_convert_tail = &user_convert;
 		git_config(read_convert_config, NULL);
 	}
@@ -1064,6 +1157,7 @@ static void convert_attrs(struct conv_attrs *ca, const char *path)
 			else if (eol_attr == EOL_CRLF)
 				ca->crlf_action = CRLF_TEXT_CRLF;
 		}
+		ca->working_tree_encoding = git_path_check_encoding(ccheck + 5);
 	} else {
 		ca->drv = NULL;
 		ca->crlf_action = CRLF_UNDEFINED;
@@ -1144,6 +1238,13 @@ int convert_to_git(const struct index_state *istate,
 		src = dst->buf;
 		len = dst->len;
 	}
+
+	ret |= encode_to_git(path, src, len, dst, ca.working_tree_encoding, conv_flags);
+	if (ret && dst) {
+		src = dst->buf;
+		len = dst->len;
+	}
+
 	if (!(conv_flags & CONV_EOL_KEEP_CRLF)) {
 		ret |= crlf_to_git(istate, path, src, len, dst, ca.crlf_action, conv_flags);
 		if (ret && dst) {
@@ -1167,6 +1268,7 @@ void convert_to_git_filter_fd(const struct index_state *istate,
 	if (!apply_filter(path, NULL, 0, fd, dst, ca.drv, CAP_CLEAN, NULL))
 		die("%s: clean filter '%s' failed", path, ca.drv->name);
 
+	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(path, dst->buf, dst->len, dst, ca.ident);
 }
@@ -1198,6 +1300,12 @@ static int convert_to_working_tree_internal(const char *path, const char *src,
 		}
 	}
 
+	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)
@@ -1664,6 +1772,9 @@ struct stream_filter *get_stream_filter(const char *path, const unsigned char *s
 	if (ca.drv && (ca.drv->process || ca.drv->smudge || ca.drv->clean))
 		return NULL;
 
+	if (ca.working_tree_encoding)
+		return NULL;
+
 	if (ca.crlf_action == CRLF_AUTO || ca.crlf_action == CRLF_AUTO_CRLF)
 		return NULL;