convert: add 'working-tree-encoding' attribute

larsxschneider · gitster · commit 107642fe2661 · 2018-04-16T11:40:56.000+09:00
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 &lt;larsxschneider@gmail.com&gt;
Signed-off-by: Junio C Hamano &lt;gitster@pobox.com&gt;
diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt
@@ -272,6 +272,86 @@ few exceptions.  Even though...
   catch potential problems early, safety triggers.
 
 
+`working-tree-encoding`
+^^^^^^^^^^^^^^^^^^^^^^^
+
+Git recognizes files encoded in ASCII or one of its supersets (e.g.
+UTF-8, ISO-8859-1, ...) as text files. Files encoded in certain other
+encodings (e.g. UTF-16) are 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 contents of these files by default.
+
+In these cases you can tell Git the encoding of a file in the working
+directory with the `working-tree-encoding` attribute. If a file with this
+attribute is added to Git, then Git reencodes the content from the
+specified encoding to UTF-8. Finally, Git stores the UTF-8 encoded
+content in its internal data structure (called "the index"). On checkout
+the content is reencoded back to the specified encoding.
+
+Please note that using the `working-tree-encoding` attribute may have a
+number of pitfalls:
+
+- Alternative Git implementations (e.g. JGit or libgit2) and older Git
+  versions (as of March 2018) do not support the `working-tree-encoding`
+  attribute. If you decide to use the `working-tree-encoding` attribute
+  in your repository, then it is strongly recommended to ensure that all
+  clients working with the repository support it.
+
+  For example, Microsoft Visual Studio resources files (`*.rc`) or
+  PowerShell script files (`*.ps1`) are sometimes encoded in UTF-16.
+  If you declare `*.ps1` as files as UTF-16 and you add `foo.ps1` with
+  a `working-tree-encoding` enabled Git client, then `foo.ps1` will be
+  stored as UTF-8 internally. A client without `working-tree-encoding`
+  support will checkout `foo.ps1` as UTF-8 encoded file. This will
+  typically cause trouble for the users of this file.
+
+  If a Git client, that does not support the `working-tree-encoding`
+  attribute, adds a new file `bar.ps1`, then `bar.ps1` will be
+  stored "as-is" internally (in this example probably as UTF-16).
+  A client with `working-tree-encoding` support will interpret the
+  internal contents as UTF-8 and try to convert it to UTF-16 on checkout.
+  That operation will fail and cause an error.
+
+- Reencoding content requires resources that might slow down certain
+  Git operations (e.g 'git checkout' or 'git add').
+
+Use the `working-tree-encoding` attribute only if you cannot store a file
+in UTF-8 encoding and if you want Git to be able to process the content
+as text.
+
+As an example, use the following attributes if your '*.ps1' files are
+UTF-16 encoded with byte order mark (BOM) and you want Git to perform
+automatic line ending conversion based on your platform.
+
+------------------------
+*.ps1		text working-tree-encoding=UTF-16
+------------------------
+
+Use the following attributes if your '*.ps1' files are UTF-16 little
+endian encoded without BOM and you want Git to use Windows line endings
+in the working directory. Please note, it is highly recommended to
+explicitly define the line endings with `eol` if the `working-tree-encoding`
+attribute is used to avoid ambiguity.
+
+------------------------
+*.ps1		text working-tree-encoding=UTF-16LE eol=CRLF
+------------------------
+
+You can get a list of all available encodings on your platform with the
+following command:
+
+------------------------
+iconv --list
+------------------------
+
+If you do not know the encoding of a file, then you can use the `file`
+command to guess the encoding:
+
+------------------------
+file foo.ps1
+------------------------
+
+
 `ident`
 ^^^^^^^
 
diff --git 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;
 
diff --git a/convert.h b/convert.h
@@ -12,6 +12,7 @@ struct index_state;
 #define CONV_EOL_RNDTRP_WARN  (1<<1) /* Warn if CRLF to LF to CRLF is different */
 #define CONV_EOL_RENORMALIZE  (1<<2) /* Convert CRLF to LF */
 #define CONV_EOL_KEEP_CRLF    (1<<3) /* Keep CRLF line endings as is */
+#define CONV_WRITE_OBJECT     (1<<4) /* Content is written to the index */
 
 extern int global_conv_flags_eol;
 
diff --git a/sha1_file.c b/sha1_file.c
@@ -138,7 +138,7 @@ static int get_conv_flags(unsigned flags)
 	if (flags & HASH_RENORMALIZE)
 		return CONV_EOL_RENORMALIZE;
 	else if (flags & HASH_WRITE_OBJECT)
-	  return global_conv_flags_eol;
+		return global_conv_flags_eol | CONV_WRITE_OBJECT;
 	else
 		return 0;
 }
diff --git a/t/t0028-working-tree-encoding.sh b/t/t0028-working-tree-encoding.sh

Original file line number	Diff line number	Diff line change
`@@ -138,7 +138,7 @@ static int get_conv_flags(unsigned flags)`
`138`	`138`	`if (flags & HASH_RENORMALIZE)`
`139`	`139`	`return CONV_EOL_RENORMALIZE;`
`140`	`140`	`else if (flags & HASH_WRITE_OBJECT)`
`141`		`- return global_conv_flags_eol;`
	`141`	`+ return global_conv_flags_eol \| CONV_WRITE_OBJECT;`
`142`	`142`	`else`
`143`	`143`	`return 0;`
`144`	`144`	`}`