Merge branch 'rs/archive'

* rs/archive:
  archive - leakfix for format_subst()
  Define NO_MEMMEM on Darwin as it lacks the function
  archive: rename attribute specfile to export-subst
  archive: specfile syntax change: "$Format:%PLCHLDR$" instead of just "%PLCHLDR" (take 2)
  add memmem()
  Remove unused function convert_sha1_file()
  archive: specfile support (--pretty=format: in archive files)
  Export format_commit_message()

13 files changed, 197 insertions, 23 deletions

diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt
index 46f9d591a..d0e951ee6 100644
--- a/Documentation/gitattributes.txt
+++ b/Documentation/gitattributes.txt
@@ -421,6 +421,23 @@ frotz	unspecified
 ----------------------------------------------------------------
 
 
+Creating an archive
+~~~~~~~~~~~~~~~~~~~
+
+`export-subst`
+^^^^^^^^^^^^^^
+
+If the attribute `export-subst` is set for a file then git will expand
+several placeholders when adding this file to an archive.  The
+expansion depends on the availability of a commit ID, i.e. if
+gitlink:git-archive[1] has been given a tree instead of a commit or a
+tag then no replacement will be done.  The placeholders are the same
+as those for the option `--pretty=format:` of gitlink:git-log[1],
+except that they need to be wrapped like this: `$Format:PLACEHOLDERS$`
+in the file.  E.g. the string `$Format:%H$` will be replaced by the
+commit hash.
+
+
 GIT
 ---
 Part of the gitlink:git[7] suite
diff --git a/Makefile b/Makefile
index dace2112f..61053aed5 100644
--- a/Makefile
+++ b/Makefile
@@ -28,6 +28,8 @@ all::
 #
 # Define NO_STRCASESTR if you don't have strcasestr.
 #
+# Define NO_MEMMEM if you don't have memmem.
+#
 # Define NO_STRLCPY if you don't have strlcpy.
 #
 # Define NO_STRTOUMAX if you don't have strtoumax in the C library.
@@ -396,12 +398,14 @@ ifeq ($(uname_S),Darwin)
 	NEEDS_LIBICONV = YesPlease
 	OLD_ICONV = UnfortunatelyYes
 	NO_STRLCPY = YesPlease
+	NO_MEMMEM = YesPlease
 endif
 ifeq ($(uname_S),SunOS)
 	NEEDS_SOCKET = YesPlease
 	NEEDS_NSL = YesPlease
 	SHELL_PATH = /bin/bash
 	NO_STRCASESTR = YesPlease
+	NO_MEMMEM = YesPlease
 	NO_HSTRERROR = YesPlease
 	ifeq ($(uname_R),5.8)
 		NEEDS_LIBICONV = YesPlease
@@ -424,6 +428,7 @@ ifeq ($(uname_O),Cygwin)
 	NO_D_TYPE_IN_DIRENT = YesPlease
 	NO_D_INO_IN_DIRENT = YesPlease
 	NO_STRCASESTR = YesPlease
+	NO_MEMMEM = YesPlease
 	NO_SYMLINK_HEAD = YesPlease
 	NEEDS_LIBICONV = YesPlease
 	NO_FAST_WORKING_DIRECTORY = UnfortunatelyYes
@@ -442,6 +447,7 @@ ifeq ($(uname_S),FreeBSD)
 endif
 ifeq ($(uname_S),OpenBSD)
 	NO_STRCASESTR = YesPlease
+	NO_MEMMEM = YesPlease
 	NEEDS_LIBICONV = YesPlease
 	BASIC_CFLAGS += -I/usr/local/include
 	BASIC_LDFLAGS += -L/usr/local/lib
@@ -456,6 +462,7 @@ ifeq ($(uname_S),NetBSD)
 endif
 ifeq ($(uname_S),AIX)
 	NO_STRCASESTR=YesPlease
+	NO_MEMMEM = YesPlease
 	NO_STRLCPY = YesPlease
 	NEEDS_LIBICONV=YesPlease
 endif
@@ -467,6 +474,7 @@ ifeq ($(uname_S),IRIX64)
 	NO_IPV6=YesPlease
 	NO_SETENV=YesPlease
 	NO_STRCASESTR=YesPlease
+	NO_MEMMEM = YesPlease
 	NO_STRLCPY = YesPlease
 	NO_SOCKADDR_STORAGE=YesPlease
 	SHELL_PATH=/usr/gnu/bin/bash
@@ -661,6 +669,10 @@ ifdef NO_HSTRERROR
 	COMPAT_CFLAGS += -DNO_HSTRERROR
 	COMPAT_OBJS += compat/hstrerror.o
 endif
+ifdef NO_MEMMEM
+	COMPAT_CFLAGS += -DNO_MEMMEM
+	COMPAT_OBJS += compat/memmem.o
+endif
 
 ifeq ($(TCLTK_PATH),)
 NO_TCLTK=NoThanks
diff --git a/archive-tar.c b/archive-tar.c
index 66fe3e375..c0d95dab0 100644
--- a/archive-tar.c
+++ b/archive-tar.c
@@ -17,6 +17,7 @@ static unsigned long offset;
 static time_t archive_time;
 static int tar_umask = 002;
 static int verbose;
+static const struct commit *commit;
 
 /* writes out the whole block, but only if it is full */
 static void write_if_needed(void)
@@ -285,7 +286,8 @@ static int write_tar_entry(const unsigned char *sha1,
 		buffer = NULL;
 		size = 0;
 	} else {
-		buffer = convert_sha1_file(path.buf, sha1, mode, &type, &size);
+		buffer = sha1_file_to_archive(path.buf, sha1, mode, &type,
+		                              &size, commit);
 		if (!buffer)
 			die("cannot read %s", sha1_to_hex(sha1));
 	}
@@ -304,6 +306,7 @@ int write_tar_archive(struct archiver_args *args)
 
 	archive_time = args->time;
 	verbose = args->verbose;
+	commit = args->commit;
 
 	if (args->commit_sha1)
 		write_global_extended_header(args->commit_sha1);
diff --git a/archive-zip.c b/archive-zip.c
index 444e1623d..f63dff383 100644
--- a/archive-zip.c
+++ b/archive-zip.c
@@ -12,6 +12,7 @@
 static int verbose;
 static int zip_date;
 static int zip_time;
+static const struct commit *commit;
 
 static unsigned char *zip_dir;
 static unsigned int zip_dir_size;
@@ -195,7 +196,8 @@ static int write_zip_entry(const unsigned char *sha1,
 		if (S_ISREG(mode) && zlib_compression_level != 0)
 			method = 8;
 		result = 0;
-		buffer = convert_sha1_file(path, sha1, mode, &type, &size);
+		buffer = sha1_file_to_archive(path, sha1, mode, &type, &size,
+		                              commit);
 		if (!buffer)
 			die("cannot read %s", sha1_to_hex(sha1));
 		crc = crc32(crc, buffer, size);
@@ -316,6 +318,7 @@ int write_zip_archive(struct archiver_args *args)
 	zip_dir = xmalloc(ZIP_DIRECTORY_MIN_SIZE);
 	zip_dir_size = ZIP_DIRECTORY_MIN_SIZE;
 	verbose = args->verbose;
+	commit = args->commit;
 
 	if (args->base && plen > 0 && args->base[plen - 1] == '/') {
 		char *base = xstrdup(args->base);
diff --git a/archive.h b/archive.h
index 6838dc788..5791e657e 100644
--- a/archive.h
+++ b/archive.h
@@ -8,6 +8,7 @@ struct archiver_args {
 	const char *base;
 	struct tree *tree;
 	const unsigned char *commit_sha1;
+	const struct commit *commit;
 	time_t time;
 	const char **pathspec;
 	unsigned int verbose : 1;
@@ -42,4 +43,6 @@ extern int write_tar_archive(struct archiver_args *);
 extern int write_zip_archive(struct archiver_args *);
 extern void *parse_extra_zip_args(int argc, const char **argv);
 
+extern void *sha1_file_to_archive(const char *path, const unsigned char *sha1, unsigned int mode, enum object_type *type, unsigned long *size, const struct commit *commit);
+
 #endif	/* ARCHIVE_H */
diff --git a/builtin-archive.c b/builtin-archive.c
index 187491bc1..a90c65ce5 100644
--- a/builtin-archive.c
+++ b/builtin-archive.c
@@ -10,6 +10,7 @@
 #include "exec_cmd.h"
 #include "pkt-line.h"
 #include "sideband.h"
+#include "attr.h"
 
 static const char archive_usage[] = \
 "git-archive --format=<fmt> [--prefix=<prefix>/] [--verbose] [<extra>] <tree-ish> [path...]";
@@ -80,6 +81,100 @@ static int run_remote_archiver(const char *remote, int argc,
 	return !!rv;
 }
 
+static void *format_subst(const struct commit *commit, const char *format,
+                          unsigned long *sizep)
+{
+	unsigned long len = *sizep, result_len = 0;
+	const char *a = format;
+	char *result = NULL;
+
+	for (;;) {
+		const char *b, *c;
+		char *fmt, *formatted = NULL;
+		unsigned long a_len, fmt_len, formatted_len, allocated = 0;
+
+		b = memmem(a, len, "$Format:", 8);
+		if (!b || a + len < b + 9)
+			break;
+		c = memchr(b + 8, '$', len - 8);
+		if (!c)
+			break;
+
+		a_len = b - a;
+		fmt_len = c - b - 8;
+		fmt = xmalloc(fmt_len + 1);
+		memcpy(fmt, b + 8, fmt_len);
+		fmt[fmt_len] = '\0';
+
+		formatted_len = format_commit_message(commit, fmt, &formatted,
+		                                      &allocated);
+		free(fmt);
+		result = xrealloc(result, result_len + a_len + formatted_len);
+		memcpy(result + result_len, a, a_len);
+		memcpy(result + result_len + a_len, formatted, formatted_len);
+		result_len += a_len + formatted_len;
+		len -= c + 1 - a;
+		a = c + 1;
+	}
+
+	if (result && len) {
+		result = xrealloc(result, result_len + len);
+		memcpy(result + result_len, a, len);
+		result_len += len;
+	}
+
+	*sizep = result_len;
+
+	return result;
+}
+
+static void *convert_to_archive(const char *path,
+                                const void *src, unsigned long *sizep,
+                                const struct commit *commit)
+{
+	static struct git_attr *attr_export_subst;
+	struct git_attr_check check[1];
+
+	if (!commit)
+		return NULL;
+
+        if (!attr_export_subst)
+                attr_export_subst = git_attr("export-subst", 12);
+
+	check[0].attr = attr_export_subst;
+	if (git_checkattr(path, ARRAY_SIZE(check), check))
+		return NULL;
+	if (!ATTR_TRUE(check[0].value))
+		return NULL;
+
+	return format_subst(commit, src, sizep);
+}
+
+void *sha1_file_to_archive(const char *path, const unsigned char *sha1,
+                           unsigned int mode, enum object_type *type,
+                           unsigned long *size,
+                           const struct commit *commit)
+{
+	void *buffer, *converted;
+
+	buffer = read_sha1_file(sha1, type, size);
+	if (buffer && S_ISREG(mode)) {
+		converted = convert_to_working_tree(path, buffer, size);
+		if (converted) {
+			free(buffer);
+			buffer = converted;
+		}
+
+		converted = convert_to_archive(path, buffer, size, commit);
+		if (converted) {
+			free(buffer);
+			buffer = converted;
+		}
+	}
+
+	return buffer;
+}
+
 static int init_archiver(const char *name, struct archiver *ar)
 {
 	int rv = -1, i;
@@ -109,7 +204,7 @@ void parse_treeish_arg(const char **argv, struct archiver_args *ar_args,
 	const unsigned char *commit_sha1;
 	time_t archive_time;
 	struct tree *tree;
-	struct commit *commit;
+	const struct commit *commit;
 	unsigned char sha1[20];
 
 	if (get_sha1(name, sha1))
@@ -142,6 +237,7 @@ void parse_treeish_arg(const char **argv, struct archiver_args *ar_args,
 	}
 	ar_args->tree = tree;
 	ar_args->commit_sha1 = commit_sha1;
+	ar_args->commit = commit;
 	ar_args->time = archive_time;
 }
 
diff --git a/cache.h b/cache.h
index 70abbd59b..493983cba 100644
--- a/cache.h
+++ b/cache.h
@@ -592,7 +592,6 @@ extern void trace_argv_printf(const char **argv, int count, const char *format,
 /* convert.c */
 extern char *convert_to_git(const char *path, const char *src, unsigned long *sizep);
 extern char *convert_to_working_tree(const char *path, const char *src, unsigned long *sizep);
-extern void *convert_sha1_file(const char *path, const unsigned char *sha1, unsigned int mode, enum object_type *type, unsigned long *size);
 
 /* diff.c */
 extern int diff_auto_refresh_index;
diff --git a/commit.c b/commit.c
index dc5a0643f..99f65cee0 100644
--- a/commit.c
+++ b/commit.c
@@ -787,8 +787,8 @@ static void fill_person(struct interp *table, const char *msg, int len)
 	interp_set_entry(table, 6, show_date(date, tz, DATE_ISO8601));
 }
 
-static long format_commit_message(const struct commit *commit,
-		const char *msg, char **buf_p, unsigned long *space_p)
+long format_commit_message(const struct commit *commit, const void *format,
+                           char **buf_p, unsigned long *space_p)
 {
 	struct interp table[] = {
 		{ "%H" },	/* commit hash */
@@ -843,6 +843,7 @@ static long format_commit_message(const struct commit *commit,
 	char parents[1024];
 	int i;
 	enum { HEADER, SUBJECT, BODY } state;
+	const char *msg = commit->buffer;
 
 	if (ILEFT_RIGHT + 1 != ARRAY_SIZE(table))
 		die("invalid interp table!");
@@ -924,7 +925,7 @@ static long format_commit_message(const struct commit *commit,
 		char *buf = *buf_p;
 		unsigned long space = *space_p;
 
-		space = interpolate(buf, space, user_format,
+		space = interpolate(buf, space, format,
 				    table, ARRAY_SIZE(table));
 		if (!space)
 			break;
@@ -1165,7 +1166,7 @@ unsigned long pretty_print_commit(enum cmit_fmt fmt,
 	char *buf;
 
 	if (fmt == CMIT_FMT_USERFORMAT)
-		return format_commit_message(commit, msg, buf_p, space_p);
+		return format_commit_message(commit, user_format, buf_p, space_p);
 
 	encoding = (git_log_output_encoding
 		    ? git_log_output_encoding
diff --git a/commit.h b/commit.h
index 467872eec..a8d76616d 100644
--- a/commit.h
+++ b/commit.h
@@ -61,6 +61,7 @@ enum cmit_fmt {
 };
 
 extern enum cmit_fmt get_commit_format(const char *arg);
+extern long format_commit_message(const struct commit *commit, const void *template, char **buf_p, unsigned long *space_p);
 extern unsigned long pretty_print_commit(enum cmit_fmt fmt, const struct commit *, unsigned long len, char **buf_p, unsigned long *space_p, int abbrev, const char *subject, const char *after_subject, enum date_mode dmode);
 
 /** Removes the first commit from a list sorted by date, and adds all
diff --git a/compat/memmem.c b/compat/memmem.c
new file mode 100644
index 000000000..cd0d87736
--- /dev/null
+++ b/compat/memmem.c
@@ -0,0 +1,29 @@
+#include "../git-compat-util.h"
+
+void *gitmemmem(const void *haystack, size_t haystack_len,
+                const void *needle, size_t needle_len)
+{
+	const char *begin = haystack;
+	const char *last_possible = begin + haystack_len - needle_len;
+
+	/*
+	 * The first occurrence of the empty string is deemed to occur at
+	 * the beginning of the string.
+	 */
+	if (needle_len == 0)
+		return (void *)begin;
+
+	/*
+	 * Sanity check, otherwise the loop might search through the whole
+	 * memory.
+	 */
+	if (haystack_len < needle_len)
+		return NULL;
+
+	for (; begin <= last_possible; begin++) {
+		if (!memcmp(begin, needle, needle_len))
+			return (void *)begin;
+	}
+
+	return NULL;
+}
diff --git a/convert.c b/convert.c
index 21908b103..d77c8eb8b 100644
--- a/convert.c
+++ b/convert.c
@@ -687,18 +687,3 @@ char *convert_to_working_tree(const char *path, const char *src, unsigned long *
 
 	return buf;
 }
-
-void *convert_sha1_file(const char *path, const unsigned char *sha1,
-                        unsigned int mode, enum object_type *type,
-                        unsigned long *size)
-{
-	void *buffer = read_sha1_file(sha1, type, size);
-	if (S_ISREG(mode) && buffer) {
-		void *converted = convert_to_working_tree(path, buffer, size);
-		if (converted) {
-			free(buffer);
-			buffer = converted;
-		}
-	}
-	return buffer;
-}
diff --git a/git-compat-util.h b/git-compat-util.h
index ca0a597a2..1bfbdeb94 100644
--- a/git-compat-util.h
+++ b/git-compat-util.h
@@ -172,6 +172,12 @@ extern uintmax_t gitstrtoumax(const char *, char **, int);
 extern const char *githstrerror(int herror);
 #endif
 
+#ifdef NO_MEMMEM
+#define memmem gitmemmem
+void *gitmemmem(const void *haystack, size_t haystacklen,
+                const void *needle, size_t needlelen);
+#endif
+
 extern void release_pack_memory(size_t, int);
 
 static inline char* xstrdup(const char *str)
diff --git a/t/t5000-tar-tree.sh b/t/t5000-tar-tree.sh
index 1a4c53a03..42e28ab75 100755
--- a/t/t5000-tar-tree.sh
+++ b/t/t5000-tar-tree.sh
@@ -28,12 +28,15 @@ commit id embedding:
 TAR=${TAR:-tar}
 UNZIP=${UNZIP:-unzip}
 
+SUBSTFORMAT=%H%n
+
 test_expect_success \
     'populate workdir' \
     'mkdir a b c &&
      echo simple textfile >a/a &&
      mkdir a/bin &&
      cp /bin/sh a/bin &&
+     printf "A\$Format:%s\$O" "$SUBSTFORMAT" >a/substfile &&
      ln -s a a/l1 &&
      (p=long_path_to_a_file && cd a &&
       for depth in 1 2 3 4 5; do mkdir $p && cd $p; done &&
@@ -105,6 +108,22 @@ test_expect_success \
     'diff -r a c/prefix/a'
 
 test_expect_success \
+    'create an archive with a substfile' \
+    'echo substfile export-subst >a/.gitattributes &&
+     git archive HEAD >f.tar &&
+     rm a/.gitattributes'
+
+test_expect_success \
+    'extract substfile' \
+    '(mkdir f && cd f && $TAR xf -) <f.tar'
+
+test_expect_success \
+     'validate substfile contents' \
+     'git log --max-count=1 "--pretty=format:A${SUBSTFORMAT}O" HEAD \
+      >f/a/substfile.expected &&
+      diff f/a/substfile.expected f/a/substfile'
+
+test_expect_success \
     'git archive --format=zip' \
     'git archive --format=zip HEAD >d.zip'