From 4f5de755a7931c5e15f4e7fc3d501588aa9ff88d Mon Sep 17 00:00:00 2001
From: Jonathan Nieder <jrnieder@gmail.com>
Date: Sat, 20 Nov 2010 13:25:28 -0600
Subject: vcs-svn: introduce repo_read_path to check the content at a path

The repo_tree structure remembers, for each path in each revision, a
mode (regular file, executable, symlink, or directory) and content
(blob mark or directory structure).  Maintaining a second copy of all
this information when it's already in the target repository is
wasteful, it does not persist between svn-fe invocations, and most
importantly, there is no convenient way to transfer it from one
machine to another.  So it would be nice to get rid of it.

As a first step, let's change the repo_tree API to match fast-import's
read commands more closely.  Currently to read the mode for a path,
one uses

	repo_modify_path(path, new_mode, new_content);

which changes the mode and content as a side effect.  There is no
function to read the content at a path; add one.

Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: David Barr <david.barr@cordelta.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
 vcs-svn/repo_tree.c | 12 +++++++++++-
 vcs-svn/repo_tree.h |  1 +
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/vcs-svn/repo_tree.c b/vcs-svn/repo_tree.c
index 491f0135a7..8763de5c29 100644
--- a/vcs-svn/repo_tree.c
+++ b/vcs-svn/repo_tree.c
@@ -87,7 +87,8 @@ static struct repo_dir *repo_clone_dir(struct repo_dir *orig_dir)
 	return dir_pointer(new_o);
 }
 
-static struct repo_dirent *repo_read_dirent(uint32_t revision, uint32_t *path)
+static struct repo_dirent *repo_read_dirent(uint32_t revision,
+					    const uint32_t *path)
 {
 	uint32_t name = 0;
 	struct repo_dirent *key = dent_pointer(dent_alloc(1));
@@ -157,6 +158,15 @@ static void repo_write_dirent(uint32_t *path, uint32_t mode,
 		dent_remove(&dir_pointer(parent_dir_o)->entries, dent);
 }
 
+uint32_t repo_read_path(const uint32_t *path)
+{
+	uint32_t content_offset = 0;
+	struct repo_dirent *dent = repo_read_dirent(active_commit, path);
+	if (dent != NULL)
+		content_offset = dent->content_offset;
+	return content_offset;
+}
+
 uint32_t repo_copy(uint32_t revision, uint32_t *src, uint32_t *dst)
 {
 	uint32_t mode = 0, content_offset = 0;
diff --git a/vcs-svn/repo_tree.h b/vcs-svn/repo_tree.h
index 68baeb582f..3202bbeffe 100644
--- a/vcs-svn/repo_tree.h
+++ b/vcs-svn/repo_tree.h
@@ -15,6 +15,7 @@ uint32_t next_blob_mark(void);
 uint32_t repo_copy(uint32_t revision, uint32_t *src, uint32_t *dst);
 void repo_add(uint32_t *path, uint32_t mode, uint32_t blob_mark);
 uint32_t repo_modify_path(uint32_t *path, uint32_t mode, uint32_t blob_mark);
+uint32_t repo_read_path(const uint32_t *path);
 void repo_delete(uint32_t *path);
 void repo_commit(uint32_t revision, uint32_t author, char *log, uint32_t uuid,
 		 uint32_t url, long unsigned timestamp);
-- 
cgit v1.2.1


From 5a38b186d3ac5840d6ae78511d6dccab8367f242 Mon Sep 17 00:00:00 2001
From: Jonathan Nieder <jrnieder@gmail.com>
Date: Fri, 10 Dec 2010 04:28:06 -0600
Subject: vcs-svn: handle_node: use repo_read_path

svn-fe processes each commit in two stages: first decide on the
correct content for all paths and export the relevant blobs, then
export a commit with the result.

But we can keep less state and simplify svn-fe a great deal by
exporting the commit in one step: use 'inline' blobs for each path and
remember nothing.  This way, the repo_tree structure could be
eliminated, and we would get support for incremental imports 'for
free'.

Reorganize handle_node along these lines.  This is just a code
cleanup; the changes in repo_tree and handle_revision will come later.

[db: backported to apply without text delta support]

Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: David Barr <david.barr@cordelta.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
 vcs-svn/svndump.c | 33 +++++++++++++++++++++++----------
 1 file changed, 23 insertions(+), 10 deletions(-)

diff --git a/vcs-svn/svndump.c b/vcs-svn/svndump.c
index ee7c0bb2ea..f07376f964 100644
--- a/vcs-svn/svndump.c
+++ b/vcs-svn/svndump.c
@@ -201,13 +201,14 @@ static void handle_node(void)
 	uint32_t mark = 0;
 	const uint32_t type = node_ctx.type;
 	const int have_props = node_ctx.propLength != LENGTH_UNKNOWN;
+	const int have_text = node_ctx.textLength != LENGTH_UNKNOWN;
 
 	if (node_ctx.text_delta)
 		die("text deltas not supported");
-	if (node_ctx.textLength != LENGTH_UNKNOWN)
+	if (have_text)
 		mark = next_blob_mark();
 	if (node_ctx.action == NODEACT_DELETE) {
-		if (mark || have_props || node_ctx.srcRev)
+		if (have_text || have_props || node_ctx.srcRev)
 			die("invalid dump: deletion node has "
 				"copyfrom info, text, or properties");
 		return repo_delete(node_ctx.dst);
@@ -221,13 +222,20 @@ static void handle_node(void)
 		if (node_ctx.action == NODEACT_ADD)
 			node_ctx.action = NODEACT_CHANGE;
 	}
-	if (mark && type == REPO_MODE_DIR)
+	if (have_text && type == REPO_MODE_DIR)
 		die("invalid dump: directories cannot have text attached");
+
+	/*
+	 * Decide on the new content (mark) and mode (node_ctx.type).
+	 */
 	if (node_ctx.action == NODEACT_CHANGE && !~*node_ctx.dst) {
 		if (type != REPO_MODE_DIR)
 			die("invalid dump: root of tree is not a regular file");
 	} else if (node_ctx.action == NODEACT_CHANGE) {
-		uint32_t mode = repo_modify_path(node_ctx.dst, 0, mark);
+		uint32_t mode;
+		if (!have_text)
+			mark = repo_read_path(node_ctx.dst);
+		mode = repo_modify_path(node_ctx.dst, 0, 0);
 		if (!mode)
 			die("invalid dump: path to be modified is missing");
 		if (mode == REPO_MODE_DIR && type != REPO_MODE_DIR)
@@ -236,22 +244,27 @@ static void handle_node(void)
 			die("invalid dump: cannot modify a file into a directory");
 		node_ctx.type = mode;
 	} else if (node_ctx.action == NODEACT_ADD) {
-		if (!mark && type != REPO_MODE_DIR)
+		if (!have_text && type != REPO_MODE_DIR)
 			die("invalid dump: adds node without text");
-		repo_add(node_ctx.dst, type, mark);
 	} else {
 		die("invalid dump: Node-path block lacks Node-action");
 	}
+
+	/*
+	 * Adjust mode to reflect properties.
+	 */
 	if (have_props) {
-		const uint32_t old_mode = node_ctx.type;
 		if (!node_ctx.prop_delta)
 			node_ctx.type = type;
 		if (node_ctx.propLength)
 			read_props();
-		if (node_ctx.type != old_mode)
-			repo_modify_path(node_ctx.dst, node_ctx.type, mark);
 	}
-	if (mark)
+
+	/*
+	 * Save the result.
+	 */
+	repo_add(node_ctx.dst, node_ctx.type, mark);
+	if (have_text)
 		fast_export_blob(node_ctx.type, mark,
 				 node_ctx.textLength, &input);
 }
-- 
cgit v1.2.1


From e75316de5340e0ba3ac75937c59fa2c9d6ab48d7 Mon Sep 17 00:00:00 2001
From: Jonathan Nieder <jrnieder@gmail.com>
Date: Fri, 10 Dec 2010 00:53:54 -0600
Subject: vcs-svn: simplify repo_modify_path and repo_copy

Restrict the repo_tree API to functions that are actually needed.

 - decouple reading the mode and content of dirents from other
   operations.
 - remove repo_modify_path.  It is only used to read the mode from
   dirents.
 - remove the ability to use repo_read_mode on a missing path.  The
   existing code only errors out in that case, anyway.

Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: David Barr <david.barr@cordelta.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
 vcs-svn/repo_tree.c | 27 ++++++++++-----------------
 vcs-svn/repo_tree.h |  4 ++--
 vcs-svn/svndump.c   |  4 +---
 3 files changed, 13 insertions(+), 22 deletions(-)

diff --git a/vcs-svn/repo_tree.c b/vcs-svn/repo_tree.c
index 8763de5c29..14bcc192b6 100644
--- a/vcs-svn/repo_tree.c
+++ b/vcs-svn/repo_tree.c
@@ -106,7 +106,7 @@ static struct repo_dirent *repo_read_dirent(uint32_t revision,
 	return dent;
 }
 
-static void repo_write_dirent(uint32_t *path, uint32_t mode,
+static void repo_write_dirent(const uint32_t *path, uint32_t mode,
 			      uint32_t content_offset, uint32_t del)
 {
 	uint32_t name, revision, dir_o = ~0, parent_dir_o = ~0;
@@ -167,7 +167,15 @@ uint32_t repo_read_path(const uint32_t *path)
 	return content_offset;
 }
 
-uint32_t repo_copy(uint32_t revision, uint32_t *src, uint32_t *dst)
+uint32_t repo_read_mode(const uint32_t *path)
+{
+	struct repo_dirent *dent = repo_read_dirent(active_commit, path);
+	if (dent == NULL)
+		die("invalid dump: path to be modified is missing");
+	return dent->mode;
+}
+
+void repo_copy(uint32_t revision, const uint32_t *src, const uint32_t *dst)
 {
 	uint32_t mode = 0, content_offset = 0;
 	struct repo_dirent *src_dent;
@@ -177,7 +185,6 @@ uint32_t repo_copy(uint32_t revision, uint32_t *src, uint32_t *dst)
 		content_offset = src_dent->content_offset;
 		repo_write_dirent(dst, mode, content_offset, 0);
 	}
-	return mode;
 }
 
 void repo_add(uint32_t *path, uint32_t mode, uint32_t blob_mark)
@@ -185,20 +192,6 @@ void repo_add(uint32_t *path, uint32_t mode, uint32_t blob_mark)
 	repo_write_dirent(path, mode, blob_mark, 0);
 }
 
-uint32_t repo_modify_path(uint32_t *path, uint32_t mode, uint32_t blob_mark)
-{
-	struct repo_dirent *src_dent;
-	src_dent = repo_read_dirent(active_commit, path);
-	if (!src_dent)
-		return 0;
-	if (!blob_mark)
-		blob_mark = src_dent->content_offset;
-	if (!mode)
-		mode = src_dent->mode;
-	repo_write_dirent(path, mode, blob_mark, 0);
-	return mode;
-}
-
 void repo_delete(uint32_t *path)
 {
 	repo_write_dirent(path, 0, 0, 1);
diff --git a/vcs-svn/repo_tree.h b/vcs-svn/repo_tree.h
index 3202bbeffe..11d48c2444 100644
--- a/vcs-svn/repo_tree.h
+++ b/vcs-svn/repo_tree.h
@@ -12,10 +12,10 @@
 #define REPO_MAX_PATH_DEPTH 1000
 
 uint32_t next_blob_mark(void);
-uint32_t repo_copy(uint32_t revision, uint32_t *src, uint32_t *dst);
+void repo_copy(uint32_t revision, const uint32_t *src, const uint32_t *dst);
 void repo_add(uint32_t *path, uint32_t mode, uint32_t blob_mark);
-uint32_t repo_modify_path(uint32_t *path, uint32_t mode, uint32_t blob_mark);
 uint32_t repo_read_path(const uint32_t *path);
+uint32_t repo_read_mode(const uint32_t *path);
 void repo_delete(uint32_t *path);
 void repo_commit(uint32_t revision, uint32_t author, char *log, uint32_t uuid,
 		 uint32_t url, long unsigned timestamp);
diff --git a/vcs-svn/svndump.c b/vcs-svn/svndump.c
index f07376f964..e6d84bada5 100644
--- a/vcs-svn/svndump.c
+++ b/vcs-svn/svndump.c
@@ -235,9 +235,7 @@ static void handle_node(void)
 		uint32_t mode;
 		if (!have_text)
 			mark = repo_read_path(node_ctx.dst);
-		mode = repo_modify_path(node_ctx.dst, 0, 0);
-		if (!mode)
-			die("invalid dump: path to be modified is missing");
+		mode = repo_read_mode(node_ctx.dst);
 		if (mode == REPO_MODE_DIR && type != REPO_MODE_DIR)
 			die("invalid dump: cannot modify a directory into a file");
 		if (mode != REPO_MODE_DIR && type == REPO_MODE_DIR)
-- 
cgit v1.2.1


From efc749b48f729992d838484d652ba24f5291ee28 Mon Sep 17 00:00:00 2001
From: Jonathan Nieder <jrnieder@gmail.com>
Date: Sun, 10 Oct 2010 21:51:21 -0500
Subject: vcs-svn: allow input errors to be detected promptly

The line_buffer library silently flags input errors until
buffer_deinit time; unfortunately, by that point usually errno is
invalid.  Expose the error flag so callers can check for and
report errors early for easy debugging.

	some_error_prone_operation(...);
	if (buffer_ferror(buf))
		return error("input error: %s", strerror(errno));

Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: David Barr <david.barr@cordelta.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
 vcs-svn/line_buffer.c | 5 +++++
 vcs-svn/line_buffer.h | 1 +
 2 files changed, 6 insertions(+)

diff --git a/vcs-svn/line_buffer.c b/vcs-svn/line_buffer.c
index aedf105b70..eb8a6a7f7b 100644
--- a/vcs-svn/line_buffer.c
+++ b/vcs-svn/line_buffer.c
@@ -59,6 +59,11 @@ long buffer_tmpfile_prepare_to_read(struct line_buffer *buf)
 	return pos;
 }
 
+int buffer_ferror(struct line_buffer *buf)
+{
+	return ferror(buf->infile);
+}
+
 int buffer_read_char(struct line_buffer *buf)
 {
 	return fgetc(buf->infile);
diff --git a/vcs-svn/line_buffer.h b/vcs-svn/line_buffer.h
index 96ce966a22..3c9629e09d 100644
--- a/vcs-svn/line_buffer.h
+++ b/vcs-svn/line_buffer.h
@@ -21,6 +21,7 @@ int buffer_tmpfile_init(struct line_buffer *buf);
 FILE *buffer_tmpfile_rewind(struct line_buffer *buf);	/* prepare to write. */
 long buffer_tmpfile_prepare_to_read(struct line_buffer *buf);
 
+int buffer_ferror(struct line_buffer *buf);
 char *buffer_read_line(struct line_buffer *buf);
 char *buffer_read_string(struct line_buffer *buf, uint32_t len);
 int buffer_read_char(struct line_buffer *buf);
-- 
cgit v1.2.1


From 93b709c79eea6231b7d75a6817245a416b4f8fb5 Mon Sep 17 00:00:00 2001
From: Jonathan Nieder <jrnieder@gmail.com>
Date: Sun, 10 Oct 2010 21:46:24 -0500
Subject: vcs-svn: improve support for reading large files

Move from uint32_t to off_t as the fundamental unit of length used by
the line_buffer library.  Performance would get worse if anything but
I think it's worth it for support of deltas that need to skip large
pieces (> 4 GiB).

Exception: buffer_read_string still takes a uint32_t, since it keeps
its result in an in-core obj_pool.

Callers still have to be updated to take advantage of this.

Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: David Barr <david.barr@cordelta.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
 vcs-svn/line_buffer.c | 4 ++--
 vcs-svn/line_buffer.h | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/vcs-svn/line_buffer.c b/vcs-svn/line_buffer.c
index eb8a6a7f7b..747de07e6b 100644
--- a/vcs-svn/line_buffer.c
+++ b/vcs-svn/line_buffer.c
@@ -104,7 +104,7 @@ void buffer_read_binary(struct line_buffer *buf,
 	strbuf_fread(sb, size, buf->infile);
 }
 
-void buffer_copy_bytes(struct line_buffer *buf, uint32_t len)
+void buffer_copy_bytes(struct line_buffer *buf, off_t len)
 {
 	char byte_buffer[COPY_BUFFER_LEN];
 	uint32_t in;
@@ -120,7 +120,7 @@ void buffer_copy_bytes(struct line_buffer *buf, uint32_t len)
 	}
 }
 
-void buffer_skip_bytes(struct line_buffer *buf, uint32_t len)
+void buffer_skip_bytes(struct line_buffer *buf, off_t len)
 {
 	char byte_buffer[COPY_BUFFER_LEN];
 	uint32_t in;
diff --git a/vcs-svn/line_buffer.h b/vcs-svn/line_buffer.h
index 3c9629e09d..a090dd6874 100644
--- a/vcs-svn/line_buffer.h
+++ b/vcs-svn/line_buffer.h
@@ -26,7 +26,7 @@ char *buffer_read_line(struct line_buffer *buf);
 char *buffer_read_string(struct line_buffer *buf, uint32_t len);
 int buffer_read_char(struct line_buffer *buf);
 void buffer_read_binary(struct line_buffer *buf, struct strbuf *sb, uint32_t len);
-void buffer_copy_bytes(struct line_buffer *buf, uint32_t len);
-void buffer_skip_bytes(struct line_buffer *buf, uint32_t len);
+void buffer_copy_bytes(struct line_buffer *buf, off_t len);
+void buffer_skip_bytes(struct line_buffer *buf, off_t len);
 
 #endif
-- 
cgit v1.2.1


From d234f54b2f82067699f36593188e687fc7dc321a Mon Sep 17 00:00:00 2001
From: Jonathan Nieder <jrnieder@gmail.com>
Date: Sun, 10 Oct 2010 21:44:21 -0500
Subject: vcs-svn: make buffer_skip_bytes return length read

Currently there is no way to detect when input ended if it ended
early during buffer_skip_bytes.  Tell the calling program how many
bytes were actually skipped for easier debugging.

Existing callers will still ignore early EOF.

Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: David Barr <david.barr@cordelta.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
 vcs-svn/line_buffer.c   | 13 +++++++------
 vcs-svn/line_buffer.h   |  2 +-
 vcs-svn/line_buffer.txt |  3 ++-
 3 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/vcs-svn/line_buffer.c b/vcs-svn/line_buffer.c
index 747de07e6b..39d52b88b7 100644
--- a/vcs-svn/line_buffer.c
+++ b/vcs-svn/line_buffer.c
@@ -120,15 +120,16 @@ void buffer_copy_bytes(struct line_buffer *buf, off_t len)
 	}
 }
 
-void buffer_skip_bytes(struct line_buffer *buf, off_t len)
+off_t buffer_skip_bytes(struct line_buffer *buf, off_t nbytes)
 {
 	char byte_buffer[COPY_BUFFER_LEN];
-	uint32_t in;
-	while (len > 0 && !feof(buf->infile) && !ferror(buf->infile)) {
-		in = len < COPY_BUFFER_LEN ? len : COPY_BUFFER_LEN;
-		in = fread(byte_buffer, 1, in, buf->infile);
-		len -= in;
+	off_t done = 0;
+	while (done < nbytes && !feof(buf->infile) && !ferror(buf->infile)) {
+		off_t len = nbytes - done;
+		size_t in = len < COPY_BUFFER_LEN ? len : COPY_BUFFER_LEN;
+		done += fread(byte_buffer, 1, in, buf->infile);
 	}
+	return done;
 }
 
 void buffer_reset(struct line_buffer *buf)
diff --git a/vcs-svn/line_buffer.h b/vcs-svn/line_buffer.h
index a090dd6874..7d10f9c751 100644
--- a/vcs-svn/line_buffer.h
+++ b/vcs-svn/line_buffer.h
@@ -27,6 +27,6 @@ char *buffer_read_string(struct line_buffer *buf, uint32_t len);
 int buffer_read_char(struct line_buffer *buf);
 void buffer_read_binary(struct line_buffer *buf, struct strbuf *sb, uint32_t len);
 void buffer_copy_bytes(struct line_buffer *buf, off_t len);
-void buffer_skip_bytes(struct line_buffer *buf, off_t len);
+off_t buffer_skip_bytes(struct line_buffer *buf, off_t len);
 
 #endif
diff --git a/vcs-svn/line_buffer.txt b/vcs-svn/line_buffer.txt
index e89cc41d56..4ef0755cf5 100644
--- a/vcs-svn/line_buffer.txt
+++ b/vcs-svn/line_buffer.txt
@@ -76,7 +76,8 @@ Functions
 
 `buffer_skip_bytes`::
 	Discards `len` bytes from the input stream (stopping early
-	if necessary because of an error or eof).
+	if necessary because of an error or eof).  Return value is
+	the number of bytes successfully read.
 
 `buffer_reset`::
 	Deallocates non-static buffers.
-- 
cgit v1.2.1


From 26557fc1b37480d184a32de025b060aa1aa231db Mon Sep 17 00:00:00 2001
From: Jonathan Nieder <jrnieder@gmail.com>
Date: Tue, 28 Dec 2010 04:26:17 -0600
Subject: vcs-svn: make buffer_copy_bytes return length read

Currently buffer_copy_bytes does not report to its caller whether
it encountered an early end of file.

Add a return value representing the number of bytes read (but not
the number of bytes copied).  This way all three unusual conditions
can be distinguished: input error with buffer_ferror, output error
with ferror(outfile), early end of input by checking the return
value.

Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: David Barr <david.barr@cordelta.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
 vcs-svn/line_buffer.c | 18 +++++++++---------
 vcs-svn/line_buffer.h |  3 ++-
 2 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/vcs-svn/line_buffer.c b/vcs-svn/line_buffer.c
index 39d52b88b7..33e733a04c 100644
--- a/vcs-svn/line_buffer.c
+++ b/vcs-svn/line_buffer.c
@@ -104,20 +104,20 @@ void buffer_read_binary(struct line_buffer *buf,
 	strbuf_fread(sb, size, buf->infile);
 }
 
-void buffer_copy_bytes(struct line_buffer *buf, off_t len)
+off_t buffer_copy_bytes(struct line_buffer *buf, off_t nbytes)
 {
 	char byte_buffer[COPY_BUFFER_LEN];
-	uint32_t in;
-	while (len > 0 && !feof(buf->infile) && !ferror(buf->infile)) {
-		in = len < COPY_BUFFER_LEN ? len : COPY_BUFFER_LEN;
+	off_t done = 0;
+	while (done < nbytes && !feof(buf->infile) && !ferror(buf->infile)) {
+		off_t len = nbytes - done;
+		size_t in = len < COPY_BUFFER_LEN ? len : COPY_BUFFER_LEN;
 		in = fread(byte_buffer, 1, in, buf->infile);
-		len -= in;
+		done += in;
 		fwrite(byte_buffer, 1, in, stdout);
-		if (ferror(stdout)) {
-			buffer_skip_bytes(buf, len);
-			return;
-		}
+		if (ferror(stdout))
+			return done + buffer_skip_bytes(buf, nbytes - done);
 	}
+	return done;
 }
 
 off_t buffer_skip_bytes(struct line_buffer *buf, off_t nbytes)
diff --git a/vcs-svn/line_buffer.h b/vcs-svn/line_buffer.h
index 7d10f9c751..f5c468afa4 100644
--- a/vcs-svn/line_buffer.h
+++ b/vcs-svn/line_buffer.h
@@ -26,7 +26,8 @@ char *buffer_read_line(struct line_buffer *buf);
 char *buffer_read_string(struct line_buffer *buf, uint32_t len);
 int buffer_read_char(struct line_buffer *buf);
 void buffer_read_binary(struct line_buffer *buf, struct strbuf *sb, uint32_t len);
-void buffer_copy_bytes(struct line_buffer *buf, off_t len);
+/* Returns number of bytes read (not necessarily written). */
+off_t buffer_copy_bytes(struct line_buffer *buf, off_t len);
 off_t buffer_skip_bytes(struct line_buffer *buf, off_t len);
 
 #endif
-- 
cgit v1.2.1


From c9d1c8ba059577e64fb2213cb0c5f3c4619c7519 Mon Sep 17 00:00:00 2001
From: Jonathan Nieder <jrnieder@gmail.com>
Date: Tue, 28 Dec 2010 04:30:54 -0600
Subject: vcs-svn: improve reporting of input errors

Catch input errors and exit early enough to print a reasonable
diagnosis based on errno.

Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: David Barr <david.barr@cordelta.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
 vcs-svn/fast_export.c | 13 +++++++++++--
 vcs-svn/svndump.c     | 29 ++++++++++++++++++++++++++---
 2 files changed, 37 insertions(+), 5 deletions(-)

diff --git a/vcs-svn/fast_export.c b/vcs-svn/fast_export.c
index 260cf50e77..07a8353c8b 100644
--- a/vcs-svn/fast_export.c
+++ b/vcs-svn/fast_export.c
@@ -63,14 +63,23 @@ void fast_export_commit(uint32_t revision, uint32_t author, char *log,
 	printf("progress Imported commit %"PRIu32".\n\n", revision);
 }
 
+static void die_short_read(struct line_buffer *input)
+{
+	if (buffer_ferror(input))
+		die_errno("error reading dump file");
+	die("invalid dump: unexpected end of file");
+}
+
 void fast_export_blob(uint32_t mode, uint32_t mark, uint32_t len, struct line_buffer *input)
 {
 	if (mode == REPO_MODE_LNK) {
 		/* svn symlink blobs start with "link " */
-		buffer_skip_bytes(input, 5);
 		len -= 5;
+		if (buffer_skip_bytes(input, 5) != 5)
+			die_short_read(input);
 	}
 	printf("blob\nmark :%"PRIu32"\ndata %"PRIu32"\n", mark, len);
-	buffer_copy_bytes(input, len);
+	if (buffer_copy_bytes(input, len) != len)
+		die_short_read(input);
 	fputc('\n', stdout);
 }
diff --git a/vcs-svn/svndump.c b/vcs-svn/svndump.c
index e6d84bada5..15f822ea84 100644
--- a/vcs-svn/svndump.c
+++ b/vcs-svn/svndump.c
@@ -149,6 +149,13 @@ static void handle_property(uint32_t key, const char *val, uint32_t len,
 	}
 }
 
+static void die_short_read(void)
+{
+	if (buffer_ferror(&input))
+		die_errno("error reading dump file");
+	die("invalid dump: unexpected end of file");
+}
+
 static void read_props(void)
 {
 	uint32_t key = ~0;
@@ -170,12 +177,21 @@ static void read_props(void)
 		uint32_t len;
 		const char *val;
 		const char type = t[0];
+		int ch;
 
 		if (!type || t[1] != ' ')
 			die("invalid property line: %s\n", t);
 		len = atoi(&t[2]);
 		val = buffer_read_string(&input, len);
-		buffer_skip_bytes(&input, 1);	/* Discard trailing newline. */
+		if (!val || strlen(val) != len)
+			die_short_read();
+
+		/* Discard trailing newline. */
+		ch = buffer_read_char(&input);
+		if (ch == EOF)
+			die_short_read();
+		if (ch != '\n')
+			die("invalid dump: expected newline after %s", val);
 
 		switch (type) {
 		case 'K':
@@ -344,7 +360,11 @@ void svndump_read(const char *url)
 			node_ctx.prop_delta = !strcmp(val, "true");
 		} else if (key == keys.content_length) {
 			len = atoi(val);
-			buffer_read_line(&input);
+			t = buffer_read_line(&input);
+			if (!t)
+				die_short_read();
+			if (*t)
+				die("invalid dump: expected blank line after content length header");
 			if (active_ctx == REV_CTX) {
 				read_props();
 			} else if (active_ctx == NODE_CTX) {
@@ -352,10 +372,13 @@ void svndump_read(const char *url)
 				active_ctx = REV_CTX;
 			} else {
 				fprintf(stderr, "Unexpected content length header: %"PRIu32"\n", len);
-				buffer_skip_bytes(&input, len);
+				if (buffer_skip_bytes(&input, len) != len)
+					die_short_read();
 			}
 		}
 	}
+	if (buffer_ferror(&input))
+		die_short_read();
 	if (active_ctx == NODE_CTX)
 		handle_node();
 	if (active_ctx != DUMP_CTX)
-- 
cgit v1.2.1


From dce33c9c18e2987da1fe8ade67d27057bcb80a67 Mon Sep 17 00:00:00 2001
From: David Barr <david.barr@cordelta.com>
Date: Tue, 22 Mar 2011 10:49:50 +1100
Subject: vcs-svn: use strbuf for revision log

obj_pool is overkill for this application: all that is needed is a
buffer that can resize from rev to rev to accomodate differently-sized
strings.  In the spirit of commit deadcef4 (2010-11-06), use a strbuf
instead.

This is a small step towards removing dependence on obj_pool.h.

Signed-off-by: David Barr <david.barr@cordelta.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
 vcs-svn/svndump.c | 28 ++++++++--------------------
 1 file changed, 8 insertions(+), 20 deletions(-)

diff --git a/vcs-svn/svndump.c b/vcs-svn/svndump.c
index 15f822ea84..559a8084ab 100644
--- a/vcs-svn/svndump.c
+++ b/vcs-svn/svndump.c
@@ -11,8 +11,8 @@
 #include "repo_tree.h"
 #include "fast_export.h"
 #include "line_buffer.h"
-#include "obj_pool.h"
 #include "string_pool.h"
+#include "strbuf.h"
 
 #define NODEACT_REPLACE 4
 #define NODEACT_DELETE 3
@@ -27,20 +27,8 @@
 #define LENGTH_UNKNOWN (~0)
 #define DATE_RFC2822_LEN 31
 
-/* Create memory pool for log messages */
-obj_pool_gen(log, char, 4096)
-
 static struct line_buffer input = LINE_BUFFER_INIT;
 
-static char *log_copy(uint32_t length, const char *log)
-{
-	char *buffer;
-	log_free(log_pool.size);
-	buffer = log_pointer(log_alloc(length));
-	strncpy(buffer, log, length);
-	return buffer;
-}
-
 static struct {
 	uint32_t action, propLength, textLength, srcRev, type;
 	uint32_t src[REPO_MAX_PATH_DEPTH], dst[REPO_MAX_PATH_DEPTH];
@@ -50,7 +38,7 @@ static struct {
 static struct {
 	uint32_t revision, author;
 	unsigned long timestamp;
-	char *log;
+	struct strbuf log;
 } rev_ctx;
 
 static struct {
@@ -83,7 +71,7 @@ static void reset_rev_ctx(uint32_t revision)
 {
 	rev_ctx.revision = revision;
 	rev_ctx.timestamp = 0;
-	rev_ctx.log = NULL;
+	strbuf_reset(&rev_ctx.log);
 	rev_ctx.author = ~0;
 }
 
@@ -123,8 +111,8 @@ static void handle_property(uint32_t key, const char *val, uint32_t len,
 	if (key == keys.svn_log) {
 		if (!val)
 			die("invalid dump: unsets svn:log");
-		/* Value length excludes terminating nul. */
-		rev_ctx.log = log_copy(len + 1, val);
+		strbuf_reset(&rev_ctx.log);
+		strbuf_add(&rev_ctx.log, val, len);
 	} else if (key == keys.svn_author) {
 		rev_ctx.author = pool_intern(val);
 	} else if (key == keys.svn_date) {
@@ -286,7 +274,7 @@ static void handle_node(void)
 static void handle_revision(void)
 {
 	if (rev_ctx.revision)
-		repo_commit(rev_ctx.revision, rev_ctx.author, rev_ctx.log,
+		repo_commit(rev_ctx.revision, rev_ctx.author, rev_ctx.log.buf,
 			dump_ctx.uuid, dump_ctx.url, rev_ctx.timestamp);
 }
 
@@ -390,6 +378,7 @@ int svndump_init(const char *filename)
 	if (buffer_init(&input, filename))
 		return error("cannot open %s: %s", filename, strerror(errno));
 	repo_init();
+	strbuf_init(&rev_ctx.log, 4096);
 	reset_dump_ctx(~0);
 	reset_rev_ctx(0);
 	reset_node_ctx(NULL);
@@ -399,11 +388,11 @@ int svndump_init(const char *filename)
 
 void svndump_deinit(void)
 {
-	log_reset();
 	repo_reset();
 	reset_dump_ctx(~0);
 	reset_rev_ctx(0);
 	reset_node_ctx(NULL);
+	strbuf_release(&rev_ctx.log);
 	if (buffer_deinit(&input))
 		fprintf(stderr, "Input error\n");
 	if (ferror(stdout))
@@ -412,7 +401,6 @@ void svndump_deinit(void)
 
 void svndump_reset(void)
 {
-	log_reset();
 	buffer_reset(&input);
 	repo_reset();
 	reset_dump_ctx(~0);
-- 
cgit v1.2.1


From 7c5817d3ba111bb71a5d7e3c8526e0925f96c92d Mon Sep 17 00:00:00 2001
From: David Barr <david.barr@cordelta.com>
Date: Tue, 22 Mar 2011 17:52:17 -0500
Subject: vcs-svn: use strbuf for author, UUID, and URL

Use strbufs and strings instead of interned strings for values of rev,
dump, and node fields that happen to be strings.  After this change,
the only remaining string_pool use is for paths in the repo_tree API
and internals.

Functional change: treat an empty author, UUID, or URL as none at all.
So for example, in repos where the first revision has an empty
svn:author property, the first rev will be treated as by "nobody"
rather than by a person with empty name and email address created by
prepending an @ sign to the repository UUID.

Signed-off-by: David Barr <david.barr@cordelta.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
 vcs-svn/fast_export.c | 14 +++++++-------
 vcs-svn/fast_export.h |  5 +++--
 vcs-svn/repo_tree.c   |  4 ++--
 vcs-svn/repo_tree.h   |  5 +++--
 vcs-svn/svndump.c     | 45 ++++++++++++++++++++++++++++-----------------
 5 files changed, 43 insertions(+), 30 deletions(-)

diff --git a/vcs-svn/fast_export.c b/vcs-svn/fast_export.c
index 07a8353c8b..a4d4d9993d 100644
--- a/vcs-svn/fast_export.c
+++ b/vcs-svn/fast_export.c
@@ -31,24 +31,24 @@ void fast_export_modify(uint32_t depth, uint32_t *path, uint32_t mode,
 }
 
 static char gitsvnline[MAX_GITSVN_LINE_LEN];
-void fast_export_commit(uint32_t revision, uint32_t author, char *log,
-			uint32_t uuid, uint32_t url,
+void fast_export_commit(uint32_t revision, const char *author, char *log,
+			const char *uuid, const char *url,
 			unsigned long timestamp)
 {
 	if (!log)
 		log = "";
-	if (~uuid && ~url) {
+	if (*uuid && *url) {
 		snprintf(gitsvnline, MAX_GITSVN_LINE_LEN,
 				"\n\ngit-svn-id: %s@%"PRIu32" %s\n",
-				 pool_fetch(url), revision, pool_fetch(uuid));
+				 url, revision, uuid);
 	} else {
 		*gitsvnline = '\0';
 	}
 	printf("commit refs/heads/master\n");
 	printf("committer %s <%s@%s> %ld +0000\n",
-		   ~author ? pool_fetch(author) : "nobody",
-		   ~author ? pool_fetch(author) : "nobody",
-		   ~uuid ? pool_fetch(uuid) : "local", timestamp);
+		   *author ? author : "nobody",
+		   *author ? author : "nobody",
+		   *uuid ? uuid : "local", timestamp);
 	printf("data %"PRIu32"\n%s%s\n",
 		   (uint32_t) (strlen(log) + strlen(gitsvnline)),
 		   log, gitsvnline);
diff --git a/vcs-svn/fast_export.h b/vcs-svn/fast_export.h
index 054e7d5eb1..05cf97f3a7 100644
--- a/vcs-svn/fast_export.h
+++ b/vcs-svn/fast_export.h
@@ -6,8 +6,9 @@
 void fast_export_delete(uint32_t depth, uint32_t *path);
 void fast_export_modify(uint32_t depth, uint32_t *path, uint32_t mode,
 			uint32_t mark);
-void fast_export_commit(uint32_t revision, uint32_t author, char *log,
-			uint32_t uuid, uint32_t url, unsigned long timestamp);
+void fast_export_commit(uint32_t revision, const char *author, char *log,
+			const char *uuid, const char *url,
+			unsigned long timestamp);
 void fast_export_blob(uint32_t mode, uint32_t mark, uint32_t len,
 		      struct line_buffer *input);
 
diff --git a/vcs-svn/repo_tree.c b/vcs-svn/repo_tree.c
index 14bcc192b6..d722e3212f 100644
--- a/vcs-svn/repo_tree.c
+++ b/vcs-svn/repo_tree.c
@@ -278,8 +278,8 @@ void repo_diff(uint32_t r1, uint32_t r2)
 		    repo_commit_root_dir(commit_pointer(r2)));
 }
 
-void repo_commit(uint32_t revision, uint32_t author, char *log, uint32_t uuid,
-		 uint32_t url, unsigned long timestamp)
+void repo_commit(uint32_t revision, const char *author, char *log,
+		 const char *uuid, const char *url, unsigned long timestamp)
 {
 	fast_export_commit(revision, author, log, uuid, url, timestamp);
 	dent_commit();
diff --git a/vcs-svn/repo_tree.h b/vcs-svn/repo_tree.h
index 11d48c2444..a1b0e87651 100644
--- a/vcs-svn/repo_tree.h
+++ b/vcs-svn/repo_tree.h
@@ -17,8 +17,9 @@ void repo_add(uint32_t *path, uint32_t mode, uint32_t blob_mark);
 uint32_t repo_read_path(const uint32_t *path);
 uint32_t repo_read_mode(const uint32_t *path);
 void repo_delete(uint32_t *path);
-void repo_commit(uint32_t revision, uint32_t author, char *log, uint32_t uuid,
-		 uint32_t url, long unsigned timestamp);
+void repo_commit(uint32_t revision, const char *author,
+		char *log, const char *uuid, const char *url,
+		long unsigned timestamp);
 void repo_diff(uint32_t r1, uint32_t r2);
 void repo_init(void);
 void repo_reset(void);
diff --git a/vcs-svn/svndump.c b/vcs-svn/svndump.c
index 559a8084ab..7ac74877fa 100644
--- a/vcs-svn/svndump.c
+++ b/vcs-svn/svndump.c
@@ -36,13 +36,14 @@ static struct {
 } node_ctx;
 
 static struct {
-	uint32_t revision, author;
+	uint32_t revision;
 	unsigned long timestamp;
-	struct strbuf log;
+	struct strbuf log, author;
 } rev_ctx;
 
 static struct {
-	uint32_t version, uuid, url;
+	uint32_t version;
+	struct strbuf uuid, url;
 } dump_ctx;
 
 static struct {
@@ -72,14 +73,16 @@ static void reset_rev_ctx(uint32_t revision)
 	rev_ctx.revision = revision;
 	rev_ctx.timestamp = 0;
 	strbuf_reset(&rev_ctx.log);
-	rev_ctx.author = ~0;
+	strbuf_reset(&rev_ctx.author);
 }
 
-static void reset_dump_ctx(uint32_t url)
+static void reset_dump_ctx(const char *url)
 {
-	dump_ctx.url = url;
+	strbuf_reset(&dump_ctx.url);
+	if (url)
+		strbuf_addstr(&dump_ctx.url, url);
 	dump_ctx.version = 1;
-	dump_ctx.uuid = ~0;
+	strbuf_reset(&dump_ctx.uuid);
 }
 
 static void init_keys(void)
@@ -114,7 +117,9 @@ static void handle_property(uint32_t key, const char *val, uint32_t len,
 		strbuf_reset(&rev_ctx.log);
 		strbuf_add(&rev_ctx.log, val, len);
 	} else if (key == keys.svn_author) {
-		rev_ctx.author = pool_intern(val);
+		strbuf_reset(&rev_ctx.author);
+		if (val)
+			strbuf_add(&rev_ctx.author, val, len);
 	} else if (key == keys.svn_date) {
 		if (!val)
 			die("invalid dump: unsets svn:date");
@@ -274,8 +279,9 @@ static void handle_node(void)
 static void handle_revision(void)
 {
 	if (rev_ctx.revision)
-		repo_commit(rev_ctx.revision, rev_ctx.author, rev_ctx.log.buf,
-			dump_ctx.uuid, dump_ctx.url, rev_ctx.timestamp);
+		repo_commit(rev_ctx.revision, rev_ctx.author.buf,
+			rev_ctx.log.buf, dump_ctx.uuid.buf, dump_ctx.url.buf,
+			rev_ctx.timestamp);
 }
 
 void svndump_read(const char *url)
@@ -286,7 +292,7 @@ void svndump_read(const char *url)
 	uint32_t len;
 	uint32_t key;
 
-	reset_dump_ctx(pool_intern(url));
+	reset_dump_ctx(url);
 	while ((t = buffer_read_line(&input))) {
 		val = strstr(t, ": ");
 		if (!val)
@@ -301,7 +307,8 @@ void svndump_read(const char *url)
 				die("expected svn dump format version <= 3, found %"PRIu32,
 				    dump_ctx.version);
 		} else if (key == keys.uuid) {
-			dump_ctx.uuid = pool_intern(val);
+			strbuf_reset(&dump_ctx.uuid);
+			strbuf_addstr(&dump_ctx.uuid, val);
 		} else if (key == keys.revision_number) {
 			if (active_ctx == NODE_CTX)
 				handle_node();
@@ -378,8 +385,11 @@ int svndump_init(const char *filename)
 	if (buffer_init(&input, filename))
 		return error("cannot open %s: %s", filename, strerror(errno));
 	repo_init();
+	strbuf_init(&dump_ctx.uuid, 4096);
+	strbuf_init(&dump_ctx.url, 4096);
 	strbuf_init(&rev_ctx.log, 4096);
-	reset_dump_ctx(~0);
+	strbuf_init(&rev_ctx.author, 4096);
+	reset_dump_ctx(NULL);
 	reset_rev_ctx(0);
 	reset_node_ctx(NULL);
 	init_keys();
@@ -389,7 +399,7 @@ int svndump_init(const char *filename)
 void svndump_deinit(void)
 {
 	repo_reset();
-	reset_dump_ctx(~0);
+	reset_dump_ctx(NULL);
 	reset_rev_ctx(0);
 	reset_node_ctx(NULL);
 	strbuf_release(&rev_ctx.log);
@@ -403,7 +413,8 @@ void svndump_reset(void)
 {
 	buffer_reset(&input);
 	repo_reset();
-	reset_dump_ctx(~0);
-	reset_rev_ctx(0);
-	reset_node_ctx(NULL);
+	strbuf_release(&dump_ctx.uuid);
+	strbuf_release(&dump_ctx.url);
+	strbuf_release(&rev_ctx.log);
+	strbuf_release(&rev_ctx.author);
 }
-- 
cgit v1.2.1


From 044ad2906a5e4b805bc8c8d121466d8ff94ecbfb Mon Sep 17 00:00:00 2001
From: David Barr <david.barr@cordelta.com>
Date: Mon, 13 Dec 2010 19:13:24 +1100
Subject: vcs-svn: implement perfect hash for node-prop keys

Instead of interning property names and comparing their string_pool
keys, look them up in a table by string length, which should be about
as fast.

This is a small step towards removing dependence on string_pool.

Signed-off-by: David Barr <david.barr@cordelta.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
 vcs-svn/svndump.c | 62 ++++++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 43 insertions(+), 19 deletions(-)

diff --git a/vcs-svn/svndump.c b/vcs-svn/svndump.c
index 15f822ea84..322d1cd305 100644
--- a/vcs-svn/svndump.c
+++ b/vcs-svn/svndump.c
@@ -14,6 +14,12 @@
 #include "obj_pool.h"
 #include "string_pool.h"
 
+/*
+ * Compare start of string to literal of equal length;
+ * must be guarded by length test.
+ */
+#define constcmp(s, ref) memcmp(s, ref, sizeof(ref) - 1)
+
 #define NODEACT_REPLACE 4
 #define NODEACT_DELETE 3
 #define NODEACT_ADD 2
@@ -58,8 +64,7 @@ static struct {
 } dump_ctx;
 
 static struct {
-	uint32_t svn_log, svn_author, svn_date, svn_executable, svn_special, uuid,
-		revision_number, node_path, node_kind, node_action,
+	uint32_t uuid, revision_number, node_path, node_kind, node_action,
 		node_copyfrom_path, node_copyfrom_rev, text_content_length,
 		prop_content_length, content_length, svn_fs_dump_format_version,
 		/* version 3 format */
@@ -96,11 +101,6 @@ static void reset_dump_ctx(uint32_t url)
 
 static void init_keys(void)
 {
-	keys.svn_log = pool_intern("svn:log");
-	keys.svn_author = pool_intern("svn:author");
-	keys.svn_date = pool_intern("svn:date");
-	keys.svn_executable = pool_intern("svn:executable");
-	keys.svn_special = pool_intern("svn:special");
 	keys.uuid = pool_intern("UUID");
 	keys.revision_number = pool_intern("Revision-number");
 	keys.node_path = pool_intern("Node-path");
@@ -117,22 +117,43 @@ static void init_keys(void)
 	keys.prop_delta = pool_intern("Prop-delta");
 }
 
-static void handle_property(uint32_t key, const char *val, uint32_t len,
+static void handle_property(const struct strbuf *key_buf,
+				const char *val, uint32_t len,
 				uint32_t *type_set)
 {
-	if (key == keys.svn_log) {
+	const char *key = key_buf->buf;
+	size_t keylen = key_buf->len;
+
+	switch (keylen + 1) {
+	case sizeof("svn:log"):
+		if (constcmp(key, "svn:log"))
+			break;
 		if (!val)
 			die("invalid dump: unsets svn:log");
 		/* Value length excludes terminating nul. */
 		rev_ctx.log = log_copy(len + 1, val);
-	} else if (key == keys.svn_author) {
+		break;
+	case sizeof("svn:author"):
+		if (constcmp(key, "svn:author"))
+			break;
 		rev_ctx.author = pool_intern(val);
-	} else if (key == keys.svn_date) {
+		break;
+	case sizeof("svn:date"):
+		if (constcmp(key, "svn:date"))
+			break;
 		if (!val)
 			die("invalid dump: unsets svn:date");
 		if (parse_date_basic(val, &rev_ctx.timestamp, NULL))
 			warning("invalid timestamp: %s", val);
-	} else if (key == keys.svn_executable || key == keys.svn_special) {
+		break;
+	case sizeof("svn:executable"):
+	case sizeof("svn:special"):
+		if (keylen == strlen("svn:executable") &&
+		    constcmp(key, "svn:executable"))
+			break;
+		if (keylen == strlen("svn:special") &&
+		    constcmp(key, "svn:special"))
+			break;
 		if (*type_set) {
 			if (!val)
 				return;
@@ -143,7 +164,7 @@ static void handle_property(uint32_t key, const char *val, uint32_t len,
 			return;
 		}
 		*type_set = 1;
-		node_ctx.type = key == keys.svn_executable ?
+		node_ctx.type = keylen == strlen("svn:executable") ?
 				REPO_MODE_EXE :
 				REPO_MODE_LNK;
 	}
@@ -158,7 +179,7 @@ static void die_short_read(void)
 
 static void read_props(void)
 {
-	uint32_t key = ~0;
+	static struct strbuf key = STRBUF_INIT;
 	const char *t;
 	/*
 	 * NEEDSWORK: to support simple mode changes like
@@ -195,16 +216,19 @@ static void read_props(void)
 
 		switch (type) {
 		case 'K':
-			key = pool_intern(val);
-			continue;
 		case 'D':
-			key = pool_intern(val);
+			strbuf_reset(&key);
+			if (val)
+				strbuf_add(&key, val, len);
+			if (type == 'K')
+				continue;
+			assert(type == 'D');
 			val = NULL;
 			len = 0;
 			/* fall through */
 		case 'V':
-			handle_property(key, val, len, &type_set);
-			key = ~0;
+			handle_property(&key, val, len, &type_set);
+			strbuf_reset(&key);
 			continue;
 		default:
 			die("invalid property line: %s\n", t);
-- 
cgit v1.2.1


From 90c0a3cfe390208c86144bf97ec8fa5610febe0f Mon Sep 17 00:00:00 2001
From: David Barr <david.barr@cordelta.com>
Date: Mon, 13 Dec 2010 19:56:01 +1100
Subject: vcs-svn: implement perfect hash for top-level keys

Instead of interning property names and comparing their string_pool
keys, look them up in a table by string length, which should be about
as fast.

Another small step towards removing dependence on string_pool
altogether.

Signed-off-by: David Barr <david.barr@cordelta.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
 vcs-svn/svndump.c | 109 +++++++++++++++++++++++++++++-------------------------
 1 file changed, 59 insertions(+), 50 deletions(-)

diff --git a/vcs-svn/svndump.c b/vcs-svn/svndump.c
index 322d1cd305..77680a31e8 100644
--- a/vcs-svn/svndump.c
+++ b/vcs-svn/svndump.c
@@ -63,14 +63,6 @@ static struct {
 	uint32_t version, uuid, url;
 } dump_ctx;
 
-static struct {
-	uint32_t uuid, revision_number, node_path, node_kind, node_action,
-		node_copyfrom_path, node_copyfrom_rev, text_content_length,
-		prop_content_length, content_length, svn_fs_dump_format_version,
-		/* version 3 format */
-		text_delta, prop_delta;
-} keys;
-
 static void reset_node_ctx(char *fname)
 {
 	node_ctx.type = 0;
@@ -99,24 +91,6 @@ static void reset_dump_ctx(uint32_t url)
 	dump_ctx.uuid = ~0;
 }
 
-static void init_keys(void)
-{
-	keys.uuid = pool_intern("UUID");
-	keys.revision_number = pool_intern("Revision-number");
-	keys.node_path = pool_intern("Node-path");
-	keys.node_kind = pool_intern("Node-kind");
-	keys.node_action = pool_intern("Node-action");
-	keys.node_copyfrom_path = pool_intern("Node-copyfrom-path");
-	keys.node_copyfrom_rev = pool_intern("Node-copyfrom-rev");
-	keys.text_content_length = pool_intern("Text-content-length");
-	keys.prop_content_length = pool_intern("Prop-content-length");
-	keys.content_length = pool_intern("Content-length");
-	keys.svn_fs_dump_format_version = pool_intern("SVN-fs-dump-format-version");
-	/* version 3 format (Subversion 1.1.0) */
-	keys.text_delta = pool_intern("Text-delta");
-	keys.prop_delta = pool_intern("Prop-delta");
-}
-
 static void handle_property(const struct strbuf *key_buf,
 				const char *val, uint32_t len,
 				uint32_t *type_set)
@@ -320,44 +294,61 @@ void svndump_read(const char *url)
 	char *t;
 	uint32_t active_ctx = DUMP_CTX;
 	uint32_t len;
-	uint32_t key;
 
 	reset_dump_ctx(pool_intern(url));
 	while ((t = buffer_read_line(&input))) {
 		val = strstr(t, ": ");
 		if (!val)
 			continue;
-		*val++ = '\0';
-		*val++ = '\0';
-		key = pool_intern(t);
+		val += 2;
 
-		if (key == keys.svn_fs_dump_format_version) {
+		/* strlen(key) + 1 */
+		switch (val - t - 1) {
+		case sizeof("SVN-fs-dump-format-version"):
+			if (constcmp(t, "SVN-fs-dump-format-version"))
+				continue;
 			dump_ctx.version = atoi(val);
 			if (dump_ctx.version > 3)
 				die("expected svn dump format version <= 3, found %"PRIu32,
 				    dump_ctx.version);
-		} else if (key == keys.uuid) {
+			break;
+		case sizeof("UUID"):
+			if (constcmp(t, "UUID"))
+				continue;
 			dump_ctx.uuid = pool_intern(val);
-		} else if (key == keys.revision_number) {
+			break;
+		case sizeof("Revision-number"):
+			if (constcmp(t, "Revision-number"))
+				continue;
 			if (active_ctx == NODE_CTX)
 				handle_node();
 			if (active_ctx != DUMP_CTX)
 				handle_revision();
 			active_ctx = REV_CTX;
 			reset_rev_ctx(atoi(val));
-		} else if (key == keys.node_path) {
-			if (active_ctx == NODE_CTX)
-				handle_node();
-			active_ctx = NODE_CTX;
-			reset_node_ctx(val);
-		} else if (key == keys.node_kind) {
+			break;
+		case sizeof("Node-path"):
+			if (prefixcmp(t, "Node-"))
+				continue;
+			if (!constcmp(t + strlen("Node-"), "path")) {
+				if (active_ctx == NODE_CTX)
+					handle_node();
+				active_ctx = NODE_CTX;
+				reset_node_ctx(val);
+				break;
+			}
+			if (constcmp(t + strlen("Node-"), "kind"))
+				continue;
 			if (!strcmp(val, "dir"))
 				node_ctx.type = REPO_MODE_DIR;
 			else if (!strcmp(val, "file"))
 				node_ctx.type = REPO_MODE_BLB;
 			else
 				fprintf(stderr, "Unknown node-kind: %s\n", val);
-		} else if (key == keys.node_action) {
+			break;
+		case sizeof("Node-action"):
+			if (constcmp(t, "Node-action"))
+				continue;
 			if (!strcmp(val, "delete")) {
 				node_ctx.action = NODEACT_DELETE;
 			} else if (!strcmp(val, "add")) {
@@ -370,19 +361,38 @@ void svndump_read(const char *url)
 				fprintf(stderr, "Unknown node-action: %s\n", val);
 				node_ctx.action = NODEACT_UNKNOWN;
 			}
-		} else if (key == keys.node_copyfrom_path) {
+			break;
+		case sizeof("Node-copyfrom-path"):
+			if (constcmp(t, "Node-copyfrom-path"))
+				continue;
 			pool_tok_seq(REPO_MAX_PATH_DEPTH, node_ctx.src, "/", val);
-		} else if (key == keys.node_copyfrom_rev) {
+			break;
+		case sizeof("Node-copyfrom-rev"):
+			if (constcmp(t, "Node-copyfrom-rev"))
+				continue;
 			node_ctx.srcRev = atoi(val);
-		} else if (key == keys.text_content_length) {
-			node_ctx.textLength = atoi(val);
-		} else if (key == keys.prop_content_length) {
+			break;
+		case sizeof("Text-content-length"):
+			if (!constcmp(t, "Text-content-length")) {
+				node_ctx.textLength = atoi(val);
+				break;
+			}
+			if (constcmp(t, "Prop-content-length"))
+				continue;
 			node_ctx.propLength = atoi(val);
-		} else if (key == keys.text_delta) {
-			node_ctx.text_delta = !strcmp(val, "true");
-		} else if (key == keys.prop_delta) {
+			break;
+		case sizeof("Text-delta"):
+			if (!constcmp(t, "Text-delta")) {
+				node_ctx.text_delta = !strcmp(val, "true");
+				break;
+			}
+			if (constcmp(t, "Prop-delta"))
+				continue;
 			node_ctx.prop_delta = !strcmp(val, "true");
-		} else if (key == keys.content_length) {
+			break;
+		case sizeof("Content-length"):
+			if (constcmp(t, "Content-length"))
+				continue;
 			len = atoi(val);
 			t = buffer_read_line(&input);
 			if (!t)
@@ -417,7 +427,6 @@ int svndump_init(const char *filename)
 	reset_dump_ctx(~0);
 	reset_rev_ctx(0);
 	reset_node_ctx(NULL);
-	init_keys();
 	return 0;
 }
 
-- 
cgit v1.2.1


From f1602054e3a45e195edf814681e8f5ba88851623 Mon Sep 17 00:00:00 2001
From: David Barr <david.barr@cordelta.com>
Date: Tue, 14 Dec 2010 11:06:43 +1100
Subject: vcs-svn: use strchr to find RFC822 delimiter

This is a small optimisation (4% reduction in user time) but is the
largest artifact within the parsing portion of svndump.c

Signed-off-by: David Barr <david.barr@cordelta.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
 vcs-svn/svndump.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/vcs-svn/svndump.c b/vcs-svn/svndump.c
index 77680a31e8..0919a576dc 100644
--- a/vcs-svn/svndump.c
+++ b/vcs-svn/svndump.c
@@ -297,10 +297,13 @@ void svndump_read(const char *url)
 
 	reset_dump_ctx(pool_intern(url));
 	while ((t = buffer_read_line(&input))) {
-		val = strstr(t, ": ");
+		val = strchr(t, ':');
 		if (!val)
 			continue;
-		val += 2;
+		val++;
+		if (*val != ' ')
+			continue;
+		val++;
 
 		/* strlen(key) + 1 */
 		switch (val - t - 1) {
-- 
cgit v1.2.1