git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH 06/10] vcs-svn: do not rely on marks for old blobs

From
Jonathan Nieder <jrnieder@gmail.com>
Date
Dec 10, 2010, 10:26 UTC
Message-ID
<20101210102619.GF26331@burratino>
In-Reply-To
<20101210102007.GA26298@burratino>

Retrieve old blobs by name and revision number from fast-import. One step closer to bounded memory usage in svn-fe.

Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
Superfluous except that it shows how to parse 'ls' responses.
A demo.
 vcs-svn/fast_export.c |   53 +++++++++++++++++++++++++++++++++++++++++++++++++
 vcs-svn/fast_export.h |    3 ++
 vcs-svn/string_pool.c |    2 +-
 vcs-svn/string_pool.h |    2 +-
 vcs-svn/svndump.c     |    6 +++++
 5 files changed, 64 insertions(+), 2 deletions(-)
diff --git a/vcs-svn/fast_export.c b/vcs-svn/fast_export.c
index 960b252..cca9810 100644
--- a/vcs-svn/fast_export.c
+++ b/vcs-svn/fast_export.c
@@ -88,6 +88,21 @@ static int ends_with(const char *s, size_t len, const char *suffix)
 	return !memcmp(s + len - suffixlen, suffix, suffixlen);
 }
 
+static int parse_ls_response_line(const char *line, struct strbuf *objnam)
+{
+	const char *end = line + strlen(line);
+	const char *name, *tab;
+
+	if (end - line < strlen("100644 blob "))
+		return error("ls response too short: %s", line);
+	name = line + strlen("100644 blob ");
+	tab = memchr(name, '\t', end - name);
+	if (!tab)
+		return error("ls response does not contain tab: %s", line);
+	strbuf_add(objnam, name, tab - name);
+	return 0;
+}
+
 static int parse_cat_response_line(const char *header, off_t *len)
 {
 	size_t headerlen = strlen(header);
@@ -129,6 +144,31 @@ static off_t cat_mark(uint32_t mark)
 	return length;
 }
 
+static off_t cat_from_rev(uint32_t rev, const uint32_t *path)
+{
+	const char *response;
+	off_t length = length;
+	struct strbuf blob_name = STRBUF_INIT;
+
+	/* ls :5 "path/to/old/file" */
+	printf("ls :%"PRIu32" \"", rev);
+	pool_print_seq(REPO_MAX_PATH_DEPTH, path, '/', stdout);
+	printf("\"\n");
+	fflush(stdout);
+
+	response = get_response_line();
+	if (parse_ls_response_line(response, &blob_name))
+		die("invalid ls response: %s", response);
+
+	printf("cat-blob %s\n", blob_name.buf);
+	fflush(stdout);
+	response = get_response_line();
+	if (parse_cat_response_line(response, &length))
+		die("invalid cat-blob response: %s", response);
+	strbuf_release(&blob_name);
+	return length;
+}
+
 static long delta_apply(uint32_t mark, off_t len, struct line_buffer *input,
 			off_t preimage_len, uint32_t old_mode)
 {
@@ -195,3 +235,16 @@ void fast_export_blob_delta(uint32_t mode, uint32_t mark,
 						old_mode);
 	record_postimage(mark, mode, postimage_len);
 }
+
+void fast_export_blob_delta_rev(uint32_t mode, uint32_t mark, uint32_t old_mode,
+				uint32_t old_rev, const uint32_t *old_path,
+				uint32_t len, struct line_buffer *input)
+{
+	long postimage_len;
+	if (len > maximum_signed_value_of_type(off_t))
+		die("enormous delta");
+	postimage_len = delta_apply(mark, (off_t) len, input,
+					cat_from_rev(old_rev, old_path),
+					old_mode);
+	record_postimage(mark, mode, postimage_len);
+}
diff --git a/vcs-svn/fast_export.h b/vcs-svn/fast_export.h
index 6f77c3b..487d3d4 100644
--- a/vcs-svn/fast_export.h
+++ b/vcs-svn/fast_export.h
@@ -13,5 +13,8 @@ void fast_export_blob(uint32_t mode, uint32_t mark, uint32_t len,
 void fast_export_blob_delta(uint32_t mode, uint32_t mark,
 			uint32_t old_mode, uint32_t old_mark,
 			uint32_t len, struct line_buffer *input);
+void fast_export_blob_delta_rev(uint32_t mode, uint32_t mark, uint32_t old_mode,
+			uint32_t old_rev, const uint32_t *old_path,
+			uint32_t len, struct line_buffer *input);
 
 #endif
diff --git a/vcs-svn/string_pool.c b/vcs-svn/string_pool.c
index f5b1da8..c08abac 100644
--- a/vcs-svn/string_pool.c
+++ b/vcs-svn/string_pool.c
@@ -65,7 +65,7 @@ uint32_t pool_tok_r(char *str, const char *delim, char **saveptr)
 	return token ? pool_intern(token) : ~0;
 }
 
-void pool_print_seq(uint32_t len, uint32_t *seq, char delim, FILE *stream)
+void pool_print_seq(uint32_t len, const uint32_t *seq, char delim, FILE *stream)
 {
 	uint32_t i;
 	for (i = 0; i < len && ~seq[i]; i++) {
diff --git a/vcs-svn/string_pool.h b/vcs-svn/string_pool.h
index 222fb66..3720cf8 100644
--- a/vcs-svn/string_pool.h
+++ b/vcs-svn/string_pool.h
@@ -4,7 +4,7 @@
 uint32_t pool_intern(const char *key);
 const char *pool_fetch(uint32_t entry);
 uint32_t pool_tok_r(char *str, const char *delim, char **saveptr);
-void pool_print_seq(uint32_t len, uint32_t *seq, char delim, FILE *stream);
+void pool_print_seq(uint32_t len, const uint32_t *seq, char delim, FILE *stream);
 uint32_t pool_tok_seq(uint32_t sz, uint32_t *seq, const char *delim, char *str);
 void pool_reset(void);
 
diff --git a/vcs-svn/svndump.c b/vcs-svn/svndump.c
index c6d6337..da968fa 100644
--- a/vcs-svn/svndump.c
+++ b/vcs-svn/svndump.c
@@ -259,6 +259,12 @@ static void handle_node(void)
 		fast_export_blob(node_ctx.type, mark, node_ctx.textLength, &input);
 		return;
 	}
+	if (node_ctx.srcRev) {
+		fast_export_blob_delta_rev(node_ctx.type, mark, old_mode,
+					node_ctx.srcRev, node_ctx.src,
+					node_ctx.textLength, &input);
+		return;
+	}
 	fast_export_blob_delta(node_ctx.type, mark, old_mode, old_mark,
 				node_ctx.textLength, &input);
 }
-- 
1.7.2.4
Previous: Jonathan NiederNext: Jonathan Nieder
Message 8 of 37 in “vcs-svn: prepare for (implement?) incremental import”
  1. 00/10 vcs-svn: prepare for (implement?) incremental importJonathan Nieder, Dec 10, 2010
  2. 01/10 vcs-svn: use higher mark numbers for blobsJonathan Nieder, Dec 10, 2010
  3. 02/10 vcs-svn: save marks for imported commitsJonathan Nieder, Dec 10, 2010
  4. Jonathan NiederMar 6, 2011
  5. 03/10 vcs-svn: introduce cat_mark function to retrieve a marked blobJonathan Nieder, Dec 10, 2010
  6. 04/10 vcs-svn: make apply_delta caller retrieve preimageJonathan Nieder, Dec 10, 2010
  7. 05/10 vcs-svn: split off function to export result from delta applicationJonathan Nieder, Dec 10, 2010
  8. 06/10 vcs-svn: do not rely on marks for old blobsJonathan Nieder, Dec 10, 2010
  9. 07/10 vcs-svn: split off function to make 'ls' requestsJonathan Nieder, Dec 10, 2010
  10. 08/10 vcs-svn: prepare to eliminate repo_tree structureJonathan Nieder, Dec 10, 2010
  11. vcs-svn: prepare to eliminate repo_tree structureJonathan Nieder, Mar 6, 2011
  12. David BarrMar 6, 2011
  13. 09/10 vcs-svn: simplifications for repo_modify_path et alJonathan Nieder, Dec 10, 2010
  14. 10/10 vcs-svn: eliminate repo_tree structureJonathan Nieder, Dec 10, 2010
  15. 12/10 vcs-svn: quote paths correctly for ls commandDavid Michael Barr, Dec 11, 2010
  16. vcs-svn: quote all paths passed to fast-importJonathan Nieder, Dec 11, 2010
  17. 13/10 vcs-svn: use mark from previous import for parent commitDavid Michael Barr, Dec 12, 2010
  18. Jonathan NiederDec 12, 2010
  19. 00/12 vcs-svn: incremental importJonathan Nieder, Mar 6, 2011
  20. 01/12 vcs-svn: use higher mark numbers for blobsJonathan Nieder, Mar 6, 2011
  21. Junio C HamanoMar 8, 2011
  22. Jonathan NiederMar 9, 2011
  23. 02/12 vcs-svn: save marks for imported commitsJonathan Nieder, Mar 6, 2011
  24. 03/12 vcs-svn: introduce repo_read_path to check the content at a pathJonathan Nieder, Mar 6, 2011
  25. 04/12 vcs-svn: handle_node: use repo_read_pathJonathan Nieder, Mar 6, 2011
  26. 05/12 vcs-svn: simplify repo_modify_path and repo_copyJonathan Nieder, Mar 6, 2011
  27. 06/12 vcs-svn: add a comment before each commitJonathan Nieder, Mar 6, 2011
  28. 07/12 vcs-svn: allow input errors to be detected promptlyJonathan Nieder, Mar 6, 2011
  29. 08/12 vcs-svn: set up channel to read fast-import cat-blob responseJonathan Nieder, Mar 6, 2011
  30. 09/12 vcs-svn: eliminate repo_tree structureJonathan Nieder, Mar 6, 2011
  31. 10/12 vcs-svn: quote paths correctly for ls commandJonathan Nieder, Mar 6, 2011
  32. 11/12 vcs-svn: handle filenames with dq correctlyJonathan Nieder, Mar 6, 2011
  33. 12/12 vcs-svn: use mark from previous import for parent commitJonathan Nieder, Mar 6, 2011
  34. Sverre RabbelierMar 7, 2011
  35. Jonathan NiederMar 7, 2011
  36. fast-import: treat filemodify with empty tree as deleteJonathan Nieder, Dec 11, 2010
  37. vcs-svn: avoid git-isms in fast-import streamJonathan Nieder, Dec 11, 2010

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.