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

[PATCH 14/16] vcs-svn: let deltas use data from preimage

From
David Barr <david.barr@cordelta.com>
Date
Mar 19, 2011, 07:20 UTC
Message-ID
<1300519254-20201-15-git-send-email-david.barr@cordelta.com>
In-Reply-To
<1300519254-20201-1-git-send-email-david.barr@cordelta.com>
From: Jonathan Nieder <jrnieder@gmail.com>

The copyfrom_source instruction appends data from the preimage buffer to the end of output. Its arguments are a length and an offset relative to the beginning of the source view.

With this change, the delta applier is able to reproduce all 5,636,613 blobs in the early history of the ASF repository. Tested with

	mkfifo backflow
	svn-fe <svn-asf-public-r0:940166 3<backflow |
	git fast-import --cat-blob-fd=3 3>backflow

with svn-asf-public-r0:940166 produced by whatever version of Subversion the dumps in /dump/ on svn.apache.org use (presumably 1.6.something).

Improved-by: Ramkumar Ramachandra <artagnon@gmail.com>
Improved-by: David Barr <david.barr@cordelta.com>
Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
Acked-by: Ramkumar Ramachandra <artagnon@gmail.com>
Signed-off-by: David Barr <david.barr@cordelta.com>
---
 t/t9011-svn-da.sh |   35 +++++++++++++++++++++++++++++++++++
 vcs-svn/svndiff.c |   28 +++++++++++++++++++++++-----
 2 files changed, 58 insertions(+), 5 deletions(-)
diff --git a/t/t9011-svn-da.sh b/t/t9011-svn-da.sh
index d13115a..45e396f 100755
--- a/t/t9011-svn-da.sh
+++ b/t/t9011-svn-da.sh
@@ -212,4 +212,39 @@ test_expect_success 'catch copy that overflows' '
 	test_must_fail test-svn-fe -d preimage copytarget.overflow $len
 '
 
+test_expect_success 'copyfrom source' '
+	printf foo >expect &&
+	printf "SVNQ%b%b" "Q\003\003\002Q" "\003Q" | q_to_nul >copysource.all &&
+	test-svn-fe -d preimage copysource.all 11 >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'copy backwards' '
+	printf oof >expect &&
+	printf "SVNQ%b%b" "Q\003\003\006Q" "\001\002\001\001\001Q" |
+		q_to_nul >copysource.rev &&
+	test-svn-fe -d preimage copysource.rev 15 >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'offsets are relative to window' '
+	printf fo >expect &&
+	printf "SVNQ%b%b%b%b" "Q\003\001\002Q" "\001Q" \
+		"\002\001\001\002Q" "\001Q" |
+		q_to_nul >copysource.two &&
+	test-svn-fe -d preimage copysource.two 18 >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'example from notes/svndiff' '
+	printf aaaaccccdddddddd >expect &&
+	printf aaaabbbbcccc >source &&
+	printf "SVNQ%b%b%s" "Q\014\020\007\001" \
+		"\004Q\004\010\0201\0107\010" d |
+		q_to_nul >delta.example &&
+	len=$(wc -c <delta.example) &&
+	test-svn-fe -d source delta.example $len >actual &&
+	test_cmp expect actual
+'
+
 test_done
diff --git a/vcs-svn/svndiff.c b/vcs-svn/svndiff.c
index f4c5dae..b7d40c8 100644
--- a/vcs-svn/svndiff.c
+++ b/vcs-svn/svndiff.c
@@ -24,6 +24,7 @@
  * view_selector ::= copyfrom_source
  *   | copyfrom_target
  *   ;
+ * copyfrom_source ::= # binary 00 000000;
  * copyfrom_target ::= # binary 01 000000;
  * copyfrom_data ::= # binary 10 000000;
  * packed_view_selector ::= # view_selector OR-ed with 6 bit value;
@@ -34,6 +35,7 @@
  */
 
 #define INSN_MASK	0xc0
+#define INSN_COPYFROM_SOURCE	0x00
 #define INSN_COPYFROM_TARGET	0x40
 #define INSN_COPYFROM_DATA	0x80
 #define OPERAND_MASK	0x3f
@@ -43,12 +45,13 @@
 #define VLI_BITS_PER_DIGIT 7
 
 struct window {
+	struct sliding_view *in;
 	struct strbuf out;
 	struct strbuf instructions;
 	struct strbuf data;
 };
 
-#define WINDOW_INIT	{ STRBUF_INIT, STRBUF_INIT, STRBUF_INIT }
+#define WINDOW_INIT(w)	{ w, STRBUF_INIT, STRBUF_INIT, STRBUF_INIT }
 
 static void window_release(struct window *ctx)
 {
@@ -161,6 +164,19 @@ static int read_length(struct line_buffer *in, size_t *result, off_t *len)
 	return 0;
 }
 
+static int copyfrom_source(struct window *ctx, const char **instructions,
+			   size_t nbytes, const char *insns_end)
+{
+	size_t offset;
+	if (parse_int(instructions, &offset, insns_end))
+		return -1;
+	if (unsigned_add_overflows(offset, nbytes) ||
+	    offset + nbytes > ctx->in->width)
+		return error("invalid delta: copies source data outside view");
+	strbuf_add(&ctx->out, ctx->in->buf.buf + offset, nbytes);
+	return 0;
+}
+
 static int copyfrom_target(struct window *ctx, const char **instructions,
 			   size_t nbytes, const char *instructions_end)
 {
@@ -209,12 +225,14 @@ static int execute_one_instruction(struct window *ctx,
 	if (parse_first_operand(instructions, &nbytes, insns_end))
 		return -1;
 	switch (instruction & INSN_MASK) {
+	case INSN_COPYFROM_SOURCE:
+		return copyfrom_source(ctx, instructions, nbytes, insns_end);
 	case INSN_COPYFROM_TARGET:
 		return copyfrom_target(ctx, instructions, nbytes, insns_end);
 	case INSN_COPYFROM_DATA:
 		return copyfrom_data(ctx, data_pos, nbytes);
 	default:
-		return error("Unknown instruction %x", instruction);
+		return error("invalid delta: unrecognized instruction");
 	}
 }
 
@@ -238,9 +256,9 @@ static int apply_window_in_core(struct window *ctx)
 }
 
 static int apply_one_window(struct line_buffer *delta, off_t *delta_len,
-			    FILE *out)
+			    struct sliding_view *preimage, FILE *out)
 {
-	struct window ctx = WINDOW_INIT;
+	struct window ctx = WINDOW_INIT(preimage);
 	size_t out_len;
 	size_t instructions_len;
 	size_t data_len;
@@ -285,7 +303,7 @@ int svndiff0_apply(struct line_buffer *delta, off_t delta_len,
 		if (read_offset(delta, &pre_off, &delta_len) ||
 		    read_length(delta, &pre_len, &delta_len) ||
 		    move_window(preimage, pre_off, pre_len) ||
-		    apply_one_window(delta, &delta_len, postimage))
+		    apply_one_window(delta, &delta_len, preimage, postimage))
 			return -1;
 	}
 	return 0;
-- 
1.7.3.2.846.gf4b062
Previous: David BarrNext: David Barr
Message 36 of 72 in “vcs-svn: purge obsolete data structures and code”
  1. David BarrMar 19, 2011
  2. 1/9 vcs-svn: pass paths through to fast-importDavid Barr, Mar 19, 2011
  3. Jonathan NiederMar 19, 2011
  4. 2/9 vcs-svn: avoid using ls command twiceDavid Barr, Mar 19, 2011
  5. Jonathan NiederMar 19, 2011
  6. 3/9 vcs-svn: implement perfect hash for node-prop keysDavid Barr, Mar 19, 2011
  7. Jonathan NiederMar 19, 2011
  8. 1/3 vcs-svn: implement perfect hash for node-prop keysDavid Barr, Mar 21, 2011
  9. 2/3 vcs-svn: implement perfect hash for top-level keysDavid Barr, Mar 21, 2011
  10. 3/3 vcs-svn: use switch rather than cascading ifsDavid Barr, Mar 21, 2011
  11. [PATCHv2] vcs-svn: use switch rather than cascading ifsDavid Barr, Mar 21, 2011
  12. 4/9 vcs-svn: implement perfect hash for top-level keysDavid Barr, Mar 19, 2011
  13. Jonathan NiederMar 19, 2011
  14. 5/9 vcs-svn: factor out usage of string_poolDavid Barr, Mar 19, 2011
  15. Jonathan NiederMar 19, 2011
  16. 6/9 vcs-svn: drop string_poolDavid Barr, Mar 19, 2011
  17. 7/9 vcs-svn: drop trp.hDavid Barr, Mar 19, 2011
  18. 8/9 vcs-svn: drop obj_pool.hDavid Barr, Mar 19, 2011
  19. 9/9 vcs-svn: use strchr to find RFC822 delimiterDavid Barr, Mar 19, 2011
  20. Jonathan NiederMar 19, 2011
  21. vcs-svn: integrate support for text deltasDavid Barr, Mar 19, 2011
  22. 01/16 vcs-svn: improve support for reading large filesDavid Barr, Mar 19, 2011
  23. 02/16 vcs-svn: make buffer_skip_bytes return length readDavid Barr, Mar 19, 2011
  24. 03/16 vcs-svn: make buffer_copy_bytes return length readDavid Barr, Mar 19, 2011
  25. 04/16 vcs-svn: improve reporting of input errorsDavid Barr, Mar 19, 2011
  26. 05/16 vcs-svn: learn to maintain a sliding view of a fileDavid Barr, Mar 19, 2011
  27. 06/16 vcs-svn: skeleton of an svn delta parserDavid Barr, Mar 19, 2011
  28. Jonathan NiederMar 28, 2011
  29. 07/16 vcs-svn: parse svndiff0 window headerDavid Barr, Mar 19, 2011
  30. 08/16 vcs-svn: read the preimage when applying deltasDavid Barr, Mar 19, 2011
  31. 09/16 vcs-svn: read inline data from deltasDavid Barr, Mar 19, 2011
  32. 10/16 vcs-svn: read instructions from deltasDavid Barr, Mar 19, 2011
  33. 11/16 vcs-svn: implement copyfrom_data delta instructionDavid Barr, Mar 19, 2011
  34. 12/16 vcs-svn: verify that deltas consume all inline dataDavid Barr, Mar 19, 2011
  35. 13/16 vcs-svn: let deltas use data from postimageDavid Barr, Mar 19, 2011
  36. 14/16 vcs-svn: let deltas use data from preimageDavid Barr, Mar 19, 2011
  37. 15/16 vcs-svn: microcleanup in svndiff0 window-reading codeDavid Barr, Mar 19, 2011
  38. 16/16 vcs-svn: implement text-delta handlingDavid Barr, Mar 19, 2011
  39. Jonathan NiederMar 28, 2011
  40. David BarrMar 28, 2011
  41. 00/11 vcs-svn: purge obsolete data structures and codeDavid Barr, Mar 21, 2011
  42. 01/11 vcs-svn: use strbuf for revision logDavid Barr, Mar 21, 2011
  43. 02/11 vcs-svn: pass paths through to fast-importDavid Barr, Mar 21, 2011
  44. 03/11 vcs-svn: avoid using ls command twiceDavid Barr, Mar 21, 2011
  45. 04/11 vcs-svn: implement perfect hash for node-prop keysDavid Barr, Mar 21, 2011
  46. 05/11 vcs-svn: implement perfect hash for top-level keysDavid Barr, Mar 21, 2011
  47. 06/11 vcs-svn: use switch rather than cascading ifsDavid Barr, Mar 21, 2011
  48. 07/11 vcs-svn: factor out usage of string_poolDavid Barr, Mar 21, 2011
  49. 08/11 vcs-svn: drop string_poolDavid Barr, Mar 21, 2011
  50. =??q?=5BPATCH=2009/11=5D=20vcs-svn=3A=20drop=20trp=2Eh?=David Barr, Mar 21, 2011
  51. 10/11 vcs-svn: drop obj_pool.hDavid Barr, Mar 21, 2011
  52. 11/11 vcs-svn: use strchr to find RFC822 delimiterDavid Barr, Mar 21, 2011
  53. [PULL svn-fe] vcs-svn: simplifications, error handling improvementsJonathan Nieder, Mar 23, 2011
  54. Junio C HamanoMar 23, 2011
  55. Junio C HamanoMar 23, 2011
  56. Jonathan NiederMar 26, 2011
  57. t0081-line-buffer.sh hangs (Re: [PULL svn-fe] vcs-svn: simplifications, error handling improvements)Jonathan Nieder, Mar 26, 2011
  58. David BarrMar 23, 2011
  59. fixup! vcs-svn: improve reporting of input errorsDavid Barr, Mar 24, 2011
  60. Jonathan NiederMar 25, 2011
  61. 0/4 vcs-svn: null bytes in propertiesJonathan Nieder, Mar 25, 2011
  62. 1/4 vcs-svn: make reading of properties binary-safeJonathan Nieder, Mar 25, 2011
  63. tbMar 28, 2011
  64. Jonathan NiederMar 28, 2011
  65. Torsten BögershausenMar 28, 2011
  66. Jonathan NiederMar 28, 2011
  67. 2/4 vcs-svn: remove buffer_read_stringJonathan Nieder, Mar 25, 2011
  68. 3/4 vcs-svn: avoid unnecessary copying of log message and authorJonathan Nieder, Mar 25, 2011
  69. 4/4 vcs-svn: handle log message with embedded null bytesJonathan Nieder, Mar 25, 2011
  70. Jonathan NiederMar 26, 2011
  71. Junio C HamanoMar 26, 2011
  72. vcs-svn: add missing cast to printf argumentJonathan Nieder, Mar 28, 2011

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.