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

[PATCH 4/4] vcs-svn: handle log message with embedded null bytes

From
Jonathan Nieder <jrnieder@gmail.com>
Date
Mar 25, 2011, 04:11 UTC
Message-ID
<20110325041120.GE3007@elie>
In-Reply-To
<20110325033431.GA3007@elie>

Use fwrite instead of printf to write the log message to fast-import so embedded ASCII NUL characters can be preserved.

Currently "git log" doesn't show the embedded NULs but "git cat-file commit" can.

Signed-off-by: Jonathan Nieder <jrnieder@gmail.com>
---
 t/t9010-svn-fe.sh     |   77 +++++++++++++++++++++++++++++++++++++++++++++++++
 vcs-svn/fast_export.c |   12 ++++---
 vcs-svn/fast_export.h |    9 +++--
 vcs-svn/repo_tree.c   |    5 ++-
 vcs-svn/repo_tree.h   |    4 +-
 vcs-svn/svndump.c     |    2 +-
 6 files changed, 95 insertions(+), 14 deletions(-)
diff --git a/t/t9010-svn-fe.sh b/t/t9010-svn-fe.sh
index 47f1e4f..be35139 100755
--- a/t/t9010-svn-fe.sh
+++ b/t/t9010-svn-fe.sh
@@ -397,6 +397,83 @@ test_expect_success 'null byte in property value' '
 	test_cmp expect.message actual.message
 '
 
+test_expect_success 'null bytes' '
+	# Caveat: svnadmin 1.6.16 (r1073529) truncates at \0 in the
+	# svn:specialQnotreally example.
+	reinit_git &&
+	cat >expect <<-\EOF &&
+	OBJID
+	:100644 100644 OBJID OBJID M	greeting
+	OBJID
+	:000000 100644 OBJID OBJID A	greeting
+	EOF
+	printf "\n%s" "something with a null byte (Q)" >expect.message &&
+	printf "%s\n" "helQo" >expect.hello1 &&
+	printf "%s\n" "link hello" >expect.hello2 &&
+	{
+		properties svn:log "something with a null byte (Q)" &&
+		echo PROPS-END
+	} |
+	q_to_nul >props &&
+	{
+		q_to_nul <<-\EOF &&
+		SVN-fs-dump-format-version: 3
+
+		Revision-number: 1
+		Prop-content-length: 10
+		Content-length: 10
+
+		PROPS-END
+
+		Node-path: greeting
+		Node-kind: file
+		Node-action: add
+		Prop-content-length: 10
+		Text-content-length: 6
+		Content-length: 16
+
+		PROPS-END
+		helQo
+
+		Revision-number: 2
+		EOF
+		echo Prop-content-length: $(wc -c <props) &&
+		echo Content-length: $(wc -c <props) &&
+		echo &&
+		cat props &&
+		q_to_nul <<-\EOF
+
+		Node-path: greeting
+		Node-kind: file
+		Node-action: change
+		Prop-content-length: 43
+		Text-content-length: 11
+		Content-length: 54
+
+		K 21
+		svn:specialQnotreally
+		V 1
+		*
+		PROPS-END
+		link hello
+		EOF
+	} >8bitclean.dump &&
+	test-svn-fe 8bitclean.dump >stream &&
+	git fast-import <stream &&
+	{
+		git rev-list HEAD |
+		git diff-tree --root --stdin |
+		sed "s/$_x40/OBJID/g"
+	} >actual &&
+	git cat-file commit HEAD | nul_to_q | sed -ne "/^\$/,\$ p" >actual.message &&
+	git cat-file blob HEAD^:greeting | nul_to_q >actual.hello1 &&
+	git cat-file blob HEAD:greeting | nul_to_q >actual.hello2 &&
+	test_cmp expect actual &&
+	test_cmp expect.message actual.message &&
+	test_cmp expect.hello1 actual.hello1 &&
+	test_cmp expect.hello2 actual.hello2
+'
+
 test_expect_success 'change file mode and reiterate content' '
 	reinit_git &&
 	cat >expect <<-\EOF &&
diff --git a/vcs-svn/fast_export.c b/vcs-svn/fast_export.c
index a4d4d99..2e5bb67 100644
--- a/vcs-svn/fast_export.c
+++ b/vcs-svn/fast_export.c
@@ -31,12 +31,14 @@ 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, const char *author, char *log,
+void fast_export_commit(uint32_t revision, const char *author,
+			const struct strbuf *log,
 			const char *uuid, const char *url,
 			unsigned long timestamp)
 {
+	static const struct strbuf empty = STRBUF_INIT;
 	if (!log)
-		log = "";
+		log = &empty;
 	if (*uuid && *url) {
 		snprintf(gitsvnline, MAX_GITSVN_LINE_LEN,
 				"\n\ngit-svn-id: %s@%"PRIu32" %s\n",
@@ -49,9 +51,9 @@ void fast_export_commit(uint32_t revision, const char *author, char *log,
 		   *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);
+	printf("data %"PRIuMAX"\n", log->len + strlen(gitsvnline));
+	fwrite(log->buf, log->len, 1, stdout);
+	printf("%s\n", gitsvnline);
 	if (!first_commit_done) {
 		if (revision > 1)
 			printf("from refs/heads/master^0\n");
diff --git a/vcs-svn/fast_export.h b/vcs-svn/fast_export.h
index 05cf97f..5878381 100644
--- a/vcs-svn/fast_export.h
+++ b/vcs-svn/fast_export.h
@@ -1,14 +1,15 @@
 #ifndef FAST_EXPORT_H_
 #define FAST_EXPORT_H_
 
-#include "line_buffer.h"
+struct line_buffer;
+struct strbuf;
 
 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, const char *author, char *log,
-			const char *uuid, const char *url,
-			unsigned long timestamp);
+void fast_export_commit(uint32_t revision, const char *author,
+			const struct strbuf *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 d722e32..8caa015 100644
--- a/vcs-svn/repo_tree.c
+++ b/vcs-svn/repo_tree.c
@@ -278,8 +278,9 @@ void repo_diff(uint32_t r1, uint32_t r2)
 		    repo_commit_root_dir(commit_pointer(r2)));
 }
 
-void repo_commit(uint32_t revision, const char *author, char *log,
-		 const char *uuid, const char *url, unsigned long timestamp)
+void repo_commit(uint32_t revision, const char *author,
+		const struct strbuf *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 a1b0e87..37bde2e 100644
--- a/vcs-svn/repo_tree.h
+++ b/vcs-svn/repo_tree.h
@@ -1,7 +1,7 @@
 #ifndef REPO_TREE_H_
 #define REPO_TREE_H_
 
-#include "git-compat-util.h"
+struct strbuf;
 
 #define REPO_MODE_DIR 0040000
 #define REPO_MODE_BLB 0100644
@@ -18,7 +18,7 @@ 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, const char *author,
-		char *log, const char *uuid, const char *url,
+		const struct strbuf *log, const char *uuid, const char *url,
 		long unsigned timestamp);
 void repo_diff(uint32_t r1, uint32_t r2);
 void repo_init(void);
diff --git a/vcs-svn/svndump.c b/vcs-svn/svndump.c
index 88ecef1..eef49ca 100644
--- a/vcs-svn/svndump.c
+++ b/vcs-svn/svndump.c
@@ -274,7 +274,7 @@ static void handle_revision(void)
 {
 	if (rev_ctx.revision)
 		repo_commit(rev_ctx.revision, rev_ctx.author.buf,
-			rev_ctx.log.buf, dump_ctx.uuid.buf, dump_ctx.url.buf,
+			&rev_ctx.log, dump_ctx.uuid.buf, dump_ctx.url.buf,
 			rev_ctx.timestamp);
 }
 
-- 
1.7.4.1
Previous: Jonathan NiederNext: Jonathan Nieder
Message 69 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.