From: David Barr <david.barr@cordelta.com>
To: Git Mailing List <git@vger.kernel.org>
Cc: Jonathan Nieder <jrnieder@gmail.com>,
Ramkumar Ramachandra <artagnon@gmail.com>,
Sverre Rabbelier <srabbelier@gmail.com>,
David Barr <david.barr@cordelta.com>
Subject: [PATCH 5/5] svn-fe: Use the cat-blob command to apply deltas
Date: Fri, 15 Oct 2010 23:54:16 +1100 [thread overview]
Message-ID: <1287147256-9457-6-git-send-email-david.barr@cordelta.com> (raw)
In-Reply-To: <1287147256-9457-1-git-send-email-david.barr@cordelta.com>
Use the new cat-blob command for fast-import to extract
blobs so that text-deltas may be applied.
The backchannel should only need to be configured when
parsing v3 svn dump streams.
Based-on-patch-by: Ramkumar Ramachandra <artagnon@gmail.com>
Based-on-patch-by: Jonathan Nieder <jrnieder@gmail.com>
Tested-by: David Barr <david.barr@cordelta.com>
Signed-off-by: David Barr <david.barr@cordelta.com>
---
contrib/svn-fe/svn-fe.txt | 6 +++-
t/t9010-svn-fe.sh | 6 ++--
vcs-svn/fast_export.c | 86 +++++++++++++++++++++++++++++++++++++++++++-
3 files changed, 92 insertions(+), 6 deletions(-)
diff --git a/contrib/svn-fe/svn-fe.txt b/contrib/svn-fe/svn-fe.txt
index 35f84bd..39ffa07 100644
--- a/contrib/svn-fe/svn-fe.txt
+++ b/contrib/svn-fe/svn-fe.txt
@@ -7,7 +7,11 @@ svn-fe - convert an SVN "dumpfile" to a fast-import stream
SYNOPSIS
--------
-svnadmin dump --incremental REPO | svn-fe [url] | git fast-import
+[verse]
+mkfifo backchannel &&
+svnadmin dump --incremental REPO |
+ svn-fe [url] 3<backchannel |
+ git fast-import --cat-blob-fd=3 3>backchannel
DESCRIPTION
-----------
diff --git a/t/t9010-svn-fe.sh b/t/t9010-svn-fe.sh
index de976ed..d750c7a 100755
--- a/t/t9010-svn-fe.sh
+++ b/t/t9010-svn-fe.sh
@@ -34,10 +34,10 @@ test_dump () {
svnadmin load "$label-svn" < "$TEST_DIRECTORY/$dump" &&
svn_cmd export "file://$PWD/$label-svn" "$label-svnco" &&
git init "$label-git" &&
- test-svn-fe "$TEST_DIRECTORY/$dump" >"$label.fe" &&
(
- cd "$label-git" &&
- git fast-import < ../"$label.fe"
+ cd "$label-git" && mkfifo backchannel && \
+ test-svn-fe "$TEST_DIRECTORY/$dump" 3< backchannel | \
+ git fast-import --cat-blob-fd=3 3> backchannel
) &&
(
cd "$label-svnco" &&
diff --git a/vcs-svn/fast_export.c b/vcs-svn/fast_export.c
index b017dfb..812563d 100644
--- a/vcs-svn/fast_export.c
+++ b/vcs-svn/fast_export.c
@@ -8,10 +8,17 @@
#include "line_buffer.h"
#include "repo_tree.h"
#include "string_pool.h"
+#include "svndiff.h"
#define MAX_GITSVN_LINE_LEN 4096
+#define REPORT_FILENO 3
+
+#define SHA1_HEX_LENGTH 40
static uint32_t first_commit_done;
+static struct line_buffer preimage = LINE_BUFFER_INIT;
+static struct line_buffer postimage = LINE_BUFFER_INIT;
+static struct line_buffer backchannel = LINE_BUFFER_INIT;
void fast_export_delete(uint32_t depth, uint32_t *path)
{
@@ -63,16 +70,91 @@ void fast_export_commit(uint32_t revision, uint32_t author, char *log,
printf("progress Imported commit %"PRIu32".\n\n", revision);
}
+static int fast_export_save_blob(FILE *out)
+{
+ size_t len;
+ char *header;
+ char *end;
+ char *tail;
+
+ if (!backchannel.infile)
+ backchannel.infile = fdopen(REPORT_FILENO, "r");
+ if (!backchannel.infile)
+ return error("Could not open backchannel fd: %d", REPORT_FILENO);
+ header = buffer_read_line(&backchannel);
+ if (header == NULL)
+ return 1;
+ end = strchr(header, '\0');
+ if (end - header > 7 && !strcmp(end - 7, "missing"))
+ return error("cat-blob reports missing blob: %s", header);
+ if (end - header < SHA1_HEX_LENGTH)
+ return error("cat-blob header too short for SHA1: %s", header);
+ if (strncmp(header + SHA1_HEX_LENGTH, " blob ", 6))
+ return error("cat-blob header has wrong object type: %s", header);
+ len = strtoumax(header + SHA1_HEX_LENGTH + 6, &end, 10);
+ if (end == header + SHA1_HEX_LENGTH + 6)
+ return error("cat-blob header did not contain length: %s", header);
+ if (*end)
+ return error("cat-blob header contained garbage after length: %s", header);
+ buffer_copy_bytes(&backchannel, out, len);
+ tail = buffer_read_line(&backchannel);
+ if (!tail)
+ return 1;
+ if (*tail)
+ return error("cat-blob trailing line contained garbage: %s", tail);
+ return 0;
+}
+
void fast_export_blob(uint32_t mode, uint32_t mark, uint32_t len,
uint32_t delta, uint32_t srcMark, uint32_t srcMode,
struct line_buffer *input)
{
+ long preimage_len = 0;
+
+ if (delta) {
+ if (!preimage.infile)
+ preimage.infile = tmpfile();
+ if (!preimage.infile)
+ die("Unable to open temp file for blob retrieval");
+ if (srcMark) {
+ printf("cat-blob :%"PRIu32"\n", srcMark);
+ fflush(stdout);
+ if (srcMode == REPO_MODE_LNK)
+ fwrite("link ", 1, 5, preimage.infile);
+ if (fast_export_save_blob(preimage.infile))
+ die("Failed to retrieve blob for delta application");
+ }
+ preimage_len = ftell(preimage.infile);
+ fseek(preimage.infile, 0, SEEK_SET);
+ if (!postimage.infile)
+ postimage.infile = tmpfile();
+ if (!postimage.infile)
+ die("Unable to open temp file for blob application");
+ svndiff0_apply(input, len, &preimage, postimage.infile);
+ len = ftell(postimage.infile);
+ fseek(postimage.infile, 0, SEEK_SET);
+ }
+
if (mode == REPO_MODE_LNK) {
/* svn symlink blobs start with "link " */
- buffer_skip_bytes(input, 5);
+ if (delta)
+ buffer_skip_bytes(&postimage, 5);
+ else
+ buffer_skip_bytes(input, 5);
len -= 5;
}
printf("blob\nmark :%"PRIu32"\ndata %"PRIu32"\n", mark, len);
- buffer_copy_bytes(input, stdout, len);
+ if (!delta)
+ buffer_copy_bytes(input, stdout, len);
+ else
+ buffer_copy_bytes(&postimage, stdout, len);
fputc('\n', stdout);
+
+ if (preimage.infile) {
+ fseek(preimage.infile, 0, SEEK_SET);
+ }
+
+ if (postimage.infile) {
+ fseek(postimage.infile, 0, SEEK_SET);
+ }
}
--
1.7.3.32.g634ef
next prev parent reply other threads:[~2010-10-15 12:55 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-10-15 12:54 [PATCHv2] Add support for subversion dump format v3 David Barr
2010-10-15 12:54 ` [PATCH 1/5] fast-import: Let importers retrieve blobs David Barr
2010-10-18 7:36 ` Ramkumar Ramachandra
2010-10-18 8:50 ` Jonathan Nieder
2010-10-18 8:26 ` Jonathan Nieder
[not found] ` <20101119093530.GA19061@burratino>
2010-11-19 9:47 ` [PATCH 3/4] fast-import: let " Jonathan Nieder
2010-11-19 9:51 ` [PATCH 4/4] fast-import: Allow cat-blob requests at arbitrary points in stream Jonathan Nieder
[not found] ` <20101119094045.GC19061@burratino>
2010-11-19 11:58 ` [PATCH 2/4] fast-import: clarify documentation of "feature" command Sverre Rabbelier
2010-11-28 19:41 ` [PATCH/RFC v3 resend 0/4] fast-import: Let importers retrieve blobs Jonathan Nieder
2010-11-28 19:42 ` [PATCH 1/4] fast-import: stricter parsing of integer options Jonathan Nieder
2010-11-30 1:01 ` Junio C Hamano
2010-11-28 19:43 ` [PATCH 2/4] fast-import: clarify documentation of "feature" command Jonathan Nieder
2010-11-28 19:45 ` [PATCH 3/4] fast-import: let importers retrieve blobs Jonathan Nieder
2010-11-29 23:48 ` [PATCH] fixup! " David Barr
2010-11-30 0:16 ` David Barr
2010-11-30 1:22 ` Jonathan Nieder
2010-12-03 10:30 ` [PATCH 3/4] " Thomas Rast
2010-12-03 19:06 ` Jonathan Nieder
2010-12-03 20:17 ` Junio C Hamano
2010-12-03 20:26 ` Jonathan Nieder
2010-12-04 13:24 ` Thomas Rast
2010-12-04 2:35 ` Jonathan Nieder
2011-01-16 2:16 ` [PATCH] Documentation/fast-import: capitalize beginning of sentence Jonathan Nieder
2010-11-28 19:45 ` [PATCH 4/4] fast-import: Allow cat-blob requests at arbitrary points in stream Jonathan Nieder
2010-10-15 12:54 ` [PATCH 2/5] vcs-svn: Extend svndump to parse version 3 format David Barr
2010-10-15 12:54 ` [PATCH 3/5] vcs-svn: Implement prop-delta handling David Barr
2010-10-18 15:10 ` Ramkumar Ramachandra
2010-10-15 12:54 ` [PATCH 4/5] vcs-svn: Add outfile option to buffer_copy_bytes() David Barr
2010-10-18 8:59 ` Jonathan Nieder
2010-10-15 12:54 ` David Barr [this message]
2010-10-18 6:57 ` [PATCH 5/5] svn-fe: Use the cat-blob command to apply deltas Ramkumar Ramachandra
2010-10-18 9:24 ` Jonathan Nieder
2010-10-18 12:18 ` Ramkumar Ramachandra
2010-10-18 9:54 ` [PATCHv2] Add support for subversion dump format v3 Jonathan Nieder
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: http://vger.kernel.org/majordomo-info.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1287147256-9457-6-git-send-email-david.barr@cordelta.com \
--to=david.barr@cordelta.com \
--cc=artagnon@gmail.com \
--cc=git@vger.kernel.org \
--cc=jrnieder@gmail.com \
--cc=srabbelier@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://80x24.org/mirrors/git.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).