[PATCH v6 15/16] remote-svn: add marks-file regeneration

[PATCH v6 15/16] remote-svn: add marks-file regeneration

[Florian Achleitner]

fast-import mark files are stored outside the object database and are
therefore not fetched and can be lost somehow else.  marks provide a
svn revision --> git sha1 mapping, while the notes that are attached
to each commit when it is imported provide a git sha1 --> svn revision
mapping.

If the marks file is not available or not plausible, regenerate it by
walking through the notes tree.  , i.e.  The plausibility check tests
if the highest revision in the marks file matches the revision of the
top ref. It doesn't ensure that the mark file is completely correct.
This could only be done with an effort equal to unconditional
regeneration.

Signed-off-by: Florian Achleitner <florian.achleitner.2.6.31@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 remote-testsvn.c |   68 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 68 insertions(+)

diff --git a/remote-testsvn.c b/remote-testsvn.c
index e90d221..09dc304 100644
--- a/remote-testsvn.c
+++ b/remote-testsvn.c
@@ -86,6 +86,73 @@ static int parse_rev_note(const char *msg, struct rev_note *res) {
 	return 0;
 }
 
+static int note2mark_cb(const unsigned char *object_sha1,
+		const unsigned char *note_sha1, char *note_path,
+		void *cb_data) {
+	FILE *file = (FILE *)cb_data;
+	char *msg;
+	unsigned long msglen;
+	enum object_type type;
+	struct rev_note note;
+	if (!(msg = read_sha1_file(note_sha1, &type, &msglen)) ||
+			!msglen || type != OBJ_BLOB) {
+		free(msg);
+		return 1;
+	}
+	if (parse_rev_note(msg, &note))
+		return 2;
+	if (fprintf(file, ":%d %s\n", note.rev_nr, sha1_to_hex(object_sha1)) < 1)
+		return 3;
+	return 0;
+}
+
+static void regenerate_marks(void)
+{
+	int ret;
+	FILE *marksfile;
+	marksfile = fopen(marksfilename, "w+");
+	if (!marksfile)
+		die_errno("Couldn't create mark file %s.", marksfilename);
+	ret = for_each_note(NULL, 0, note2mark_cb, marksfile);
+	if (ret)
+		die("Regeneration of marks failed, returned %d.", ret);
+	fclose(marksfile);
+}
+
+static void check_or_regenerate_marks(int latestrev) {
+	FILE *marksfile;
+	char *line = NULL;
+	size_t linelen = 0;
+	struct strbuf sb = STRBUF_INIT;
+	int found = 0;
+
+	if (latestrev < 1)
+		return;
+
+	init_notes(NULL, notes_ref, NULL, 0);
+	marksfile = fopen(marksfilename, "r");
+	if (!marksfile) {
+		regenerate_marks();
+		marksfile = fopen(marksfilename, "r");
+		if (!marksfile)
+			die_errno("cannot read marks file %s!", marksfilename);
+		fclose(marksfile);
+	} else {
+		strbuf_addf(&sb, ":%d ", latestrev);
+		while (getline(&line, &linelen, marksfile) != -1) {
+			if (!prefixcmp(line, sb.buf)) {
+				found++;
+				break;
+			}
+		}
+		fclose(marksfile);
+		if (!found)
+			regenerate_marks();
+	}
+	free_notes(NULL);
+	strbuf_release(&sb);
+}
+
 static int cmd_import(const char *line)
 {
 	int code;
@@ -111,6 +178,7 @@ static int cmd_import(const char *line)
 			free(note_msg);
 		}
 	}
+	check_or_regenerate_marks(startrev - 1);
 
 	if (dump_from_file) {
 		dumpin_fd = open(url, O_RDONLY);
-- 
1.7.9.5

Re: [PATCH v6 15/16] remote-svn: add marks-file regeneration

[Joachim Schmitz]

"Florian Achleitner" <florian.achleitner.2.6.31@gmail.com> schrieb im Newsbeitrag
news:<1345662961-9587-16-git-send-email-florian.achleitner.2.6.31@gmail.com>...
> fast-import mark files are stored outside the object database and are
> therefore not fetched and can be lost somehow else.  marks provide a
> svn revision --> git sha1 mapping, while the notes that are attached
> to each commit when it is imported provide a git sha1 --> svn revision
> mapping.
> 
> If the marks file is not available or not plausible, regenerate it by
> walking through the notes tree.  , i.e.  The plausibility check tests
> if the highest revision in the marks file matches the revision of the
> top ref. It doesn't ensure that the mark file is completely correct.
> This could only be done with an effort equal to unconditional
> regeneration.
> 
> Signed-off-by: Florian Achleitner <florian.achleitner.2.6.31@gmail.com>
> Signed-off-by: Junio C Hamano <gitster@pobox.com>
> ---
>  remote-testsvn.c |   68 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 68 insertions(+)
> 
> diff --git a/remote-testsvn.c b/remote-testsvn.c
> index e90d221..09dc304 100644
> --- a/remote-testsvn.c
> +++ b/remote-testsvn.c
...
> +static void check_or_regenerate_marks(int latestrev) {
> +	FILE *marksfile;
> +	char *line = NULL;
> +	size_t linelen = 0;
> +	struct strbuf sb = STRBUF_INIT;
> +	int found = 0;
> +
> +	if (latestrev < 1)
> +		return;
> +
> +	init_notes(NULL, notes_ref, NULL, 0);
> +	marksfile = fopen(marksfilename, "r");
> +	if (!marksfile) {
> +		regenerate_marks();
> +		marksfile = fopen(marksfilename, "r");
> +		if (!marksfile)
> +			die_errno("cannot read marks file %s!", marksfilename);
> +		fclose(marksfile);
> +	} else {
> +		strbuf_addf(&sb, ":%d ", latestrev);
> +		while (getline(&line, &linelen, marksfile) != -1) {

getline() is not available to anybody, e.g. it is not in HP NonStop.

Bye, Jojo

RE: [PATCH v6 15/16] remote-svn: add marks-file regeneration

[Joachim Schmitz]

> From: Joachim Schmitz [mailto:jojo@schmitz-digital.de]
> Sent: Saturday, August 25, 2012 5:55 PM
> To: 'florian.achleitner.2.6.31@gmail.com'
> Cc: git@vger.kernel.org
> Subject: Re: [PATCH v6 15/16] remote-svn: add marks-file regeneration
> 
> "Florian Achleitner" <florian.achleitner.2.6.31@gmail.com> schrieb im Newsbeitrag news:<1345662961-9587-16-git-send-email-
> florian.achleitner.2.6.31@gmail.com>...
> > fast-import mark files are stored outside the object database and are
> > therefore not fetched and can be lost somehow else.  marks provide a
> > svn revision --> git sha1 mapping, while the notes that are attached
> > to each commit when it is imported provide a git sha1 --> svn revision
> > mapping.
> >
> > If the marks file is not available or not plausible, regenerate it by
> > walking through the notes tree.  , i.e.  The plausibility check tests
> > if the highest revision in the marks file matches the revision of the
> > top ref. It doesn't ensure that the mark file is completely correct.
> > This could only be done with an effort equal to unconditional
> > regeneration.
> >
> > Signed-off-by: Florian Achleitner <florian.achleitner.2.6.31@gmail.com>
> > Signed-off-by: Junio C Hamano <gitster@pobox.com>
> > ---
> >  remote-testsvn.c |   68 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
> >  1 file changed, 68 insertions(+)
> >
> > diff --git a/remote-testsvn.c b/remote-testsvn.c
> > index e90d221..09dc304 100644
> > --- a/remote-testsvn.c
> > +++ b/remote-testsvn.c
> ...
> > +static void check_or_regenerate_marks(int latestrev) {
> > +	FILE *marksfile;
> > +	char *line = NULL;
> > +	size_t linelen = 0;
> > +	struct strbuf sb = STRBUF_INIT;
> > +	int found = 0;
> > +
> > +	if (latestrev < 1)
> > +		return;
> > +
> > +	init_notes(NULL, notes_ref, NULL, 0);
> > +	marksfile = fopen(marksfilename, "r");
> > +	if (!marksfile) {
> > +		regenerate_marks();
> > +		marksfile = fopen(marksfilename, "r");
> > +		if (!marksfile)
> > +			die_errno("cannot read marks file %s!", marksfilename);
> > +		fclose(marksfile);
> > +	} else {
> > +		strbuf_addf(&sb, ":%d ", latestrev);
> > +		while (getline(&line, &linelen, marksfile) != -1) {
> 
> getline() is not available to anybody, e.g. it is not in HP NonStop.

I'd like to confirm that Ramsey's patch works for me too, so I second his request.
(Subject: [PATCH 1/3] remote-testsvn.c: Avoid the getline() GNU extension function)

Bye, Jojo