summaryrefslogtreecommitdiff
path: root/vcs-svn
diff options
context:
space:
mode:
Diffstat (limited to 'vcs-svn')
-rw-r--r--vcs-svn/fast_export.c40
-rw-r--r--vcs-svn/fast_export.h11
-rw-r--r--vcs-svn/line_buffer.c121
-rw-r--r--vcs-svn/line_buffer.h33
-rw-r--r--vcs-svn/line_buffer.txt49
-rw-r--r--vcs-svn/repo_tree.c55
-rw-r--r--vcs-svn/repo_tree.h13
-rw-r--r--vcs-svn/string_pool.c2
-rw-r--r--vcs-svn/svndump.c438
-rw-r--r--vcs-svn/svndump.h2
-rw-r--r--vcs-svn/trp.h3
-rw-r--r--vcs-svn/trp.txt12
12 files changed, 512 insertions, 267 deletions
diff --git a/vcs-svn/fast_export.c b/vcs-svn/fast_export.c
index 6cfa256a37..99ed70b88a 100644
--- a/vcs-svn/fast_export.c
+++ b/vcs-svn/fast_export.c
@@ -31,27 +31,30 @@ 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, uint32_t author, char *log,
- uint32_t uuid, uint32_t url,
+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 = "";
- if (~uuid && ~url) {
+ log = ∅
+ if (*uuid && *url) {
snprintf(gitsvnline, MAX_GITSVN_LINE_LEN,
"\n\ngit-svn-id: %s@%"PRIu32" %s\n",
- pool_fetch(url), revision, pool_fetch(uuid));
+ url, revision, uuid);
} else {
*gitsvnline = '\0';
}
printf("commit refs/heads/master\n");
printf("committer %s <%s@%s> %ld +0000\n",
- ~author ? pool_fetch(author) : "nobody",
- ~author ? pool_fetch(author) : "nobody",
- ~uuid ? pool_fetch(uuid) : "local", timestamp);
- printf("data %"PRIu32"\n%s%s\n",
- (uint32_t) (strlen(log) + strlen(gitsvnline)),
- log, gitsvnline);
+ *author ? author : "nobody",
+ *author ? author : "nobody",
+ *uuid ? uuid : "local", timestamp);
+ printf("data %"PRIuMAX"\n",
+ (uintmax_t) (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");
@@ -63,14 +66,23 @@ void fast_export_commit(uint32_t revision, uint32_t author, char *log,
printf("progress Imported commit %"PRIu32".\n\n", revision);
}
-void fast_export_blob(uint32_t mode, uint32_t mark, uint32_t len)
+static void die_short_read(struct line_buffer *input)
+{
+ if (buffer_ferror(input))
+ die_errno("error reading dump file");
+ die("invalid dump: unexpected end of file");
+}
+
+void fast_export_blob(uint32_t mode, uint32_t mark, uint32_t len, struct line_buffer *input)
{
if (mode == REPO_MODE_LNK) {
/* svn symlink blobs start with "link " */
- buffer_skip_bytes(5);
len -= 5;
+ if (buffer_skip_bytes(input, 5) != 5)
+ die_short_read(input);
}
printf("blob\nmark :%"PRIu32"\ndata %"PRIu32"\n", mark, len);
- buffer_copy_bytes(len);
+ if (buffer_copy_bytes(input, len) != len)
+ die_short_read(input);
fputc('\n', stdout);
}
diff --git a/vcs-svn/fast_export.h b/vcs-svn/fast_export.h
index 2aaaea53d5..33a8fe996f 100644
--- a/vcs-svn/fast_export.h
+++ b/vcs-svn/fast_export.h
@@ -1,11 +1,16 @@
#ifndef FAST_EXPORT_H_
#define FAST_EXPORT_H_
+#include "line_buffer.h"
+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, uint32_t author, char *log,
- uint32_t uuid, uint32_t url, unsigned long timestamp);
-void fast_export_blob(uint32_t mode, uint32_t mark, uint32_t len);
+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);
#endif
diff --git a/vcs-svn/line_buffer.c b/vcs-svn/line_buffer.c
index 1543567093..c39038723e 100644
--- a/vcs-svn/line_buffer.c
+++ b/vcs-svn/line_buffer.c
@@ -5,47 +5,81 @@
#include "git-compat-util.h"
#include "line_buffer.h"
-#include "obj_pool.h"
+#include "strbuf.h"
-#define LINE_BUFFER_LEN 10000
#define COPY_BUFFER_LEN 4096
-/* Create memory pool for char sequence of known length */
-obj_pool_gen(blob, char, 4096)
+int buffer_init(struct line_buffer *buf, const char *filename)
+{
+ buf->infile = filename ? fopen(filename, "r") : stdin;
+ if (!buf->infile)
+ return -1;
+ return 0;
+}
-static char line_buffer[LINE_BUFFER_LEN];
-static char byte_buffer[COPY_BUFFER_LEN];
-static FILE *infile;
+int buffer_fdinit(struct line_buffer *buf, int fd)
+{
+ buf->infile = fdopen(fd, "r");
+ if (!buf->infile)
+ return -1;
+ return 0;
+}
-int buffer_init(const char *filename)
+int buffer_tmpfile_init(struct line_buffer *buf)
{
- infile = filename ? fopen(filename, "r") : stdin;
- if (!infile)
+ buf->infile = tmpfile();
+ if (!buf->infile)
return -1;
return 0;
}
-int buffer_deinit(void)
+int buffer_deinit(struct line_buffer *buf)
{
int err;
- if (infile == stdin)
- return ferror(infile);
- err = ferror(infile);
- err |= fclose(infile);
+ if (buf->infile == stdin)
+ return ferror(buf->infile);
+ err = ferror(buf->infile);
+ err |= fclose(buf->infile);
return err;
}
+FILE *buffer_tmpfile_rewind(struct line_buffer *buf)
+{
+ rewind(buf->infile);
+ return buf->infile;
+}
+
+long buffer_tmpfile_prepare_to_read(struct line_buffer *buf)
+{
+ long pos = ftell(buf->infile);
+ if (pos < 0)
+ return error("ftell error: %s", strerror(errno));
+ if (fseek(buf->infile, 0, SEEK_SET))
+ return error("seek error: %s", strerror(errno));
+ return pos;
+}
+
+int buffer_ferror(struct line_buffer *buf)
+{
+ return ferror(buf->infile);
+}
+
+int buffer_read_char(struct line_buffer *buf)
+{
+ return fgetc(buf->infile);
+}
+
/* Read a line without trailing newline. */
-char *buffer_read_line(void)
+char *buffer_read_line(struct line_buffer *buf)
{
char *end;
- if (!fgets(line_buffer, sizeof(line_buffer), infile))
+ if (!fgets(buf->line_buffer, sizeof(buf->line_buffer), buf->infile))
/* Error or data exhausted. */
return NULL;
- end = line_buffer + strlen(line_buffer);
+ end = buf->line_buffer + strlen(buf->line_buffer);
if (end[-1] == '\n')
end[-1] = '\0';
- else if (feof(infile))
+ else if (feof(buf->infile))
; /* No newline at end of file. That's fine. */
else
/*
@@ -54,44 +88,43 @@ char *buffer_read_line(void)
* but for now let's return an error.
*/
return NULL;
- return line_buffer;
+ return buf->line_buffer;
}
-char *buffer_read_string(uint32_t len)
+void buffer_read_binary(struct line_buffer *buf,
+ struct strbuf *sb, uint32_t size)
{
- char *s;
- blob_free(blob_pool.size);
- s = blob_pointer(blob_alloc(len + 1));
- s[fread(s, 1, len, infile)] = '\0';
- return ferror(infile) ? NULL : s;
+ strbuf_fread(sb, size, buf->infile);
}
-void buffer_copy_bytes(uint32_t len)
+off_t buffer_copy_bytes(struct line_buffer *buf, off_t nbytes)
{
- uint32_t in;
- while (len > 0 && !feof(infile) && !ferror(infile)) {
- in = len < COPY_BUFFER_LEN ? len : COPY_BUFFER_LEN;
- in = fread(byte_buffer, 1, in, infile);
- len -= in;
+ char byte_buffer[COPY_BUFFER_LEN];
+ off_t done = 0;
+ while (done < nbytes && !feof(buf->infile) && !ferror(buf->infile)) {
+ off_t len = nbytes - done;
+ size_t in = len < COPY_BUFFER_LEN ? len : COPY_BUFFER_LEN;
+ in = fread(byte_buffer, 1, in, buf->infile);
+ done += in;
fwrite(byte_buffer, 1, in, stdout);
- if (ferror(stdout)) {
- buffer_skip_bytes(len);
- return;
- }
+ if (ferror(stdout))
+ return done + buffer_skip_bytes(buf, nbytes - done);
}
+ return done;
}
-void buffer_skip_bytes(uint32_t len)
+off_t buffer_skip_bytes(struct line_buffer *buf, off_t nbytes)
{
- uint32_t in;
- while (len > 0 && !feof(infile) && !ferror(infile)) {
- in = len < COPY_BUFFER_LEN ? len : COPY_BUFFER_LEN;
- in = fread(byte_buffer, 1, in, infile);
- len -= in;
+ char byte_buffer[COPY_BUFFER_LEN];
+ off_t done = 0;
+ while (done < nbytes && !feof(buf->infile) && !ferror(buf->infile)) {
+ off_t len = nbytes - done;
+ size_t in = len < COPY_BUFFER_LEN ? len : COPY_BUFFER_LEN;
+ done += fread(byte_buffer, 1, in, buf->infile);
}
+ return done;
}
-void buffer_reset(void)
+void buffer_reset(struct line_buffer *buf)
{
- blob_reset();
}
diff --git a/vcs-svn/line_buffer.h b/vcs-svn/line_buffer.h
index 9c78ae11a1..d0b22dda76 100644
--- a/vcs-svn/line_buffer.h
+++ b/vcs-svn/line_buffer.h
@@ -1,12 +1,31 @@
#ifndef LINE_BUFFER_H_
#define LINE_BUFFER_H_
-int buffer_init(const char *filename);
-int buffer_deinit(void);
-char *buffer_read_line(void);
-char *buffer_read_string(uint32_t len);
-void buffer_copy_bytes(uint32_t len);
-void buffer_skip_bytes(uint32_t len);
-void buffer_reset(void);
+#include "strbuf.h"
+
+#define LINE_BUFFER_LEN 10000
+
+struct line_buffer {
+ char line_buffer[LINE_BUFFER_LEN];
+ FILE *infile;
+};
+#define LINE_BUFFER_INIT { "", NULL }
+
+int buffer_init(struct line_buffer *buf, const char *filename);
+int buffer_fdinit(struct line_buffer *buf, int fd);
+int buffer_deinit(struct line_buffer *buf);
+void buffer_reset(struct line_buffer *buf);
+
+int buffer_tmpfile_init(struct line_buffer *buf);
+FILE *buffer_tmpfile_rewind(struct line_buffer *buf); /* prepare to write. */
+long buffer_tmpfile_prepare_to_read(struct line_buffer *buf);
+
+int buffer_ferror(struct line_buffer *buf);
+char *buffer_read_line(struct line_buffer *buf);
+int buffer_read_char(struct line_buffer *buf);
+void buffer_read_binary(struct line_buffer *buf, struct strbuf *sb, uint32_t len);
+/* Returns number of bytes read (not necessarily written). */
+off_t buffer_copy_bytes(struct line_buffer *buf, off_t len);
+off_t buffer_skip_bytes(struct line_buffer *buf, off_t len);
#endif
diff --git a/vcs-svn/line_buffer.txt b/vcs-svn/line_buffer.txt
index 8906fb1f50..8e139eb22d 100644
--- a/vcs-svn/line_buffer.txt
+++ b/vcs-svn/line_buffer.txt
@@ -14,22 +14,46 @@ Calling sequence
The calling program:
+ - initializes a `struct line_buffer` to LINE_BUFFER_INIT
- specifies a file to read with `buffer_init`
- - processes input with `buffer_read_line`, `buffer_read_string`,
- `buffer_skip_bytes`, and `buffer_copy_bytes`
+ - processes input with `buffer_read_line`, `buffer_skip_bytes`,
+ and `buffer_copy_bytes`
- closes the file with `buffer_deinit`, perhaps to start over and
read another file.
-Before exiting, the caller can use `buffer_reset` to deallocate
-resources for the benefit of profiling tools.
+When finished, the caller can use `buffer_reset` to deallocate
+resources.
+
+Using temporary files
+---------------------
+
+Temporary files provide a place to store data that should not outlive
+the calling program. A program
+
+ - initializes a `struct line_buffer` to LINE_BUFFER_INIT
+ - requests a temporary file with `buffer_tmpfile_init`
+ - acquires an output handle by calling `buffer_tmpfile_rewind`
+ - uses standard I/O functions like `fprintf` and `fwrite` to fill
+ the temporary file
+ - declares writing is over with `buffer_tmpfile_prepare_to_read`
+ - can re-read what was written with `buffer_read_line`,
+ `buffer_copy_bytes`, and so on
+ - can reuse the temporary file by calling `buffer_tmpfile_rewind`
+ again
+ - removes the temporary file with `buffer_deinit`, perhaps to
+ reuse the line_buffer for some other file.
+
+When finished, the calling program can use `buffer_reset` to deallocate
+resources.
Functions
---------
-`buffer_init`::
- Open the named file for input. If filename is NULL,
- start reading from stdin. On failure, returns -1 (with
- errno indicating the nature of the failure).
+`buffer_init`, `buffer_fdinit`::
+ Open the named file or file descriptor for input.
+ buffer_init(buf, NULL) prepares to read from stdin.
+ On failure, returns -1 (with errno indicating the nature
+ of the failure).
`buffer_deinit`::
Stop reading from the current file (closing it unless
@@ -40,19 +64,14 @@ Functions
Read a line and strip off the trailing newline.
On failure or end of file, returns NULL.
-`buffer_read_string`::
- Read `len` characters of input or up to the end of the
- file, whichever comes first. Returns NULL on error.
- Returns whatever characters were read (possibly "")
- for end of file.
-
`buffer_copy_bytes`::
Read `len` bytes of input and dump them to the standard output
stream. Returns early for error or end of file.
`buffer_skip_bytes`::
Discards `len` bytes from the input stream (stopping early
- if necessary because of an error or eof).
+ if necessary because of an error or eof). Return value is
+ the number of bytes successfully read.
`buffer_reset`::
Deallocates non-static buffers.
diff --git a/vcs-svn/repo_tree.c b/vcs-svn/repo_tree.c
index e94d91d129..a21d89de97 100644
--- a/vcs-svn/repo_tree.c
+++ b/vcs-svn/repo_tree.c
@@ -38,7 +38,7 @@ static uint32_t mark;
static int repo_dirent_name_cmp(const void *a, const void *b);
/* Treap for directory entries */
-trp_gen(static, dent_, struct repo_dirent, children, dent, repo_dirent_name_cmp);
+trp_gen(static, dent_, struct repo_dirent, children, dent, repo_dirent_name_cmp)
uint32_t next_blob_mark(void)
{
@@ -87,7 +87,8 @@ static struct repo_dir *repo_clone_dir(struct repo_dir *orig_dir)
return dir_pointer(new_o);
}
-static struct repo_dirent *repo_read_dirent(uint32_t revision, uint32_t *path)
+static struct repo_dirent *repo_read_dirent(uint32_t revision,
+ const uint32_t *path)
{
uint32_t name = 0;
struct repo_dirent *key = dent_pointer(dent_alloc(1));
@@ -105,7 +106,7 @@ static struct repo_dirent *repo_read_dirent(uint32_t revision, uint32_t *path)
return dent;
}
-static void repo_write_dirent(uint32_t *path, uint32_t mode,
+static void repo_write_dirent(const uint32_t *path, uint32_t mode,
uint32_t content_offset, uint32_t del)
{
uint32_t name, revision, dir_o = ~0, parent_dir_o = ~0;
@@ -131,7 +132,7 @@ static void repo_write_dirent(uint32_t *path, uint32_t mode,
if (dent == key) {
dent->mode = REPO_MODE_DIR;
dent->content_offset = 0;
- dent_insert(&dir->entries, dent);
+ dent = dent_insert(&dir->entries, dent);
}
if (dent_offset(dent) < dent_pool.committed) {
@@ -142,7 +143,7 @@ static void repo_write_dirent(uint32_t *path, uint32_t mode,
dent->name_offset = name;
dent->mode = REPO_MODE_DIR;
dent->content_offset = dir_o;
- dent_insert(&dir->entries, dent);
+ dent = dent_insert(&dir->entries, dent);
}
dir = repo_dir_from_dirent(dent);
@@ -157,42 +158,37 @@ static void repo_write_dirent(uint32_t *path, uint32_t mode,
dent_remove(&dir_pointer(parent_dir_o)->entries, dent);
}
-uint32_t repo_copy(uint32_t revision, uint32_t *src, uint32_t *dst)
+uint32_t repo_read_path(const uint32_t *path)
{
- uint32_t mode = 0, content_offset = 0;
- struct repo_dirent *src_dent;
- src_dent = repo_read_dirent(revision, src);
- if (src_dent != NULL) {
- mode = src_dent->mode;
- content_offset = src_dent->content_offset;
- repo_write_dirent(dst, mode, content_offset, 0);
- }
- return mode;
+ uint32_t content_offset = 0;
+ struct repo_dirent *dent = repo_read_dirent(active_commit, path);
+ if (dent != NULL)
+ content_offset = dent->content_offset;
+ return content_offset;
}
-void repo_add(uint32_t *path, uint32_t mode, uint32_t blob_mark)
+uint32_t repo_read_mode(const uint32_t *path)
{
- repo_write_dirent(path, mode, blob_mark, 0);
+ struct repo_dirent *dent = repo_read_dirent(active_commit, path);
+ if (dent == NULL)
+ die("invalid dump: path to be modified is missing");
+ return dent->mode;
}
-uint32_t repo_replace(uint32_t *path, uint32_t blob_mark)
+void repo_copy(uint32_t revision, const uint32_t *src, const uint32_t *dst)
{
- uint32_t mode = 0;
+ uint32_t mode = 0, content_offset = 0;
struct repo_dirent *src_dent;
- src_dent = repo_read_dirent(active_commit, path);
+ src_dent = repo_read_dirent(revision, src);
if (src_dent != NULL) {
mode = src_dent->mode;
- repo_write_dirent(path, mode, blob_mark, 0);
+ content_offset = src_dent->content_offset;
+ repo_write_dirent(dst, mode, content_offset, 0);
}
- return mode;
}
-void repo_modify(uint32_t *path, uint32_t mode, uint32_t blob_mark)
+void repo_add(uint32_t *path, uint32_t mode, uint32_t blob_mark)
{
- struct repo_dirent *src_dent;
- src_dent = repo_read_dirent(active_commit, path);
- if (src_dent != NULL && blob_mark == 0)
- blob_mark = src_dent->content_offset;
repo_write_dirent(path, mode, blob_mark, 0);
}
@@ -282,8 +278,9 @@ void repo_diff(uint32_t r1, uint32_t r2)
repo_commit_root_dir(commit_pointer(r2)));
}
-void repo_commit(uint32_t revision, uint32_t author, char *log, uint32_t uuid,
- uint32_t 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 5476175922..37bde2e374 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
@@ -12,13 +12,14 @@
#define REPO_MAX_PATH_DEPTH 1000
uint32_t next_blob_mark(void);
-uint32_t repo_copy(uint32_t revision, uint32_t *src, uint32_t *dst);
+void repo_copy(uint32_t revision, const uint32_t *src, const uint32_t *dst);
void repo_add(uint32_t *path, uint32_t mode, uint32_t blob_mark);
-uint32_t repo_replace(uint32_t *path, uint32_t blob_mark);
-void repo_modify(uint32_t *path, uint32_t mode, uint32_t blob_mark);
+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, uint32_t author, char *log, uint32_t uuid,
- uint32_t url, long unsigned timestamp);
+void repo_commit(uint32_t revision, const char *author,
+ 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);
void repo_reset(void);
diff --git a/vcs-svn/string_pool.c b/vcs-svn/string_pool.c
index f5b1da836e..8af8d54d6e 100644
--- a/vcs-svn/string_pool.c
+++ b/vcs-svn/string_pool.c
@@ -30,7 +30,7 @@ static int node_cmp(struct node *a, struct node *b)
}
/* Build a Treap from the node structure (a trp_node w/ offset) */
-trp_gen(static, tree_, struct node, children, node, node_cmp);
+trp_gen(static, tree_, struct node, children, node, node_cmp)
const char *pool_fetch(uint32_t entry)
{
diff --git a/vcs-svn/svndump.c b/vcs-svn/svndump.c
index 53d0215d2d..bc792223b2 100644
--- a/vcs-svn/svndump.c
+++ b/vcs-svn/svndump.c
@@ -11,8 +11,15 @@
#include "repo_tree.h"
#include "fast_export.h"
#include "line_buffer.h"
-#include "obj_pool.h"
#include "string_pool.h"
+#include "strbuf.h"
+#include "svndump.h"
+
+/*
+ * Compare start of string to literal of equal length;
+ * must be guarded by length test.
+ */
+#define constcmp(s, ref) memcmp(s, ref, sizeof(ref) - 1)
#define NODEACT_REPLACE 4
#define NODEACT_DELETE 3
@@ -27,40 +34,25 @@
#define LENGTH_UNKNOWN (~0)
#define DATE_RFC2822_LEN 31
-/* Create memory pool for log messages */
-obj_pool_gen(log, char, 4096)
-
-static char* log_copy(uint32_t length, char *log)
-{
- char *buffer;
- log_free(log_pool.size);
- buffer = log_pointer(log_alloc(length));
- strncpy(buffer, log, length);
- return buffer;
-}
+static struct line_buffer input = LINE_BUFFER_INIT;
static struct {
- uint32_t action, propLength, textLength, srcRev, srcMode, mark, type;
+ uint32_t action, propLength, textLength, srcRev, type;
uint32_t src[REPO_MAX_PATH_DEPTH], dst[REPO_MAX_PATH_DEPTH];
+ uint32_t text_delta, prop_delta;
} node_ctx;
static struct {
- uint32_t revision, author;
+ uint32_t revision;
unsigned long timestamp;
- char *log;
+ struct strbuf log, author;
} rev_ctx;
static struct {
- uint32_t uuid, url;
+ uint32_t version;
+ struct strbuf uuid, url;
} dump_ctx;
-static struct {
- uint32_t svn_log, svn_author, svn_date, svn_executable, svn_special, uuid,
- revision_number, node_path, node_kind, node_action,
- node_copyfrom_path, node_copyfrom_rev, text_content_length,
- prop_content_length, content_length;
-} keys;
-
static void reset_node_ctx(char *fname)
{
node_ctx.type = 0;
@@ -69,124 +61,223 @@ static void reset_node_ctx(char *fname)
node_ctx.textLength = LENGTH_UNKNOWN;
node_ctx.src[0] = ~0;
node_ctx.srcRev = 0;
- node_ctx.srcMode = 0;
pool_tok_seq(REPO_MAX_PATH_DEPTH, node_ctx.dst, "/", fname);
- node_ctx.mark = 0;
+ node_ctx.text_delta = 0;
+ node_ctx.prop_delta = 0;
}
static void reset_rev_ctx(uint32_t revision)
{
rev_ctx.revision = revision;
rev_ctx.timestamp = 0;
- rev_ctx.log = NULL;
- rev_ctx.author = ~0;
+ strbuf_reset(&rev_ctx.log);
+ strbuf_reset(&rev_ctx.author);
+}
+
+static void reset_dump_ctx(const char *url)
+{
+ strbuf_reset(&dump_ctx.url);
+ if (url)
+ strbuf_addstr(&dump_ctx.url, url);
+ dump_ctx.version = 1;
+ strbuf_reset(&dump_ctx.uuid);
}
-static void reset_dump_ctx(uint32_t url)
+static void handle_property(const struct strbuf *key_buf,
+ struct strbuf *val,
+ uint32_t *type_set)
{
- dump_ctx.url = url;
- dump_ctx.uuid = ~0;
+ const char *key = key_buf->buf;
+ size_t keylen = key_buf->len;
+
+ switch (keylen + 1) {
+ case sizeof("svn:log"):
+ if (constcmp(key, "svn:log"))
+ break;
+ if (!val)
+ die("invalid dump: unsets svn:log");
+ strbuf_swap(&rev_ctx.log, val);
+ break;
+ case sizeof("svn:author"):
+ if (constcmp(key, "svn:author"))
+ break;
+ if (!val)
+ strbuf_reset(&rev_ctx.author);
+ else
+ strbuf_swap(&rev_ctx.author, val);
+ break;
+ case sizeof("svn:date"):
+ if (constcmp(key, "svn:date"))
+ break;
+ if (!val)
+ die("invalid dump: unsets svn:date");
+ if (parse_date_basic(val->buf, &rev_ctx.timestamp, NULL))
+ warning("invalid timestamp: %s", val->buf);
+ break;
+ case sizeof("svn:executable"):
+ case sizeof("svn:special"):
+ if (keylen == strlen("svn:executable") &&
+ constcmp(key, "svn:executable"))
+ break;
+ if (keylen == strlen("svn:special") &&
+ constcmp(key, "svn:special"))
+ break;
+ if (*type_set) {
+ if (!val)
+ return;
+ die("invalid dump: sets type twice");
+ }
+ if (!val) {
+ node_ctx.type = REPO_MODE_BLB;
+ return;
+ }
+ *type_set = 1;
+ node_ctx.type = keylen == strlen("svn:executable") ?
+ REPO_MODE_EXE :
+ REPO_MODE_LNK;
+ }
}
-static void init_keys(void)
+static void die_short_read(void)
{
- keys.svn_log = pool_intern("svn:log");
- keys.svn_author = pool_intern("svn:author");
- keys.svn_date = pool_intern("svn:date");
- keys.svn_executable = pool_intern("svn:executable");
- keys.svn_special = pool_intern("svn:special");
- keys.uuid = pool_intern("UUID");
- keys.revision_number = pool_intern("Revision-number");
- keys.node_path = pool_intern("Node-path");
- keys.node_kind = pool_intern("Node-kind");
- keys.node_action = pool_intern("Node-action");
- keys.node_copyfrom_path = pool_intern("Node-copyfrom-path");
- keys.node_copyfrom_rev = pool_intern("Node-copyfrom-rev");
- keys.text_content_length = pool_intern("Text-content-length");
- keys.prop_content_length = pool_intern("Prop-content-length");
- keys.content_length = pool_intern("Content-length");
+ if (buffer_ferror(&input))
+ die_errno("error reading dump file");
+ die("invalid dump: unexpected end of file");
}
static void read_props(void)
{
- uint32_t len;
- uint32_t key = ~0;
- char *val = NULL;
- char *t;
- while ((t = buffer_read_line()) && strcmp(t, "PROPS-END")) {
- if (!strncmp(t, "K ", 2)) {
- len = atoi(&t[2]);
- key = pool_intern(buffer_read_string(len));
- buffer_read_line();
- } else if (!strncmp(t, "V ", 2)) {
- len = atoi(&t[2]);
- val = buffer_read_string(len);
- if (key == keys.svn_log) {
- /* Value length excludes terminating nul. */
- rev_ctx.log = log_copy(len + 1, val);
- } else if (key == keys.svn_author) {
- rev_ctx.author = pool_intern(val);
- } else if (key == keys.svn_date) {
- if (parse_date_basic(val, &rev_ctx.timestamp, NULL))
- fprintf(stderr, "Invalid timestamp: %s\n", val);
- } else if (key == keys.svn_executable) {
- node_ctx.type = REPO_MODE_EXE;
- } else if (key == keys.svn_special) {
- node_ctx.type = REPO_MODE_LNK;
- }
- key = ~0;
- buffer_read_line();
+ static struct strbuf key = STRBUF_INIT;
+ static struct strbuf val = STRBUF_INIT;
+ const char *t;
+ /*
+ * NEEDSWORK: to support simple mode changes like
+ * K 11
+ * svn:special
+ * V 1
+ * *
+ * D 14
+ * svn:executable
+ * we keep track of whether a mode has been set and reset to
+ * plain file only if not. We should be keeping track of the
+ * symlink and executable bits separately instead.
+ */
+ uint32_t type_set = 0;
+ while ((t = buffer_read_line(&input)) && strcmp(t, "PROPS-END")) {
+ uint32_t len;
+ const char type = t[0];
+ int ch;
+
+ if (!type || t[1] != ' ')
+ die("invalid property line: %s\n", t);
+ len = atoi(&t[2]);
+ strbuf_reset(&val);
+ buffer_read_binary(&input, &val, len);
+ if (val.len < len)
+ die_short_read();
+
+ /* Discard trailing newline. */
+ ch = buffer_read_char(&input);
+ if (ch == EOF)
+ die_short_read();
+ if (ch != '\n')
+ die("invalid dump: expected newline after %s", val.buf);
+
+ switch (type) {
+ case 'K':
+ strbuf_swap(&key, &val);
+ continue;
+ case 'D':
+ handle_property(&val, NULL, &type_set);
+ continue;
+ case 'V':
+ handle_property(&key, &val, &type_set);
+ strbuf_reset(&key);
+ continue;
+ default:
+ die("invalid property line: %s\n", t);
}
}
}
static void handle_node(void)
{
- if (node_ctx.propLength != LENGTH_UNKNOWN && node_ctx.propLength)
- read_props();
-
- if (node_ctx.srcRev)
- node_ctx.srcMode = repo_copy(node_ctx.srcRev, node_ctx.src, node_ctx.dst);
-
- if (node_ctx.textLength != LENGTH_UNKNOWN &&
- node_ctx.type != REPO_MODE_DIR)
- node_ctx.mark = next_blob_mark();
+ uint32_t mark = 0;
+ const uint32_t type = node_ctx.type;
+ const int have_props = node_ctx.propLength != LENGTH_UNKNOWN;
+ const int have_text = node_ctx.textLength != LENGTH_UNKNOWN;
+ if (node_ctx.text_delta)
+ die("text deltas not supported");
+ if (have_text)
+ mark = next_blob_mark();
if (node_ctx.action == NODEACT_DELETE) {
+ if (have_text || have_props || node_ctx.srcRev)
+ die("invalid dump: deletion node has "
+ "copyfrom info, text, or properties");
+ repo_delete(node_ctx.dst);
+ return;
+ }
+ if (node_ctx.action == NODEACT_REPLACE) {
repo_delete(node_ctx.dst);
- } else if (node_ctx.action == NODEACT_CHANGE ||
- node_ctx.action == NODEACT_REPLACE) {
- if (node_ctx.action == NODEACT_REPLACE &&
- node_ctx.type == REPO_MODE_DIR)
- repo_replace(node_ctx.dst, node_ctx.mark);
- else if (node_ctx.propLength != LENGTH_UNKNOWN)
- repo_modify(node_ctx.dst, node_ctx.type, node_ctx.mark);
- else if (node_ctx.textLength != LENGTH_UNKNOWN)
- node_ctx.srcMode = repo_replace(node_ctx.dst, node_ctx.mark);
+ node_ctx.action = NODEACT_ADD;
+ }
+ if (node_ctx.srcRev) {
+ repo_copy(node_ctx.srcRev, node_ctx.src, node_ctx.dst);
+ if (node_ctx.action == NODEACT_ADD)
+ node_ctx.action = NODEACT_CHANGE;
+ }
+ if (have_text && type == REPO_MODE_DIR)
+ die("invalid dump: directories cannot have text attached");
+
+ /*
+ * Decide on the new content (mark) and mode (node_ctx.type).
+ */
+ if (node_ctx.action == NODEACT_CHANGE && !~*node_ctx.dst) {
+ if (type != REPO_MODE_DIR)
+ die("invalid dump: root of tree is not a regular file");
+ } else if (node_ctx.action == NODEACT_CHANGE) {
+ uint32_t mode;
+ if (!have_text)
+ mark = repo_read_path(node_ctx.dst);
+ mode = repo_read_mode(node_ctx.dst);
+ if (mode == REPO_MODE_DIR && type != REPO_MODE_DIR)
+ die("invalid dump: cannot modify a directory into a file");
+ if (mode != REPO_MODE_DIR && type == REPO_MODE_DIR)
+ die("invalid dump: cannot modify a file into a directory");
+ node_ctx.type = mode;
} else if (node_ctx.action == NODEACT_ADD) {
- if (node_ctx.srcRev && node_ctx.propLength != LENGTH_UNKNOWN)
- repo_modify(node_ctx.dst, node_ctx.type, node_ctx.mark);
- else if (node_ctx.srcRev && node_ctx.textLength != LENGTH_UNKNOWN)
- node_ctx.srcMode = repo_replace(node_ctx.dst, node_ctx.mark);
- else if ((node_ctx.type == REPO_MODE_DIR && !node_ctx.srcRev) ||
- node_ctx.textLength != LENGTH_UNKNOWN)
- repo_add(node_ctx.dst, node_ctx.type, node_ctx.mark);
+ if (!have_text && type != REPO_MODE_DIR)
+ die("invalid dump: adds node without text");
+ } else {
+ die("invalid dump: Node-path block lacks Node-action");
}
- if (node_ctx.propLength == LENGTH_UNKNOWN && node_ctx.srcMode)
- node_ctx.type = node_ctx.srcMode;
+ /*
+ * Adjust mode to reflect properties.
+ */
+ if (have_props) {
+ if (!node_ctx.prop_delta)
+ node_ctx.type = type;
+ if (node_ctx.propLength)
+ read_props();
+ }
- if (node_ctx.mark)
- fast_export_blob(node_ctx.type, node_ctx.mark, node_ctx.textLength);
- else if (node_ctx.textLength != LENGTH_UNKNOWN)
- buffer_skip_bytes(node_ctx.textLength);
+ /*
+ * Save the result.
+ */
+ repo_add(node_ctx.dst, node_ctx.type, mark);
+ if (have_text)
+ fast_export_blob(node_ctx.type, mark,
+ node_ctx.textLength, &input);
}
static void handle_revision(void)
{
if (rev_ctx.revision)
- repo_commit(rev_ctx.revision, rev_ctx.author, rev_ctx.log,
- dump_ctx.uuid, dump_ctx.url, rev_ctx.timestamp);
+ repo_commit(rev_ctx.revision, rev_ctx.author.buf,
+ &rev_ctx.log, dump_ctx.uuid.buf, dump_ctx.url.buf,
+ rev_ctx.timestamp);
}
void svndump_read(const char *url)
@@ -195,39 +286,65 @@ void svndump_read(const char *url)
char *t;
uint32_t active_ctx = DUMP_CTX;
uint32_t len;
- uint32_t key;
- reset_dump_ctx(pool_intern(url));
- while ((t = buffer_read_line())) {
- val = strstr(t, ": ");
+ reset_dump_ctx(url);
+ while ((t = buffer_read_line(&input))) {
+ val = strchr(t, ':');
if (!val)
continue;
- *val++ = '\0';
- *val++ = '\0';
- key = pool_intern(t);
+ val++;
+ if (*val != ' ')
+ continue;
+ val++;
- if (key == keys.uuid) {
- dump_ctx.uuid = pool_intern(val);
- } else if (key == keys.revision_number) {
+ /* strlen(key) + 1 */
+ switch (val - t - 1) {
+ case sizeof("SVN-fs-dump-format-version"):
+ if (constcmp(t, "SVN-fs-dump-format-version"))
+ continue;
+ dump_ctx.version = atoi(val);
+ if (dump_ctx.version > 3)
+ die("expected svn dump format version <= 3, found %"PRIu32,
+ dump_ctx.version);
+ break;
+ case sizeof("UUID"):
+ if (constcmp(t, "UUID"))
+ continue;
+ strbuf_reset(&dump_ctx.uuid);
+ strbuf_addstr(&dump_ctx.uuid, val);
+ break;
+ case sizeof("Revision-number"):
+ if (constcmp(t, "Revision-number"))
+ continue;
if (active_ctx == NODE_CTX)
handle_node();
if (active_ctx != DUMP_CTX)
handle_revision();
active_ctx = REV_CTX;
reset_rev_ctx(atoi(val));
- } else if (key == keys.node_path) {
- if (active_ctx == NODE_CTX)
- handle_node();
- active_ctx = NODE_CTX;
- reset_node_ctx(val);
- } else if (key == keys.node_kind) {
+ break;
+ case sizeof("Node-path"):
+ if (prefixcmp(t, "Node-"))
+ continue;
+ if (!constcmp(t + strlen("Node-"), "path")) {
+ if (active_ctx == NODE_CTX)
+ handle_node();
+ active_ctx = NODE_CTX;
+ reset_node_ctx(val);
+ break;
+ }
+ if (constcmp(t + strlen("Node-"), "kind"))
+ continue;
if (!strcmp(val, "dir"))
node_ctx.type = REPO_MODE_DIR;
else if (!strcmp(val, "file"))
node_ctx.type = REPO_MODE_BLB;
else
fprintf(stderr, "Unknown node-kind: %s\n", val);
- } else if (key == keys.node_action) {
+ break;
+ case sizeof("Node-action"):
+ if (constcmp(t, "Node-action"))
+ continue;
if (!strcmp(val, "delete")) {
node_ctx.action = NODEACT_DELETE;
} else if (!strcmp(val, "add")) {
@@ -240,17 +357,44 @@ void svndump_read(const char *url)
fprintf(stderr, "Unknown node-action: %s\n", val);
node_ctx.action = NODEACT_UNKNOWN;
}
- } else if (key == keys.node_copyfrom_path) {
+ break;
+ case sizeof("Node-copyfrom-path"):
+ if (constcmp(t, "Node-copyfrom-path"))
+ continue;
pool_tok_seq(REPO_MAX_PATH_DEPTH, node_ctx.src, "/", val);
- } else if (key == keys.node_copyfrom_rev) {
+ break;
+ case sizeof("Node-copyfrom-rev"):
+ if (constcmp(t, "Node-copyfrom-rev"))
+ continue;
node_ctx.srcRev = atoi(val);
- } else if (key == keys.text_content_length) {
- node_ctx.textLength = atoi(val);
- } else if (key == keys.prop_content_length) {
+ break;
+ case sizeof("Text-content-length"):
+ if (!constcmp(t, "Text-content-length")) {
+ node_ctx.textLength = atoi(val);
+ break;
+ }
+ if (constcmp(t, "Prop-content-length"))
+ continue;
node_ctx.propLength = atoi(val);
- } else if (key == keys.content_length) {
+ break;
+ case sizeof("Text-delta"):
+ if (!constcmp(t, "Text-delta")) {
+ node_ctx.text_delta = !strcmp(val, "true");
+ break;
+ }
+ if (constcmp(t, "Prop-delta"))
+ continue;
+ node_ctx.prop_delta = !strcmp(val, "true");
+ break;
+ case sizeof("Content-length"):
+ if (constcmp(t, "Content-length"))
+ continue;
len = atoi(val);
- buffer_read_line();
+ t = buffer_read_line(&input);
+ if (!t)
+ die_short_read();
+ if (*t)
+ die("invalid dump: expected blank line after content length header");
if (active_ctx == REV_CTX) {
read_props();
} else if (active_ctx == NODE_CTX) {
@@ -258,34 +402,42 @@ void svndump_read(const char *url)
active_ctx = REV_CTX;
} else {
fprintf(stderr, "Unexpected content length header: %"PRIu32"\n", len);
- buffer_skip_bytes(len);
+ if (buffer_skip_bytes(&input, len) != len)
+ die_short_read();
}
}
}
+ if (buffer_ferror(&input))
+ die_short_read();
if (active_ctx == NODE_CTX)
handle_node();
if (active_ctx != DUMP_CTX)
handle_revision();
}
-void svndump_init(const char *filename)
+int svndump_init(const char *filename)
{
- buffer_init(filename);
+ if (buffer_init(&input, filename))
+ return error("cannot open %s: %s", filename, strerror(errno));
repo_init();
- reset_dump_ctx(~0);
+ strbuf_init(&dump_ctx.uuid, 4096);
+ strbuf_init(&dump_ctx.url, 4096);
+ strbuf_init(&rev_ctx.log, 4096);
+ strbuf_init(&rev_ctx.author, 4096);
+ reset_dump_ctx(NULL);
reset_rev_ctx(0);
reset_node_ctx(NULL);
- init_keys();
+ return 0;
}
void svndump_deinit(void)
{
- log_reset();
repo_reset();
- reset_dump_ctx(~0);
+ reset_dump_ctx(NULL);
reset_rev_ctx(0);
reset_node_ctx(NULL);
- if (buffer_deinit())
+ strbuf_release(&rev_ctx.log);
+ if (buffer_deinit(&input))
fprintf(stderr, "Input error\n");
if (ferror(stdout))
fprintf(stderr, "Output error\n");
@@ -293,10 +445,10 @@ void svndump_deinit(void)
void svndump_reset(void)
{
- log_reset();
- buffer_reset();
+ buffer_reset(&input);
repo_reset();
- reset_dump_ctx(~0);
- reset_rev_ctx(0);
- reset_node_ctx(NULL);
+ strbuf_release(&dump_ctx.uuid);
+ strbuf_release(&dump_ctx.url);
+ strbuf_release(&rev_ctx.log);
+ strbuf_release(&rev_ctx.author);
}
diff --git a/vcs-svn/svndump.h b/vcs-svn/svndump.h
index 93c412f14a..df9ceb0e8d 100644
--- a/vcs-svn/svndump.h
+++ b/vcs-svn/svndump.h
@@ -1,7 +1,7 @@
#ifndef SVNDUMP_H_
#define SVNDUMP_H_
-void svndump_init(const char *filename);
+int svndump_init(const char *filename);
void svndump_read(const char *url);
void svndump_deinit(void);
void svndump_reset(void);
diff --git a/vcs-svn/trp.h b/vcs-svn/trp.h
index ee35c688a0..c32b9184e9 100644
--- a/vcs-svn/trp.h
+++ b/vcs-svn/trp.h
@@ -188,11 +188,12 @@ a_attr uint32_t MAYBE_UNUSED a_pre##insert_recurse(uint32_t cur_node, uint32_t i
return ret; \
} \
} \
-a_attr void MAYBE_UNUSED a_pre##insert(struct trp_root *treap, a_type *node) \
+a_attr a_type *MAYBE_UNUSED a_pre##insert(struct trp_root *treap, a_type *node) \
{ \
uint32_t offset = trpn_offset(a_base, node); \
trp_node_new(a_base, a_field, offset); \
treap->trp_root = a_pre##insert_recurse(treap->trp_root, offset); \
+ return trpn_pointer(a_base, offset); \
} \
a_attr uint32_t MAYBE_UNUSED a_pre##remove_recurse(uint32_t cur_node, uint32_t rem_node) \
{ \
diff --git a/vcs-svn/trp.txt b/vcs-svn/trp.txt
index eb4c191875..177ebca335 100644
--- a/vcs-svn/trp.txt
+++ b/vcs-svn/trp.txt
@@ -21,7 +21,9 @@ The caller:
. Allocates a `struct trp_root` variable and sets it to {~0}.
-. Adds new nodes to the set using `foo_insert`.
+. Adds new nodes to the set using `foo_insert`. Any pointers
+ to existing nodes cannot be relied upon any more, so the caller
+ might retrieve them anew with `foo_pointer`.
. Can find a specific item in the set using `foo_search`.
@@ -73,10 +75,14 @@ int (*cmp)(node_type \*a, node_type \*b)
and returning a value less than, equal to, or greater than zero
according to the result of comparison.
-void foo_insert(struct trp_root *treap, node_type \*node)::
+node_type {asterisk}foo_insert(struct trp_root *treap, node_type \*node)::
Insert node into treap. If inserted multiple times,
a node will appear in the treap multiple times.
++
+The return value is the address of the node within the treap,
+which might differ from `node` if `pool_alloc` had to call
+`realloc` to expand the pool.
void foo_remove(struct trp_root *treap, node_type \*node)::
@@ -90,7 +96,7 @@ node_type *foo_search(struct trp_root \*treap, node_type \*key)::
node_type *foo_nsearch(struct trp_root \*treap, node_type \*key)::
- Like `foo_search`, but if if the key is missing return what
+ Like `foo_search`, but if the key is missing return what
would be key's successor, were key in treap (NULL if no
successor).
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-14 21:23:02 +0000