SYNOPSIS
--------
'git-svnimport' [ -o <branch-for-HEAD> ] [ -h ] [ -v ] [ -d | -D ]
- [ -C <GIT_repository> ] [ -i ] [ -u ] [-l limit_rev]
- [ -b branch_subdir ] [ -T trunk_subdir ] [ -t tag_subdir ]
- [ -s start_chg ] [ -m ] [ -M regex ]
- <SVN_repository_URL> [ <path> ]
+ [ -C <GIT_repository> ] [ -i ] [ -u ] [-l limit_rev]
+ [ -b branch_subdir ] [ -T trunk_subdir ] [ -t tag_subdir ]
+ [ -s start_chg ] [ -m ] [ -r ] [ -M regex ]
+ [ -I <ignorefile_name> ] [ -A <author_file> ]
+ <SVN_repository_URL> [ <path> ]
DESCRIPTION
Prepend 'rX: ' to commit messages, where X is the imported
subversion revision.
+-I <ignorefile_name>::
+ Import the svn:ignore directory property to files with this
+ name in each directory. (The Subversion and GIT ignore
+ syntaxes are similar enough that using the Subversion patterns
+ directly with "-I .gitignore" will almost always just work.)
+
+-A <author_file>::
+ Read a file with lines on the form
+
+ username = User's Full Name <email@addr.es>
+
+ and use "User's Full Name <email@addr.es>" as the GIT
+ author and committer for Subversion commits made by
+ "username". If encountering a commit made by a user not in the
+ list, abort.
+
+ For convenience, this data is saved to $GIT_DIR/svn-authors
+ each time the -A option is provided, and read from that same
+ file each time git-svnimport is run with an existing GIT
+ repository without -A.
+
-m::
Attempt to detect merges based on the commit message. This option
will enable default regexes that try to capture the name source
git-upload-pack$X git-verify-pack$X git-write-tree$X \
git-update-ref$X git-symbolic-ref$X git-check-ref-format$X \
git-name-rev$X git-pack-redundant$X git-repo-config$X git-var$X \
- git-describe$X git-merge-tree$X
+ git-describe$X git-merge-tree$X git-blame$X
# what 'all' will build and 'install' will install, in gitexecdir
ALL_PROGRAMS = $(PROGRAMS) $(SIMPLE_PROGRAMS) $(SCRIPTS)
static const char apply_usage[] =
"git-apply [--stat] [--numstat] [--summary] [--check] [--index] [--apply] [--no-add] [--index-info] [--allow-binary-replacement] [-z] [-pNUM] <patch>...";
+static enum whitespace_eol {
+ nowarn_whitespace,
+ warn_on_whitespace,
+ error_on_whitespace,
+ strip_whitespace,
+} new_whitespace = nowarn_whitespace;
+static int whitespace_error = 0;
+static int squelch_whitespace_errors = 5;
+static int applied_after_stripping = 0;
+static const char *patch_input_file = NULL;
+
+static void parse_whitespace_option(const char *option)
+{
+ if (!option) {
+ new_whitespace = nowarn_whitespace;
+ return;
+ }
+ if (!strcmp(option, "warn")) {
+ new_whitespace = warn_on_whitespace;
+ return;
+ }
+ if (!strcmp(option, "error")) {
+ new_whitespace = error_on_whitespace;
+ return;
+ }
+ if (!strcmp(option, "error-all")) {
+ new_whitespace = error_on_whitespace;
+ squelch_whitespace_errors = 0;
+ return;
+ }
+ if (!strcmp(option, "strip")) {
+ new_whitespace = strip_whitespace;
+ return;
+ }
+ die("unrecognized whitespace option '%s'", option);
+}
+
/*
* For "diff-stat" like behaviour, we keep track of the biggest change
* we've seen, and the longest filename. That allows us to do simple
oldlines--;
break;
case '+':
+ /*
+ * We know len is at least two, since we have a '+' and
+ * we checked that the last character was a '\n' above.
+ * That is, an addition of an empty line would check
+ * the '+' here. Sneaky...
+ */
+ if ((new_whitespace != nowarn_whitespace) &&
+ isspace(line[len-2])) {
+ whitespace_error++;
+ if (squelch_whitespace_errors &&
+ squelch_whitespace_errors <
+ whitespace_error)
+ ;
+ else {
+ fprintf(stderr, "Adds trailing whitespace.\n%s:%d:%.*s\n",
+ patch_input_file,
+ linenr, len-2, line+1);
+ }
+ }
added++;
newlines--;
break;
unsigned long alloc;
};
+static int apply_line(char *output, const char *patch, int plen)
+{
+ /* plen is number of bytes to be copied from patch,
+ * starting at patch+1 (patch[0] is '+'). Typically
+ * patch[plen] is '\n'.
+ */
+ int add_nl_to_tail = 0;
+ if ((new_whitespace == strip_whitespace) &&
+ 1 < plen && isspace(patch[plen-1])) {
+ if (patch[plen] == '\n')
+ add_nl_to_tail = 1;
+ plen--;
+ while (0 < plen && isspace(patch[plen]))
+ plen--;
+ applied_after_stripping++;
+ }
+ memcpy(output, patch + 1, plen);
+ if (add_nl_to_tail)
+ output[plen++] = '\n';
+ return plen;
+}
+
static int apply_one_fragment(struct buffer_desc *desc, struct fragment *frag)
{
char *buf = desc->buffer;
break;
/* Fall-through for ' ' */
case '+':
- if (*patch != '+' || !no_add) {
- memcpy(new + newsize, patch + 1, plen);
- newsize += plen;
- }
+ if (*patch != '+' || !no_add)
+ newsize += apply_line(new + newsize, patch,
+ plen);
break;
case '@': case '\\':
/* Ignore it, we already handled it */
return 1;
}
-static int apply_patch(int fd)
+static int apply_patch(int fd, const char *filename)
{
int newfd;
unsigned long offset, size;
struct patch *list = NULL, **listp = &list;
int skipped_patch = 0;
+ patch_input_file = filename;
if (!buffer)
return -1;
offset = 0;
}
newfd = -1;
+ if (whitespace_error && (new_whitespace == error_on_whitespace))
+ apply = 0;
+
write_index = check_index && apply;
if (write_index)
newfd = hold_index_file_for_update(&cache_file, get_index_file());
return 0;
}
+static int git_apply_config(const char *var, const char *value)
+{
+ if (!strcmp(var, "apply.whitespace")) {
+ apply_default_whitespace = strdup(value);
+ return 0;
+ }
+ return git_default_config(var, value);
+}
+
+
int main(int argc, char **argv)
{
int i;
int read_stdin = 1;
+ const char *whitespace_option = NULL;
for (i = 1; i < argc; i++) {
const char *arg = argv[i];
int fd;
if (!strcmp(arg, "-")) {
- apply_patch(0);
+ apply_patch(0, "<stdin>");
read_stdin = 0;
continue;
}
line_termination = 0;
continue;
}
+ if (!strncmp(arg, "--whitespace=", 13)) {
+ whitespace_option = arg + 13;
+ parse_whitespace_option(arg + 13);
+ continue;
+ }
if (check_index && prefix_length < 0) {
prefix = setup_git_directory();
prefix_length = prefix ? strlen(prefix) : 0;
- git_config(git_default_config);
+ git_config(git_apply_config);
+ if (!whitespace_option && apply_default_whitespace)
+ parse_whitespace_option(apply_default_whitespace);
}
if (0 < prefix_length)
arg = prefix_filename(prefix, prefix_length, arg);
if (fd < 0)
usage(apply_usage);
read_stdin = 0;
- apply_patch(fd);
+ apply_patch(fd, arg);
close(fd);
}
if (read_stdin)
- apply_patch(0);
+ apply_patch(0, "<stdin>");
+ if (whitespace_error) {
+ if (squelch_whitespace_errors &&
+ squelch_whitespace_errors < whitespace_error) {
+ int squelched =
+ whitespace_error - squelch_whitespace_errors;
+ fprintf(stderr, "warning: squelched %d whitespace error%s\n",
+ squelched,
+ squelched == 1 ? "" : "s");
+ }
+ if (new_whitespace == error_on_whitespace)
+ die("%d line%s add%s trailing whitespaces.",
+ whitespace_error,
+ whitespace_error == 1 ? "" : "s",
+ whitespace_error == 1 ? "s" : "");
+ if (applied_after_stripping)
+ fprintf(stderr, "warning: %d line%s applied after"
+ " stripping trailing whitespaces.\n",
+ applied_after_stripping,
+ applied_after_stripping == 1 ? "" : "s");
+ else if (whitespace_error)
+ fprintf(stderr, "warning: %d line%s add%s trailing"
+ " whitespaces.\n",
+ whitespace_error,
+ whitespace_error == 1 ? "" : "s",
+ whitespace_error == 1 ? "s" : "");
+ }
return 0;
}
--- /dev/null
+#include <assert.h>
+
+#include "cache.h"
+#include "refs.h"
+#include "tag.h"
+#include "commit.h"
+#include "tree.h"
+#include "blob.h"
+#include "epoch.h"
+#include "diff.h"
+
+#define DEBUG 0
+
+struct commit** blame_lines;
+int num_blame_lines;
+
+struct util_info
+{
+ int* line_map;
+ int num_lines;
+ unsigned char sha1[20]; /* blob sha, not commit! */
+ char* buf;
+ unsigned long size;
+// const char* path;
+};
+
+struct chunk
+{
+ int off1, len1; // ---
+ int off2, len2; // +++
+};
+
+struct patch
+{
+ struct chunk* chunks;
+ int num;
+};
+
+static void get_blob(struct commit* commit);
+
+int num_get_patch = 0;
+int num_commits = 0;
+
+struct patch* get_patch(struct commit* commit, struct commit* other)
+{
+ struct patch* ret = xmalloc(sizeof(struct patch));
+ ret->chunks = NULL;
+ ret->num = 0;
+
+ struct util_info* info_c = (struct util_info*) commit->object.util;
+ struct util_info* info_o = (struct util_info*) other->object.util;
+
+ if(!memcmp(info_c->sha1, info_o->sha1, 20))
+ return ret;
+
+ get_blob(commit);
+ get_blob(other);
+
+ FILE* fout = fopen("/tmp/git-blame-tmp1", "w");
+ if(!fout)
+ die("fopen tmp1 failed: %s", strerror(errno));
+
+ if(fwrite(info_c->buf, info_c->size, 1, fout) != 1)
+ die("fwrite 1 failed: %s", strerror(errno));
+ fclose(fout);
+
+ fout = fopen("/tmp/git-blame-tmp2", "w");
+ if(!fout)
+ die("fopen tmp2 failed: %s", strerror(errno));
+
+ if(fwrite(info_o->buf, info_o->size, 1, fout) != 1)
+ die("fwrite 2 failed: %s", strerror(errno));
+ fclose(fout);
+
+ FILE* fin = popen("diff -u0 /tmp/git-blame-tmp1 /tmp/git-blame-tmp2", "r");
+ if(!fin)
+ die("popen failed: %s", strerror(errno));
+
+ char buf[1024];
+ while(fgets(buf, sizeof(buf), fin)) {
+ if(buf[0] != '@' || buf[1] != '@')
+ continue;
+
+ if(DEBUG)
+ printf("chunk line: %s", buf);
+ ret->num++;
+ ret->chunks = xrealloc(ret->chunks, sizeof(struct chunk)*ret->num);
+ struct chunk* chunk = &ret->chunks[ret->num-1];
+
+ assert(!strncmp(buf, "@@ -", 4));
+
+ char* start = buf+4;
+ char* sp = index(start, ' ');
+ *sp = '\0';
+ if(index(start, ',')) {
+ int ret = sscanf(start, "%d,%d", &chunk->off1, &chunk->len1);
+ assert(ret == 2);
+ } else {
+ int ret = sscanf(start, "%d", &chunk->off1);
+ assert(ret == 1);
+ chunk->len1 = 1;
+ }
+ *sp = ' ';
+
+ start = sp+1;
+ sp = index(start, ' ');
+ *sp = '\0';
+ if(index(start, ',')) {
+ int ret = sscanf(start, "%d,%d", &chunk->off2, &chunk->len2);
+ assert(ret == 2);
+ } else {
+ int ret = sscanf(start, "%d", &chunk->off2);
+ assert(ret == 1);
+ chunk->len2 = 1;
+ }
+ *sp = ' ';
+
+ if(chunk->off1 > 0)
+ chunk->off1 -= 1;
+ if(chunk->off2 > 0)
+ chunk->off2 -= 1;
+
+ assert(chunk->off1 >= 0);
+ assert(chunk->off2 >= 0);
+ }
+ fclose(fin);
+
+ num_get_patch++;
+ return ret;
+}
+
+void free_patch(struct patch* p)
+{
+ free(p->chunks);
+ free(p);
+}
+
+static int get_blob_sha1_internal(unsigned char *sha1, const char *base, int baselen,
+ const char *pathname, unsigned mode, int stage);
+
+
+static unsigned char blob_sha1[20];
+static int get_blob_sha1(struct tree* t, const char* pathname, unsigned char* sha1)
+{
+ const char *pathspec[2];
+ pathspec[0] = pathname;
+ pathspec[1] = NULL;
+ memset(blob_sha1, 0, sizeof(blob_sha1));
+ read_tree_recursive(t, "", 0, 0, pathspec, get_blob_sha1_internal);
+
+ int i;
+ for(i = 0; i < 20; i++) {
+ if(blob_sha1[i] != 0)
+ break;
+ }
+
+ if(i == 20)
+ return -1;
+
+ memcpy(sha1, blob_sha1, 20);
+ return 0;
+}
+
+static int get_blob_sha1_internal(unsigned char *sha1, const char *base, int baselen,
+ const char *pathname, unsigned mode, int stage)
+{
+// printf("Got blob: %s base: '%s' baselen: %d pathname: '%s' mode: %o stage: %d\n",
+// sha1_to_hex(sha1), base, baselen, pathname, mode, stage);
+
+ if(S_ISDIR(mode))
+ return READ_TREE_RECURSIVE;
+
+ memcpy(blob_sha1, sha1, 20);
+ return -1;
+}
+
+static void get_blob(struct commit* commit)
+{
+ struct util_info* info = commit->object.util;
+ char type[20];
+
+ if(info->buf)
+ return;
+
+ info->buf = read_sha1_file(info->sha1, type, &info->size);
+ assert(!strcmp(type, "blob"));
+}
+
+void print_patch(struct patch* p)
+{
+ printf("Num chunks: %d\n", p->num);
+ int i;
+ for(i = 0; i < p->num; i++) {
+ printf("%d,%d %d,%d\n", p->chunks[i].off1, p->chunks[i].len1, p->chunks[i].off2, p->chunks[i].len2);
+ }
+}
+
+
+// p is a patch from commit to other.
+void fill_line_map(struct commit* commit, struct commit* other, struct patch* p)
+{
+ int num_lines = ((struct util_info*) commit->object.util)->num_lines;
+ int* line_map = ((struct util_info*) commit->object.util)->line_map;
+ int num_lines2 = ((struct util_info*) other->object.util)->num_lines;
+ int* line_map2 = ((struct util_info*) other->object.util)->line_map;
+ int cur_chunk = 0;
+ int i1, i2;
+
+ if(p->num && DEBUG)
+ print_patch(p);
+
+ for(i1 = 0; i1 < num_lines; i1++)
+ line_map[i1] = -1;
+
+ if(DEBUG)
+ printf("num lines 1: %d num lines 2: %d\n", num_lines, num_lines2);
+
+ for(i1 = 0, i2 = 0; i1 < num_lines; i1++, i2++) {
+ if(DEBUG > 1)
+ printf("%d %d\n", i1, i2);
+
+ if(i2 >= num_lines2)
+ break;
+
+ line_map[i1] = line_map2[i2];
+
+ struct chunk* chunk = NULL;
+ if(cur_chunk < p->num)
+ chunk = &p->chunks[cur_chunk];
+
+ if(chunk && chunk->off1 == i1) {
+ i2 = chunk->off2;
+
+ if(chunk->len1 > 0)
+ i1 += chunk->len1-1;
+ if(chunk->len2 > 0)
+ i2 += chunk->len2-1;
+ cur_chunk++;
+ }
+ }
+}
+
+int map_line(struct commit* commit, int line)
+{
+ struct util_info* info = commit->object.util;
+ assert(line >= 0 && line < info->num_lines);
+ return info->line_map[line];
+}
+
+int fill_util_info(struct commit* commit, const char* path)
+{
+ if(commit->object.util)
+ return 0;
+
+ struct util_info* util = xmalloc(sizeof(struct util_info));
+ util->buf = NULL;
+ util->size = 0;
+ util->num_lines = -1;
+ util->line_map = NULL;
+
+ commit->object.util = util;
+
+ if(get_blob_sha1(commit->tree, path, util->sha1))
+ return -1;
+
+ return 0;
+}
+
+void alloc_line_map(struct commit* commit)
+{
+ struct util_info* util = commit->object.util;
+
+ if(util->line_map)
+ return;
+
+ get_blob(commit);
+
+ int i;
+ util->num_lines = 0;
+ for(i = 0; i < util->size; i++) {
+ if(util->buf[i] == '\n')
+ util->num_lines++;
+ }
+ util->line_map = xmalloc(sizeof(int)*util->num_lines);
+}
+
+void copy_line_map(struct commit* dst, struct commit* src)
+{
+ struct util_info* u_dst = dst->object.util;
+ struct util_info* u_src = src->object.util;
+
+ u_dst->line_map = u_src->line_map;
+ u_dst->num_lines = u_src->num_lines;
+ u_dst->buf = u_src->buf;
+ u_dst->size = u_src->size;
+}
+
+void process_commits(struct commit_list* list, const char* path)
+{
+ int i;
+
+ while(list) {
+ struct commit* commit = pop_commit(&list);
+ struct commit_list* parents;
+ struct util_info* info;
+
+ info = commit->object.util;
+ num_commits++;
+ if(DEBUG)
+ printf("\nProcessing commit: %d %s\n", num_commits, sha1_to_hex(commit->object.sha1));
+ for(parents = commit->parents;
+ parents != NULL; parents = parents->next) {
+ struct commit* parent = parents->item;
+
+ if(parse_commit(parent) < 0)
+ die("parse_commit error");
+
+ if(DEBUG)
+ printf("parent: %s\n", sha1_to_hex(parent->object.sha1));
+
+ if(fill_util_info(parent, path))
+ continue;
+
+ // Temporarily assign everything to the parent.
+ int num_blame = 0;
+ for(i = 0; i < num_blame_lines; i++) {
+ if(blame_lines[i] == commit) {
+ num_blame++;
+ blame_lines[i] = parent;
+ }
+ }
+
+ if(num_blame == 0)
+ continue;
+
+ struct patch* patch = get_patch(parent, commit);
+ if(patch->num == 0) {
+ copy_line_map(parent, commit);
+ } else {
+ alloc_line_map(parent);
+ fill_line_map(parent, commit, patch);
+ }
+
+ for(i = 0; i < patch->num; i++) {
+ int l;
+ for(l = 0; l < patch->chunks[i].len2; l++) {
+ int mapped_line = map_line(commit, patch->chunks[i].off2 + l);
+ if(mapped_line != -1 && blame_lines[mapped_line] == parent)
+ blame_lines[mapped_line] = commit;
+ }
+ }
+ free_patch(patch);
+ }
+ }
+}
+
+#define SEEN 1
+struct commit_list* get_commit_list(struct commit* commit, const char* pathname)
+{
+ struct commit_list* ret = NULL;
+ struct commit_list* process = NULL;
+ unsigned char sha1[20];
+
+ commit_list_insert(commit, &process);
+
+ while(process) {
+ struct commit* com = pop_commit(&process);
+ if(com->object.flags & SEEN)
+ continue;
+
+ com->object.flags |= SEEN;
+ commit_list_insert(com, &ret);
+ struct commit_list* parents;
+
+ parse_commit(com);
+
+ for(parents = com->parents;
+ parents != NULL; parents = parents->next) {
+ struct commit* parent = parents->item;
+
+ parse_commit(parent);
+
+ if(!get_blob_sha1(parent->tree, pathname, sha1))
+ commit_list_insert(parent, &process);
+ }
+ }
+
+ return ret;
+}
+
+int main(int argc, const char **argv)
+{
+ unsigned char sha1[20];
+ struct commit *commit;
+ const char* filename;
+ int i;
+
+ setup_git_directory();
+
+ if (argc != 3)
+ die("Usage: blame commit-ish file");
+
+ if (get_sha1(argv[1], sha1))
+ die("get_sha1 failed");
+
+ commit = lookup_commit_reference(sha1);
+
+ filename = argv[2];
+
+ struct commit_list* list = get_commit_list(commit, filename);
+ sort_in_topological_order(&list, 1);
+
+ if(fill_util_info(commit, filename)) {
+ printf("%s not found in %s\n", filename, argv[1]);
+ return 0;
+ }
+ alloc_line_map(commit);
+
+ struct util_info* util = commit->object.util;
+ num_blame_lines = util->num_lines;
+ blame_lines = xmalloc(sizeof(struct commit*)*num_blame_lines);
+
+
+ for(i = 0; i < num_blame_lines; i++) {
+ blame_lines[i] = commit;
+
+ ((struct util_info*) commit->object.util)->line_map[i] = i;
+ }
+
+ process_commits(list, filename);
+
+ for(i = 0; i < num_blame_lines; i++) {
+ printf("%d %s\n", i+1-1, sha1_to_hex(blame_lines[i]->object.sha1));
+// printf("%d %s\n", i+1-1, find_unique_abbrev(blame_lines[i]->object.sha1, 6));
+ }
+
+ if(DEBUG) {
+ printf("num get patch: %d\n", num_get_patch);
+ printf("num commits: %d\n", num_commits);
+ }
+
+ return 0;
+}
extern int commit_index_file(struct cache_file *);
extern void rollback_index_file(struct cache_file *);
+/* Environment bits from configuration mechanism */
extern int trust_executable_bit;
extern int assume_unchanged;
extern int only_use_symrefs;
extern int diff_rename_limit_default;
extern int shared_repository;
+extern const char *apply_default_whitespace;
#define GIT_REPO_VERSION 0
extern int repository_format_version;
* The delta-parsing part is almost straight copy of patch-delta.c
* which is (C) 2005 Nicolas Pitre <nico@cam.org>.
*/
+#include "cache.h"
+#include "delta.h"
+#include "count-delta.h"
#include <stdlib.h>
#include <string.h>
#include <limits.h>
-#include "delta.h"
-#include "count-delta.h"
+
+struct span {
+ struct span *next;
+ unsigned long ofs;
+ unsigned long end;
+};
+
+static void touch_range(struct span **span,
+ unsigned long ofs, unsigned long end)
+{
+ struct span *e = *span;
+ struct span *p = NULL;
+
+ while (e && e->ofs <= ofs) {
+ again:
+ if (ofs < e->end) {
+ while (e->end < end) {
+ if (e->next && e->next->ofs <= end) {
+ e->end = e->next->ofs;
+ e = e->next;
+ }
+ else {
+ e->end = end;
+ return;
+ }
+ }
+ return;
+ }
+ p = e;
+ e = e->next;
+ }
+ if (e && e->ofs <= end) {
+ e->ofs = ofs;
+ goto again;
+ }
+ else {
+ e = xmalloc(sizeof(*e));
+ e->ofs = ofs;
+ e->end = end;
+ if (p) {
+ e->next = p->next;
+ p->next = e;
+ }
+ else {
+ e->next = *span;
+ *span = e;
+ }
+ }
+}
+
+static unsigned long count_range(struct span *s)
+{
+ struct span *t;
+ unsigned long sz = 0;
+ while (s) {
+ t = s;
+ sz += s->end - s->ofs;
+ s = s->next;
+ free(t);
+ }
+ return sz;
+}
/*
* NOTE. We do not _interpret_ delta fully. As an approximation, we
int count_delta(void *delta_buf, unsigned long delta_size,
unsigned long *src_copied, unsigned long *literal_added)
{
- unsigned long copied_from_source, added_literal;
+ unsigned long added_literal;
const unsigned char *data, *top;
unsigned char cmd;
unsigned long src_size, dst_size, out;
+ struct span *span = NULL;
if (delta_size < DELTA_SIZE_MIN)
return -1;
src_size = get_delta_hdr_size(&data);
dst_size = get_delta_hdr_size(&data);
- added_literal = copied_from_source = out = 0;
+ added_literal = out = 0;
while (data < top) {
cmd = *data++;
if (cmd & 0x80) {
if (cmd & 0x40) cp_size |= (*data++ << 16);
if (cp_size == 0) cp_size = 0x10000;
- copied_from_source += cp_size;
+ touch_range(&span, cp_off, cp_off+cp_size);
out += cp_size;
} else {
/* write literal into dst */
}
}
+ *src_copied = count_range(span);
+
/* sanity check */
if (data != top || out != dst_size)
return -1;
/* delete size is what was _not_ copied from source.
* edit size is that and literal additions.
*/
- *src_copied = copied_from_source;
*literal_added = added_literal;
return 0;
}
*/
#include <stdlib.h>
+#include <string.h>
+#include <zlib.h>
#include "delta.h"
-#include "zlib.h"
/* block size: min = 16, max = 64k, power of 2 */
#define MIN(a, b) ((a) < (b) ? (a) : (b))
#define GR_PRIME 0x9e370001
-#define HASH(v, b) (((unsigned int)(v) * GR_PRIME) >> (32 - (b)))
-
-static unsigned int hashbits(unsigned int size)
-{
- unsigned int val = 1, bits = 0;
- while (val < size && bits < 32) {
- val <<= 1;
- bits++;
- }
- return bits ? bits: 1;
-}
-
-typedef struct s_chanode {
- struct s_chanode *next;
- int icurr;
-} chanode_t;
-
-typedef struct s_chastore {
- int isize, nsize;
- chanode_t *ancur;
-} chastore_t;
-
-static void cha_init(chastore_t *cha, int isize, int icount)
-{
- cha->isize = isize;
- cha->nsize = icount * isize;
- cha->ancur = NULL;
-}
-
-static void *cha_alloc(chastore_t *cha)
-{
- chanode_t *ancur;
- void *data;
+#define HASH(v, shift) (((unsigned int)(v) * GR_PRIME) >> (shift))
- ancur = cha->ancur;
- if (!ancur || ancur->icurr == cha->nsize) {
- ancur = malloc(sizeof(chanode_t) + cha->nsize);
- if (!ancur)
- return NULL;
- ancur->icurr = 0;
- ancur->next = cha->ancur;
- cha->ancur = ancur;
- }
-
- data = (void *)ancur + sizeof(chanode_t) + ancur->icurr;
- ancur->icurr += cha->isize;
- return data;
-}
-
-static void cha_free(chastore_t *cha)
-{
- chanode_t *cur = cha->ancur;
- while (cur) {
- chanode_t *tmp = cur;
- cur = cur->next;
- free(tmp);
- }
-}
-
-typedef struct s_bdrecord {
- struct s_bdrecord *next;
- unsigned int fp;
+struct index {
const unsigned char *ptr;
-} bdrecord_t;
-
-typedef struct s_bdfile {
- chastore_t cha;
- unsigned int fphbits;
- bdrecord_t **fphash;
-} bdfile_t;
+ unsigned int val;
+ struct index *next;
+};
-static int delta_prepare(const unsigned char *buf, int bufsize, bdfile_t *bdf)
+static struct index ** delta_index(const unsigned char *buf,
+ unsigned long bufsize,
+ unsigned int *hash_shift)
{
- unsigned int fphbits;
- int i, hsize;
- const unsigned char *data, *top;
- bdrecord_t *brec;
- bdrecord_t **fphash;
-
- fphbits = hashbits(bufsize / BLK_SIZE + 1);
- hsize = 1 << fphbits;
- fphash = malloc(hsize * sizeof(bdrecord_t *));
- if (!fphash)
- return -1;
- for (i = 0; i < hsize; i++)
- fphash[i] = NULL;
- cha_init(&bdf->cha, sizeof(bdrecord_t), hsize / 4 + 1);
-
- top = buf + bufsize;
- data = buf + (bufsize / BLK_SIZE) * BLK_SIZE;
- if (data == top)
+ unsigned int hsize, hshift, entries, blksize, i;
+ const unsigned char *data;
+ struct index *entry, **hash;
+ void *mem;
+
+ /* determine index hash size */
+ entries = (bufsize + BLK_SIZE - 1) / BLK_SIZE;
+ hsize = entries / 4;
+ for (i = 4; (1 << i) < hsize && i < 16; i++);
+ hsize = 1 << i;
+ hshift = 32 - i;
+ *hash_shift = hshift;
+
+ /* allocate lookup index */
+ mem = malloc(hsize * sizeof(*hash) + entries * sizeof(*entry));
+ if (!mem)
+ return NULL;
+ hash = mem;
+ entry = mem + hsize * sizeof(*hash);
+ memset(hash, 0, hsize * sizeof(*hash));
+
+ /* then populate it */
+ data = buf + entries * BLK_SIZE - BLK_SIZE;
+ blksize = bufsize - (data - buf);
+ while (data >= buf) {
+ unsigned int val = adler32(0, data, blksize);
+ i = HASH(val, hshift);
+ entry->ptr = data;
+ entry->val = val;
+ entry->next = hash[i];
+ hash[i] = entry++;
+ blksize = BLK_SIZE;
data -= BLK_SIZE;
+ }
- for ( ; data >= buf; data -= BLK_SIZE) {
- brec = cha_alloc(&bdf->cha);
- if (!brec) {
- cha_free(&bdf->cha);
- free(fphash);
- return -1;
- }
- brec->fp = adler32(0, data, MIN(BLK_SIZE, top - data));
- brec->ptr = data;
- i = HASH(brec->fp, fphbits);
- brec->next = fphash[i];
- fphash[i] = brec;
- }
-
- bdf->fphbits = fphbits;
- bdf->fphash = fphash;
-
- return 0;
-}
-
-static void delta_cleanup(bdfile_t *bdf)
-{
- free(bdf->fphash);
- cha_free(&bdf->cha);
+ return hash;
}
+/* provide the size of the copy opcode given the block offset and size */
#define COPYOP_SIZE(o, s) \
(!!(o & 0xff) + !!(o & 0xff00) + !!(o & 0xff0000) + !!(o & 0xff000000) + \
!!(s & 0xff) + !!(s & 0xff00) + 1)
+/* the maximum size for any opcode */
+#define MAX_OP_SIZE COPYOP_SIZE(0xffffffff, 0xffffffff)
+
void *diff_delta(void *from_buf, unsigned long from_size,
void *to_buf, unsigned long to_size,
unsigned long *delta_size,
unsigned long max_size)
{
- int i, outpos, outsize, inscnt, csize, msize, moff;
- unsigned int fp;
- const unsigned char *ref_data, *ref_top, *data, *top, *ptr1, *ptr2;
- unsigned char *out, *orig;
- bdrecord_t *brec;
- bdfile_t bdf;
+ unsigned int i, outpos, outsize, inscnt, hash_shift;
+ const unsigned char *ref_data, *ref_top, *data, *top;
+ unsigned char *out;
+ struct index *entry, **hash;
- if (!from_size || !to_size || delta_prepare(from_buf, from_size, &bdf))
+ if (!from_size || !to_size)
+ return NULL;
+ hash = delta_index(from_buf, from_size, &hash_shift);
+ if (!hash)
return NULL;
-
+
outpos = 0;
outsize = 8192;
+ if (max_size && outsize >= max_size)
+ outsize = max_size + MAX_OP_SIZE + 1;
out = malloc(outsize);
if (!out) {
- delta_cleanup(&bdf);
+ free(hash);
return NULL;
}
}
inscnt = 0;
- moff = 0;
- while (data < top) {
- msize = 0;
- fp = adler32(0, data, MIN(top - data, BLK_SIZE));
- i = HASH(fp, bdf.fphbits);
- for (brec = bdf.fphash[i]; brec; brec = brec->next) {
- if (brec->fp == fp) {
- csize = ref_top - brec->ptr;
- if (csize > top - data)
- csize = top - data;
- for (ptr1 = brec->ptr, ptr2 = data;
- csize && *ptr1 == *ptr2;
- csize--, ptr1++, ptr2++);
- csize = ptr1 - brec->ptr;
- if (csize > msize) {
- moff = brec->ptr - ref_data;
- msize = csize;
- if (msize >= 0x10000) {
- msize = 0x10000;
- break;
- }
+ while (data < top) {
+ unsigned int moff = 0, msize = 0;
+ unsigned int blksize = MIN(top - data, BLK_SIZE);
+ unsigned int val = adler32(0, data, blksize);
+ i = HASH(val, hash_shift);
+ for (entry = hash[i]; entry; entry = entry->next) {
+ const unsigned char *ref = entry->ptr;
+ const unsigned char *src = data;
+ unsigned int ref_size = ref_top - ref;
+ if (entry->val != val)
+ continue;
+ if (ref_size > top - src)
+ ref_size = top - src;
+ while (ref_size && *src++ == *ref) {
+ ref++;
+ ref_size--;
+ }
+ ref_size = ref - entry->ptr;
+ if (ref_size > msize) {
+ /* this is our best match so far */
+ moff = entry->ptr - ref_data;
+ msize = ref_size;
+ if (msize >= 0x10000) {
+ msize = 0x10000;
+ break;
}
}
}
inscnt = 0;
}
} else {
+ unsigned char *op;
+
if (inscnt) {
out[outpos - inscnt - 1] = inscnt;
inscnt = 0;
}
data += msize;
- orig = out + outpos++;
+ op = out + outpos++;
i = 0x80;
if (moff & 0xff) { out[outpos++] = moff; i |= 0x01; }
msize >>= 8;
if (msize & 0xff) { out[outpos++] = msize; i |= 0x20; }
- *orig = i;
- }
-
- if (max_size && outpos > max_size) {
- free(out);
- delta_cleanup(&bdf);
- return NULL;
+ *op = i;
}
- /* next time around the largest possible output is 1 + 4 + 3 */
- if (outpos > outsize - 8) {
+ if (outpos >= outsize - MAX_OP_SIZE) {
void *tmp = out;
outsize = outsize * 3 / 2;
- out = realloc(out, outsize);
+ if (max_size && outsize >= max_size)
+ outsize = max_size + MAX_OP_SIZE + 1;
+ if (max_size && outpos > max_size)
+ out = NULL;
+ else
+ out = realloc(out, outsize);
if (!out) {
free(tmp);
- delta_cleanup(&bdf);
+ free(hash);
return NULL;
}
}
if (inscnt)
out[outpos - inscnt - 1] = inscnt;
- delta_cleanup(&bdf);
+ free(hash);
*delta_size = outpos;
return out;
}
copy_file('+', temp[1].name);
}
-static void builtin_diff(const char *name_a,
+static const char *builtin_diff(const char *name_a,
const char *name_b,
struct diff_tempfile *temp,
const char *xfrm_msg,
- int complete_rewrite)
+ int complete_rewrite,
+ const char **args)
{
int i, next_at, cmd_size;
const char *const diff_cmd = "diff -L%s -L%s";
}
if (xfrm_msg && xfrm_msg[0])
puts(xfrm_msg);
+ /*
+ * we do not run diff between different kind
+ * of objects.
+ */
if (strncmp(temp[0].mode, temp[1].mode, 3))
- /* we do not run diff between different kind
- * of objects.
- */
- exit(0);
+ return NULL;
if (complete_rewrite) {
- fflush(NULL);
emit_rewrite_diff(name_a, name_b, temp);
- exit(0);
+ return NULL;
}
}
- fflush(NULL);
- execlp("/bin/sh","sh", "-c", cmd, NULL);
+
+ /* This is disgusting */
+ *args++ = "sh";
+ *args++ = "-c";
+ *args++ = cmd;
+ *args = NULL;
+ return "/bin/sh";
}
struct diff_filespec *alloc_filespec(const char *path)
raise(signo);
}
+static int spawn_prog(const char *pgm, const char **arg)
+{
+ pid_t pid;
+ int status;
+
+ fflush(NULL);
+ pid = fork();
+ if (pid < 0)
+ die("unable to fork");
+ if (!pid) {
+ execvp(pgm, (char *const*) arg);
+ exit(255);
+ }
+
+ while (waitpid(pid, &status, 0) < 0) {
+ if (errno == EINTR)
+ continue;
+ return -1;
+ }
+
+ /* Earlier we did not check the exit status because
+ * diff exits non-zero if files are different, and
+ * we are not interested in knowing that. It was a
+ * mistake which made it harder to quit a diff-*
+ * session that uses the git-apply-patch-script as
+ * the GIT_EXTERNAL_DIFF. A custom GIT_EXTERNAL_DIFF
+ * should also exit non-zero only when it wants to
+ * abort the entire diff-* session.
+ */
+ if (WIFEXITED(status) && !WEXITSTATUS(status))
+ return 0;
+ return -1;
+}
+
/* An external diff command takes:
*
* diff-cmd name infile1 infile1-sha1 infile1-mode \
const char *xfrm_msg,
int complete_rewrite)
{
+ const char *spawn_arg[10];
struct diff_tempfile *temp = diff_temp;
- pid_t pid;
- int status;
+ int retval;
static int atexit_asked = 0;
const char *othername;
signal(SIGINT, remove_tempfile_on_signal);
}
- fflush(NULL);
- pid = fork();
- if (pid < 0)
- die("unable to fork");
- if (!pid) {
- if (pgm) {
- if (one && two) {
- const char *exec_arg[10];
- const char **arg = &exec_arg[0];
- *arg++ = pgm;
- *arg++ = name;
- *arg++ = temp[0].name;
- *arg++ = temp[0].hex;
- *arg++ = temp[0].mode;
- *arg++ = temp[1].name;
- *arg++ = temp[1].hex;
- *arg++ = temp[1].mode;
- if (other) {
- *arg++ = other;
- *arg++ = xfrm_msg;
- }
- *arg = NULL;
- execvp(pgm, (char *const*) exec_arg);
+ if (pgm) {
+ const char **arg = &spawn_arg[0];
+ if (one && two) {
+ *arg++ = pgm;
+ *arg++ = name;
+ *arg++ = temp[0].name;
+ *arg++ = temp[0].hex;
+ *arg++ = temp[0].mode;
+ *arg++ = temp[1].name;
+ *arg++ = temp[1].hex;
+ *arg++ = temp[1].mode;
+ if (other) {
+ *arg++ = other;
+ *arg++ = xfrm_msg;
}
- else
- execlp(pgm, pgm, name, NULL);
+ } else {
+ *arg++ = pgm;
+ *arg++ = name;
}
- /*
- * otherwise we use the built-in one.
- */
- if (one && two)
- builtin_diff(name, othername, temp, xfrm_msg,
- complete_rewrite);
- else
+ *arg = NULL;
+ } else {
+ if (one && two) {
+ pgm = builtin_diff(name, othername, temp, xfrm_msg, complete_rewrite, spawn_arg);
+ } else
printf("* Unmerged path %s\n", name);
- exit(0);
}
- if (waitpid(pid, &status, 0) < 0 ||
- !WIFEXITED(status) || WEXITSTATUS(status)) {
- /* Earlier we did not check the exit status because
- * diff exits non-zero if files are different, and
- * we are not interested in knowing that. It was a
- * mistake which made it harder to quit a diff-*
- * session that uses the git-apply-patch-script as
- * the GIT_EXTERNAL_DIFF. A custom GIT_EXTERNAL_DIFF
- * should also exit non-zero only when it wants to
- * abort the entire diff-* session.
- */
- remove_tempfile();
+
+ retval = 0;
+ if (pgm)
+ retval = spawn_prog(pgm, spawn_arg);
+ remove_tempfile();
+ if (retval) {
fprintf(stderr, "external diff died, stopping at %s.\n", name);
exit(1);
}
- remove_tempfile();
}
static void diff_fill_sha1_info(struct diff_filespec *one)
#define MAX_SCORE 60000.0
#define DEFAULT_RENAME_SCORE 30000 /* rename/copy similarity minimum (50%) */
#define DEFAULT_BREAK_SCORE 30000 /* minimum for break to happen (50%)*/
-#define DEFAULT_MERGE_SCORE 48000 /* maximum for break-merge to happen (80%)*/
+#define DEFAULT_MERGE_SCORE 45000 /* maximum for break-merge to happen (75%)*/
#define MINIMUM_BREAK_SIZE 400 /* do not break a file smaller than this */
int repository_format_version = 0;
char git_commit_encoding[MAX_ENCODING_LENGTH] = "utf-8";
int shared_repository = 0;
+const char *apply_default_whitespace = NULL;
static char *git_dir, *git_object_dir, *git_index_file, *git_refs_dir,
*git_graft_file;
use strict;
use warnings;
use Getopt::Std;
+use File::Copy;
use File::Spec;
use File::Temp qw(tempfile);
use File::Path qw(mkpath);
$SIG{'PIPE'}="IGNORE";
$ENV{'TZ'}="UTC";
-our($opt_h,$opt_o,$opt_v,$opt_u,$opt_C,$opt_i,$opt_m,$opt_M,$opt_t,$opt_T,$opt_b,$opt_r,$opt_s,$opt_l,$opt_d,$opt_D);
+our($opt_h,$opt_o,$opt_v,$opt_u,$opt_C,$opt_i,$opt_m,$opt_M,$opt_t,$opt_T,
+ $opt_b,$opt_r,$opt_I,$opt_A,$opt_s,$opt_l,$opt_d,$opt_D);
sub usage() {
print STDERR <<END;
Usage: ${\basename $0} # fetch/update GIT from SVN
[-o branch-for-HEAD] [-h] [-v] [-l max_rev]
[-C GIT_repository] [-t tagname] [-T trunkname] [-b branchname]
- [-d|-D] [-i] [-u] [-r] [-s start_chg] [-m] [-M regex] [SVN_URL]
+ [-d|-D] [-i] [-u] [-r] [-I ignorefilename] [-s start_chg]
+ [-m] [-M regex] [-A author_file] [SVN_URL]
END
exit(1);
}
-getopts("b:C:dDhil:mM:o:rs:t:T:uv") or usage();
+getopts("A:b:C:dDhiI:l:mM:o:rs:t:T:uv") or usage();
usage if $opt_h;
my $tag_name = $opt_t || "tags";
push (@mergerx, qr/$opt_M/);
}
+# Absolutize filename now, since we will have chdir'ed by the time we
+# get around to opening it.
+$opt_A = File::Spec->rel2abs($opt_A) if $opt_A;
+
+our %users = ();
+our $users_file = undef;
+sub read_users($) {
+ $users_file = File::Spec->rel2abs(@_);
+ die "Cannot open $users_file\n" unless -f $users_file;
+ open(my $authors,$users_file);
+ while(<$authors>) {
+ chomp;
+ next unless /^(\S+?)\s*=\s*(.+?)\s*<(.+)>\s*$/;
+ (my $user,my $name,my $email) = ($1,$2,$3);
+ $users{$user} = [$name,$email];
+ }
+ close($authors);
+}
+
select(STDERR); $|=1; select(STDOUT);
DIR => File::Spec->tmpdir(), UNLINK => 1);
print "... $rev $path ...\n" if $opt_v;
- my $pool = SVN::Pool->new();
- eval { $self->{'svn'}->get_file($path,$rev,$fh,$pool); };
- $pool->clear;
+ my (undef, $properties);
+ eval { (undef, $properties)
+ = $self->{'svn'}->get_file($path,$rev,$fh); };
if($@) {
return undef if $@ =~ /Attempted to get checksum/;
die $@;
}
+ my $mode;
+ if (exists $properties->{'svn:executable'}) {
+ $mode = '0755';
+ } else {
+ $mode = '0644';
+ }
close ($fh);
- return $name;
+ return ($name, $mode);
+}
+
+sub ignore {
+ my($self,$path,$rev) = @_;
+
+ print "... $rev $path ...\n" if $opt_v;
+ my (undef,undef,$properties)
+ = $self->{'svn'}->get_dir($path,$rev,undef);
+ if (exists $properties->{'svn:ignore'}) {
+ my ($fh, $name) = tempfile('gitsvn.XXXXXX',
+ DIR => File::Spec->tmpdir(),
+ UNLINK => 1);
+ print $fh $properties->{'svn:ignore'};
+ close($fh);
+ return $name;
+ } else {
+ return undef;
+ }
}
package main;
-d $git_dir
or die "Could not create git subdir ($git_dir).\n";
+my $default_authors = "$git_dir/svn-authors";
+if ($opt_A) {
+ read_users($opt_A);
+ copy($opt_A,$default_authors) or die "Copy failed: $!";
+} else {
+ read_users($default_authors) if -f $default_authors;
+}
+
open BRANCHES,">>", "$git_dir/svn2git";
sub node_kind($$$) {
my $svnpath = revert_split_path($branch,$path);
# now get it
- my $name;
+ my ($name,$mode);
if($opt_d) {
my($req,$res);
return undef if $res->code == 301; # directory?
die $res->status_line." at $url\n";
}
+ $mode = '0644'; # can't obtain mode via direct http request?
} else {
- $name = $svn->file("$svnpath",$rev);
+ ($name,$mode) = $svn->file("$svnpath",$rev);
return undef unless defined $name;
}
chomp $sha;
close $F;
unlink $name;
- my $mode = "0644"; # SV does not seem to store any file modes
return [$mode, $sha, $path];
}
+sub get_ignore($$$$$) {
+ my($new,$old,$rev,$branch,$path) = @_;
+
+ return unless $opt_I;
+ my $svnpath = revert_split_path($branch,$path);
+ my $name = $svn->ignore("$svnpath",$rev);
+ if ($path eq '/') {
+ $path = $opt_I;
+ } else {
+ $path = File::Spec->catfile($path,$opt_I);
+ }
+ if (defined $name) {
+ my $pid = open(my $F, '-|');
+ die $! unless defined $pid;
+ if (!$pid) {
+ exec("git-hash-object", "-w", $name)
+ or die "Cannot create object: $!\n";
+ }
+ my $sha = <$F>;
+ chomp $sha;
+ close $F;
+ unlink $name;
+ push(@$new,['0644',$sha,$path]);
+ } else {
+ push(@$old,$path);
+ }
+}
+
sub split_path($$) {
my($rev,$path) = @_;
my $branch;
if (not defined $author) {
$author_name = $author_email = "unknown";
+ } elsif (defined $users_file) {
+ die "User $author is not listed in $users_file\n"
+ unless exists $users{$author};
+ ($author_name,$author_email) = @{$users{$author}};
} elsif ($author =~ /^(.*?)\s+<(.*)>$/) {
($author_name, $author_email) = ($1, $2);
} else {
my $opath = $action->[3];
print STDERR "$revision: $branch: could not fetch '$opath'\n";
}
+ } elsif ($node_kind eq $SVN::Node::dir) {
+ get_ignore(\@new, \@old, $revision,
+ $branch,$path);
}
} elsif ($action->[0] eq "D") {
push(@old,$path);
if ($node_kind eq $SVN::Node::file) {
my $f = get_file($revision,$branch,$path);
push(@new,$f) if $f;
+ } elsif ($node_kind eq $SVN::Node::dir) {
+ get_ignore(\@new, \@old, $revision,
+ $branch,$path);
}
} else {
die "$revision: unknown action '".$action->[0]."' for $path\n";