diff options
-rw-r--r-- | doc/usage-intro.txt | 19 | ||||
-rw-r--r-- | src/Makefile | 18 | ||||
-rw-r--r-- | src/cache.c | 229 | ||||
-rw-r--r-- | src/cache.h | 13 | ||||
-rw-r--r-- | src/context.c | 199 | ||||
-rw-r--r-- | src/context.h | 28 | ||||
-rw-r--r-- | src/dbstruct.h | 60 | ||||
-rw-r--r-- | src/dbutil.c | 167 | ||||
-rw-r--r-- | src/dbutil.h | 13 | ||||
-rw-r--r-- | src/diff.c | 345 | ||||
-rw-r--r-- | src/diff.h | 18 | ||||
-rw-r--r-- | src/dump.c | 32 | ||||
-rw-r--r-- | src/dump.h | 8 | ||||
-rw-r--r-- | src/history.c | 48 | ||||
-rw-r--r-- | src/history.h | 8 | ||||
-rw-r--r-- | src/info.c | 25 | ||||
-rw-r--r-- | src/info.h | 8 | ||||
-rw-r--r-- | src/list.c | 162 | ||||
-rw-r--r-- | src/list.h | 8 | ||||
-rw-r--r-- | src/md5.c | 381 | ||||
-rw-r--r-- | src/md5.h | 91 | ||||
-rw-r--r-- | src/md5util.c | 85 | ||||
-rw-r--r-- | src/md5util.h | 30 | ||||
-rw-r--r-- | src/merge.c | 132 | ||||
-rw-r--r-- | src/merge.h | 8 | ||||
-rw-r--r-- | src/package.c | 310 | ||||
-rw-r--r-- | src/package.h | 14 | ||||
-rw-r--r-- | src/syrep.c | 301 | ||||
-rw-r--r-- | src/syrep.ggo | 27 | ||||
-rw-r--r-- | src/syrep.h | 13 | ||||
-rw-r--r-- | src/update.c | 207 | ||||
-rw-r--r-- | src/update.h | 9 | ||||
-rw-r--r-- | src/util.c | 106 | ||||
-rw-r--r-- | src/util.h | 16 | ||||
-rw-r--r-- | test/Makefile | 20 |
35 files changed, 3158 insertions, 0 deletions
diff --git a/doc/usage-intro.txt b/doc/usage-intro.txt new file mode 100644 index 0000000..dcb9ee3 --- /dev/null +++ b/doc/usage-intro.txt @@ -0,0 +1,19 @@ +diff [DIR|SNAP] [DIR|SNAP] + +update [-S SNAP] DIR + +list [DIR|SNAP] + +info [DIR|SNAP] + +merge [-S SNAP] SNAP DIR +merge [-S SNAP] PATCH DIR + +makepatch [-S SNAP] -O PATCH SNAP DIR +makepatch [-S SNAP] SNAP DIR > PATCH + +extract [-o DIR] PATCH + +history [DIR|SNAP] + + diff --git a/src/Makefile b/src/Makefile new file mode 100644 index 0000000..45f00b2 --- /dev/null +++ b/src/Makefile @@ -0,0 +1,18 @@ +CFLAGS=-Wall -pipe -O0 -g +CC=gcc + + +all: syrep + +syrep: cache.o update.o util.o syrep.o md5.o md5util.o context.o package.o dbutil.o cmdline.o info.o history.o dump.o list.o diff.o merge.o + $(CC) -g $^ -o $@ -ldb + +cmdline.c cmdline.h: syrep.ggo Makefile + gengetopt --unamed-opts < $< + +update.o: cmdline.h + +clean: + rm -f *.o syrep cmdline.[ch] + +.PHONY: all clean diff --git a/src/cache.c b/src/cache.c new file mode 100644 index 0000000..860b4fb --- /dev/null +++ b/src/cache.c @@ -0,0 +1,229 @@ +#include <db.h> +#include <stdlib.h> +#include <assert.h> +#include <time.h> +#include <string.h> +#include <unistd.h> +#include <fcntl.h> +#include <errno.h> +#include <sys/types.h> +#include <sys/stat.h> + +#include "cache.h" +#include "md5util.h" + +struct syrep_cache_key { + uint64_t dev; + uint64_t inode; + uint32_t date; + uint64_t size; +}; + +struct syrep_cache_data { + uint8_t digest[16]; + uint32_t timestamp; +}; + +struct syrep_md_cache { + DB* db; + uint32_t timestamp; + int ro; +}; + +struct syrep_md_cache* md_cache_open(const char* fn, int ro) { + struct syrep_md_cache *c = NULL; + int ret; + + assert(fn); + + if (!(c = malloc(sizeof(struct syrep_md_cache)))) + goto fail; + + c->timestamp = time(NULL); + c->ro = ro; + + if ((ret = db_create(&c->db, NULL, 0))) { + fprintf(stderr, "db_create: %s\n", db_strerror(ret)); + goto fail; + } + + if ((ret = c->db->open(c->db, NULL, fn, NULL, DB_BTREE, ro ? DB_RDONLY : DB_CREATE, 0664))) { + c->db->err(c->db, ret, "open(%s)", fn); + goto fail; + } + + return c; + +fail: + + if (c) { + if (c->db) + c->db->close(c->db, 0); + + free(c); + } + + return NULL; +} + +void md_cache_close(struct syrep_md_cache *c) { + assert(c); + + if (c->db) + c->db->close(c->db, 0); + + free(c); +} + +static int get(struct syrep_md_cache *c, const struct syrep_cache_key *k, uint8_t digest[16]) { + int ret; + DBT key, data; + + assert(c && c->db && k); + + memset(&key, 0, sizeof(key)); + memset(&data, 0, sizeof(data)); + + key.data = (void*) k; + key.size = sizeof(struct syrep_cache_key); + + if ((ret = c->db->get(c->db, NULL, &key, &data, 0)) != 0) { + if (ret == DB_NOTFOUND) { + //fprintf(stderr, "Cache MISS!\n"); + return 0; + } + + c->db->err(c->db, ret, "cache::get"); + return -1; + } + + //fprintf(stderr, "Cache HIT\n"); + + assert(data.data); + memcpy(digest, &((struct syrep_cache_data*) data.data)->digest, 16); + + return 1; +} + +static int put(struct syrep_md_cache *c, const struct syrep_cache_key *k, const uint8_t digest[16], uint32_t timestamp) { + int ret; + DBT key, data; + struct syrep_cache_data d; + + assert(c && c->db && k); + + memset(&key, 0, sizeof(key)); + key.data = (void*) k; + key.size = sizeof(struct syrep_cache_key); + + memcpy(d.digest, digest, 16); + d.timestamp = timestamp; + + memset(&data, 0, sizeof(data)); + data.data = &d; + data.size = sizeof(struct syrep_cache_data); + + if ((ret = c->db->put(c->db, NULL, &key, &data, 0)) != 0) { + c->db->err(c->db, ret, "cache::put"); + return -1; + } + + return 0; +} + +int md_cache_get(struct syrep_md_cache *c, const char *path, uint8_t digest[16]) { + struct syrep_cache_key k; + int r = -1, fd = -1, j; + struct stat st; + + if ((fd = open(path, O_RDONLY)) < 0) { + fprintf(stderr, "open(%s): %s\n", path, strerror(errno)); + goto finish; + } + + if (fstat(fd, &st) < 0) { + fprintf(stderr, "fstat(%s): %s\n", path, strerror(errno)); + goto finish; + } + + if (!S_ISREG(st.st_mode)) { + fprintf(stderr, "<%s> not a regular file: %s\n", path, strerror(errno)); + goto finish; + } + + memset(&k, 0, sizeof(k)); + k.dev = (uint64_t) st.st_dev; + k.inode = (uint64_t) st.st_ino; + k.date = (uint32_t) st.st_mtime; + k.size = (uint64_t) st.st_size; + + if (!c) + j = 0; + else + if ((j = get(c, &k, digest)) < 0) + goto finish; + + + if (!j) + if (fdmd5(fd, st.st_size, digest) < 0) + goto finish; + + if (c && !c->ro) + put(c, &k, digest, c->timestamp); + + r = 0; + +finish: + + if (fd >= 0) + close(fd); + + return r; +} + +int md_cache_vacuum(struct syrep_md_cache*c) { + int r = -1, ret; + DBC *cursor; + DBT key, data; + int ndel = 0, ntotal = 0; + + if (c->ro) + return 0; + + assert(c && c->db); + + if ((ret = c->db->cursor(c->db, NULL, &cursor, 0)) != 0) { + c->db->err(c->db, ret, "cache::vacuum"); + return -1; + } + + memset(&key, 0, sizeof(key)); + memset(&data, 0, sizeof(data)); + + while ((ret = cursor->c_get(cursor, &key, &data, DB_NEXT)) == 0) { + struct syrep_cache_data *d; + + ntotal++; + d = (struct syrep_cache_data*) data.data; + assert(d); + if (d->timestamp < c->timestamp) { + cursor->c_del(cursor, 0); + ndel++; + } + } + + if (ret != DB_NOTFOUND) { + c->db->err(c->db, ret, "cache::vacuum()"); + goto finish; + } + + /*fprintf(stderr, "Cache vacuum successfully completed, %i of %i entries deleted.\n", ndel, ntotal);*/ + + r = 0; + +finish: + + cursor->c_close(cursor); + + return r; +} diff --git a/src/cache.h b/src/cache.h new file mode 100644 index 0000000..7087b03 --- /dev/null +++ b/src/cache.h @@ -0,0 +1,13 @@ +#ifndef foomdcachehfoo +#define foomdcachehfoo + +#include <stdint.h> + +struct syrep_md_cache; + +struct syrep_md_cache* md_cache_open(const char* fn, int ro); +void md_cache_close(struct syrep_md_cache *c); +int md_cache_get(struct syrep_md_cache *c, const char *path, uint8_t digest[16]); +int md_cache_vacuum(struct syrep_md_cache *c); + +#endif diff --git a/src/context.c b/src/context.c new file mode 100644 index 0000000..00455ea --- /dev/null +++ b/src/context.c @@ -0,0 +1,199 @@ +#include <stdlib.h> +#include <string.h> +#include <assert.h> +#include <time.h> +#include <limits.h> +#include <sys/stat.h> +#include <errno.h> +#include <unistd.h> + +#include "context.h" +#include "package.h" + +int db_context_free(struct syrep_db_context* c) { + if (c) { + + if (c->db_id_meta) + c->db_id_meta->close(c->db_id_meta, 0); + + if (c->db_md_name) + c->db_md_name->close(c->db_md_name, 0); + + if (c->db_name_md) + c->db_name_md->close(c->db_name_md, 0); + + if (c->db_md_lastname) + c->db_md_lastname->close(c->db_md_lastname, 0); + + if (c->db_name_lastmd) + c->db_name_lastmd->close(c->db_name_lastmd, 0); + + if (c->db_version_timestamp) + c->db_version_timestamp->close(c->db_version_timestamp, 0); + + if (c->package) + package_remove(c->package); + + if (c->origin) + free(c->origin); + + free(c); + } + + return 0; +} + + +static DB* open_db(const char*path, int dup) { + int ret; + DB* db; + + if ((ret = db_create(&db, NULL, 0))) { + fprintf(stderr, "db_create: %s\n", db_strerror(ret)); + return NULL; + } + + if (dup) + db->set_flags(db, DB_DUPSORT); + + //db->set_pagesize(db, 4096*8); + + if ((ret = db->open(db, NULL, path, NULL, DB_BTREE, DB_CREATE, 0664))) { + db->err(db, ret, "open(%s)", path); + db->close(db, 0); + return NULL; + } + + return db; +} + +struct syrep_db_context* db_context_open(const char *filename) { + struct syrep_db_context *c = NULL; + const char* path; + FILE *f; + + if (!(c = malloc(sizeof(struct syrep_db_context)))) + goto fail; + + memset(c, 0, sizeof(struct syrep_db_context)); + + if (!(c->package = package_open(filename))) + goto fail; + + path = package_get_item(c->package, "timestamp"); + if ((f = fopen(path, "r"))) { + if (fscanf(f, "%i", &c->timestamp) != 1) + c->timestamp = 0; + fclose(f); + } + + if (!c->timestamp) + c->timestamp = time(NULL); + + path = package_get_item(c->package, "version"); + if ((f = fopen(path, "r"))) { + if (fscanf(f, "%u", &c->version) != 1) + c->version = 0; + fclose(f); + } + + path = package_get_item(c->package, "origin"); + if ((f = fopen(path, "r"))) { + char hn[256]; + if (fgets(hn, sizeof(hn), f)) { + char *nl; + + if ((nl = strchr(hn, '\n'))) + *nl = 0; + + if (hn[0]) + c->origin = strdup(hn); + } + + fclose(f); + } else + c->version = 0; + + if (!c->origin) { + char hn[256]; + if (gethostname(hn, sizeof(hn)) < 0) + goto fail; + + c->origin = strdup(hn); + } + + /* Creating database id_meta */ + if (!(c->db_id_meta = open_db(package_get_item(c->package, "id_meta"), 0))) + goto fail; + + /* Creating database md_name */ + if (!(c->db_md_name = open_db(package_get_item(c->package, "md_name"), 1))) + goto fail; + + /* Creating database name_md */ + if (!(c->db_name_md = open_db(package_get_item(c->package, "name_md"), 1))) + goto fail; + + /* Creating database name_lastmd */ + if (!(c->db_name_lastmd = open_db(package_get_item(c->package, "name_lastmd"), 0))) + goto fail; + + /* Creating database md_lastname */ + if (!(c->db_md_lastname = open_db(package_get_item(c->package, "md_lastname"), 0))) + goto fail; + + /* Creating database version_timestamp */ + if (!(c->db_version_timestamp = open_db(package_get_item(c->package, "version_timestamp"), 0))) + goto fail; + + return c; + + +fail: + db_context_free(c); + + return NULL; +} + +int db_context_save(struct syrep_db_context *c, const char *filename) { + FILE *f; + assert(c && c->package && filename); + + if (c->db_id_meta) + c->db_id_meta->sync(c->db_id_meta, 0); + + if (c->db_md_name) + c->db_md_name->sync(c->db_md_name, 0); + + if (c->db_name_md) + c->db_name_md->sync(c->db_name_md, 0); + + if (c->db_md_lastname) + c->db_md_lastname->sync(c->db_md_lastname, 0); + + if (c->db_name_lastmd) + c->db_name_lastmd->sync(c->db_name_lastmd, 0); + + if (c->db_version_timestamp) + c->db_version_timestamp->sync(c->db_version_timestamp, 0); + + if (!(f = fopen(package_get_item(c->package, "timestamp"), "w+"))) + return -1; + + fprintf(f, "%i\n", c->timestamp); + fclose(f); + + if (!(f = fopen(package_get_item(c->package, "version"), "w+"))) + return -1; + + fprintf(f, "%u\n", c->version); + fclose(f); + + if (!(f = fopen(package_get_item(c->package, "origin"), "w+"))) + return -1; + + fprintf(f, "%s\n", c->origin); + fclose(f); + + return package_save(c->package, filename); +} diff --git a/src/context.h b/src/context.h new file mode 100644 index 0000000..6e51b1c --- /dev/null +++ b/src/context.h @@ -0,0 +1,28 @@ +#ifndef foocontexthfoo +#define foocontexthfoo + +#include <db.h> +#include <stdint.h> + +struct syrep_db_context { + struct package *package; + + DB *db_id_meta, + *db_md_name, + *db_name_md, + *db_name_lastmd, + *db_md_lastname, + *db_version_timestamp; + + uint32_t timestamp; + uint32_t version; + int modified; + + char* origin; +}; + +struct syrep_db_context* db_context_open(const char *path); +int db_context_save(struct syrep_db_context *c, const char *path); +int db_context_free(struct syrep_db_context* c); + +#endif diff --git a/src/dbstruct.h b/src/dbstruct.h new file mode 100644 index 0000000..2555cc1 --- /dev/null +++ b/src/dbstruct.h @@ -0,0 +1,60 @@ +#ifndef foodbstructhfoo +#define foodbstructhfoo + +#include <limits.h> +#include <stdint.h> + +#include "syrep.h" + +struct syrep_md { + uint8_t digest[SYREP_DIGESTLENGTH]; +}; + +struct syrep_name { + char path[PATH_MAX+1]; +}; + +struct syrep_id { + struct syrep_md md; + struct syrep_name name; +}; + +struct syrep_meta { + uint32_t first_seen; + uint32_t last_seen; +}; + +/* struct syrep_namels { */ +/* uint32_t last_seen; */ +/* struct syrep_name name; */ +/* }; */ + +/* struct syrep_mdls { */ +/* uint32_t last_seen; */ +/* struct syrep_md md; */ +/* }; */ + +struct syrep_timestamp { + uint32_t t; +}; + +struct syrep_version { + uint32_t v; +}; + +/* Table layout: + * + * syrep_id :: syrep_meta => id_meta + * syrep_md :: syrep_name => md_name (DUP) + * syrep_name :: syrep_md => name_md (DUP) + * syrep_version :: syrep_timestamp => version_timestamp + * syrep_name :: syrep_md => name_lastmd + * syrep_md :: last_md => md_lastmd + * + */ + +/* + * syrep_namels :: syrep_md => namels_md + * syrep_mdls :: syrep_name => mdls_name + */ +#endif diff --git a/src/dbutil.c b/src/dbutil.c new file mode 100644 index 0000000..b7b44b9 --- /dev/null +++ b/src/dbutil.c @@ -0,0 +1,167 @@ +#include <string.h> +#include <assert.h> +#include <time.h> + +#include "dbutil.h" +#include "util.h" + +int get_meta_by_name_md(struct syrep_db_context *c, const struct syrep_name*name, const struct syrep_md *md, struct syrep_meta *meta) { + int ret; + struct syrep_id id; + DBT key, data; + + assert(c && c->db_id_meta && name); + + memset(&id, 0, sizeof(id)); + memcpy(&id.name, name, sizeof(struct syrep_name)); + memcpy(&id.md, md, sizeof(struct syrep_md)); + + memset(&key, 0, sizeof(key)); + memset(&data, 0, sizeof(data)); + + key.data = &id; + key.size = sizeof(struct syrep_id); + + if ((ret = c->db_id_meta->get(c->db_id_meta, NULL, &key, &data, 0))) { + if (ret == DB_NOTFOUND) + return 0; + + c->db_id_meta->err(c->db_id_meta, ret, "id_meta::get"); + return -1; + } + + assert(data.data); + + if (meta) + memcpy(meta, data.data, sizeof(struct syrep_meta)); + + return 1; +} + + +int get_current_name_by_md(struct syrep_db_context *c, const struct syrep_md *md, struct syrep_name *name) { + int ret, f; + struct syrep_meta meta; + DBT key, data; + + memset(&key, 0, sizeof(key)); + memset(&data, 0, sizeof(data)); + key.data = (void*) md; + key.size = sizeof(struct syrep_md); + + if ((ret = c->db_md_lastname->get(c->db_md_lastname, NULL, &key, &data, 0))) { + if (ret == DB_NOTFOUND) + return 0; + + c->db_md_lastname->err(c->db_md_lastname, ret, "md_lastname::get()"); + return -1; + } + + assert(data.data); + + if ((f = get_meta_by_name_md(c, (struct syrep_name*) data.data, md, &meta)) < 0) + return -1; + + if (!f) { + fprintf(stderr, "Database inconsistency\n"); + return -1; + } + + if (meta.last_seen != c->version) + return 0; + + if (name) + memcpy(name, data.data, sizeof(struct syrep_name)); + + return 1; +} + +int get_last_md_by_name(struct syrep_db_context *c, const struct syrep_name *name, struct syrep_md *md) { + int ret; + DBT key, data; + + memset(&key, 0, sizeof(key)); + memset(&data, 0, sizeof(data)); + + key.data = (void*) name; + key.size = sizeof(struct syrep_name); + + if ((ret = c->db_name_lastmd->get(c->db_name_lastmd, NULL, &key, &data, 0))) { + if (ret == DB_NOTFOUND) { + return 0; + } + + c->db_name_lastmd->err(c->db_name_lastmd, ret, "name_lastmd::get()"); + return -1; + } + + + assert(data.data); + if (md) + memcpy(md, data.data, sizeof(struct syrep_md)); + + return 1; +} + + +int get_current_md_by_name(struct syrep_db_context *c, const struct syrep_name *name, struct syrep_md *md) { + struct syrep_md lmd; + struct syrep_meta meta; + int f; + + if ((f = get_last_md_by_name(c, name, &lmd)) < 0) + return -1; + + if (!f) + return 0; + + if ((f = get_meta_by_name_md(c, name, &lmd, &meta)) < 0) + return -1; + + if (!f) { + fprintf(stderr, "Database inconsistency\n"); + return -1; + } + + if (meta.last_seen != c->version) + return 0; + + memcpy(md, &lmd, sizeof(struct syrep_md)); + return 1; +} + + +uint32_t get_version_timestamp(struct syrep_db_context *c, uint32_t v) { + DBT key, data; + struct syrep_version version; + struct syrep_timestamp *timestamp; + int ret; + + assert(c && c->db_version_timestamp); + + if (v > c->version) + return time(NULL); + + if (v <= 0) + v = 1; + + memset(&version, 0, sizeof(version)); + version.v = v; + + memset(&key, 0, sizeof(key)); + memset(&data, 0, sizeof(data)); + + key.data = &version; + key.size = sizeof(version); + + if ((ret = c->db_version_timestamp->get(c->db_version_timestamp, NULL, &key, &data, 0))) { + c->db_version_timestamp->err(c->db_version_timestamp, ret, "version_timestamp::get"); + return (uint32_t) -1; + } + + timestamp = (struct syrep_timestamp*) data.data; + assert(timestamp); + + return timestamp->t; +} + diff --git a/src/dbutil.h b/src/dbutil.h new file mode 100644 index 0000000..8f6a95a --- /dev/null +++ b/src/dbutil.h @@ -0,0 +1,13 @@ +#ifndef foodbutilhfoo +#define foodbutilhfoo + +#include "dbstruct.h" +#include "context.h" + +int get_meta_by_name_md(struct syrep_db_context *c, const struct syrep_name*name, const struct syrep_md *md, struct syrep_meta *meta); +int get_last_md_by_name(struct syrep_db_context *c, const struct syrep_name *name, struct syrep_md *md); +int get_current_md_by_name(struct syrep_db_context *c, const struct syrep_name *name, struct syrep_md *md); +int get_current_name_by_md(struct syrep_db_context *c, const struct syrep_md *md, struct syrep_name *name); +uint32_t get_version_timestamp(struct syrep_db_context *c, uint32_t v); + +#endif diff --git a/src/diff.c b/src/diff.c new file mode 100644 index 0000000..100d4f9 --- /dev/null +++ b/src/diff.c @@ -0,0 +1,345 @@ +#include <assert.h> +#include <string.h> +#include <stdlib.h> + +#include "diff.h" +#include "dbstruct.h" +#include "util.h" +#include "md5util.h" +#include "dbutil.h" + +static int add_diff_entry(DB *ddb, struct syrep_name *name, int action, struct syrep_db_context *repository) { + DBT key, data; + int ret; + struct diff_entry de; + + memset(&de, 0, sizeof(de)); + de.action = action; + de.repository = repository; + + memset(&key, 0, sizeof(key)); + memset(&data, 0, sizeof(data)); + + key.data = name; + key.size = sizeof(struct syrep_name); + + data.data = &de; + data.size = sizeof(struct diff_entry); + + if ((ret = ddb->put(ddb, NULL, &key, &data, DB_NOOVERWRITE)) != 0) { + DBT data2; + + if (ret != DB_KEYEXIST) { + ddb->err(ddb, ret, "ddb::put()"); + return -1; + } + + memset(&data2, 0, sizeof(data2)); + + if ((ret = ddb->get(ddb, NULL, &key, &data2, 0)) != 0) { + ddb->err(ddb, ret, "ddb::get()"); + return -1; + } + + if (data.size != data2.size || memcmp(data.data, data2.data, data.size)) { + fprintf(stderr, "Snapshot inconsistency\n"); + return -1; + } + } + + return 0; +} + +static int foreach(DB *ddb, struct syrep_db_context *c1, struct syrep_db_context *c2, struct syrep_name *name) { + struct syrep_md md1, md2; + int md1_valid, md2_valid; + + + if ((md1_valid = get_current_md_by_name(c1, name, &md1)) < 0) + return -1; + + if ((md2_valid = get_current_md_by_name(c2, name, &md2)) < 0) + return -1; + + + //fprintf(stderr, "FOREACH %i %i %s\n", md1_valid, md2_valid, name->path); + + if (md1_valid && md2_valid) { + int f1, f2; + + /* Same file? */ + if (!memcmp(&md1, &md2, sizeof(struct syrep_md))) + return 0; + + if ((f1 = get_meta_by_name_md(c1, name, &md2, NULL)) < 0) + return -1; + + if ((f2 = get_meta_by_name_md(c2, name, &md1, NULL)) < 0) + return -1; + + /* The version in c1 is a newer version of that in c2 */ + if (f1 && !f2) + return add_diff_entry(ddb, name, DIFF_COPY, c1); + + /* Vice versa */ + if (!f1 && f2) + return add_diff_entry(ddb, name, DIFF_COPY, c2); + + /* Completely different file */ + return add_diff_entry(ddb, name, DIFF_CONFLICT, NULL); + + } else if (md1_valid) { + struct syrep_meta meta1, meta2; + int f1, f2; + uint32_t t1, t2; + + if ((md2_valid = get_last_md_by_name(c2, name, &md2)) < 0) + return -1; + + if (!md2_valid) + return add_diff_entry(ddb, name, DIFF_COPY, c1); + + if (memcmp(&md1, &md2, sizeof(struct syrep_md))) + return add_diff_entry(ddb, name, DIFF_COPY, c1); + + if ((f1 = get_meta_by_name_md(c1, name, &md1, &meta1)) < 0) + return -1; + + if ((f2 = get_meta_by_name_md(c2, name, &md2, &meta2)) < 0) + return -1; + + if (!f1 || !f2) { + fprintf(stderr, "Database inconsistency\n"); + return -1; + } + + /* Check whether file reappeared in c1 */ + if ((t1 = get_version_timestamp(c1, meta1.first_seen-1)) == (uint32_t) -1) + return -1; + + if ((t2 = get_version_timestamp(c2, meta2.last_seen+1)) == (uint32_t) -1) + return -1; + + if (t1 >= t2) + return add_diff_entry(ddb, name, DIFF_COPY, c1); + + + /* Check whether file was deleted in c2 */ + if ((t1 = get_version_timestamp(c1, meta1.first_seen)) == (uint32_t) -1) + return -1; + + if ((t2 = get_version_timestamp(c2, meta2.last_seen)) == (uint32_t) -1) + return -1; + + if (t1 < t2) + return add_diff_entry(ddb, name, DIFF_DELETE, c1); + + return add_diff_entry(ddb, name, DIFF_CONFLICT, NULL); + + } else if (md2_valid) { + fprintf(stderr, "This should be impossible!\n"); + abort(); + } + + return 0; +} + + +static int enumerate(DB *ddb, struct syrep_db_context *c1, struct syrep_db_context *c2) { + int r = -1, ret; + DBC *cursor = NULL; + DBT key, data; + + if ((ret = c1->db_id_meta->cursor(c1->db_id_meta, NULL, &cursor, 0)) != 0) { + c1->db_id_meta->err(c1->db_id_meta, ret, "id_meta::cursor()"); + goto finish; + } + + memset(&key, 0, sizeof(key)); + memset(&data, 0, sizeof(data)); + + while ((ret = cursor->c_get(cursor, &key, &data, DB_NEXT)) == 0) { + struct syrep_id *id = (struct syrep_id*) key.data; + struct syrep_meta *meta = (struct syrep_meta*) data.data; + + + + assert(id && meta); + + if (meta->last_seen != c1->version) + continue; + + if (foreach(ddb, c1, c2, &id->name) < 0) { + fprintf(stderr, "foreach() failed\n"); + goto finish; + } + } + + + if (ret != DB_NOTFOUND) { + c1->db_id_meta->err(c1->db_id_meta, ret, "id_meta::c_get()"); + goto finish; + } + + r = 0; + +finish: + + if (cursor) + cursor->c_close(cursor); + + return r; +} + +DB* make_diff(struct syrep_db_context *c1, struct syrep_db_context *c2) { + int ret; + DB *ddb = NULL; + + if ((ret = db_create(&ddb, NULL, 0))) { + fprintf(stderr, "ddb::create(): %s\n", db_strerror(ret)); + goto finish; + } + + if ((ret = ddb->open(ddb, NULL, NULL, NULL, DB_BTREE, DB_CREATE, 0664))) { + ddb->err(ddb, ret, "ddb::open()"); + goto finish; + } + + if (enumerate(ddb, c1, c2) < 0) + goto finish; + + if (enumerate(ddb, c2, c1) < 0) + goto finish; + + return ddb; + +finish: + + if (ddb) + ddb->close(ddb, 0); + + return NULL; +} + + +struct cb_info { + struct syrep_db_context *c1, *c2; +}; + +static int list_cb(DB *ddb, struct syrep_name *name, struct diff_entry *de, void *p) { + struct syrep_md md1, md2; + int f1, f2; + struct cb_info *cb_info = p; + + assert(name && de); + + if ((f1 = get_last_md_by_name(cb_info->c1, name, &md1)) < 0) + return -1; + + if ((f2 = get_last_md_by_name(cb_info->c2, name, &md2)) < 0) + return -1; + + if (!(f1 || f2)) { + fprintf(stderr, "Diff inconsicteny\n"); + return -1; + } + + switch (de->action) { + case DIFF_COPY: { + char d[33]; + char src, dst; + + if (de->repository == cb_info->c1) { + src = 'A'; dst = 'B'; + fhex_md5(md1.digest, d); + } else { + src = 'B'; dst = 'A'; + fhex_md5(md2.digest, d); + } + + d[32] = 0; + + fprintf(stderr, "COPY <%s|%s> FROM %c TO %c\n", d, name->path, src, dst); + break; + } + + case DIFF_DELETE: { + char d[33]; + int rep; + + if (de->repository == cb_info->c1) { + rep = 'A'; + fhex_md5(md1.digest, d); + } else { + rep = 'B'; + fhex_md5(md2.digest, d); + } + + d[32] = 0; + + fprintf(stderr, "DELETE <%s|%s> FROM %c\n", d, name->path, rep); + break; + + } + + case DIFF_CONFLICT: { + char d1[33], d2[33]; + + fhex_md5(md1.digest, d1); + fhex_md5(md2.digest, d2); + + d1[32] = d2[32] = 0; + + fprintf(stderr, "CONFLICT <%s> BETWEEN <%s> IN A AND <%s> IN B\n", name->path, d1, d2); + break; + } + } + + return 0; +} + +int list_diff(struct syrep_db_context *c1, struct syrep_db_context *c2, DB *ddb) { + struct cb_info cb_info; + cb_info.c1 = c1; + cb_info.c2 = c2; + + return diff_foreach(ddb, list_cb, &cb_info); +} + +int diff_foreach(DB *ddb, int (*cb)(DB *ddb, struct syrep_name *name, struct diff_entry *de, void *p), void *p) { + DBC *cursor = NULL; + int r = -1, ret; + DBT key, data; + + if ((ret = ddb->cursor(ddb, NULL, &cursor, 0)) != 0) { + ddb->err(ddb, ret, "ddb::cursor()"); + goto finish; + } + + memset(&key, 0, sizeof(key)); + memset(&data, 0, sizeof(data)); + + while ((ret = cursor->c_get(cursor, &key, &data, DB_NEXT)) == 0) { + int t; + struct syrep_name *name = (struct syrep_name*) key.data; + struct diff_entry *de = (struct diff_entry*) data.data; + + if ((t = cb(ddb, name, de, p)) < 0) { + r = t; + goto finish; + } + } + + if (ret != DB_NOTFOUND) { + ddb->err(ddb, ret, "ddb::c_get() failed"); + goto finish; + } + + r = 0; + +finish: + if (cursor) + cursor->c_close(cursor); + + return r; +} diff --git a/src/diff.h b/src/diff.h new file mode 100644 index 0000000..b4a8295 --- /dev/null +++ b/src/diff.h @@ -0,0 +1,18 @@ +#ifndef foodiffhfoo +#define foodiffhfoo + +#include "context.h" +#include "dbstruct.h" + +enum { DIFF_COPY, DIFF_DELETE, DIFF_CONFLICT, DIFF_IGNORE }; + +struct diff_entry { + int action; + struct syrep_db_context *repository; +}; + +DB* make_diff(struct syrep_db_context *c1, struct syrep_db_context *c2); +int diff_foreach(DB *ddb, int (*cb)(DB *db, struct syrep_name *name, struct diff_entry *de, void *p), void *p); +int list_diff(struct syrep_db_context *c1, struct syrep_db_context *c2, DB *ddb); + +#endif diff --git a/src/dump.c b/src/dump.c new file mode 100644 index 0000000..c09da8d --- /dev/null +++ b/src/dump.c @@ -0,0 +1,32 @@ +#include <stdio.h> +#include <assert.h> +#include <string.h> +#include <errno.h> +#include <sys/stat.h> + +#include "dump.h" +#include "package.h" + +static int foreach(struct package *p, char *name, char *path, void *u) { + struct stat st; + uint32_t size; + + if (stat(path, &st) < 0) { + if (errno == ENOENT) + size = 0; + else { + fprintf(stderr, "stat(%s) failed: %s\n", path, strerror(errno)); + return -1; + } + } else + size = (uint32_t) st.st_size; + + printf("%s (%u bytes)\n", name, size); + return 0; +} + +int dump(struct syrep_db_context *c) { + assert(c); + + return package_foreach(c->package, foreach, NULL); +} diff --git a/src/dump.h b/src/dump.h new file mode 100644 index 0000000..b0690a5 --- /dev/null +++ b/src/dump.h @@ -0,0 +1,8 @@ +#ifndef foodumphfoo +#define foodumphfoo + +#include "context.h" + +int dump(struct syrep_db_context *c); + +#endif diff --git a/src/history.c b/src/history.c new file mode 100644 index 0000000..f8fbe63 --- /dev/null +++ b/src/history.c @@ -0,0 +1,48 @@ +#include <assert.h> +#include <string.h> +#include <time.h> + +#include "history.h" +#include "dbstruct.h" + +int history(struct syrep_db_context *c) { + int r = -1, ret; + DBC *cursor = NULL; + DBT key, data; + + assert(c && c->db_version_timestamp); + + if ((ret = c->db_version_timestamp->cursor(c->db_version_timestamp, NULL, &cursor, 0)) != 0) { + c->db_version_timestamp->err(c->db_version_timestamp, ret, "version_timestamp::cursor()"); + goto finish; + } + + memset(&key, 0, sizeof(key)); + memset(&data, 0, sizeof(data)); + + while ((ret = cursor->c_get(cursor, &key, &data, DB_NEXT)) == 0) { + struct syrep_version *version; + struct syrep_timestamp *timestamp; + + version = key.data; + timestamp = data.data; + + assert(version && timestamp); + + fprintf(stderr, "%4u %10u %s", version->v, timestamp->t, ctime((time_t*) (×tamp->t))); + } + + if (ret != DB_NOTFOUND) { + c->db_version_timestamp->err(c->db_version_timestamp, ret, "version_timestamp::c_get()"); + goto finish; + } + + r = 0; + +finish: + + if (cursor) + cursor->c_close(cursor); + + return r; +} diff --git a/src/history.h b/src/history.h new file mode 100644 index 0000000..2082a0c --- /dev/null +++ b/src/history.h @@ -0,0 +1,8 @@ +#ifndef foohistoryfoo +#define foohistoryfoo + +#include "context.h" + +int history(struct syrep_db_context *c); + +#endif diff --git a/src/info.c b/src/info.c new file mode 100644 index 0000000..1475f37 --- /dev/null +++ b/src/info.c @@ -0,0 +1,25 @@ +#include <stdio.h> +#include <assert.h> + +#include "info.h" +#include "util.h" + +int info(struct syrep_db_context *c) { + assert(c); + fprintf(stderr, "Origin: %s\n", c->origin); + fprintf(stderr, "Timestamp: %u\n", c->timestamp); + fprintf(stderr, "Version: %u\n", c->version); + fprintf(stderr, "Database name_meta: "); + statistics(c->db_id_meta); + fprintf(stderr, "Database md_name: "); + statistics(c->db_md_name); + fprintf(stderr, "Database name_md: "); + statistics(c->db_name_md); + fprintf(stderr, "Database name_lastmd: "); + statistics(c->db_name_lastmd); + fprintf(stderr, "Database md_lastname: "); + statistics(c->db_md_lastname); + fprintf(stderr, "Database version_timestamp: "); + statistics(c->db_version_timestamp); + return 0; +} diff --git a/src/info.h b/src/info.h new file mode 100644 index 0000000..93a38b8 --- /dev/null +++ b/src/info.h @@ -0,0 +1,8 @@ +#ifndef fooinfohfoo +#define fooinfohfoo + +#include "context.h" + +int info(struct syrep_db_context *c); + +#endif diff --git a/src/list.c b/src/list.c new file mode 100644 index 0000000..c5c8b90 --- /dev/null +++ b/src/list.c @@ -0,0 +1,162 @@ +#include <string.h> +#include <assert.h> +#include <stdlib.h> + +#include "list.h" +#include "context.h" +#include "md5util.h" +#include "dbstruct.h" +#include "util.h" +#include "dbutil.h" +#include "syrep.h" + +static int handle_file(struct syrep_db_context *c, const struct syrep_name *name, const struct syrep_md *md, const struct syrep_meta *meta) { + struct syrep_meta local_meta; + assert(c && name && md); + + if (!meta) { + int f; + if ((f = get_meta_by_name_md(c, name, md, &local_meta)) < 0) + return -1; + + if (f) + meta = &local_meta; + } + + if (!args.show_deleted_flag && meta->last_seen != c->version) + return 0; + + if (meta) { + if (!args.show_by_md_flag) { + char d[SYREP_DIGESTLENGTH*2+1]; + fhex(md->digest, SYREP_DIGESTLENGTH, d); + d[SYREP_DIGESTLENGTH*2] = 0; + + fprintf(stderr, "%s %s%s", d, name->path, meta->last_seen == c->version ? "\t\t" : "\t(deleted)"); + } else + fprintf(stderr, "\t%s%s", name->path, meta->last_seen == c->version ? "\t\t" : "\t(deleted)"); + + if (args.show_times_flag) + fprintf(stderr, "\t(first-seen: %u; last-seen: %u)\n", meta->first_seen, meta->last_seen); + else + fputc('\n', stderr); + } else { + char d[SYREP_DIGESTLENGTH*2+1]; + fhex(md->digest, SYREP_DIGESTLENGTH, d); + d[SYREP_DIGESTLENGTH*2] = 0; + + fprintf(stderr, "\t%s", name->path); + } + + return 0; +} + +int list(struct syrep_db_context *c) { + int r = -1, ret; + DBC *cursor = NULL; + DBT key, data; + + +#if 1 + + { + if ((ret = c->db_name_lastmd->cursor(c->db_name_lastmd, NULL, &cursor, 0)) != 0) { + c->db_name_lastmd->err(c->db_name_lastmd, ret, "db_name_lastmd"); + goto finish; + } + + memset(&key, 0, sizeof(key)); + memset(&data, 0, sizeof(data)); + + while ((ret = cursor->c_get(cursor, &key, &data, DB_NEXT)) == 0) { + struct syrep_name *name = (struct syrep_name*) key.data; + struct syrep_md *md = (struct syrep_md*) data.data; + + if (handle_file(c, name, md, NULL) < 0) + fprintf(stderr, "handle_file() failed\n"); + + } + + if (ret != DB_NOTFOUND) { + c->db_name_lastmd->err(c->db_name_lastmd, ret, "name_lastmd::c_get"); + goto finish; + } + + r = 0; + } + + goto finish; + +#endif + + if (args.show_by_md_flag) { + struct syrep_md previous_md; + memset(&previous_md, 0, sizeof(previous_md)); + + if ((ret = c->db_md_name->cursor(c->db_md_name, NULL, &cursor, 0)) != 0) { + c->db_md_name->err(c->db_md_name, ret, "md_name"); + goto finish; + } + + memset(&key, 0, sizeof(key)); + memset(&data, 0, sizeof(data)); + + while ((ret = cursor->c_get(cursor, &key, &data, DB_NEXT)) == 0) { + struct syrep_md *md = (struct syrep_md*) key.data; + struct syrep_name *name = (struct syrep_name*) data.data; + struct syrep_meta meta; + + if (memcmp(&previous_md, md, sizeof(previous_md))) { + char d[SYREP_DIGESTLENGTH*2+1]; + fhex(md->digest, SYREP_DIGESTLENGTH, d); + d[SYREP_DIGESTLENGTH*2] = 0; + fprintf(stderr, "%s:\n", d); + memcpy(&previous_md, md, sizeof(previous_md)); + } + + if ((ret = get_meta_by_name_md(c, name, md, &meta)) < 0) + goto finish; + + if (handle_file(c, name, md, &meta) < 0) + fprintf(stderr, "handle_file() failed\n"); + } + + if (ret != DB_NOTFOUND) { + c->db_md_name->err(c->db_md_name, ret, "md_name::c_get"); + goto finish; + } + + r = 0; + } else { + + if ((ret = c->db_id_meta->cursor(c->db_id_meta, NULL, &cursor, 0)) != 0) { + c->db_id_meta->err(c->db_id_meta, ret, "id_meta"); + goto finish; + } + + memset(&key, 0, sizeof(key)); + memset(&data, 0, sizeof(data)); + + while ((ret = cursor->c_get(cursor, &key, &data, DB_NEXT)) == 0) { + struct syrep_id *id = (struct syrep_id*) key.data; + + if (handle_file(c, &id->name, &id->md, (struct syrep_meta*) data.data) < 0) + fprintf(stderr, "handle_file() failed\n"); + + } + + if (ret != DB_NOTFOUND) { + c->db_id_meta->err(c->db_id_meta, ret, "id_meta::c_get"); + goto finish; + } + + r = 0; + } + +finish: + + if (cursor) + cursor->c_close(cursor); + + return r; +} diff --git a/src/list.h b/src/list.h new file mode 100644 index 0000000..c66fe75 --- /dev/null +++ b/src/list.h @@ -0,0 +1,8 @@ +#ifndef foolisthfoo +#define foolisthfoo + +#include "context.h" + +int list(struct syrep_db_context *c); + +#endif diff --git a/src/md5.c b/src/md5.c new file mode 100644 index 0000000..2c9c2fc --- /dev/null +++ b/src/md5.c @@ -0,0 +1,381 @@ +/* + Copyright (C) 1999, 2000, 2002 Aladdin Enterprises. All rights reserved. + + This software is provided 'as-is', without any express or implied + warranty. In no event will the authors be held liable for any damages + arising from the use of this software. + + Permission is granted to anyone to use this software for any purpose, + including commercial applications, and to alter it and redistribute it + freely, subject to the following restrictions: + + 1. The origin of this software must not be misrepresented; you must not + claim that you wrote the original software. If you use this software + in a product, an acknowledgment in the product documentation would be + appreciated but is not required. + 2. Altered source versions must be plainly marked as such, and must not be + misrepresented as being the original software. + 3. This notice may not be removed or altered from any source distribution. + + L. Peter Deutsch + ghost@aladdin.com + + */ +/* $Id$ */ +/* + Independent implementation of MD5 (RFC 1321). + + This code implements the MD5 Algorithm defined in RFC 1321, whose + text is available at + http://www.ietf.org/rfc/rfc1321.txt + The code is derived from the text of the RFC, including the test suite + (section A.5) but excluding the rest of Appendix A. It does not include + any code or documentation that is identified in the RFC as being + copyrighted. + + The original and principal author of md5.c is L. Peter Deutsch + <ghost@aladdin.com>. Other authors are noted in the change history + that follows (in reverse chronological order): + + 2002-04-13 lpd Clarified derivation from RFC 1321; now handles byte order + either statically or dynamically; added missing #include <string.h> + in library. + 2002-03-11 lpd Corrected argument list for main(), and added int return + type, in test program and T value program. + 2002-02-21 lpd Added missing #include <stdio.h> in test program. + 2000-07-03 lpd Patched to eliminate warnings about "constant is + unsigned in ANSI C, signed in traditional"; made test program + self-checking. + 1999-11-04 lpd Edited comments slightly for automatic TOC extraction. + 1999-10-18 lpd Fixed typo in header comment (ansi2knr rather than md5). + 1999-05-03 lpd Original version. + */ + +#include "md5.h" +#include <string.h> + +#undef BYTE_ORDER /* 1 = big-endian, -1 = little-endian, 0 = unknown */ +#ifdef ARCH_IS_BIG_ENDIAN +# define BYTE_ORDER (ARCH_IS_BIG_ENDIAN ? 1 : -1) +#else +# define BYTE_ORDER 0 +#endif + +#define T_MASK ((md5_word_t)~0) +#define T1 /* 0xd76aa478 */ (T_MASK ^ 0x28955b87) +#define T2 /* 0xe8c7b756 */ (T_MASK ^ 0x173848a9) +#define T3 0x242070db +#define T4 /* 0xc1bdceee */ (T_MASK ^ 0x3e423111) +#define T5 /* 0xf57c0faf */ (T_MASK ^ 0x0a83f050) +#define T6 0x4787c62a +#define T7 /* 0xa8304613 */ (T_MASK ^ 0x57cfb9ec) +#define T8 /* 0xfd469501 */ (T_MASK ^ 0x02b96afe) +#define T9 0x698098d8 +#define T10 /* 0x8b44f7af */ (T_MASK ^ 0x74bb0850) +#define T11 /* 0xffff5bb1 */ (T_MASK ^ 0x0000a44e) +#define T12 /* 0x895cd7be */ (T_MASK ^ 0x76a32841) +#define T13 0x6b901122 +#define T14 /* 0xfd987193 */ (T_MASK ^ 0x02678e6c) +#define T15 /* 0xa679438e */ (T_MASK ^ 0x5986bc71) +#define T16 0x49b40821 +#define T17 /* 0xf61e2562 */ (T_MASK ^ 0x09e1da9d) +#define T18 /* 0xc040b340 */ (T_MASK ^ 0x3fbf4cbf) +#define T19 0x265e5a51 +#define T20 /* 0xe9b6c7aa */ (T_MASK ^ 0x16493855) +#define T21 /* 0xd62f105d */ (T_MASK ^ 0x29d0efa2) +#define T22 0x02441453 +#define T23 /* 0xd8a1e681 */ (T_MASK ^ 0x275e197e) +#define T24 /* 0xe7d3fbc8 */ (T_MASK ^ 0x182c0437) +#define T25 0x21e1cde6 +#define T26 /* 0xc33707d6 */ (T_MASK ^ 0x3cc8f829) +#define T27 /* 0xf4d50d87 */ (T_MASK ^ 0x0b2af278) +#define T28 0x455a14ed +#define T29 /* 0xa9e3e905 */ (T_MASK ^ 0x561c16fa) +#define T30 /* 0xfcefa3f8 */ (T_MASK ^ 0x03105c07) +#define T31 0x676f02d9 +#define T32 /* 0x8d2a4c8a */ (T_MASK ^ 0x72d5b375) +#define T33 /* 0xfffa3942 */ (T_MASK ^ 0x0005c6bd) +#define T34 /* 0x8771f681 */ (T_MASK ^ 0x788e097e) +#define T35 0x6d9d6122 +#define T36 /* 0xfde5380c */ (T_MASK ^ 0x021ac7f3) +#define T37 /* 0xa4beea44 */ (T_MASK ^ 0x5b4115bb) +#define T38 0x4bdecfa9 +#define T39 /* 0xf6bb4b60 */ (T_MASK ^ 0x0944b49f) +#define T40 /* 0xbebfbc70 */ (T_MASK ^ 0x4140438f) +#define T41 0x289b7ec6 +#define T42 /* 0xeaa127fa */ (T_MASK ^ 0x155ed805) +#define T43 /* 0xd4ef3085 */ (T_MASK ^ 0x2b10cf7a) +#define T44 0x04881d05 +#define T45 /* 0xd9d4d039 */ (T_MASK ^ 0x262b2fc6) +#define T46 /* 0xe6db99e5 */ (T_MASK ^ 0x1924661a) +#define T47 0x1fa27cf8 +#define T48 /* 0xc4ac5665 */ (T_MASK ^ 0x3b53a99a) +#define T49 /* 0xf4292244 */ (T_MASK ^ 0x0bd6ddbb) +#define T50 0x432aff97 +#define T51 /* 0xab9423a7 */ (T_MASK ^ 0x546bdc58) +#define T52 /* 0xfc93a039 */ (T_MASK ^ 0x036c5fc6) +#define T53 0x655b59c3 +#define T54 /* 0x8f0ccc92 */ (T_MASK ^ 0x70f3336d) +#define T55 /* 0xffeff47d */ (T_MASK ^ 0x00100b82) +#define T56 /* 0x85845dd1 */ (T_MASK ^ 0x7a7ba22e) +#define T57 0x6fa87e4f +#define T58 /* 0xfe2ce6e0 */ (T_MASK ^ 0x01d3191f) +#define T59 /* 0xa3014314 */ (T_MASK ^ 0x5cfebceb) +#define T60 0x4e0811a1 +#define T61 /* 0xf7537e82 */ (T_MASK ^ 0x08ac817d) +#define T62 /* 0xbd3af235 */ (T_MASK ^ 0x42c50dca) +#define T63 0x2ad7d2bb +#define T64 /* 0xeb86d391 */ (T_MASK ^ 0x14792c6e) + + +static void +md5_process(md5_state_t *pms, const md5_byte_t *data /*[64]*/) +{ + md5_word_t + a = pms->abcd[0], b = pms->abcd[1], + c = pms->abcd[2], d = pms->abcd[3]; + md5_word_t t; +#if BYTE_ORDER > 0 + /* Define storage only for big-endian CPUs. */ + md5_word_t X[16]; +#else + /* Define storage for little-endian or both types of CPUs. */ + md5_word_t xbuf[16]; + const md5_word_t *X; +#endif + + { +#if BYTE_ORDER == 0 + /* + * Determine dynamically whether this is a big-endian or + * little-endian machine, since we can use a more efficient + * algorithm on the latter. + */ + static const int w = 1; + + if (*((const md5_byte_t *)&w)) /* dynamic little-endian */ +#endif +#if BYTE_ORDER <= 0 /* little-endian */ + { + /* + * On little-endian machines, we can process properly aligned + * data without copying it. + */ + if (!((data - (const md5_byte_t *)0) & 3)) { + /* data are properly aligned */ + X = (const md5_word_t *)data; + } else { + /* not aligned */ + memcpy(xbuf, data, 64); + X = xbuf; + } + } +#endif +#if BYTE_ORDER == 0 + else /* dynamic big-endian */ +#endif +#if BYTE_ORDER >= 0 /* big-endian */ + { + /* + * On big-endian machines, we must arrange the bytes in the + * right order. + */ + const md5_byte_t *xp = data; + int i; + +# if BYTE_ORDER == 0 + X = xbuf; /* (dynamic only) */ +# else +# define xbuf X /* (static only) */ +# endif + for (i = 0; i < 16; ++i, xp += 4) + xbuf[i] = xp[0] + (xp[1] << 8) + (xp[2] << 16) + (xp[3] << 24); + } +#endif + } + +#define ROTATE_LEFT(x, n) (((x) << (n)) | ((x) >> (32 - (n)))) + + /* Round 1. */ + /* Let [abcd k s i] denote the operation + a = b + ((a + F(b,c,d) + X[k] + T[i]) <<< s). */ +#define F(x, y, z) (((x) & (y)) | (~(x) & (z))) +#define SET(a, b, c, d, k, s, Ti)\ + t = a + F(b,c,d) + X[k] + Ti;\ + a = ROTATE_LEFT(t, s) + b + /* Do the following 16 operations. */ + SET(a, b, c, d, 0, 7, T1); + SET(d, a, b, c, 1, 12, T2); + SET(c, d, a, b, 2, 17, T3); + SET(b, c, d, a, 3, 22, T4); + SET(a, b, c, d, 4, 7, T5); + SET(d, a, b, c, 5, 12, T6); + SET(c, d, a, b, 6, 17, T7); + SET(b, c, d, a, 7, 22, T8); + SET(a, b, c, d, 8, 7, T9); + SET(d, a, b, c, 9, 12, T10); + SET(c, d, a, b, 10, 17, T11); + SET(b, c, d, a, 11, 22, T12); + SET(a, b, c, d, 12, 7, T13); + SET(d, a, b, c, 13, 12, T14); + SET(c, d, a, b, 14, 17, T15); + SET(b, c, d, a, 15, 22, T16); +#undef SET + + /* Round 2. */ + /* Let [abcd k s i] denote the operation + a = b + ((a + G(b,c,d) + X[k] + T[i]) <<< s). */ +#define G(x, y, z) (((x) & (z)) | ((y) & ~(z))) +#define SET(a, b, c, d, k, s, Ti)\ + t = a + G(b,c,d) + X[k] + Ti;\ + a = ROTATE_LEFT(t, s) + b + /* Do the following 16 operations. */ + SET(a, b, c, d, 1, 5, T17); + SET(d, a, b, c, 6, 9, T18); + SET(c, d, a, b, 11, 14, T19); + SET(b, c, d, a, 0, 20, T20); + SET(a, b, c, d, 5, 5, T21); + SET(d, a, b, c, 10, 9, T22); + SET(c, d, a, b, 15, 14, T23); + SET(b, c, d, a, 4, 20, T24); + SET(a, b, c, d, 9, 5, T25); + SET(d, a, b, c, 14, 9, T26); + SET(c, d, a, b, 3, 14, T27); + SET(b, c, d, a, 8, 20, T28); + SET(a, b, c, d, 13, 5, T29); + SET(d, a, b, c, 2, 9, T30); + SET(c, d, a, b, 7, 14, T31); + SET(b, c, d, a, 12, 20, T32); +#undef SET + + /* Round 3. */ + /* Let [abcd k s t] denote the operation + a = b + ((a + H(b,c,d) + X[k] + T[i]) <<< s). */ +#define H(x, y, z) ((x) ^ (y) ^ (z)) +#define SET(a, b, c, d, k, s, Ti)\ + t = a + H(b,c,d) + X[k] + Ti;\ + a = ROTATE_LEFT(t, s) + b + /* Do the following 16 operations. */ + SET(a, b, c, d, 5, 4, T33); + SET(d, a, b, c, 8, 11, T34); + SET(c, d, a, b, 11, 16, T35); + SET(b, c, d, a, 14, 23, T36); + SET(a, b, c, d, 1, 4, T37); + SET(d, a, b, c, 4, 11, T38); + SET(c, d, a, b, 7, 16, T39); + SET(b, c, d, a, 10, 23, T40); + SET(a, b, c, d, 13, 4, T41); + SET(d, a, b, c, 0, 11, T42); + SET(c, d, a, b, 3, 16, T43); + SET(b, c, d, a, 6, 23, T44); + SET(a, b, c, d, 9, 4, T45); + SET(d, a, b, c, 12, 11, T46); + SET(c, d, a, b, 15, 16, T47); + SET(b, c, d, a, 2, 23, T48); +#undef SET + + /* Round 4. */ + /* Let [abcd k s t] denote the operation + a = b + ((a + I(b,c,d) + X[k] + T[i]) <<< s). */ +#define I(x, y, z) ((y) ^ ((x) | ~(z))) +#define SET(a, b, c, d, k, s, Ti)\ + t = a + I(b,c,d) + X[k] + Ti;\ + a = ROTATE_LEFT(t, s) + b + /* Do the following 16 operations. */ + SET(a, b, c, d, 0, 6, T49); + SET(d, a, b, c, 7, 10, T50); + SET(c, d, a, b, 14, 15, T51); + SET(b, c, d, a, 5, 21, T52); + SET(a, b, c, d, 12, 6, T53); + SET(d, a, b, c, 3, 10, T54); + SET(c, d, a, b, 10, 15, T55); + SET(b, c, d, a, 1, 21, T56); + SET(a, b, c, d, 8, 6, T57); + SET(d, a, b, c, 15, 10, T58); + SET(c, d, a, b, 6, 15, T59); + SET(b, c, d, a, 13, 21, T60); + SET(a, b, c, d, 4, 6, T61); + SET(d, a, b, c, 11, 10, T62); + SET(c, d, a, b, 2, 15, T63); + SET(b, c, d, a, 9, 21, T64); +#undef SET + + /* Then perform the following additions. (That is increment each + of the four registers by the value it had before this block + was started.) */ + pms->abcd[0] += a; + pms->abcd[1] += b; + pms->abcd[2] += c; + pms->abcd[3] += d; +} + +void +md5_init(md5_state_t *pms) +{ + pms->count[0] = pms->count[1] = 0; + pms->abcd[0] = 0x67452301; + pms->abcd[1] = /*0xefcdab89*/ T_MASK ^ 0x10325476; + pms->abcd[2] = /*0x98badcfe*/ T_MASK ^ 0x67452301; + pms->abcd[3] = 0x10325476; +} + +void +md5_append(md5_state_t *pms, const md5_byte_t *data, int nbytes) +{ + const md5_byte_t *p = data; + int left = nbytes; + int offset = (pms->count[0] >> 3) & 63; + md5_word_t nbits = (md5_word_t)(nbytes << 3); + + if (nbytes <= 0) + return; + + /* Update the message length. */ + pms->count[1] += nbytes >> 29; + pms->count[0] += nbits; + if (pms->count[0] < nbits) + pms->count[1]++; + + /* Process an initial partial block. */ + if (offset) { + int copy = (offset + nbytes > 64 ? 64 - offset : nbytes); + + memcpy(pms->buf + offset, p, copy); + if (offset + copy < 64) + return; + p += copy; + left -= copy; + md5_process(pms, pms->buf); + } + + /* Process full blocks. */ + for (; left >= 64; p += 64, left -= 64) + md5_process(pms, p); + + /* Process a final partial block. */ + if (left) + memcpy(pms->buf, p, left); +} + +void +md5_finish(md5_state_t *pms, md5_byte_t digest[16]) +{ + static const md5_byte_t pad[64] = { + 0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 + }; + md5_byte_t data[8]; + int i; + + /* Save the length before padding. */ + for (i = 0; i < 8; ++i) + data[i] = (md5_byte_t)(pms->count[i >> 2] >> ((i & 3) << 3)); + /* Pad to 56 bytes mod 64. */ + md5_append(pms, pad, ((55 - (pms->count[0] >> 3)) & 63) + 1); + /* Append the length. */ + md5_append(pms, data, 8); + for (i = 0; i < 16; ++i) + digest[i] = (md5_byte_t)(pms->abcd[i >> 2] >> ((i & 3) << 3)); +} diff --git a/src/md5.h b/src/md5.h new file mode 100644 index 0000000..5eb6d6c --- /dev/null +++ b/src/md5.h @@ -0,0 +1,91 @@ +/* + Copyright (C) 1999, 2002 Aladdin Enterprises. All rights reserved. + + This software is provided 'as-is', without any express or implied + warranty. In no event will the authors be held liable for any damages + arising from the use of this software. + + Permission is granted to anyone to use this software for any purpose, + including commercial applications, and to alter it and redistribute it + freely, subject to the following restrictions: + + 1. The origin of this software must not be misrepresented; you must not + claim that you wrote the original software. If you use this software + in a product, an acknowledgment in the product documentation would be + appreciated but is not required. + 2. Altered source versions must be plainly marked as such, and must not be + misrepresented as being the original software. + 3. This notice may not be removed or altered from any source distribution. + + L. Peter Deutsch + ghost@aladdin.com + + */ +/* $Id$ */ +/* + Independent implementation of MD5 (RFC 1321). + + This code implements the MD5 Algorithm defined in RFC 1321, whose + text is available at + http://www.ietf.org/rfc/rfc1321.txt + The code is derived from the text of the RFC, including the test suite + (section A.5) but excluding the rest of Appendix A. It does not include + any code or documentation that is identified in the RFC as being + copyrighted. + + The original and principal author of md5.h is L. Peter Deutsch + <ghost@aladdin.com>. Other authors are noted in the change history + that follows (in reverse chronological order): + + 2002-04-13 lpd Removed support for non-ANSI compilers; removed + references to Ghostscript; clarified derivation from RFC 1321; + now handles byte order either statically or dynamically. + 1999-11-04 lpd Edited comments slightly for automatic TOC extraction. + 1999-10-18 lpd Fixed typo in header comment (ansi2knr rather than md5); + added conditionalization for C++ compilation from Martin + Purschke <purschke@bnl.gov>. + 1999-05-03 lpd Original version. + */ + +#ifndef md5_INCLUDED +# define md5_INCLUDED + +/* + * This package supports both compile-time and run-time determination of CPU + * byte order. If ARCH_IS_BIG_ENDIAN is defined as 0, the code will be + * compiled to run only on little-endian CPUs; if ARCH_IS_BIG_ENDIAN is + * defined as non-zero, the code will be compiled to run only on big-endian + * CPUs; if ARCH_IS_BIG_ENDIAN is not defined, the code will be compiled to + * run on either big- or little-endian CPUs, but will run slightly less + * efficiently on either one than if ARCH_IS_BIG_ENDIAN is defined. + */ + +typedef unsigned char md5_byte_t; /* 8-bit byte */ +typedef unsigned int md5_word_t; /* 32-bit word */ + +/* Define the state of the MD5 Algorithm. */ +typedef struct md5_state_s { + md5_word_t count[2]; /* message length in bits, lsw first */ + md5_word_t abcd[4]; /* digest buffer */ + md5_byte_t buf[64]; /* accumulate block */ +} md5_state_t; + +#ifdef __cplusplus +extern "C" +{ +#endif + +/* Initialize the algorithm. */ +void md5_init(md5_state_t *pms); + +/* Append a string to the message. */ +void md5_append(md5_state_t *pms, const md5_byte_t *data, int nbytes); + +/* Finish the message and return the digest. */ +void md5_finish(md5_state_t *pms, md5_byte_t digest[16]); + +#ifdef __cplusplus +} /* end extern "C" */ +#endif + +#endif /* md5_INCLUDED */ diff --git a/src/md5util.c b/src/md5util.c new file mode 100644 index 0000000..41a5a31 --- /dev/null +++ b/src/md5util.c @@ -0,0 +1,85 @@ +/*** + This file is part of pam_dotfile. + + pam_dotfile is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + pam_dotfile is distributed in the hope that it will be useful, but + WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + General Public License for more details. + + You should have received a copy of the GNU General Public License + along with pam_dotfile; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 + USA +***/ + +#include <unistd.h> +#include <sys/mman.h> +#include <stdio.h> +#include <stdlib.h> + +#include "md5util.h" +#include "md5.h" + +void fhex(const unsigned char *bin,int len, char *txt) { + const static char hex[] = "0123456789abcdef"; + int i; + + for (i = 0; i < len; i++) { + txt[i*2] = hex[bin[i]>>4]; + txt[i*2+1] = hex[bin[i]&0xF]; + } +} + +#define MMAPSIZE (100*1024*1024) +#define BUFSIZE (1024*1024) + +int fdmd5(int fd, size_t l, char *md) { + void *d; + off_t o = 0; + size_t m; + int r = 0; + md5_state_t s; + + md5_init(&s); + + m = l < MMAPSIZE ? l : MMAPSIZE; + + while (l > 0 && (d = mmap(NULL, m, PROT_READ, MAP_SHARED, fd, o))) { + md5_append(&s, d, m); + munmap(d, m); + + o += m; + l -= m; + m = l < MMAPSIZE ? l : MMAPSIZE; + + } + + if (l > 0) { + void *p; + fprintf(stderr, "mmap() failed\n"); + + if (!(p = malloc(BUFSIZE))) + r = -1; + else { + + for (;;) { + ssize_t r; + + if ((r = read(fd, p, BUFSIZE)) <= 0) + break; + + md5_append(&s, p, r); + } + + free(p); + } + } + + md5_finish(&s, md); + return r; +} diff --git a/src/md5util.h b/src/md5util.h new file mode 100644 index 0000000..83f4bb7 --- /dev/null +++ b/src/md5util.h @@ -0,0 +1,30 @@ +#ifndef foomd5utilhfoo +#define foomd5utilhfoo + +/*** + This file is part of pam_dotfile. + + pam_dotfile is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + pam_dotfile is distributed in the hope that it will be useful, but + WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + General Public License for more details. + + You should have received a copy of the GNU General Public License + along with pam_dotfile; if not, write to the Free Software + Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 + USA +***/ + +#include <sys/types.h> + +void fhex(const unsigned char *bin, int len, char *txt); +#define fhex_md5(bin,txt) fhex((bin),16,(txt)) + +int fdmd5(int fd, size_t l, char *md); + +#endif diff --git a/src/merge.c b/src/merge.c new file mode 100644 index 0000000..aef3f8f --- /dev/null +++ b/src/merge.c @@ -0,0 +1,132 @@ +#include <stdio.h> +#include <assert.h> +#include <string.h> +#include <unistd.h> +#include <errno.h> + +#include "md5util.h" +#include "diff.h" +#include "dbutil.h" + +struct cb_info { + struct syrep_db_context *c1; + struct syrep_db_context *c2; + const char *root; +}; + +int conflict_phase(DB *ddb, struct syrep_name *name, struct diff_entry *de, void *p) { + struct cb_info *cb_info = p; + char path[PATH_MAX+1]; + + assert(ddb && name && de && p); + + if (de->action != DIFF_CONFLICT) + return 0; + + snprintf(path, sizeof(path), "%s/%s", cb_info->root, name->path); + fprintf(stderr, "QUERY %s\n", path); + + return 0; +} + +int copy_phase(DB *ddb, struct syrep_name *name, struct diff_entry *de, void *p) { + struct cb_info *cb_info = p; + struct syrep_name name2; + struct syrep_md md; + char path[PATH_MAX+1]; + int f; + char d[SYREP_DIGESTLENGTH*2+1]; + + assert(ddb && name && de && p); + + if (de->action != DIFF_COPY) + return 0; + + if (de->repository == cb_info->c2) + return 0; + + snprintf(path, sizeof(path), "%s/%s", cb_info->root, name->path); + + if ((f = get_current_md_by_name(cb_info->c1, name, &md)) < 0) + return -1; + + + if (!f) { + fprintf(stderr, "Diff invalid!\n"); + return -1; + } + + fhex(md.digest, SYREP_DIGESTLENGTH, d); + d[SYREP_DIGESTLENGTH*2] = 0; + + fprintf(stderr, "Searching for %s\n", d); + + if ((f = get_current_name_by_md(cb_info->c2, &md, &name2)) < 0) + return -1; + + if (f) { + char path2[PATH_MAX+1]; + snprintf(path2, sizeof(path2), "%s/%s", cb_info->root, name2.path); + fprintf(stderr, "Linking file <%s> to <%s>\n", path2, path); + if (link(path2, path) < 0) { + fprintf(stderr, "Failed to link: %s\n", strerror(errno)); + return -1; + } + } else + fprintf(stderr, "MISSING FILE %s\n", path); + + return 0; +} + +int delete_phase(DB *ddb, struct syrep_name *name, struct diff_entry *de, void *p) { + struct cb_info *cb_info = p; + char path[PATH_MAX+1]; + + assert(ddb && name && de && p); + + if (de->action != DIFF_DELETE) + return 0; + + if (de->repository == cb_info->c1) + return 0; + + snprintf(path, sizeof(path), "%s/%s", cb_info->root, name->path); + fprintf(stderr, "Deleting file <%s>\n", path); + + if (unlink(path) < 0) { + fprintf(stderr, "Failed to unlink: %s\n", strerror(errno)); + return -1; + } + + return 0; +} + +/* Merges c1 into c2 in directory "root" */ +int merge_snapshot(struct syrep_db_context *c1, struct syrep_db_context *c2, const char* root) { + struct cb_info cb_info; + DB *ddb = NULL; + + memset(&cb_info, 0, sizeof(cb_info)); + cb_info.c1 = c1; + cb_info.c2 = c2; + cb_info.root = root; + + if (!(ddb = make_diff(c1, c2))) + goto finish; + + if (diff_foreach(ddb, conflict_phase, &cb_info) < 0) + goto finish; + + if (diff_foreach(ddb, copy_phase, &cb_info) < 0) + goto finish; + + if (diff_foreach(ddb, delete_phase, &cb_info) < 0) + goto finish; + +finish: + if (ddb) + ddb->close(ddb, 0); + + return 0; +} + diff --git a/src/merge.h b/src/merge.h new file mode 100644 index 0000000..2b88712 --- /dev/null +++ b/src/merge.h @@ -0,0 +1,8 @@ +#ifndef foomergehfoo +#define foomergehfoo + +#include "context.h" + +int merge_snapshot(struct syrep_db_context *c1, struct syrep_db_context *c2, const char* root); + +#endif diff --git a/src/package.c b/src/package.c new file mode 100644 index 0000000..168a6d8 --- /dev/null +++ b/src/package.c @@ -0,0 +1,310 @@ +#include <stdio.h> +#include <stdint.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> +#include <limits.h> +#include <unistd.h> +#include <assert.h> +#include <sys/types.h> +#include <sys/stat.h> + +#include "package.h" + +struct package_item; + +struct package_item { + char *name; + char *path; + struct package_item *next; +}; + +struct package { + char *base; + int count; + struct package_item *items; + struct package_item *last; +}; + +static int copy(FILE *f, FILE *t, uint32_t len) { + static char buf[2048*4]; + + while (len > 0) { + uint32_t n; + + if (feof(f)) + return -1; + + n = len > sizeof(buf) ? sizeof(buf) : len; + + if (fread(buf, n, 1, f) != 1) + return -1; + + if (fwrite(buf, n, 1, t) != 1) + return -1; + + len -= n; + } + + return 0; +} + +static char *tmp(char *fn, int l) { + char *t; + + if (!(t = getenv("TMPDIR"))) + if (!(t = getenv("TEMP"))) + if (!(t = getenv("TMP"))) + t = "/tmp"; + + snprintf(fn, l, "%s/pkgXXXXXX", t); + return fn; +} + +static struct package_item *item_new(const char *name, const char *path) { + struct package_item *i = NULL; + + if (!(i = malloc(sizeof(struct package_item)))) + return NULL; + + memset(i, 0, sizeof(struct package_item)); + + if (!(i->name = strdup(name))) + goto fail; + + if (!(i->path = strdup(path))) + goto fail; + + return i; + +fail: + if(i) { + if (i->path) + free(i->path); + if (i->name) + free(i->name); + free(i); + } + + return NULL; +} + +struct package* package_open(const char *fn) { + struct package *p; + FILE *f = NULL; + char path[PATH_MAX]; + + if (!(p = malloc(sizeof(struct package)))) { + fprintf(stderr, "Failed to allocate package structure.\n"); + return NULL; + } + + memset(p, 0, sizeof(struct package)); + + tmp(path, sizeof(path)); + if (!mkdtemp(path)) { + fprintf(stderr, "Failed to create temporary directory.\n"); + goto finish; + } + + if (!(p->base = strdup(path))) { + fprintf(stderr, "Failed to allocate memory.\n"); + goto finish; + } + + if (fn) { + if (!(f = fopen(fn, "r"))) { + fprintf(stderr, "Failed to open <%s>: %s\n", fn, strerror(errno)); + goto finish; + } + + for (;;) { + uint32_t len; + char name[PACKAGE_ITEM_NAME_LEN+1]; + FILE *d = NULL; + struct package_item *pi; + + if (!fread(name, sizeof(name)-1, 1, f)) + break; + + name[sizeof(name)-1] = 0; + + if (fread(&len, sizeof(len), 1, f) != 1) { + fprintf(stderr, "Short read while reading length: %s\n", strerror(errno)); + goto finish; + } + + snprintf(path, sizeof(path), "%s/%i", p->base, p->count++); + if (!(d = fopen(path, "w+"))) { + fprintf(stderr, "Failed to open target file: %s\n", strerror(errno)); + goto finish; + } + + if (copy(f, d, len) < 0) { + fprintf(stderr, "Copy failed: %s\n", strerror(errno)); + fclose(d); + unlink(path); + goto finish; + } + + fclose(d); + if (!(pi = item_new(name, path))) { + unlink(path); + fprintf(stderr, "Failed to allocate memory.\n"); + goto finish; + } + + assert(!!p->last == !!p->items); + + if (p->last) { + p->last->next = pi; + p->last = pi; + } else + p->items = p->last = pi; + } + + fclose(f); + } + + return p; + +finish: + if (f) + fclose(f); + + if (p) + package_remove(p); + + return NULL; +} + +int package_save(struct package *p, const char *fn) { + FILE *f, *s = NULL; + int r = 0; + struct package_item *i; + + assert(p && fn); + + if (!(f = fopen(fn, "w+"))) + return -1; + + for (i = p->items; i; i = i->next) { + char name[PACKAGE_ITEM_NAME_LEN+1]; + uint32_t len; + struct stat st; + + if (!i->name || !i->path) + continue; + + if (!(s = fopen(i->path, "r"))) + continue; + + //fprintf(stderr, "Saving %s (%s)...\n", i->name, i->path); + + memset(name, 0, sizeof(name)); + strncpy(name, i->name, sizeof(name)-1); + + if (fwrite(name, sizeof(name)-1, 1, f) != 1) { + r = 1; + break; + } + + if (fstat(fileno(s), &st) < 0) { + fprintf(stderr, "Could not get file size: %s\n", strerror(errno)); + r = 1; + break; + } + + len = st.st_size; + + if (fwrite(&len, sizeof(len), 1, f) != 1) { + r = 1; + break; + } + + if (copy(s, f, len) < 0) { + fprintf(stderr, "Could not copy file to package: %s\n", strerror(errno)); + r = 1; + break; + } + + fclose(s); + s = NULL; + } + + if (s) + fclose(s); + + fclose(f); + + if (r != 0) + unlink(fn); + + return r; +} + +const char *package_get_item(struct package* p, const char *name) { + struct package_item *i; + char path[PATH_MAX]; + assert(p && name); + + for (i = p->items; i; i = i->next) { + if (strncmp(name, i->name, PACKAGE_ITEM_NAME_LEN) == 0) + return i->path; + } + + snprintf(path, sizeof(path), "%s/%i", p->base, p->count++); + + if (!(i = item_new(name, path))) { + unlink(path); + return NULL; + } + + assert(!!p->last == !!p->items); + + if (p->last) { + p->last->next = i; + p->last = i; + } else + p->items = p->last = i; + + return i->path; +} + +void package_remove(struct package *p) { + struct package_item *i, *n; + assert(p); + + for (i = p->items; i; i = n) { + n = i->next; + + if (i->path) + if (unlink(i->path)) + if (errno != ENOENT) + fprintf(stderr, "Failed to remove <%s>: %s\n", i->path, strerror(errno)); + + free(i->path); + free(i->name); + free(i); + } + + if (p->base) { + if (rmdir(p->base)) + fprintf(stderr, "Failed to remove <%s>: %s\n", p->base, strerror(errno)); + + free(p->base); + } + free(p); +} + + +int package_foreach(struct package *p, int (*cb) (struct package *p, char *name, char *path, void *u), void *u) { + struct package_item *i; + assert(p); + + for (i = p->items; i; i = i->next) + if (cb(p, i->name, i->path, u) < 0) + return -1; + + return 0; +} diff --git a/src/package.h b/src/package.h new file mode 100644 index 0000000..62aca3b --- /dev/null +++ b/src/package.h @@ -0,0 +1,14 @@ +#ifndef foopackagehfoo +#define foopackagehfoo + +#define PACKAGE_ITEM_NAME_LEN 32 + +struct package; + +struct package* package_open(const char *fn); +void package_remove(struct package *p); +int package_save(struct package *p, const char *fn); +const char *package_get_item(struct package* p, const char *name); +int package_foreach(struct package *p, int (*cb) (struct package *p, char *name, char *path, void *u), void *u); + +#endif diff --git a/src/syrep.c b/src/syrep.c new file mode 100644 index 0000000..07bbe37 --- /dev/null +++ b/src/syrep.c @@ -0,0 +1,301 @@ +#include <stdint.h> +#include <limits.h> +#include <db.h> +#include <assert.h> +#include <malloc.h> +#include <string.h> +#include <sys/types.h> +#include <dirent.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <unistd.h> +#include <stdlib.h> +#include <errno.h> + +#include "md5util.h" +#include "md5.h" +#include "context.h" +#include "cache.h" +#include "update.h" +#include "list.h" +#include "diff.h" +#include "util.h" +#include "cmdline.h" +#include "syrep.h" +#include "merge.h" +#include "info.h" +#include "history.h" +#include "dump.h" + +struct gengetopt_args_info args; + +int do_diff(void) { + struct syrep_db_context *c1 = NULL, *c2 = NULL; + char *path1 = NULL, *path2 = NULL; + DB *ddb = NULL; + int r = 1; + + if (args.inputs_num != 2) { + fprintf(stderr, "ERROR: Need exactly two repository snapshots for diff command\n"); + goto finish; + } + + if (!(path1 = strdup(get_attached_filename(args.inputs[0], SYREP_SNAPSHOTFILENAME)))) + goto finish; + + if (!(path2 = strdup(get_attached_filename(args.inputs[1], SYREP_SNAPSHOTFILENAME)))) + goto finish; + + if (!strcmp(path1, path2)) { + fprintf(stderr, "ERROR: diff command requires two distinct snapshots as arguments\n"); + goto finish; + } + + if (!(c1 = db_context_open(path1))) + goto finish; + + if (!(c2 = db_context_open(path2))) + goto finish; + + if (!(ddb = make_diff(c1, c2))) + goto finish; + + if (list_diff(c1, c2, ddb) < 0) + goto finish; + + r = 0; + +finish: + if (c1) + db_context_free(c1); + + if (c2) + db_context_free(c2); + + if (ddb) + ddb->close(ddb, 0); + + if (path1) + free(path1); + + if (path2) + free(path2); + + return r; +} + +int do_merge(void) { + struct syrep_db_context *c1 = NULL, *c2 = NULL; + char *path1 = NULL, *path2 = NULL; + int r = 1; + + if (args.inputs_num != 2) { + fprintf(stderr, "ERROR: Need exactly one repository snapshot and one repository for merge command\n"); + goto finish; + } + + if (isdirectory(args.inputs[1]) <= 0) { + fprintf(stderr, "ERROR: %s is not a directory\n", args.inputs[1]); + goto finish; + } + + if (!(path1 = strdup(get_attached_filename(args.inputs[0], SYREP_SNAPSHOTFILENAME)))) + goto finish; + + if (!(path2 = strdup(get_attached_filename(args.inputs[1], SYREP_SNAPSHOTFILENAME)))) + goto finish; + + if (!strcmp(path1, path2)) { + fprintf(stderr, "ERROR: diff command requires two distinct snapshots as arguments\n"); + goto finish; + } + + if (!(c1 = db_context_open(path1))) + goto finish; + + if (!(c2 = db_context_open(path2))) + goto finish; + + if (merge_snapshot(c1, c2, args.inputs[1]) < 0) + goto finish; + + r = 0; + +finish: + if (c1) + db_context_free(c1); + + if (c2) + db_context_free(c2); + + if (path1) + free(path1); + + if (path2) + free(path2); + + return r; +} + +int do_foreach(int (*func) (struct syrep_db_context *c)) { + char *path = NULL; + int r = 1, i; + struct syrep_db_context *c = NULL; + + if (args.inputs_num < 1) + fprintf(stderr, "WARNING: No repository or snapshot to specified!\n"); + + for (i = 0; i < args.inputs_num; i++) { + + if (!(path = strdup(get_attached_filename(args.inputs[i], SYREP_SNAPSHOTFILENAME)))) + goto finish; + + if (!(c = db_context_open(path))) + goto finish; + + if (args.inputs_num > 1) + fprintf(stderr, "*** %s ***\n", path); + + if (func(c) < 0) + goto finish; + + if (args.inputs_num > 1 && i < args.inputs_num-1) + fprintf(stderr, "\n"); + + db_context_free(c); + c = NULL; + + free(path); + path = NULL; + } + + r = 0; + +finish: + if (c) + db_context_free(c); + + if (path) + free(path); + + return r; +} + +int do_update(void) { + char *path = NULL; + int r = 1, i; + struct syrep_db_context *c = NULL; + struct syrep_md_cache *cache = NULL; + + if (args.inputs_num < 1) + fprintf(stderr, "WARNING: No repository to update specified!\n"); + + if (args.snapshot_given && args.inputs_num != 1) { + fprintf(stderr, "ERROR: If a snapshot file is specified only a single directory name is accepted!\n"); + goto finish; + } + + for (i = 0; i < args.inputs_num; i++) { + static char saved_cwd[PATH_MAX]; + + if (isdirectory(args.inputs[i]) <= 0) { + fprintf(stderr, "%s is not a directory\n", args.inputs[i]); + return 1; + } + + if (!(path = strdup(get_attached_filename(args.inputs[i], SYREP_SNAPSHOTFILENAME)))) + goto finish; + + if (!(c = db_context_open(path))) { + fprintf(stderr, "Initializing repository.\n"); + if (!(c = db_context_open(NULL))) + goto finish; + } + + if (!args.no_cache_flag) { + const char *p; + + if (args.cache_given) + cache = md_cache_open(args.cache_arg, args.ro_cache_flag); + else if ((p = get_attached_filename(args.inputs[i], SYREP_MDCACHEFILENAME))) + cache = md_cache_open(p, args.ro_cache_flag); + } + + if (getcwd(saved_cwd, sizeof(saved_cwd)) < 0) { + fprintf(stderr, "getcwd(): %s\n", strerror(errno)); + goto finish; + } + + if (chdir(args.inputs[i]) < 0) { + fprintf(stderr, "Failed to chdir() to directory %s: %s\n", args.inputs[i], strerror(errno)); + goto finish; + } + + if (update(c, cache) < 0) + goto finish; + + if (chdir(saved_cwd) < 0) { + fprintf(stderr, "Failed to chdir() back to directory %s: %s\n", saved_cwd, strerror(errno)); + goto finish; + } + + if (db_context_save(c, path) < 0) + goto finish; + + if (!args.no_purge_flag && cache) + md_cache_vacuum(cache); + + db_context_free(c); + c = NULL; + + free(path); + path = NULL; + + if (cache) { + md_cache_close(cache); + cache = NULL; + } + } + + r = 0; + +finish: + if (c) + db_context_free(c); + + if (path) + free(path); + + if (cache) + md_cache_close(cache); + + return r; +} + +int main(int argc, char *argv[]) { + char *b; + + if ((b = strrchr(argv[0], '/'))) + argv[0] = b+1; + + cmdline_parser(argc, argv, &args); + + if (args.list_flag) + return do_foreach(list); + else if (args.info_flag) + return do_foreach(info); + else if (args.history_flag) + return do_foreach(history); + else if (args.diff_flag) + return do_diff(); + else if (args.update_flag) + return do_update(); + else if (args.merge_flag) + return do_merge(); + else if (args.dump_flag) + return do_foreach(dump); + + cmdline_parser_print_help(); + + return 1; +} diff --git a/src/syrep.ggo b/src/syrep.ggo new file mode 100644 index 0000000..20aa0bf --- /dev/null +++ b/src/syrep.ggo @@ -0,0 +1,27 @@ +purpose "Synchronize Repositories" +package "syrep" +version "0.1" + +option "verbose" - "Enable verbose operation" flag off + +option "list" - "List a repository snapshot" flag off + option "show-deleted" - "list: Show deleted entries of repository snapshot" flag off + option "show-by-md" - "list: Show files by message digests" flag off + option "show-times" - "list: Show first and last seen times" flag off + +option "info" - "Show information about a repository or snapshot" flag off +option "history" - "Show history of a repository or snapshot" flag off +option "dump" - "Show a structure dump of a repository or snapshot" flag off + +option "update" - "Update a repository snapshot" flag off + option "snapshot" S "update: Use the specified snapshot file instead of the one contained in the repository" string no + option "cache" C "update: Use the specified cache file instead of the one contained in the repository" string no + option "no-cache" - "update: Don't use a message digest cache" flag off + option "no-purge" - "update: Don't pruge obsolete entries from cache after update run" flag off + option "ro-cache" - "update: Use read only cache" flag off + option "progress" - "update: Show progress" flag off + +option "diff" - "Show difference between two repositories or snapshots" flag off + +option "merge" - "Merge a snapshot or a repository into a repository" flag off + option "question" - "merge: Ask a question before each action" flag off diff --git a/src/syrep.h b/src/syrep.h new file mode 100644 index 0000000..66d0a4d --- /dev/null +++ b/src/syrep.h @@ -0,0 +1,13 @@ +#ifndef foosyrephfoo +#define foosyrephfoo + +#include "cmdline.h" + +#define SYREP_SNAPSHOTFILENAME "current.syrep" +#define SYREP_MDCACHEFILENAME "md-cache" + +#define SYREP_DIGESTLENGTH 16 + +extern struct gengetopt_args_info args; + +#endif diff --git a/src/update.c b/src/update.c new file mode 100644 index 0000000..2104217 --- /dev/null +++ b/src/update.c @@ -0,0 +1,207 @@ +#include <dirent.h> +#include <sys/stat.h> +#include <string.h> +#include <errno.h> +#include <assert.h> +#include <time.h> + +#include "update.h" +#include "dbstruct.h" +#include "util.h" +#include "dbutil.h" +#include "md5util.h" + +static int dbput(DB* db, const void *k, int klen, const void*d, int dlen, int f) { + DBT key, data; + int ret; + + memset(&key, 0, sizeof(key)); + key.data = (void*) k; + key.size = klen; + + memset(&data, 0, sizeof(data)); + data.data = (void*) d; + data.size = dlen; + + if ((ret = db->put(db, NULL, &key, &data, f)) != 0) { + if (ret != DB_KEYEXIST) { + db->err(db, ret, "db::put()"); + return -1; + } + + return 0; + } + + return 1; +} + +static int write_entry(struct syrep_db_context *c, const struct syrep_name *name, const struct syrep_md *md, const struct syrep_meta *meta) { + struct syrep_id id; + int f; + + assert(c && c->db_id_meta && c->db_md_name && c->db_name_md && c->db_md_lastname && c->db_name_lastmd && name && md && meta); + + /*** Update id_meta ***/ + memset(&id, 0, sizeof(id)); + memcpy(&id.name, name, sizeof(struct syrep_name)); + memcpy(&id.md, md, sizeof(struct syrep_md)); + + if (dbput(c->db_id_meta, &id, sizeof(struct syrep_id), meta, sizeof(struct syrep_meta), 0) < 0) + return -1; + + /*** Update md_name ***/ + if (dbput(c->db_md_name, md, sizeof(struct syrep_md), name, sizeof(struct syrep_name), DB_NODUPDATA) < 0) + return -1; + + /*** Update name_md ***/ + if (dbput(c->db_name_md, name, sizeof(struct syrep_name), md, sizeof(struct syrep_md), DB_NODUPDATA) < 0) + return -1; + + /*** Update md_lastname ***/ + if (dbput(c->db_md_lastname, md, sizeof(struct syrep_md), name, sizeof(struct syrep_name), 0) < 0) + return -1; + + /*** Update name_lastmd ***/ + if ((f = dbput(c->db_name_lastmd, name, sizeof(struct syrep_name), md, sizeof(struct syrep_md), 0)) < 0) + return -1; + + //fprintf(stderr, "Insert: %s %i\n", name->path, f); + + c->modified = 1; + return 0; +} + +static int handle_file(struct syrep_db_context *c, uint32_t version, const char *path, const struct syrep_md *md) { + int r; + struct syrep_meta meta; + struct syrep_name name; + + memset(&name, 0, sizeof(name)); + strncpy(name.path, path, PATH_MAX); + + memset(&meta, 0, sizeof(meta)); + + if ((r = get_meta_by_name_md(c, &name, md, &meta)) < 0) + return -1; + + if (r) { /* File is alread known */ + + if (meta.last_seen != c->version) { /* File was deleted preiously */ + if (args.verbose_flag) + fprintf(stderr, "%s: File reappeared\n", path); + meta.first_seen = meta.last_seen = version; + } else { /* File is not new */ + if (args.verbose_flag) + fprintf(stderr, "%s: File still available\n", path); + meta.last_seen = version; + } + + } else { /* File is new */ + if (args.verbose_flag) + fprintf(stderr, "%s: File is new\n", path); + meta.first_seen = meta.last_seen = version; + } + + return write_entry(c, &name, md, &meta); +} + +static int iterate_dir(struct syrep_db_context *c, struct syrep_md_cache *cache, uint32_t version, const char *root) { + DIR *dir; + struct dirent *de; + char p[PATH_MAX]; + + if (!(dir = opendir(root))) + return -1; + + while ((de = readdir(dir))) { + struct syrep_md md; + struct stat st; + + if (de->d_name[0] == '.') + continue; + + if (!strncmp(de->d_name, ".syrep", 6)) + continue; + + if (args.progress_flag) + rotdash(); + + snprintf(p, sizeof(p), "%s/%s", root, de->d_name); + + normalize_path(p); + + if (stat(p, &st) < 0) { + fprintf(stderr, "stat(%s) failed: %s\n", p, strerror(errno)); + continue; + } + + if (S_ISDIR(st.st_mode)) { + if (iterate_dir(c, cache, version, p) < 0) + fprintf(stderr, "iterate_dir(%s) failed: %s\n", p, strerror(errno)); + } else if (S_ISREG(st.st_mode)) { + if (md_cache_get(cache, p, md.digest) < 0) + continue; + + if ((handle_file(c, version, p, &md)) < 0) { + fprintf(stderr, "handle_file(%s) failed.\n", p); + return -1; + } + } + } + + closedir(dir); + + return 0; +} + +static int new_version(struct syrep_db_context *c, uint32_t v, uint32_t t) { + DBT key, data; + struct syrep_version version; + struct syrep_timestamp timestamp; + int ret; + + assert(c && c->db_version_timestamp); + + memset(&key, 0, sizeof(key)); + memset(&data, 0, sizeof(data)); + memset(&version, 0, sizeof(version)); + memset(×tamp, 0, sizeof(timestamp)); + + version.v = v; + key.data = &version; + key.size = sizeof(version); + + timestamp.t = t; + data.data = ×tamp; + data.size = sizeof(timestamp); + + if ((ret = c->db_version_timestamp->put(c->db_version_timestamp, NULL, &key, &data, 0))) { + c->db_version_timestamp->err(c->db_version_timestamp, ret, "version_timestamp::get"); + return -1; + } + + c->timestamp = t; + c->version = v; + + return 0; +} + +int update(struct syrep_db_context *c, struct syrep_md_cache *cache) { + uint32_t now, version; + + assert(c); + + now = (uint32_t) time(NULL); + version = c->version+1; + + if (iterate_dir(c, cache, version, ".") < 0) + return -1; + + if (new_version(c, version, now) < 0) + return -1; + + if (args.verbose_flag) + fprintf(stderr, "Wrote version %u.\n", c->version); + + return 0; +} diff --git a/src/update.h b/src/update.h new file mode 100644 index 0000000..f176e05 --- /dev/null +++ b/src/update.h @@ -0,0 +1,9 @@ +#ifndef fooupdatehfoo +#define fooupdatehfoo + +#include "context.h" +#include "cache.h" + +int update(struct syrep_db_context *c, struct syrep_md_cache *cache); + +#endif diff --git a/src/util.c b/src/util.c new file mode 100644 index 0000000..91954dd --- /dev/null +++ b/src/util.c @@ -0,0 +1,106 @@ +#include <stdio.h> +#include <assert.h> +#include <stdlib.h> +#include <sys/stat.h> +#include <string.h> +#include <errno.h> +#include <limits.h> +#include <unistd.h> +#include "util.h" + +void statistics(DB *db) { + DB_BTREE_STAT *statp; + int ret; + + assert(db); + + if ((ret = db->stat(db, &statp, 0)) != 0) { + db->err(db, ret, "DB->stat"); + return; + } + + printf("Database contains %lu records\n", (long unsigned) statp->bt_ndata); + free(statp); +} + +char* normalize_path(char *s) { + char *l, *p, *d; + + // deletes /./ and // + + if (*s == '/') + l = p = d = s+1; + else + l = p = d = s; + + for (; *p; p++) { + if (*p == '/') { + + if (l-p == 0) { + l++; + continue; + } + + if (p-l == 1 && *l == '.') { + l += 2; + continue; + } + + while (l <= p) + *(d++) = *(l++); + } + } + + while (l <= p) + *(d++) = *(l++); + + return s; +} + +void rotdash(void) { + static const char dashes[] = /* ".oOo"; */ "|/-\\"; + const static char *d = dashes; + + if (isatty(fileno(stderr))) { + fprintf(stderr, "%c\b", *d); + + d++; + if (!*d) + d = dashes; + } +} + +const char* get_attached_filename(const char *path, const char *fn) { + static char npath[PATH_MAX]; + struct stat st; + + if (stat(path, &st) < 0) { + if (errno == ENOENT) + return path; + + fprintf(stderr, "stat(%s) failed: %s\n", path, strerror(errno)); + return NULL; + } + + if (S_ISREG(st.st_mode)) + return path; + + if (S_ISDIR(st.st_mode)) { + snprintf(npath, sizeof(npath), "%s/.syrep", path); + mkdir(npath, 0777); + snprintf(npath, sizeof(npath), "%s/.syrep/%s", path, fn); + return npath; + } + + fprintf(stderr, "<%s> is not a valid syrep snapshot\n", path); + return NULL; +} + +int isdirectory(const char *path) { + struct stat st; + + if (stat(path, &st) < 0) + return -1; + + return !!S_ISDIR(st.st_mode); +} diff --git a/src/util.h b/src/util.h new file mode 100644 index 0000000..dbdb165 --- /dev/null +++ b/src/util.h @@ -0,0 +1,16 @@ +#ifndef fooutilhfoo +#define fooutilhfoo + +#include <db.h> + +void statistics(DB *db); +char* normalize_path(char *s); +void rotdash(void); +const char* get_attached_filename(const char *path, const char *fn); +int isdirectory(const char *path); + +#ifndef MIN +#define MIN(a,b) ((a)<(b)?(a):(b)) +#endif + +#endif diff --git a/test/Makefile b/test/Makefile new file mode 100644 index 0000000..f5d2ae0 --- /dev/null +++ b/test/Makefile @@ -0,0 +1,20 @@ +SYREP=../syrep + +%: + mkdir -p rep1 rep2 + $(SYREP) --show-deleted --show-times --$@ rep1 rep2 + +all: update + +merge: + @echo "Merging rep1 into rep2" + $(SYREP) --merge rep1 rep2 + @echo "Merging rep2 into rep1" + $(SYREP) --merge rep2 rep1 + +clean: + +mrproper: + rm -rf rep1/.syrep rep2/.syrep + +.PHONY: all merge clean mrproper |