devs/profanity
2
0
Fork 0
mirror of https://git.jabber.space/devs/cproof.git synced 2026-07-18 15:36:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(history): flat-file backend with bidirectional SQLite migration

Browse Source 
A flat-file alternative to the SQLite chatlog backend with runtime
switching, full migration tooling, integrity verification, and a
synthetic load harness. SQLite remains the default; both backends share
one dispatch layer (db_backend_t vtable) so callers don't change.

Storage layout
- Per-contact append-only `flatlog/<account>/<contact>/history.log`
  under XDG_DATA_HOME, one line per message
- Single-line file header with embedded format-version marker
  (FLATFILE_FORMAT_VERSION); reader warns on missing or mismatched
  marker, writer and checker stay in sync via preprocessor
  stringification
- Deterministic key=value metadata (`id`, `aid`, `corrects`, `to`,
  `to_res`, `read`) plus escaped body \u2014 `\|`, `\]`, `\\`, `\n`, `\r`
  literals prevent log injection
- Sparse byte-offset index (FF_INDEX_STEP=500) per contact for
  O(log n) time-range lookups; rebuilt on inode / size / mtime
  change, extended in-place when the file just grew
- Per-contact GHashTable caches for archive_id presence and
  stanza_id \u2192 from_jid mapping (O(1) MAM dedup, O(1) LMC sender
  validation)

Hardening
- Path-traversal protection: JID directory name normalisation
  (`@` \u2192 `_at_`, slashes and `..` rejected at construction); every
  per-contact path is anchored under the account's flatlog/
  directory and validated before open
- Symlink-attack protection: every fopen / open uses O_NOFOLLOW; on
  ELOOP the operation aborts with an error rather than following
- Filesystem permissions: log files created with mode 0600,
  directories with mode 0700; both enforced at creation, verified
  on each open and reported on drift by `/history verify`
- Atomic crash-safe export: write to a temp file via mkstemp (mode
  0600, random suffix, no name collisions between concurrent
  exports), fsync, then rename \u2014 partial state never replaces the
  live file
- Concurrency: advisory flock(LOCK_EX) held for the duration of
  every write, including append from live messages and full rewrite
  from export, so two profanity processes can't interleave bytes
  on the same log
- DoS / abuse guards:
    * FF_MAX_LINE_LEN = 10 MB \u2014 lines longer than this are rejected
      at read with a warning; the parser will not allocate
      unbounded memory for a single record
    * FF_MAX_LMC_DEPTH = 100 \u2014 `corrects:` chain walk stops at this
      depth and emits a warning, preventing a malicious correction
      cycle from spinning the apply pass
    * FF_VERSION_SCAN_MAX = 16 \u2014 header version probe never reads
      past 16 leading comment lines, even on garbage input
    * Empty / inverted byte-range early-return in page-up read path
      so a malformed time filter cannot cause an unbounded scan
    * Zero-entry index guard so a file whose every line failed to
      parse cannot cause a NULL deref on later page-up
- LMC sender validation: an incoming correction whose sender does
  not match the original message's sender is rejected at write
  time and surfaced via cons_show_error; a cycle in the apply pass
  is broken via a visited-set
- jid_create_from_bare_and_resource treats NULL, empty string, and
  the literal "(null)" as no resource and returns a bare jid;
  similar normalisation for barejid eliminates the legacy
  "user@host/(null)" artefact that leaked into stored fulljids
  whenever g_strdup_printf("%s", NULL) ran inside create_fulljid

Commands
- `/history switch sqlite|flatfile` \u2014 runtime backend swap, closes
  the old backend and opens the new one without reconnecting
- `/history export [<jid>]` \u2014 SQLite -> flat-file, merging with any
  existing flatlog (dedup keyed on a SHA-256 hash mixing stanza_id,
  timestamp, from_jid, body \u2014 robust against id reuse by older
  clients)
- `/history import [<jid>]` \u2014 flat-file -> SQLite, same merge
  semantics, runs inside a single SQLite transaction with rollback
  on per-contact failure
- `/history verify [<jid>]` \u2014 integrity check; emits a structured
  list of issues (ERROR / WARNING / INFO) per file:
    * file-level: missing log, wrong permissions (\u2260 0600), UTF-8
      BOM present, CRLF line endings, empty file
    * line-level: invalid UTF-8 (with byte offset), embedded
      control characters, unparsable lines, timestamps out of
      order, duplicate `id:` and `aid:` (tracked separately so a
      stanza/archive id collision isn't double-reported)
    * cross-line: broken `corrects:` references whose target id is
      not present in the file
- `/history backend` \u2014 show currently active backend
- Active backend indicator `[sqlite]` / `[flatfile]` in the status
  bar next to the JID
- Roster-JID autocomplete for verify / export / import
- export and import open a SQLite handle on demand when the
  flatfile backend is currently active, so migration works
  regardless of which backend is live

Tests
- Unit: database_export (parser round-trip, escape/unescape, dedup
  key stability, JID normalisation), database_stress (14 cases
  exercising rapid writes, large messages, deep LMC chains, MAM
  dedup, concurrent contacts)
- Functional: history persistence across reconnects, export /
  import round-trip with content equality, MUC migration,
  timestamp normalisation across timezones
- Bench harness P1\u2013P5 (synthetic load: bulk insert, time-range
  read, page-up scroll, MAM ingest, mixed workload) and failure
  modes F1\u2013F17 (page-up cursor and forward-iteration symmetry,
  oversized lines, MAM dedup, LMC depth and cycles, BOM/CRLF,
  missing log, empty file, mtime+inode flip, broken corrects, etc.)
- All bench tests integrate with the existing make targets and
  emit CSV rows for baseline comparison

Author: jabber.developer2 <jabber.developer2@jabber.space>
Reviewed-by: jabber.developer <jabber.developer@jabber.space>
This commit is contained in:
Jabber Developer
2026-05-05 19:26:07 +00:00
parent 0feacbc9da
commit 3f36c303c2
50 changed files with 13811 additions and 793 deletions
Download Patch File Download Diff File Expand all files Collapse all files

996
src/database_sqlite.c Normal file
View File

@@ -0,0 +1,996 @@
/*
* database_sqlite.c
* vim: expandtab:ts=4:sts=4:sw=4
*
* Copyright (C) 2020 - 2025 Michael Vetter <jubalh@iodoru.org>
*
* This file is part of Profanity.
*
* Profanity 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 3 of the License, or
* (at your option) any later version.
*
* Profanity 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 Profanity. If not, see <https://www.gnu.org/licenses/>.
*
* In addition, as a special exception, the copyright holders give permission to
* link the code of portions of this program with the OpenSSL library under
* certain conditions as described in each individual source file, and
* distribute linked combinations including the two.
*
* You must obey the GNU General Public License in all respects for all of the
* code used other than OpenSSL. If you modify file(s) with this exception, you
* may extend this exception to your version of the file(s), but you are not
* obligated to do so. If you do not wish to do so, delete this exception
* statement from your version. If you delete this exception statement from all
* source files in the program, then also delete it here.
*
*/
#include "config.h"
#include <sys/stat.h>
#include <sys/statvfs.h>
#include <sqlite3.h>
#include <glib.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include "log.h"
#include "common.h"
#include "config/files.h"
#include "database.h"
#include "config/preferences.h"
#include "ui/ui.h"
#include "xmpp/xmpp.h"
#include "xmpp/message.h"
static sqlite3* g_chatlog_database;
static void _add_to_db(ProfMessage* message, const char* type, const Jid* const from_jid, const Jid* const to_jid);
static char* _get_db_filename(ProfAccount* account);
static prof_msg_type_t _get_message_type_type(const char* const type);
static prof_enc_t _get_message_enc_type(const char* const encstr);
static int _get_db_version(void);
static gboolean _migrate_to_v2(void);
static gboolean _check_available_space_for_db_migration(char* path_to_db);
static const int latest_version = 2;
gboolean
db_sqlite_is_open(void)
{
return g_chatlog_database != NULL;
}
// Helper: close DB handle (if any), warn on busy, and shutdown SQLite
static void
_db_teardown(const char* ctx)
{
if (g_chatlog_database) {
int rc = sqlite3_close_v2(g_chatlog_database);
if (rc != SQLITE_OK) {
log_warning("sqlite3_close_v2 in %s returned %d; database may still have active statements.",
ctx ? ctx : "db_teardown", rc);
}
g_chatlog_database = NULL;
}
sqlite3_shutdown();
}
// Helper: prepare a statement and log a contextual error on failure
static gboolean
_db_prepare_ctx(const char* query, sqlite3_stmt** stmt, const char* ctx)
{
int rc = sqlite3_prepare_v2(g_chatlog_database, query, -1, stmt, NULL);
if (rc != SQLITE_OK) {
log_error("SQLite error in %s: (error code: %d) %s",
ctx ? ctx : "sqlite3_prepare_v2",
rc,
sqlite3_errmsg(g_chatlog_database));
return FALSE;
}
return TRUE;
}
static char*
_db_strdup(const char* str)
{
return str ? strdup(str) : NULL;
}
#define auto_sqlite __attribute__((__cleanup__(auto_free_sqlite)))
static void
auto_free_sqlite(gchar** str)
{
if (str == NULL)
return;
sqlite3_free(*str);
}
static char*
_get_db_filename(ProfAccount* account)
{
return files_file_in_account_data_path(DIR_DATABASE, account->jid, "chatlog.db");
}
static gboolean
_sqlite_init(ProfAccount* account)
{
int ret = sqlite3_initialize();
if (ret != SQLITE_OK) {
log_error("Error initializing SQLite database: %d", ret);
return FALSE;
}
auto_char char* filename = _get_db_filename(account);
if (!filename) {
log_error("Error initializing SQLite database: could not derive chatlog.db path for account '%s'.",
account && account->jid ? account->jid : "(unknown)");
sqlite3_shutdown();
return FALSE;
}
ret = sqlite3_open(filename, &g_chatlog_database);
if (ret != SQLITE_OK) {
const char* err_msg = g_chatlog_database ? sqlite3_errmsg(g_chatlog_database) : "(no handle)";
log_error("Error opening SQLite database: %s", err_msg);
_db_teardown("_sqlite_init(open)");
return FALSE;
}
char* err_msg = NULL;
int db_version = _get_db_version();
if (db_version == latest_version) {
return TRUE;
}
// ChatLogs schema overview:
// id AUTOINCREMENT primary key. Used internally as the
// anchor for LMC (Last Message Correction) chains.
// from_jid/to_jid Bare JIDs (NOT NULL). Used for window resolution.
// from_resource Resource of the sender (NULLable for legacy rows).
// to_resource Resource of the recipient (NULLable).
// message Plaintext after decryption / format normalisation.
// timestamp ISO-8601 (UTC). Indexed for range queries.
// type "chat" | "muc" | "mucpm" (mirrors prof_msg_type_t).
// stanza_id XEP-0359 unique-and-stable id, used for dedup +
// LMC sender lookup.
// archive_id MAM (XEP-0313) archive id; dedupes rebroadcast.
// encryption "none" | "omemo" | "otr" | "pgp" | "ox"
// (mirrors prof_enc_t).
// marked_read 0/1 — for unread-message badge bookkeeping.
// replace_id XEP-0308 message-correction stanza-id of the
// original message this row replaces.
// replaces_db_id Local FK back-link: id of the row this row
// corrects. Set on insert when replace_id resolves.
// replaced_by_db_id Inverse FK: id of the most recent correction.
// Maintained by the AFTER INSERT trigger below so
// readers can follow the chain forward in O(1).
const char* query = "CREATE TABLE IF NOT EXISTS `ChatLogs` ("
"`id` INTEGER PRIMARY KEY AUTOINCREMENT, "
"`from_jid` TEXT NOT NULL, "
"`to_jid` TEXT NOT NULL, "
"`from_resource` TEXT, "
"`to_resource` TEXT, "
"`message` TEXT, "
"`timestamp` TEXT, "
"`type` TEXT, "
"`stanza_id` TEXT, "
"`archive_id` TEXT, "
"`encryption` TEXT, "
"`marked_read` INTEGER, "
"`replace_id` TEXT, "
"`replaces_db_id` INTEGER, "
"`replaced_by_db_id` INTEGER)";
if (SQLITE_OK != sqlite3_exec(g_chatlog_database, query, NULL, 0, &err_msg)) {
goto out;
}
query = "CREATE TRIGGER IF NOT EXISTS update_corrected_message "
"AFTER INSERT ON ChatLogs "
"FOR EACH ROW "
"WHEN NEW.replaces_db_id IS NOT NULL "
"BEGIN "
"UPDATE ChatLogs "
"SET replaced_by_db_id = NEW.id "
"WHERE id = NEW.replaces_db_id; "
"END;";
if (SQLITE_OK != sqlite3_exec(g_chatlog_database, query, NULL, 0, &err_msg)) {
log_error("Unable to add `update_corrected_message` trigger.");
goto out;
}
query = "CREATE INDEX IF NOT EXISTS ChatLogs_timestamp_IDX ON `ChatLogs` (`timestamp`)";
if (SQLITE_OK != sqlite3_exec(g_chatlog_database, query, NULL, 0, &err_msg)) {
log_error("Unable to create index for timestamp.");
goto out;
}
query = "CREATE INDEX IF NOT EXISTS ChatLogs_to_from_jid_IDX ON `ChatLogs` (`to_jid`, `from_jid`)";
if (SQLITE_OK != sqlite3_exec(g_chatlog_database, query, NULL, 0, &err_msg)) {
log_error("Unable to create index for to_jid.");
goto out;
}
query = "CREATE TABLE IF NOT EXISTS `DbVersion` (`dv_id` INTEGER PRIMARY KEY, `version` INTEGER UNIQUE)";
if (SQLITE_OK != sqlite3_exec(g_chatlog_database, query, NULL, 0, &err_msg)) {
goto out;
}
if (db_version == -1) {
query = "INSERT OR IGNORE INTO `DbVersion` (`version`) VALUES ('2')";
if (SQLITE_OK != sqlite3_exec(g_chatlog_database, query, NULL, 0, &err_msg)) {
goto out;
}
db_version = _get_db_version();
}
if (db_version == -1) {
cons_show_error("DB Initialization Error: Unable to check DB version.");
goto out;
}
if (db_version < latest_version) {
cons_show("Migrating database schema. This operation may take a while...");
if (db_version < 2 && (!_check_available_space_for_db_migration(filename) || !_migrate_to_v2())) {
cons_show_error("Database Initialization Error: Unable to migrate database to version 2. Please, check error logs for details.");
goto out;
}
cons_show("Database schema migration was successful.");
}
log_debug("Initialized SQLite database: %s", filename);
return TRUE;
out:
if (err_msg) {
log_error("SQLite error in _sqlite_init(): %s", err_msg);
sqlite3_free(err_msg);
} else {
log_error("Unknown SQLite error in _sqlite_init().");
}
_db_teardown("_sqlite_init(out)");
return FALSE;
}
static void
_sqlite_close(void)
{
log_debug("_sqlite_close() called");
_db_teardown("_sqlite_close");
}
static void
_sqlite_add_incoming(ProfMessage* message)
{
if (message->to_jid) {
_add_to_db(message, NULL, message->from_jid, message->to_jid);
} else {
_add_to_db(message, NULL, message->from_jid, connection_get_jid());
}
}
static void
_log_database_add_outgoing(const char* type, const char* const id, const char* const barejid, const char* const message, const char* const replace_id, prof_enc_t enc)
{
ProfMessage* msg = message_init();
msg->id = _db_strdup(id);
msg->from_jid = jid_create(barejid);
msg->plain = _db_strdup(message);
msg->replace_id = _db_strdup(replace_id);
msg->timestamp = g_date_time_new_now_local();
msg->enc = enc;
_add_to_db(msg, type, connection_get_jid(), msg->from_jid);
message_free(msg);
}
static void
_sqlite_add_outgoing_chat(const char* const id, const char* const barejid, const char* const message, const char* const replace_id, prof_enc_t enc)
{
_log_database_add_outgoing("chat", id, barejid, message, replace_id, enc);
}
static void
_sqlite_add_outgoing_muc(const char* const id, const char* const barejid, const char* const message, const char* const replace_id, prof_enc_t enc)
{
_log_database_add_outgoing("muc", id, barejid, message, replace_id, enc);
}
static void
_sqlite_add_outgoing_muc_pm(const char* const id, const char* const barejid, const char* const message, const char* const replace_id, prof_enc_t enc)
{
_log_database_add_outgoing("mucpm", id, barejid, message, replace_id, enc);
}
static ProfMessage*
_sqlite_get_limits_info(const gchar* const contact_barejid, gboolean is_last)
{
sqlite3_stmt* stmt = NULL;
const Jid* myjid = connection_get_jid();
ProfMessage* msg = message_init();
if (!myjid || !myjid->str) {
if (is_last) {
msg->timestamp = g_date_time_new_now_utc();
}
return msg;
}
const char* order = is_last ? "DESC" : "ASC";
auto_sqlite char* query = sqlite3_mprintf("SELECT `archive_id`, `timestamp` FROM `ChatLogs` WHERE "
"(`from_jid` = %Q AND `to_jid` = %Q) OR "
"(`from_jid` = %Q AND `to_jid` = %Q) "
"ORDER BY `timestamp` %s LIMIT 1;",
contact_barejid, myjid->barejid, myjid->barejid, contact_barejid, order);
if (!query) {
log_error("Could not allocate memory for SQL query in _sqlite_get_limits_info()");
if (is_last) {
msg->timestamp = g_date_time_new_now_utc();
}
return msg;
}
if (!_db_prepare_ctx(query, &stmt, "_sqlite_get_limits_info()")) {
if (is_last) {
msg->timestamp = g_date_time_new_now_utc();
}
return msg;
}
if (sqlite3_step(stmt) == SQLITE_ROW) {
char* archive_id = (char*)sqlite3_column_text(stmt, 0);
char* date = (char*)sqlite3_column_text(stmt, 1);
msg->stanzaid = _db_strdup(archive_id);
msg->timestamp = g_date_time_new_from_iso8601(date, NULL);
}
sqlite3_finalize(stmt);
if (!msg->timestamp && is_last) {
msg->timestamp = g_date_time_new_now_utc();
}
return msg;
}
static db_history_result_t
_sqlite_get_previous_chat(const gchar* const contact_barejid, const gchar* start_time, const gchar* end_time, gboolean from_start, gboolean flip, GSList** result)
{
if (!g_chatlog_database) {
log_warning("_sqlite_get_previous_chat() called but db is not initialized");
return DB_RESPONSE_ERROR;
}
sqlite3_stmt* stmt = NULL;
const Jid* myjid = connection_get_jid();
if (!myjid->str) {
log_warning("_sqlite_get_previous_chat() called but no connection detected.");
return DB_RESPONSE_ERROR;
}
const gchar* sort1 = from_start ? "ASC" : "DESC";
const gchar* sort2 = !flip ? "ASC" : "DESC";
GDateTime* now = g_date_time_new_now_local();
auto_gchar gchar* end_date_fmt = end_time ? g_strdup(end_time) : g_date_time_format_iso8601(now);
auto_sqlite gchar* query = sqlite3_mprintf("SELECT * FROM ("
"SELECT COALESCE(B.`message`, A.`message`) AS message, "
"A.`timestamp`, A.`from_jid`, A.`from_resource`, A.`to_jid`, A.`to_resource`, A.`type`, A.`encryption`, A.`stanza_id` FROM `ChatLogs` AS A "
"LEFT JOIN `ChatLogs` AS B ON (A.`replaced_by_db_id` = B.`id` AND A.`from_jid` = B.`from_jid`) "
"WHERE (A.`replaces_db_id` IS NULL) "
"AND ((A.`from_jid` = %Q AND A.`to_jid` = %Q) OR (A.`from_jid` = %Q AND A.`to_jid` = %Q)) "
"AND A.`timestamp` < %Q "
"AND (%Q IS NULL OR A.`timestamp` > %Q) "
"ORDER BY A.`timestamp` %s LIMIT %d) "
"ORDER BY `timestamp` %s;",
contact_barejid, myjid->barejid, myjid->barejid, contact_barejid, end_date_fmt, start_time, start_time, sort1, MESSAGES_TO_RETRIEVE, sort2);
g_date_time_unref(now);
if (!query) {
log_error("Could not allocate memory.");
return DB_RESPONSE_ERROR;
}
if (!_db_prepare_ctx(query, &stmt, "_sqlite_get_previous_chat()")) {
return DB_RESPONSE_ERROR;
}
while (sqlite3_step(stmt) == SQLITE_ROW) {
char* message = (char*)sqlite3_column_text(stmt, 0);
char* date = (char*)sqlite3_column_text(stmt, 1);
char* from_jid = (char*)sqlite3_column_text(stmt, 2);
char* from_resource = (char*)sqlite3_column_text(stmt, 3);
char* to_jid = (char*)sqlite3_column_text(stmt, 4);
char* to_resource = (char*)sqlite3_column_text(stmt, 5);
char* type = (char*)sqlite3_column_text(stmt, 6);
char* encryption = (char*)sqlite3_column_text(stmt, 7);
char* id = (char*)sqlite3_column_text(stmt, 8);
ProfMessage* msg = message_init();
msg->id = id ? strdup(id) : NULL;
msg->from_jid = jid_create_from_bare_and_resource(from_jid, from_resource);
msg->to_jid = jid_create_from_bare_and_resource(to_jid, to_resource);
msg->plain = strdup(message ?: "");
msg->timestamp = g_date_time_new_from_iso8601(date, NULL);
msg->type = _get_message_type_type(type);
msg->enc = _get_message_enc_type(encryption);
*result = g_slist_append(*result, msg);
}
sqlite3_finalize(stmt);
return g_slist_length(*result) != 0 ? DB_RESPONSE_SUCCESS : DB_RESPONSE_EMPTY;
}
static GSList*
_sqlite_verify_integrity(const gchar* const contact_barejid)
{
GSList* issues = NULL;
if (!g_chatlog_database) {
integrity_issue_t* issue = g_malloc0(sizeof(integrity_issue_t));
issue->level = INTEGRITY_ERROR;
issue->file = g_strdup("chatlog.db");
issue->line = 0;
issue->message = g_strdup("Database not initialized");
issues = g_slist_append(issues, issue);
return issues;
}
// PRAGMA integrity_check
sqlite3_stmt* stmt = NULL;
if (_db_prepare_ctx("PRAGMA integrity_check", &stmt, "_sqlite_verify_integrity()")) {
while (sqlite3_step(stmt) == SQLITE_ROW) {
const char* result = (const char*)sqlite3_column_text(stmt, 0);
if (g_strcmp0(result, "ok") != 0) {
integrity_issue_t* issue = g_malloc0(sizeof(integrity_issue_t));
issue->level = INTEGRITY_ERROR;
issue->file = g_strdup("chatlog.db");
issue->line = 0;
issue->message = g_strdup_printf("SQLite integrity check: %s", result);
issues = g_slist_append(issues, issue);
}
}
sqlite3_finalize(stmt);
}
// Check timestamp ordering for a specific contact or all
const Jid* myjid = connection_get_jid();
if (myjid && myjid->barejid) {
auto_sqlite char* query = NULL;
if (contact_barejid) {
query = sqlite3_mprintf(
"SELECT A.`id`, A.`timestamp`, B.`id`, B.`timestamp` FROM `ChatLogs` A "
"JOIN `ChatLogs` B ON B.`id` = A.`id` + 1 "
"WHERE A.`timestamp` > B.`timestamp` "
"AND ((A.`from_jid` = %Q AND A.`to_jid` = %Q) OR (A.`from_jid` = %Q AND A.`to_jid` = %Q)) "
"LIMIT 50",
contact_barejid, myjid->barejid, myjid->barejid, contact_barejid);
} else {
query = sqlite3_mprintf(
"SELECT A.`id`, A.`timestamp`, B.`id`, B.`timestamp` FROM `ChatLogs` A "
"JOIN `ChatLogs` B ON B.`id` = A.`id` + 1 "
"WHERE A.`timestamp` > B.`timestamp` "
"LIMIT 50");
}
if (query && _db_prepare_ctx(query, &stmt, "_sqlite_verify_integrity(timestamp_order)")) {
while (sqlite3_step(stmt) == SQLITE_ROW) {
int id_a = sqlite3_column_int(stmt, 0);
const char* ts_a = (const char*)sqlite3_column_text(stmt, 1);
int id_b = sqlite3_column_int(stmt, 2);
const char* ts_b = (const char*)sqlite3_column_text(stmt, 3);
integrity_issue_t* issue = g_malloc0(sizeof(integrity_issue_t));
issue->level = INTEGRITY_WARNING;
issue->file = g_strdup("chatlog.db");
issue->line = id_a;
issue->message = g_strdup_printf("Timestamp out of order: row %d (%s) > row %d (%s)",
id_a, ts_a ? ts_a : "NULL", id_b, ts_b ? ts_b : "NULL");
issues = g_slist_append(issues, issue);
}
sqlite3_finalize(stmt);
}
// Check broken LMC references
auto_sqlite char* lmc_query = sqlite3_mprintf(
"SELECT A.`id`, A.`replaces_db_id` FROM `ChatLogs` A "
"WHERE A.`replaces_db_id` IS NOT NULL "
"AND NOT EXISTS (SELECT 1 FROM `ChatLogs` B WHERE B.`id` = A.`replaces_db_id`) "
"LIMIT 50");
if (lmc_query && _db_prepare_ctx(lmc_query, &stmt, "_sqlite_verify_integrity(lmc_check)")) {
while (sqlite3_step(stmt) == SQLITE_ROW) {
int id = sqlite3_column_int(stmt, 0);
int replaces_id = sqlite3_column_int(stmt, 1);
integrity_issue_t* issue = g_malloc0(sizeof(integrity_issue_t));
issue->level = INTEGRITY_ERROR;
issue->file = g_strdup("chatlog.db");
issue->line = id;
issue->message = g_strdup_printf("Broken LMC reference: row %d references non-existent row %d",
id, replaces_id);
issues = g_slist_append(issues, issue);
}
sqlite3_finalize(stmt);
}
}
return issues;
}
// --- Type conversion helpers ---
static const char*
_get_message_type_str(prof_msg_type_t type)
{
switch (type) {
case PROF_MSG_TYPE_CHAT:
return "chat";
case PROF_MSG_TYPE_MUC:
return "muc";
case PROF_MSG_TYPE_MUCPM:
return "mucpm";
case PROF_MSG_TYPE_UNINITIALIZED:
return NULL;
}
return NULL;
}
static prof_msg_type_t
_get_message_type_type(const char* const type)
{
if (g_strcmp0(type, "chat") == 0) {
return PROF_MSG_TYPE_CHAT;
} else if (g_strcmp0(type, "muc") == 0) {
return PROF_MSG_TYPE_MUC;
} else if (g_strcmp0(type, "mucpm") == 0) {
return PROF_MSG_TYPE_MUCPM;
} else {
return PROF_MSG_TYPE_UNINITIALIZED;
}
}
static const char*
_get_message_enc_str(prof_enc_t enc)
{
switch (enc) {
case PROF_MSG_ENC_OX:
return "ox";
case PROF_MSG_ENC_PGP:
return "pgp";
case PROF_MSG_ENC_OTR:
return "otr";
case PROF_MSG_ENC_OMEMO:
return "omemo";
case PROF_MSG_ENC_NONE:
return "none";
}
return "none";
}
static prof_enc_t
_get_message_enc_type(const char* const encstr)
{
if (g_strcmp0(encstr, "ox") == 0) {
return PROF_MSG_ENC_OX;
} else if (g_strcmp0(encstr, "pgp") == 0) {
return PROF_MSG_ENC_PGP;
} else if (g_strcmp0(encstr, "otr") == 0) {
return PROF_MSG_ENC_OTR;
} else if (g_strcmp0(encstr, "omemo") == 0) {
return PROF_MSG_ENC_OMEMO;
}
return PROF_MSG_ENC_NONE;
}
// --- Core write logic ---
static void
_add_to_db(ProfMessage* message, const char* type, const Jid* const from_jid, const Jid* const to_jid)
{
auto_gchar gchar* pref_dblog = prefs_get_string(PREF_DBLOG);
sqlite_int64 original_message_id = -1;
if (g_strcmp0(pref_dblog, "off") == 0) {
return;
} else if (g_strcmp0(pref_dblog, "redact") == 0) {
if (message->plain) {
free(message->plain);
}
message->plain = strdup("[REDACTED]");
}
if (!g_chatlog_database) {
log_debug("_add_to_db() called but db is not initialized");
return;
}
char* err_msg;
auto_gchar gchar* date_fmt = NULL;
if (message->timestamp) {
date_fmt = g_date_time_format_iso8601(message->timestamp);
} else {
GDateTime* dt = g_date_time_new_now_local();
date_fmt = g_date_time_format_iso8601(dt);
g_date_time_unref(dt);
}
const char* enc = _get_message_enc_str(message->enc);
if (!type) {
type = (char*)_get_message_type_str(message->type);
}
// Apply LMC and check its validity (XEP-0308)
if (message->replace_id) {
auto_sqlite char* replace_check_query = sqlite3_mprintf("SELECT `id`, `from_jid`, `replaces_db_id` FROM `ChatLogs` WHERE `stanza_id` = %Q ORDER BY `timestamp` DESC LIMIT 1",
message->replace_id);
if (!replace_check_query) {
log_error("Could not allocate memory for SQL replace query in _add_to_db()");
return;
}
sqlite3_stmt* lmc_stmt = NULL;
if (!_db_prepare_ctx(replace_check_query, &lmc_stmt, "_add_to_db(replace_check)")) {
return;
}
if (sqlite3_step(lmc_stmt) == SQLITE_ROW) {
original_message_id = sqlite3_column_int64(lmc_stmt, 0);
const char* from_jid_orig = (const char*)sqlite3_column_text(lmc_stmt, 1);
sqlite_int64 tmp = sqlite3_column_int64(lmc_stmt, 2);
original_message_id = tmp ? tmp : original_message_id;
if (g_strcmp0(from_jid_orig, from_jid->barejid) != 0) {
log_error("Mismatch in sender JIDs when trying to do LMC. Corrected message sender: %s. Original message sender: %s. Replace-ID: %s. Message: %s", from_jid->barejid, from_jid_orig, message->replace_id, message->plain);
cons_show_error("%s sent a message correction with mismatched sender. See log for details.", from_jid->barejid);
sqlite3_finalize(lmc_stmt);
return;
}
} else {
log_warning("Got LMC message that does not have original message counterpart in the database from %s", message->from_jid->fulljid);
}
sqlite3_finalize(lmc_stmt);
}
if (message->stanzaid && !message->is_mam) {
auto_sqlite char* duplicate_check_query = sqlite3_mprintf("SELECT 1 FROM `ChatLogs` WHERE (`archive_id` = %Q)",
message->stanzaid);
if (!duplicate_check_query) {
log_error("Could not allocate memory for SQL duplicate query in _add_to_db()");
return;
}
sqlite3_stmt* stmt;
if (_db_prepare_ctx(duplicate_check_query, &stmt, "_add_to_db(duplicate_check)")) {
if (sqlite3_step(stmt) == SQLITE_ROW) {
log_error("Duplicate stanza-id found for the message. stanza_id: %s; archive_id: %s; sender: %s; content: %s", message->id, message->stanzaid, from_jid->barejid, message->plain);
cons_show_error("Got a message with duplicate (server-generated) stanza-id from %s.", from_jid->fulljid);
}
sqlite3_finalize(stmt);
}
}
auto_sqlite char* orig_message_id = original_message_id == -1 ? NULL : sqlite3_mprintf("%d", original_message_id);
auto_sqlite char* query = sqlite3_mprintf("INSERT INTO `ChatLogs` "
"(`from_jid`, `from_resource`, `to_jid`, `to_resource`, "
"`message`, `timestamp`, `stanza_id`, `archive_id`, "
"`replaces_db_id`, `replace_id`, `type`, `encryption`) "
"VALUES (%Q, %Q, %Q, %Q, %Q, %Q, %Q, %Q, %Q, %Q, %Q, %Q)",
from_jid->barejid,
from_jid->resourcepart,
to_jid->barejid,
to_jid->resourcepart,
message->plain,
date_fmt,
message->id,
message->stanzaid,
orig_message_id,
message->replace_id,
type,
enc);
if (!query) {
log_error("Could not allocate memory for SQL insert query in _add_to_db()");
return;
}
log_debug("Writing to DB. Query: %s", query);
if (SQLITE_OK != sqlite3_exec(g_chatlog_database, query, NULL, 0, &err_msg)) {
if (err_msg) {
log_error("SQLite error in _add_to_db(): %s", err_msg);
sqlite3_free(err_msg);
} else {
log_error("Unknown SQLite error in _add_to_db().");
}
} else {
int inserted_rows_count = sqlite3_changes(g_chatlog_database);
if (inserted_rows_count < 1) {
log_error("SQLite did not insert message (rows: %d, id: %s, content: %s)", inserted_rows_count, message->id, message->plain);
}
}
}
// --- DB version and migration ---
static int
_get_db_version(void)
{
int current_version = -1;
const char* query = "SELECT `version` FROM `DbVersion` LIMIT 1";
sqlite3_stmt* statement;
if (_db_prepare_ctx(query, &statement, "_get_db_version()")) {
if (sqlite3_step(statement) == SQLITE_ROW) {
current_version = sqlite3_column_int(statement, 0);
}
sqlite3_finalize(statement);
}
return current_version;
}
static gboolean
_migrate_to_v2(void)
{
char* err_msg = NULL;
const char* sql_statements[] = {
"BEGIN TRANSACTION",
"ALTER TABLE `ChatLogs` ADD COLUMN `replaces_db_id` INTEGER;",
"ALTER TABLE `ChatLogs` ADD COLUMN `replaced_by_db_id` INTEGER;",
"UPDATE `ChatLogs` AS A "
"SET `replaces_db_id` = B.`id` "
"FROM `ChatLogs` AS B "
"WHERE A.`replace_id` IS NOT NULL AND A.`replace_id` != '' "
"AND A.`replace_id` = B.`stanza_id` "
"AND A.`from_jid` = B.`from_jid` AND A.`to_jid` = B.`to_jid`;",
"UPDATE `ChatLogs` AS A "
"SET `replaced_by_db_id` = B.`id` "
"FROM `ChatLogs` AS B "
"WHERE (A.`replace_id` IS NULL OR A.`replace_id` = '') "
"AND A.`id` = B.`replaces_db_id` "
"AND A.`from_jid` = B.`from_jid`;",
"UPDATE ChatLogs SET "
"from_resource = COALESCE(NULLIF(from_resource, ''), NULL), "
"to_resource = COALESCE(NULLIF(to_resource, ''), NULL), "
"message = COALESCE(NULLIF(message, ''), NULL), "
"timestamp = COALESCE(NULLIF(timestamp, ''), NULL), "
"stanza_id = COALESCE(NULLIF(stanza_id, ''), NULL), "
"archive_id = COALESCE(NULLIF(archive_id, ''), NULL), "
"replace_id = COALESCE(NULLIF(replace_id, ''), NULL), "
"type = COALESCE(NULLIF(type, ''), NULL), "
"encryption = COALESCE(NULLIF(encryption, ''), NULL);",
"UPDATE `DbVersion` SET `version` = 2;",
"END TRANSACTION"
};
int statements_count = sizeof(sql_statements) / sizeof(sql_statements[0]);
for (int i = 0; i < statements_count; i++) {
if (SQLITE_OK != sqlite3_exec(g_chatlog_database, sql_statements[i], NULL, 0, &err_msg)) {
log_error("SQLite error in _migrate_to_v2() on statement %d: %s", i, err_msg);
if (err_msg) {
sqlite3_free(err_msg);
err_msg = NULL;
}
goto cleanup;
}
}
return TRUE;
cleanup:
if (SQLITE_OK != sqlite3_exec(g_chatlog_database, "ROLLBACK;", NULL, 0, &err_msg)) {
log_error("[DB Migration] Unable to ROLLBACK: %s", err_msg);
if (err_msg) {
sqlite3_free(err_msg);
}
}
return FALSE;
}
static gboolean
_check_available_space_for_db_migration(char* path_to_db)
{
struct stat file_stat;
struct statvfs fs_stat;
if (statvfs(path_to_db, &fs_stat) == 0 && stat(path_to_db, &file_stat) == 0) {
unsigned long long file_size = file_stat.st_size / 1024;
unsigned long long available_space_kb = fs_stat.f_frsize * fs_stat.f_bavail / 1024;
log_debug("_check_available_space_for_db_migration(): Available space on disk: %llu KB; DB size: %llu KB", available_space_kb, file_size);
return (available_space_kb >= (file_size + (file_size * 10 / 4)));
} else {
log_error("Error checking available space.");
return FALSE;
}
}
// --- Backend vtable ---
static db_backend_t sqlite_backend = {
.name = "sqlite",
.init = _sqlite_init,
.close = _sqlite_close,
.add_incoming = _sqlite_add_incoming,
.add_outgoing_chat = _sqlite_add_outgoing_chat,
.add_outgoing_muc = _sqlite_add_outgoing_muc,
.add_outgoing_muc_pm = _sqlite_add_outgoing_muc_pm,
.get_previous_chat = _sqlite_get_previous_chat,
.get_limits_info = _sqlite_get_limits_info,
.verify_integrity = _sqlite_verify_integrity,
};
db_backend_t*
db_backend_sqlite(void)
{
return &sqlite_backend;
}
void
db_sqlite_begin_transaction(void)
{
if (!g_chatlog_database)
return;
char* err_msg = NULL;
if (SQLITE_OK != sqlite3_exec(g_chatlog_database, "BEGIN TRANSACTION", NULL, 0, &err_msg)) {
if (err_msg) {
log_error("SQLite BEGIN TRANSACTION failed: %s", err_msg);
sqlite3_free(err_msg);
}
}
}
void
db_sqlite_end_transaction(void)
{
if (!g_chatlog_database)
return;
char* err_msg = NULL;
if (SQLITE_OK != sqlite3_exec(g_chatlog_database, "END TRANSACTION", NULL, 0, &err_msg)) {
if (err_msg) {
log_error("SQLite END TRANSACTION failed: %s", err_msg);
sqlite3_free(err_msg);
}
}
}
void
db_sqlite_rollback_transaction(void)
{
if (!g_chatlog_database)
return;
char* err_msg = NULL;
if (SQLITE_OK != sqlite3_exec(g_chatlog_database, "ROLLBACK", NULL, 0, &err_msg)) {
if (err_msg) {
log_error("SQLite ROLLBACK failed: %s", err_msg);
sqlite3_free(err_msg);
}
}
}
int
db_sqlite_last_changes(void)
{
if (!g_chatlog_database)
return 0;
return sqlite3_changes(g_chatlog_database);
}
GSList*
db_sqlite_get_all_chat(const gchar* const contact_barejid)
{
GSList* result = NULL;
if (!g_chatlog_database)
return NULL;
const Jid* myjid = connection_get_jid();
if (!myjid || !myjid->barejid)
return NULL;
sqlite3_stmt* stmt = NULL;
auto_sqlite char* query = sqlite3_mprintf(
"SELECT COALESCE(B.`message`, A.`message`) AS message, "
"A.`timestamp`, A.`from_jid`, A.`from_resource`, A.`to_jid`, A.`to_resource`, "
"A.`type`, A.`encryption`, A.`stanza_id`, A.`archive_id`, A.`marked_read` "
"FROM `ChatLogs` AS A "
"LEFT JOIN `ChatLogs` AS B ON (A.`replaced_by_db_id` = B.`id` AND A.`from_jid` = B.`from_jid`) "
"WHERE (A.`replaces_db_id` IS NULL) "
"AND ((A.`from_jid` = %Q AND A.`to_jid` = %Q) OR (A.`from_jid` = %Q AND A.`to_jid` = %Q)) "
"ORDER BY A.`timestamp` ASC",
contact_barejid, myjid->barejid, myjid->barejid, contact_barejid);
if (!query)
return NULL;
if (!_db_prepare_ctx(query, &stmt, "db_sqlite_get_all_chat()"))
return NULL;
while (sqlite3_step(stmt) == SQLITE_ROW) {
char* message = (char*)sqlite3_column_text(stmt, 0);
char* date = (char*)sqlite3_column_text(stmt, 1);
char* from_jid = (char*)sqlite3_column_text(stmt, 2);
char* from_resource = (char*)sqlite3_column_text(stmt, 3);
char* to_jid = (char*)sqlite3_column_text(stmt, 4);
char* to_resource = (char*)sqlite3_column_text(stmt, 5);
char* type = (char*)sqlite3_column_text(stmt, 6);
char* encryption = (char*)sqlite3_column_text(stmt, 7);
char* id = (char*)sqlite3_column_text(stmt, 8);
char* archive_id = (char*)sqlite3_column_text(stmt, 9);
int marked_read_raw = sqlite3_column_type(stmt, 10) == SQLITE_NULL ? -1 : sqlite3_column_int(stmt, 10);
ProfMessage* msg = message_init();
msg->id = _db_strdup(id);
msg->stanzaid = _db_strdup(archive_id);
msg->from_jid = jid_create_from_bare_and_resource(from_jid, from_resource);
msg->to_jid = jid_create_from_bare_and_resource(to_jid, to_resource);
msg->plain = _db_strdup(message);
if (!msg->plain)
msg->plain = strdup("");
msg->timestamp = g_date_time_new_from_iso8601(date, NULL);
msg->type = _get_message_type_type(type);
msg->enc = _get_message_enc_type(encryption);
msg->marked_read = marked_read_raw;
result = g_slist_prepend(result, msg);
}
sqlite3_finalize(stmt);
return g_slist_reverse(result);
}
GSList*
db_sqlite_list_contacts(void)
{
GSList* contacts = NULL;
if (!g_chatlog_database)
return NULL;
const Jid* myjid = connection_get_jid();
if (!myjid || !myjid->barejid)
return NULL;
const char* q = "SELECT DISTINCT `from_jid` FROM `ChatLogs` "
"WHERE `from_jid` != ? "
"UNION "
"SELECT DISTINCT `to_jid` FROM `ChatLogs` "
"WHERE `to_jid` != ?";
sqlite3_stmt* stmt = NULL;
if (!_db_prepare_ctx(q, &stmt, "db_sqlite_list_contacts"))
return NULL;
sqlite3_bind_text(stmt, 1, myjid->barejid, -1, SQLITE_STATIC);
sqlite3_bind_text(stmt, 2, myjid->barejid, -1, SQLITE_STATIC);
while (sqlite3_step(stmt) == SQLITE_ROW) {
const char* jid = (const char*)sqlite3_column_text(stmt, 0);
if (jid && strlen(jid) > 0) {
contacts = g_slist_prepend(contacts, g_strdup(jid));
}
}
sqlite3_finalize(stmt);
return g_slist_reverse(contacts);
}