Some checks failed
CI Code / Check spelling (pull_request) Successful in 20s
CI Code / Check coding style (pull_request) Failing after 33s
CI Code / Code Coverage (pull_request) Successful in 4m50s
CI Code / Linux (debian) (pull_request) Successful in 6m14s
CI Code / Linux (ubuntu) (pull_request) Successful in 6m23s
CI Code / Linux (arch) (pull_request) Successful in 6m29s
Replace per-contact directory structure with a single flat file per contact. Each file uses pipe-delimited records with a sparse byte-offset index that is rebuilt on demand and cached in memory. - Rewrite _ff_write_record / _ff_read_records for single-file format - Add sparse index (every Nth record) for O(log N) seek on history read - Cursor-based pagination: _ff_get_previous_chat uses saved byte offset - LMC corrections applied in-place during read (_ff_apply_lmc) - Newline escaping (\n) in message bodies for line-based storage - Simplify verify: parse + timestamp order + LMC reference check - Update parser helpers for new field layout
148 lines
4.2 KiB
C
148 lines
4.2 KiB
C
/*
|
|
* database_flatfile.h
|
|
* vim: expandtab:ts=4:sts=4:sw=4
|
|
*
|
|
* Copyright (C) 2026 Profanity Contributors
|
|
*
|
|
* 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/>.
|
|
*
|
|
* Internal header shared between database_flatfile*.c modules.
|
|
* Not part of the public API — do not include from outside the flatfile backend.
|
|
*/
|
|
|
|
#ifndef DATABASE_FLATFILE_H
|
|
#define DATABASE_FLATFILE_H
|
|
|
|
#include <glib.h>
|
|
#include <stdio.h>
|
|
#include <sys/types.h>
|
|
|
|
#include "database.h"
|
|
#include "xmpp/xmpp.h"
|
|
#include "xmpp/message.h"
|
|
|
|
// --- Constants ---
|
|
|
|
#define DIR_FLATLOG "flatlog"
|
|
#define FLATFILE_HEADER "# profanity chat log — UTF-8, LF line endings\n# vim: set fileencoding=utf-8 fileformat=unix :\n"
|
|
#define FF_MAX_LINE_LEN (10 * 1024 * 1024) /* 10 MB — reject lines longer than this */
|
|
#define FF_MAX_LMC_DEPTH 100 /* max correction chain depth */
|
|
|
|
// --- Shared global ---
|
|
|
|
// Account JID stored during init for path construction.
|
|
// Defined in database_flatfile.c, used by all flatfile modules.
|
|
extern char* g_flatfile_account_jid;
|
|
|
|
// --- Parsed line structure ---
|
|
|
|
typedef struct
|
|
{
|
|
char* timestamp_str;
|
|
GDateTime* timestamp;
|
|
char* type;
|
|
char* enc;
|
|
char* stanza_id;
|
|
char* archive_id;
|
|
char* replace_id;
|
|
char* from_jid;
|
|
char* from_resource;
|
|
char* message;
|
|
off_t file_offset;
|
|
} ff_parsed_line_t;
|
|
|
|
// --- Sparse index for single-file lookup ---
|
|
|
|
#define FF_INDEX_STEP 500
|
|
|
|
typedef struct
|
|
{
|
|
off_t byte_offset;
|
|
gint64 timestamp_epoch;
|
|
} ff_index_entry_t;
|
|
|
|
typedef struct
|
|
{
|
|
time_t mtime;
|
|
off_t size;
|
|
ino_t inode;
|
|
} ff_file_stamp_t;
|
|
|
|
typedef struct
|
|
{
|
|
char* filepath;
|
|
ff_index_entry_t* entries;
|
|
size_t n_entries;
|
|
size_t cap_entries;
|
|
size_t total_lines;
|
|
ff_file_stamp_t stamp;
|
|
off_t cursor_offset;
|
|
int bom_len;
|
|
} ff_contact_state_t;
|
|
|
|
// State management
|
|
ff_contact_state_t* ff_state_new(const char* filepath);
|
|
void ff_state_free(ff_contact_state_t* state);
|
|
gboolean ff_state_ensure_fresh(ff_contact_state_t* state);
|
|
off_t ff_state_offset_for_time(ff_contact_state_t* state, const char* iso_time);
|
|
|
|
// --- Type conversion helpers ---
|
|
|
|
const char* ff_get_message_type_str(prof_msg_type_t type);
|
|
prof_msg_type_t ff_get_message_type_type(const char* const type);
|
|
const char* ff_get_message_enc_str(prof_enc_t enc);
|
|
prof_enc_t ff_get_message_enc_type(const char* const encstr);
|
|
|
|
// --- Path helpers ---
|
|
|
|
char* ff_jid_to_dir(const char* jid);
|
|
char* ff_get_contact_dir(const char* contact_barejid);
|
|
char* ff_get_log_path(const char* contact_barejid);
|
|
gboolean ff_ensure_dir(const char* path);
|
|
|
|
// --- Escape / unescape ---
|
|
|
|
char* ff_escape_message(const char* text);
|
|
char* ff_unescape_message(const char* text);
|
|
char* ff_escape_meta_value(const char* val);
|
|
char* ff_unescape_meta_value(const char* val);
|
|
|
|
// --- I/O ---
|
|
|
|
char* ff_readline(FILE* fp, gboolean* truncated);
|
|
void ff_write_line(FILE* fp, const char* timestamp, const char* type, const char* enc,
|
|
const char* stanza_id, const char* archive_id, const char* replace_id,
|
|
const char* from_jid, const char* from_resource, const char* message_text);
|
|
|
|
// --- Parser helpers ---
|
|
|
|
const char* ff_find_unescaped_char(const char* str, char ch);
|
|
char** ff_split_meta(const char* meta);
|
|
const char* ff_find_unescaped_colonspace(const char* str);
|
|
char* ff_unescape_sender_resource(const char* res);
|
|
|
|
// --- Parser ---
|
|
|
|
void ff_parsed_line_free(ff_parsed_line_t* pl);
|
|
ff_parsed_line_t* ff_parse_line(const char* line);
|
|
ProfMessage* ff_parsed_to_profmessage(ff_parsed_line_t* pl);
|
|
|
|
// --- Integrity verification (database_flatfile_verify.c) ---
|
|
|
|
GSList* ff_verify_integrity(const gchar* const contact_barejid);
|
|
|
|
#endif
|