cproof/src/database_flatfile.h

// SPDX-License-Identifier: GPL-3.0-or-later
//
// This file is part of CProof.
// See LICENSE for the full GPLv3 text and the special OpenSSL linking exception.

/*
 * database_flatfile.h
 * vim: expandtab:ts=4:sts=4:sw=4
 *
 * 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_FORMAT_VERSION 1
#define FF_VERSION_MARKER       "format-version: "
#define FF_STRINGIFY_(x)        #x
#define FF_STRINGIFY(x)         FF_STRINGIFY_(x)
#define FLATFILE_HEADER         "# profanity chat log — UTF-8, LF line endings, " FF_VERSION_MARKER FF_STRINGIFY(FLATFILE_FORMAT_VERSION) "\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* to_jid;
    char* to_resource;
    int marked_read; // -1 = unset (NULL in DB), 0 = unread, 1 = read
    char* message;
    off_t file_offset;
} ff_parsed_line_t;

// --- Sparse index for single-file lookup ---

// Sample every N-th log line for the sparse index.
// 500 lines ≈ one index entry per ~50 KB of log data, so a 100K-message
// contact requires only ~200 entries (~3 KB) for O(log n) time-range lookup.
#define FF_INDEX_STEP 500

// --- Metadata field prefixes (used in _ff_cache_line_ids and ff_parse_line) ---

#define FF_META_PREFIX_ID  "id:"
#define FF_META_PREFIX_AID "aid:"

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;
    int bom_len;
    GHashTable* archive_ids;    // set: archive_id -> NULL (MAM dedup, O(1))
    GHashTable* stanza_senders; // map: stanza_id -> from_jid (LMC validation, O(1))
} 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 ---

// Skip UTF-8 BOM if present; returns 3 if skipped, 0 otherwise.
int ff_skip_bom(FILE* fp);

// Scan leading '#' comment lines for the format-version marker. Returns
// the version found, 0 if no marker is present, or -1 on read error.
// File position is rewound to the start of the comment block on entry.
int ff_read_format_version(FILE* fp);

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* to_jid, const char* to_resource, int marked_read,
                   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) ---

// Run integrity checks against one contact's history.log (or every contact
// when contact_barejid == NULL).
//
// Returns a freshly allocated GSList<integrity_issue_t*> reporting:
//   - File-level: missing log, BOM, CRLF, empty, wrong permissions
//   - Line-level: invalid UTF-8, control characters, unparsable lines,
//                 timestamps out of order, duplicate stanza-id /
//                 archive-id (tracked separately)
//   - Cross-line: broken `corrects:` LMC references
//
// Callers must free with g_slist_free_full(issues, integrity_issue_free).
GSList* ff_verify_integrity(const gchar* const contact_barejid);

#endif