mirror of
https://git.jabber.space/devs/cproof.git
synced 2026-07-18 11:56:22 +00:00
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>
784 lines
23 KiB
C
784 lines
23 KiB
C
// 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.
|
|
|
|
/*
|
|
* test_database_export.c
|
|
*
|
|
* Unit tests for the flatfile write→parse round-trip, escape/unescape helpers,
|
|
* jid_to_dir path construction, and parser edge cases — these are the core
|
|
* functions exercised by database_export.c during export and import.
|
|
*/
|
|
|
|
#include "prof_cmocka.h"
|
|
|
|
#include <glib.h>
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
#include <unistd.h>
|
|
|
|
#include "config.h"
|
|
#include "database_flatfile.h"
|
|
|
|
/* ================================================================
|
|
* Helper: write a single line to a temporary file, then read and
|
|
* parse it back. Returns the parsed result; caller must free with
|
|
* ff_parsed_line_free(). The temp file is removed automatically.
|
|
* ================================================================ */
|
|
static ff_parsed_line_t*
|
|
_roundtrip(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)
|
|
{
|
|
char tmppath[] = "/tmp/proftest_rt_XXXXXX";
|
|
int fd = mkstemp(tmppath);
|
|
assert_true(fd >= 0);
|
|
|
|
FILE* fp = fdopen(fd, "w");
|
|
assert_non_null(fp);
|
|
|
|
ff_write_line(fp, timestamp, type, enc,
|
|
stanza_id, archive_id, replace_id,
|
|
from_jid, from_resource,
|
|
to_jid, to_resource, marked_read,
|
|
message);
|
|
fclose(fp);
|
|
|
|
/* Read & parse */
|
|
fp = fopen(tmppath, "r");
|
|
assert_non_null(fp);
|
|
|
|
gboolean truncated = FALSE;
|
|
char* buf = ff_readline(fp, &truncated);
|
|
fclose(fp);
|
|
unlink(tmppath);
|
|
|
|
assert_non_null(buf);
|
|
assert_false(truncated);
|
|
|
|
ff_parsed_line_t* pl = ff_parse_line(buf);
|
|
free(buf);
|
|
|
|
return pl;
|
|
}
|
|
|
|
/* ================================================================
|
|
* Write → parse round-trip tests
|
|
* ================================================================ */
|
|
|
|
void
|
|
test_ff_roundtrip_simple_chat(void** state)
|
|
{
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-06-15T12:30:00+00:00", "chat", "none",
|
|
NULL, NULL, NULL,
|
|
"alice@example.com", NULL,
|
|
NULL, NULL, -1,
|
|
"Hello, world!");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->timestamp_str, "2025-06-15T12:30:00+00:00");
|
|
assert_string_equal(pl->type, "chat");
|
|
assert_string_equal(pl->enc, "none");
|
|
assert_string_equal(pl->from_jid, "alice@example.com");
|
|
assert_null(pl->stanza_id);
|
|
assert_null(pl->archive_id);
|
|
assert_null(pl->replace_id);
|
|
assert_string_equal(pl->message, "Hello, world!");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_with_all_metadata(void** state)
|
|
{
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-06-15T12:30:00+00:00", "chat", "omemo",
|
|
"sid-abc-123", "aid-xyz-789", "corrects-old-id",
|
|
"bob@example.com", "phone",
|
|
NULL, NULL, -1,
|
|
"Encrypted message.");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->stanza_id, "sid-abc-123");
|
|
assert_string_equal(pl->archive_id, "aid-xyz-789");
|
|
assert_string_equal(pl->replace_id, "corrects-old-id");
|
|
assert_string_equal(pl->enc, "omemo");
|
|
assert_string_equal(pl->from_jid, "bob@example.com");
|
|
assert_string_equal(pl->from_resource, "phone");
|
|
assert_string_equal(pl->message, "Encrypted message.");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_with_resource(void** state)
|
|
{
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-01-01T00:00:00Z", "chat", "none",
|
|
NULL, NULL, NULL,
|
|
"user@jabber.org", "Profanity.abc123",
|
|
NULL, NULL, -1,
|
|
"hi");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->from_jid, "user@jabber.org");
|
|
assert_string_equal(pl->from_resource, "Profanity.abc123");
|
|
assert_string_equal(pl->message, "hi");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_newline_in_body(void** state)
|
|
{
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-03-01T10:00:00Z", "chat", "none",
|
|
NULL, NULL, NULL,
|
|
"alice@x.com", NULL,
|
|
NULL, NULL, -1,
|
|
"line1\nline2\nline3");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->message, "line1\nline2\nline3");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_pipe_in_stanza_id(void** state)
|
|
{
|
|
/* pipes in stanza_id must be escaped in metadata */
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-03-01T10:00:00Z", "chat", "none",
|
|
"id|with|pipes", "aid|also|has|pipes", NULL,
|
|
"a@b.com", NULL,
|
|
NULL, NULL, -1,
|
|
"test");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->stanza_id, "id|with|pipes");
|
|
assert_string_equal(pl->archive_id, "aid|also|has|pipes");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_backslash_in_body(void** state)
|
|
{
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-03-01T10:00:00Z", "chat", "none",
|
|
NULL, NULL, NULL,
|
|
"a@b.com", NULL,
|
|
NULL, NULL, -1,
|
|
"path\\to\\file C:\\Users\\test");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->message, "path\\to\\file C:\\Users\\test");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_unicode_body(void** state)
|
|
{
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-03-01T10:00:00Z", "chat", "none",
|
|
NULL, NULL, NULL,
|
|
"a@b.com", NULL,
|
|
NULL, NULL, -1,
|
|
"Привет мир 🌍 日本語テスト");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->message, "Привет мир 🌍 日本語テスト");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_empty_body(void** state)
|
|
{
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-03-01T10:00:00Z", "chat", "none",
|
|
NULL, NULL, NULL,
|
|
"a@b.com", NULL,
|
|
NULL, NULL, -1,
|
|
"");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->message, "");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_colonspace_in_resource(void** state)
|
|
{
|
|
/* ": " in resource must be escaped during write and unescaped on parse */
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-03-01T10:00:00Z", "chat", "none",
|
|
NULL, NULL, NULL,
|
|
"a@b.com", "res: with: colons",
|
|
NULL, NULL, -1,
|
|
"msg");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->from_jid, "a@b.com");
|
|
assert_string_equal(pl->from_resource, "res: with: colons");
|
|
assert_string_equal(pl->message, "msg");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_muc_type(void** state)
|
|
{
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-03-01T10:00:00Z", "muc", "none",
|
|
NULL, NULL, NULL,
|
|
"room@conference.x.com", "nick",
|
|
NULL, NULL, -1,
|
|
"hello room");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->type, "muc");
|
|
assert_string_equal(pl->from_jid, "room@conference.x.com");
|
|
assert_string_equal(pl->from_resource, "nick");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_omemo_enc(void** state)
|
|
{
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-03-01T10:00:00Z", "chat", "omemo",
|
|
"sid-1", NULL, NULL,
|
|
"a@b.com", NULL,
|
|
NULL, NULL, -1,
|
|
"secret");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->enc, "omemo");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_replace_id(void** state)
|
|
{
|
|
/* LMC (Last Message Correction): corrects: field round-trip */
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-03-01T10:00:00Z", "chat", "none",
|
|
"new-id", NULL, "old-id-to-correct",
|
|
"a@b.com", NULL,
|
|
NULL, NULL, -1,
|
|
"corrected text");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->stanza_id, "new-id");
|
|
assert_string_equal(pl->replace_id, "old-id-to-correct");
|
|
assert_string_equal(pl->message, "corrected text");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_to_jid_and_marked_read(void** state)
|
|
{
|
|
/* to_jid, to_resource, and marked_read round-trip */
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-06-15T12:30:00+00:00", "chat", "none",
|
|
"sid-1", NULL, NULL,
|
|
"alice@example.com", "phone",
|
|
"bob@example.com", "laptop", 1,
|
|
"Hello Bob!");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->from_jid, "alice@example.com");
|
|
assert_string_equal(pl->from_resource, "phone");
|
|
assert_string_equal(pl->to_jid, "bob@example.com");
|
|
assert_string_equal(pl->to_resource, "laptop");
|
|
assert_int_equal(pl->marked_read, 1);
|
|
assert_string_equal(pl->message, "Hello Bob!");
|
|
ff_parsed_line_free(pl);
|
|
|
|
/* marked_read = 0 (unread) */
|
|
pl = _roundtrip(
|
|
"2025-06-15T12:31:00+00:00", "chat", "none",
|
|
NULL, NULL, NULL,
|
|
"bob@example.com", NULL,
|
|
"alice@example.com", NULL, 0,
|
|
"Reply");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->to_jid, "alice@example.com");
|
|
assert_null(pl->to_resource);
|
|
assert_int_equal(pl->marked_read, 0);
|
|
ff_parsed_line_free(pl);
|
|
|
|
/* marked_read = -1 (unset) — should NOT appear in output */
|
|
pl = _roundtrip(
|
|
"2025-06-15T12:32:00+00:00", "chat", "none",
|
|
NULL, NULL, NULL,
|
|
"a@b.com", NULL,
|
|
NULL, NULL, -1,
|
|
"no read flag");
|
|
|
|
assert_non_null(pl);
|
|
assert_null(pl->to_jid);
|
|
assert_null(pl->to_resource);
|
|
assert_int_equal(pl->marked_read, -1);
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
/* ================================================================
|
|
* Escape / unescape symmetry tests
|
|
* ================================================================ */
|
|
|
|
void
|
|
test_ff_escape_unescape_message_identity(void** state)
|
|
{
|
|
const char* inputs[] = {
|
|
"simple text",
|
|
"has\\backslash",
|
|
"has\nnewline",
|
|
"has\rcarriage return",
|
|
"all\\together\nnow\r!",
|
|
"already escaped \\n \\r \\\\",
|
|
"",
|
|
};
|
|
|
|
for (size_t i = 0; i < sizeof(inputs) / sizeof(inputs[0]); i++) {
|
|
char* escaped = ff_escape_message(inputs[i]);
|
|
assert_non_null(escaped);
|
|
/* escaped must not contain raw newlines */
|
|
assert_null(strchr(escaped, '\n'));
|
|
assert_null(strchr(escaped, '\r'));
|
|
|
|
char* unescaped = ff_unescape_message(escaped);
|
|
assert_string_equal(unescaped, inputs[i]);
|
|
|
|
g_free(escaped);
|
|
g_free(unescaped);
|
|
}
|
|
}
|
|
|
|
void
|
|
test_ff_escape_unescape_meta_identity(void** state)
|
|
{
|
|
const char* inputs[] = {
|
|
"simple-id",
|
|
"has|pipe",
|
|
"has]bracket",
|
|
"has\\backslash",
|
|
"has\nnewline",
|
|
"all|to]ge\\th\ner",
|
|
};
|
|
|
|
for (size_t i = 0; i < sizeof(inputs) / sizeof(inputs[0]); i++) {
|
|
char* escaped = ff_escape_meta_value(inputs[i]);
|
|
assert_non_null(escaped);
|
|
|
|
char* unescaped = ff_unescape_meta_value(escaped);
|
|
assert_string_equal(unescaped, inputs[i]);
|
|
|
|
g_free(escaped);
|
|
g_free(unescaped);
|
|
}
|
|
}
|
|
|
|
void
|
|
test_ff_escape_meta_null_returns_null(void** state)
|
|
{
|
|
assert_null(ff_escape_meta_value(NULL));
|
|
assert_null(ff_escape_meta_value(""));
|
|
assert_null(ff_unescape_meta_value(NULL));
|
|
}
|
|
|
|
void
|
|
test_ff_escape_message_null_returns_empty(void** state)
|
|
{
|
|
char* result = ff_escape_message(NULL);
|
|
assert_non_null(result);
|
|
assert_string_equal(result, "");
|
|
g_free(result);
|
|
|
|
result = ff_unescape_message(NULL);
|
|
assert_non_null(result);
|
|
assert_string_equal(result, "");
|
|
g_free(result);
|
|
}
|
|
|
|
/* ================================================================
|
|
* jid_to_dir tests
|
|
* ================================================================ */
|
|
|
|
void
|
|
test_ff_jid_to_dir_simple(void** state)
|
|
{
|
|
char* dir = ff_jid_to_dir("alice");
|
|
assert_non_null(dir);
|
|
assert_string_equal(dir, "alice");
|
|
g_free(dir);
|
|
}
|
|
|
|
void
|
|
test_ff_jid_to_dir_with_at(void** state)
|
|
{
|
|
char* dir = ff_jid_to_dir("alice@example.com");
|
|
assert_non_null(dir);
|
|
assert_string_equal(dir, "alice_at_example.com");
|
|
g_free(dir);
|
|
}
|
|
|
|
void
|
|
test_ff_jid_to_dir_path_traversal_rejected(void** state)
|
|
{
|
|
/* Slashes and '..' must be sanitized */
|
|
char* dir = ff_jid_to_dir("../../etc/passwd");
|
|
assert_non_null(dir);
|
|
/* No slashes or '..' sequences should remain */
|
|
assert_null(strchr(dir, '/'));
|
|
assert_null(strstr(dir, ".."));
|
|
g_free(dir);
|
|
}
|
|
|
|
void
|
|
test_ff_jid_to_dir_null(void** state)
|
|
{
|
|
assert_null(ff_jid_to_dir(NULL));
|
|
assert_null(ff_jid_to_dir(""));
|
|
}
|
|
|
|
/* ================================================================
|
|
* Parser edge-case tests
|
|
* ================================================================ */
|
|
|
|
void
|
|
test_ff_parse_line_empty(void** state)
|
|
{
|
|
assert_null(ff_parse_line(NULL));
|
|
assert_null(ff_parse_line(""));
|
|
}
|
|
|
|
void
|
|
test_ff_parse_line_comment(void** state)
|
|
{
|
|
assert_null(ff_parse_line("# this is a comment"));
|
|
assert_null(ff_parse_line("# cproof chat log — UTF-8, LF line endings"));
|
|
}
|
|
|
|
void
|
|
test_ff_parse_line_legacy_format(void** state)
|
|
{
|
|
/* Legacy chatlog.c format: {timestamp} - {sender}: {message} */
|
|
ff_parsed_line_t* pl = ff_parse_line(
|
|
"2025-06-15T12:30:00+00:00 - alice@example.com: Hello legacy");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->timestamp_str, "2025-06-15T12:30:00+00:00");
|
|
assert_string_equal(pl->from_jid, "alice@example.com");
|
|
assert_string_equal(pl->message, "Hello legacy");
|
|
assert_string_equal(pl->type, "chat");
|
|
assert_string_equal(pl->enc, "none");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_parse_line_no_metadata(void** state)
|
|
{
|
|
/* Simple format without [] brackets */
|
|
ff_parsed_line_t* pl = ff_parse_line(
|
|
"2025-06-15T12:30:00Z alice@example.com: Simple message");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->from_jid, "alice@example.com");
|
|
assert_string_equal(pl->message, "Simple message");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_parse_line_invalid_timestamp(void** state)
|
|
{
|
|
/* Invalid timestamp should cause parse failure */
|
|
ff_parsed_line_t* pl = ff_parse_line(
|
|
"not-a-timestamp [chat|none] a@b.com: msg");
|
|
|
|
assert_null(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_parse_line_empty_timestamp(void** state)
|
|
{
|
|
/* The space before "[" makes the timestamp empty -> g_date_time_new_from_iso8601
|
|
must reject it. */
|
|
ff_parsed_line_t* pl = ff_parse_line(
|
|
" [chat|none] a@b.com: msg");
|
|
assert_null(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_parse_line_partial_iso_timestamp(void** state)
|
|
{
|
|
/* Year-only or yyyy-mm without time portion is not ISO-8601 enough for
|
|
g_date_time_new_from_iso8601 — must fail rather than silently succeed. */
|
|
assert_null(ff_parse_line("2025 [chat|none] a@b.com: msg"));
|
|
assert_null(ff_parse_line("2025-06-15 [chat|none] a@b.com: msg"));
|
|
}
|
|
|
|
void
|
|
test_ff_parse_line_garbage_timestamp(void** state)
|
|
{
|
|
/* Random characters where timestamp should be — parse failure, no segfault. */
|
|
assert_null(ff_parse_line("@@@@@@ [chat|none] a@b.com: msg"));
|
|
assert_null(ff_parse_line("12345 [chat|none] a@b.com: msg"));
|
|
}
|
|
|
|
void
|
|
test_ff_parse_line_impossible_calendar_date(void** state)
|
|
{
|
|
/* Day 32 / Month 13 — well-formed ISO syntax but impossible date,
|
|
g_date_time_new_from_iso8601 returns NULL. */
|
|
assert_null(ff_parse_line(
|
|
"2025-13-01T12:00:00Z [chat|none] a@b.com: msg"));
|
|
assert_null(ff_parse_line(
|
|
"2025-06-32T12:00:00Z [chat|none] a@b.com: msg"));
|
|
assert_null(ff_parse_line(
|
|
"2025-06-15T25:00:00Z [chat|none] a@b.com: msg"));
|
|
}
|
|
|
|
void
|
|
test_ff_parse_line_negative_year_timestamp(void** state)
|
|
{
|
|
/* Negative year is not parseable by g_date_time_new_from_iso8601. */
|
|
assert_null(ff_parse_line(
|
|
"-0001-06-15T12:00:00Z [chat|none] a@b.com: msg"));
|
|
}
|
|
|
|
void
|
|
test_ff_parse_line_far_future_timestamp(void** state)
|
|
{
|
|
/* Year 9999 is valid ISO-8601 and should parse — sanity check that we
|
|
don't artificially reject valid far-future dates. */
|
|
ff_parsed_line_t* pl = ff_parse_line(
|
|
"9999-12-31T23:59:59Z [chat|none] a@b.com: hi");
|
|
assert_non_null(pl);
|
|
assert_non_null(pl->timestamp);
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
/* ================================================================
|
|
* Type / enc conversion round-trip
|
|
* ================================================================ */
|
|
|
|
void
|
|
test_ff_type_str_roundtrip(void** state)
|
|
{
|
|
assert_int_equal(PROF_MSG_TYPE_CHAT, ff_get_message_type_type(ff_get_message_type_str(PROF_MSG_TYPE_CHAT)));
|
|
assert_int_equal(PROF_MSG_TYPE_MUC, ff_get_message_type_type(ff_get_message_type_str(PROF_MSG_TYPE_MUC)));
|
|
assert_int_equal(PROF_MSG_TYPE_MUCPM, ff_get_message_type_type(ff_get_message_type_str(PROF_MSG_TYPE_MUCPM)));
|
|
}
|
|
|
|
void
|
|
test_ff_enc_str_roundtrip(void** state)
|
|
{
|
|
assert_int_equal(PROF_MSG_ENC_NONE, ff_get_message_enc_type(ff_get_message_enc_str(PROF_MSG_ENC_NONE)));
|
|
assert_int_equal(PROF_MSG_ENC_OTR, ff_get_message_enc_type(ff_get_message_enc_str(PROF_MSG_ENC_OTR)));
|
|
assert_int_equal(PROF_MSG_ENC_PGP, ff_get_message_enc_type(ff_get_message_enc_str(PROF_MSG_ENC_PGP)));
|
|
assert_int_equal(PROF_MSG_ENC_OX, ff_get_message_enc_type(ff_get_message_enc_str(PROF_MSG_ENC_OX)));
|
|
assert_int_equal(PROF_MSG_ENC_OMEMO, ff_get_message_enc_type(ff_get_message_enc_str(PROF_MSG_ENC_OMEMO)));
|
|
}
|
|
|
|
/* ================================================================
|
|
* Additional round-trip tests
|
|
* ================================================================ */
|
|
|
|
void
|
|
test_ff_roundtrip_bracket_in_stanza_id(void** state)
|
|
{
|
|
/* ']' in stanza_id must be escaped as \] to avoid breaking metadata parser */
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-03-01T10:00:00Z", "chat", "none",
|
|
"id]with]brackets", "aid]also]has]brackets", NULL,
|
|
"a@b.com", NULL,
|
|
NULL, NULL, -1,
|
|
"test brackets");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->stanza_id, "id]with]brackets");
|
|
assert_string_equal(pl->archive_id, "aid]also]has]brackets");
|
|
assert_string_equal(pl->message, "test brackets");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_backslash_in_resource(void** state)
|
|
{
|
|
/* backslash in from_resource must survive round-trip */
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-03-01T10:00:00Z", "chat", "none",
|
|
NULL, NULL, NULL,
|
|
"a@b.com", "res\\with\\backslash",
|
|
NULL, NULL, -1,
|
|
"msg");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->from_jid, "a@b.com");
|
|
assert_string_equal(pl->from_resource, "res\\with\\backslash");
|
|
assert_string_equal(pl->message, "msg");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_mucpm_type(void** state)
|
|
{
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-03-01T10:00:00Z", "mucpm", "none",
|
|
NULL, NULL, NULL,
|
|
"room@conference.x.com", "nick",
|
|
NULL, NULL, -1,
|
|
"private message");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->type, "mucpm");
|
|
assert_string_equal(pl->from_resource, "nick");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_all_enc_types(void** state)
|
|
{
|
|
const char* enc_types[] = { "none", "otr", "pgp", "ox", "omemo" };
|
|
for (size_t i = 0; i < sizeof(enc_types) / sizeof(enc_types[0]); i++) {
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-03-01T10:00:00Z", "chat", enc_types[i],
|
|
NULL, NULL, NULL,
|
|
"a@b.com", NULL,
|
|
NULL, NULL, -1,
|
|
"msg");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->enc, enc_types[i]);
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_crlf_handling(void** state)
|
|
{
|
|
/* Write a line, then read it with \r\n ending — parser should strip \r */
|
|
char tmppath[] = "/tmp/proftest_crlf_XXXXXX";
|
|
int fd = mkstemp(tmppath);
|
|
assert_true(fd >= 0);
|
|
|
|
FILE* fp = fdopen(fd, "w");
|
|
assert_non_null(fp);
|
|
|
|
/* Write a raw line with \r\n ending */
|
|
fprintf(fp, "2025-03-01T10:00:00Z [chat|none] a@b.com: hello\r\n");
|
|
fclose(fp);
|
|
|
|
fp = fopen(tmppath, "r");
|
|
assert_non_null(fp);
|
|
|
|
gboolean truncated = FALSE;
|
|
char* buf = ff_readline(fp, &truncated);
|
|
fclose(fp);
|
|
unlink(tmppath);
|
|
|
|
assert_non_null(buf);
|
|
ff_parsed_line_t* pl = ff_parse_line(buf);
|
|
free(buf);
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->from_jid, "a@b.com");
|
|
assert_string_equal(pl->message, "hello");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_to_jid_special_chars(void** state)
|
|
{
|
|
/* to: and to_res: with pipe and bracket chars that need escaping */
|
|
ff_parsed_line_t* pl = _roundtrip(
|
|
"2025-03-01T10:00:00Z", "chat", "none",
|
|
NULL, NULL, NULL,
|
|
"a@b.com", NULL,
|
|
"to|user@c.com", "res]with|special", -1,
|
|
"msg with special to");
|
|
|
|
assert_non_null(pl);
|
|
assert_string_equal(pl->to_jid, "to|user@c.com");
|
|
assert_string_equal(pl->to_resource, "res]with|special");
|
|
assert_string_equal(pl->message, "msg with special to");
|
|
ff_parsed_line_free(pl);
|
|
}
|
|
|
|
void
|
|
test_ff_roundtrip_multiple_lines(void** state)
|
|
{
|
|
/* Write several lines, read and parse them all sequentially */
|
|
char tmppath[] = "/tmp/proftest_multi_XXXXXX";
|
|
int fd = mkstemp(tmppath);
|
|
assert_true(fd >= 0);
|
|
|
|
FILE* fp = fdopen(fd, "w");
|
|
assert_non_null(fp);
|
|
|
|
ff_write_line(fp, "2025-01-01T00:00:01Z", "chat", "none",
|
|
NULL, NULL, NULL, "a@b.com", NULL,
|
|
NULL, NULL, -1, "first");
|
|
ff_write_line(fp, "2025-01-01T00:00:02Z", "chat", "none",
|
|
NULL, NULL, NULL, "c@d.com", NULL,
|
|
NULL, NULL, -1, "second");
|
|
ff_write_line(fp, "2025-01-01T00:00:03Z", "muc", "omemo",
|
|
"sid-3", NULL, NULL, "room@conf.com", "nick",
|
|
NULL, NULL, -1, "third");
|
|
fclose(fp);
|
|
|
|
fp = fopen(tmppath, "r");
|
|
assert_non_null(fp);
|
|
|
|
int count = 0;
|
|
const char* expected_msgs[] = { "first", "second", "third" };
|
|
const char* expected_from[] = { "a@b.com", "c@d.com", "room@conf.com" };
|
|
|
|
while (1) {
|
|
gboolean truncated = FALSE;
|
|
char* buf = ff_readline(fp, &truncated);
|
|
if (!buf)
|
|
break;
|
|
ff_parsed_line_t* pl = ff_parse_line(buf);
|
|
free(buf);
|
|
if (pl) {
|
|
assert_true(count < 3);
|
|
assert_string_equal(pl->message, expected_msgs[count]);
|
|
assert_string_equal(pl->from_jid, expected_from[count]);
|
|
ff_parsed_line_free(pl);
|
|
count++;
|
|
}
|
|
}
|
|
fclose(fp);
|
|
unlink(tmppath);
|
|
|
|
assert_int_equal(count, 3);
|
|
}
|
|
|
|
/* ================================================================
|
|
* Additional parser edge-case tests
|
|
* ================================================================ */
|
|
|
|
void
|
|
test_ff_parsed_line_free_null_safe(void** state)
|
|
{
|
|
/* ff_parsed_line_free(NULL) must not crash */
|
|
ff_parsed_line_free(NULL);
|
|
}
|
|
|
|
void
|
|
test_ff_parse_line_no_space_rejected(void** state)
|
|
{
|
|
/* A line with no spaces at all cannot be parsed */
|
|
assert_null(ff_parse_line("noseparatoratall"));
|
|
}
|
|
|
|
void
|
|
test_ff_parse_line_unclosed_bracket(void** state)
|
|
{
|
|
/* Unclosed metadata bracket should return NULL */
|
|
assert_null(ff_parse_line("2025-03-01T10:00:00Z [chat|none a@b.com: msg"));
|
|
}
|