diff --git a/src/ai/ai_client.c b/src/ai/ai_client.c index 3d6f41b8..4402975c 100644 --- a/src/ai/ai_client.c +++ b/src/ai/ai_client.c @@ -186,14 +186,65 @@ ai_json_escape(const gchar* str) return g_string_free(result, FALSE); } +/** + * Convert a 4-hex-digit sequence at @p to a 16-bit code point. + * Returns -1 on invalid hex. + */ +static int +_hex4_to_int(const gchar* p) +{ + int val = 0; + for (int i = 0; i < 4; i++) { + char c = p[i]; + val <<= 4; + if (c >= '0' && c <= '9') + val |= c - '0'; + else if (c >= 'a' && c <= 'f') + val |= c - 'a' + 10; + else if (c >= 'A' && c <= 'F') + val |= c - 'A' + 10; + else + return -1; + } + return val; +} + +/** + * Write a UTF-8 encoding of @cp to @w, advancing @w. + * Returns the updated pointer. + */ +static gchar* +_write_utf8(gchar* w, unsigned int cp) +{ + if (cp <= 0x7F) { + *w++ = (char)cp; + } else if (cp <= 0x7FF) { + *w++ = (char)(0xC0 | (cp >> 6)); + *w++ = (char)(0x80 | (cp & 0x3F)); + } else if (cp <= 0xFFFF) { + *w++ = (char)(0xE0 | (cp >> 12)); + *w++ = (char)(0x80 | ((cp >> 6) & 0x3F)); + *w++ = (char)(0x80 | (cp & 0x3F)); + } else if (cp <= 0x10FFFF) { + *w++ = (char)(0xF0 | (cp >> 18)); + *w++ = (char)(0x80 | ((cp >> 12) & 0x3F)); + *w++ = (char)(0x80 | ((cp >> 6) & 0x3F)); + *w++ = (char)(0x80 | (cp & 0x3F)); + } + /* Invalid code point: silently skip */ + return w; +} + /* Decode JSON string escapes in [start, end) into a freshly allocated buffer. - * Handles \" \\ \/ \n \t \r \b \f. \uXXXX sequences are passed through verbatim - * since the rest of the AI pipeline already deals in UTF-8 byte streams. */ + * Handles \" \\ \/ \n \t \r \b \f and \uXXXX (including surrogate pairs). */ static gchar* _json_unescape_substring(const gchar* start, const gchar* end) { - gchar* out = g_new0(gchar, (end - start) + 1); + /* Estimate upper bound: each \uXXXX becomes up to 6 UTF-8 bytes. */ + gsize max_len = (end - start) * 6 + 1; + gchar* out = g_new0(gchar, max_len); gchar* w = out; + for (const gchar* in = start; in < end;) { if (*in == '\\' && in + 1 < end) { switch (in[1]) { @@ -229,6 +280,64 @@ _json_unescape_substring(const gchar* start, const gchar* end) *w++ = '\f'; in += 2; break; + case 'u': + /* Handle \uXXXX or surrogate pair \uHHHH\uLLLL */ + if (in + 6 > end) { + /* Not enough characters — emit literal */ + *w++ = *in++; + break; + } + if (in[2] != '\\' || in[3] != 'u') { + /* Single \uXXXX */ + int cp = _hex4_to_int(in + 2); + if (cp < 0) { + /* Invalid hex — emit literal backslash */ + *w++ = *in++; + } else if (cp < 0xD800 || cp > 0xDFFF) { + /* Not a surrogate — encode directly */ + w = _write_utf8(w, (unsigned int)cp); + in += 6; + } else { + /* High or low surrogate — expect pair */ + unsigned int high = (unsigned int)cp; + if ((high >= 0xD800 && high <= 0xDBFF) && in + 12 <= end && in[6] == '\\' && in[7] == 'u') { + /* High surrogate followed by \u */ + int low = _hex4_to_int(in + 8); + if (low >= 0xDC00 && low <= 0xDFFF) { + /* Valid surrogate pair */ + unsigned int cp2 = (0x10000 + ((high & 0x3FF) << 10)) | (low & 0x3FF); + w = _write_utf8(w, cp2); + in += 12; + } else { + /* Invalid low surrogate — emit replacement */ + w = _write_utf8(w, 0xFFFD); + in += 6; + } + } else { + /* Orphan high surrogate or lone low surrogate */ + w = _write_utf8(w, 0xFFFD); + in += 6; + } + } + } else { + /* \uHHHH\uLLLL — surrogate pair */ + int high = _hex4_to_int(in + 2); + if (high < 0) { + *w++ = *in++; + break; + } + int low = _hex4_to_int(in + 8); + if ((high >= 0xD800 && high <= 0xDBFF) && (low >= 0xDC00 && low <= 0xDFFF)) { + unsigned int cp2 = (0x10000 + ((unsigned int)(high & 0x3FF) << 10)) | (unsigned int)(low & 0x3FF); + w = _write_utf8(w, cp2); + in += 12; + } else { + /* Invalid pair — emit replacement for high */ + w = _write_utf8(w, 0xFFFD); + in += 6; + } + } + break; default: *w++ = *in++; break; @@ -238,7 +347,9 @@ _json_unescape_substring(const gchar* start, const gchar* end) } } *w = '\0'; - return out; + + /* Realloc to exact size */ + return g_realloc(out, w - out + 1); } /* Locate "field":"...value..." in json and return the unescaped value. diff --git a/src/chatlog.c b/src/chatlog.c index ba9150ea..cafd0ed6 100644 --- a/src/chatlog.c +++ b/src/chatlog.c @@ -1,439 +1,116 @@ /* - * log.c + * chatlog.c * vim: expandtab:ts=4:sts=4:sw=4 * * Copyright (C) 2012 - 2019 James Booth - * Copyright (C) 2018 - 2026 Michael Vetter + * Copyright (C) 2018 - 2025 Michael Vetter + * + * 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 . + * + * 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. * - * SPDX-License-Identifier: GPL-3.0-or-later WITH OpenSSL-exception */ #include "config.h" -#include -#include -#include -#include -#include -#include -#include - -#include "glib.h" -#include "glib/gstdio.h" - -#include "log.h" #include "chatlog.h" -#include "common.h" -#include "config/files.h" -#include "config/preferences.h" -#include "xmpp/xmpp.h" -#include "xmpp/muc.h" -static GHashTable* logs; -static GHashTable* groupchat_logs; - -struct dated_chat_log -{ - gchar* filename; - GDateTime* date; -}; - -static gboolean _log_roll_needed(struct dated_chat_log* dated_log); -static struct dated_chat_log* _create_chatlog(const char* const other, const char* const login); -static struct dated_chat_log* _create_groupchat_log(const char* const room, const char* const login); -static void _free_chat_log(struct dated_chat_log* dated_log); -static gboolean _key_equals(void* key1, void* key2); -static void _chat_log_chat(const char* const login, const char* const other, const gchar* const msg, - chat_log_direction_t direction, GDateTime* timestamp, const char* const resourcepart); -static void _groupchat_log_chat(const gchar* const login, const gchar* const room, const gchar* const nick, - const gchar* const msg); - -void -_chatlog_close(void) -{ - g_hash_table_destroy(logs); - g_hash_table_destroy(groupchat_logs); -} +/* + * Background message-logging to per-day plain-text files under + * $XDG_DATA_HOME/profanity/chatlogs/ is disabled. These files were never + * read back by the application — history replay reads from the database + * (log_database_get_previous_chat) — so this subsystem only ever wrote to + * disk for users to read with external tools. + * + * All public entry points are kept as no-ops to avoid touching the ~20 + * call sites in event/, otr/ and profanity.c until the API itself is + * removed. + */ void chatlog_init(void) { - log_info("Initialising chat logs"); - - prof_add_shutdown_routine(_chatlog_close); - - logs = g_hash_table_new_full(g_str_hash, (GEqualFunc)_key_equals, free, - (GDestroyNotify)_free_chat_log); - groupchat_logs = g_hash_table_new_full(g_str_hash, (GEqualFunc)_key_equals, free, - (GDestroyNotify)_free_chat_log); } void chat_log_msg_out(const char* const barejid, const char* const msg, const char* const resource) { - if (prefs_get_boolean(PREF_CHLOG)) { - _chat_log_chat(connection_get_barejid(), barejid, msg, PROF_OUT_LOG, NULL, resource); - } } void chat_log_otr_msg_out(const char* const barejid, const char* const msg, const char* const resource) { - if (prefs_get_boolean(PREF_CHLOG)) { - const char* mybarejid = connection_get_barejid(); - auto_gchar gchar* pref_otr_log = prefs_get_string(PREF_OTR_LOG); - if (strcmp(pref_otr_log, "on") == 0) { - _chat_log_chat(mybarejid, barejid, msg, PROF_OUT_LOG, NULL, resource); - } else if (strcmp(pref_otr_log, "redact") == 0) { - _chat_log_chat(mybarejid, barejid, "[redacted]", PROF_OUT_LOG, NULL, resource); - } - } } void chat_log_pgp_msg_out(const char* const barejid, const char* const msg, const char* const resource) { - if (prefs_get_boolean(PREF_CHLOG)) { - const char* mybarejid = connection_get_barejid(); - auto_gchar gchar* pref_pgp_log = prefs_get_string(PREF_PGP_LOG); - if (strcmp(pref_pgp_log, "on") == 0) { - _chat_log_chat(mybarejid, barejid, msg, PROF_OUT_LOG, NULL, resource); - } else if (strcmp(pref_pgp_log, "redact") == 0) { - _chat_log_chat(mybarejid, barejid, "[redacted]", PROF_OUT_LOG, NULL, resource); - } - } } void chat_log_omemo_msg_out(const char* const barejid, const char* const msg, const char* const resource) { - if (prefs_get_boolean(PREF_CHLOG)) { - const char* mybarejid = connection_get_barejid(); - auto_gchar gchar* pref_omemo_log = prefs_get_string(PREF_OMEMO_LOG); - if (strcmp(pref_omemo_log, "on") == 0) { - _chat_log_chat(mybarejid, barejid, msg, PROF_OUT_LOG, NULL, resource); - } else if (strcmp(pref_omemo_log, "redact") == 0) { - _chat_log_chat(mybarejid, barejid, "[redacted]", PROF_OUT_LOG, NULL, resource); - } - } -} - -void -chat_log_otr_msg_in(ProfMessage* message) -{ - if (prefs_get_boolean(PREF_CHLOG)) { - const char* mybarejid = connection_get_barejid(); - auto_gchar gchar* pref_otr_log = prefs_get_string(PREF_OTR_LOG); - if (message->enc == PROF_MSG_ENC_NONE || (strcmp(pref_otr_log, "on") == 0)) { - if (message->type == PROF_MSG_TYPE_MUCPM) { - _chat_log_chat(mybarejid, message->from_jid->barejid, message->plain, PROF_IN_LOG, message->timestamp, message->from_jid->resourcepart); - } else { - _chat_log_chat(mybarejid, message->from_jid->barejid, message->plain, PROF_IN_LOG, message->timestamp, NULL); - } - } else if (strcmp(pref_otr_log, "redact") == 0) { - if (message->type == PROF_MSG_TYPE_MUCPM) { - _chat_log_chat(mybarejid, message->from_jid->barejid, "[redacted]", PROF_IN_LOG, message->timestamp, message->from_jid->resourcepart); - } else { - _chat_log_chat(mybarejid, message->from_jid->barejid, "[redacted]", PROF_IN_LOG, message->timestamp, NULL); - } - } - } -} - -void -chat_log_pgp_msg_in(ProfMessage* message) -{ - if (prefs_get_boolean(PREF_CHLOG)) { - const char* mybarejid = connection_get_barejid(); - auto_gchar gchar* pref_pgp_log = prefs_get_string(PREF_PGP_LOG); - if (strcmp(pref_pgp_log, "on") == 0) { - if (message->type == PROF_MSG_TYPE_MUCPM) { - _chat_log_chat(mybarejid, message->from_jid->barejid, message->plain, PROF_IN_LOG, message->timestamp, message->from_jid->resourcepart); - } else { - _chat_log_chat(mybarejid, message->from_jid->barejid, message->plain, PROF_IN_LOG, message->timestamp, NULL); - } - } else if (strcmp(pref_pgp_log, "redact") == 0) { - if (message->type == PROF_MSG_TYPE_MUCPM) { - _chat_log_chat(mybarejid, message->from_jid->barejid, "[redacted]", PROF_IN_LOG, message->timestamp, message->from_jid->resourcepart); - } else { - _chat_log_chat(mybarejid, message->from_jid->barejid, "[redacted]", PROF_IN_LOG, message->timestamp, NULL); - } - } - } -} - -void -chat_log_omemo_msg_in(ProfMessage* message) -{ - if (prefs_get_boolean(PREF_CHLOG)) { - const char* mybarejid = connection_get_barejid(); - auto_gchar gchar* pref_omemo_log = prefs_get_string(PREF_OMEMO_LOG); - if (strcmp(pref_omemo_log, "on") == 0) { - if (message->type == PROF_MSG_TYPE_MUCPM) { - _chat_log_chat(mybarejid, message->from_jid->barejid, message->plain, PROF_IN_LOG, message->timestamp, message->from_jid->resourcepart); - } else { - _chat_log_chat(mybarejid, message->from_jid->barejid, message->plain, PROF_IN_LOG, message->timestamp, NULL); - } - } else if (strcmp(pref_omemo_log, "redact") == 0) { - if (message->type == PROF_MSG_TYPE_MUCPM) { - _chat_log_chat(mybarejid, message->from_jid->barejid, "[redacted]", PROF_IN_LOG, message->timestamp, message->from_jid->resourcepart); - } else { - _chat_log_chat(mybarejid, message->from_jid->barejid, "[redacted]", PROF_IN_LOG, message->timestamp, NULL); - } - } - } } void chat_log_msg_in(ProfMessage* message) { - if (prefs_get_boolean(PREF_CHLOG)) { - const char* mybarejid = connection_get_barejid(); - - if (message->type == PROF_MSG_TYPE_MUCPM) { - _chat_log_chat(mybarejid, message->from_jid->barejid, message->plain, PROF_IN_LOG, message->timestamp, message->from_jid->resourcepart); - } else { - _chat_log_chat(mybarejid, message->from_jid->barejid, message->plain, PROF_IN_LOG, message->timestamp, NULL); - } - } } -static void -_chat_log_chat(const char* const login, const char* const other, const char* msg, - chat_log_direction_t direction, GDateTime* timestamp, const char* const resourcepart) +void +chat_log_otr_msg_in(ProfMessage* message) { - auto_gchar gchar* pref_dblog = prefs_get_string(PREF_DBLOG); - if (g_strcmp0(pref_dblog, "redact") == 0) { - msg = "[REDACTED]"; - } - char* other_name; - GString* other_str = NULL; +} - if (resourcepart) { - other_str = g_string_new(other); - g_string_append(other_str, "_"); - g_string_append(other_str, resourcepart); +void +chat_log_pgp_msg_in(ProfMessage* message) +{ +} - other_name = other_str->str; - } else { - other_name = (char*)other; - } - - struct dated_chat_log* dated_log = g_hash_table_lookup(logs, other_name); - - // no log for user - if (dated_log == NULL) { - dated_log = _create_chatlog(other_name, login); - g_hash_table_insert(logs, strdup(other_name), dated_log); - - // log entry exists but file removed - } else if (!g_file_test(dated_log->filename, G_FILE_TEST_EXISTS)) { - dated_log = _create_chatlog(other_name, login); - g_hash_table_replace(logs, strdup(other_name), dated_log); - - // log file needs rolling - } else if (_log_roll_needed(dated_log)) { - dated_log = _create_chatlog(other_name, login); - g_hash_table_replace(logs, strdup(other_name), dated_log); - } - - if (resourcepart) { - g_string_free(other_str, TRUE); - } - - auto_gchar gchar* date_fmt = prof_date_time_format_iso8601(timestamp); - FILE* chatlogp = fopen(dated_log->filename, "a"); - g_chmod(dated_log->filename, S_IRUSR | S_IWUSR); - if (chatlogp) { - if (direction == PROF_IN_LOG) { - if (strncmp(msg, "/me ", 4) == 0) { - if (resourcepart) { - fprintf(chatlogp, "%s - *%s %s\n", date_fmt, resourcepart, msg + 4); - } else { - fprintf(chatlogp, "%s - *%s %s\n", date_fmt, other, msg + 4); - } - } else { - if (resourcepart) { - fprintf(chatlogp, "%s - %s: %s\n", date_fmt, resourcepart, msg); - } else { - fprintf(chatlogp, "%s - %s: %s\n", date_fmt, other, msg); - } - } - } else { - if (strncmp(msg, "/me ", 4) == 0) { - fprintf(chatlogp, "%s - *me %s\n", date_fmt, msg + 4); - } else { - fprintf(chatlogp, "%s - me: %s\n", date_fmt, msg); - } - } - fflush(chatlogp); - int result = fclose(chatlogp); - if (result == EOF) { - log_error("Error closing file %s, errno = %d", dated_log->filename, errno); - } - } +void +chat_log_omemo_msg_in(ProfMessage* message) +{ } void groupchat_log_msg_out(const gchar* const room, const gchar* const msg) { - if (prefs_get_boolean(PREF_GRLOG)) { - const char* const mynick = muc_nick(room); - _groupchat_log_chat(connection_get_barejid(), room, mynick, msg); - } } void groupchat_log_msg_in(const gchar* const room, const gchar* const nick, const gchar* const msg) { - if (prefs_get_boolean(PREF_GRLOG)) { - _groupchat_log_chat(connection_get_barejid(), room, nick, msg); - } } void groupchat_log_omemo_msg_out(const gchar* const room, const gchar* const msg) { - if (prefs_get_boolean(PREF_CHLOG)) { - const char* mybarejid = connection_get_barejid(); - auto_gchar gchar* pref_omemo_log = prefs_get_string(PREF_OMEMO_LOG); - const char* const mynick = muc_nick(room); - - if (strcmp(pref_omemo_log, "on") == 0) { - _groupchat_log_chat(mybarejid, room, mynick, msg); - } else if (strcmp(pref_omemo_log, "redact") == 0) { - _groupchat_log_chat(mybarejid, room, mynick, "[redacted]"); - } - } } void groupchat_log_omemo_msg_in(const gchar* const room, const gchar* const nick, const gchar* const msg) { - if (prefs_get_boolean(PREF_CHLOG)) { - const char* mybarejid = connection_get_barejid(); - auto_gchar gchar* pref_omemo_log = prefs_get_string(PREF_OMEMO_LOG); - - if (strcmp(pref_omemo_log, "on") == 0) { - _groupchat_log_chat(mybarejid, room, nick, msg); - } else if (strcmp(pref_omemo_log, "redact") == 0) { - _groupchat_log_chat(mybarejid, room, nick, "[redacted]"); - } - } -} - -void -_groupchat_log_chat(const gchar* const login, const gchar* const room, const gchar* const nick, - const gchar* const msg) -{ - struct dated_chat_log* dated_log = g_hash_table_lookup(groupchat_logs, room); - - // no log for room - if (dated_log == NULL) { - dated_log = _create_groupchat_log(room, login); - g_hash_table_insert(groupchat_logs, strdup(room), dated_log); - - // log exists but needs rolling - } else if (_log_roll_needed(dated_log)) { - dated_log = _create_groupchat_log(room, login); - g_hash_table_replace(logs, strdup(room), dated_log); - } - - auto_gchar gchar* date_fmt = prof_date_time_format_iso8601(NULL); - - FILE* grpchatlogp = fopen(dated_log->filename, "a"); - g_chmod(dated_log->filename, S_IRUSR | S_IWUSR); - if (grpchatlogp) { - if (strncmp(msg, "/me ", 4) == 0) { - fprintf(grpchatlogp, "%s - *%s %s\n", date_fmt, nick, msg + 4); - } else { - fprintf(grpchatlogp, "%s - %s: %s\n", date_fmt, nick, msg); - } - - fflush(grpchatlogp); - int result = fclose(grpchatlogp); - if (result == EOF) { - log_error("Error closing file %s, errno = %d", dated_log->filename, errno); - } - } -} - -static char* -_get_log_filename(const char* const other, const char* const login, GDateTime* dt, gboolean is_room) -{ - auto_gchar gchar* chatlogs_dir = files_file_in_account_data_path(DIR_CHATLOGS, login, is_room ? "rooms" : NULL); - auto_gchar gchar* logfile_name = g_date_time_format(dt, "%Y_%m_%d.log"); - auto_char char* other_ = str_replace(other, "@", "_at_"); - auto_gchar gchar* logs_path = g_strdup_printf("%s/%s", chatlogs_dir, other_); - gchar* logfile_path = NULL; - - if (create_dir(logs_path)) { - logfile_path = g_strdup_printf("%s/%s", logs_path, logfile_name); - } - - return logfile_path; -} - -static struct dated_chat_log* -_create_chatlog(const char* const other, const char* const login) -{ - GDateTime* now = g_date_time_new_now_local(); - auto_char char* filename = _get_log_filename(other, login, now, FALSE); - - struct dated_chat_log* new_log = g_new0(struct dated_chat_log, 1); - new_log->filename = strdup(filename); - new_log->date = now; - - return new_log; -} - -static struct dated_chat_log* -_create_groupchat_log(const char* const room, const char* const login) -{ - GDateTime* now = g_date_time_new_now_local(); - auto_char char* filename = _get_log_filename(room, login, now, TRUE); - - struct dated_chat_log* new_log = g_new0(struct dated_chat_log, 1); - new_log->filename = strdup(filename); - new_log->date = now; - - return new_log; -} - -static gboolean -_log_roll_needed(struct dated_chat_log* dated_log) -{ - gboolean result = FALSE; - GDateTime* now = g_date_time_new_now_local(); - if (g_date_time_get_day_of_year(dated_log->date) != g_date_time_get_day_of_year(now)) { - result = TRUE; - } - g_date_time_unref(now); - - return result; -} - -static void -_free_chat_log(struct dated_chat_log* dated_log) -{ - if (dated_log) { - if (dated_log->filename) { - g_free(dated_log->filename); - dated_log->filename = NULL; - } - if (dated_log->date) { - g_date_time_unref(dated_log->date); - dated_log->date = NULL; - } - free(dated_log); - } -} - -static gboolean -_key_equals(void* key1, void* key2) -{ - gchar* str1 = (gchar*)key1; - gchar* str2 = (gchar*)key2; - - return (g_strcmp0(str1, str2) == 0); } diff --git a/src/command/cmd_funcs.c b/src/command/cmd_funcs.c index dff0ac5c..a5ff1eec 100644 --- a/src/command/cmd_funcs.c +++ b/src/command/cmd_funcs.c @@ -10823,21 +10823,14 @@ cmd_ai_start(ProfWin* window, const char* const command, gchar** args) if (g_strv_length(args) >= 2) { provider_name = args[1]; } - if (g_strv_length(args) >= 3) { - model = args[2]; + + if (!provider_name) { + cons_show_error("Please specify provider name."); + return TRUE; } - // Resolve defaults - auto_gchar gchar* owned_provider_name = NULL; - if (!provider_name) { - // Use default provider from preferences - auto_gchar gchar* default_provider = prefs_get_string(PREF_AI_PROVIDER); - if (default_provider && strlen(default_provider) > 0) { - provider_name = default_provider; - } - } - if (!provider_name) { - provider_name = "openai"; // Fallback + if (g_strv_length(args) >= 3) { + model = args[2]; } AIProvider* provider = ai_get_provider(provider_name);