diff --git a/Cargo.lock b/Cargo.lock index 42ad9b6..9237ba4 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -301,6 +301,12 @@ version = "1.1.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "c2db04e74f0a9a93103b50e90b96024c9b2bdca8bce6a632ec71b88736d3d359" +[[package]] +name = "equivalent" +version = "1.0.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f" + [[package]] name = "errno" version = "0.3.14" @@ -377,13 +383,19 @@ dependencies = [ "ahash", ] +[[package]] +name = "hashbrown" +version = "0.17.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4f467dd6dccf739c208452f8014c75c18bb8301b050ad1cfb27153803edb0f51" + [[package]] name = "hashlink" version = "0.9.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "6ba4ff7128dee98c7dc9794b6a411377e1404dba1c97deb8d1a55297bd25d8af" dependencies = [ - "hashbrown", + "hashbrown 0.14.5", ] [[package]] @@ -425,6 +437,16 @@ dependencies = [ "cc", ] +[[package]] +name = "indexmap" +version = "2.14.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d466e9454f08e4a911e14806c24e16fba1b4c121d1ea474396f396069cf949d9" +dependencies = [ + "equivalent", + "hashbrown 0.17.0", +] + [[package]] name = "inout" version = "0.1.4" @@ -771,6 +793,19 @@ dependencies = [ "serde", ] +[[package]] +name = "serde_yaml" +version = "0.9.34+deprecated" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6a8b1a1a2ebf674015cc02edccce75287f1a0130d394307b36743c2f5d504b47" +dependencies = [ + "indexmap", + "itoa", + "ryu", + "serde", + "unsafe-libyaml", +] + [[package]] name = "sha2" version = "0.10.9" @@ -897,6 +932,12 @@ version = "1.0.24" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75" +[[package]] +name = "unsafe-libyaml" +version = "0.2.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "673aac59facbab8a9007c7f6108d11f63b603f7cabff99fabf650fea5c32b861" + [[package]] name = "utf8parse" version = "0.2.2" @@ -1277,6 +1318,7 @@ dependencies = [ "rusqlite", "serde", "serde_json", + "serde_yaml", "sha2", "tokio", "windows", diff --git a/Cargo.toml b/Cargo.toml index 4a6ab54..e04011a 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -3,7 +3,7 @@ name = "wx-cli" version = "0.1.1" edition = "2021" description = "WeChat 4.x (macOS/Linux) local data CLI — decrypt SQLCipher DBs, query chat history, watch new messages" -license = "MIT" +license = "Apache-2.0" repository = "https://github.com/jackwener/wx-cli" keywords = ["wechat", "sqlcipher", "decrypt", "cli"] categories = ["command-line-utilities"] @@ -23,6 +23,7 @@ tokio = { version = "1", features = ["full"] } # 序列化 serde = { version = "1", features = ["derive"] } serde_json = "=1.0.140" +serde_yaml = "0.9" # SQLite rusqlite = { version = "0.31", features = ["bundled"] } diff --git a/LICENSE b/LICENSE index d75c68f..d645695 100644 --- a/LICENSE +++ b/LICENSE @@ -1,21 +1,202 @@ -MIT License -Copyright (c) 2026 jackwener + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ -Permission is hereby granted, free of charge, to any person obtaining a copy -of this software and associated documentation files (the "Software"), to deal -in the Software without restriction, including without limitation the rights -to use, copy, modify, merge, publish, distribute, sublicense, and/or sell -copies of the Software, and to permit persons to whom the Software is -furnished to do so, subject to the following conditions: + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION -The above copyright notice and this permission notice shall be included in all -copies or substantial portions of the Software. + 1. Definitions. -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, -OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE -SOFTWARE. + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. diff --git a/README.md b/README.md index bb88ccd..75143ee 100644 --- a/README.md +++ b/README.md @@ -4,8 +4,8 @@ **从命令行查询本地微信数据** -[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE) -[![Platform](https://img.shields.io/badge/platform-macOS%20%7C%20Linux-lightgrey.svg)](#安装) +[![License: Apache-2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE) +[![Platform](https://img.shields.io/badge/platform-macOS%20%7C%20Linux%20%7C%20Windows-lightgrey.svg)](#安装) [![Rust](https://img.shields.io/badge/built%20with-Rust-orange.svg)](https://www.rust-lang.org) 会话 · 聊天记录 · 搜索 · 联系人 · 群成员 · 收藏 · 统计 · 导出 @@ -25,31 +25,40 @@ ## 安装 +**macOS / Linux** + ```bash curl -fsSL https://raw.githubusercontent.com/jackwener/wx-cli/main/install.sh | bash ``` -> 支持：macOS Apple Silicon / Intel，Linux x86_64 / arm64 +**Windows**（PowerShell，以管理员身份运行） + +```powershell +irm https://raw.githubusercontent.com/jackwener/wx-cli/main/install.ps1 | iex +```
其他安装方式 **手动下载** -从 [Releases](https://github.com/jackwener/wx-cli/releases) 下载对应平台文件，重命名为 `wx`，`chmod +x` 后放入 PATH： +从 [Releases](https://github.com/jackwener/wx-cli/releases) 下载对应平台文件： | 平台 | 文件 | |------|------| | macOS Apple Silicon | `wx-macos-arm64` | | macOS Intel | `wx-macos-x86_64` | | Linux x86_64 | `wx-linux-x86_64` | +| Windows x86_64 | `wx-windows-x86_64.exe` | + +macOS / Linux：`chmod +x wx && sudo mv wx /usr/local/bin/` **从源码构建** ```bash git clone git@github.com:jackwener/wx-cli.git && cd wx-cli cargo build --release -# 产物：target/release/wx +# 产物：target/release/wx（Windows: wx.exe） ```
@@ -58,18 +67,27 @@ cargo build --release ## 快速开始 -微信 4.x（macOS 版）需要先做 ad-hoc 签名才能扫描内存： +保持微信运行，然后初始化（只需一次）： + +**macOS**（需要先对微信做 ad-hoc 签名，才能扫描其内存） ```bash sudo codesign --force --deep --sign - /Applications/WeChat.app +sudo wx init ``` -保持微信运行，然后初始化（只需一次）： +**Linux** ```bash sudo wx init ``` +**Windows**（以管理员身份运行 PowerShell） + +```powershell +wx init +``` + 之后直接用，daemon 会在首次调用时自动启动： ```bash diff --git a/find_all_keys_macos.c b/find_all_keys_macos.c deleted file mode 100644 index eb6a9e5..0000000 --- a/find_all_keys_macos.c +++ /dev/null @@ -1,319 +0,0 @@ -/* - * find_all_keys_macos.c - macOS WeChat memory key scanner - * - * Scans WeChat process memory for SQLCipher encryption keys in the - * x'' format used by WeChat 4.x on macOS. - * - * Prerequisites: - * - WeChat must be ad-hoc signed (or SIP disabled) - * - Must run as root (sudo) - * - * Build: - * cc -O2 -o find_all_keys_macos find_all_keys_macos.c -framework Foundation - * - * Usage: - * sudo ./find_all_keys_macos [pid] - * If pid is omitted, automatically finds WeChat PID. - * - * Output: JSON file at ./all_keys.json (compatible with decrypt_db.py) - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define MAX_KEYS 256 -#define KEY_SIZE 32 -#define SALT_SIZE 16 -#define HEX_PATTERN_LEN 96 /* 64 hex (key) + 32 hex (salt) */ -#define CHUNK_SIZE (2 * 1024 * 1024) - -typedef struct { - char key_hex[65]; - char salt_hex[33]; - char full_pragma[100]; -} key_entry_t; - -/* Forward declaration */ -static int read_db_salt(const char *path, char *salt_hex_out); - -/* nftw callback state for collecting DB files */ -#define MAX_DBS 256 -static char g_db_salts[MAX_DBS][33]; -static char g_db_names[MAX_DBS][256]; -static int g_db_count = 0; -static int nftw_collect_db(const char *fpath, const struct stat *sb, - int typeflag, struct FTW *ftwbuf) { - (void)sb; (void)ftwbuf; - if (typeflag != FTW_F) return 0; - size_t len = strlen(fpath); - if (len < 3 || strcmp(fpath + len - 3, ".db") != 0) return 0; - if (g_db_count >= MAX_DBS) return 0; - - char salt[33]; - if (read_db_salt(fpath, salt) != 0) return 0; - - strcpy(g_db_salts[g_db_count], salt); - /* Extract relative path from db_storage/ */ - const char *rel = strstr(fpath, "db_storage/"); - if (rel) rel += strlen("db_storage/"); - else { - rel = strrchr(fpath, '/'); - rel = rel ? rel + 1 : fpath; - } - strncpy(g_db_names[g_db_count], rel, 255); - g_db_names[g_db_count][255] = '\0'; - printf(" %s: salt=%s\n", g_db_names[g_db_count], salt); - g_db_count++; - return 0; -} - -static int is_hex_char(unsigned char c) { - return (c >= '0' && c <= '9') || (c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F'); -} - -static pid_t find_wechat_pid(void) { - FILE *fp = popen("pgrep -x WeChat", "r"); - if (!fp) return -1; - char buf[64]; - pid_t pid = -1; - if (fgets(buf, sizeof(buf), fp)) - pid = atoi(buf); - pclose(fp); - return pid; -} - -/* Read DB salt (first 16 bytes) and return hex string */ -static int read_db_salt(const char *path, char *salt_hex_out) { - FILE *f = fopen(path, "rb"); - if (!f) return -1; - unsigned char header[16]; - if (fread(header, 1, 16, f) != 16) { fclose(f); return -1; } - fclose(f); - /* Check if unencrypted */ - if (memcmp(header, "SQLite format 3", 15) == 0) return -1; - for (int i = 0; i < 16; i++) - sprintf(salt_hex_out + i * 2, "%02x", header[i]); - salt_hex_out[32] = '\0'; - return 0; -} - -int main(int argc, char *argv[]) { - pid_t pid; - if (argc >= 2) - pid = atoi(argv[1]); - else - pid = find_wechat_pid(); - - if (pid <= 0) { - fprintf(stderr, "WeChat not running or invalid PID\n"); - return 1; - } - - printf("============================================================\n"); - printf(" macOS WeChat Memory Key Scanner (C version)\n"); - printf("============================================================\n"); - printf("WeChat PID: %d\n", pid); - - /* Get task port */ - mach_port_t task; - kern_return_t kr = task_for_pid(mach_task_self(), pid, &task); - if (kr != KERN_SUCCESS) { - fprintf(stderr, "task_for_pid failed: %d\n", kr); - fprintf(stderr, "Make sure: (1) running as root, (2) WeChat is ad-hoc signed\n"); - return 1; - } - printf("Got task port: %u\n", task); - - /* Resolve real user's HOME (sudo may change HOME to /var/root) */ - const char *home = getenv("HOME"); - const char *sudo_user = getenv("SUDO_USER"); - if (sudo_user) { - struct passwd *pw = getpwnam(sudo_user); - if (pw && pw->pw_dir) - home = pw->pw_dir; - } - if (!home) home = "/root"; - printf("User home: %s\n", home); - - /* Collect DB salts by recursively walking db_storage directories. - * Note: POSIX glob() does not support ** recursive matching on macOS, - * so we use nftw() to walk the directory tree instead. */ - printf("\nScanning for DB files...\n"); - char db_base_dir[512]; - snprintf(db_base_dir, sizeof(db_base_dir), - "%s/Library/Containers/com.tencent.xinWeChat/Data/Documents/xwechat_files", - home); - - /* Walk each account's db_storage directory */ - DIR *xdir = opendir(db_base_dir); - if (xdir) { - struct dirent *ent; - while ((ent = readdir(xdir)) != NULL) { - if (ent->d_name[0] == '.') continue; - char storage_path[768]; - snprintf(storage_path, sizeof(storage_path), - "%s/%s/db_storage", db_base_dir, ent->d_name); - struct stat st; - if (stat(storage_path, &st) == 0 && S_ISDIR(st.st_mode)) { - nftw(storage_path, nftw_collect_db, 20, FTW_PHYS); - } - } - closedir(xdir); - } - printf("Found %d encrypted DBs\n", g_db_count); - - /* Scan memory for x' patterns */ - printf("\nScanning memory for keys...\n"); - key_entry_t keys[MAX_KEYS]; - int key_count = 0; - size_t total_scanned = 0; - int region_count = 0; - - mach_vm_address_t addr = 0; - while (1) { - mach_vm_size_t size = 0; - vm_region_basic_info_data_64_t info; - mach_msg_type_number_t info_count = VM_REGION_BASIC_INFO_COUNT_64; - mach_port_t obj_name; - - kr = mach_vm_region(task, &addr, &size, VM_REGION_BASIC_INFO_64, - (vm_region_info_t)&info, &info_count, &obj_name); - if (kr != KERN_SUCCESS) break; - if (size == 0) { addr++; continue; } /* guard against infinite loop */ - - if ((info.protection & (VM_PROT_READ | VM_PROT_WRITE)) == - (VM_PROT_READ | VM_PROT_WRITE)) { - region_count++; - - mach_vm_address_t ca = addr; - while (ca < addr + size) { - mach_vm_size_t cs = addr + size - ca; - if (cs > CHUNK_SIZE) cs = CHUNK_SIZE; - - vm_offset_t data; - mach_msg_type_number_t dc; - kr = mach_vm_read(task, ca, cs, &data, &dc); - if (kr == KERN_SUCCESS) { - unsigned char *buf = (unsigned char *)data; - total_scanned += dc; - - for (size_t i = 0; i + HEX_PATTERN_LEN + 3 < dc; i++) { - if (buf[i] == 'x' && buf[i + 1] == '\'') { - /* Check if followed by 96 hex chars and closing ' */ - int valid = 1; - for (int j = 0; j < HEX_PATTERN_LEN; j++) { - if (!is_hex_char(buf[i + 2 + j])) { valid = 0; break; } - } - if (!valid) continue; - if (buf[i + 2 + HEX_PATTERN_LEN] != '\'') continue; - - /* Extract key and salt hex */ - char key_hex[65], salt_hex[33]; - memcpy(key_hex, buf + i + 2, 64); - key_hex[64] = '\0'; - memcpy(salt_hex, buf + i + 2 + 64, 32); - salt_hex[32] = '\0'; - - /* Convert to lowercase for comparison */ - for (int j = 0; key_hex[j]; j++) - if (key_hex[j] >= 'A' && key_hex[j] <= 'F') - key_hex[j] += 32; - for (int j = 0; salt_hex[j]; j++) - if (salt_hex[j] >= 'A' && salt_hex[j] <= 'F') - salt_hex[j] += 32; - - /* Deduplicate */ - int dup = 0; - for (int k = 0; k < key_count; k++) { - if (strcmp(keys[k].key_hex, key_hex) == 0 && - strcmp(keys[k].salt_hex, salt_hex) == 0) { - dup = 1; break; - } - } - if (dup) continue; - - if (key_count < MAX_KEYS) { - strcpy(keys[key_count].key_hex, key_hex); - strcpy(keys[key_count].salt_hex, salt_hex); - snprintf(keys[key_count].full_pragma, sizeof(keys[key_count].full_pragma), - "x'%s%s'", key_hex, salt_hex); - key_count++; - } - } - } - mach_vm_deallocate(mach_task_self(), data, dc); - } - /* Advance with overlap to catch patterns spanning chunk boundaries. - * Pattern is x'<96 hex chars>' = 99 bytes total. */ - if (cs > HEX_PATTERN_LEN + 3) - ca += cs - (HEX_PATTERN_LEN + 3); - else - ca += cs; - } - } - addr += size; - } - - printf("\nScan complete: %zuMB scanned, %d regions, %d unique keys\n", - total_scanned / 1024 / 1024, region_count, key_count); - - /* Match keys to DBs */ - printf("\n%-25s %-66s %s\n", "Database", "Key", "Salt"); - printf("%-25s %-66s %s\n", - "-------------------------", - "------------------------------------------------------------------", - "--------------------------------"); - - int matched = 0; - for (int i = 0; i < key_count; i++) { - const char *db = NULL; - for (int j = 0; j < g_db_count; j++) { - if (strcmp(keys[i].salt_hex, g_db_salts[j]) == 0) { - db = g_db_names[j]; - matched++; - break; - } - } - printf("%-25s %-66s %s\n", - db ? db : "(unknown)", - keys[i].key_hex, - keys[i].salt_hex); - } - printf("\nMatched %d/%d keys to known DBs\n", matched, key_count); - - /* Save JSON: { "rel/path.db": { "enc_key": "hex" }, ... } - * Uses forward slashes (native macOS paths, valid JSON without escaping). - */ - const char *out_path = "all_keys.json"; - FILE *fp = fopen(out_path, "w"); - if (fp) { - fprintf(fp, "{\n"); - int first = 1; - for (int i = 0; i < key_count; i++) { - const char *db = NULL; - for (int j = 0; j < g_db_count; j++) { - if (strcmp(keys[i].salt_hex, g_db_salts[j]) == 0) { - db = g_db_names[j]; - break; - } - } - if (!db) continue; - fprintf(fp, "%s \"%s\": {\"enc_key\": \"%s\"}", - first ? "" : ",\n", db, keys[i].key_hex); - first = 0; - } - fprintf(fp, "\n}\n"); - fclose(fp); - printf("Saved to %s\n", out_path); - } - - return 0; -} diff --git a/install.ps1 b/install.ps1 new file mode 100644 index 0000000..d56cecd --- /dev/null +++ b/install.ps1 @@ -0,0 +1,50 @@ +# wx-cli Windows installer +# Run with: irm https://raw.githubusercontent.com/jackwener/wx-cli/main/install.ps1 | iex + +$ErrorActionPreference = "Stop" + +$Repo = "jackwener/wx-cli" +$BinName = "wx.exe" +$Asset = "wx-windows-x86_64.exe" +$InstallDir = "$env:LOCALAPPDATA\wx-cli" + +# ── 获取最新版本 ──────────────────────────────────────────── +Write-Host "正在获取最新版本..." +$Release = Invoke-RestMethod "https://api.github.com/repos/$Repo/releases/latest" +$Tag = $Release.tag_name + +if (-not $Tag) { + Write-Error "获取版本失败，请检查网络或访问 https://github.com/$Repo/releases" + exit 1 +} + +Write-Host "版本: $Tag" + +# ── 下载 ──────────────────────────────────────────────────── +$Url = "https://github.com/$Repo/releases/download/$Tag/$Asset" +$TmpFile = Join-Path $env:TEMP "wx-cli-download.exe" + +Write-Host "下载中: $Url" +Invoke-WebRequest -Uri $Url -OutFile $TmpFile -UseBasicParsing + +# ── 安装 ──────────────────────────────────────────────────── +if (-not (Test-Path $InstallDir)) { + New-Item -ItemType Directory -Path $InstallDir | Out-Null +} + +Move-Item -Force $TmpFile (Join-Path $InstallDir $BinName) + +# ── 加入 PATH（当前用户） ──────────────────────────────────── +$UserPath = [Environment]::GetEnvironmentVariable("PATH", "User") +if ($UserPath -notlike "*$InstallDir*") { + [Environment]::SetEnvironmentVariable("PATH", "$UserPath;$InstallDir", "User") + Write-Host "已将 $InstallDir 加入用户 PATH（重新打开终端生效）" +} + +Write-Host "" +Write-Host "✓ wx 已安装到 $InstallDir\$BinName" +Write-Host "" +Write-Host "快速开始（以管理员身份运行）：" +Write-Host " wx init # 首次初始化（需要微信正在运行）" +Write-Host " wx sessions # 查看最近会话" +Write-Host " wx --help # 查看所有命令" diff --git a/src/cli/contacts.rs b/src/cli/contacts.rs index f2b78c2..e52a30b 100644 --- a/src/cli/contacts.rs +++ b/src/cli/contacts.rs @@ -1,28 +1,12 @@ use anyhow::Result; use crate::ipc::Request; use super::transport; +use super::output::{resolve, print_value}; pub fn cmd_contacts(query: Option, limit: usize, json: bool) -> Result<()> { - let req = Request::Contacts { query, limit }; - let resp = transport::send(req)?; - + let resp = transport::send(Request::Contacts { query, limit })?; let contacts = resp.data.get("contacts") - .and_then(|v| v.as_array()) .cloned() - .unwrap_or_default(); - let total = resp.data["total"].as_i64().unwrap_or(contacts.len() as i64); - - if json { - println!("{}", serde_json::to_string_pretty(&contacts)?); - return Ok(()); - } - - println!("共 {} 个联系人（显示 {} 个）:\n", total, contacts.len()); - for c in &contacts { - let display = c["display"].as_str().unwrap_or(""); - let username = c["username"].as_str().unwrap_or(""); - println!(" {:<20} {}", display, username); - } - - Ok(()) + .unwrap_or(serde_json::Value::Array(vec![])); + print_value(&contacts, &resolve(json)) } diff --git a/src/cli/export.rs b/src/cli/export.rs index d5ab7f6..85a6989 100644 --- a/src/cli/export.rs +++ b/src/cli/export.rs @@ -20,6 +20,7 @@ pub fn cmd_export( offset: 0, since: since_ts, until: until_ts, + msg_type: None, }; let resp = transport::send(req)?; diff --git a/src/cli/favorites.rs b/src/cli/favorites.rs new file mode 100644 index 0000000..84db1d6 --- /dev/null +++ b/src/cli/favorites.rs @@ -0,0 +1,29 @@ +use anyhow::Result; +use crate::ipc::Request; +use super::transport; +use super::output::{resolve, print_value}; + +fn parse_fav_type(s: &str) -> Option { + match s { + "text" => Some(1), + "image" => Some(2), + "article" => Some(5), + "card" => Some(19), + "video" => Some(20), + _ => None, + } +} + +pub fn cmd_favorites( + limit: usize, + fav_type: Option, + query: Option, + json: bool, +) -> Result<()> { + let type_val = fav_type.as_deref().and_then(parse_fav_type); + let resp = transport::send(Request::Favorites { limit, fav_type: type_val, query })?; + let items = resp.data.get("items") + .cloned() + .unwrap_or(serde_json::Value::Array(vec![])); + print_value(&items, &resolve(json)) +} diff --git a/src/cli/history.rs b/src/cli/history.rs index 1ccf058..b5fabb7 100644 --- a/src/cli/history.rs +++ b/src/cli/history.rs @@ -1,6 +1,7 @@ use anyhow::Result; use crate::ipc::Request; use super::transport; +use super::output::{resolve, print_value}; pub fn cmd_history( chat: String, @@ -8,73 +9,65 @@ pub fn cmd_history( offset: usize, since: Option, until: Option, + msg_type: Option, json: bool, ) -> Result<()> { let since_ts = since.as_deref().map(parse_time).transpose()?; - let until_ts = until.as_deref().map(|s| parse_time_end(s)).transpose()?; - - let req = Request::History { - chat, - limit, - offset, - since: since_ts, - until: until_ts, - }; + let until_ts = until.as_deref().map(parse_time_end).transpose()?; + let type_val = msg_type.as_deref().and_then(parse_msg_type); + let req = Request::History { chat, limit, offset, since: since_ts, until: until_ts, msg_type: type_val }; let resp = transport::send(req)?; - if json { - let msgs = resp.data.get("messages").cloned().unwrap_or(serde_json::Value::Array(vec![])); - println!("{}", serde_json::to_string_pretty(&msgs)?); - return Ok(()); - } - - let chat_name = resp.data["chat"].as_str().unwrap_or(""); - let is_group = resp.data["is_group"].as_bool().unwrap_or(false); - let count = resp.data["count"].as_i64().unwrap_or(0); - let group_str = if is_group { " [群]" } else { "" }; - println!("=== {}{} ({} 条) ===\n", chat_name, group_str, count); - - if let Some(msgs) = resp.data["messages"].as_array() { - for m in msgs { - let time = m["time"].as_str().unwrap_or(""); - let sender = m["sender"].as_str().unwrap_or(""); - let content = m["content"].as_str().unwrap_or(""); - - let sender_str = if !sender.is_empty() { - format!("\x1b[33m{}\x1b[0m: ", sender) - } else { - String::new() - }; - - println!("\x1b[90m[{}]\x1b[0m {}{}", time, sender_str, content); - } - } - - Ok(()) + let msgs = resp.data.get("messages") + .cloned() + .unwrap_or(serde_json::Value::Array(vec![])); + print_value(&msgs, &resolve(json)) } pub fn parse_time(s: &str) -> Result { - for fmt in &["%Y-%m-%d %H:%M:%S", "%Y-%m-%d %H:%M", "%Y-%m-%d"] { + use chrono::{Local, TimeZone}; + for fmt in &["%Y-%m-%d %H:%M:%S", "%Y-%m-%d %H:%M"] { if let Ok(dt) = chrono::NaiveDateTime::parse_from_str(s, fmt) { - return Ok(dt.and_utc().timestamp()); - } - // 尝试仅日期格式 - if let Ok(d) = chrono::NaiveDate::parse_from_str(s, fmt) { - let dt = d.and_hms_opt(0, 0, 0).unwrap(); - return Ok(dt.and_utc().timestamp()); + return Local.from_local_datetime(&dt).single() + .map(|d| d.timestamp()) + .ok_or_else(|| anyhow::anyhow!("本地时间歧义: {}", s)); } } + if let Ok(d) = chrono::NaiveDate::parse_from_str(s, "%Y-%m-%d") { + let dt = d.and_hms_opt(0, 0, 0).unwrap(); + return Local.from_local_datetime(&dt).single() + .map(|d| d.timestamp()) + .ok_or_else(|| anyhow::anyhow!("本地时间歧义: {}", s)); + } anyhow::bail!("无法解析时间 '{}'，支持 YYYY-MM-DD / YYYY-MM-DD HH:MM / YYYY-MM-DD HH:MM:SS", s) } pub fn parse_time_end(s: &str) -> Result { - // 对于仅日期格式，结束时间为当天 23:59:59 + use chrono::{Local, TimeZone}; if s.len() == 10 { if let Ok(d) = chrono::NaiveDate::parse_from_str(s, "%Y-%m-%d") { let dt = d.and_hms_opt(23, 59, 59).unwrap(); - return Ok(dt.and_utc().timestamp()); + return Local.from_local_datetime(&dt).single() + .map(|d| d.timestamp()) + .ok_or_else(|| anyhow::anyhow!("本地时间歧义: {}", s)); } } parse_time(s) } + +/// 将消息类型字符串转为 local_type 整数，未知类型返回 None +pub fn parse_msg_type(s: &str) -> Option { + match s { + "text" => Some(1), + "image" => Some(3), + "voice" => Some(34), + "video" => Some(43), + "sticker" => Some(47), + "location" => Some(48), + "link" | "file" => Some(49), + "call" => Some(50), + "system" => Some(10000), + _ => None, + } +} diff --git a/src/cli/members.rs b/src/cli/members.rs new file mode 100644 index 0000000..2579fd1 --- /dev/null +++ b/src/cli/members.rs @@ -0,0 +1,12 @@ +use anyhow::Result; +use crate::ipc::Request; +use super::transport; +use super::output::{resolve, print_value}; + +pub fn cmd_members(chat: String, json: bool) -> Result<()> { + let resp = transport::send(Request::Members { chat })?; + let members = resp.data.get("members") + .cloned() + .unwrap_or(serde_json::Value::Array(vec![])); + print_value(&members, &resolve(json)) +} diff --git a/src/cli/mod.rs b/src/cli/mod.rs index b5f45d3..4d493de 100644 --- a/src/cli/mod.rs +++ b/src/cli/mod.rs @@ -4,9 +4,14 @@ pub mod history; pub mod search; pub mod contacts; pub mod export; -pub mod watch; pub mod daemon_cmd; pub mod transport; +pub mod output; +pub mod unread; +pub mod members; +pub mod new_messages; +pub mod stats; +pub mod favorites; use anyhow::Result; use clap::{Parser, Subcommand}; @@ -32,7 +37,7 @@ enum Commands { /// 会话数量 #[arg(short = 'n', long, default_value = "20")] limit: usize, - /// 输出原始 JSON + /// 输出 JSON（默认 YAML） #[arg(long)] json: bool, }, @@ -52,7 +57,11 @@ enum Commands { /// 结束时间 YYYY-MM-DD #[arg(long)] until: Option, - /// 输出原始 JSON + /// 消息类型过滤 [text|image|voice|video|sticker|location|link|file|call|system] + #[arg(long = "type", value_name = "TYPE", + value_parser = ["text","image","voice","video","sticker","location","link","file","call","system"])] + msg_type: Option, + /// 输出 JSON（默认 YAML） #[arg(long)] json: bool, }, @@ -72,7 +81,11 @@ enum Commands { /// 结束时间 YYYY-MM-DD #[arg(long)] until: Option, - /// 输出原始 JSON + /// 消息类型过滤 [text|image|voice|video|sticker|location|link|file|call|system] + #[arg(long = "type", value_name = "TYPE", + value_parser = ["text","image","voice","video","sticker","location","link","file","call","system"])] + msg_type: Option, + /// 输出 JSON（默认 YAML） #[arg(long)] json: bool, }, @@ -84,7 +97,7 @@ enum Commands { /// 显示数量 #[arg(short = 'n', long, default_value = "50")] limit: usize, - /// 输出原始 JSON + /// 输出 JSON（默认 YAML） #[arg(long)] json: bool, }, @@ -101,19 +114,66 @@ enum Commands { /// 最多导出条数 #[arg(short = 'n', long, default_value = "500")] limit: usize, - /// 输出格式 [markdown|txt|json] - #[arg(short = 'f', long, default_value = "markdown", value_parser = ["markdown", "txt", "json"])] + /// 输出格式 [markdown|txt|json|yaml] + #[arg(short = 'f', long, default_value = "markdown", value_parser = ["markdown", "txt", "json", "yaml"])] format: String, /// 输出文件（默认 stdout） #[arg(short = 'o', long)] output: Option, }, - /// 实时监听新消息（Ctrl+C 退出） - Watch { - /// 只显示指定聊天的消息 + /// 显示有未读消息的会话 + Unread { + /// 显示数量 + #[arg(short = 'n', long, default_value = "20")] + limit: usize, + /// 输出 JSON（默认 YAML） #[arg(long)] - chat: Option, - /// 输出 JSON lines + json: bool, + }, + /// 查看群成员 + Members { + /// 群聊名称（支持模糊匹配） + chat: String, + /// 输出 JSON（默认 YAML） + #[arg(long)] + json: bool, + }, + /// 获取自上次检查以来的新消息 + NewMessages { + /// 显示数量上限 + #[arg(short = 'n', long, default_value = "200")] + limit: usize, + /// 输出 JSON（默认 YAML） + #[arg(long)] + json: bool, + }, + /// 聊天统计分析 + Stats { + /// 聊天对象名称（支持模糊匹配） + chat: String, + /// 起始时间 YYYY-MM-DD + #[arg(long)] + since: Option, + /// 结束时间 YYYY-MM-DD + #[arg(long)] + until: Option, + /// 输出 JSON（默认 YAML） + #[arg(long)] + json: bool, + }, + /// 查看微信收藏内容 + Favorites { + /// 显示数量 + #[arg(short = 'n', long, default_value = "50")] + limit: usize, + /// 类型过滤 [text|image|article|card|video] + #[arg(long = "type", value_name = "TYPE", + value_parser = ["text","image","article","card","video"])] + fav_type: Option, + /// 内容关键词搜索 + #[arg(short = 'q', long)] + query: Option, + /// 输出 JSON（默认 YAML） #[arg(long)] json: bool, }, @@ -153,17 +213,25 @@ fn dispatch(cli: Cli) -> Result<()> { match cli.command { Commands::Init { force } => init::cmd_init(force), Commands::Sessions { limit, json } => sessions::cmd_sessions(limit, json), - Commands::History { chat, limit, offset, since, until, json } => { - history::cmd_history(chat, limit, offset, since, until, json) + Commands::History { chat, limit, offset, since, until, msg_type, json } => { + history::cmd_history(chat, limit, offset, since, until, msg_type, json) } - Commands::Search { keyword, chats, limit, since, until, json } => { - search::cmd_search(keyword, chats, limit, since, until, json) + Commands::Search { keyword, chats, limit, since, until, msg_type, json } => { + search::cmd_search(keyword, chats, limit, since, until, msg_type, json) } Commands::Contacts { query, limit, json } => contacts::cmd_contacts(query, limit, json), Commands::Export { chat, since, until, limit, format, output } => { export::cmd_export(chat, since, until, limit, format, output) } - Commands::Watch { chat, json } => watch::cmd_watch(chat, json), + Commands::Unread { limit, json } => unread::cmd_unread(limit, json), + Commands::Members { chat, json } => members::cmd_members(chat, json), + Commands::NewMessages { limit, json } => new_messages::cmd_new_messages(limit, json), + Commands::Stats { chat, since, until, json } => { + stats::cmd_stats(chat, since, until, json) + } + Commands::Favorites { limit, fav_type, query, json } => { + favorites::cmd_favorites(limit, fav_type, query, json) + } Commands::Daemon { cmd } => daemon_cmd::cmd_daemon(cmd), } } diff --git a/src/cli/new_messages.rs b/src/cli/new_messages.rs new file mode 100644 index 0000000..b847210 --- /dev/null +++ b/src/cli/new_messages.rs @@ -0,0 +1,58 @@ +use anyhow::Result; +use std::collections::HashMap; +use crate::ipc::Request; +use super::transport; +use super::output::{resolve, print_value}; + +fn state_file() -> std::path::PathBuf { + dirs::home_dir() + .unwrap_or_else(|| std::path::PathBuf::from(".")) + .join(".wx-cli") + .join("last_check.json") +} + +/// 加载上次的 per-session 时间戳快照 +/// 格式：{ "sessions": { "username": timestamp, ... } } +/// 旧格式（只有 timestamp 字段）直接丢弃，重新全量获取 +fn load_state() -> Option> { + let data = std::fs::read_to_string(state_file()).ok()?; + let v: serde_json::Value = serde_json::from_str(&data).ok()?; + // 旧格式（只有 timestamp 字段）没有 sessions key → 返回 None 触发首次运行逻辑 + let map: HashMap = v.get("sessions")? + .as_object()? + .iter() + .filter_map(|(k, v)| v.as_i64().map(|ts| (k.clone(), ts))) + .collect(); + // 空 map 也是合法状态（账号无任何会话），返回 Some(empty) 而非 None + // 这样不会误触发全量历史拉取 + Some(map) +} + +fn save_state(new_state: &HashMap) -> Result<()> { + let path = state_file(); + if let Some(parent) = path.parent() { + std::fs::create_dir_all(parent)?; + } + std::fs::write(&path, serde_json::to_string(&serde_json::json!({ "sessions": new_state }))?)?; + Ok(()) +} + +pub fn cmd_new_messages(limit: usize, json: bool) -> Result<()> { + let state = load_state(); + let resp = transport::send(Request::NewMessages { state, limit })?; + + // 保存 daemon 返回的 new_state + if let Some(obj) = resp.data.get("new_state").and_then(|v| v.as_object()) { + let map: HashMap = obj.iter() + .filter_map(|(k, v)| v.as_i64().map(|ts| (k.clone(), ts))) + .collect(); + if !map.is_empty() { + let _ = save_state(&map); + } + } + + let messages = resp.data.get("messages") + .cloned() + .unwrap_or(serde_json::Value::Array(vec![])); + print_value(&messages, &resolve(json)) +} diff --git a/src/cli/output.rs b/src/cli/output.rs new file mode 100644 index 0000000..33ef78a --- /dev/null +++ b/src/cli/output.rs @@ -0,0 +1,18 @@ +/// 输出格式 +pub enum Fmt { + Yaml, + Json, +} + +/// 默认 YAML，--json 时输出 JSON +pub fn resolve(json: bool) -> Fmt { + if json { Fmt::Json } else { Fmt::Yaml } +} + +pub fn print_value(value: &serde_json::Value, fmt: &Fmt) -> anyhow::Result<()> { + match fmt { + Fmt::Json => println!("{}", serde_json::to_string_pretty(value)?), + Fmt::Yaml => print!("{}", serde_yaml::to_string(value)?), + } + Ok(()) +} diff --git a/src/cli/search.rs b/src/cli/search.rs index 6f79d3d..e6f3d00 100644 --- a/src/cli/search.rs +++ b/src/cli/search.rs @@ -1,7 +1,8 @@ use anyhow::Result; use crate::ipc::Request; use super::transport; -use super::history::{parse_time, parse_time_end}; +use super::history::{parse_time, parse_time_end, parse_msg_type}; +use super::output::{resolve, print_value}; pub fn cmd_search( keyword: String, @@ -9,53 +10,26 @@ pub fn cmd_search( limit: usize, since: Option, until: Option, + msg_type: Option, json: bool, ) -> Result<()> { let since_ts = since.as_deref().map(parse_time).transpose()?; let until_ts = until.as_deref().map(parse_time_end).transpose()?; - + let type_val = msg_type.as_deref().and_then(parse_msg_type); let chats_opt = if chats.is_empty() { None } else { Some(chats) }; let req = Request::Search { - keyword: keyword.clone(), + keyword, chats: chats_opt, limit, since: since_ts, until: until_ts, + msg_type: type_val, }; let resp = transport::send(req)?; let results = resp.data.get("results") - .and_then(|v| v.as_array()) .cloned() - .unwrap_or_default(); - let count = resp.data["count"].as_i64().unwrap_or(results.len() as i64); - - if json { - println!("{}", serde_json::to_string_pretty(&results)?); - return Ok(()); - } - - println!("搜索 \"{}\"，找到 {} 条:\n", keyword, count); - for r in &results { - let time = r["time"].as_str().unwrap_or(""); - let chat = r["chat"].as_str().unwrap_or(""); - let sender = r["sender"].as_str().unwrap_or(""); - let content = r["content"].as_str().unwrap_or(""); - - let chat_str = if !chat.is_empty() { - format!("\x1b[36m[{}]\x1b[0m ", chat) - } else { - String::new() - }; - let sender_str = if !sender.is_empty() { - format!("\x1b[33m{}\x1b[0m: ", sender) - } else { - String::new() - }; - - println!("\x1b[90m[{}]\x1b[0m {}{}{}", time, chat_str, sender_str, content); - } - - Ok(()) + .unwrap_or(serde_json::Value::Array(vec![])); + print_value(&results, &resolve(json)) } diff --git a/src/cli/sessions.rs b/src/cli/sessions.rs index cfedf79..9ccadb8 100644 --- a/src/cli/sessions.rs +++ b/src/cli/sessions.rs @@ -1,44 +1,12 @@ use anyhow::Result; use crate::ipc::Request; use super::transport; +use super::output::{resolve, print_value}; pub fn cmd_sessions(limit: usize, json: bool) -> Result<()> { let resp = transport::send(Request::Sessions { limit })?; let data = resp.data.get("sessions") - .and_then(|v| v.as_array()) .cloned() - .unwrap_or_default(); - - if json { - println!("{}", serde_json::to_string_pretty(&data)?); - return Ok(()); - } - - for s in &data { - let time = s["time"].as_str().unwrap_or(""); - let chat = s["chat"].as_str().unwrap_or(""); - let is_group = s["is_group"].as_bool().unwrap_or(false); - let unread = s["unread"].as_i64().unwrap_or(0); - let msg_type = s["last_msg_type"].as_str().unwrap_or(""); - let sender = s["last_sender"].as_str().unwrap_or(""); - let summary = s["summary"].as_str().unwrap_or(""); - - let unread_str = if unread > 0 { - format!(" \x1b[31m({}未读)\x1b[0m", unread) - } else { - String::new() - }; - let group_str = if is_group { " [群]" } else { "" }; - let sender_str = if !sender.is_empty() { - format!("{}: ", sender) - } else { - String::new() - }; - - println!("\x1b[90m[{}]\x1b[0m \x1b[1m{}\x1b[0m{}{}", time, chat, group_str, unread_str); - println!(" {}: {}{}", msg_type, sender_str, summary); - println!(); - } - - Ok(()) + .unwrap_or(serde_json::Value::Array(vec![])); + print_value(&data, &resolve(json)) } diff --git a/src/cli/stats.rs b/src/cli/stats.rs new file mode 100644 index 0000000..2e9a293 --- /dev/null +++ b/src/cli/stats.rs @@ -0,0 +1,18 @@ +use anyhow::Result; +use crate::ipc::Request; +use super::transport; +use super::history::{parse_time, parse_time_end}; +use super::output::{resolve, print_value}; + +pub fn cmd_stats( + chat: String, + since: Option, + until: Option, + json: bool, +) -> Result<()> { + let since_ts = since.as_deref().map(parse_time).transpose()?; + let until_ts = until.as_deref().map(parse_time_end).transpose()?; + + let resp = transport::send(Request::Stats { chat, since: since_ts, until: until_ts })?; + print_value(&resp.data, &resolve(json)) +} diff --git a/src/cli/unread.rs b/src/cli/unread.rs new file mode 100644 index 0000000..595081a --- /dev/null +++ b/src/cli/unread.rs @@ -0,0 +1,12 @@ +use anyhow::Result; +use crate::ipc::Request; +use super::transport; +use super::output::{resolve, print_value}; + +pub fn cmd_unread(limit: usize, json: bool) -> Result<()> { + let resp = transport::send(Request::Unread { limit })?; + let data = resp.data.get("sessions") + .cloned() + .unwrap_or(serde_json::Value::Array(vec![])); + print_value(&data, &resolve(json)) +} diff --git a/src/cli/watch.rs b/src/cli/watch.rs deleted file mode 100644 index 73c15d1..0000000 --- a/src/cli/watch.rs +++ /dev/null @@ -1,94 +0,0 @@ -use anyhow::Result; -use std::io::BufRead; - -use crate::ipc::Request; -use super::transport; - -pub fn cmd_watch(chat: Option, json: bool) -> Result<()> { - transport::ensure_daemon()?; - - let sock_path = crate::config::sock_path(); - - // 连接 socket - #[cfg(unix)] - let mut stream = { - use std::os::unix::net::UnixStream; - UnixStream::connect(&sock_path)? - }; - - // 发送 watch 请求 - let req_line = serde_json::to_string(&Request::Watch)? + "\n"; - #[cfg(unix)] - { - use std::io::Write; - stream.write_all(req_line.as_bytes())?; - } - - if !json { - eprintln!("监听中（Ctrl+C 退出）...\n"); - } - - #[cfg(windows)] - { - anyhow::bail!("watch 命令在 Windows 上暂不支持，请使用 Unix 系统"); - } - - #[cfg(unix)] - { - let reader = std::io::BufReader::new(stream.try_clone()?); - for line_result in reader.lines() { - let line = match line_result { - Ok(l) => l, - Err(_) => break, - }; - let line = line.trim().to_string(); - if line.is_empty() { - continue; - } - let event: serde_json::Value = match serde_json::from_str(&line) { - Ok(v) => v, - Err(_) => continue, - }; - - let evt = event["event"].as_str().unwrap_or(""); - if evt == "connected" || evt == "heartbeat" { - continue; - } - - // 过滤指定聊天 - if let Some(ref filter_chat) = chat { - let event_chat = event["chat"].as_str().unwrap_or(""); - let event_user = event["username"].as_str().unwrap_or(""); - if event_chat != filter_chat && event_user != filter_chat { - continue; - } - } - - if json { - println!("{}", line); - continue; - } - - let time_s = event["time"].as_str().unwrap_or(""); - let chat_s = event["chat"].as_str().unwrap_or(""); - let is_group = event["is_group"].as_bool().unwrap_or(false); - let sender = event["sender"].as_str().unwrap_or(""); - let content = event["content"].as_str().unwrap_or(""); - - let chat_part = if is_group { - format!("\x1b[36m[{}]\x1b[0m ", chat_s) - } else { - format!("\x1b[1m{}\x1b[0m ", chat_s) - }; - let sender_part = if !sender.is_empty() { - format!("\x1b[33m{}\x1b[0m: ", sender) - } else { - String::new() - }; - - println!("\x1b[90m[{}]\x1b[0m {}{}{}", time_s, chat_part, sender_part, content); - } - } - - Ok(()) -} diff --git a/src/crypto/mod.rs b/src/crypto/mod.rs index 0d07469..e5407b5 100644 --- a/src/crypto/mod.rs +++ b/src/crypto/mod.rs @@ -7,6 +7,8 @@ use cbc::cipher::{BlockDecryptMut, KeyIvInit}; use std::io::{Read, Write}; use std::path::Path; +type Block = aes::cipher::Block; + pub const PAGE_SZ: usize = 4096; pub const SALT_SZ: usize = 16; pub const RESERVE_SZ: usize = 80; // IV(16) + HMAC(64) @@ -62,16 +64,13 @@ fn aes_cbc_decrypt(key: &[u8; 32], iv: &[u8; 16], data: &[u8]) -> Result if data.is_empty() || data.len() % 16 != 0 { bail!("密文长度不是 AES 块大小的倍数: {}", data.len()); } - let mut buf = data.to_vec(); - // 使用 raw 模式不处理 padding + // 将 &[u8] 复制为 Block 数组，避免 unsafe from_raw_parts_mut + let mut blocks: Vec = data.chunks_exact(16) + .map(Block::clone_from_slice) + .collect(); Aes256CbcDec::new(key.into(), iv.into()) - .decrypt_blocks_mut(unsafe { - std::slice::from_raw_parts_mut( - buf.as_mut_ptr() as *mut aes::cipher::Block, - buf.len() / 16, - ) - }); - Ok(buf) + .decrypt_blocks_mut(&mut blocks); + Ok(blocks.iter().flat_map(|b| b.iter().copied()).collect()) } /// 完整解密一个 SQLCipher 数据库文件（流式，逐页读写避免全量载入内存） diff --git a/src/daemon/cache.rs b/src/daemon/cache.rs index 229ddfc..9801396 100644 --- a/src/daemon/cache.rs +++ b/src/daemon/cache.rs @@ -56,8 +56,7 @@ impl DbCache { fn cache_file_path(&self, rel_key: &str) -> PathBuf { let hash = format!("{:x}", md5::compute(rel_key.as_bytes())); - let short = &hash[..12]; - self.cache_dir.join(format!("{}.db", short)) + self.cache_dir.join(format!("{}.db", hash)) } /// 从持久化文件加载 mtime 记录，复用未过期的解密文件 diff --git a/src/daemon/mod.rs b/src/daemon/mod.rs index 1ca44d2..63e1fe5 100644 --- a/src/daemon/mod.rs +++ b/src/daemon/mod.rs @@ -4,9 +4,7 @@ pub mod server; use anyhow::Result; use std::collections::HashMap; -use std::path::PathBuf; use std::sync::Arc; -use tokio::sync::broadcast; use crate::config; @@ -78,154 +76,12 @@ async fn async_run() -> Result<()> { let names_arc = Arc::new(std::sync::RwLock::new(names)); - // 启动 WAL watcher - let (watch_tx, _) = broadcast::channel::(500); - let session_wal = cfg.db_dir.join("session").join("session.db-wal"); - - // SAFETY: 我们确保 db 和 names_arc 在 daemon 生命周期内有效 - // 使用 Arc 传递引用避免 'static 问题 - let db_arc = Arc::clone(&db); - let names_arc2 = Arc::clone(&names_arc); - let tx_clone = watch_tx.clone(); - let session_wal2 = session_wal.clone(); - tokio::spawn(async move { - run_watcher(db_arc, names_arc2, tx_clone, session_wal2).await; - }); - // 启动 IPC server（阻塞） - server::serve(Arc::clone(&db), Arc::clone(&names_arc), watch_tx).await?; + server::serve(Arc::clone(&db), Arc::clone(&names_arc)).await?; Ok(()) } -async fn run_watcher( - db: Arc, - names: Arc>, - tx: broadcast::Sender, - session_wal: PathBuf, -) { - use std::collections::HashMap; - use std::time::Duration; - use crate::ipc::WatchEvent; - - let mut last_mtime = 0u64; - let mut last_ts: HashMap = HashMap::new(); - let mut initialized = false; - - loop { - tokio::time::sleep(Duration::from_millis(500)).await; - - if tx.receiver_count() == 0 { - continue; - } - - let wal_mtime = match mtime_nanos(&session_wal) { - 0 => continue, - m => m, - }; - if wal_mtime == last_mtime { - continue; - } - last_mtime = wal_mtime; - - let path = match db.get("session/session.db").await { - Ok(Some(p)) => p, - _ => continue, - }; - - let path2 = path.clone(); - let rows: Vec<(String, Vec, i64, i64, String)> = match tokio::task::spawn_blocking(move || { - let conn = rusqlite::Connection::open(&path2)?; - let mut stmt = conn.prepare( - "SELECT username, summary, last_timestamp, last_msg_type, last_msg_sender - FROM SessionTable WHERE last_timestamp > 0 - ORDER BY last_timestamp DESC LIMIT 50" - )?; - let rows = stmt.query_map([], |row| { - Ok(( - row.get::<_, String>(0)?, - row.get::<_, Vec>(1) - .or_else(|_| row.get::<_, String>(1).map(|s| s.into_bytes())) - .unwrap_or_default(), - row.get::<_, i64>(2)?, - row.get::<_, i64>(3).unwrap_or(0), - row.get::<_, String>(4).unwrap_or_default(), - )) - })?.collect::>>()?; - Ok::<_, anyhow::Error>(rows) - }).await { - Ok(Ok(r)) => r, - _ => continue, - }; - - let names_guard = match names.read() { - Ok(g) => g, - Err(_) => continue, - }; - - for (username, summary_bytes, ts, msg_type, sender) in &rows { - if !initialized { - last_ts.insert(username.clone(), *ts); - continue; - } - let prev_ts = last_ts.get(username).copied().unwrap_or(0); - if *ts <= prev_ts { - continue; - } - last_ts.insert(username.clone(), *ts); - - let display = names_guard.display(username); - let is_group = username.contains("@chatroom"); - let summary = decompress_or_str(summary_bytes); - let summary = if summary.contains(":\n") { - summary.splitn(2, ":\n").nth(1).unwrap_or(&summary).to_string() - } else { - summary - }; - let sender_display = if !sender.is_empty() { - names_guard.map.get(sender).cloned().unwrap_or_else(|| sender.clone()) - } else { - String::new() - }; - - let event = WatchEvent { - event: "message".into(), - time: Some(fmt_hhmm(*ts)), - chat: Some(display), - username: Some(username.clone()), - is_group: Some(is_group), - sender: Some(sender_display), - content: Some(summary), - msg_type: Some(query::fmt_type(*msg_type)), - timestamp: Some(*ts), - }; - let _ = tx.send(event); - } - - if !initialized { - initialized = true; - } - } -} - -use cache::mtime_nanos; - -fn decompress_or_str(data: &[u8]) -> String { - if data.is_empty() { return String::new(); } - if let Ok(dec) = zstd::decode_all(data) { - if let Ok(s) = String::from_utf8(dec) { return s; } - } - String::from_utf8_lossy(data).into_owned() -} - -fn fmt_hhmm(ts: i64) -> String { - use chrono::{Local, TimeZone}; - Local.timestamp_opt(ts, 0) - .single() - .map(|dt| dt.format("%H:%M").to_string()) - .unwrap_or_else(|| ts.to_string()) -} - /// 从 all_keys.json 提取 rel_key -> enc_key 映射 /// /// 兼容两种格式： diff --git a/src/daemon/query.rs b/src/daemon/query.rs index 30bcc81..da42bba 100644 --- a/src/daemon/query.rs +++ b/src/daemon/query.rs @@ -1,5 +1,5 @@ use anyhow::{Context, Result}; -use chrono::{Local, TimeZone}; +use chrono::{Local, TimeZone, Timelike}; use regex::Regex; use rusqlite::Connection; use serde_json::{json, Value}; @@ -140,6 +140,7 @@ pub async fn q_history( offset: usize, since: Option, until: Option, + msg_type: Option, ) -> Result { let username = resolve_username(chat, names) .with_context(|| format!("找不到联系人: {}", chat))?; @@ -164,7 +165,9 @@ pub async fn q_history( let offset2 = offset; let msgs: Vec = tokio::task::spawn_blocking(move || { - query_messages(&path, &tname, &uname, is_group2, &names_map, since2, until2, limit2 + offset2, 0) + // per-DB 软上限：offset + limit 已足够全局分页，避免大群全量加载 + let per_db_cap = offset2 + limit2; + query_messages(&path, &tname, &uname, is_group2, &names_map, since2, until2, msg_type, per_db_cap, 0) }).await??; all_msgs.extend(msgs); @@ -193,6 +196,7 @@ pub async fn q_search( limit: usize, since: Option, until: Option, + msg_type: Option, ) -> Result { let mut targets: Vec<(String, String, String, String)> = Vec::new(); // (path, table, display, uname) @@ -277,7 +281,7 @@ pub async fn q_search( for (tname, display, uname) in &table_list { let is_group = uname.contains("@chatroom"); match search_in_table(&conn, tname, &uname, is_group, - &names_map2, &kw2, since2, until2, limit2) + &names_map2, &kw2, since2, until2, msg_type, limit2) { Ok(rows) => { for mut row in rows { @@ -343,19 +347,21 @@ fn resolve_username(chat_name: &str, names: &Names) -> Option { return Some(chat_name.to_string()); } let low = chat_name.to_lowercase(); - // 精确匹配显示名 - for (uname, display) in &names.map { - if low == display.to_lowercase() { - return Some(uname.clone()); - } + // 精确匹配显示名：排序后取第一个，保证确定性 + let mut exact: Vec<&String> = names.map.iter() + .filter(|(_, display)| display.to_lowercase() == low) + .map(|(uname, _)| uname) + .collect(); + exact.sort(); + if let Some(u) = exact.into_iter().next() { + return Some(u.clone()); } - // 模糊匹配 - for (uname, display) in &names.map { - if display.to_lowercase().contains(&low) { - return Some(uname.clone()); - } - } - None + // 模糊匹配：取 display name 最短的（最精确），相同长度取字典序最小 + let mut candidates: Vec<(&String, &String)> = names.map.iter() + .filter(|(_, display)| display.to_lowercase().contains(&low)) + .collect(); + candidates.sort_by_key(|(uname, display)| (display.len(), uname.as_str())); + candidates.into_iter().next().map(|(uname, _)| uname.clone()) } async fn find_msg_tables( @@ -364,8 +370,7 @@ async fn find_msg_tables( username: &str, ) -> Result> { let table_name = format!("Msg_{:x}", md5::compute(username.as_bytes())); - let re = Regex::new(r"^Msg_[0-9a-f]{32}$").unwrap(); - if !re.is_match(&table_name) { + if !msg_table_re().is_match(&table_name) { return Ok(Vec::new()); } @@ -413,6 +418,7 @@ fn query_messages( names_map: &HashMap, since: Option, until: Option, + msg_type: Option, limit: usize, offset: usize, ) -> Result> { @@ -429,6 +435,10 @@ fn query_messages( clauses.push("create_time <= ?"); params.push(Box::new(u)); } + if let Some(t) = msg_type { + clauses.push("local_type = ?"); + params.push(Box::new(t)); + } let where_clause = if clauses.is_empty() { String::new() } else { @@ -487,6 +497,7 @@ fn search_in_table( keyword: &str, since: Option, until: Option, + msg_type: Option, limit: usize, ) -> Result> { let id2u = load_id2u(conn); @@ -502,6 +513,10 @@ fn search_in_table( clauses.push("create_time <= ?".into()); params.push(Box::new(u)); } + if let Some(t) = msg_type { + clauses.push("local_type = ?".into()); + params.push(Box::new(t)); + } let where_clause = format!("WHERE {}", clauses.join(" AND ")); let sql = format!( "SELECT local_id, local_type, create_time, real_sender_id, @@ -761,3 +776,639 @@ fn fmt_time(ts: i64, fmt: &str) -> String { .unwrap_or_else(|| ts.to_string()) } +// ─── 新增命令查询函数 ────────────────────────────────────────────────────────── + +/// 查询有未读消息的会话 +pub async fn q_unread(db: &DbCache, names: &Names, limit: usize) -> Result { + let path = db.get("session/session.db").await? + .context("无法解密 session.db")?; + + let limit_val = limit; + let rows: Vec<(String, i64, Vec, i64, i64, String, String)> = tokio::task::spawn_blocking(move || { + let conn = Connection::open(&path)?; + let mut stmt = conn.prepare( + "SELECT username, unread_count, summary, last_timestamp, + last_msg_type, last_msg_sender, last_sender_display_name + FROM SessionTable + WHERE unread_count > 0 + ORDER BY last_timestamp DESC LIMIT ?" + )?; + let rows = stmt.query_map([limit_val as i64], |row| { + Ok(( + row.get::<_, String>(0)?, + row.get::<_, i64>(1).unwrap_or(0), + get_content_bytes(row, 2), + row.get::<_, i64>(3).unwrap_or(0), + row.get::<_, i64>(4).unwrap_or(0), + row.get::<_, String>(5).unwrap_or_default(), + row.get::<_, String>(6).unwrap_or_default(), + )) + })? + .collect::>>()?; + Ok::<_, anyhow::Error>(rows) + }).await??; + + let mut results = Vec::new(); + for (username, unread, summary_bytes, ts, msg_type, sender, sender_name) in rows { + let display = names.display(&username); + let is_group = username.contains("@chatroom"); + let summary = decompress_or_str(&summary_bytes); + let summary = strip_group_prefix(&summary); + let sender_display = if is_group && !sender.is_empty() { + names.map.get(&sender).cloned().unwrap_or_else(|| { + if !sender_name.is_empty() { sender_name.clone() } else { sender.clone() } + }) + } else { + String::new() + }; + results.push(json!({ + "chat": display, + "username": username, + "is_group": is_group, + "unread": unread, + "last_msg_type": fmt_type(msg_type), + "last_sender": sender_display, + "summary": summary, + "timestamp": ts, + "time": fmt_time(ts, "%m-%d %H:%M"), + })); + } + let total = results.len(); + Ok(json!({ "sessions": results, "total": total })) +} + +/// 查询群成员：优先从 contact.db 的 chatroom_member/chat_room 表获取完整列表， +/// 若表不存在则退化为从消息记录聚合有发言记录的成员 +pub async fn q_members(db: &DbCache, names: &Names, chat: &str) -> Result { + let username = resolve_username(chat, names) + .with_context(|| format!("找不到联系人: {}", chat))?; + + if !username.contains("@chatroom") { + anyhow::bail!("'{}' 不是群聊，无法查看群成员", names.display(&username)); + } + + let display = names.display(&username); + let names_map = names.map.clone(); + + // 优先路径：contact.db → chatroom_member + chat_room（完整成员列表） + if let Some(contact_p) = db.get("contact/contact.db").await? { + let uname2 = username.clone(); + let display2 = display.clone(); + let names_map2 = names_map.clone(); + + let members_opt: Option> = tokio::task::spawn_blocking(move || { + let conn = Connection::open(&contact_p)?; + + let has_table: bool = conn.query_row( + "SELECT 1 FROM sqlite_master WHERE type='table' AND name='chatroom_member'", + [], + |_| Ok(true), + ).unwrap_or(false); + + if !has_table { + return Ok::<_, anyhow::Error>(None); + } + + // 从 chat_room 表获取整数 room_id 和群主 + // WeChat 不同版本列名可能不同：username / chat_room_name / name + let (room_id, owner): (i64, String) = [ + "SELECT id, owner FROM chat_room WHERE username = ?", + "SELECT id, owner FROM chat_room WHERE chat_room_name = ?", + "SELECT id, owner FROM chat_room WHERE name = ?", + ].iter().find_map(|sql| { + conn.query_row(sql, [&uname2], |row| { + Ok((row.get::<_, i64>(0)?, row.get::<_, String>(1).unwrap_or_default())) + }).ok() + }).unwrap_or((0, String::new())); + + if room_id == 0 { + return Ok::<_, anyhow::Error>(None); + } + + let mut stmt = conn.prepare( + "SELECT c.username, c.nick_name, c.remark + FROM chatroom_member cm + LEFT JOIN contact c ON c.id = cm.member_id + WHERE cm.room_id = ?" + )?; + let raw: Vec<(String, String, String)> = stmt.query_map([room_id], |row| { + Ok(( + row.get::<_, String>(0).unwrap_or_default(), + row.get::<_, String>(1).unwrap_or_default(), + row.get::<_, String>(2).unwrap_or_default(), + )) + })? + .filter_map(|r| r.ok()) + .filter(|(uid, _, _)| !uid.is_empty()) + .collect(); + + if raw.is_empty() { + return Ok(None); + } + + let mut members: Vec = raw.iter().map(|(uid, nick, remark)| { + let disp = if !remark.is_empty() { remark.clone() } + else if !nick.is_empty() { nick.clone() } + else { names_map2.get(uid).cloned().unwrap_or_else(|| uid.clone()) }; + let is_owner = uid == &owner && !owner.is_empty(); + json!({ "username": uid, "display": disp, "is_owner": is_owner }) + }).collect(); + + // 群主排首位，其余按 display 字典序 + members.sort_by(|a, b| { + let ao = a["is_owner"].as_bool().unwrap_or(false); + let bo = b["is_owner"].as_bool().unwrap_or(false); + if ao != bo { return bo.cmp(&ao); } + a["display"].as_str().unwrap_or("").cmp(b["display"].as_str().unwrap_or("")) + }); + + let _ = display2; // 不在此 closure 内使用 + Ok(Some(members)) + }).await??; + + if let Some(members) = members_opt { + return Ok(json!({ + "chat": display, + "username": username, + "count": members.len(), + "members": members, + })); + } + } + + // 降级路径：从消息记录中聚合发言过的成员 + let tables = find_msg_tables(db, names, &username).await?; + if tables.is_empty() { + return Ok(json!({ + "chat": display, + "username": username, + "count": 0, + "members": [], + })); + } + + let mut sender_set: std::collections::HashSet = std::collections::HashSet::new(); + for (db_path, table_name) in &tables { + let path = db_path.clone(); + let tname = table_name.clone(); + let uname = username.clone(); + + let senders: Vec = tokio::task::spawn_blocking(move || { + let conn = Connection::open(&path)?; + let id2u = load_id2u(&conn); + let mut stmt = conn.prepare(&format!( + "SELECT DISTINCT real_sender_id FROM [{}] WHERE real_sender_id > 0", tname + ))?; + let ids: Vec = stmt.query_map([], |row| row.get(0))? + .filter_map(|r| r.ok()) + .collect(); + let senders: Vec = ids.iter() + .filter_map(|id| id2u.get(id)) + .filter(|u| *u != &uname) + .cloned() + .collect(); + Ok::<_, anyhow::Error>(senders) + }).await??; + + sender_set.extend(senders); + } + + let mut members: Vec = sender_set.iter().map(|u| { + json!({ + "username": u, + "display": names_map.get(u).cloned().unwrap_or_else(|| u.clone()), + "is_owner": false, + }) + }).collect(); + members.sort_by(|a, b| { + a["display"].as_str().unwrap_or("").cmp(b["display"].as_str().unwrap_or("")) + }); + + Ok(json!({ + "chat": display, + "username": username, + "count": members.len(), + "members": members, + })) +} + +/// 查询新消息：以 session.db 的 last_timestamp 作为 inbox 索引， +/// 只查询 last_timestamp > state[username] 的会话，精确且高效 +pub async fn q_new_messages( + db: &DbCache, + names: &Names, + state: Option>, + limit: usize, +) -> Result { + // 首次运行（state=None）或未见过的会话，用 24h 前作为起点， + // 避免第一次运行时把全量历史消息涌入 + let fallback_ts = chrono::Utc::now().timestamp() - 86400; + + // 1. 从 session.db 读取所有会话的当前 last_timestamp + let session_path = db.get("session/session.db").await? + .context("无法解密 session.db")?; + + let all_sessions: Vec<(String, i64)> = tokio::task::spawn_blocking(move || { + let conn = Connection::open(&session_path)?; + let mut stmt = conn.prepare( + "SELECT username, last_timestamp FROM SessionTable WHERE last_timestamp > 0" + )?; + let rows = stmt.query_map([], |row| { + Ok((row.get::<_, String>(0)?, row.get::<_, i64>(1).unwrap_or(0))) + })? + .collect::>>()?; + Ok::<_, anyhow::Error>(rows) + }).await??; + + // 2. 记录 session.db 的当前快照（用于构建 new_state 基础） + let session_ts_map: HashMap = all_sessions.iter() + .map(|(u, ts)| (u.clone(), *ts)) + .collect(); + + // 3. 找出有新消息的会话 + // 不在 state 中的会话（首次运行或新会话）以 fallback_ts 为基准 + let changed: Vec<(String, i64)> = all_sessions.into_iter() + .filter(|(uname, ts)| { + let last_known = state.as_ref() + .and_then(|m| m.get(uname)) + .copied() + .unwrap_or(fallback_ts); + *ts > last_known + }) + .collect(); + + if changed.is_empty() { + return Ok(json!({ + "count": 0, + "messages": [], + "new_state": session_ts_map, + })); + } + + // 4. 只查询有新消息的会话的消息表 + // per_table_limit 取 limit*5 防止单表截断，最终由全局 truncate 收尾 + let per_table_limit = limit.saturating_mul(5).max(200); + let mut all_msgs: Vec = Vec::new(); + + for (uname, _) in &changed { + let since_ts = state.as_ref() + .and_then(|m| m.get(uname)) + .copied() + .unwrap_or(fallback_ts); + let tables = find_msg_tables(db, names, uname).await?; + if tables.is_empty() { continue; } + + let display = names.display(uname); + let is_group = uname.contains("@chatroom"); + + for (db_path, table_name) in &tables { + let path = db_path.clone(); + let tname = table_name.clone(); + let uname2 = uname.clone(); + let display2 = display.clone(); + let names_map = names.map.clone(); + let tname_for_log = tname.clone(); + + let msgs: Vec = match tokio::task::spawn_blocking(move || { + let conn = Connection::open(&path)?; + let id2u = load_id2u(&conn); + + let sql = format!( + "SELECT local_id, local_type, create_time, real_sender_id, + message_content, WCDB_CT_message_content + FROM [{}] WHERE create_time > ? ORDER BY create_time ASC LIMIT ?", + tname + ); + let rows: Vec<_> = conn.prepare(&sql) + .and_then(|mut stmt| { + stmt.query_map( + rusqlite::params![since_ts, per_table_limit as i64], + |row| Ok(( + row.get::<_, i64>(0)?, + row.get::<_, i64>(1)?, + row.get::<_, i64>(2)?, + row.get::<_, i64>(3)?, + get_content_bytes(row, 4), + row.get::<_, i64>(5).unwrap_or(0), + )), + ).map(|it| it.filter_map(|r| r.ok()).collect()) + }) + .unwrap_or_default(); + + let mut result = Vec::new(); + for (local_id, local_type, ts, real_sender_id, content_bytes, ct) in rows { + let content = decompress_message(&content_bytes, ct); + let sender = sender_label(real_sender_id, &content, is_group, &uname2, &id2u, &names_map); + let text = fmt_content(local_id, local_type, &content, is_group); + result.push(json!({ + "chat": display2, + "username": uname2, + "is_group": is_group, + "timestamp": ts, + "time": fmt_time(ts, "%Y-%m-%d %H:%M"), + "sender": sender, + "content": text, + "type": fmt_type(local_type), + })); + } + Ok::<_, anyhow::Error>(result) + }).await { + Ok(Ok(v)) => v, + Ok(Err(e)) => { eprintln!("[new-messages] skip {}: {}", tname_for_log, e); continue; } + Err(e) => { eprintln!("[new-messages] task error: {}", e); continue; } + }; + + all_msgs.extend(msgs); + } + } + + all_msgs.sort_by_key(|m| m["timestamp"].as_i64().unwrap_or(0)); + all_msgs.truncate(limit); + + // 5. 重建 new_state，防止全局 limit 截断导致消息永久丢失： + // - 未变化的会话：沿用 session.db 的 last_timestamp + // - 变化但全被截断（无消息在最终结果中）：保留旧 since_ts，下次重试 + // - 变化且有消息返回：推进到该会话在结果中的最大 timestamp + let mut new_state = session_ts_map; + // 先把 changed 会话重置回旧 since_ts + for (uname, _) in &changed { + let old_ts = state.as_ref() + .and_then(|m| m.get(uname)) + .copied() + .unwrap_or(fallback_ts); + new_state.insert(uname.clone(), old_ts); + } + // 再根据实际返回的消息向前推进 + for m in &all_msgs { + if let (Some(uname), Some(ts)) = (m["username"].as_str(), m["timestamp"].as_i64()) { + let e = new_state.entry(uname.to_string()).or_insert(0); + if ts > *e { *e = ts; } + } + } + + Ok(json!({ + "count": all_msgs.len(), + "messages": all_msgs, + "new_state": new_state, + })) +} + +/// 查询收藏内容（favorite/favorite.db 的 fav_db_item 表） +pub async fn q_favorites( + db: &DbCache, + limit: usize, + fav_type: Option, + query: Option, +) -> Result { + let path = db.get("favorite/favorite.db").await? + .context("找不到 favorite.db，请确认微信数据目录")?; + + let rows: Vec = tokio::task::spawn_blocking(move || { + let conn = Connection::open(&path)?; + + let mut clauses: Vec<&'static str> = Vec::new(); + let mut params: Vec> = Vec::new(); + + if let Some(t) = fav_type { + clauses.push("type = ?"); + params.push(Box::new(t)); + } + let like_str: Option = query.map(|q| { + let esc = q.replace('\\', "\\\\").replace('%', "\\%").replace('_', "\\_"); + format!("%{}%", esc) + }); + if let Some(ref s) = like_str { + clauses.push("content LIKE ? ESCAPE '\\'"); + params.push(Box::new(s.clone())); + } + + let where_clause = if clauses.is_empty() { + String::new() + } else { + format!("WHERE {}", clauses.join(" AND ")) + }; + params.push(Box::new(limit as i64)); + + let sql = format!( + "SELECT local_id, type, update_time, content, fromusr, realchatname + FROM fav_db_item {} ORDER BY update_time DESC LIMIT ?", + where_clause + ); + + let params_ref: Vec<&dyn rusqlite::types::ToSql> = params.iter().map(|p| p.as_ref()).collect(); + let mut stmt = conn.prepare(&sql)?; + let rows: Vec = stmt.query_map(params_ref.as_slice(), |row| { + Ok(( + row.get::<_, i64>(0).unwrap_or(0), + row.get::<_, i64>(1).unwrap_or(0), + row.get::<_, i64>(2).unwrap_or(0), + row.get::<_, String>(3).unwrap_or_default(), + row.get::<_, String>(4).unwrap_or_default(), + row.get::<_, String>(5).unwrap_or_default(), + )) + })? + .filter_map(|r| r.ok()) + .map(|(local_id, ftype, ts, content, fromusr, chatname)| { + let type_str = match ftype { + 1 => "文本", + 2 => "图片", + 5 => "文章", + 19 => "名片", + 20 => "视频", + _ => "其他", + }; + // 安全截断（按 Unicode 字符而非字节） + let preview: String = content.chars().take(100).collect(); + let preview = if content.chars().count() > 100 { + format!("{}...", preview) + } else { + preview + }; + // WeChat 部分版本的 update_time 为毫秒，10位以上判定为毫秒后转秒 + let ts_secs = if ts > 9_999_999_999 { ts / 1000 } else { ts }; + json!({ + "id": local_id, + "type": type_str, + "type_num": ftype, + "time": fmt_time(ts_secs, "%Y-%m-%d %H:%M"), + "timestamp": ts_secs, + "preview": preview, + "from": fromusr, + "chat": chatname, + }) + }) + .collect(); + + Ok::<_, anyhow::Error>(rows) + }).await??; + + Ok(json!({ + "count": rows.len(), + "items": rows, + })) +} + +/// 聊天统计：消息总数、类型分布、发言排行、24小时分布 +pub async fn q_stats( + db: &DbCache, + names: &Names, + chat: &str, + since: Option, + until: Option, +) -> Result { + let username = resolve_username(chat, names) + .with_context(|| format!("找不到联系人: {}", chat))?; + let display = names.display(&username); + let is_group = username.contains("@chatroom"); + + let tables = find_msg_tables(db, names, &username).await?; + if tables.is_empty() { + anyhow::bail!("找不到 {} 的消息记录", display); + } + + // 跨所有分片 DB 累计统计 + let mut total: i64 = 0; + let mut type_counts: HashMap = HashMap::new(); + let mut sender_counts: HashMap = HashMap::new(); + let mut hour_counts = [0i64; 24]; + + for (db_path, table_name) in &tables { + let path = db_path.clone(); + let tname = table_name.clone(); + let uname = username.clone(); + let is_group2 = is_group; + let names_map = names.map.clone(); + + // 用 SQL GROUP BY 在数据库侧聚合，避免把全量消息内容加载进内存 + let result: (i64, HashMap, HashMap, [i64; 24]) = + tokio::task::spawn_blocking(move || { + let conn = Connection::open(&path)?; + let id2u = load_id2u(&conn); + + let mut clauses = Vec::new(); + let mut params: Vec> = Vec::new(); + if let Some(s) = since { + clauses.push("create_time >= ?"); + params.push(Box::new(s)); + } + if let Some(u) = until { + clauses.push("create_time <= ?"); + params.push(Box::new(u)); + } + let where_clause = if clauses.is_empty() { + String::new() + } else { + format!("WHERE {}", clauses.join(" AND ")) + }; + let params_ref: Vec<&dyn rusqlite::types::ToSql> = + params.iter().map(|p| p.as_ref()).collect(); + + // 1. 总数 + let count: i64 = conn.query_row( + &format!("SELECT COUNT(*) FROM [{}] {}", tname, where_clause), + params_ref.as_slice(), + |row| row.get(0), + ).unwrap_or(0); + + // 2. 类型分布：SQL GROUP BY，不加载消息内容 + let type_sql = format!( + "SELECT (local_type & 0xFFFFFFFF), COUNT(*) FROM [{}] {} GROUP BY (local_type & 0xFFFFFFFF)", + tname, where_clause + ); + let mut type_c: HashMap = HashMap::new(); + if let Ok(mut stmt) = conn.prepare(&type_sql) { + let _ = stmt.query_map(params_ref.as_slice(), |row| { + Ok((row.get::<_, i64>(0)?, row.get::<_, i64>(1)?)) + }).map(|rows| { + for r in rows.flatten() { + *type_c.entry(fmt_type(r.0)).or_insert(0) += r.1; + } + }); + } + + // 3. 小时分布：只取时间戳，不加载消息内容 + let hour_sql = format!( + "SELECT create_time FROM [{}] {}", + tname, where_clause + ); + let mut hour_c = [0i64; 24]; + if let Ok(mut stmt) = conn.prepare(&hour_sql) { + let _ = stmt.query_map(params_ref.as_slice(), |row| row.get::<_, i64>(0)) + .map(|rows| { + for ts in rows.flatten() { + if let Some(dt) = Local.timestamp_opt(ts, 0).single() { + let h = dt.hour() as usize; + if h < 24 { hour_c[h] += 1; } + } + } + }); + } + + // 4. 发言排行：只取 real_sender_id，不加载消息内容 + // where_clause 可能已含 WHERE，用 AND 追加而非重复写 WHERE + let sender_filter = if where_clause.is_empty() { + "WHERE real_sender_id > 0".to_string() + } else { + format!("{} AND real_sender_id > 0", where_clause) + }; + let sender_sql = format!( + "SELECT real_sender_id, COUNT(*) FROM [{}] {} GROUP BY real_sender_id", + tname, sender_filter + ); + let mut sender_c: HashMap = HashMap::new(); + if is_group2 { + if let Ok(mut stmt) = conn.prepare(&sender_sql) { + let _ = stmt.query_map(params_ref.as_slice(), |row| { + Ok((row.get::<_, i64>(0)?, row.get::<_, i64>(1)?)) + }).map(|rows| { + for (id, cnt) in rows.flatten() { + if let Some(u) = id2u.get(&id) { + if u != &uname { + let name = names_map.get(u).cloned().unwrap_or_else(|| u.clone()); + *sender_c.entry(name).or_insert(0) += cnt; + } + } + } + }); + } + } + + Ok::<_, anyhow::Error>((count, type_c, sender_c, hour_c)) + }).await??; + + let (count, type_c, sender_c, hour_c) = result; + total += count; + for (k, v) in type_c { *type_counts.entry(k).or_insert(0) += v; } + for (k, v) in sender_c { *sender_counts.entry(k).or_insert(0) += v; } + for i in 0..24 { hour_counts[i] += hour_c[i]; } + } + + // 类型分布，按数量降序 + let mut by_type: Vec = type_counts.iter() + .map(|(t, c)| json!({ "type": t, "count": c })) + .collect(); + by_type.sort_by_key(|v| std::cmp::Reverse(v["count"].as_i64().unwrap_or(0))); + + // 发言排行，Top 10 + let mut top_senders: Vec = sender_counts.iter() + .map(|(s, c)| json!({ "sender": s, "count": c })) + .collect(); + top_senders.sort_by_key(|v| std::cmp::Reverse(v["count"].as_i64().unwrap_or(0))); + top_senders.truncate(10); + + // 24小时分布 + let by_hour: Vec = hour_counts.iter().enumerate() + .map(|(h, c)| json!({ "hour": h, "count": c })) + .collect(); + + Ok(json!({ + "chat": display, + "username": username, + "is_group": is_group, + "total": total, + "by_type": by_type, + "top_senders": top_senders, + "by_hour": by_hour, + })) +} + diff --git a/src/daemon/server.rs b/src/daemon/server.rs index 89d81f0..35eabe1 100644 --- a/src/daemon/server.rs +++ b/src/daemon/server.rs @@ -1,10 +1,8 @@ use anyhow::Result; use std::sync::Arc; -use std::time::Duration; use tokio::io::{AsyncBufReadExt, AsyncWriteExt, BufReader}; -use tokio::sync::broadcast; -use crate::ipc::{Request, Response, WatchEvent}; +use crate::ipc::{Request, Response}; use super::cache::DbCache; use super::query::Names; @@ -12,12 +10,11 @@ use super::query::Names; pub async fn serve( db: Arc, names: Arc>, - watch_tx: broadcast::Sender, ) -> Result<()> { #[cfg(unix)] - serve_unix(db, names, watch_tx).await?; + serve_unix(db, names).await?; #[cfg(windows)] - serve_windows(db, names, watch_tx).await?; + serve_windows(db, names).await?; Ok(()) } @@ -25,7 +22,6 @@ pub async fn serve( async fn serve_unix( db: Arc, names: Arc>, - watch_tx: broadcast::Sender, ) -> Result<()> { use tokio::net::UnixListener; let sock_path = crate::config::sock_path(); @@ -49,10 +45,9 @@ async fn serve_unix( let (stream, _) = listener.accept().await?; let db2 = Arc::clone(&db); let names2 = Arc::clone(&names); - let tx2 = watch_tx.clone(); tokio::spawn(async move { - if let Err(e) = handle_connection_unix(stream, db2, names2, tx2).await { + if let Err(e) = handle_connection_unix(stream, db2, names2).await { eprintln!("[server] 连接处理错误: {}", e); } }); @@ -64,7 +59,6 @@ async fn handle_connection_unix( stream: tokio::net::UnixStream, db: Arc, names: Arc>, - watch_tx: broadcast::Sender, ) -> Result<()> { let (reader, mut writer) = stream.into_split(); let mut lines = BufReader::new(reader).lines(); @@ -84,41 +78,8 @@ async fn handle_connection_unix( } }; - match req { - Request::Watch => { - // 流式模式：持续推送事件 - let mut rx = watch_tx.subscribe(); - let connected = WatchEvent::connected(); - writer.write_all(connected.to_json_line()?.as_bytes()).await?; - - loop { - tokio::select! { - event = rx.recv() => { - match event { - Ok(e) => { - if writer.write_all(e.to_json_line()?.as_bytes()).await.is_err() { - break; - } - } - Err(broadcast::error::RecvError::Lagged(_)) => continue, - Err(_) => break, - } - } - _ = tokio::time::sleep(Duration::from_secs(30)) => { - // 心跳 - let hb = WatchEvent::heartbeat(); - if writer.write_all(hb.to_json_line()?.as_bytes()).await.is_err() { - break; - } - } - } - } - } - other => { - let resp = dispatch(other, &db, &names).await; - writer.write_all(resp.to_json_line()?.as_bytes()).await?; - } - } + let resp = dispatch(req, &db, &names).await; + writer.write_all(resp.to_json_line()?.as_bytes()).await?; Ok(()) } @@ -126,7 +87,6 @@ async fn handle_connection_unix( async fn serve_windows( db: Arc, names: Arc>, - watch_tx: broadcast::Sender, ) -> Result<()> { use interprocess::local_socket::{ tokio::prelude::*, GenericNamespaced, ListenerOptions, @@ -143,10 +103,9 @@ async fn serve_windows( let conn = listener.accept().await?; let db2 = Arc::clone(&db); let names2 = Arc::clone(&names); - let tx2 = watch_tx.clone(); tokio::spawn(async move { - if let Err(e) = handle_connection_generic(conn, db2, names2, tx2).await { + if let Err(e) = handle_connection_generic(conn, db2, names2).await { eprintln!("[server] 连接处理错误: {}", e); } }); @@ -164,7 +123,6 @@ async fn dispatch( match req { Ping => Response::ok(serde_json::json!({ "pong": true })), Sessions { limit } => { - // 在 await 前获取并复制所需数据，避免 RwLockGuard 跨 await let names_snapshot = match clone_names(names) { Ok(n) => n, Err(e) => return Response::err(e), @@ -174,22 +132,22 @@ async fn dispatch( Err(e) => Response::err(e.to_string()), } } - History { chat, limit, offset, since, until } => { + History { chat, limit, offset, since, until, msg_type } => { let names_snapshot = match clone_names(names) { Ok(n) => n, Err(e) => return Response::err(e), }; - match query::q_history(db, &names_snapshot, &chat, limit, offset, since, until).await { + match query::q_history(db, &names_snapshot, &chat, limit, offset, since, until, msg_type).await { Ok(v) => Response::ok(v), Err(e) => Response::err(e.to_string()), } } - Search { keyword, chats, limit, since, until } => { + Search { keyword, chats, limit, since, until, msg_type } => { let names_snapshot = match clone_names(names) { Ok(n) => n, Err(e) => return Response::err(e), }; - match query::q_search(db, &names_snapshot, &keyword, chats, limit, since, until).await { + match query::q_search(db, &names_snapshot, &keyword, chats, limit, since, until, msg_type).await { Ok(v) => Response::ok(v), Err(e) => Response::err(e.to_string()), } @@ -204,7 +162,52 @@ async fn dispatch( Err(e) => Response::err(e.to_string()), } } - Watch => Response::err("Watch 命令不应通过 dispatch 处理"), + Unread { limit } => { + let names_snapshot = match clone_names(names) { + Ok(n) => n, + Err(e) => return Response::err(e), + }; + match query::q_unread(db, &names_snapshot, limit).await { + Ok(v) => Response::ok(v), + Err(e) => Response::err(e.to_string()), + } + } + Members { chat } => { + let names_snapshot = match clone_names(names) { + Ok(n) => n, + Err(e) => return Response::err(e), + }; + match query::q_members(db, &names_snapshot, &chat).await { + Ok(v) => Response::ok(v), + Err(e) => Response::err(e.to_string()), + } + } + NewMessages { state, limit } => { + let names_snapshot = match clone_names(names) { + Ok(n) => n, + Err(e) => return Response::err(e), + }; + match query::q_new_messages(db, &names_snapshot, state, limit).await { + Ok(v) => Response::ok(v), + Err(e) => Response::err(e.to_string()), + } + } + Favorites { limit, fav_type, query } => { + match query::q_favorites(db, limit, fav_type, query).await { + Ok(v) => Response::ok(v), + Err(e) => Response::err(e.to_string()), + } + } + Stats { chat, since, until } => { + let names_snapshot = match clone_names(names) { + Ok(n) => n, + Err(e) => return Response::err(e), + }; + match query::q_stats(db, &names_snapshot, &chat, since, until).await { + Ok(v) => Response::ok(v), + Err(e) => Response::err(e.to_string()), + } + } } } diff --git a/src/ipc.rs b/src/ipc.rs index 130ed22..cf21993 100644 --- a/src/ipc.rs +++ b/src/ipc.rs @@ -1,3 +1,4 @@ +use std::collections::HashMap; use serde::{Deserialize, Serialize}; use serde_json::Value; @@ -20,6 +21,8 @@ pub enum Request { since: Option, #[serde(skip_serializing_if = "Option::is_none")] until: Option, + #[serde(skip_serializing_if = "Option::is_none")] + msg_type: Option, }, Search { keyword: String, @@ -31,6 +34,8 @@ pub enum Request { since: Option, #[serde(skip_serializing_if = "Option::is_none")] until: Option, + #[serde(skip_serializing_if = "Option::is_none")] + msg_type: Option, }, Contacts { #[serde(skip_serializing_if = "Option::is_none")] @@ -38,7 +43,38 @@ pub enum Request { #[serde(default = "default_limit_50")] limit: usize, }, - Watch, + Unread { + #[serde(default = "default_limit_20")] + limit: usize, + }, + Members { + chat: String, + }, + NewMessages { + /// 上次检查时各会话的 last_timestamp 快照（username -> ts） + /// None 表示首次运行，会返回 new_state 供下次使用 + #[serde(skip_serializing_if = "Option::is_none")] + state: Option>, + #[serde(default = "default_limit_200")] + limit: usize, + }, + Stats { + chat: String, + #[serde(skip_serializing_if = "Option::is_none")] + since: Option, + #[serde(skip_serializing_if = "Option::is_none")] + until: Option, + }, + Favorites { + #[serde(default = "default_limit_50")] + limit: usize, + /// 类型过滤：1=文本,2=图片,5=文章,19=名片,20=视频 + #[serde(skip_serializing_if = "Option::is_none")] + fav_type: Option, + /// 内容关键词搜索 + #[serde(skip_serializing_if = "Option::is_none")] + query: Option, + }, } @@ -69,48 +105,4 @@ impl Response { fn default_limit_20() -> usize { 20 } fn default_limit_50() -> usize { 50 } - -/// Watch 事件（daemon -> CLI 流式推送） -#[derive(Debug, Clone, Serialize, Deserialize)] -pub struct WatchEvent { - pub event: String, - #[serde(skip_serializing_if = "Option::is_none")] - pub time: Option, - #[serde(skip_serializing_if = "Option::is_none")] - pub chat: Option, - #[serde(skip_serializing_if = "Option::is_none")] - pub username: Option, - #[serde(skip_serializing_if = "Option::is_none")] - pub is_group: Option, - #[serde(skip_serializing_if = "Option::is_none")] - pub sender: Option, - #[serde(skip_serializing_if = "Option::is_none")] - pub content: Option, - #[serde(rename = "type", skip_serializing_if = "Option::is_none")] - pub msg_type: Option, - #[serde(skip_serializing_if = "Option::is_none")] - pub timestamp: Option, -} - -impl WatchEvent { - pub fn connected() -> Self { - Self { - event: "connected".into(), - time: None, chat: None, username: None, is_group: None, - sender: None, content: None, msg_type: None, timestamp: None, - } - } - - pub fn heartbeat() -> Self { - Self { - event: "heartbeat".into(), - time: None, chat: None, username: None, is_group: None, - sender: None, content: None, msg_type: None, timestamp: None, - } - } - - pub fn to_json_line(&self) -> anyhow::Result { - let s = serde_json::to_string(self)?; - Ok(s + "\n") - } -} +fn default_limit_200() -> usize { 200 } diff --git a/src/scanner/macos.rs b/src/scanner/macos.rs index ec7e988..bc48dfd 100644 --- a/src/scanner/macos.rs +++ b/src/scanner/macos.rs @@ -246,7 +246,7 @@ fn scan_region( /// 在缓冲区中搜索 x'<96个十六进制字符>' 模式 /// /// 格式：x'<64hex(key)><32hex(salt)>'（总计 99 字节） -fn search_pattern(buf: &[u8], results: &mut Vec<(String, String)>) { +pub(crate) fn search_pattern(buf: &[u8], results: &mut Vec<(String, String)>) { let total = HEX_PATTERN_LEN + 3; // x' + 96 hex + ' if buf.len() < total { return; @@ -291,3 +291,152 @@ fn search_pattern(buf: &[u8], results: &mut Vec<(String, String)>) { i += total; } } + +#[cfg(test)] +mod tests { + use super::*; + + /// 构造一条合法的 x'' 模式字节串 + fn make_pattern(key: &[u8; 64], salt: &[u8; 32]) -> Vec { + let mut v = vec![b'x', b'\'']; + v.extend_from_slice(key); + v.extend_from_slice(salt); + v.push(b'\''); + v + } + + #[test] + fn test_is_hex_char_valid() { + for c in b'0'..=b'9' { assert!(is_hex_char(c), "digit {}", c as char); } + for c in b'a'..=b'f' { assert!(is_hex_char(c), "lower {}", c as char); } + for c in b'A'..=b'F' { assert!(is_hex_char(c), "upper {}", c as char); } + } + + #[test] + fn test_is_hex_char_invalid() { + for c in [b'g', b'G', b'x', b'\'', b' ', b'\0', b'z', b'Z'] { + assert!(!is_hex_char(c), "expected non-hex: {}", c as char); + } + } + + #[test] + fn test_search_pattern_basic() { + let key = [b'a'; 64]; + let salt = [b'b'; 32]; + let buf = make_pattern(&key, &salt); + let mut results = Vec::new(); + search_pattern(&buf, &mut results); + assert_eq!(results.len(), 1); + assert_eq!(results[0].0, "a".repeat(64)); + assert_eq!(results[0].1, "b".repeat(32)); + } + + #[test] + fn test_search_pattern_uppercase_lowercased() { + // 大写十六进制字符应被统一转为小写 + let key = [b'A'; 64]; + let salt = [b'B'; 32]; + let buf = make_pattern(&key, &salt); + let mut results = Vec::new(); + search_pattern(&buf, &mut results); + assert_eq!(results.len(), 1); + assert_eq!(results[0].0, "a".repeat(64)); + assert_eq!(results[0].1, "b".repeat(32)); + } + + #[test] + fn test_search_pattern_not_all_hex() { + // 96 个十六进制字符中有一个非法字符 → 不匹配 + let mut buf = vec![b'x', b'\'']; + buf.extend_from_slice(&[b'a'; 95]); + buf.push(b'g'); // 'g' 不是合法十六进制字符 + buf.push(b'\''); + let mut results = Vec::new(); + search_pattern(&buf, &mut results); + assert!(results.is_empty()); + } + + #[test] + fn test_search_pattern_wrong_closing_quote() { + // 结尾引号错误 → 不匹配 + let mut buf = vec![b'x', b'\'']; + buf.extend_from_slice(&[b'a'; 96]); + buf.push(b'"'); // 应为 b'\'' + let mut results = Vec::new(); + search_pattern(&buf, &mut results); + assert!(results.is_empty()); + } + + #[test] + fn test_search_pattern_dedup() { + // 相同模式出现两次 → 只保留一条 + let key = [b'1'; 64]; + let salt = [b'2'; 32]; + let pattern = make_pattern(&key, &salt); + let mut buf = pattern.clone(); + buf.extend_from_slice(&pattern); + let mut results = Vec::new(); + search_pattern(&buf, &mut results); + assert_eq!(results.len(), 1); + } + + #[test] + fn test_search_pattern_multiple_distinct() { + // 两个不同的合法模式 → 各自独立捕获 + let key1 = [b'a'; 64]; let salt1 = [b'b'; 32]; + let key2 = [b'c'; 64]; let salt2 = [b'd'; 32]; + let mut buf = make_pattern(&key1, &salt1); + buf.extend_from_slice(&make_pattern(&key2, &salt2)); + let mut results = Vec::new(); + search_pattern(&buf, &mut results); + assert_eq!(results.len(), 2); + let keys: Vec<&str> = results.iter().map(|(k, _)| k.as_str()).collect(); + assert!(keys.contains(&"a".repeat(64).as_str())); + assert!(keys.contains(&"c".repeat(64).as_str())); + } + + #[test] + fn test_search_pattern_embedded_in_garbage() { + // 模式夹在垃圾字节中间，仍应找到 + let mut buf = vec![0xFFu8; 50]; + let key = [b'e'; 64]; + let salt = [b'f'; 32]; + buf.extend_from_slice(&make_pattern(&key, &salt)); + buf.extend_from_slice(&[0x00u8; 50]); + let mut results = Vec::new(); + search_pattern(&buf, &mut results); + assert_eq!(results.len(), 1); + } + + #[test] + fn test_search_pattern_too_short() { + // 缓冲区太小，无法容纳完整模式 + let buf = [b'x', b'\'', b'a', b'b']; + let mut results = Vec::new(); + search_pattern(&buf, &mut results); + assert!(results.is_empty()); + } + + #[test] + fn test_search_pattern_empty_buf() { + let mut results = Vec::new(); + search_pattern(&[], &mut results); + assert!(results.is_empty()); + } + + #[test] + fn test_search_pattern_real_hex_mix() { + // 合法的混合大小写十六进制（0-9, a-f, A-F） + let mut key = [b'0'; 64]; + for (i, c) in b"0123456789abcdefABCDEF0123456789abcdef0123456789abcdef01234567".iter().enumerate() { + if i < 64 { key[i] = *c; } + } + let salt = [b'9'; 32]; + let buf = make_pattern(&key, &salt); + let mut results = Vec::new(); + search_pattern(&buf, &mut results); + assert_eq!(results.len(), 1); + // 结果应全小写 + assert!(results[0].0.chars().all(|c| c.is_ascii_lowercase() || c.is_ascii_digit())); + } +} diff --git a/src/scanner/mod.rs b/src/scanner/mod.rs index abed70c..0d76a50 100644 --- a/src/scanner/mod.rs +++ b/src/scanner/mod.rs @@ -82,3 +82,161 @@ mod hex { bytes.iter().map(|b| format!("{:02x}", b)).collect() } } + +#[cfg(test)] +mod tests { + use super::*; + use std::fs; + + /// 创建一个进程唯一的临时目录（测试用），返回路径；测试结束后调用方负责删除 + fn make_temp_dir(label: &str) -> std::path::PathBuf { + let mut p = std::env::temp_dir(); + // 用 label + thread id 保证同进程内并发测试不冲突 + p.push(format!("wx-cli-test-{}-{:?}", label, std::thread::current().id())); + fs::create_dir_all(&p).unwrap(); + p + } + + // ── read_db_salt ────────────────────────────────────────────────────────── + + #[test] + fn test_read_db_salt_plaintext_sqlite() { + let dir = make_temp_dir("salt-plain"); + let path = dir.join("plain.db"); + // 明文 SQLite 头：前 15 字节是 "SQLite format 3" + let mut content = b"SQLite format 3\x00".to_vec(); + content.extend_from_slice(&[0u8; 100]); + fs::write(&path, &content).unwrap(); + + assert!(read_db_salt(&path).is_none(), "明文 SQLite 应返回 None"); + fs::remove_dir_all(&dir).ok(); + } + + #[test] + fn test_read_db_salt_encrypted() { + let dir = make_temp_dir("salt-enc"); + let path = dir.join("enc.db"); + // 非 SQLite 头 → 视为加密数据库，取前 16 字节作为 salt + let header: [u8; 16] = [ + 0xde, 0xad, 0xbe, 0xef, 0x01, 0x02, 0x03, 0x04, + 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, + ]; + fs::write(&path, &header).unwrap(); + + let salt = read_db_salt(&path).expect("加密 DB 应返回 Some"); + assert_eq!(salt, "deadbeef0102030405060708090a0b0c"); + fs::remove_dir_all(&dir).ok(); + } + + #[test] + fn test_read_db_salt_too_short() { + let dir = make_temp_dir("salt-short"); + let path = dir.join("short.db"); + fs::write(&path, b"tooshort").unwrap(); // < 16 bytes + + assert!(read_db_salt(&path).is_none(), "文件太短应返回 None"); + fs::remove_dir_all(&dir).ok(); + } + + #[test] + fn test_read_db_salt_nonexistent() { + assert!(read_db_salt(Path::new("/nonexistent/surely/not/here.db")).is_none()); + } + + #[test] + fn test_read_db_salt_exactly_16_bytes() { + let dir = make_temp_dir("salt-16"); + let path = dir.join("exact.db"); + let header = [0xabu8; 16]; + fs::write(&path, &header).unwrap(); + + let salt = read_db_salt(&path).unwrap(); + // 0xab × 16 → "ab" × 16 = 32 chars + assert_eq!(salt, "ab".repeat(16)); + fs::remove_dir_all(&dir).ok(); + } + + // ── collect_db_salts ────────────────────────────────────────────────────── + + #[test] + fn test_collect_db_salts_empty_dir() { + let dir = make_temp_dir("collect-empty"); + let salts = collect_db_salts(&dir); + assert!(salts.is_empty()); + fs::remove_dir_all(&dir).ok(); + } + + #[test] + fn test_collect_db_salts_skips_plaintext_sqlite() { + let dir = make_temp_dir("collect-plain"); + let mut content = b"SQLite format 3\x00".to_vec(); + content.extend_from_slice(&[0u8; 100]); + fs::write(dir.join("plain.db"), &content).unwrap(); + + assert!(collect_db_salts(&dir).is_empty(), "明文 SQLite 应被跳过"); + fs::remove_dir_all(&dir).ok(); + } + + #[test] + fn test_collect_db_salts_finds_encrypted() { + let dir = make_temp_dir("collect-enc"); + let header = [0x11u8; 16]; + fs::write(dir.join("msg.db"), &header).unwrap(); + + let salts = collect_db_salts(&dir); + assert_eq!(salts.len(), 1); + assert_eq!(salts[0].0, "11".repeat(16)); // 0x11 × 16 → "11" × 16 + assert_eq!(salts[0].1, "msg.db"); + fs::remove_dir_all(&dir).ok(); + } + + #[test] + fn test_collect_db_salts_recursive() { + let dir = make_temp_dir("collect-rec"); + let subdir = dir.join("sub"); + fs::create_dir_all(&subdir).unwrap(); + + let header = [0xaau8; 16]; + fs::write(dir.join("root.db"), &header).unwrap(); + fs::write(subdir.join("nested.db"), &header).unwrap(); + fs::write(dir.join("ignored.txt"), b"text file").unwrap(); + + let salts = collect_db_salts(&dir); + assert_eq!(salts.len(), 2, "应递归找到 2 个加密 .db"); + + let names: Vec<&str> = salts.iter().map(|(_, n)| n.as_str()).collect(); + assert!(names.contains(&"root.db")); + assert!(names.contains(&"sub/nested.db")); + fs::remove_dir_all(&dir).ok(); + } + + #[test] + fn test_collect_db_salts_ignores_non_db_extensions() { + let dir = make_temp_dir("collect-ext"); + let header = [0xbbu8; 16]; + fs::write(dir.join("data.txt"), &header).unwrap(); + fs::write(dir.join("data.json"), &header).unwrap(); + fs::write(dir.join("data.sqlite"), &header).unwrap(); + + assert!(collect_db_salts(&dir).is_empty(), "非 .db 文件应被忽略"); + fs::remove_dir_all(&dir).ok(); + } + + #[test] + fn test_collect_db_salts_multiple_files_unique_salts() { + let dir = make_temp_dir("collect-multi"); + fs::write(dir.join("a.db"), &[0x11u8; 16]).unwrap(); + fs::write(dir.join("b.db"), &[0x22u8; 16]).unwrap(); + fs::write(dir.join("c.db"), &[0x33u8; 16]).unwrap(); + + let salts = collect_db_salts(&dir); + assert_eq!(salts.len(), 3); + + let salt_vals: std::collections::HashSet<&str> = + salts.iter().map(|(s, _)| s.as_str()).collect(); + assert!(salt_vals.contains("11".repeat(16).as_str())); + assert!(salt_vals.contains("22".repeat(16).as_str())); + assert!(salt_vals.contains("33".repeat(16).as_str())); + fs::remove_dir_all(&dir).ok(); + } +}