fix: improve chat ID parsing in Save method and fallback to configured chat_id

client/bot/handlers/add_task.go

@@ -3,6 +3,7 @@ package handlers
 import (
 	"errors"
 	"fmt"
+	"path"
 	"strings"
 
 	"github.com/celestix/gotgproto/dispatcher"
@@ -11,6 +12,7 @@ import (
 	"github.com/gotd/td/tg"
 	"github.com/krau/SaveAny-Bot/client/bot/handlers/utils/msgelem"
 	"github.com/krau/SaveAny-Bot/client/bot/handlers/utils/shortcut"
+	"github.com/krau/SaveAny-Bot/common/utils/fsutil"
 	"github.com/krau/SaveAny-Bot/database"
 	"github.com/krau/SaveAny-Bot/pkg/enums/tasktype"
 	"github.com/krau/SaveAny-Bot/pkg/tcbdata"
@@ -74,6 +76,9 @@ func handleAddCallback(ctx *ext.Context, update *ext.Update) error {
 	case tasktype.TaskTypeTphpics:
 		return shortcut.CreateAndAddtelegraphWithEdit(ctx, userID, data.TphPageNode, data.TphDirPath, data.TphPics, selectedStorage, msgID)
 	case tasktype.TaskTypeParseditem:
+		if len(data.ParsedItem.Resources) > 1 {
+			dirPath = path.Join(dirPath, fsutil.NormalizePathname(data.ParsedItem.Title))
+		}
 		shortcut.CreateAndAddParsedTaskWithEdit(ctx, selectedStorage, dirPath, data.ParsedItem, msgID, userID)
 	default:
 		log.FromContext(ctx).Errorf("Unsupported task type: %s", data.TaskType)

client/bot/handlers/parse.go

@@ -11,6 +11,7 @@ import (
 	"github.com/gotd/td/tg"
 	"github.com/krau/SaveAny-Bot/client/bot/handlers/utils/msgelem"
 	"github.com/krau/SaveAny-Bot/client/bot/handlers/utils/shortcut"
+	"github.com/krau/SaveAny-Bot/common/utils/fsutil"
 	"github.com/krau/SaveAny-Bot/parsers"
 	"github.com/krau/SaveAny-Bot/pkg/enums/tasktype"
 	"github.com/krau/SaveAny-Bot/pkg/tcbdata"
@@ -106,5 +107,9 @@ func handleSilentSaveText(ctx *ext.Context, u *ext.Update) error {
 		logger.Errorf("Failed to send message: %s", err)
 		return dispatcher.EndGroups
 	}
-	return shortcut.CreateAndAddParsedTaskWithEdit(ctx, stor, "", item, msg.ID, userID)
+	dirPath := ""
+	if len(item.Resources) > 1 {
+		dirPath = fsutil.NormalizePathname(item.Title)
+	}
+	return shortcut.CreateAndAddParsedTaskWithEdit(ctx, stor, dirPath, item, msg.ID, userID)
 }

client/bot/handlers/register.go

@@ -112,7 +112,10 @@ func listenMediaMessageEvent(ch chan userclient.MediaMessageEvent) {
 			}
 			var dirPath string
 			if user.ApplyRule && user.Rules != nil {
-				matchedStorageName, matchedDirPath := ruleutil.ApplyRule(ctx, user.Rules, ruleutil.NewInput(file))
+				matched, matchedStorageName, matchedDirPath := ruleutil.ApplyRule(ctx, user.Rules, ruleutil.NewInput(file))
+				if !matched {
+					goto startCreateTask
+				}
 				dirPath = matchedDirPath.String()
 				if matchedStorageName.IsUsable() {
 					stor, err = storage.GetStorageByUserIDAndName(ctx, user.ChatID, matchedStorageName.String())
@@ -122,6 +125,7 @@ func listenMediaMessageEvent(ch chan userclient.MediaMessageEvent) {
 					}
 				}
 			}
+		startCreateTask:
 			storagePath := stor.JoinStoragePath(path.Join(dirPath, file.Name()))
 			injectCtx := tgutil.ExtWithContext(ctx.Context, ctx)
 			taskid := xid.New().String()

client/bot/handlers/utils/ruleutil/rule.go

@@ -48,9 +48,9 @@ func (m MatchedDirPath) NeedNewForAlbum() bool {
 	return m != "" && m == rule.RuleDirPathNewForAlbum
 }
 
-func ApplyRule(ctx context.Context, rules []database.Rule, inputs *ruleInput) (matchedStorageName matchedStorName, dirPath MatchedDirPath) {
+func ApplyRule(ctx context.Context, rules []database.Rule, inputs *ruleInput) (matched bool, matchedStorageName matchedStorName, dirPath MatchedDirPath) {
 	if inputs == nil || len(rules) == 0 {
-		return "", ""
+		return false, "", ""
 	}
 	logger := log.FromContext(ctx)
 	for _, ur := range rules {
@@ -106,5 +106,8 @@ func ApplyRule(ctx context.Context, rules []database.Rule, inputs *ruleInput) (m
 			}
 		}
 	}
-	return
+	if matchedStorageName != "" || dirPath != "" {
+		return true, matchedStorageName, dirPath
+	}
+	return false, "", ""
 }

client/bot/handlers/utils/shortcut/tftask.go

@@ -34,8 +34,13 @@ func CreateAndAddTGFileTaskWithEdit(ctx *ext.Context, userID int64, stor storage
 		return dispatcher.EndGroups
 	}
 	if user.ApplyRule && user.Rules != nil {
-		matchedStorageName, matchedDirPath := ruleutil.ApplyRule(ctx, user.Rules, ruleutil.NewInput(file))
-		dirPath = matchedDirPath.String()
+		matched, matchedStorageName, matchedDirPath := ruleutil.ApplyRule(ctx, user.Rules, ruleutil.NewInput(file))
+		if !matched {
+			goto startCreateTask
+		}
+		if matchedDirPath != "" {
+			dirPath = matchedDirPath.String()
+		}
 		if matchedStorageName.IsUsable() {
 			stor, err = storage.GetStorageByUserIDAndName(ctx, user.ChatID, matchedStorageName.String())
 			if err != nil {
@@ -48,7 +53,7 @@ func CreateAndAddTGFileTaskWithEdit(ctx *ext.Context, userID int64, stor storage
 			}
 		}
 	}
-
+startCreateTask:
 	storagePath := stor.JoinStoragePath(path.Join(dirPath, file.Name()))
 	injectCtx := tgutil.ExtWithContext(ctx.Context, ctx)
 	taskid := xid.New().String()
@@ -101,8 +106,10 @@ func CreateAndAddBatchTGFileTaskWithEdit(ctx *ext.Context, userID int64, stor st
 		if !useRule {
 			return stor.Name(), ruleutil.MatchedDirPath(dirPath)
 		}
-		storName, dirP := ruleutil.ApplyRule(ctx, user.Rules, ruleutil.NewInput(file))
-
+		matched, storName, dirP := ruleutil.ApplyRule(ctx, user.Rules, ruleutil.NewInput(file))
+		if !matched {
+			return stor.Name(), ruleutil.MatchedDirPath(dirPath)
+		}
 		storname := storName.String()
 		if !storName.IsUsable() {
 			storname = stor.Name()

common/utils/fsutil/fs.go

@@ -3,6 +3,8 @@ package fsutil
 import (
 	"os"
 	"path/filepath"
+	"strings"
+	"unicode"
 
 	"github.com/gabriel-vasile/mimetype"
 )
@@ -55,3 +57,21 @@ func CreateFile(fp string) (*File, error) {
 	}
 	return &File{File: file}, nil
 }
+
+func NormalizePathname(s string) string {
+	specials := `\/:*?"<>|` + "\n\r\t"
+	var builder strings.Builder
+	for _, ch := range s {
+		if strings.ContainsRune(specials, ch) || unicode.IsControl(ch) {
+			builder.WriteRune('_')
+		} else {
+			builder.WriteRune(ch)
+		}
+	}
+
+	result := strings.TrimRightFunc(builder.String(), func(r rune) bool {
+		return r == '.' || r == '_' || unicode.IsSpace(r)
+	})
+
+	return result
+}

common/utils/fsutil/normalize_pathname_test.go

@@ -0,0 +1,46 @@
+package fsutil_test
+
+import (
+	"testing"
+
+	"github.com/krau/SaveAny-Bot/common/utils/fsutil"
+)
+
+func TestNormalizePathname(t *testing.T) {
+	tests := []struct {
+		input    string
+		expected string
+	}{
+		{
+			input:    "hello/world?.txt  ",
+			expected: "hello_world_.txt",
+		},
+		{
+			input:    "bad|name:\nfile\r.",
+			expected: "bad_name__file",
+		},
+		{
+			input:    "normal.txt",
+			expected: "normal.txt",
+		},
+		{
+			input:    "test....   ",
+			expected: "test",
+		},
+		{
+			input:    "abc<>def",
+			expected: "abc__def",
+		},
+		{
+			input:    "with\tcontrol",
+			expected: "with_control",
+		},
+	}
+
+	for _, tc := range tests {
+		got := fsutil.NormalizePathname(tc.input)
+		if got != tc.expected {
+			t.Errorf("NormalizePathname(%q) = %q; want %q", tc.input, got, tc.expected)
+		}
+	}
+}

common/utils/tgutil/message.go

@@ -4,6 +4,7 @@ import (
 	"fmt"
 	"strconv"
 	"strings"
+	"unicode"
 
 	"github.com/celestix/gotgproto/ext"
 	"github.com/duke-git/lancet/v2/maputil"
@@ -61,16 +62,12 @@ func GenFileNameFromMessage(message tg.Message) string {
 			return fmt.Sprintf("%s_%s", tagStr, strconv.Itoa(message.GetID()))
 		}
 		text = lcstrutil.Substring(strings.Map(func(r rune) rune {
-			if r < 0x20 || r == 0x7F {
-				return '_'
-			}
 			switch r {
-			// invalid characters
 			case '/', '\\',
 				':', '*', '?', '"', '<', '>', '|':
 				return '_'
-			// empty
-			case ' ', '\t', '\r', '\n':
+			}
+			if unicode.IsControl(r) || unicode.IsSpace(r) {
 				return '_'
 			}
 			if validator.IsPrintable(string(r)) {

common/utils/tgutil/resolve.go

@@ -86,7 +86,7 @@ func ParseMessageLink(ctx *ext.Context, link string) (int64, int, error) {
 		return chatID, msgID, nil
 	case 3:
 		// https://t.me/c/123456789/123
-		// https://t.me/acherkrau/123/456 , 456: message thread ID
+		// https://t.me/acherkrau/123/456 , 123: topic id
 		chatPart, msgPart := paths[1], paths[2]
 		if paths[0] != "c" {
 			chatPart = paths[0]

config/storage/telegram.go

@@ -9,6 +9,7 @@ import (
 type TelegramStorageConfig struct {
 	BaseConfig
 	ChatID    int64 `toml:"chat_id" mapstructure:"chat_id" json:"chat_id"`
+	ForceFile bool  `toml:"force_file" mapstructure:"force_file" json:"force_file"`
 	RateLimit int   `toml:"rate_limit" mapstructure:"rate_limit" json:"rate_limit"`
 	RateBurst int   `toml:"rate_burst" mapstructure:"rate_burst" json:"rate_burst"`
 }

core/tasks/parsed/task.go

@@ -6,6 +6,7 @@ import (
 	"sync"
 	"sync/atomic"
 
+	"github.com/krau/SaveAny-Bot/common/utils/netutil"
 	"github.com/krau/SaveAny-Bot/config"
 	"github.com/krau/SaveAny-Bot/pkg/enums/tasktype"
 	"github.com/krau/SaveAny-Bot/pkg/parser"
@@ -47,12 +48,7 @@ func NewTask(
 	item *parser.Item,
 	progressTracker ProgressTracker,
 ) *Task {
-	client := &http.Client{
-		Transport: &http.Transport{
-			// [TODO] configure it via config
-			Proxy: http.ProxyFromEnvironment,
-		},
-	}
+	client := netutil.DefaultParserHTTPClient()
 	_, ok := stor.(storage.StorageCannotStream)
 	stream := config.C().Stream && !ok
 	return &Task{

docs/content/zh/contribute/_index.md

@@ -29,6 +29,6 @@ weight: 20
 1. 在 `parsers` 目录下新建一个包, 编写解析器实现
 2. 在 `parsers/parser.go` 的 `init` 中注册解析器
 
-如果使用 JavaScript 编写, 请参考 `plugins/example_parser.js` 的实现, 并在该文件夹下新建一个 js 文件, 实现你的解析逻辑.
+如果使用 JavaScript 编写, 请参考 `plugins/example_parser_basic.js` 的实现, 并在该文件夹下新建一个 js 文件, 实现你的解析逻辑.
 
 需要注意, `plugins` 目录下解析器默认不会被编译到二进制文件中, 用户需要手动下载它们并放到本地指定目录下以启用它们.

docs/content/zh/usage/_index.md

@@ -120,4 +120,5 @@ IS-ALBUM true MyWebdav NEW-FOR-ALBUM
 
 只需向 Bot 发送符合解析器要求的链接即可使用, 当前内置的解析器:
 
-- Twitter
+- Twitter
+- Kemono

storage/telegram/telegram.go

@@ -5,12 +5,13 @@ import (
 	"fmt"
 	"io"
 	"path"
-	"strconv"
 	"strings"
 	"time"
 
-	"github.com/duke-git/lancet/v2/convertor"
+	"github.com/charmbracelet/log"
+	"github.com/duke-git/lancet/v2/slice"
 	"github.com/gabriel-vasile/mimetype"
+	"github.com/gotd/td/constant"
 	"github.com/gotd/td/telegram/message"
 	"github.com/gotd/td/telegram/message/styling"
 	"github.com/gotd/td/telegram/uploader"
@@ -75,26 +76,46 @@ func (t *Telegram) Save(ctx context.Context, r io.Reader, storagePath string) er
 	if tctx == nil {
 		return fmt.Errorf("failed to get telegram context")
 	}
+	// 去除前导斜杠并分隔路径, 当 len(parts):
+	// ==0, 存储到配置文件中的 chat_id, 随机文件名
+	// ==1, 视作只有文件名, 存储到配置文件中的 chat_id
+	// ==2, parts[0]: 视作要存储到的 chat_id, parts[1]: filename
+
+	parts := slice.Compact(strings.Split(strings.TrimPrefix(storagePath, "/"), "/"))
+	filename := ""
 	chatID := t.config.ChatID
-	if after, ok0 := strings.CutPrefix(convertor.ToString(chatID), "-100"); ok0 {
-		cid, err := strconv.ParseInt(after, 10, 64)
+	if len(parts) >= 1 {
+		filename = parts[len(parts)-1]
+	}
+	if len(parts) >= 2 {
+		cid, err := tgutil.ParseChatID(tctx, parts[0])
 		if err != nil {
-			return fmt.Errorf("failed to parse chat ID: %w", err)
+			// id不合法时使用配置文件中的 chat_id
+			log.FromContext(ctx).Warnf("Failed to parse chat ID from path, using configured chat_id: %s", err)
+			cid = chatID
+		} else {
+			if cid > constant.MaxTDLibChannelID || cid > constant.MaxTDLibChatID || cid > constant.MaxTDLibUserID {
+				cid = chatID
+			}
 		}
 		chatID = cid
 	}
-	peer := tctx.PeerStorage.GetInputPeerById(chatID)
-	if peer == nil {
-		return fmt.Errorf("failed to get input peer for chat ID %d", chatID)
-	}
 	mtype, err := mimetype.DetectReader(rs)
 	if err != nil {
 		return fmt.Errorf("failed to detect mimetype: %w", err)
 	}
-	filename := path.Base(storagePath)
 	if filename == "" {
 		filename = xid.New().String() + mtype.Extension()
 	}
+
+	if chatID < 0 {
+		chatID = chatID - constant.ZeroTDLibChannelID
+	}
+	peer := tctx.PeerStorage.GetInputPeerById(chatID)
+	if peer == nil {
+		return fmt.Errorf("failed to get input peer for chat ID %d", chatID)
+	}
+
 	if _, err := rs.Seek(0, io.SeekStart); err != nil {
 		return fmt.Errorf("failed to seek reader: %w", err)
 	}
@@ -122,7 +143,7 @@ func (t *Telegram) Save(ctx context.Context, r io.Reader, storagePath string) er
 	caption := styling.Plain(filename)
 	docb := message.UploadedDocument(file, caption).
 		Filename(filename).
-		ForceFile(false).
+		ForceFile(t.config.ForceFile).
 		MIME(mtype.String())
 
 	var media message.MediaOption = docb
@@ -135,7 +156,6 @@ func (t *Telegram) Save(ctx context.Context, r io.Reader, storagePath string) er
 	case strings.HasPrefix(mtypeStr, "image/") && !strings.HasSuffix(mtypeStr, "webp"):
 		media = message.UploadedPhoto(file, caption)
 	}
-
 	sender := tctx.Sender
 	_, err = sender.WithUploader(upler).To(peer).Media(ctx, media)
 	return err