refactor(service): 重构服务代码结构并更新配置

service/prompt/prompt_files_handle_service.go

@@ -0,0 +1,261 @@
+package prompt
+
+import (
+	"archive/zip"
+	"bytes"
+	"context"
+	"fmt"
+	"io"
+	"net/http"
+	"strings"
+	"time"
+
+	"prompts-core/common/util"
+	"prompts-core/service/gateway"
+
+	"github.com/gogf/gf/v2/frame/g"
+)
+
+// FetchFileTexts 从 URL 列表获取文件内容，支持 zip 内文件
+func FetchFileTexts(ctx context.Context, urls []string) map[string]string {
+	result := make(map[string]string)
+
+	if len(urls) == 0 {
+		return result
+	}
+
+	client := &http.Client{
+		Timeout: time.Duration(g.Cfg().MustGet(ctx, "userFiles.httpTimeoutSec", 8).Int()) * time.Second,
+	}
+
+	for _, rawURL := range urls {
+		url := util.SanitizeURL(rawURL)
+		if url == "" {
+			continue
+		}
+
+		if util.IsBannedExtension(url) {
+			continue
+		}
+
+		if util.IsZipExtension(url) {
+			zipTexts := fetchZipFileTexts(ctx, client, url)
+			for k, v := range zipTexts {
+				result[k] = v
+			}
+			continue
+		}
+
+		text, err := fetchFileContent(ctx, client, url)
+		if err != nil {
+			continue
+		}
+
+		if text == "" {
+			continue
+		}
+
+		text = util.CleanSymbols(text)
+		result[url] = text
+	}
+
+	return result
+}
+
+// fetchZipFileTexts 下载并解压 zip 文件，提取可读文本内容
+func fetchZipFileTexts(ctx context.Context, client *http.Client, url string) map[string]string {
+	result := make(map[string]string)
+
+	zipBytes, err := downloadFile(client, url,
+		int64(g.Cfg().MustGet(ctx, "userFiles.zipMaxSizeMB", 10).Int())*1024*1024,
+	)
+	if err != nil {
+		return result
+	}
+
+	reader, err := zip.NewReader(bytes.NewReader(zipBytes), int64(len(zipBytes)))
+	if err != nil {
+		return result
+	}
+
+	entryMaxSize := int64(g.Cfg().MustGet(ctx, "userFiles.zipEntryMaxSizeKB", 500).Int()) * 1024
+
+	for _, file := range reader.File {
+		if file.FileInfo().IsDir() {
+			continue
+		}
+
+		fileName := file.Name
+
+		if util.IsBannedExtension(fileName) {
+			continue
+		}
+
+		if util.IsZipExtension(fileName) {
+			continue
+		}
+
+		rc, err := file.Open()
+		if err != nil {
+			continue
+		}
+
+		content, err := io.ReadAll(io.LimitReader(rc, entryMaxSize))
+		rc.Close()
+		if err != nil {
+			continue
+		}
+
+		contentType := http.DetectContentType(content)
+		if !util.IsReadableContentType(contentType) {
+			continue
+		}
+
+		text := util.CleanSymbols(string(content))
+		if text == "" {
+			continue
+		}
+
+		key := url + "::" + fileName
+		result[key] = text
+	}
+
+	return result
+}
+
+// downloadFile 下载文件，限制最大大小
+func downloadFile(client *http.Client, url string, maxSize int64) ([]byte, error) {
+	req, err := http.NewRequest(http.MethodGet, url, nil)
+	if err != nil {
+		return nil, err
+	}
+
+	resp, err := client.Do(req)
+	if err != nil {
+		return nil, err
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
+		return nil, fmt.Errorf("HTTP %d", resp.StatusCode)
+	}
+
+	return io.ReadAll(io.LimitReader(resp.Body, maxSize))
+}
+
+// fetchFileContent 获取单个文本文件内容
+func fetchFileContent(ctx context.Context, client *http.Client, url string) (string, error) {
+	req, err := http.NewRequest(http.MethodGet, url, nil)
+	if err != nil {
+		return "", err
+	}
+
+	resp, err := client.Do(req)
+	if err != nil {
+		return "", err
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
+		return "", fmt.Errorf("HTTP %d", resp.StatusCode)
+	}
+
+	contentType := resp.Header.Get("Content-Type")
+	if !util.IsReadableContentType(contentType) {
+		return "", fmt.Errorf("unreadable content-type: %s", contentType)
+	}
+
+	body, err := io.ReadAll(
+		io.LimitReader(resp.Body,
+			int64(g.Cfg().MustGet(ctx, "userFiles.textFileMaxSizeKB", 500).Int())*1024,
+		),
+	)
+	if err != nil {
+		return "", err
+	}
+
+	return strings.TrimSpace(string(body)), nil
+}
+
+// SkillMdContent 根据 skillName 获取 zip 内所有 md 文件拼接内容
+func SkillMdContent(ctx context.Context, skillName string) string {
+	skillResp, err := gateway.GetSkillUser(ctx, skillName)
+	if err != nil {
+		return ""
+	}
+
+	fullUrl := skillResp.ImgAddressPrefix + skillResp.FileUrl
+
+	client := &http.Client{
+		Timeout: time.Duration(g.Cfg().MustGet(ctx, "skillFiles.httpTimeoutSec", 30).Int()) * time.Second,
+	}
+
+	zipBytes, err := downloadFile(client, fullUrl,
+		int64(g.Cfg().MustGet(ctx, "skillFiles.zipMaxSizeMB", 10).Int())*1024*1024,
+	)
+	if err != nil {
+		return ""
+	}
+
+	mdContents, err := extractMdFiles(ctx, zipBytes)
+	if err != nil {
+		return ""
+	}
+
+	if len(mdContents) == 0 {
+		return ""
+	}
+
+	var builder strings.Builder
+	builder.WriteString(fmt.Sprintf("# Skill: %s\n\n", skillResp.Name))
+	if skillResp.Description != "" {
+		builder.WriteString(fmt.Sprintf("> %s\n\n", skillResp.Description))
+	}
+
+	for fileName, content := range mdContents {
+		builder.WriteString(fmt.Sprintf("## %s\n\n", fileName))
+		builder.WriteString(content)
+		builder.WriteString("\n\n---\n\n")
+	}
+
+	return strings.TrimSpace(builder.String())
+}
+
+// extractMdFiles 解压 zip 并提取所有 .md 文件内容
+func extractMdFiles(ctx context.Context, zipBytes []byte) (map[string]string, error) {
+	result := make(map[string]string)
+
+	reader, err := zip.NewReader(bytes.NewReader(zipBytes), int64(len(zipBytes)))
+	if err != nil {
+		return nil, err
+	}
+
+	entryMaxSize := int64(g.Cfg().MustGet(ctx, "skillFiles.mdMaxSizeKB", 500).Int()) * 1024
+
+	for _, file := range reader.File {
+		if file.FileInfo().IsDir() {
+			continue
+		}
+
+		if !strings.HasSuffix(strings.ToLower(file.Name), ".md") {
+			continue
+		}
+
+		rc, err := file.Open()
+		if err != nil {
+			continue
+		}
+
+		content, err := io.ReadAll(io.LimitReader(rc, entryMaxSize))
+		rc.Close()
+		if err != nil {
+			continue
+		}
+
+		if len(content) > 0 {
+			result[file.Name] = strings.TrimSpace(string(content))
+		}
+	}
+
+	return result, nil
+}