Init

2026-04-09 10:01:23 +08:00
commit efe801b8bf
707 changed files with 110595 additions and 0 deletions
@@ -0,0 +1,115 @@
+package utils
+
+import (
+	"strings"
+
+	"golang.org/x/net/html"
+)
+
+type ContentChunkType string
+
+const (
+	ContentChunkTypeText  ContentChunkType = "text"
+	ContentChunkTypeImage ContentChunkType = "image"
+)
+
+type ContentChunk struct {
+	Type    ContentChunkType //
+	Content string           // text content or image url
+}
+
+func SplitHTMLContentChunks(content string) ([]ContentChunk, error) {
+	root, err := html.Parse(strings.NewReader("<div>" + strings.TrimSpace(content) + "</div>"))
+	if err != nil {
+		return nil, err
+	}
+
+	var (
+		chunks []ContentChunk
+		buffer strings.Builder
+	)
+	flushText := func() {
+		text := normalizeContentChunkText(buffer.String())
+		buffer.Reset()
+		if text == "" {
+			return
+		}
+		chunks = append(chunks, ContentChunk{
+			Type:    ContentChunkTypeText,
+			Content: text,
+		})
+	}
+
+	var walk func(*html.Node)
+	walk = func(node *html.Node) {
+		if node == nil {
+			return
+		}
+		switch node.Type {
+		case html.TextNode:
+			buffer.WriteString(node.Data)
+		case html.ElementNode:
+			switch node.Data {
+			case "br":
+				buffer.WriteString("\n")
+			case "p", "div", "li", "blockquote":
+				buffer.WriteString("\n")
+			case "img":
+				flushText()
+				src := strings.TrimSpace(findContentChunkHTMLAttr(node, "src"))
+				if src == "" {
+					return
+				}
+				chunks = append(chunks, ContentChunk{
+					Type:    ContentChunkTypeImage,
+					Content: src,
+				})
+				return
+			}
+		}
+		for child := node.FirstChild; child != nil; child = child.NextSibling {
+			walk(child)
+		}
+		if node.Type == html.ElementNode {
+			switch node.Data {
+			case "p", "div", "li", "blockquote":
+				buffer.WriteString("\n")
+			}
+		}
+	}
+	walk(root)
+	flushText()
+	return chunks, nil
+}
+
+func normalizeContentChunkText(value string) string {
+	value = strings.ReplaceAll(value, "\u00a0", " ")
+	lines := strings.Split(value, "\n")
+	normalizedLines := make([]string, 0, len(lines))
+	for _, line := range lines {
+		line = strings.Join(strings.Fields(strings.TrimSpace(line)), " ")
+		if line == "" {
+			if len(normalizedLines) > 0 && normalizedLines[len(normalizedLines)-1] != "" {
+				normalizedLines = append(normalizedLines, "")
+			}
+			continue
+		}
+		normalizedLines = append(normalizedLines, line)
+	}
+	for len(normalizedLines) > 0 && normalizedLines[0] == "" {
+		normalizedLines = normalizedLines[1:]
+	}
+	for len(normalizedLines) > 0 && normalizedLines[len(normalizedLines)-1] == "" {
+		normalizedLines = normalizedLines[:len(normalizedLines)-1]
+	}
+	return strings.Join(normalizedLines, "\n")
+}
+
+func findContentChunkHTMLAttr(node *html.Node, key string) string {
+	for _, attr := range node.Attr {
+		if strings.EqualFold(attr.Key, key) {
+			return attr.Val
+		}
+	}
+	return ""
+}
@@ -0,0 +1,72 @@
+package utils
+
+import (
+	"reflect"
+	"testing"
+)
+
+func TestSplitHTMLContentChunks(t *testing.T) {
+	tests := []struct {
+		name    string
+		content string
+		want    []ContentChunk
+	}{
+		{
+			name:    "plain text paragraph",
+			content: "<p>你好，微信用户</p>",
+			want: []ContentChunk{
+				{Type: ContentChunkTypeText, Content: "你好，微信用户"},
+			},
+		},
+		{
+			name:    "single image",
+			content: `<p><img src="https://example.com/a.png" alt="a"></p>`,
+			want: []ContentChunk{
+				{Type: ContentChunkTypeImage, Content: "https://example.com/a.png"},
+			},
+		},
+		{
+			name:    "mixed text and images keep order",
+			content: `<p>第一段</p><p><img src="https://example.com/1.png"></p><p>第二段<img src="https://example.com/2.png">第三段</p>`,
+			want: []ContentChunk{
+				{Type: ContentChunkTypeText, Content: "第一段"},
+				{Type: ContentChunkTypeImage, Content: "https://example.com/1.png"},
+				{Type: ContentChunkTypeText, Content: "第二段"},
+				{Type: ContentChunkTypeImage, Content: "https://example.com/2.png"},
+				{Type: ContentChunkTypeText, Content: "第三段"},
+			},
+		},
+		{
+			name:    "normalize blank lines and spaces",
+			content: "<div>  第一行  <br><br>   第二行 </div>",
+			want: []ContentChunk{
+				{Type: ContentChunkTypeText, Content: "第一行\n\n第二行"},
+			},
+		},
+		{
+			name:    "ignore image without src",
+			content: `<p>前文</p><img alt="missing-src"><p>后文</p>`,
+			want: []ContentChunk{
+				{Type: ContentChunkTypeText, Content: "前文"},
+				{Type: ContentChunkTypeText, Content: "后文"},
+			},
+		},
+		{
+			name:    "empty html returns empty chunks",
+			content: "<p><br></p>",
+			want:    nil,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got, err := SplitHTMLContentChunks(tt.content)
+			if err != nil {
+				t.Fatalf("SplitHTMLContentChunks() error = %v", err)
+			}
+			if !reflect.DeepEqual(got, tt.want) {
+				t.Fatalf("SplitHTMLContentChunks() = %#v, want %#v", got, tt.want)
+			}
+		})
+	}
+}
@@ -0,0 +1,103 @@
+package utils
+
+import (
+	"crypto/rand"
+	"cs-agent/internal/models"
+	"cs-agent/internal/pkg/dto"
+	"cs-agent/internal/pkg/errorsx"
+	"strconv"
+	"strings"
+	"time"
+
+	"github.com/spf13/cast"
+)
+
+func NormalizeNullableString(value *string) *string {
+	if value == nil {
+		return nil
+	}
+	v := strings.TrimSpace(*value)
+	if v == "" {
+		return nil
+	}
+	return &v
+}
+
+func BuildAuditFields(operator *dto.AuthPrincipal) models.AuditFields {
+	now := time.Now()
+	fields := models.AuditFields{
+		CreatedAt: now,
+		UpdatedAt: now,
+	}
+	if operator != nil {
+		fields.CreateUserID = operator.UserID
+		fields.CreateUserName = operator.Username
+		fields.UpdateUserID = operator.UserID
+		fields.UpdateUserName = operator.Username
+	}
+	return fields
+}
+
+func FormatTimePtr(t *time.Time) string {
+	if t == nil || t.IsZero() {
+		return ""
+	}
+	return t.Format(time.DateTime)
+}
+
+func FormatTime(t time.Time) string {
+	if t.IsZero() {
+		return ""
+	}
+	return t.Format(time.DateTime)
+}
+
+func GenerateRandomPassword(length int) (string, error) {
+	if length <= 0 {
+		return "", errorsx.InvalidParam("密码长度不合法")
+	}
+
+	const charset = "ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz23456789"
+	buf := make([]byte, length)
+	random := make([]byte, length)
+	if _, err := rand.Read(random); err != nil {
+		return "", err
+	}
+	for i := range buf {
+		buf[i] = charset[int(random[i])%len(charset)]
+	}
+	return string(buf), nil
+}
+
+func JoinInt64s(values []int64) string {
+	if len(values) == 0 {
+		return ""
+	}
+	parts := make([]string, 0, len(values))
+	for _, value := range values {
+		parts = append(parts, cast.ToString(value))
+	}
+	return strings.Join(parts, ",")
+}
+
+func SplitInt64s(raw string) []int64 {
+	parts := strings.Split(strings.TrimSpace(raw), ",")
+	ret := make([]int64, 0, len(parts))
+	seen := make(map[int64]struct{})
+	for _, part := range parts {
+		value := strings.TrimSpace(part)
+		if value == "" {
+			continue
+		}
+		id, err := strconv.ParseInt(value, 10, 64)
+		if err != nil || id <= 0 {
+			continue
+		}
+		if _, exists := seen[id]; exists {
+			continue
+		}
+		seen[id] = struct{}{}
+		ret = append(ret, id)
+	}
+	return ret
+}