重写书名处理逻辑

cmd/clname.go

@@ -79,7 +79,7 @@ func ParseEpub(file string, c *ClnameConfig) error {
 		return fmt.Errorf("无法获得书籍标题")
 	}
 	title := book.Opf.Metadata.Title[0]
-	newTitle := util.CleanTitle(title)
+	newTitle := util.TryCleanTitle(title)
 	if title == newTitle {
 		return nil
 	}

go.mod

@@ -4,10 +4,10 @@ go 1.18
 
 require (
 	github.com/kapmahc/epub v0.1.1
-	github.com/spf13/cobra v1.6.1
+	github.com/spf13/cobra v1.8.1
 )
 
 require (
-	github.com/inconshreveable/mousetrap v1.0.1 // indirect
+	github.com/inconshreveable/mousetrap v1.1.0 // indirect
 	github.com/spf13/pflag v1.0.5 // indirect
 )

go.sum

@@ -1,11 +1,11 @@
-github.com/cpuguy83/go-md2man/v2 v2.0.2/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
-github.com/inconshreveable/mousetrap v1.0.1 h1:U3uMjPSQEBMNp1lFxmllqCPM6P5u/Xq7Pgzkat/bFNc=
-github.com/inconshreveable/mousetrap v1.0.1/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
+github.com/cpuguy83/go-md2man/v2 v2.0.4/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
+github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
+github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
 github.com/kapmahc/epub v0.1.1 h1:a4fgmhh/q2vyzFR2QXOVohR2zAuQvbacCjMZ1LGr0lw=
 github.com/kapmahc/epub v0.1.1/go.mod h1:UpnUbQO78vpmp6TC4emDTAIG6XVcdnZTnaTx06qbtYM=
 github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
-github.com/spf13/cobra v1.6.1 h1:o94oiPyS4KD1mPy2fmcYYHHfCxLqYjJOhGsCHFZtEzA=
-github.com/spf13/cobra v1.6.1/go.mod h1:IOw/AERYS7UzyrGinqmz6HLUo219MORXGxhbaJUqzrY=
+github.com/spf13/cobra v1.8.1 h1:e5/vxKd/rZsfSJMUX1agtjeTDf+qv1/JdBF8gg5k9ZM=
+github.com/spf13/cobra v1.8.1/go.mod h1:wHxEcudfqmLYa8iTfL+OuZPbBZkmvliBWKIezN3kD9Y=
 github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA=
 github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=

pkg/util/cleanname.go

@@ -3,6 +3,7 @@ package util
 import (
 	"regexp"
 	"strings"
+	"unicode/utf8"
 )
 
 var (
@@ -13,7 +14,243 @@ func CleanTitle(title string) string {
 	if len(ReNameReg.FindAllString(title, -1)) == 0 {
 		return title
 	}
+
+	for _, match := range ReNameReg.FindAllStringSubmatch(title, -1) {
+		if len(match[0]) < 10 {
+			println(title + "--------" + match[0])
+			return title
+		}
+	}
 	newTitle := ReNameReg.ReplaceAllString(title, "")
 	newTitle = strings.TrimSpace(strings.ReplaceAll(newTitle, "\"", " "))
 	return newTitle
 }
+
+type Stack struct {
+	items []string
+}
+
+func (s *Stack) Push(item string) {
+	s.items = append(s.items, item)
+}
+
+func (s *Stack) Pop() string {
+	if len(s.items) == 0 {
+		return ""
+	}
+	item := s.items[len(s.items)-1]
+	s.items = s.items[:len(s.items)-1]
+	return item
+}
+
+func (s *Stack) IsEmpty() bool {
+	return len(s.items) == 0
+}
+
+func (s *Stack) Peek() string {
+	if len(s.items) == 0 {
+		return ""
+	}
+	return s.items[len(s.items)-1]
+}
+
+func (s *Stack) GetItems() []string {
+	return s.items
+}
+
+func TryCleanTitle(title string) string {
+
+	stack := &Stack{}
+
+	//fmt.Println(title)
+	reader := strings.NewReader(title)
+
+	word := ""
+	symbol := &Stack{}
+	symbolPair := map[string]string{
+		"【": "】",
+		"[": "]",
+		"（": "）",
+		"(": ")",
+		"】": "【",
+		"]": "[",
+		"）": "（",
+		")": "(",
+	}
+	for {
+		r, _, err := reader.ReadRune()
+		if err != nil {
+			break
+		}
+		char := string(r)
+		//《大江大河》作者阿耐合集（共12册）（含《大江大河》(全4册)《欢乐颂》（全3册）《都挺好》(全2册)《不得往生》《食荤者》《余生》，阿耐出品，必是精品！作品改编影视剧均引起热议！）
+		//fmt.Println("【needSymbol】 " + strings.Join(symbol.GetItems(), " | "))
+		switch char {
+		case "【", "[", "（", "(":
+			if symbol.IsEmpty() && utf8.RuneCountInString(word) > 0 {
+				stack.Push(word)
+				word = char
+			} else {
+				word += char
+			}
+			symbol.Push(char)
+		case "】", "]", "）", ")":
+			word += char
+			if symbol.Peek() == symbolPair[char] {
+				symbol.Pop()
+				stack.Push(word)
+				word = ""
+			}
+		default:
+			word += char
+		}
+
+		//fmt.Println(word, "----", strings.Join(stack.GetItems(), " | "))
+	}
+
+	if symbol.IsEmpty() || len(word) != 0 {
+		stack.Push(word)
+	}
+
+	outTitle := ""
+	for i, v := range stack.GetItems() {
+		if i == 0 {
+			outTitle = v
+		} else if i <= 2 && preserve(v) {
+			outTitle += v
+		}
+	}
+
+	// 去除首尾空格
+	outTitle = strings.ReplaceAll(outTitle, "\"", " ")
+	outTitle = strings.TrimSpace(outTitle)
+	if utf8.RuneCountInString(outTitle) == 0 {
+		return title
+	}
+	return outTitle
+}
+
+func preserve(content string) bool {
+
+	c := strings.TrimPrefix(content, "【")
+	c = strings.TrimPrefix(c, "[")
+	c = strings.TrimPrefix(c, "（")
+	c = strings.TrimPrefix(c, "(")
+
+	c = strings.TrimSuffix(c, "】")
+	c = strings.TrimSuffix(c, "]")
+	c = strings.TrimSuffix(c, "）")
+	c = strings.TrimSuffix(c, ")")
+
+	if utf8.RuneCountInString(c) <= 3 {
+		return true
+	}
+	// 定义需要保留的括号内容的正则表达式
+	preservePatterns := []string{
+		`.{2,6}篇`,
+		`[上中下+]`,
+		`[上中下、]+[册本卷部辑]`,
+		`套装.*?[册本卷部辑]`,
+		`[全共].*?[册本卷部辑]`,
+		`\d+[册本卷部辑]`,
+		`第.*?[版卷部辑]`,
+		`[\d一二三四五六七八九十百千]+[-~—～][\d一二三四五六七八九十百千]+`,
+		`\d{4}[-~—～]\d{4}`,
+	}
+	// 合并保留模式为一个正则表达式
+	preserveRegex := regexp.MustCompile(strings.Join(preservePatterns, "|"))
+	b := preserveRegex.MatchString(c) && utf8.RuneCountInString(c) < 20
+	if !b {
+		return strings.HasSuffix(c, "版") && utf8.RuneCountInString(c) < 10
+	}
+	return b
+}
+
+func NewCleanTitle(title string) string {
+	// 移除方括号 【】和 []
+	reSquareBrackets := regexp.MustCompile(`[【\[].*?[】\]]`)
+	title = reSquareBrackets.ReplaceAllString(title, "")
+
+	// 定义需要保留的括号内容的正则表达式
+	preservePatterns := []string{
+		`.{2,6}篇`,
+		`修订版`,
+		`[上中下、]+[册本卷部]`,
+		`套装.*?[册本卷部]`,
+		`[全共].*?[册本卷部]`,
+		`第.*?[版卷部]`,
+		`[\d一二三四五六七八九十百千]+[-~—～][\d一二三四五六七八九十百千]+`,
+		`\d{4}[-~—～]\d{4}`,
+	}
+	// 合并保留模式为一个正则表达式
+	preserveRegex := regexp.MustCompile(strings.Join(preservePatterns, "|"))
+
+	// 处理中文括号 （）
+	reChineseParentheses := regexp.MustCompile(`（.*?）`)
+	title = reChineseParentheses.ReplaceAllStringFunc(title, func(s string) string {
+		content := strings.Trim(s, "（）")
+		println(content)
+		// 如果内容长度小于8，保留
+		if len([]rune(content)) < 8 {
+			return s
+		}
+		if preserveRegex.MatchString(content) {
+			return s
+		}
+		return ""
+	})
+
+	// 处理英文括号 ()
+	reEnglishParentheses := regexp.MustCompile(`\(.*?\)`)
+	title = reEnglishParentheses.ReplaceAllStringFunc(title, func(s string) string {
+		content := strings.Trim(s, "()")
+		println(content)
+		// 如果内容长度小于8，保留
+		if len([]rune(content)) < 8 {
+			return s
+		}
+		if preserveRegex.MatchString(content) {
+			return s
+		}
+		return ""
+	})
+
+	// 处理中文英文括号 （)
+	reChinese2Parentheses := regexp.MustCompile(`（.*?\)`)
+	title = reChinese2Parentheses.ReplaceAllStringFunc(title, func(s string) string {
+		content := strings.Trim(s, "（)")
+		println(content)
+		// 如果内容长度小于8，保留
+		if len([]rune(content)) < 8 {
+			return s
+		}
+		if preserveRegex.MatchString(content) {
+			return s
+		}
+		return ""
+	})
+	// 处理英文中文括号 (）
+	reEnglish2Parentheses := regexp.MustCompile(`\(.*?）`)
+	title = reEnglish2Parentheses.ReplaceAllStringFunc(title, func(s string) string {
+		content := strings.Trim(s, "(）")
+		println(content)
+		// 如果内容长度小于8，保留
+		if len([]rune(content)) < 8 {
+			return s
+		}
+		if preserveRegex.MatchString(content) {
+			return s
+		}
+		return ""
+	})
+
+	// 移除书名号 《和》
+	if strings.HasPrefix(title, "《") && strings.HasSuffix(title, "》") {
+		title = title[3:]
+		title = title[:len(title)-3]
+	}
+	// 去除首尾空格
+	title = strings.ReplaceAll(title, "\"", " ")
+	title = strings.TrimSpace(title)
+	return title
+}