Improve code quality and test assertions

Author: yeasy

cmd/build_test.go

@@ -345,15 +345,6 @@ func TestRewriteMarkdownLinksInHTML_ValidTargets(t *testing.T) {
 	}
 }
 
-// TestBuildVariables_Initialization tests that build variables are initialized
-func TestBuildVariables_Initialization(t *testing.T) {
-	_ = buildFormat
-	_ = buildBranch
-	_ = buildSubDir
-	_ = buildOutput
-	_ = buildSummary
-}
-
 // TestBuildCommand_ExamplesInHelp tests that build help contains examples
 func TestBuildCommand_ExamplesInHelp(t *testing.T) {
 	if !strings.Contains(buildCmd.Long, "mdpress build") {

cmd/root_test.go

@@ -64,9 +64,9 @@ func TestCacheDirFlagParsing(t *testing.T) {
 
 	for i, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
-			// Reset environment before each test
-			os.Unsetenv("MDPRESS_CACHE_DIR")
-			os.Unsetenv("MDPRESS_DISABLE_CACHE")
+			// Reset environment before each test (t.Setenv auto-restores)
+			t.Setenv("MDPRESS_CACHE_DIR", "")
+			t.Setenv("MDPRESS_DISABLE_CACHE", "")
 
 			// Create a test command to verify flag parsing
 			testCmd := &cobra.Command{Use: "test", RunE: func(cmd *cobra.Command, args []string) error {
@@ -107,8 +107,8 @@ func TestCacheDirFlagParsing(t *testing.T) {
 
 // TestNoCacheDisablesBothFlags tests that --no-cache properly disables caching
 func TestNoCacheDisablesFlagCaching(t *testing.T) {
-	os.Unsetenv("MDPRESS_CACHE_DIR")
-	os.Unsetenv("MDPRESS_DISABLE_CACHE")
+	t.Setenv("MDPRESS_CACHE_DIR", "")
+	t.Setenv("MDPRESS_DISABLE_CACHE", "")
 
 	// Simulate flag parsing and configuration
 	noCache = true
@@ -123,8 +123,8 @@ func TestNoCacheDisablesFlagCaching(t *testing.T) {
 
 // TestCacheDirOverrideWorks tests that --cache-dir properly overrides default
 func TestCacheDirOverrideWorks(t *testing.T) {
-	os.Unsetenv("MDPRESS_CACHE_DIR")
-	os.Unsetenv("MDPRESS_DISABLE_CACHE")
+	t.Setenv("MDPRESS_CACHE_DIR", "")
+	t.Setenv("MDPRESS_DISABLE_CACHE", "")
 
 	customPath := "/custom/cache/path"
 	cacheDir = customPath
@@ -158,8 +158,8 @@ func TestFlagDefaults(t *testing.T) {
 
 // TestConfigureRuntimeCacheEnvDoesNotPanicOnEmpty tests robustness
 func TestConfigureRuntimeCacheEnvRobustness(t *testing.T) {
-	os.Unsetenv("MDPRESS_CACHE_DIR")
-	os.Unsetenv("MDPRESS_DISABLE_CACHE")
+	t.Setenv("MDPRESS_CACHE_DIR", "")
+	t.Setenv("MDPRESS_DISABLE_CACHE", "")
 
 	cacheDir = ""
 	noCache = false

internal/config/config.go

@@ -172,15 +172,15 @@ func DefaultConfig() *BookConfig {
 // It also auto-detects GLOSSARY.md and LANGS.md.
 func Load(path string) (*BookConfig, error) {
 	// Limit config size to guard against malformed or malicious YAML inputs.
+	// Check size via os.Stat before reading to avoid loading large files into memory.
 	const maxConfigSize = 10 * 1024 * 1024 // 10MB
-	fi, err := os.Stat(path)
+	info, err := os.Stat(path)
 	if err != nil {
-		return nil, fmt.Errorf("failed to read config file: %w (ensure %s exists and is readable)", err, path)
+		return nil, fmt.Errorf("failed to stat config file: %w (ensure %s exists and is readable)", err, path)
 	}
-	if fi.Size() > maxConfigSize {
-		return nil, fmt.Errorf("config file is too large (%d bytes; max allowed is %d bytes)", fi.Size(), maxConfigSize)
+	if info.Size() > int64(maxConfigSize) {
+		return nil, fmt.Errorf("config file is too large (%d bytes; max allowed is %d bytes)", info.Size(), maxConfigSize)
 	}
-
 	data, err := os.ReadFile(path)
 	if err != nil {
 		return nil, fmt.Errorf("failed to read config file: %w (ensure %s exists and is readable)", err, path)
@@ -295,8 +295,17 @@ func (c *BookConfig) Validate() error {
 	return nil
 }
 
+const maxChapterNestingDepth = 20
+
 // validateChapters recursively validates chapter definitions and their nested sections.
 func (c *BookConfig) validateChapters(chapters []ChapterDef, prefix string) error {
+	return c.validateChaptersDepth(chapters, prefix, 0)
+}
+
+func (c *BookConfig) validateChaptersDepth(chapters []ChapterDef, prefix string, depth int) error {
+	if depth > maxChapterNestingDepth {
+		return fmt.Errorf("chapter nesting exceeds maximum depth of %d", maxChapterNestingDepth)
+	}
 	for i, ch := range chapters {
 		label := fmt.Sprintf("%s%d", prefix, i+1)
 		if ch.File == "" {
@@ -309,7 +318,7 @@ func (c *BookConfig) validateChapters(chapters []ChapterDef, prefix string) erro
 		}
 		// Recursively validate nested sections.
 		if len(ch.Sections) > 0 {
-			if err := c.validateChapters(ch.Sections, label+"."); err != nil {
+			if err := c.validateChaptersDepth(ch.Sections, label+".", depth+1); err != nil {
 				return fmt.Errorf("nested section validation failed: %w", err)
 			}
 		}

internal/config/discover.go

@@ -106,8 +106,11 @@ func Discover(ctx context.Context, dir string) (*BookConfig, error) {
 		}
 	}
 
-	// If book.json was found and we got this far, return the config from it
+	// If book.json was found and we got this far, validate and return the config.
 	if hasBookJSON {
+		if err := cfg.Validate(); err != nil {
+			return nil, fmt.Errorf("book.json config validation failed: %w", err)
+		}
 		return cfg, nil
 	}
 
@@ -237,9 +240,11 @@ func fileNameToTitle(path string) string {
 		"-", " ",
 	).Replace(name)
 
-	// Uppercase the first letter.
-	if len(name) > 0 {
-		name = strings.ToUpper(name[:1]) + name[1:]
+	// Uppercase the first rune (safe for multi-byte UTF-8).
+	runes := []rune(name)
+	if len(runes) > 0 {
+		runes[0] = unicode.ToUpper(runes[0])
+		name = string(runes)
 	}
 
 	return name
@@ -427,8 +432,10 @@ func inferBookTitle(h1Title, content, dir string) string {
 	dirName := filepath.Base(dir)
 	dirName = strings.ReplaceAll(dirName, "_", " ")
 	dirName = strings.ReplaceAll(dirName, "-", " ")
-	if len(dirName) > 0 {
-		dirName = strings.ToUpper(dirName[:1]) + dirName[1:]
+	dr := []rune(dirName)
+	if len(dr) > 0 {
+		dr[0] = unicode.ToUpper(dr[0])
+		dirName = string(dr)
 	}
 	return dirName
 }

internal/markdown/diagnostics.go

@@ -408,7 +408,7 @@ func isMatchingBracket(open, close rune) bool {
 }
 
 func runeCountBytes(b []byte) int {
-	return utf8.RuneCountInString(string(b))
+	return utf8.RuneCount(b)
 }
 
 // longHeadingThreshold 是触发"标题文本过长"警告的字符数阈值。

internal/markdown/extensions.go

@@ -3,43 +3,40 @@ package markdown
 import (
 	"fmt"
 	"strings"
-	"sync"
 
 	"github.com/yuin/goldmark/ast"
 	"github.com/yuin/goldmark/parser"
 	"github.com/yuin/goldmark/text"
 )
 
-// headingIDTransformer 为标题自动生成唯一 ID 属性
-type headingIDTransformer struct {
-	usedIDs map[string]int
-	mu      sync.Mutex
-}
+// headingIDTransformer 为标题自动生成唯一 ID 属性.
+// It is safe for concurrent use: each Transform call uses a local map so
+// multiple documents can be parsed in parallel without interference.
+type headingIDTransformer struct{}
 
 func newHeadingIDTransformer() parser.ASTTransformer {
-	return &headingIDTransformer{
-		usedIDs: make(map[string]int),
-	}
+	return &headingIDTransformer{}
 }
 
-// Transform 遍历 AST，为所有标题节点生成 ID
+// Transform 遍历 AST，为所有标题节点生成 ID.
+// A fresh usedIDs map is created per call so heading IDs are scoped to a
+// single document and concurrent Transform calls don't interfere.
 func (t *headingIDTransformer) Transform(node *ast.Document, reader text.Reader, pc parser.Context) {
+	usedIDs := make(map[string]int)
 	source := reader.Source()
-	if err := ast.Walk(node, func(n ast.Node, entering bool) (ast.WalkStatus, error) {
+	_ = ast.Walk(node, func(n ast.Node, entering bool) (ast.WalkStatus, error) {
 		if !entering {
 			return ast.WalkContinue, nil
 		}
 		if heading, ok := n.(*ast.Heading); ok {
-			t.processHeading(heading, source)
+			processHeading(heading, source, usedIDs)
 		}
 		return ast.WalkContinue, nil
-	}); err != nil {
-		return
-	}
+	})
 }
 
 // processHeading 为单个标题节点设置 ID 属性
-func (t *headingIDTransformer) processHeading(heading *ast.Heading, source []byte) {
+func processHeading(heading *ast.Heading, source []byte, usedIDs map[string]int) {
 	if _, ok := heading.AttributeString("id"); ok {
 		return
 	}
@@ -49,27 +46,24 @@ func (t *headingIDTransformer) processHeading(heading *ast.Heading, source []byt
 		return
 	}
 
-	id := t.generateUniqueID(headingText)
+	id := generateUniqueID(headingText, usedIDs)
 	heading.SetAttributeString("id", []byte(id))
 }
 
 // generateUniqueID 生成唯一的标题 ID，遇到重复自动添加后缀
-func (t *headingIDTransformer) generateUniqueID(text string) string {
+func generateUniqueID(text string, usedIDs map[string]int) string {
 	baseID := generateHeadingID(text)
 	if baseID == "" {
 		baseID = "heading"
 	}
 
-	t.mu.Lock()
-	defer t.mu.Unlock()
-
-	count, exists := t.usedIDs[baseID]
+	count, exists := usedIDs[baseID]
 	if !exists {
-		t.usedIDs[baseID] = 1
+		usedIDs[baseID] = 1
 		return baseID
 	}
 
-	t.usedIDs[baseID] = count + 1
+	usedIDs[baseID] = count + 1
 	return fmt.Sprintf("%s-%d", baseID, count+1)
 }