all: Rework page store, add a dynacache, improve partial rebuilds, and some general spring cleaning

There are some breaking changes in this commit, see #11455. Closes #11455 Closes #11549 This fixes a set of bugs (see issue list) and it is also paying some technical debt accumulated over the years. We now build with Staticcheck enabled in the CI build. The performance should be about the same as before for regular sized Hugo sites, but it should perform and scale much better to larger data sets, as objects that uses lots of memory (e.g. rendered Markdown, big JSON files read into maps with transform.Unmarshal etc.) will now get automatically garbage collected if needed. Performance on partial rebuilds when running the server in fast render mode should be the same, but the change detection should be much more accurate. A list of the notable new features: * A new dependency tracker that covers (almost) all of Hugo's API and is used to do fine grained partial rebuilds when running the server. * A new and simpler tree document store which allows fast lookups and prefix-walking in all dimensions (e.g. language) concurrently. * You can now configure an upper memory limit allowing for much larger data sets and/or running on lower specced PCs. We have lifted the "no resources in sub folders" restriction for branch bundles (e.g. sections). Memory Limit * Hugos will, by default, set aside a quarter of the total system memory, but you can set this via the OS environment variable HUGO_MEMORYLIMIT (in gigabytes). This is backed by a partitioned LRU cache used throughout Hugo. A cache that gets dynamically resized in low memory situations, allowing Go's Garbage Collector to free the memory. New Dependency Tracker: Hugo has had a rule based coarse grained approach to server rebuilds that has worked mostly pretty well, but there have been some surprises (e.g. stale content). This is now revamped with a new dependency tracker that can quickly calculate the delta given a changed resource (e.g. a content file, template, JS file etc.). This handles transitive relations, e.g. $page -> js.Build -> JS import, or $page1.Content -> render hook -> site.GetPage -> $page2.Title, or $page1.Content -> shortcode -> partial -> site.RegularPages -> $page2.Content -> shortcode ..., and should also handle changes to aggregated values (e.g. site.Lastmod) effectively. This covers all of Hugo's API with 2 known exceptions (a list that may not be fully exhaustive): Changes to files loaded with template func os.ReadFile may not be handled correctly. We recommend loading resources with resources.Get Changes to Hugo objects (e.g. Page) passed in the template context to lang.Translate may not be detected correctly. We recommend having simple i18n templates without too much data context passed in other than simple types such as strings and numbers. Note that the cachebuster configuration (when A changes then rebuild B) works well with the above, but we recommend that you revise that configuration, as it in most situations should not be needed. One example where it is still needed is with TailwindCSS and using changes to hugo_stats.json to trigger new CSS rebuilds. Document Store: Previously, a little simplified, we split the document store (where we store pages and resources) in a tree per language. This worked pretty well, but the structure made some operations harder than they needed to be. We have now restructured it into one Radix tree for all languages. Internally the language is considered to be a dimension of that tree, and the tree can be viewed in all dimensions concurrently. This makes some operations re. language simpler (e.g. finding translations is just a slice range), but the idea is that it should also be relatively inexpensive to add more dimensions if needed (e.g. role). Fixes #10169 Fixes #10364 Fixes #10482 Fixes #10630 Fixes #10656 Fixes #10694 Fixes #10918 Fixes #11262 Fixes #11439 Fixes #11453 Fixes #11457 Fixes #11466 Fixes #11540 Fixes #11551 Fixes #11556 Fixes #11654 Fixes #11661 Fixes #11663 Fixes #11664 Fixes #11669 Fixes #11671 Fixes #11807 Fixes #11808 Fixes #11809 Fixes #11815 Fixes #11840 Fixes #11853 Fixes #11860 Fixes #11883 Fixes #11904 Fixes #7388 Fixes #7425 Fixes #7436 Fixes #7544 Fixes #7882 Fixes #7960 Fixes #8255 Fixes #8307 Fixes #8863 Fixes #8927 Fixes #9192 Fixes #9324
2025-08-15 20:44:01 +02:00 · 2023-12-24 19:11:05 +01:00
parent 5fd1e74903
commit 7285e74090
437 changed files with 19304 additions and 18384 deletions
--- a/common/paths/path.go
+++ b/common/paths/path.go
@@ -16,14 +16,18 @@ package paths
 import (
 	"errors"
 	"fmt"
+	"net/url"
 	"path"
 	"path/filepath"
-	"regexp"
 	"strings"
+	"unicode"
 )

 // FilePathSeparator as defined by os.Separator.
-const FilePathSeparator = string(filepath.Separator)
+const (
+	FilePathSeparator = string(filepath.Separator)
+	slash             = "/"
+)

 // filepathPathBridge is a bridge for common functionality in filepath vs path
 type filepathPathBridge interface {
@@ -72,6 +76,30 @@ func AbsPathify(workingDir, inPath string) string {
 	return filepath.Join(workingDir, inPath)
 }

+// AddTrailingSlash adds a trailing Unix styled slash (/) if not already
+// there.
+func AddTrailingSlash(path string) string {
+	if !strings.HasSuffix(path, "/") {
+		path += "/"
+	}
+	return path
+}
+
+// AddLeadingSlash adds a leading Unix styled slash (/) if not already
+// there.
+func AddLeadingSlash(path string) string {
+	if !strings.HasPrefix(path, "/") {
+		path = "/" + path
+	}
+	return path
+}
+
+// AddTrailingAndLeadingSlash adds a leading and trailing Unix styled slash (/) if not already
+// there.
+func AddLeadingAndTrailingSlash(path string) string {
+	return AddTrailingSlash(AddLeadingSlash(path))
+}
+
 // MakeTitle converts the path given to a suitable title, trimming whitespace
 // and replacing hyphens with whitespace.
 func MakeTitle(inpath string) string {
@@ -94,43 +122,6 @@ func makePathRelative(inPath string, possibleDirectories ...string) (string, err
 	return inPath, errors.New("can't extract relative path, unknown prefix")
 }

-// Should be good enough for Hugo.
-var isFileRe = regexp.MustCompile(`.*\..{1,6}$`)
-
-// GetDottedRelativePath expects a relative path starting after the content directory.
-// It returns a relative path with dots ("..") navigating up the path structure.
-func GetDottedRelativePath(inPath string) string {
-	inPath = path.Clean(filepath.ToSlash(inPath))
-
-	if inPath == "." {
-		return "./"
-	}
-
-	if !isFileRe.MatchString(inPath) && !strings.HasSuffix(inPath, "/") {
-		inPath += "/"
-	}
-
-	if !strings.HasPrefix(inPath, "/") {
-		inPath = "/" + inPath
-	}
-
-	dir, _ := filepath.Split(inPath)
-
-	sectionCount := strings.Count(dir, "/")
-
-	if sectionCount == 0 || dir == "/" {
-		return "./"
-	}
-
-	var dottedPath string
-
-	for i := 1; i < sectionCount; i++ {
-		dottedPath += "../"
-	}
-
-	return dottedPath
-}
-
 // ExtNoDelimiter takes a path and returns the extension, excluding the delimiter, i.e. "md".
 func ExtNoDelimiter(in string) string {
 	return strings.TrimPrefix(Ext(in), ".")
@@ -167,12 +158,6 @@ func Filename(in string) (name string) {
 	return
 }

-// PathNoExt takes a path, strips out the extension,
-// and returns the name of the file.
-func PathNoExt(in string) string {
-	return strings.TrimSuffix(in, path.Ext(in))
-}
-
 // FileAndExt returns the filename and any extension of a file path as
 // two separate strings.
 //
@@ -252,16 +237,125 @@ func prettifyPath(in string, b filepathPathBridge) string {
 	return b.Join(b.Dir(in), name, "index"+ext)
 }

-type NamedSlice struct {
-	Name  string
-	Slice []string
+// CommonDir returns the common directory of the given paths.
+func CommonDir(path1, path2 string) string {
+	if path1 == "" || path2 == "" {
+		return ""
+	}
+
+	p1 := strings.Split(path1, "/")
+	p2 := strings.Split(path2, "/")
+
+	var common []string
+
+	for i := 0; i < len(p1) && i < len(p2); i++ {
+		if p1[i] == p2[i] {
+			common = append(common, p1[i])
+		} else {
+			break
+		}
+	}
+
+	return strings.Join(common, "/")
 }

-func (n NamedSlice) String() string {
-	if len(n.Slice) == 0 {
-		return n.Name
+// Sanitize sanitizes string to be used in Hugo's file paths and URLs, allowing only
+// a predefined set of special Unicode characters.
+//
+// Spaces will be replaced with a single hyphen.
+//
+// This function is the core function used to normalize paths in Hugo.
+//
+// Note that this is the first common step for URL/path sanitation,
+// the final URL/path may end up looking differently  if the user has stricter rules defined (e.g. removePathAccents=true).
+func Sanitize(s string) string {
+	var willChange bool
+	for i, r := range s {
+		willChange = !isAllowedPathCharacter(s, i, r)
+		if willChange {
+			break
+		}
 	}
-	return fmt.Sprintf("%s%s{%s}", n.Name, FilePathSeparator, strings.Join(n.Slice, ","))
+
+	if !willChange {
+		// Prevent allocation when nothing changes.
+		return s
+	}
+
+	target := make([]rune, 0, len(s))
+	var (
+		prependHyphen bool
+		wasHyphen     bool
+	)
+
+	for i, r := range s {
+		isAllowed := isAllowedPathCharacter(s, i, r)
+
+		if isAllowed {
+			// track explicit hyphen in input; no need to add a new hyphen if
+			// we just saw one.
+			wasHyphen = r == '-'
+
+			if prependHyphen {
+				// if currently have a hyphen, don't prepend an extra one
+				if !wasHyphen {
+					target = append(target, '-')
+				}
+				prependHyphen = false
+			}
+			target = append(target, r)
+		} else if len(target) > 0 && !wasHyphen && unicode.IsSpace(r) {
+			prependHyphen = true
+		}
+	}
+
+	return string(target)
+}
+
+func isAllowedPathCharacter(s string, i int, r rune) bool {
+	if r == ' ' {
+		return false
+	}
+	// Check for the most likely first (faster).
+	isAllowed := unicode.IsLetter(r) || unicode.IsDigit(r)
+	isAllowed = isAllowed || r == '.' || r == '/' || r == '\\' || r == '_' || r == '#' || r == '+' || r == '~' || r == '-' || r == '@'
+	isAllowed = isAllowed || unicode.IsMark(r)
+	isAllowed = isAllowed || (r == '%' && i+2 < len(s) && ishex(s[i+1]) && ishex(s[i+2]))
+	return isAllowed
+}
+
+// From https://golang.org/src/net/url/url.go
+func ishex(c byte) bool {
+	switch {
+	case '0' <= c && c <= '9':
+		return true
+	case 'a' <= c && c <= 'f':
+		return true
+	case 'A' <= c && c <= 'F':
+		return true
+	}
+	return false
+}
+
+var slashFunc = func(r rune) bool {
+	return r == '/'
+}
+
+// Dir behaves like path.Dir without the path.Clean step.
+//
+//	The returned path ends in a slash only if it is the root "/".
+func Dir(s string) string {
+	dir, _ := path.Split(s)
+	if len(dir) > 1 && dir[len(dir)-1] == '/' {
+		return dir[:len(dir)-1]
+	}
+	return dir
+}
+
+// FieldsSlash cuts s into fields separated with '/'.
+func FieldsSlash(s string) []string {
+	f := strings.FieldsFunc(s, slashFunc)
+	return f
 }

 // DirFile holds the result from path.Split.
@@ -274,3 +368,27 @@ type DirFile struct {
 func (df DirFile) String() string {
 	return fmt.Sprintf("%s|%s", df.Dir, df.File)
 }
+
+// PathEscape escapes unicode letters in pth.
+// Use URLEscape to escape full URLs including scheme, query etc.
+// This is slightly faster for the common case.
+// Note, there is a url.PathEscape function, but that also
+// escapes /.
+func PathEscape(pth string) string {
+	u, err := url.Parse(pth)
+	if err != nil {
+		panic(err)
+	}
+	return u.EscapedPath()
+}
+
+// ToSlashTrimLeading is just a filepath.ToSlash with an added / prefix trimmer.
+func ToSlashTrimLeading(s string) string {
+	return strings.TrimPrefix(filepath.ToSlash(s), "/")
+}
+
+// ToSlashPreserveLeading converts the path given to a forward slash separated path
+// and preserves the leading slash if present trimming any trailing slash.
+func ToSlashPreserveLeading(s string) string {
+	return "/" + strings.Trim(filepath.ToSlash(s), "/")
+}