summaryrefslogtreecommitdiffstats
path: root/helpers
diff options
context:
space:
mode:
authorBjørn Erik Pedersen <bjorn.erik.pedersen@gmail.com>2023-12-24 19:11:05 +0100
committerBjørn Erik Pedersen <bjorn.erik.pedersen@gmail.com>2024-01-27 16:28:14 +0100
commit7285e74090852b5d52f25e577850fa75f4aa8573 (patch)
tree54d07cb4a7de2db5c89f2590266595f0aca6cbd6 /helpers
parent5fd1e7490305570872d3899f5edda950903c5213 (diff)
all: Rework page store, add a dynacache, improve partial rebuilds, and some general spring cleaningdevelop2024
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
Diffstat (limited to 'helpers')
-rw-r--r--helpers/content.go11
-rw-r--r--helpers/content_test.go6
-rw-r--r--helpers/general.go32
-rw-r--r--helpers/general_test.go28
-rw-r--r--helpers/path.go105
-rw-r--r--helpers/path_test.go5
-rw-r--r--helpers/pathspec.go6
-rw-r--r--helpers/processing_stats.go2
-rw-r--r--helpers/url.go47
-rw-r--r--helpers/url_test.go37
10 files changed, 64 insertions, 215 deletions
diff --git a/helpers/content.go b/helpers/content.go
index a3abb334d..889294382 100644
--- a/helpers/content.go
+++ b/helpers/content.go
@@ -30,7 +30,6 @@ import (
"github.com/spf13/afero"
"github.com/gohugoio/hugo/markup/converter"
- "github.com/gohugoio/hugo/markup/converter/hooks"
"github.com/gohugoio/hugo/markup"
@@ -38,19 +37,15 @@ import (
)
var (
- openingPTag = []byte("<p>")
- closingPTag = []byte("</p>")
- paragraphIndicator = []byte("<p")
- closingIndicator = []byte("</")
+ openingPTag = []byte("<p>")
+ closingPTag = []byte("</p>")
)
// ContentSpec provides functionality to render markdown content.
type ContentSpec struct {
Converters markup.ConverterProvider
anchorNameSanitizer converter.AnchorNameSanitizer
- getRenderer func(t hooks.RendererType, id any) any
-
- Cfg config.AllProvider
+ Cfg config.AllProvider
}
// NewContentSpec returns a ContentSpec initialized
diff --git a/helpers/content_test.go b/helpers/content_test.go
index 72e3eeb49..e2bf501d2 100644
--- a/helpers/content_test.go
+++ b/helpers/content_test.go
@@ -1,4 +1,4 @@
-// Copyright 2023 The Hugo Authors. All rights reserved.
+// Copyright 2024 The Hugo Authors. All rights reserved.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
@@ -24,8 +24,6 @@ import (
"github.com/gohugoio/hugo/helpers"
)
-const tstHTMLContent = "<!DOCTYPE html><html><head><script src=\"http://two/foobar.js\"></script></head><body><nav><ul><li hugo-nav=\"section_0\"></li><li hugo-nav=\"section_1\"></li></ul></nav><article>content <a href=\"http://two/foobar\">foobar</a>. Follow up</article><p>This is some text.<br>And some more.</p></body></html>"
-
func TestTrimShortHTML(t *testing.T) {
tests := []struct {
input, output []byte
@@ -68,7 +66,6 @@ func BenchmarkTestTruncateWordsToWholeSentence(b *testing.B) {
}
func TestTruncateWordsToWholeSentence(t *testing.T) {
-
type test struct {
input, expected string
max int
@@ -101,7 +98,6 @@ func TestTruncateWordsToWholeSentence(t *testing.T) {
}
func TestTruncateWordsByRune(t *testing.T) {
-
type test struct {
input, expected string
max int
diff --git a/helpers/general.go b/helpers/general.go
index b16aec0b0..35e35a7e0 100644
--- a/helpers/general.go
+++ b/helpers/general.go
@@ -196,6 +196,7 @@ func ReaderContains(r io.Reader, subslice []byte) bool {
func GetTitleFunc(style string) func(s string) string {
switch strings.ToLower(style) {
case "go":
+ //lint:ignore SA1019 keep for now.
return strings.Title
case "chicago":
tc := transform.NewTitleConverter(transform.ChicagoStyle)
@@ -263,10 +264,11 @@ func MD5String(f string) string {
return hex.EncodeToString(h.Sum([]byte{}))
}
-// MD5FromFileFast creates a MD5 hash from the given file. It only reads parts of
+// MD5FromReaderFast creates a MD5 hash from the given file. It only reads parts of
// the file for speed, so don't use it if the files are very subtly different.
// It will not close the file.
-func MD5FromFileFast(r io.ReadSeeker) (string, error) {
+// It will return the MD5 hash and the size of r in bytes.
+func MD5FromReaderFast(r io.ReadSeeker) (string, int64, error) {
const (
// Do not change once set in stone!
maxChunks = 8
@@ -284,7 +286,7 @@ func MD5FromFileFast(r io.ReadSeeker) (string, error) {
if err == io.EOF {
break
}
- return "", err
+ return "", 0, err
}
}
@@ -294,12 +296,14 @@ func MD5FromFileFast(r io.ReadSeeker) (string, error) {
h.Write(buff)
break
}
- return "", err
+ return "", 0, err
}
h.Write(buff)
}
- return hex.EncodeToString(h.Sum(nil)), nil
+ size, _ := r.Seek(0, io.SeekEnd)
+
+ return hex.EncodeToString(h.Sum(nil)), size, nil
}
// MD5FromReader creates a MD5 hash from the given reader.
@@ -328,3 +332,21 @@ func PrintFs(fs afero.Fs, path string, w io.Writer) {
return nil
})
}
+
+// FormatByteCount pretty formats b.
+func FormatByteCount(bc uint64) string {
+ const (
+ Gigabyte = 1 << 30
+ Megabyte = 1 << 20
+ Kilobyte = 1 << 10
+ )
+ switch {
+ case bc > Gigabyte || -bc > Gigabyte:
+ return fmt.Sprintf("%.2f GB", float64(bc)/Gigabyte)
+ case bc > Megabyte || -bc > Megabyte:
+ return fmt.Sprintf("%.2f MB", float64(bc)/Megabyte)
+ case bc > Kilobyte || -bc > Kilobyte:
+ return fmt.Sprintf("%.2f KB", float64(bc)/Kilobyte)
+ }
+ return fmt.Sprintf("%d B", bc)
+}
diff --git a/helpers/general_test.go b/helpers/general_test.go
index 1463458fa..54607d699 100644
--- a/helpers/general_test.go
+++ b/helpers/general_test.go
@@ -1,4 +1,4 @@
-// Copyright 2023 The Hugo Authors. All rights reserved.
+// Copyright 2024 The Hugo Authors. All rights reserved.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
@@ -259,19 +259,19 @@ func TestUniqueStringsSorted(t *testing.T) {
func TestFastMD5FromFile(t *testing.T) {
fs := afero.NewMemMapFs()
- if err := afero.WriteFile(fs, "small.txt", []byte("abc"), 0777); err != nil {
+ if err := afero.WriteFile(fs, "small.txt", []byte("abc"), 0o777); err != nil {
t.Fatal(err)
}
- if err := afero.WriteFile(fs, "small2.txt", []byte("abd"), 0777); err != nil {
+ if err := afero.WriteFile(fs, "small2.txt", []byte("abd"), 0o777); err != nil {
t.Fatal(err)
}
- if err := afero.WriteFile(fs, "bigger.txt", []byte(strings.Repeat("a bc d e", 100)), 0777); err != nil {
+ if err := afero.WriteFile(fs, "bigger.txt", []byte(strings.Repeat("a bc d e", 100)), 0o777); err != nil {
t.Fatal(err)
}
- if err := afero.WriteFile(fs, "bigger2.txt", []byte(strings.Repeat("c d e f g", 100)), 0777); err != nil {
+ if err := afero.WriteFile(fs, "bigger2.txt", []byte(strings.Repeat("c d e f g", 100)), 0o777); err != nil {
t.Fatal(err)
}
@@ -292,19 +292,19 @@ func TestFastMD5FromFile(t *testing.T) {
defer bf1.Close()
defer bf2.Close()
- m1, err := helpers.MD5FromFileFast(sf1)
+ m1, _, err := helpers.MD5FromReaderFast(sf1)
c.Assert(err, qt.IsNil)
c.Assert(m1, qt.Equals, "e9c8989b64b71a88b4efb66ad05eea96")
- m2, err := helpers.MD5FromFileFast(sf2)
+ m2, _, err := helpers.MD5FromReaderFast(sf2)
c.Assert(err, qt.IsNil)
c.Assert(m2, qt.Not(qt.Equals), m1)
- m3, err := helpers.MD5FromFileFast(bf1)
+ m3, _, err := helpers.MD5FromReaderFast(bf1)
c.Assert(err, qt.IsNil)
c.Assert(m3, qt.Not(qt.Equals), m2)
- m4, err := helpers.MD5FromFileFast(bf2)
+ m4, _, err := helpers.MD5FromReaderFast(bf2)
c.Assert(err, qt.IsNil)
c.Assert(m4, qt.Not(qt.Equals), m3)
@@ -320,7 +320,7 @@ func BenchmarkMD5FromFileFast(b *testing.B) {
b.Run(fmt.Sprintf("full=%t", full), func(b *testing.B) {
for i := 0; i < b.N; i++ {
b.StopTimer()
- if err := afero.WriteFile(fs, "file.txt", []byte(strings.Repeat("1234567890", 2000)), 0777); err != nil {
+ if err := afero.WriteFile(fs, "file.txt", []byte(strings.Repeat("1234567890", 2000)), 0o777); err != nil {
b.Fatal(err)
}
f, err := fs.Open("file.txt")
@@ -333,7 +333,7 @@ func BenchmarkMD5FromFileFast(b *testing.B) {
b.Fatal(err)
}
} else {
- if _, err := helpers.MD5FromFileFast(f); err != nil {
+ if _, _, err := helpers.MD5FromReaderFast(f); err != nil {
b.Fatal(err)
}
}
@@ -350,7 +350,7 @@ func BenchmarkUniqueStrings(b *testing.B) {
for i := 0; i < b.N; i++ {
result := helpers.UniqueStrings(input)
if len(result) != 6 {
- b.Fatal(fmt.Sprintf("invalid count: %d", len(result)))
+ b.Fatalf("invalid count: %d", len(result))
}
}
})
@@ -369,7 +369,7 @@ func BenchmarkUniqueStrings(b *testing.B) {
result := helpers.UniqueStringsReuse(inputc)
if len(result) != 6 {
- b.Fatal(fmt.Sprintf("invalid count: %d", len(result)))
+ b.Fatalf("invalid count: %d", len(result))
}
}
})
@@ -388,7 +388,7 @@ func BenchmarkUniqueStrings(b *testing.B) {
result := helpers.UniqueStringsSorted(inputc)
if len(result) != 6 {
- b.Fatal(fmt.Sprintf("invalid count: %d", len(result)))
+ b.Fatalf("invalid count: %d", len(result))
}
}
})
diff --git a/helpers/path.go b/helpers/path.go
index 3172d3452..4a6c9a688 100644
--- a/helpers/path.go
+++ b/helpers/path.go
@@ -1,4 +1,4 @@
-// Copyright 2023 The Hugo Authors. All rights reserved.
+// Copyright 2024 The Hugo Authors. All rights reserved.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
@@ -23,12 +23,12 @@ import (
"regexp"
"sort"
"strings"
- "unicode"
"github.com/gohugoio/hugo/common/herrors"
"github.com/gohugoio/hugo/common/text"
"github.com/gohugoio/hugo/htesting"
+ "github.com/gohugoio/hugo/common/paths"
"github.com/gohugoio/hugo/hugofs"
"github.com/gohugoio/hugo/common/hugio"
@@ -41,7 +41,11 @@ import (
// whilst preserving the original casing of the string.
// E.g. Social Media -> Social-Media
func (p *PathSpec) MakePath(s string) string {
- return p.UnicodeSanitize(s)
+ s = paths.Sanitize(s)
+ if p.Cfg.RemovePathAccents() {
+ s = text.RemoveAccentsString(s)
+ }
+ return s
}
// MakePathsSanitized applies MakePathSanitized on every item in the slice
@@ -59,74 +63,13 @@ func (p *PathSpec) MakePathSanitized(s string) string {
return strings.ToLower(p.MakePath(s))
}
-// ToSlashTrimLeading is just a filepath.ToSlaas with an added / prefix trimmer.
-func ToSlashTrimLeading(s string) string {
- return strings.TrimPrefix(filepath.ToSlash(s), "/")
-}
-
// MakeTitle converts the path given to a suitable title, trimming whitespace
// and replacing hyphens with whitespace.
func MakeTitle(inpath string) string {
return strings.Replace(strings.TrimSpace(inpath), "-", " ", -1)
}
-// From https://golang.org/src/net/url/url.go
-func ishex(c rune) 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
-}
-
-// UnicodeSanitize sanitizes string to be used in Hugo URL's, allowing only
-// a predefined set of special Unicode characters.
-// If RemovePathAccents configuration flag is enabled, Unicode accents
-// are also removed.
-// Hyphens in the original input are maintained.
-// Spaces will be replaced with a single hyphen, and sequential replacement hyphens will be reduced to one.
-func (p *PathSpec) UnicodeSanitize(s string) string {
- if p.Cfg.RemovePathAccents() {
- s = text.RemoveAccentsString(s)
- }
-
- source := []rune(s)
- target := make([]rune, 0, len(source))
- var (
- prependHyphen bool
- wasHyphen bool
- )
-
- for i, r := range source {
- isAllowed := r == '.' || r == '/' || r == '\\' || r == '_' || r == '#' || r == '+' || r == '~' || r == '-' || r == '@'
- isAllowed = isAllowed || unicode.IsLetter(r) || unicode.IsDigit(r) || unicode.IsMark(r)
- isAllowed = isAllowed || (r == '%' && i+2 < len(source) && ishex(source[i+1]) && ishex(source[i+2]))
-
- 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)
-}
-
+// MakeTitleInPath converts the path given to a suitable title, trimming whitespace
func MakePathRelative(inPath string, possibleDirectories ...string) (string, error) {
for _, currentPath := range possibleDirectories {
if strings.HasPrefix(inPath, currentPath) {
@@ -317,13 +260,12 @@ func FindCWD() (string, error) {
return path, nil
}
-// SymbolicWalk is like filepath.Walk, but it follows symbolic links.
-func SymbolicWalk(fs afero.Fs, root string, walker hugofs.WalkFunc) error {
+// Walk walks the file tree rooted at root, calling walkFn for each file or
+// directory in the tree, including root.
+func Walk(fs afero.Fs, root string, walker hugofs.WalkFunc) error {
if _, isOs := fs.(*afero.OsFs); isOs {
- // Mainly to track symlinks.
fs = hugofs.NewBaseFileDecorator(fs)
}
-
w := hugofs.NewWalkway(hugofs.WalkwayConfig{
Fs: fs,
Root: root,
@@ -333,16 +275,6 @@ func SymbolicWalk(fs afero.Fs, root string, walker hugofs.WalkFunc) error {
return w.Walk()
}
-// LstatIfPossible can be used to call Lstat if possible, else Stat.
-func LstatIfPossible(fs afero.Fs, path string) (os.FileInfo, error) {
- if lstater, ok := fs.(afero.Lstater); ok {
- fi, _, err := lstater.LstatIfPossible(path)
- return fi, err
- }
-
- return fs.Stat(path)
-}
-
// SafeWriteToDisk is the same as WriteToDisk
// but it also checks to see if file/directory already exists.
func SafeWriteToDisk(inpath string, r io.Reader, fs afero.Fs) (err error) {
@@ -382,7 +314,7 @@ func OpenFileForWriting(fs afero.Fs, filename string) (afero.File, error) {
if !herrors.IsNotExist(err) {
return nil, err
}
- if err = fs.MkdirAll(filepath.Dir(filename), 0777); err != nil { // before umask
+ if err = fs.MkdirAll(filepath.Dir(filename), 0o777); err != nil { // before umask
return nil, err
}
f, err = fs.Create(filename)
@@ -402,7 +334,7 @@ func GetCacheDir(fs afero.Fs, cacheDir string) (string, error) {
return "", err
}
if !exists {
- err := fs.MkdirAll(cacheDir, 0777) // Before umask
+ err := fs.MkdirAll(cacheDir, 0o777) // Before umask
if err != nil {
return "", fmt.Errorf("failed to create cache dir: %w", err)
}
@@ -417,7 +349,7 @@ func GetCacheDir(fs afero.Fs, cacheDir string) (string, error) {
userCacheDir, err := os.UserCacheDir()
if err == nil {
cacheDir := filepath.Join(userCacheDir, hugoCacheBase)
- if err := fs.Mkdir(cacheDir, 0777); err == nil || os.IsExist(err) {
+ if err := fs.Mkdir(cacheDir, 0o777); err == nil || os.IsExist(err) {
return cacheDir, nil
}
}
@@ -494,12 +426,3 @@ func IsEmpty(path string, fs afero.Fs) (bool, error) {
func Exists(path string, fs afero.Fs) (bool, error) {
return afero.Exists(fs, path)
}
-
-// AddTrailingSlash adds a trailing Unix styled slash (/) if not already
-// there.
-func AddTrailingSlash(path string) string {
- if !strings.HasSuffix(path, "/") {
- path += "/"
- }
- return path
-}
diff --git a/helpers/path_test.go b/helpers/path_test.go
index 45b692923..6f3699589 100644
--- a/helpers/path_test.go
+++ b/helpers/path_test.go
@@ -1,4 +1,4 @@
-// Copyright 2023 The Hugo Authors. All rights reserved.
+// Copyright 2024 The Hugo Authors. All rights reserved.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
@@ -134,7 +134,6 @@ func TestMakePathRelative(t *testing.T) {
}
func TestGetDottedRelativePath(t *testing.T) {
- // on Windows this will receive both kinds, both country and western ...
for _, f := range []func(string) string{filepath.FromSlash, func(s string) string { return s }} {
doTestGetDottedRelativePath(f, t)
}
@@ -258,7 +257,7 @@ func createNonZeroSizedFileInTempDir(t *testing.T) *os.File {
f := createZeroSizedFileInTempDir(t)
byteString := []byte("byteString")
- err := os.WriteFile(f.Name(), byteString, 0644)
+ err := os.WriteFile(f.Name(), byteString, 0o644)
if err != nil {
t.Error(err)
}
diff --git a/helpers/pathspec.go b/helpers/pathspec.go
index c9bb49038..88571b93c 100644
--- a/helpers/pathspec.go
+++ b/helpers/pathspec.go
@@ -74,9 +74,5 @@ func NewPathSpecWithBaseBaseFsProvided(fs *hugofs.Fs, cfg config.AllProvider, lo
// PermalinkForBaseURL creates a permalink from the given link and baseURL.
func (p *PathSpec) PermalinkForBaseURL(link, baseURL string) string {
- link = strings.TrimPrefix(link, "/")
- if !strings.HasSuffix(baseURL, "/") {
- baseURL += "/"
- }
- return baseURL + link
+ return baseURL + strings.TrimPrefix(link, "/")
}
diff --git a/helpers/processing_stats.go b/helpers/processing_stats.go
index 3e3e9a3ca..540060aa2 100644
--- a/helpers/processing_stats.go
+++ b/helpers/processing_stats.go
@@ -31,7 +31,6 @@ type ProcessingStats struct {
ProcessedImages uint64
Files uint64
Aliases uint64
- Sitemaps uint64
Cleaned uint64
}
@@ -48,7 +47,6 @@ func (s *ProcessingStats) toVals() []processingStatsTitleVal {
{"Static files", s.Static},
{"Processed images", s.ProcessedImages},
{"Aliases", s.Aliases},
- {"Sitemaps", s.Sitemaps},
{"Cleaned", s.Cleaned},
}
}
diff --git a/helpers/url.go b/helpers/url.go
index 7d86c529c..d5a613029 100644
--- a/helpers/url.go
+++ b/helpers/url.go
@@ -20,55 +20,8 @@ import (
"strings"
"github.com/gohugoio/hugo/common/paths"
-
- "github.com/PuerkitoBio/purell"
)
-func sanitizeURLWithFlags(in string, f purell.NormalizationFlags) string {
- s, err := purell.NormalizeURLString(in, f)
- if err != nil {
- return in
- }
-
- // Temporary workaround for the bug fix and resulting
- // behavioral change in purell.NormalizeURLString():
- // a leading '/' was inadvertently added to relative links,
- // but no longer, see #878.
- //
- // I think the real solution is to allow Hugo to
- // make relative URL with relative path,
- // e.g. "../../post/hello-again/", as wished by users
- // in issues #157, #622, etc., without forcing
- // relative URLs to begin with '/'.
- // Once the fixes are in, let's remove this kludge
- // and restore SanitizeURL() to the way it was.
- // -- @anthonyfok, 2015-02-16
- //
- // Begin temporary kludge
- u, err := url.Parse(s)
- if err != nil {
- panic(err)
- }
- if len(u.Path) > 0 && !strings.HasPrefix(u.Path, "/") {
- u.Path = "/" + u.Path
- }
- return u.String()
- // End temporary kludge
-
- // return s
-
-}
-
-// SanitizeURL sanitizes the input URL string.
-func SanitizeURL(in string) string {
- return sanitizeURLWithFlags(in, purell.FlagsSafe|purell.FlagRemoveTrailingSlash|purell.FlagRemoveDotSegments|purell.FlagRemoveDuplicateSlashes|purell.FlagRemoveUnnecessaryHostDots|purell.FlagRemoveEmptyPortSeparator)
-}
-
-// SanitizeURLKeepTrailingSlash is the same as SanitizeURL, but will keep any trailing slash.
-func SanitizeURLKeepTrailingSlash(in string) string {
- return sanitizeURLWithFlags(in, purell.FlagsSafe|purell.FlagRemoveDotSegments|purell.FlagRemoveDuplicateSlashes|purell.FlagRemoveUnnecessaryHostDots|purell.FlagRemoveEmptyPortSeparator)
-}
-
// URLize is similar to MakePath, but with Unicode handling
// Example:
//
diff --git a/helpers/url_test.go b/helpers/url_test.go
index 448756b5b..ce1b24487 100644
--- a/helpers/url_test.go
+++ b/helpers/url_test.go
@@ -1,4 +1,4 @@
-// Copyright 2023 The Hugo Authors. All rights reserved.
+// Copyright 2024 The Hugo Authors. All rights reserved.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
@@ -20,7 +20,6 @@ import (
qt "github.com/frankban/quicktest"
"github.com/gohugoio/hugo/config"
- "github.com/gohugoio/hugo/helpers"
)
func TestURLize(t *testing.T) {
@@ -193,7 +192,6 @@ func doTestRelURL(t testing.TB, defaultInSubDir, addLanguage, multilingual bool,
canonify bool
expected string
}{
-
// Issue 9994
{"/foo/bar", "https://example.org/foo/", false, "MULTI/foo/bar"},
{"foo/bar", "https://example.org/foo/", false, "/fooMULTI/foo/bar"},
@@ -211,7 +209,7 @@ func doTestRelURL(t testing.TB, defaultInSubDir, addLanguage, multilingual bool,
{"test/", "http://base/sub/", false, "/subMULTI/test/"},
{"/test/", "http://base/sub/", true, "MULTI/test/"},
{"", "http://base/ace/", false, "/aceMULTI/"},
- {"", "http://base/ace", false, "/aceMULTI"},
+ {"", "http://base/ace", false, "/aceMULTI/"},
{"http://abs", "http://base/", false, "http://abs"},
{"//schemaless", "http://base/", false, "//schemaless"},
}
@@ -231,7 +229,6 @@ func doTestRelURL(t testing.TB, defaultInSubDir, addLanguage, multilingual bool,
for i, test := range tests {
c.Run(fmt.Sprintf("%v/defaultInSubDir=%t;addLanguage=%t;multilingual=%t/%s", test, defaultInSubDir, addLanguage, multilingual, lang), func(c *qt.C) {
-
v.Set("baseURL", test.baseURL)
v.Set("canonifyURLs", test.canonify)
defaultContentLanguage := lang
@@ -255,36 +252,6 @@ func doTestRelURL(t testing.TB, defaultInSubDir, addLanguage, multilingual bool,
c.Assert(output, qt.Equals, expected, qt.Commentf("[%d] %s", i, test.input))
})
-
- }
-}
-
-func TestSanitizeURL(t *testing.T) {
- tests := []struct {
- input string
- expected string
- }{
- {"http://foo.bar/", "http://foo.bar"},
- {"http://foo.bar", "http://foo.bar"}, // issue #1105
- {"http://foo.bar/zoo/", "http://foo.bar/zoo"}, // issue #931
- }
-
- for i, test := range tests {
- o1 := helpers.SanitizeURL(test.input)
- o2 := helpers.SanitizeURLKeepTrailingSlash(test.input)
-
- expected2 := test.expected
-
- if strings.HasSuffix(test.input, "/") && !strings.HasSuffix(expected2, "/") {
- expected2 += "/"
- }
-
- if o1 != test.expected {
- t.Errorf("[%d] 1: Expected %#v, got %#v\n", i, test.expected, o1)
- }
- if o2 != expected2 {
- t.Errorf("[%d] 2: Expected %#v, got %#v\n", i, expected2, o2)
- }
}
}