Introduce a tree map for all content

This commit introduces a new data structure to store pages and their resources.

This data structure is backed by radix trees.

This simplies tree operations, makes all pages a bundle,  and paves the way for #6310.

It also solves a set of annoying issues (see list below).

Not a motivation behind this, but this commit also makes Hugo in general a little bit faster and more memory effective (see benchmarks). Especially for partial rebuilds on content edits, but also when taxonomies is in use.

```
name                                   old time/op    new time/op    delta
SiteNew/Bundle_with_image/Edit-16        1.32ms ± 8%    1.00ms ± 9%  -24.42%  (p=0.029 n=4+4)
SiteNew/Bundle_with_JSON_file/Edit-16    1.28ms ± 0%    0.94ms ± 0%  -26.26%  (p=0.029 n=4+4)
SiteNew/Tags_and_categories/Edit-16      33.9ms ± 2%    21.8ms ± 1%  -35.67%  (p=0.029 n=4+4)
SiteNew/Canonify_URLs/Edit-16            40.6ms ± 1%    37.7ms ± 3%   -7.20%  (p=0.029 n=4+4)
SiteNew/Deep_content_tree/Edit-16        56.7ms ± 0%    51.7ms ± 1%   -8.82%  (p=0.029 n=4+4)
SiteNew/Many_HTML_templates/Edit-16      19.9ms ± 2%    18.3ms ± 3%   -7.64%  (p=0.029 n=4+4)
SiteNew/Page_collections/Edit-16         37.9ms ± 4%    34.0ms ± 2%  -10.28%  (p=0.029 n=4+4)
SiteNew/Bundle_with_image-16             10.7ms ± 0%    10.6ms ± 0%   -1.15%  (p=0.029 n=4+4)
SiteNew/Bundle_with_JSON_file-16         10.8ms ± 0%    10.7ms ± 0%   -1.05%  (p=0.029 n=4+4)
SiteNew/Tags_and_categories-16           43.2ms ± 1%    39.6ms ± 1%   -8.35%  (p=0.029 n=4+4)
SiteNew/Canonify_URLs-16                 47.6ms ± 1%    47.3ms ± 0%     ~     (p=0.057 n=4+4)
SiteNew/Deep_content_tree-16             73.0ms ± 1%    74.2ms ± 1%     ~     (p=0.114 n=4+4)
SiteNew/Many_HTML_templates-16           37.9ms ± 0%    38.1ms ± 1%     ~     (p=0.114 n=4+4)
SiteNew/Page_collections-16              53.6ms ± 1%    54.7ms ± 1%   +2.09%  (p=0.029 n=4+4)

name                                   old alloc/op   new alloc/op   delta
SiteNew/Bundle_with_image/Edit-16         486kB ± 0%     430kB ± 0%  -11.47%  (p=0.029 n=4+4)
SiteNew/Bundle_with_JSON_file/Edit-16     265kB ± 0%     209kB ± 0%  -21.06%  (p=0.029 n=4+4)
SiteNew/Tags_and_categories/Edit-16      13.6MB ± 0%     8.8MB ± 0%  -34.93%  (p=0.029 n=4+4)
SiteNew/Canonify_URLs/Edit-16            66.5MB ± 0%    63.9MB ± 0%   -3.95%  (p=0.029 n=4+4)
SiteNew/Deep_content_tree/Edit-16        28.8MB ± 0%    25.8MB ± 0%  -10.55%  (p=0.029 n=4+4)
SiteNew/Many_HTML_templates/Edit-16      6.16MB ± 0%    5.56MB ± 0%   -9.86%  (p=0.029 n=4+4)
SiteNew/Page_collections/Edit-16         16.9MB ± 0%    16.0MB ± 0%   -5.19%  (p=0.029 n=4+4)
SiteNew/Bundle_with_image-16             2.28MB ± 0%    2.29MB ± 0%   +0.35%  (p=0.029 n=4+4)
SiteNew/Bundle_with_JSON_file-16         2.07MB ± 0%    2.07MB ± 0%     ~     (p=0.114 n=4+4)
SiteNew/Tags_and_categories-16           14.3MB ± 0%    13.2MB ± 0%   -7.30%  (p=0.029 n=4+4)
SiteNew/Canonify_URLs-16                 69.1MB ± 0%    69.0MB ± 0%     ~     (p=0.343 n=4+4)
SiteNew/Deep_content_tree-16             31.3MB ± 0%    31.8MB ± 0%   +1.49%  (p=0.029 n=4+4)
SiteNew/Many_HTML_templates-16           10.8MB ± 0%    10.9MB ± 0%   +1.11%  (p=0.029 n=4+4)
SiteNew/Page_collections-16              21.4MB ± 0%    21.6MB ± 0%   +1.15%  (p=0.029 n=4+4)

name                                   old allocs/op  new allocs/op  delta
SiteNew/Bundle_with_image/Edit-16         4.74k ± 0%     3.86k ± 0%  -18.57%  (p=0.029 n=4+4)
SiteNew/Bundle_with_JSON_file/Edit-16     4.73k ± 0%     3.85k ± 0%  -18.58%  (p=0.029 n=4+4)
SiteNew/Tags_and_categories/Edit-16        301k ± 0%      198k ± 0%  -34.14%  (p=0.029 n=4+4)
SiteNew/Canonify_URLs/Edit-16              389k ± 0%      373k ± 0%   -4.07%  (p=0.029 n=4+4)
SiteNew/Deep_content_tree/Edit-16          338k ± 0%      262k ± 0%  -22.63%  (p=0.029 n=4+4)
SiteNew/Many_HTML_templates/Edit-16        102k ± 0%       88k ± 0%  -13.81%  (p=0.029 n=4+4)
SiteNew/Page_collections/Edit-16           176k ± 0%      152k ± 0%  -13.32%  (p=0.029 n=4+4)
SiteNew/Bundle_with_image-16              26.8k ± 0%     26.8k ± 0%   +0.05%  (p=0.029 n=4+4)
SiteNew/Bundle_with_JSON_file-16          26.8k ± 0%     26.8k ± 0%   +0.05%  (p=0.029 n=4+4)
SiteNew/Tags_and_categories-16             273k ± 0%      245k ± 0%  -10.36%  (p=0.029 n=4+4)
SiteNew/Canonify_URLs-16                   396k ± 0%      398k ± 0%   +0.39%  (p=0.029 n=4+4)
SiteNew/Deep_content_tree-16               317k ± 0%      325k ± 0%   +2.53%  (p=0.029 n=4+4)
SiteNew/Many_HTML_templates-16             146k ± 0%      147k ± 0%   +0.98%  (p=0.029 n=4+4)
SiteNew/Page_collections-16                210k ± 0%      215k ± 0%   +2.44%  (p=0.029 n=4+4)
```

Fixes #6312
Fixes #6087
Fixes #6738
Fixes #6412
Fixes #6743
Fixes #6875
Fixes #6034
Fixes #6902
Fixes #6173
Fixes #6590
This commit is contained in:
Bjørn Erik Pedersen
2019-09-10 11:26:34 +02:00
parent e5329f13c0
commit eada236f87
71 changed files with 4859 additions and 2531 deletions

View File

@@ -61,7 +61,10 @@ type pageMeta struct {
// a fixed pageOutput.
standalone bool
bundleType string
draft bool // Only published when running with -D flag
buildConfig pagemeta.BuildConfig
bundleType files.ContentClass
// Params contains configuration defined in the params section of page frontmatter.
params map[string]interface{}
@@ -85,8 +88,6 @@ type pageMeta struct {
aliases []string
draft bool
description string
keywords []string
@@ -94,13 +95,6 @@ type pageMeta struct {
resource.Dates
// This is enabled if it is a leaf bundle (the "index.md" type) and it is marked as headless in front matter.
// Being headless means that
// 1. The page itself is not rendered to disk
// 2. It is not available in .Site.Pages etc.
// 3. But you can get it via .Site.GetPage
headless bool
// Set if this page is bundled inside another.
bundled bool
@@ -160,7 +154,7 @@ func (p *pageMeta) Authors() page.AuthorList {
return al
}
func (p *pageMeta) BundleType() string {
func (p *pageMeta) BundleType() files.ContentClass {
return p.bundleType
}
@@ -309,40 +303,53 @@ func (p *pageMeta) Weight() int {
return p.weight
}
func (pm *pageMeta) setMetadata(bucket *pagesMapBucket, p *pageState, frontmatter map[string]interface{}) error {
if frontmatter == nil && bucket.cascade == nil {
return errors.New("missing frontmatter data")
func (pm *pageMeta) mergeBucketCascades(b1, b2 *pagesMapBucket) {
if b1.cascade == nil {
b1.cascade = make(map[string]interface{})
}
if b2 != nil && b2.cascade != nil {
for k, v := range b2.cascade {
if _, found := b1.cascade[k]; !found {
b1.cascade[k] = v
}
}
}
}
func (pm *pageMeta) setMetadata(parentBucket *pagesMapBucket, p *pageState, frontmatter map[string]interface{}) error {
pm.params = make(maps.Params)
if frontmatter == nil && (parentBucket == nil || parentBucket.cascade == nil) {
return nil
}
if frontmatter != nil {
// Needed for case insensitive fetching of params values
maps.ToLower(frontmatter)
if p.IsNode() {
if p.bucket != nil {
// Check for any cascade define on itself.
if cv, found := frontmatter["cascade"]; found {
cvm := maps.ToStringMap(cv)
if bucket.cascade == nil {
bucket.cascade = cvm
} else {
for k, v := range cvm {
bucket.cascade[k] = v
}
}
}
}
if bucket != nil && bucket.cascade != nil {
for k, v := range bucket.cascade {
if _, found := frontmatter[k]; !found {
frontmatter[k] = v
}
p.bucket.cascade = maps.ToStringMap(cv)
}
}
} else {
frontmatter = make(map[string]interface{})
for k, v := range bucket.cascade {
}
var cascade map[string]interface{}
if p.bucket != nil {
if parentBucket != nil {
// Merge missing keys from parent into this.
pm.mergeBucketCascades(p.bucket, parentBucket)
}
cascade = p.bucket.cascade
} else if parentBucket != nil {
cascade = parentBucket.cascade
}
for k, v := range cascade {
if _, found := frontmatter[k]; !found {
frontmatter[k] = v
}
}
@@ -379,6 +386,11 @@ func (pm *pageMeta) setMetadata(bucket *pagesMapBucket, p *pageState, frontmatte
p.s.Log.ERROR.Printf("Failed to handle dates for page %q: %s", p.pathOrTitle(), err)
}
pm.buildConfig, err = pagemeta.DecodeBuildConfig(frontmatter["_build"])
if err != nil {
return err
}
var sitemapSet bool
var draft, published, isCJKLanguage *bool
@@ -439,12 +451,15 @@ func (pm *pageMeta) setMetadata(bucket *pagesMapBucket, p *pageState, frontmatte
pm.keywords = cast.ToStringSlice(v)
pm.params[loki] = pm.keywords
case "headless":
// For now, only the leaf bundles ("index.md") can be headless (i.e. produce no output).
// We may expand on this in the future, but that gets more complex pretty fast.
if p.File().TranslationBaseName() == "index" {
pm.headless = cast.ToBool(v)
// Legacy setting for leaf bundles.
// This is since Hugo 0.63 handled in a more general way for all
// pages.
isHeadless := cast.ToBool(v)
pm.params[loki] = isHeadless
if p.File().TranslationBaseName() == "index" && isHeadless {
pm.buildConfig.List = false
pm.buildConfig.Render = false
}
pm.params[loki] = pm.headless
case "outputs":
o := cast.ToStringSlice(v)
if len(o) > 0 {
@@ -594,7 +609,23 @@ func (pm *pageMeta) setMetadata(bucket *pagesMapBucket, p *pageState, frontmatte
return nil
}
func (p *pageMeta) applyDefaultValues(ps *pageState) error {
func (p *pageMeta) noList() bool {
return !p.buildConfig.List
}
func (p *pageMeta) noRender() bool {
return !p.buildConfig.Render
}
func (p *pageMeta) applyDefaultValues(n *contentNode) error {
if p.buildConfig.IsZero() {
p.buildConfig, _ = pagemeta.DecodeBuildConfig(nil)
}
if !p.s.isEnabled(p.Kind()) {
(&p.buildConfig).Disable()
}
if p.markup == "" {
if !p.File().IsZero() {
// Fall back to file extension
@@ -610,13 +641,21 @@ func (p *pageMeta) applyDefaultValues(ps *pageState) error {
case page.KindHome:
p.title = p.s.Info.title
case page.KindSection:
sectionName := helpers.FirstUpper(p.sections[0])
var sectionName string
if n != nil {
sectionName = n.rootSection()
} else {
sectionName = p.sections[0]
}
sectionName = helpers.FirstUpper(sectionName)
if p.s.Cfg.GetBool("pluralizeListTitles") {
p.title = inflect.Pluralize(sectionName)
} else {
p.title = sectionName
}
case page.KindTaxonomy:
// TODO(bep) improve
key := p.sections[len(p.sections)-1]
p.title = strings.Replace(p.s.titleFunc(key), "-", " ", -1)
case page.KindTaxonomyTerm:
@@ -653,7 +692,7 @@ func (p *pageMeta) applyDefaultValues(ps *pageState) error {
markup = "markdown"
}
cp, err := p.newContentConverter(ps, markup, renderingConfigOverrides)
cp, err := p.newContentConverter(n.p, markup, renderingConfigOverrides)
if err != nil {
return err
}
@@ -665,6 +704,9 @@ func (p *pageMeta) applyDefaultValues(ps *pageState) error {
}
func (p *pageMeta) newContentConverter(ps *pageState, markup string, renderingConfigOverrides map[string]interface{}) (converter.Converter, error) {
if ps == nil {
panic("no Page provided")
}
cp := p.s.ContentSpec.Converters.Get(markup)
if cp == nil {
return nil, errors.Errorf("no content renderer found for markup %q", p.markup)