hugo/hugolib/page_collections.go
Bjørn Erik Pedersen 3cdf19e9b7
Implement Page bundling and image handling
This commit is not the smallest in Hugo's history.

Some hightlights include:

* Page bundles (for complete articles, keeping images and content together etc.).
* Bundled images can be processed in as many versions/sizes as you need with the three methods `Resize`, `Fill` and `Fit`.
* Processed images are cached inside `resources/_gen/images` (default) in your project.
* Symbolic links (both files and dirs) are now allowed anywhere inside /content
* A new table based build summary
* The "Total in nn ms" now reports the total including the handling of the files inside /static. So if it now reports more than you're used to, it is just **more real** and probably faster than before (see below).

A site building  benchmark run compared to `v0.31.1` shows that this should be slightly faster and use less memory:

```bash
▶ ./benchSite.sh "TOML,num_langs=.*,num_root_sections=5,num_pages=(500|1000),tags_per_page=5,shortcodes,render"

benchmark                                                                                                         old ns/op     new ns/op     delta
BenchmarkSiteBuilding/TOML,num_langs=1,num_root_sections=5,num_pages=500,tags_per_page=5,shortcodes,render-4      101785785     78067944      -23.30%
BenchmarkSiteBuilding/TOML,num_langs=1,num_root_sections=5,num_pages=1000,tags_per_page=5,shortcodes,render-4     185481057     149159919     -19.58%
BenchmarkSiteBuilding/TOML,num_langs=3,num_root_sections=5,num_pages=500,tags_per_page=5,shortcodes,render-4      103149918     85679409      -16.94%
BenchmarkSiteBuilding/TOML,num_langs=3,num_root_sections=5,num_pages=1000,tags_per_page=5,shortcodes,render-4     203515478     169208775     -16.86%

benchmark                                                                                                         old allocs     new allocs     delta
BenchmarkSiteBuilding/TOML,num_langs=1,num_root_sections=5,num_pages=500,tags_per_page=5,shortcodes,render-4      532464         391539         -26.47%
BenchmarkSiteBuilding/TOML,num_langs=1,num_root_sections=5,num_pages=1000,tags_per_page=5,shortcodes,render-4     1056549        772702         -26.87%
BenchmarkSiteBuilding/TOML,num_langs=3,num_root_sections=5,num_pages=500,tags_per_page=5,shortcodes,render-4      555974         406630         -26.86%
BenchmarkSiteBuilding/TOML,num_langs=3,num_root_sections=5,num_pages=1000,tags_per_page=5,shortcodes,render-4     1086545        789922         -27.30%

benchmark                                                                                                         old bytes     new bytes     delta
BenchmarkSiteBuilding/TOML,num_langs=1,num_root_sections=5,num_pages=500,tags_per_page=5,shortcodes,render-4      53243246      43598155      -18.12%
BenchmarkSiteBuilding/TOML,num_langs=1,num_root_sections=5,num_pages=1000,tags_per_page=5,shortcodes,render-4     105811617     86087116      -18.64%
BenchmarkSiteBuilding/TOML,num_langs=3,num_root_sections=5,num_pages=500,tags_per_page=5,shortcodes,render-4      54558852      44545097      -18.35%
BenchmarkSiteBuilding/TOML,num_langs=3,num_root_sections=5,num_pages=1000,tags_per_page=5,shortcodes,render-4     106903858     86978413      -18.64%
```

Fixes #3651
Closes #3158
Fixes #1014
Closes #2021
Fixes #1240
Updates #3757
2017-12-27 18:44:47 +01:00

195 lines
5.2 KiB
Go

// Copyright 2016 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.
// You may obtain a copy of the License at
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package hugolib
import (
"path"
"path/filepath"
"github.com/gohugoio/hugo/cache"
)
// PageCollections contains the page collections for a site.
type PageCollections struct {
// Includes only pages of all types, and only pages in the current language.
Pages Pages
// Includes all pages in all languages, including the current one.
// Includes pages of all types.
AllPages Pages
// A convenience cache for the traditional index types, taxonomies, home page etc.
// This is for the current language only.
indexPages Pages
// A convenience cache for the regular pages.
// This is for the current language only.
RegularPages Pages
// A convenience cache for the all the regular pages.
AllRegularPages Pages
// Includes absolute all pages (of all types), including drafts etc.
rawAllPages Pages
pageCache *cache.PartitionedLazyCache
}
func (c *PageCollections) refreshPageCaches() {
c.indexPages = c.findPagesByKindNotIn(KindPage, c.Pages)
c.RegularPages = c.findPagesByKindIn(KindPage, c.Pages)
c.AllRegularPages = c.findPagesByKindIn(KindPage, c.AllPages)
cacheLoader := func(kind string) func() (map[string]interface{}, error) {
return func() (map[string]interface{}, error) {
cache := make(map[string]interface{})
switch kind {
case KindPage:
// Note that we deliberately use the pages from all sites
// in this cache, as we intend to use this in the ref and relref
// shortcodes. If the user says "sect/doc1.en.md", he/she knows
// what he/she is looking for.
for _, p := range c.AllRegularPages {
cache[filepath.ToSlash(p.Source.Path())] = p
// Ref/Relref supports this potentially ambiguous lookup.
cache[p.Source.LogicalName()] = p
}
default:
for _, p := range c.indexPages {
key := path.Join(p.sections...)
cache[key] = p
}
}
return cache, nil
}
}
partitions := make([]cache.Partition, len(allKindsInPages))
for i, kind := range allKindsInPages {
partitions[i] = cache.Partition{Key: kind, Load: cacheLoader(kind)}
}
c.pageCache = cache.NewPartitionedLazyCache(partitions...)
}
func newPageCollections() *PageCollections {
return &PageCollections{}
}
func newPageCollectionsFromPages(pages Pages) *PageCollections {
return &PageCollections{rawAllPages: pages}
}
func (c *PageCollections) getPage(typ string, sections ...string) *Page {
var key string
if len(sections) == 1 {
key = filepath.ToSlash(sections[0])
} else {
key = path.Join(sections...)
}
p, _ := c.pageCache.Get(typ, key)
if p == nil {
return nil
}
return p.(*Page)
}
func (*PageCollections) findPagesByKindIn(kind string, inPages Pages) Pages {
var pages Pages
for _, p := range inPages {
if p.Kind == kind {
pages = append(pages, p)
}
}
return pages
}
func (*PageCollections) findPagesByKindNotIn(kind string, inPages Pages) Pages {
var pages Pages
for _, p := range inPages {
if p.Kind != kind {
pages = append(pages, p)
}
}
return pages
}
func (c *PageCollections) findPagesByKind(kind string) Pages {
return c.findPagesByKindIn(kind, c.Pages)
}
func (c *PageCollections) addPage(page *Page) {
c.rawAllPages = append(c.rawAllPages, page)
}
// When we get a REMOVE event we're not always getting all the individual files,
// so we need to remove all below a given path.
func (c *PageCollections) removePageByPathPrefix(path string) {
for {
i := c.rawAllPages.findFirstPagePosByFilePathPrefix(path)
if i == -1 {
break
}
c.rawAllPages = append(c.rawAllPages[:i], c.rawAllPages[i+1:]...)
}
}
func (c *PageCollections) removePageByPath(path string) {
if i := c.rawAllPages.findPagePosByFilePath(path); i >= 0 {
c.clearResourceCacheForPage(c.rawAllPages[i])
c.rawAllPages = append(c.rawAllPages[:i], c.rawAllPages[i+1:]...)
}
}
func (c *PageCollections) removePage(page *Page) {
if i := c.rawAllPages.findPagePos(page); i >= 0 {
c.clearResourceCacheForPage(c.rawAllPages[i])
c.rawAllPages = append(c.rawAllPages[:i], c.rawAllPages[i+1:]...)
}
}
func (c *PageCollections) findPagesByShortcode(shortcode string) Pages {
var pages Pages
for _, p := range c.rawAllPages {
if p.shortcodeState != nil {
if _, ok := p.shortcodeState.nameSet[shortcode]; ok {
pages = append(pages, p)
}
}
}
return pages
}
func (c *PageCollections) replacePage(page *Page) {
// will find existing page that matches filepath and remove it
c.removePage(page)
c.addPage(page)
}
func (c *PageCollections) clearResourceCacheForPage(page *Page) {
if len(page.Resources) > 0 {
first := page.Resources[0]
dir := path.Dir(first.RelPermalink())
// This is done to keep the memory usage in check when doing live reloads.
page.s.resourceSpec.DeleteCacheByPrefix(dir)
}
}