Collect HTML elements during the build to use in PurgeCSS etc.

The main use case for this is to use with resources.PostProcess and resources.PostCSS with purgecss.

You would normally set it up to extract keywords from your templates, doing it from the full /public takes forever for bigger sites.

Doing the template thing misses dynamically created class names etc., and it's hard/impossible to set up in when using themes.

You can enable this in your site config:

```toml
[build]
  writeStats = true
```

It will then write a `hugo_stats.json` file to the project root as part of the build.

If you're only using this for the production build, you should consider putting it below `config/production`.

You can then set it up with PostCSS like this:

```js
const purgecss = require('@fullhuman/postcss-purgecss')({
    content: [ './hugo_stats.json' ],
    defaultExtractor: (content) => {
        let els = JSON.parse(content).htmlElements;
        return els.tags.concat(els.classes, els.ids);
    }
});

module.exports = {
    plugins: [
        require('tailwindcss'),
        require('autoprefixer'),
        ...(process.env.HUGO_ENVIRONMENT === 'production' ? [ purgecss ] : [])
    ]
};
```

Fixes gohugoio#6999

Author: bep

.gitignore

@@ -20,6 +20,7 @@ dock.sh
 GoBuilds
 dist
 
+hugolib/hugo_stats.json
 resources/sunset.jpg
 
 vendor

config/commonConfig.go

@@ -29,11 +29,16 @@ import (
 
 var DefaultBuild = Build{
 	UseResourceCacheWhen: "fallback",
+	WriteStats:           false,
 }
 
 // Build holds some build related condfiguration.
 type Build struct {
 	UseResourceCacheWhen string // never, fallback, always. Default is fallback
+
+	// When enabled, will collect and write a hugo_stats.json with some build
+	// related aggregated data (e.g. CSS class names).
+	WriteStats bool
 }
 
 func (b Build) UseResourceCache(err error) bool {

go.mod

@@ -55,7 +55,7 @@ require (
 	go.opencensus.io v0.22.0 // indirect
 	gocloud.dev v0.15.0
 	golang.org/x/image v0.0.0-20191214001246-9130b4cfad52
-	golang.org/x/net v0.0.0-20191209160850-c0dbc17a3553 // indirect
+	golang.org/x/net v0.0.0-20191209160850-c0dbc17a3553
 	golang.org/x/oauth2 v0.0.0-20190523182746-aaccbc9213b0 // indirect
 	golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e
 	golang.org/x/sys v0.0.0-20200107144601-ef85f5a75ddf // indirect

hugolib/hugo_sites.go

@@ -408,7 +408,11 @@ func applyDeps(cfg deps.DepsCfg, sites ...*Site) error {
 			s.Deps = d
 
 			// Set up the main publishing chain.
-			pub, err := publisher.NewDestinationPublisher(d.PathSpec.BaseFs.PublishFs, s.outputFormatsConfig, s.mediaTypesConfig, cfg.Cfg)
+			pub, err := publisher.NewDestinationPublisher(
+				d.ResourceSpec,
+				s.outputFormatsConfig,
+				s.mediaTypesConfig,
+			)
 
 			if err != nil {
 				return err

hugolib/hugo_sites_build.go

@@ -16,11 +16,17 @@ package hugolib
 import (
 	"bytes"
 	"context"
+	"encoding/json"
 	"fmt"
 	"os"
+	"path/filepath"
 	"runtime/trace"
 	"strings"
 
+	"github.com/gohugoio/hugo/publisher"
+
+	"github.com/gohugoio/hugo/hugofs"
+
 	"github.com/gohugoio/hugo/common/para"
 	"github.com/gohugoio/hugo/config"
 	"github.com/gohugoio/hugo/resources/postpub"
@@ -146,10 +152,10 @@ func (h *HugoSites) Build(config BuildCfg, events ...fsnotify.Event) error {
 		if err != nil {
 			h.SendError(err)
 		}
-	}
 
-	if err := h.postProcess(); err != nil {
-		h.SendError(err)
+		if err = h.postProcess(); err != nil {
+			h.SendError(err)
+		}
 	}
 
 	if h.Metrics != nil {
@@ -337,6 +343,12 @@ func (h *HugoSites) render(config *BuildCfg) error {
 }
 
 func (h *HugoSites) postProcess() error {
+	// Make sure to write any build stats to disk first so it's available
+	// to the post processors.
+	if err := h.writeBuildStats(); err != nil {
+		return err
+	}
+
 	var toPostProcess []resource.OriginProvider
 	for _, s := range h.Sites {
 		for _, v := range s.ResourceSpec.PostProcessResources {
@@ -422,3 +434,47 @@ func (h *HugoSites) postProcess() error {
 	return g.Wait()
 
 }
+
+type publishStats struct {
+	CSSClasses string `json:"cssClasses"`
+}
+
+func (h *HugoSites) writeBuildStats() error {
+	if !h.ResourceSpec.BuildConfig.WriteStats {
+		return nil
+	}
+
+	htmlElements := &publisher.HTMLElements{}
+	for _, s := range h.Sites {
+		stats := s.publisher.PublishStats()
+		htmlElements.Merge(stats.HTMLElements)
+	}
+
+	htmlElements.Sort()
+
+	stats := publisher.PublishStats{
+		HTMLElements: *htmlElements,
+	}
+
+	js, err := json.MarshalIndent(stats, "", "  ")
+	if err != nil {
+		return err
+	}
+
+	filename := filepath.Join(h.WorkingDir, "hugo_stats.json")
+
+	// Make sure it's always written to the OS fs.
+	if err := afero.WriteFile(hugofs.Os, filename, js, 0666); err != nil {
+		return err
+	}
+
+	// Write to the destination, too, if a mem fs is in play.
+	if h.Fs.Source != hugofs.Os {
+		if err := afero.WriteFile(h.Fs.Destination, filename, js, 0666); err != nil {
+			return err
+		}
+	}
+
+	return nil
+
+}

hugolib/site_test.go

@@ -980,3 +980,47 @@ func TestRefIssues(t *testing.T) {
 	b.AssertFileContent("public/post/nested-a/content-a/index.html", `Content: http://example.com/post/nested-b/content-b/`)
 
 }
+
+func TestClassCollector(t *testing.T) {
+	b := newTestSitesBuilder(t)
+	b.WithConfigFile("toml", `
+
+[build]
+  writeStats = true
+
+`)
+
+	b.WithTemplates("index.html", `
+	
+<div id="el1" class="a b c">Foo</div>
+
+Some text.
+
+<div class="c d e" id="el2">Foo</div>
+`)
+
+	b.WithContent("p1.md", "")
+
+	b.Build(BuildCfg{})
+
+	b.AssertFileContent("hugo_stats.json", `
+{
+          "htmlElements": {
+            "tags": [
+              "div"
+            ],
+            "classes": [
+              "a",
+              "b",
+              "c",
+              "d",
+              "e"
+            ],
+            "ids": [
+              "el1",
+              "el2"
+            ]
+          }
+        }
+`)
+}