hugo/langs/language.go

190 lines
4.8 KiB
Go
Raw Permalink Normal View History

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
2023-12-24 13:11:05 -05:00
// 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.
// 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 langs contains the language related types and function.
Add support for theme composition and inheritance This commit adds support for theme composition and inheritance in Hugo. With this, it helps thinking about a theme as a set of ordered components: ```toml theme = ["my-shortcodes", "base-theme", "hyde"] ``` The theme definition example above in `config.toml` creates a theme with the 3 components with presedence from left to right. So, Hugo will, for any given file, data entry etc., look first in the project, and then in `my-shortcode`, `base-theme` and lastly `hyde`. Hugo uses two different algorithms to merge the filesystems, depending on the file type: * For `i18n` and `data` files, Hugo merges deeply using the translation id and data key inside the files. * For `static`, `layouts` (templates) and `archetypes` files, these are merged on file level. So the left-most file will be chosen. The name used in the `theme` definition above must match a folder in `/your-site/themes`, e.g. `/your-site/themes/my-shortcodes`. There are plans to improve on this and get a URL scheme so this can be resolved automatically. Also note that a component that is part of a theme can have its own configuration file, e.g. `config.toml`. There are currently some restrictions to what a theme component can configure: * `params` (global and per language) * `menu` (global and per language) * `outputformats` and `mediatypes` The same rules apply here: The left-most param/menu etc. with the same ID will win. There are some hidden and experimental namespace support in the above, which we will work to improve in the future, but theme authors are encouraged to create their own namespaces to avoid naming conflicts. A final note: Themes/components can also have a `theme` definition in their `config.toml` and similar, which is the "inheritance" part of this commit's title. This is currently not supported by the Hugo theme site. We will have to wait for some "auto dependency" feature to be implemented for that to happen, but this can be a powerful feature if you want to create your own theme-variant based on others. Fixes #4460 Fixes #4450
2018-03-01 09:01:25 -05:00
package langs
import (
"fmt"
"sync"
"time"
"golang.org/x/text/collate"
"golang.org/x/text/language"
"github.com/gohugoio/hugo/common/htime"
"github.com/gohugoio/hugo/common/maps"
"github.com/gohugoio/locales"
translators "github.com/gohugoio/localescompressed"
)
type Language struct {
// The language code, e.g. "en" or "no".
// This is currently only settable as the key in the language map in the config.
Lang string
// Fields from the language config.
LanguageConfig
2021-07-26 12:28:57 -04:00
// Used for date formatting etc. We don't want these exported to the
2021-07-26 12:28:57 -04:00
// templates.
translator locales.Translator
timeFormatter htime.TimeFormatter
tag language.Tag
// collator1 and collator2 are the same, we have 2 to prevent deadlocks.
collator1 *Collator
collator2 *Collator
location *time.Location
// This is just an alias of Site.Params.
params maps.Params
}
// NewLanguage creates a new language.
func NewLanguage(lang, defaultContentLanguage, timeZone string, languageConfig LanguageConfig) (*Language, error) {
translator := translators.GetTranslator(lang)
2021-07-26 12:28:57 -04:00
if translator == nil {
translator = translators.GetTranslator(defaultContentLanguage)
2021-07-26 12:28:57 -04:00
if translator == nil {
translator = translators.GetTranslator("en")
2021-07-26 12:28:57 -04:00
}
}
2018-03-21 12:21:46 -04:00
var coll1, coll2 *Collator
tag, err := language.Parse(lang)
if err == nil {
coll1 = &Collator{
c: collate.New(tag),
}
coll2 = &Collator{
c: collate.New(tag),
}
} else {
coll1 = &Collator{
c: collate.New(language.English),
}
coll2 = &Collator{
c: collate.New(language.English),
}
}
2021-07-26 12:28:57 -04:00
l := &Language{
Lang: lang,
LanguageConfig: languageConfig,
translator: translator,
timeFormatter: htime.NewTimeFormatter(translator),
tag: tag,
collator1: coll1,
collator2: coll2,
2021-07-26 12:28:57 -04:00
}
2021-08-01 05:50:12 -04:00
return l, l.loadLocation(timeZone)
}
// This is injected from hugolib to avoid circular dependencies.
var DeprecationFunc = func(item, alternative string, err bool) {}
// Params returns the language params.
// Note that this is the same as the Site.Params, but we keep it here for legacy reasons.
// Deprecated: Use the site.Params instead.
func (l *Language) Params() maps.Params {
// TODO(bep) Remove this for now as it created a little too much noise. Need to think about this.
// See https://github.com/gohugoio/hugo/issues/11025
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
2023-12-24 13:11:05 -05:00
// DeprecationFunc(".Language.Params", paramsDeprecationWarning, false)
return l.params
}
func (l *Language) LanguageCode() string {
if l.LanguageConfig.LanguageCode != "" {
return l.LanguageConfig.LanguageCode
}
return l.Lang
}
func (l *Language) loadLocation(tzStr string) error {
location, err := time.LoadLocation(tzStr)
if err != nil {
return fmt.Errorf("invalid timeZone for language %q: %w", l.Lang, err)
}
l.location = location
return nil
}
func (l *Language) String() string {
return l.Lang
}
// Languages is a sortable list of languages.
type Languages []*Language
func (l Languages) AsSet() map[string]bool {
m := make(map[string]bool)
for _, lang := range l {
m[lang.Lang] = true
}
return m
}
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
2023-12-24 13:11:05 -05:00
// AsIndexSet returns a map with the language code as key and index in l as value.
func (l Languages) AsIndexSet() map[string]int {
m := make(map[string]int)
for i, lang := range l {
m[lang.Lang] = i
}
return m
}
2021-07-26 12:28:57 -04:00
// Internal access to unexported Language fields.
// This construct is to prevent them from leaking to the templates.
func SetParams(l *Language, params maps.Params) {
l.params = params
}
func GetTimeFormatter(l *Language) htime.TimeFormatter {
return l.timeFormatter
}
2021-07-26 12:28:57 -04:00
func GetTranslator(l *Language) locales.Translator {
return l.translator
}
func GetLocation(l *Language) *time.Location {
2021-08-01 05:50:12 -04:00
return l.location
}
func GetCollator1(l *Language) *Collator {
return l.collator1
}
func GetCollator2(l *Language) *Collator {
return l.collator2
}
type Collator struct {
sync.Mutex
c *collate.Collator
}
// CompareStrings compares a and b.
// It returns -1 if a < b, 1 if a > b and 0 if a == b.
// Note that the Collator is not thread safe, so you may want
2023-02-18 15:47:35 -05:00
// to acquire a lock on it before calling this method.
func (c *Collator) CompareStrings(a, b string) int {
return c.c.CompareString(a, b)
}