hugo/parser/pageparser/pageparser.go
Bjørn Erik Pedersen 7285e74090
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
2024-01-27 16:28:14 +01:00

266 lines
6.4 KiB
Go

// Copyright 2019 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 pageparser
import (
"bytes"
"errors"
"fmt"
"io"
"regexp"
"strings"
"github.com/gohugoio/hugo/parser/metadecoders"
)
// Result holds the parse result.
type Result interface {
// Iterator returns a new Iterator positioned at the beginning of the parse tree.
Iterator() *Iterator
// Input returns the input to Parse.
Input() []byte
}
var _ Result = (*pageLexer)(nil)
// ParseBytes parses the page in b according to the given Config.
func ParseBytes(b []byte, cfg Config) (Items, error) {
l, err := parseBytes(b, cfg, lexIntroSection)
if err != nil {
return nil, err
}
return l.items, l.err
}
// ParseBytesMain parses b starting with the main section.
func ParseBytesMain(b []byte, cfg Config) (Items, error) {
l, err := parseBytes(b, cfg, lexMainSection)
if err != nil {
return nil, err
}
return l.items, l.err
}
type ContentFrontMatter struct {
Content []byte
FrontMatter map[string]any
FrontMatterFormat metadecoders.Format
}
// ParseFrontMatterAndContent is a convenience method to extract front matter
// and content from a content page.
func ParseFrontMatterAndContent(r io.Reader) (ContentFrontMatter, error) {
var cf ContentFrontMatter
input, err := io.ReadAll(r)
if err != nil {
return cf, fmt.Errorf("failed to read page content: %w", err)
}
psr, err := ParseBytes(input, Config{})
if err != nil {
return cf, err
}
var frontMatterSource []byte
iter := NewIterator(psr)
walkFn := func(item Item) bool {
if frontMatterSource != nil {
// The rest is content.
cf.Content = input[item.low:]
// Done
return false
} else if item.IsFrontMatter() {
cf.FrontMatterFormat = FormatFromFrontMatterType(item.Type)
frontMatterSource = item.Val(input)
}
return true
}
iter.PeekWalk(walkFn)
cf.FrontMatter, err = metadecoders.Default.UnmarshalToMap(frontMatterSource, cf.FrontMatterFormat)
return cf, err
}
func FormatFromFrontMatterType(typ ItemType) metadecoders.Format {
switch typ {
case TypeFrontMatterJSON:
return metadecoders.JSON
case TypeFrontMatterORG:
return metadecoders.ORG
case TypeFrontMatterTOML:
return metadecoders.TOML
case TypeFrontMatterYAML:
return metadecoders.YAML
default:
return ""
}
}
// ParseMain parses starting with the main section. Used in tests.
func ParseMain(r io.Reader, cfg Config) (Result, error) {
return parseSection(r, cfg, lexMainSection)
}
func parseSection(r io.Reader, cfg Config, start stateFunc) (Result, error) {
b, err := io.ReadAll(r)
if err != nil {
return nil, fmt.Errorf("failed to read page content: %w", err)
}
return parseBytes(b, cfg, start)
}
func parseBytes(b []byte, cfg Config, start stateFunc) (*pageLexer, error) {
lexer := newPageLexer(b, start, cfg)
lexer.run()
return lexer, nil
}
// NewIterator creates a new Iterator.
func NewIterator(items Items) *Iterator {
return &Iterator{items: items, lastPos: -1}
}
// An Iterator has methods to iterate a parsed page with support going back
// if needed.
type Iterator struct {
items Items
lastPos int // position of the last item returned by nextItem
}
// consumes and returns the next item
func (t *Iterator) Next() Item {
t.lastPos++
return t.Current()
}
var errIndexOutOfBounds = Item{Type: tError, Err: errors.New("no more tokens")}
// Current will repeatably return the current item.
func (t *Iterator) Current() Item {
if t.lastPos >= len(t.items) {
return errIndexOutOfBounds
}
return t.items[t.lastPos]
}
// backs up one token.
func (t *Iterator) Backup() {
if t.lastPos < 0 {
panic("need to go forward before going back")
}
t.lastPos--
}
// Pos returns the current position in the input.
func (t *Iterator) Pos() int {
return t.lastPos
}
// check for non-error and non-EOF types coming next
func (t *Iterator) IsValueNext() bool {
i := t.Peek()
return i.Type != tError && i.Type != tEOF
}
// look at, but do not consume, the next item
// repeated, sequential calls will return the same item
func (t *Iterator) Peek() Item {
return t.items[t.lastPos+1]
}
// PeekWalk will feed the next items in the iterator to walkFn
// until it returns false.
func (t *Iterator) PeekWalk(walkFn func(item Item) bool) {
for i := t.lastPos + 1; i < len(t.items); i++ {
item := t.items[i]
if !walkFn(item) {
break
}
}
}
// Consume is a convenience method to consume the next n tokens,
// but back off Errors and EOF.
func (t *Iterator) Consume(cnt int) {
for i := 0; i < cnt; i++ {
token := t.Next()
if token.Type == tError || token.Type == tEOF {
t.Backup()
break
}
}
}
// LineNumber returns the current line number. Used for logging.
func (t *Iterator) LineNumber(source []byte) int {
return bytes.Count(source[:t.Current().low], lf) + 1
}
// IsProbablySourceOfItems returns true if the given source looks like original
// source of the items.
// There may be some false positives, but that is highly unlikely and good enough
// for the planned purpose.
// It will also return false if the last item is not EOF (error situations) and
// true if both source and items are empty.
func IsProbablySourceOfItems(source []byte, items Items) bool {
if len(source) == 0 && len(items) == 0 {
return false
}
if len(items) == 0 {
return false
}
last := items[len(items)-1]
if last.Type != tEOF {
return false
}
if last.Pos() != len(source) {
return false
}
for _, item := range items {
if item.Type == tError {
return false
}
if item.Type == tEOF {
return true
}
if item.Pos() >= len(source) {
return false
}
if item.firstByte != source[item.Pos()] {
return false
}
}
return true
}
var hasShortcodeRe = regexp.MustCompile(`{{[%,<][^\/]`)
// HasShortcode returns true if the given string contains a shortcode.
func HasShortcode(s string) bool {
// Fast path for the common case.
if !strings.Contains(s, "{{") {
return false
}
return hasShortcodeRe.MatchString(s)
}