Files
hugo/common/hstrings/strings.go
T
Bjørn Erik Pedersen 555dfa207a Speedup and simplify page assembly for deeper content trees
This commit moves to a forked version go-radix (fork source has not had any updates in 3 years.), whith 2 notable changes:

* It's generic (using Go generics) and thus removes a lot of type conversions/assertions.
* It allows nodes to be replaced during walk, which allows to partition the tree for parallel processing without worrying about locking.

For this repo, this means:

* The assembly step now processes nested sections in parallel, which gives a speedup for deep content trees with a slight allocation penalty (see benchmarks below).
* Nodes that needs to be reinserted are inserted directly.
* Also, there are some drive-by fixes of some allocation issues, e.g. avoid wrapping mutexes in returned anonomous functions, a common source of hidden allocations.

```
                                                                                   │ master.bench │           perf-p3.bench            │
                                                                                   │    sec/op    │   sec/op     vs base               │
AssembleDeepSiteWithManySections/depth=1/sectionsPerLevel=1/pagesPerSection=50-10     6.958m ± 3%   7.015m ± 3%        ~ (p=0.589 n=6)
AssembleDeepSiteWithManySections/depth=1/sectionsPerLevel=6/pagesPerSection=100-10    14.25m ± 1%   14.56m ± 8%        ~ (p=0.394 n=6)
AssembleDeepSiteWithManySections/depth=1/sectionsPerLevel=6/pagesPerSection=500-10    48.07m ± 3%   49.23m ± 3%        ~ (p=0.394 n=6)
AssembleDeepSiteWithManySections/depth=2/sectionsPerLevel=6/pagesPerSection=100-10    66.66m ± 4%   66.47m ± 6%        ~ (p=0.485 n=6)
AssembleDeepSiteWithManySections/depth=4/sectionsPerLevel=2/pagesPerSection=100-10    59.57m ± 4%   50.73m ± 5%  -14.85% (p=0.002 n=6)
geomean                                                                               28.54m        27.92m        -2.18%

                                                                                   │ master.bench │           perf-p3.bench            │
                                                                                   │     B/op     │     B/op      vs base              │
AssembleDeepSiteWithManySections/depth=1/sectionsPerLevel=1/pagesPerSection=50-10    4.513Mi ± 0%   4.527Mi ± 0%  +0.33% (p=0.002 n=6)
AssembleDeepSiteWithManySections/depth=1/sectionsPerLevel=6/pagesPerSection=100-10   15.35Mi ± 0%   15.49Mi ± 0%  +0.94% (p=0.002 n=6)
AssembleDeepSiteWithManySections/depth=1/sectionsPerLevel=6/pagesPerSection=500-10   62.50Mi ± 0%   63.19Mi ± 0%  +1.10% (p=0.002 n=6)
AssembleDeepSiteWithManySections/depth=2/sectionsPerLevel=6/pagesPerSection=100-10   86.78Mi ± 0%   87.73Mi ± 0%  +1.09% (p=0.002 n=6)
AssembleDeepSiteWithManySections/depth=4/sectionsPerLevel=2/pagesPerSection=100-10   62.96Mi ± 0%   63.66Mi ± 0%  +1.12% (p=0.002 n=6)
geomean                                                                              29.84Mi        30.11Mi       +0.92%

                                                                                   │ master.bench │           perf-p3.bench           │
                                                                                   │  allocs/op   │  allocs/op   vs base              │
AssembleDeepSiteWithManySections/depth=1/sectionsPerLevel=1/pagesPerSection=50-10     60.44k ± 0%   60.97k ± 0%  +0.87% (p=0.002 n=6)
AssembleDeepSiteWithManySections/depth=1/sectionsPerLevel=6/pagesPerSection=100-10    205.8k ± 0%   211.4k ± 0%  +2.70% (p=0.002 n=6)
AssembleDeepSiteWithManySections/depth=1/sectionsPerLevel=6/pagesPerSection=500-10    831.1k ± 0%   858.3k ± 0%  +3.27% (p=0.002 n=6)
AssembleDeepSiteWithManySections/depth=2/sectionsPerLevel=6/pagesPerSection=100-10    1.157M ± 0%   1.197M ± 0%  +3.41% (p=0.002 n=6)
AssembleDeepSiteWithManySections/depth=4/sectionsPerLevel=2/pagesPerSection=100-10    839.9k ± 0%   867.8k ± 0%  +3.31% (p=0.002 n=6)
geomean                                                                               398.5k        409.3k       +2.71%
```
2025-11-25 11:37:05 +01:00

200 lines
4.6 KiB
Go

// 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 hstrings
import (
"fmt"
"regexp"
"slices"
"sort"
"strings"
"sync"
"github.com/gohugoio/hugo/compare"
)
var _ compare.Eqer = StringEqualFold("")
// StringEqualFold is a string that implements the compare.Eqer interface and considers
// two strings equal if they are equal when folded to lower case.
// The compare.Eqer interface is used in Hugo to compare values in templates (e.g. using the eq template function).
type StringEqualFold string
func (s StringEqualFold) EqualFold(s2 string) bool {
return strings.EqualFold(string(s), s2)
}
func (s StringEqualFold) String() string {
return string(s)
}
func (s StringEqualFold) Eq(s2 any) bool {
switch ss := s2.(type) {
case string:
return s.EqualFold(ss)
case fmt.Stringer:
return s.EqualFold(ss.String())
}
return false
}
// EqualAny returns whether a string is equal to any of the given strings.
func EqualAny(a string, b ...string) bool {
return slices.Contains(b, a)
}
// regexpCache represents a cache of regexp objects protected by a mutex.
type regexpCache struct {
mu sync.RWMutex
re map[string]*regexp.Regexp
}
func (rc *regexpCache) getOrCompileRegexp(pattern string) (re *regexp.Regexp, err error) {
var ok bool
if re, ok = rc.get(pattern); !ok {
re, err = regexp.Compile(pattern)
if err != nil {
return nil, err
}
rc.set(pattern, re)
}
return re, nil
}
func (rc *regexpCache) get(key string) (re *regexp.Regexp, ok bool) {
rc.mu.RLock()
re, ok = rc.re[key]
rc.mu.RUnlock()
return
}
func (rc *regexpCache) set(key string, re *regexp.Regexp) {
rc.mu.Lock()
rc.re[key] = re
rc.mu.Unlock()
}
var reCache = regexpCache{re: make(map[string]*regexp.Regexp)}
// GetOrCompileRegexp retrieves a regexp object from the cache based upon the pattern.
// If the pattern is not found in the cache, the pattern is compiled and added to
// the cache.
func GetOrCompileRegexp(pattern string) (re *regexp.Regexp, err error) {
return reCache.getOrCompileRegexp(pattern)
}
// HasAnyPrefix checks if the string s has any of the prefixes given.
func HasAnyPrefix(s string, prefixes ...string) bool {
for _, p := range prefixes {
if strings.HasPrefix(s, p) {
return true
}
}
return false
}
// InSlice checks if a string is an element of a slice of strings
// and returns a boolean value.
func InSlice(arr []string, el string) bool {
return slices.Contains(arr, el)
}
// InSlicEqualFold checks if a string is an element of a slice of strings
// and returns a boolean value.
// It uses strings.EqualFold to compare.
func InSlicEqualFold(arr []string, el string) bool {
for _, v := range arr {
if strings.EqualFold(v, el) {
return true
}
}
return false
}
// ToString converts the given value to a string.
// Note that this is a more strict version compared to cast.ToString,
// as it will not try to convert numeric values to strings,
// but only accept strings or fmt.Stringer.
func ToString(v any) (string, bool) {
switch vv := v.(type) {
case string:
return vv, true
case fmt.Stringer:
return vv.String(), true
}
return "", false
}
// UniqueStrings returns a new slice with any duplicates removed.
func UniqueStrings(s []string) []string {
unique := make([]string, 0, len(s))
for i, val := range s {
var seen bool
for j := range i {
if s[j] == val {
seen = true
break
}
}
if !seen {
unique = append(unique, val)
}
}
return unique
}
// UniqueStringsReuse returns a slice with any duplicates removed.
// It will modify the input slice.
func UniqueStringsReuse(s []string) []string {
result := s[:0]
for i, val := range s {
var seen bool
for j := range i {
if s[j] == val {
seen = true
break
}
}
if !seen {
result = append(result, val)
}
}
return result
}
// UniqueStringsSorted returns a sorted slice with any duplicates removed.
// It will modify the input slice.
func UniqueStringsSorted(s []string) []string {
if len(s) == 0 {
return nil
}
ss := sort.StringSlice(s)
ss.Sort()
i := 0
for j := 1; j < len(s); j++ {
if !ss.Less(i, j) {
continue
}
i++
s[i] = s[j]
}
return s[:i+1]
}