hugo/common/herrors/file_error.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

422 lines
10 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 lfmtaw 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 herrors
import (
"encoding/json"
"errors"
"fmt"
"io"
"path/filepath"
godartsassv1 "github.com/bep/godartsass"
"github.com/bep/godartsass/v2"
"github.com/bep/golibsass/libsass/libsasserrors"
"github.com/gohugoio/hugo/common/paths"
"github.com/gohugoio/hugo/common/text"
"github.com/pelletier/go-toml/v2"
"github.com/spf13/afero"
"github.com/tdewolff/parse/v2"
)
// FileError represents an error when handling a file: Parsing a config file,
// execute a template etc.
type FileError interface {
error
// ErrorContext holds some context information about the error.
ErrorContext() *ErrorContext
text.Positioner
// UpdatePosition updates the position of the error.
UpdatePosition(pos text.Position) FileError
// UpdateContent updates the error with a new ErrorContext from the content of the file.
UpdateContent(r io.Reader, linematcher LineMatcherFn) FileError
// SetFilename sets the filename of the error.
SetFilename(filename string) FileError
}
// Unwrapper can unwrap errors created with fmt.Errorf.
type Unwrapper interface {
Unwrap() error
}
var (
_ FileError = (*fileError)(nil)
_ Unwrapper = (*fileError)(nil)
)
func (fe *fileError) SetFilename(filename string) FileError {
fe.position.Filename = filename
return fe
}
func (fe *fileError) UpdatePosition(pos text.Position) FileError {
oldFilename := fe.Position().Filename
if pos.Filename != "" && fe.fileType == "" {
_, fe.fileType = paths.FileAndExtNoDelimiter(filepath.Clean(pos.Filename))
}
if pos.Filename == "" {
pos.Filename = oldFilename
}
fe.position = pos
return fe
}
func (fe *fileError) UpdateContent(r io.Reader, linematcher LineMatcherFn) FileError {
if linematcher == nil {
linematcher = SimpleLineMatcher
}
var (
posle = fe.position
ectx *ErrorContext
)
if posle.LineNumber <= 1 && posle.Offset > 0 {
// Try to locate the line number from the content if offset is set.
ectx = locateError(r, fe, func(m LineMatcher) int {
if posle.Offset >= m.Offset && posle.Offset < m.Offset+len(m.Line) {
lno := posle.LineNumber - m.Position.LineNumber + m.LineNumber
m.Position = text.Position{LineNumber: lno}
return linematcher(m)
}
return -1
})
} else {
ectx = locateError(r, fe, linematcher)
}
if ectx.ChromaLexer == "" {
if fe.fileType != "" {
ectx.ChromaLexer = chromaLexerFromType(fe.fileType)
} else {
ectx.ChromaLexer = chromaLexerFromFilename(fe.Position().Filename)
}
}
fe.errorContext = ectx
if ectx.Position.LineNumber > 0 {
fe.position.LineNumber = ectx.Position.LineNumber
}
if ectx.Position.ColumnNumber > 0 {
fe.position.ColumnNumber = ectx.Position.ColumnNumber
}
return fe
}
type fileError struct {
position text.Position
errorContext *ErrorContext
fileType string
cause error
}
func (e *fileError) ErrorContext() *ErrorContext {
return e.errorContext
}
// Position returns the text position of this error.
func (e fileError) Position() text.Position {
return e.position
}
func (e *fileError) Error() string {
return fmt.Sprintf("%s: %s", e.position, e.causeString())
}
func (e *fileError) causeString() string {
if e.cause == nil {
return ""
}
switch v := e.cause.(type) {
// Avoid repeating the file info in the error message.
case godartsass.SassError:
return v.Message
case godartsassv1.SassError:
return v.Message
case libsasserrors.Error:
return v.Message
default:
return v.Error()
}
}
func (e *fileError) Unwrap() error {
return e.cause
}
// NewFileError creates a new FileError that wraps err.
// It will try to extract the filename and line number from err.
func NewFileError(err error) FileError {
// Filetype is used to determine the Chroma lexer to use.
fileType, pos := extractFileTypePos(err)
return &fileError{cause: err, fileType: fileType, position: pos}
}
// NewFileErrorFromName creates a new FileError that wraps err.
// The value for name should identify the file, the best
// being the full filename to the file on disk.
func NewFileErrorFromName(err error, name string) FileError {
// Filetype is used to determine the Chroma lexer to use.
fileType, pos := extractFileTypePos(err)
pos.Filename = name
if fileType == "" {
_, fileType = paths.FileAndExtNoDelimiter(filepath.Clean(name))
}
return &fileError{cause: err, fileType: fileType, position: pos}
}
// NewFileErrorFromPos will use the filename and line number from pos to create a new FileError, wrapping err.
func NewFileErrorFromPos(err error, pos text.Position) FileError {
// Filetype is used to determine the Chroma lexer to use.
fileType, _ := extractFileTypePos(err)
if fileType == "" {
_, fileType = paths.FileAndExtNoDelimiter(filepath.Clean(pos.Filename))
}
return &fileError{cause: err, fileType: fileType, position: pos}
}
func NewFileErrorFromFileInErr(err error, fs afero.Fs, linematcher LineMatcherFn) FileError {
fe := NewFileError(err)
pos := fe.Position()
if pos.Filename == "" {
return fe
}
f, realFilename, err2 := openFile(pos.Filename, fs)
if err2 != nil {
return fe
}
pos.Filename = realFilename
defer f.Close()
return fe.UpdateContent(f, linematcher)
}
func NewFileErrorFromFileInPos(err error, pos text.Position, fs afero.Fs, linematcher LineMatcherFn) FileError {
if err == nil {
panic("err is nil")
}
f, realFilename, err2 := openFile(pos.Filename, fs)
if err2 != nil {
return NewFileErrorFromPos(err, pos)
}
pos.Filename = realFilename
defer f.Close()
return NewFileErrorFromPos(err, pos).UpdateContent(f, linematcher)
}
// NewFileErrorFromFile is a convenience method to create a new FileError from a file.
func NewFileErrorFromFile(err error, filename string, fs afero.Fs, linematcher LineMatcherFn) FileError {
if err == nil {
panic("err is nil")
}
f, realFilename, err2 := openFile(filename, fs)
if err2 != nil {
return NewFileErrorFromName(err, realFilename)
}
defer f.Close()
return NewFileErrorFromName(err, realFilename).UpdateContent(f, linematcher)
}
func openFile(filename string, fs afero.Fs) (afero.File, string, error) {
realFilename := filename
// We want the most specific filename possible in the error message.
fi, err2 := fs.Stat(filename)
if err2 == nil {
if s, ok := fi.(interface {
Filename() string
}); ok {
realFilename = s.Filename()
}
}
f, err2 := fs.Open(filename)
if err2 != nil {
return nil, realFilename, err2
}
return f, realFilename, nil
}
// Cause returns the underlying error or itself if it does not implement Unwrap.
func Cause(err error) error {
if u := errors.Unwrap(err); u != nil {
return u
}
return err
}
func extractFileTypePos(err error) (string, text.Position) {
err = Cause(err)
var fileType string
// LibSass, DartSass
if pos := extractPosition(err); pos.LineNumber > 0 || pos.Offset > 0 {
_, fileType = paths.FileAndExtNoDelimiter(pos.Filename)
return fileType, pos
}
// Default to line 1 col 1 if we don't find any better.
pos := text.Position{
Offset: -1,
LineNumber: 1,
ColumnNumber: 1,
}
// JSON errors.
offset, typ := extractOffsetAndType(err)
if fileType == "" {
fileType = typ
}
if offset >= 0 {
pos.Offset = offset
}
// The error type from the minifier contains line number and column number.
if line, col := extractLineNumberAndColumnNumber(err); line >= 0 {
pos.LineNumber = line
pos.ColumnNumber = col
return fileType, pos
}
// Look in the error message for the line number.
for _, handle := range lineNumberExtractors {
lno, col := handle(err)
if lno > 0 {
pos.ColumnNumber = col
pos.LineNumber = lno
break
}
}
if fileType == "" && pos.Filename != "" {
_, fileType = paths.FileAndExtNoDelimiter(pos.Filename)
}
return fileType, pos
}
// UnwrapFileError tries to unwrap a FileError from err.
// It returns nil if this is not possible.
func UnwrapFileError(err error) FileError {
for err != nil {
switch v := err.(type) {
case FileError:
return v
default:
err = errors.Unwrap(err)
}
}
return nil
}
// UnwrapFileErrors tries to unwrap all FileError.
func UnwrapFileErrors(err error) []FileError {
var errs []FileError
for err != nil {
if v, ok := err.(FileError); ok {
errs = append(errs, v)
}
err = errors.Unwrap(err)
}
return errs
}
// UnwrapFileErrorsWithErrorContext tries to unwrap all FileError in err that has an ErrorContext.
func UnwrapFileErrorsWithErrorContext(err error) []FileError {
var errs []FileError
for err != nil {
if v, ok := err.(FileError); ok && v.ErrorContext() != nil {
errs = append(errs, v)
}
err = errors.Unwrap(err)
}
return errs
}
func extractOffsetAndType(e error) (int, string) {
switch v := e.(type) {
case *json.UnmarshalTypeError:
return int(v.Offset), "json"
case *json.SyntaxError:
return int(v.Offset), "json"
default:
return -1, ""
}
}
func extractLineNumberAndColumnNumber(e error) (int, int) {
switch v := e.(type) {
case *parse.Error:
return v.Line, v.Column
case *toml.DecodeError:
return v.Position()
}
return -1, -1
}
func extractPosition(e error) (pos text.Position) {
switch v := e.(type) {
case godartsass.SassError:
span := v.Span
start := span.Start
filename, _ := paths.UrlToFilename(span.Url)
pos.Filename = filename
pos.Offset = start.Offset
pos.ColumnNumber = start.Column
case godartsassv1.SassError:
span := v.Span
start := span.Start
filename, _ := paths.UrlToFilename(span.Url)
pos.Filename = filename
pos.Offset = start.Offset
pos.ColumnNumber = start.Column
case libsasserrors.Error:
pos.Filename = v.File
pos.LineNumber = v.Line
pos.ColumnNumber = v.Column
}
return
}
// TextSegmentError is an error with a text segment attached.
type TextSegmentError struct {
Segment string
Err error
}
func (e TextSegmentError) Unwrap() error {
return e.Err
}
func (e TextSegmentError) Error() string {
return e.Err.Error()
}