2015-12-07 13:57:01 -05:00
// Copyright 2015 The Hugo Authors. All rights reserved.
2014-02-27 18:32:09 -05:00
//
2015-11-23 22:16:36 -05:00
// Licensed under the Apache License, Version 2.0 (the "License");
2014-02-27 18:32:09 -05:00
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
2015-11-23 22:16:36 -05:00
// http://www.apache.org/licenses/LICENSE-2.0
2014-02-27 18:32:09 -05:00
//
// 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 helpers
import (
"bytes"
2014-10-16 20:20:09 -04:00
"crypto/md5"
"encoding/hex"
2014-05-15 15:07:46 -04:00
"fmt"
2014-10-16 20:20:09 -04:00
"io"
2014-05-15 15:07:46 -04:00
"net"
2014-12-07 13:48:00 -05:00
"path/filepath"
2014-02-27 18:32:09 -05:00
"strings"
2015-03-12 11:10:14 -04:00
"sync"
2015-05-28 17:05:13 -04:00
"unicode"
"unicode/utf8"
2015-01-30 09:17:50 -05:00
2017-07-30 11:46:04 -04:00
"github.com/jdkato/prose/transform"
2017-06-13 12:42:45 -04:00
bp "github.com/gohugoio/hugo/bufferpool"
2017-06-13 13:07:35 -04:00
"github.com/spf13/cast"
2015-01-30 09:17:50 -05:00
jww "github.com/spf13/jwalterweatherman"
2015-09-09 01:05:11 -04:00
"github.com/spf13/pflag"
2014-02-27 18:32:09 -05:00
)
2016-03-22 18:53:19 -04:00
// FilePathSeparator as defined by os.Separator.
2014-12-07 13:48:00 -05:00
const FilePathSeparator = string ( filepath . Separator )
2017-01-01 17:16:58 -05:00
// Strips carriage returns from third-party / external processes (useful for Windows)
func normalizeExternalHelperLineFeeds ( content [ ] byte ) [ ] byte {
return bytes . Replace ( content , [ ] byte ( "\r" ) , [ ] byte ( "" ) , - 1 )
}
2015-03-06 18:02:06 -05:00
// FindAvailablePort returns an available and valid TCP port.
2014-05-15 15:07:46 -04:00
func FindAvailablePort ( ) ( * net . TCPAddr , error ) {
l , err := net . Listen ( "tcp" , ":0" )
if err == nil {
defer l . Close ( )
addr := l . Addr ( )
if a , ok := addr . ( * net . TCPAddr ) ; ok {
return a , nil
}
return nil , fmt . Errorf ( "Unable to obtain a valid tcp port. %v" , addr )
}
return nil , err
}
2014-10-16 20:20:09 -04:00
2014-12-26 10:07:03 -05:00
// InStringArray checks if a string is an element of a slice of strings
// and returns a boolean value.
2014-10-20 20:15:33 -04:00
func InStringArray ( arr [ ] string , el string ) bool {
for _ , v := range arr {
if v == el {
return true
}
}
return false
}
2014-12-11 15:57:25 -05:00
// GuessType attempts to guess the type of file from a given string.
2014-10-16 20:20:09 -04:00
func GuessType ( in string ) string {
switch strings . ToLower ( in ) {
case "md" , "markdown" , "mdown" :
return "markdown"
Experimental AsciiDoc support with external helpers
See #470
* Based on existing support for reStructuredText files
* Handles content files with extensions `.asciidoc` and `.ad`
* Pipes content through `asciidoctor --safe -`.
If `asciidoctor` is not installed, then `asciidoc --safe -`.
* To make sure `asciidoctor` or `asciidoc` is found, after adding
a piece of AsciiDoc content, run `hugo` with the `-v` flag
and look for this message:
INFO: 2015/01/23 Rendering with /usr/bin/asciidoctor ...
Caveats:
* The final "Last updated" timestamp is currently not stripped.
* When `hugo` is run with `-v`, you may see a lot of these messages
INFO: 2015/01/23 Rendering with /usr/bin/asciidoctor ...
if you have lots of `*.ad`, `*.adoc` or `*.asciidoc` files.
* Some versions of `asciidoc` may have trouble with its safe mode.
To test if you are affected, try this:
$ echo "Hello" | asciidoc --safe -
asciidoc: ERROR: unsafe: ifeval invalid
asciidoc: FAILED: ifeval invalid safe document
If so, I recommend that you install `asciidoctor` instead.
Feedback and patches welcome!
Ideally, we should be using https://github.com/VonC/asciidocgo,
@VonC's wonderful Go implementation of Asciidoctor. However,
there is still a bit of work needed for asciidocgo to expose
its API so that Hugo can actually use it.
Until then, hope this "experimental AsciiDoc support through external
helpers" can serve as a stopgap solution for our community. :-)
2015-01-30: Updated for the replaceShortcodeTokens() syntax change
2015-02-21: Add `.adoc` extension as suggested by @Fale
Conflicts:
helpers/content.go
2015-01-23 13:59:14 -05:00
case "asciidoc" , "adoc" , "ad" :
return "asciidoc"
2015-01-30 09:17:50 -05:00
case "mmark" :
return "mmark"
2014-10-16 20:20:09 -04:00
case "rst" :
return "rst"
2017-11-30 06:15:52 -05:00
case "pandoc" , "pdc" :
return "pandoc"
2014-10-16 20:20:09 -04:00
case "html" , "htm" :
return "html"
2017-02-21 02:46:03 -05:00
case "org" :
return "org"
2014-10-16 20:20:09 -04:00
}
return "unknown"
}
2015-05-28 17:05:13 -04:00
// FirstUpper returns a string with the first character as upper case.
func FirstUpper ( s string ) string {
if s == "" {
return ""
}
r , n := utf8 . DecodeRuneInString ( s )
return string ( unicode . ToUpper ( r ) ) + s [ n : ]
}
2015-11-23 10:32:06 -05:00
// UniqueStrings returns a new slice with any duplicates removed.
func UniqueStrings ( s [ ] string ) [ ] string {
2016-03-22 18:53:19 -04:00
var unique [ ] string
2015-11-23 10:32:06 -05:00
set := map [ string ] interface { } { }
for _ , val := range s {
if _ , ok := set [ val ] ; ! ok {
unique = append ( unique , val )
set [ val ] = val
}
}
return unique
}
2014-12-26 10:07:03 -05:00
// ReaderToBytes takes an io.Reader argument, reads from it
// and returns bytes.
2014-10-16 20:20:09 -04:00
func ReaderToBytes ( lines io . Reader ) [ ] byte {
2015-03-12 15:50:44 -04:00
if lines == nil {
return [ ] byte { }
}
2015-01-30 14:12:07 -05:00
b := bp . GetBuffer ( )
defer bp . PutBuffer ( b )
2014-10-16 20:20:09 -04:00
b . ReadFrom ( lines )
2015-01-30 14:12:07 -05:00
bc := make ( [ ] byte , b . Len ( ) , b . Len ( ) )
copy ( bc , b . Bytes ( ) )
return bc
2014-10-16 20:20:09 -04:00
}
2016-10-16 13:28:21 -04:00
// ToLowerMap makes all the keys in the given map lower cased and will do so
// recursively.
// Notes:
// * This will modify the map given.
// * Any nested map[interface{}]interface{} will be converted to map[string]interface{}.
func ToLowerMap ( m map [ string ] interface { } ) {
for k , v := range m {
switch v . ( type ) {
case map [ interface { } ] interface { } :
v = cast . ToStringMap ( v )
ToLowerMap ( v . ( map [ string ] interface { } ) )
case map [ string ] interface { } :
ToLowerMap ( v . ( map [ string ] interface { } ) )
}
lKey := strings . ToLower ( k )
if k != lKey {
delete ( m , k )
2016-10-16 16:49:21 -04:00
m [ lKey ] = v
2016-10-16 13:28:21 -04:00
}
2016-10-16 16:49:21 -04:00
2016-10-16 13:28:21 -04:00
}
}
2014-12-26 10:07:03 -05:00
// ReaderToString is the same as ReaderToBytes, but returns a string.
2014-11-04 00:26:56 -05:00
func ReaderToString ( lines io . Reader ) string {
2015-03-12 15:50:44 -04:00
if lines == nil {
return ""
}
2015-01-30 14:12:07 -05:00
b := bp . GetBuffer ( )
defer bp . PutBuffer ( b )
2014-11-04 00:26:56 -05:00
b . ReadFrom ( lines )
return b . String ( )
}
2015-03-29 15:12:13 -04:00
// ReaderContains reports whether subslice is within r.
func ReaderContains ( r io . Reader , subslice [ ] byte ) bool {
2015-03-29 19:22:08 -04:00
if r == nil || len ( subslice ) == 0 {
2015-03-29 15:12:13 -04:00
return false
}
bufflen := len ( subslice ) * 4
halflen := bufflen / 2
buff := make ( [ ] byte , bufflen )
var err error
var n , i int
for {
i ++
if i == 1 {
n , err = io . ReadAtLeast ( r , buff [ : halflen ] , halflen )
} else {
if i != 2 {
// shift left to catch overlapping matches
copy ( buff [ : ] , buff [ halflen : ] )
}
n , err = io . ReadAtLeast ( r , buff [ halflen : ] , halflen )
}
if n > 0 && bytes . Contains ( buff , subslice ) {
return true
}
if err != nil {
break
}
}
return false
}
2017-07-30 11:46:04 -04:00
// GetTitleFunc returns a func that can be used to transform a string to
// title case.
//
// The supported styles are
//
// - "Go" (strings.Title)
// - "AP" (see https://www.apstylebook.com/)
// - "Chicago" (see http://www.chicagomanualofstyle.org/home.html)
//
// If an unknown or empty style is provided, AP style is what you get.
func GetTitleFunc ( style string ) func ( s string ) string {
switch strings . ToLower ( style ) {
case "go" :
return strings . Title
case "chicago" :
tc := transform . NewTitleConverter ( transform . ChicagoStyle )
return tc . Title
default :
tc := transform . NewTitleConverter ( transform . APStyle )
return tc . Title
}
}
2017-07-02 14:14:06 -04:00
// HasStringsPrefix tests whether the string slice s begins with prefix slice s.
func HasStringsPrefix ( s , prefix [ ] string ) bool {
return len ( s ) >= len ( prefix ) && compareStringSlices ( s [ 0 : len ( prefix ) ] , prefix )
}
// HasStringsSuffix tests whether the string slice s ends with suffix slice s.
func HasStringsSuffix ( s , suffix [ ] string ) bool {
return len ( s ) >= len ( suffix ) && compareStringSlices ( s [ len ( s ) - len ( suffix ) : ] , suffix )
}
func compareStringSlices ( a , b [ ] string ) bool {
if a == nil && b == nil {
return true
}
if a == nil || b == nil {
return false
}
if len ( a ) != len ( b ) {
return false
}
for i := range a {
if a [ i ] != b [ i ] {
return false
}
}
return true
}
2015-03-06 18:02:06 -05:00
// ThemeSet checks whether a theme is in use or not.
2017-02-04 22:20:06 -05:00
func ( p * PathSpec ) ThemeSet ( ) bool {
return p . theme != ""
2015-02-11 14:24:56 -05:00
}
2016-01-28 08:00:03 -05:00
type logPrinter interface {
2016-01-28 09:31:25 -05:00
// Println is the only common method that works in all of JWWs loggers.
2016-01-28 08:00:03 -05:00
Println ( a ... interface { } )
}
// DistinctLogger ignores duplicate log statements.
type DistinctLogger struct {
2015-03-12 11:10:14 -04:00
sync . RWMutex
2016-01-28 08:00:03 -05:00
logger logPrinter
m map [ string ] bool
2015-03-31 16:33:24 -04:00
}
2015-03-12 11:10:14 -04:00
2016-01-28 09:31:25 -05:00
// Println will log the string returned from fmt.Sprintln given the arguments,
// but not if it has been logged before.
func ( l * DistinctLogger ) Println ( v ... interface { } ) {
// fmt.Sprint doesn't add space between string arguments
logStatement := strings . TrimSpace ( fmt . Sprintln ( v ... ) )
l . print ( logStatement )
}
2016-01-28 08:00:03 -05:00
// Printf will log the string returned from fmt.Sprintf given the arguments,
2015-04-03 16:29:57 -04:00
// but not if it has been logged before.
2016-01-28 09:31:25 -05:00
// Note: A newline is appended.
2016-01-28 08:00:03 -05:00
func ( l * DistinctLogger ) Printf ( format string , v ... interface { } ) {
2015-03-31 16:33:24 -04:00
logStatement := fmt . Sprintf ( format , v ... )
2016-01-28 09:31:25 -05:00
l . print ( logStatement )
}
func ( l * DistinctLogger ) print ( logStatement string ) {
2015-03-31 16:33:24 -04:00
l . RLock ( )
2015-04-03 15:16:36 -04:00
if l . m [ logStatement ] {
l . RUnlock ( )
2015-03-12 11:10:14 -04:00
return
}
2015-04-03 15:16:36 -04:00
l . RUnlock ( )
2015-03-31 16:33:24 -04:00
l . Lock ( )
if ! l . m [ logStatement ] {
2016-01-28 08:00:03 -05:00
l . logger . Println ( logStatement )
2015-03-31 16:33:24 -04:00
l . m [ logStatement ] = true
2015-03-12 13:51:31 -04:00
}
2015-03-31 16:33:24 -04:00
l . Unlock ( )
}
2016-01-28 08:00:03 -05:00
// NewDistinctErrorLogger creates a new DistinctLogger that logs ERRORs
func NewDistinctErrorLogger ( ) * DistinctLogger {
return & DistinctLogger { m : make ( map [ string ] bool ) , logger : jww . ERROR }
2015-03-31 16:33:24 -04:00
}
2017-03-29 02:08:45 -04:00
// NewDistinctWarnLogger creates a new DistinctLogger that logs WARNs
func NewDistinctWarnLogger ( ) * DistinctLogger {
return & DistinctLogger { m : make ( map [ string ] bool ) , logger : jww . WARN }
}
2016-03-22 18:53:19 -04:00
// NewDistinctFeedbackLogger creates a new DistinctLogger that can be used
2016-01-28 09:31:25 -05:00
// to give feedback to the user while not spamming with duplicates.
func NewDistinctFeedbackLogger ( ) * DistinctLogger {
2017-01-03 10:57:43 -05:00
return & DistinctLogger { m : make ( map [ string ] bool ) , logger : jww . FEEDBACK }
2016-01-28 09:31:25 -05:00
}
2016-11-23 11:26:13 -05:00
var (
// DistinctErrorLog can be used to avoid spamming the logs with errors.
DistinctErrorLog = NewDistinctErrorLogger ( )
2017-03-29 02:08:45 -04:00
// DistinctWarnLog can be used to avoid spamming the logs with warnings.
DistinctWarnLog = NewDistinctWarnLogger ( )
2016-11-23 11:26:13 -05:00
// DistinctFeedbackLog can be used to avoid spamming the logs with info messages.
DistinctFeedbackLog = NewDistinctFeedbackLogger ( )
)
2015-03-31 16:33:24 -04:00
2016-09-08 10:04:04 -04:00
// InitLoggers sets up the global distinct loggers.
func InitLoggers ( ) {
2017-04-04 05:02:12 -04:00
DistinctErrorLog = NewDistinctErrorLogger ( )
DistinctWarnLog = NewDistinctWarnLogger ( )
DistinctFeedbackLog = NewDistinctFeedbackLogger ( )
2016-09-08 10:04:04 -04:00
}
2016-11-23 11:26:13 -05:00
// Deprecated informs about a deprecation, but only once for a given set of arguments' values.
// If the err flag is enabled, it logs as an ERROR (will exit with -1) and the text will
// point at the next Hugo release.
// The idea is two remove an item in two Hugo releases to give users and theme authors
// plenty of time to fix their templates.
func Deprecated ( object , item , alternative string , err bool ) {
if err {
2017-04-13 10:59:05 -04:00
DistinctErrorLog . Printf ( "%s's %s is deprecated and will be removed in Hugo %s. %s." , object , item , CurrentHugoVersion . Next ( ) . ReleaseVersion ( ) , alternative )
2016-11-23 11:26:13 -05:00
} else {
// Make sure the users see this while avoiding build breakage. This will not lead to an os.Exit(-1)
2017-02-11 04:51:22 -05:00
DistinctFeedbackLog . Printf ( "WARNING: %s's %s is deprecated and will be removed in a future release. %s." , object , item , alternative )
2016-11-23 11:26:13 -05:00
}
2015-03-12 11:10:14 -04:00
}
2014-12-26 10:07:03 -05:00
// SliceToLower goes through the source slice and lowers all values.
2014-10-16 20:20:09 -04:00
func SliceToLower ( s [ ] string ) [ ] string {
if s == nil {
return nil
}
l := make ( [ ] string , len ( s ) )
for i , v := range s {
l [ i ] = strings . ToLower ( v )
}
return l
}
:sparkles: Implement Page bundling and image handling
This commit is not the smallest in Hugo's history.
Some hightlights include:
* Page bundles (for complete articles, keeping images and content together etc.).
* Bundled images can be processed in as many versions/sizes as you need with the three methods `Resize`, `Fill` and `Fit`.
* Processed images are cached inside `resources/_gen/images` (default) in your project.
* Symbolic links (both files and dirs) are now allowed anywhere inside /content
* A new table based build summary
* The "Total in nn ms" now reports the total including the handling of the files inside /static. So if it now reports more than you're used to, it is just **more real** and probably faster than before (see below).
A site building benchmark run compared to `v0.31.1` shows that this should be slightly faster and use less memory:
```bash
▶ ./benchSite.sh "TOML,num_langs=.*,num_root_sections=5,num_pages=(500|1000),tags_per_page=5,shortcodes,render"
benchmark old ns/op new ns/op delta
BenchmarkSiteBuilding/TOML,num_langs=1,num_root_sections=5,num_pages=500,tags_per_page=5,shortcodes,render-4 101785785 78067944 -23.30%
BenchmarkSiteBuilding/TOML,num_langs=1,num_root_sections=5,num_pages=1000,tags_per_page=5,shortcodes,render-4 185481057 149159919 -19.58%
BenchmarkSiteBuilding/TOML,num_langs=3,num_root_sections=5,num_pages=500,tags_per_page=5,shortcodes,render-4 103149918 85679409 -16.94%
BenchmarkSiteBuilding/TOML,num_langs=3,num_root_sections=5,num_pages=1000,tags_per_page=5,shortcodes,render-4 203515478 169208775 -16.86%
benchmark old allocs new allocs delta
BenchmarkSiteBuilding/TOML,num_langs=1,num_root_sections=5,num_pages=500,tags_per_page=5,shortcodes,render-4 532464 391539 -26.47%
BenchmarkSiteBuilding/TOML,num_langs=1,num_root_sections=5,num_pages=1000,tags_per_page=5,shortcodes,render-4 1056549 772702 -26.87%
BenchmarkSiteBuilding/TOML,num_langs=3,num_root_sections=5,num_pages=500,tags_per_page=5,shortcodes,render-4 555974 406630 -26.86%
BenchmarkSiteBuilding/TOML,num_langs=3,num_root_sections=5,num_pages=1000,tags_per_page=5,shortcodes,render-4 1086545 789922 -27.30%
benchmark old bytes new bytes delta
BenchmarkSiteBuilding/TOML,num_langs=1,num_root_sections=5,num_pages=500,tags_per_page=5,shortcodes,render-4 53243246 43598155 -18.12%
BenchmarkSiteBuilding/TOML,num_langs=1,num_root_sections=5,num_pages=1000,tags_per_page=5,shortcodes,render-4 105811617 86087116 -18.64%
BenchmarkSiteBuilding/TOML,num_langs=3,num_root_sections=5,num_pages=500,tags_per_page=5,shortcodes,render-4 54558852 44545097 -18.35%
BenchmarkSiteBuilding/TOML,num_langs=3,num_root_sections=5,num_pages=1000,tags_per_page=5,shortcodes,render-4 106903858 86978413 -18.64%
```
Fixes #3651
Closes #3158
Fixes #1014
Closes #2021
Fixes #1240
Updates #3757
2017-07-24 03:00:23 -04:00
// MD5String takes a string and returns its MD5 hash.
func MD5String ( f string ) string {
2014-10-16 20:20:09 -04:00
h := md5 . New ( )
h . Write ( [ ] byte ( f ) )
return hex . EncodeToString ( h . Sum ( [ ] byte { } ) )
}
2014-12-26 15:18:26 -05:00
2015-07-12 05:05:37 -04:00
// IsWhitespace determines if the given rune is whitespace.
func IsWhitespace ( r rune ) bool {
return r == ' ' || r == '\t' || r == '\n' || r == '\r'
}
2015-10-06 18:58:58 -04:00
// NormalizeHugoFlags facilitates transitions of Hugo command-line flags,
2015-09-09 01:05:11 -04:00
// e.g. --baseUrl to --baseURL, --uglyUrls to --uglyURLs
2015-10-02 00:47:34 -04:00
func NormalizeHugoFlags ( f * pflag . FlagSet , name string ) pflag . NormalizedName {
2015-09-09 01:05:11 -04:00
switch name {
case "baseUrl" :
name = "baseURL"
break
case "uglyUrls" :
name = "uglyURLs"
break
}
return pflag . NormalizedName ( name )
}
2016-08-04 04:36:44 -04:00
// DiffStringSlices returns the difference between two string slices.
// Useful in tests.
// See:
// http://stackoverflow.com/questions/19374219/how-to-find-the-difference-between-two-slices-of-strings-in-golang
func DiffStringSlices ( slice1 [ ] string , slice2 [ ] string ) [ ] string {
diffStr := [ ] string { }
m := map [ string ] int { }
for _ , s1Val := range slice1 {
m [ s1Val ] = 1
}
for _ , s2Val := range slice2 {
m [ s2Val ] = m [ s2Val ] + 1
}
for mKey , mVal := range m {
if mVal == 1 {
diffStr = append ( diffStr , mKey )
}
}
return diffStr
}