// Copyright © 2014 Steve Francia .
//
// Licensed under the Simple Public 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://opensource.org/licenses/Simple-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 helpers implements general utility functions that work with
// and on content. The helper functions defined here lay down the
// foundation of how Hugo works with files and filepaths, and perform
// string operations on content.
package helpers
import (
"bytes"
"html/template"
"os/exec"
"github.com/russross/blackfriday"
bp "github.com/spf13/hugo/bufferpool"
jww "github.com/spf13/jwalterweatherman"
"github.com/spf13/viper"
"strings"
"sync"
)
// Length of the summary that Hugo extracts from a content.
var SummaryLength = 70
// Custom divider let's user define where summarization ends.
var SummaryDivider = []byte("")
// Blackfriday holds configuration values for Blackfriday rendering.
type Blackfriday struct {
AngledQuotes bool
Fractions bool
PlainIdAnchors bool
Extensions []string
}
// NewBlackfriday creates a new Blackfriday with some sane defaults.
func NewBlackfriday() *Blackfriday {
return &Blackfriday{
AngledQuotes: false,
Fractions: true,
PlainIdAnchors: false,
}
}
var blackfridayExtensionMap = map[string]int{
"noIntraEmphasis": blackfriday.EXTENSION_NO_INTRA_EMPHASIS,
"tables": blackfriday.EXTENSION_TABLES,
"fencedCode": blackfriday.EXTENSION_FENCED_CODE,
"autolink": blackfriday.EXTENSION_AUTOLINK,
"strikethrough": blackfriday.EXTENSION_STRIKETHROUGH,
"laxHtmlBlocks": blackfriday.EXTENSION_LAX_HTML_BLOCKS,
"spaceHeaders": blackfriday.EXTENSION_SPACE_HEADERS,
"hardLineBreak": blackfriday.EXTENSION_HARD_LINE_BREAK,
"tabSizeEight": blackfriday.EXTENSION_TAB_SIZE_EIGHT,
"footnotes": blackfriday.EXTENSION_FOOTNOTES,
"noEmptyLineBeforeBlock": blackfriday.EXTENSION_NO_EMPTY_LINE_BEFORE_BLOCK,
"headerIds": blackfriday.EXTENSION_HEADER_IDS,
"titleblock": blackfriday.EXTENSION_TITLEBLOCK,
"autoHeaderIds": blackfriday.EXTENSION_AUTO_HEADER_IDS,
}
var stripHTMLReplacer = strings.NewReplacer("\n", " ", "
", "\n", " ", "\n", " ", "\n")
// StripHTML accepts a string, strips out all HTML tags and returns it.
func StripHTML(s string) string {
// Shortcut strings with no tags in them
if !strings.ContainsAny(s, "<>") {
return s
}
s = stripHTMLReplacer.Replace(s)
// Walk through the string removing all tags
b := bp.GetBuffer()
defer bp.PutBuffer(b)
inTag := false
for _, r := range s {
switch r {
case '<':
inTag = true
case '>':
inTag = false
default:
if !inTag {
b.WriteRune(r)
}
}
}
return b.String()
}
// StripEmptyNav strips out empty tags from content.
func StripEmptyNav(in []byte) []byte {
return bytes.Replace(in, []byte("\n \n\n"), []byte(``), -1)
}
// BytesToHTML converts bytes to type template.HTML.
func BytesToHTML(b []byte) template.HTML {
return template.HTML(string(b))
}
// GetHtmlRenderer creates a new Renderer with the given configuration.
func GetHtmlRenderer(defaultFlags int, ctx *RenderingContext) blackfriday.Renderer {
renderParameters := blackfriday.HtmlRendererParameters{
FootnoteAnchorPrefix: viper.GetString("FootnoteAnchorPrefix"),
FootnoteReturnLinkContents: viper.GetString("FootnoteReturnLinkContents"),
}
b := len(ctx.DocumentId) != 0
if b && !ctx.getConfig().PlainIdAnchors {
renderParameters.FootnoteAnchorPrefix = ctx.DocumentId + ":" + renderParameters.FootnoteAnchorPrefix
renderParameters.HeaderIDSuffix = ":" + ctx.DocumentId
}
htmlFlags := defaultFlags
htmlFlags |= blackfriday.HTML_USE_XHTML
htmlFlags |= blackfriday.HTML_USE_SMARTYPANTS
htmlFlags |= blackfriday.HTML_SMARTYPANTS_LATEX_DASHES
htmlFlags |= blackfriday.HTML_FOOTNOTE_RETURN_LINKS
if ctx.getConfig().AngledQuotes {
htmlFlags |= blackfriday.HTML_SMARTYPANTS_ANGLED_QUOTES
}
if ctx.getConfig().Fractions {
htmlFlags |= blackfriday.HTML_SMARTYPANTS_FRACTIONS
}
return blackfriday.HtmlRendererWithParameters(htmlFlags, "", "", renderParameters)
}
func getMarkdownExtensions(ctx *RenderingContext) int {
flags := 0 | blackfriday.EXTENSION_NO_INTRA_EMPHASIS |
blackfriday.EXTENSION_TABLES | blackfriday.EXTENSION_FENCED_CODE |
blackfriday.EXTENSION_AUTOLINK | blackfriday.EXTENSION_STRIKETHROUGH |
blackfriday.EXTENSION_SPACE_HEADERS | blackfriday.EXTENSION_FOOTNOTES |
blackfriday.EXTENSION_HEADER_IDS | blackfriday.EXTENSION_AUTO_HEADER_IDS
for _, extension := range ctx.getConfig().Extensions {
if flag, ok := blackfridayExtensionMap[extension]; ok {
flags |= flag
}
}
return flags
}
func markdownRender(ctx *RenderingContext) []byte {
return blackfriday.Markdown(ctx.Content, GetHtmlRenderer(0, ctx),
getMarkdownExtensions(ctx))
}
func markdownRenderWithTOC(ctx *RenderingContext) []byte {
return blackfriday.Markdown(ctx.Content,
GetHtmlRenderer(blackfriday.HTML_TOC, ctx),
getMarkdownExtensions(ctx))
}
// ExtractTOC extracts Table of Contents from content.
func ExtractTOC(content []byte) (newcontent []byte, toc []byte) {
origContent := make([]byte, len(content))
copy(origContent, content)
first := []byte(`
`)
replacement := []byte(`
`)
startOfTOC := bytes.Index(content, first)
peekEnd := len(content)
if peekEnd > 70+startOfTOC {
peekEnd = 70 + startOfTOC
}
if startOfTOC < 0 {
return StripEmptyNav(content), toc
}
// Need to peek ahead to see if this nav element is actually the right one.
correctNav := bytes.Index(content[startOfTOC:peekEnd], []byte(` from content.
func RemoveSummaryDivider(content []byte) []byte {
return bytes.Replace(content, SummaryDivider, []byte(""), -1)
}
// TruncateWords takes content and an int and shortens down the number
// of words in the content down to the number of int.
func TruncateWords(s string, max int) string {
words := strings.Fields(s)
if max > len(words) {
return strings.Join(words, " ")
}
return strings.Join(words[:max], " ")
}
// TruncateWordsToWholeSentence takes content and an int
// and returns entire sentences from content, delimited by the int
// and whether it's truncated or not.
func TruncateWordsToWholeSentence(words []string, max int) (string, bool) {
if max >= len(words) {
return strings.Join(words, " "), false
}
for counter, word := range words[max:] {
if strings.HasSuffix(word, ".") ||
strings.HasSuffix(word, "?") ||
strings.HasSuffix(word, ".\"") ||
strings.HasSuffix(word, "!") {
upper := max + counter + 1
return strings.Join(words[:upper], " "), (upper < len(words))
}
}
return strings.Join(words[:max], " "), true
}
// GetRstContent calls the Python script rst2html as an external helper
// to convert reStructuredText content to HTML.
func GetRstContent(content []byte) string {
cleanContent := bytes.Replace(content, SummaryDivider, []byte(""), 1)
path, err := exec.LookPath("rst2html")
if err != nil {
path, err = exec.LookPath("rst2html.py")
if err != nil {
jww.ERROR.Println("rst2html / rst2html.py not found in $PATH: Please install.\n",
" Leaving reStructuredText content unrendered.")
return (string(content))
}
}
cmd := exec.Command(path, "--leave-comments")
cmd.Stdin = bytes.NewReader(cleanContent)
var out bytes.Buffer
cmd.Stdout = &out
if err := cmd.Run(); err != nil {
jww.ERROR.Println(err)
}
rstLines := strings.Split(out.String(), "\n")
for i, line := range rstLines {
if strings.HasPrefix(line, "") {
rstLines = (rstLines[i+1 : len(rstLines)-3])
}
}
return strings.Join(rstLines, "\n")
}