Add StripMarkdown option (irc). (#1145)
Enable `StripMarkdown` to strip markdown for irc.pull/1146/head
Wim
4 years ago
committed by
GitHub
parent
3c4a3e3f75
commit
ba0bfe70a8
@ -0,0 +1,3 @@
|
||||
*~
|
||||
*.swp
|
||||
cmd/strip/strip
|
||||
@ -0,0 +1,21 @@
|
||||
The MIT License (MIT)
|
||||
|
||||
Copyright (c) 2016 Write.as
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
@ -0,0 +1,51 @@
|
||||
# go-strip-markdown
|
||||
|
||||
[](https://godoc.org/github.com/writeas/go-strip-markdown)
|
||||
|
||||
A Markdown stripper written in Go (golang).
|
||||
|
||||
## Usage
|
||||
You could create a simple command-line utility:
|
||||
|
||||
```go
|
||||
package main
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"github.com/writeas/go-strip-markdown"
|
||||
"os"
|
||||
)
|
||||
|
||||
func main() {
|
||||
if len(os.Args) < 2 {
|
||||
os.Exit(1)
|
||||
}
|
||||
fmt.Println(stripmd.Strip(os.Args[1]))
|
||||
}
|
||||
```
|
||||
|
||||
You could pass it Markdown and get pure, beauteous text in return:
|
||||
|
||||
```bash
|
||||
./strip "# A Tale of Text Formatting
|
||||
|
||||
_One fateful day_ a developer was presented with [Markdown](https://daringfireball.net/projects/markdown/).
|
||||
And they wanted **none of it**."
|
||||
|
||||
# A Tale of Text Formatting
|
||||
#
|
||||
# One fateful day a developer was presented with Markdown.
|
||||
# And they wanted none of it.
|
||||
```
|
||||
|
||||
## Inspiration
|
||||
This was largely based off of [remove-markdown](https://github.com/stiang/remove-markdown), a Markdown stripper written in Javascript.
|
||||
|
||||
## Used by
|
||||
|
||||
This library is used in these projects:
|
||||
|
||||
* [WriteFreely](https://github.com/writeas/writefreely)
|
||||
|
||||
## License
|
||||
MIT.
|
||||
@ -0,0 +1,66 @@
|
||||
// Package stripmd strips Markdown from text
|
||||
package stripmd
|
||||
|
||||
import (
|
||||
"regexp"
|
||||
)
|
||||
|
||||
var (
|
||||
listLeadersReg = regexp.MustCompile(`(?m)^([\s\t]*)([\*\-\+]|\d\.)\s+`)
|
||||
|
||||
headerReg = regexp.MustCompile(`\n={2,}`)
|
||||
strikeReg = regexp.MustCompile(`~~`)
|
||||
codeReg = regexp.MustCompile("`{3}" + `.*\n`)
|
||||
|
||||
htmlReg = regexp.MustCompile("<(.*?)>")
|
||||
emphReg = regexp.MustCompile(`\*\*([^*]+)\*\*`)
|
||||
emphReg2 = regexp.MustCompile(`\*([^*]+)\*`)
|
||||
emphReg3 = regexp.MustCompile(`__([^_]+)__`)
|
||||
emphReg4 = regexp.MustCompile(`_([^_]+)_`)
|
||||
setextHeaderReg = regexp.MustCompile(`^[=\-]{2,}\s*$`)
|
||||
footnotesReg = regexp.MustCompile(`\[\^.+?\](\: .*?$)?`)
|
||||
footnotes2Reg = regexp.MustCompile(`\s{0,2}\[.*?\]: .*?$`)
|
||||
imagesReg = regexp.MustCompile(`\!\[(.*?)\]\s?[\[\(].*?[\]\)]`)
|
||||
linksReg = regexp.MustCompile(`\[(.*?)\][\[\(].*?[\]\)]`)
|
||||
blockquoteReg = regexp.MustCompile(`>\s*`)
|
||||
refLinkReg = regexp.MustCompile(`^\s{1,2}\[(.*?)\]: (\S+)( ".*?")?\s*$`)
|
||||
atxHeaderReg = regexp.MustCompile(`(?m)^\#{1,6}\s*([^#]+)\s*(\#{1,6})?$`)
|
||||
atxHeaderReg2 = regexp.MustCompile(`([\*_]{1,3})(\S.*?\S)?P1`)
|
||||
atxHeaderReg3 = regexp.MustCompile("(?m)(`{3,})" + `(.*?)?P1`)
|
||||
atxHeaderReg4 = regexp.MustCompile(`^-{3,}\s*$`)
|
||||
atxHeaderReg5 = regexp.MustCompile("`(.+?)`")
|
||||
atxHeaderReg6 = regexp.MustCompile(`\n{2,}`)
|
||||
)
|
||||
|
||||
// Strip returns the given string sans any Markdown.
|
||||
// Where necessary, elements are replaced with their best textual forms, so
|
||||
// for example, hyperlinks are stripped of their URL and become only the link
|
||||
// text, and images lose their URL and become only the alt text.
|
||||
func Strip(s string) string {
|
||||
res := s
|
||||
res = listLeadersReg.ReplaceAllString(res, "$1")
|
||||
|
||||
res = headerReg.ReplaceAllString(res, "\n")
|
||||
res = strikeReg.ReplaceAllString(res, "")
|
||||
res = codeReg.ReplaceAllString(res, "")
|
||||
|
||||
res = emphReg.ReplaceAllString(res, "$1")
|
||||
res = emphReg2.ReplaceAllString(res, "$1")
|
||||
res = emphReg3.ReplaceAllString(res, "$1")
|
||||
res = emphReg4.ReplaceAllString(res, "$1")
|
||||
res = htmlReg.ReplaceAllString(res, "$1")
|
||||
res = setextHeaderReg.ReplaceAllString(res, "")
|
||||
res = footnotesReg.ReplaceAllString(res, "")
|
||||
res = footnotes2Reg.ReplaceAllString(res, "")
|
||||
res = imagesReg.ReplaceAllString(res, "$1")
|
||||
res = linksReg.ReplaceAllString(res, "$1")
|
||||
res = blockquoteReg.ReplaceAllString(res, " ")
|
||||
res = refLinkReg.ReplaceAllString(res, "")
|
||||
res = atxHeaderReg.ReplaceAllString(res, "$1")
|
||||
res = atxHeaderReg2.ReplaceAllString(res, "$2")
|
||||
res = atxHeaderReg3.ReplaceAllString(res, "$2")
|
||||
res = atxHeaderReg4.ReplaceAllString(res, "")
|
||||
res = atxHeaderReg5.ReplaceAllString(res, "$1")
|
||||
res = atxHeaderReg6.ReplaceAllString(res, "\n\n")
|
||||
return res
|
||||
}
|
||||
Loading…
Reference in New Issue