Skip to content
Snippets Groups Projects

Compare revisions

Changes are shown as if the source revision was being merged into the target revision. Learn more about comparing revisions.

Source

Select target project
No results found
Select Git revision
  • better-queue
  • master
2 results

Target

Select target project
  • ale/crawl
1 result
Select Git revision
  • better-queue
  • master
2 results
Show changes
Commits on Source (4)
Showing
with 179 additions and 70 deletions
include: "https://git.autistici.org/ai3/build-deb/raw/master/ci-common.yml"
run_tests:
stage: test
image: "golang:1.19"
script: "go test -v ./..."
include:
- "https://git.autistici.org/pipelines/debian/raw/master/common.yml"
- "https://git.autistici.org/pipelines/images/test/golang/raw/master/ci.yml"
module git.autistici.org/ale/crawl
go 1.15
go 1.21
toolchain go1.21.4
require (
github.com/PuerkitoBio/goquery v1.8.0
github.com/PuerkitoBio/purell v1.2.0
github.com/PuerkitoBio/urlesc v0.0.0-20170810143723-de5bf2ad4578 // indirect
github.com/PuerkitoBio/goquery v1.8.1
github.com/PuerkitoBio/purell v1.2.1
github.com/google/go-cmp v0.5.6
github.com/google/uuid v1.1.1 // indirect
github.com/pborman/uuid v1.2.1
github.com/syndtr/goleveldb v1.0.0
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2 // indirect
)
require (
github.com/PuerkitoBio/urlesc v0.0.0-20170810143723-de5bf2ad4578 // indirect
github.com/andybalholm/cascadia v1.3.1 // indirect
github.com/fsnotify/fsnotify v1.4.7 // indirect
github.com/golang/protobuf v1.2.0 // indirect
github.com/golang/snappy v0.0.0-20180518054509-2e65f85255db // indirect
github.com/google/uuid v1.1.1 // indirect
github.com/hpcloud/tail v1.0.0 // indirect
github.com/onsi/ginkgo v1.7.0 // indirect
github.com/onsi/gomega v1.4.3 // indirect
github.com/yuin/goldmark v1.4.13 // indirect
golang.org/x/crypto v0.14.0 // indirect
golang.org/x/mod v0.8.0 // indirect
golang.org/x/net v0.17.0 // indirect
golang.org/x/sync v0.1.0 // indirect
golang.org/x/sys v0.13.0 // indirect
golang.org/x/term v0.13.0 // indirect
golang.org/x/text v0.13.0 // indirect
golang.org/x/tools v0.6.0 // indirect
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543 // indirect
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 // indirect
gopkg.in/fsnotify.v1 v1.4.7 // indirect
gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 // indirect
gopkg.in/yaml.v2 v2.2.1 // indirect
)
......@@ -4,12 +4,16 @@ github.com/PuerkitoBio/goquery v1.7.1 h1:oE+T06D+1T7LNrn91B4aERsRIeCLJ/oPSa6xB9F
github.com/PuerkitoBio/goquery v1.7.1/go.mod h1:XY0pP4kfraEmmV1O7Uf6XyjoslwsneBbgeDjLYuN8xY=
github.com/PuerkitoBio/goquery v1.8.0 h1:PJTF7AmFCFKk1N6V6jmKfrNH9tV5pNE6lZMkG0gta/U=
github.com/PuerkitoBio/goquery v1.8.0/go.mod h1:ypIiRMtY7COPGk+I/YbZLbxsxn9g5ejnI2HSMtkjZvI=
github.com/PuerkitoBio/goquery v1.8.1 h1:uQxhNlArOIdbrH1tr0UXwdVFgDcZDrZVdcpygAcwmWM=
github.com/PuerkitoBio/goquery v1.8.1/go.mod h1:Q8ICL1kNUJ2sXGoAhPGUdYDJvgQgHzJsnnd3H7Ho5jQ=
github.com/PuerkitoBio/purell v0.0.0-20180310210909-975f53781597 h1:1H3FyRw7YsqIty9WHPOVEGJaFJ1sfGVZ3PPDUw3ob2w=
github.com/PuerkitoBio/purell v0.0.0-20180310210909-975f53781597/go.mod h1:c11w/QuzBsJSee3cPx9rAFu61PvFxuPbtSwDGJws/X0=
github.com/PuerkitoBio/purell v0.1.0 h1:N8Bcc53nei5frgNYgAKo93qMUVdU5LUGHCBv8efdVcM=
github.com/PuerkitoBio/purell v0.1.0/go.mod h1:c11w/QuzBsJSee3cPx9rAFu61PvFxuPbtSwDGJws/X0=
github.com/PuerkitoBio/purell v1.2.0 h1:/Jdm5QfyM8zdlqT6WVZU4cfP23sot6CEHA4CS49Ezig=
github.com/PuerkitoBio/purell v1.2.0/go.mod h1:OhLRTaaIzhvIyofkJfB24gokC7tM42Px5UhoT32THBk=
github.com/PuerkitoBio/purell v1.2.1 h1:QsZ4TjvwiMpat6gBCBxEQI0rcS9ehtkKtSpiUnd9N28=
github.com/PuerkitoBio/purell v1.2.1/go.mod h1:ZwHcC/82TOaovDi//J/804umJFFmbOHPngi8iYYv/Eo=
github.com/PuerkitoBio/urlesc v0.0.0-20170810143723-de5bf2ad4578 h1:d+Bc7a5rLufV/sSk/8dngufqelfh6jnri85riMAaF/M=
github.com/PuerkitoBio/urlesc v0.0.0-20170810143723-de5bf2ad4578/go.mod h1:uGdkoq3SwY9Y+13GIhn11/XLaGBb4BfwItxLd5jeuXE=
github.com/andybalholm/cascadia v1.0.0 h1:hOCXnnZ5A+3eVDX8pvgl4kofXv2ELss0bKcqRySc45o=
......@@ -50,20 +54,35 @@ github.com/syndtr/goleveldb v0.0.0-20190923125748-758128399b1d h1:OgkXbz/O0zsJoa
github.com/syndtr/goleveldb v0.0.0-20190923125748-758128399b1d/go.mod h1:9OrXJhf154huy1nPWmuSrkgjPUtUNhA+Zmy+6AESzuA=
github.com/syndtr/goleveldb v1.0.0 h1:fBdIW9lB4Iz0n9khmH8w27SJ3QEJ7+IgjPEwGSZiFdE=
github.com/syndtr/goleveldb v1.0.0/go.mod h1:ZVVdQEZoIme9iO1Ch2Jdy24qqXrMMOU6lpPAyBWyWuQ=
github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
golang.org/x/crypto v0.14.0/go.mod h1:MVFd36DqK4CsrnJYDkBA3VC4m2GkXAM0PvzMCn4JQf4=
golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
golang.org/x/net v0.0.0-20180218175443-cbe0f9307d01/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
golang.org/x/net v0.0.0-20180906233101-161cd47e91fd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.0.0-20190926025831-c00fd9afed17 h1:qPnAdmjNA41t3QBTx2mFGf/SD1IoslhYu7AmdsVzCcs=
golang.org/x/net v0.0.0-20190926025831-c00fd9afed17/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
golang.org/x/net v0.0.0-20210614182718-04defd469f4e h1:XpT3nA5TvE525Ne3hInMh6+GETgn27Zfm9dxsThnX2Q=
golang.org/x/net v0.0.0-20210614182718-04defd469f4e/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
golang.org/x/net v0.0.0-20210916014120-12bc252f5db8 h1:/6y1LfuqNuQdHAm0jjtPtgRcxIxjVZgm5OTu8/QhZvk=
golang.org/x/net v0.0.0-20210916014120-12bc252f5db8/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
golang.org/x/net v0.0.0-20220617184016-355a448f1bc9 h1:Yqz/iviulwKwAREEeUd3nbBFn0XuyJqkoft2IlrvOhc=
golang.org/x/net v0.0.0-20220617184016-355a448f1bc9/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
golang.org/x/net v0.7.0 h1:rJrUqqhjsgNp7KqAIc25s9pZnjU7TUcSY7HcVZjdn1g=
golang.org/x/net v0.7.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
golang.org/x/net v0.17.0 h1:pVaXccu2ozPjCXewfr1S7xza/zcXTity9cCdXQYSjIM=
golang.org/x/net v0.17.0/go.mod h1:NxSsAGuq816PNPmqtQdLE42eU2Fs7NoRIZrHJAlaCOE=
golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f h1:wMNYb4v58l5UBM7MYRLPG6ZhfOqbKu7X5eyFl8ZhKvA=
golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
golang.org/x/sys v0.0.0-20180909124046-d0be0721c37e/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a h1:1BGLXjeY4akVXGgbC9HugT3Jv3hCI0z56oJR5vAMgBU=
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
......@@ -71,14 +90,28 @@ golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7w
golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.13.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
golang.org/x/term v0.13.0/go.mod h1:LTmsnFJwVN6bCy1rVCoS+qHT1HhALEFxKncY3WNNh4U=
golang.org/x/text v0.3.0 h1:g61tztE5qeGQ89tm6NTjjM9VPIm088od1l6aSorWRWg=
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/text v0.3.7 h1:olpwvP2KacW1ZWvsR7uQhoyTYvKAupfQrRGBFM352Gk=
golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
golang.org/x/text v0.7.0 h1:4BRB4x83lYWy72KwLD/qYDuTu7q9PjSagHvijDw7cLo=
golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
golang.org/x/text v0.13.0 h1:ablQoSUd0tRdKxZewP80B+BaqeKJuVhuRxj/dkrun3k=
golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
......
......@@ -40,6 +40,7 @@ Please note that because of the net/html dependency, goquery requires Go1.1+ and
**Note that goquery's API is now stable, and will not break.**
* **2023-02-18 (v1.8.1)** : Update `go.mod` dependencies, update CI workflow.
* **2021-10-25 (v1.8.0)** : Add `Render` function to render a `Selection` to an `io.Writer` (thanks [@anthonygedeon](https://github.com/anthonygedeon)).
* **2021-07-11 (v1.7.1)** : Update go.mod dependencies and add dependabot config (thanks [@jauderho](https://github.com/jauderho)).
* **2021-06-14 (v1.7.0)** : Add `Single` and `SingleMatcher` functions to optimize first-match selection (thanks [@gdollardollar](https://github.com/gdollardollar)).
......@@ -154,6 +155,8 @@ func main() {
- [Geziyor](https://github.com/geziyor/geziyor), a fast web crawling & scraping framework for Go. Supports JS rendering.
- [Pagser](https://github.com/foolin/pagser), a simple, easy, extensible, configurable HTML parser to struct based on goquery and struct tags.
- [stitcherd](https://github.com/vhodges/stitcherd), A server for doing server side includes using css selectors and DOM updates.
- [goskyr](https://github.com/jakopako/goskyr), an easily configurable command-line scraper written in Go.
- [goGetJS](https://github.com/davemolk/goGetJS), a tool for extracting, searching, and saving JavaScript files (with optional headless browser).
## Support
......
module github.com/PuerkitoBio/goquery
require (
github.com/andybalholm/cascadia v1.3.1
golang.org/x/net v0.0.0-20210916014120-12bc252f5db8
)
go 1.13
github.com/andybalholm/cascadia v1.3.1 h1:nhxRkql1kdYCc8Snf7D5/D3spOX+dBgjA6u8x004T2c=
github.com/andybalholm/cascadia v1.3.1/go.mod h1:R4bJ1UQfqADjvDa4P6HZHLh/3OxWWEqc0Sk8XGwHqvA=
golang.org/x/net v0.0.0-20210916014120-12bc252f5db8 h1:/6y1LfuqNuQdHAm0jjtPtgRcxIxjVZgm5OTu8/QhZvk=
golang.org/x/net v0.0.0-20210916014120-12bc252f5db8/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
......@@ -58,7 +58,7 @@ func nodeName(node *html.Node) string {
}
}
// Render renders the html of the first element from selector and writes it to
// Render renders the HTML of the first item in the selection and writes it to
// the writer. It behaves the same as OuterHtml but writes to w instead of
// returning the string.
func Render(w io.Writer, s *Selection) error {
......@@ -73,7 +73,7 @@ func Render(w io.Writer, s *Selection) error {
// the selection - that is, the HTML including the first element's
// tag and attributes.
//
// Unlike InnerHtml, this is a function and not a method on the Selection,
// Unlike Html, this is a function and not a method on the Selection,
// because this is not a jQuery method (in javascript-land, this is
// a property provided by the DOM).
func OuterHtml(s *Selection) (string, error) {
......
module github.com/PuerkitoBio/purell
go 1.19
require (
golang.org/x/net v0.0.0-20220617184016-355a448f1bc9
golang.org/x/text v0.3.7
)
golang.org/x/net v0.0.0-20220617184016-355a448f1bc9 h1:Yqz/iviulwKwAREEeUd3nbBFn0XuyJqkoft2IlrvOhc=
golang.org/x/net v0.0.0-20220617184016-355a448f1bc9/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
golang.org/x/text v0.3.7 h1:olpwvP2KacW1ZWvsR7uQhoyTYvKAupfQrRGBFM352Gk=
golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
......@@ -86,6 +86,7 @@ var rxDWORDHost = regexp.MustCompile(`^(\d+)((?:\.+)?(?:\:\d*)?)$`)
var rxOctalHost = regexp.MustCompile(`^(0\d*)\.(0\d*)\.(0\d*)\.(0\d*)((?:\.+)?(?:\:\d*)?)$`)
var rxHexHost = regexp.MustCompile(`^0x([0-9A-Fa-f]+)((?:\.+)?(?:\:\d*)?)$`)
var rxHostDots = regexp.MustCompile(`^(.+?)(:\d+)?$`)
var rxHostInteriorDots = regexp.MustCompile(`\.+`)
var rxEmptyPort = regexp.MustCompile(`:+$`)
// Map of flags to implementation function.
......@@ -368,6 +369,7 @@ func removeUnncessaryHostDots(u *url.URL) {
u.Host += matches[2]
}
}
u.Host = rxHostInteriorDots.ReplaceAllString(u.Host, ".")
}
}
......
module github.com/andybalholm/cascadia
go 1.16
require golang.org/x/net v0.0.0-20210916014120-12bc252f5db8
golang.org/x/net v0.0.0-20210916014120-12bc252f5db8 h1:/6y1LfuqNuQdHAm0jjtPtgRcxIxjVZgm5OTu8/QhZvk=
golang.org/x/net v0.0.0-20210916014120-12bc252f5db8/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
module github.com/google/uuid
module github.com/pborman/uuid
require github.com/google/uuid v1.0.0
github.com/google/uuid v1.0.0 h1:b4Gk+7WdP/d3HZH8EJsZpvV7EtDOgaZLtnaNGIu1adA=
github.com/google/uuid v1.0.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
# This source code refers to The Go Authors for copyright purposes.
# The master list of authors is in the main Go distribution,
# visible at http://tip.golang.org/AUTHORS.
# This source code was written by the Go contributors.
# The master list of contributors is in the main Go distribution,
# visible at http://tip.golang.org/CONTRIBUTORS.
......@@ -92,6 +92,27 @@ example, to process each anchor node in depth-first order:
The relevant specifications include:
https://html.spec.whatwg.org/multipage/syntax.html and
https://html.spec.whatwg.org/multipage/syntax.html#tokenization
# Security Considerations
Care should be taken when parsing and interpreting HTML, whether full documents
or fragments, within the framework of the HTML specification, especially with
regard to untrusted inputs.
This package provides both a tokenizer and a parser, which implement the
tokenization, and tokenization and tree construction stages of the WHATWG HTML
parsing specification respectively. While the tokenizer parses and normalizes
individual HTML tokens, only the parser constructs the DOM tree from the
tokenized HTML, as described in the tree construction stage of the
specification, dynamically modifying or extending the docuemnt's DOM tree.
If your use case requires semantically well-formed HTML documents, as defined by
the WHATWG specification, the parser should be used rather than the tokenizer.
In security contexts, if trust decisions are being made using the tokenized or
parsed content, the input must be re-serialized (for instance by using Render or
Token.String) in order for those trust decisions to hold, as the process of
tokenization or parsing may alter the content.
*/
package html // import "golang.org/x/net/html"
......
......@@ -193,6 +193,87 @@ func lower(b []byte) []byte {
return b
}
// escapeComment is like func escape but escapes its input bytes less often.
// Per https://github.com/golang/go/issues/58246 some HTML comments are (1)
// meaningful and (2) contain angle brackets that we'd like to avoid escaping
// unless we have to.
//
// "We have to" includes the '&' byte, since that introduces other escapes.
//
// It also includes those bytes (not including EOF) that would otherwise end
// the comment. Per the summary table at the bottom of comment_test.go, this is
// the '>' byte that, per above, we'd like to avoid escaping unless we have to.
//
// Studying the summary table (and T actions in its '>' column) closely, we
// only need to escape in states 43, 44, 49, 51 and 52. State 43 is at the
// start of the comment data. State 52 is after a '!'. The other three states
// are after a '-'.
//
// Our algorithm is thus to escape every '&' and to escape '>' if and only if:
// - The '>' is after a '!' or '-' (in the unescaped data) or
// - The '>' is at the start of the comment data (after the opening "<!--").
func escapeComment(w writer, s string) error {
// When modifying this function, consider manually increasing the
// maxSuffixLen constant in func TestComments, from 6 to e.g. 9 or more.
// That increase should only be temporary, not committed, as it
// exponentially affects the test running time.
if len(s) == 0 {
return nil
}
// Loop:
// - Grow j such that s[i:j] does not need escaping.
// - If s[j] does need escaping, output s[i:j] and an escaped s[j],
// resetting i and j to point past that s[j] byte.
i := 0
for j := 0; j < len(s); j++ {
escaped := ""
switch s[j] {
case '&':
escaped = "&amp;"
case '>':
if j > 0 {
if prev := s[j-1]; (prev != '!') && (prev != '-') {
continue
}
}
escaped = "&gt;"
default:
continue
}
if i < j {
if _, err := w.WriteString(s[i:j]); err != nil {
return err
}
}
if _, err := w.WriteString(escaped); err != nil {
return err
}
i = j + 1
}
if i < len(s) {
if _, err := w.WriteString(s[i:]); err != nil {
return err
}
}
return nil
}
// escapeCommentString is to EscapeString as escapeComment is to escape.
func escapeCommentString(s string) string {
if strings.IndexAny(s, "&>") == -1 {
return s
}
var buf bytes.Buffer
escapeComment(&buf, s)
return buf.String()
}
const escapedChars = "&'<>\"\r"
func escape(w writer, s string) error {
......
......@@ -184,7 +184,7 @@ func (p *parser) clearStackToContext(s scope) {
}
}
// parseGenericRawTextElements implements the generic raw text element parsing
// parseGenericRawTextElement implements the generic raw text element parsing
// algorithm defined in 12.2.6.2.
// https://html.spec.whatwg.org/multipage/parsing.html#parsing-elements-that-contain-only-text
// TODO: Since both RAWTEXT and RCDATA states are treated as tokenizer's part
......@@ -734,7 +734,7 @@ func inHeadIM(p *parser) bool {
return false
}
// 12.2.6.4.5.
// Section 12.2.6.4.5.
func inHeadNoscriptIM(p *parser) bool {
switch p.tok.Type {
case DoctypeToken:
......