-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
8 changed files
with
104 additions
and
13 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,57 @@ | ||
| package crossref | ||
|
|
||
| import ( | ||
| "bytes" | ||
| "encoding/xml" | ||
| "log/slog" | ||
|
|
||
| "golang.org/x/net/html" | ||
| ) | ||
|
|
||
| type Body struct { | ||
| Sections []Section `xml:"sec"` | ||
| } | ||
|
|
||
| type Section struct { | ||
| XMLName xml.Name `xml:"jats:abstract"` | ||
| Para []string `xml:"jats:p"` | ||
| } | ||
|
|
||
| func parseHTML(htmlContent string) (*html.Node, error) { | ||
| doc, err := html.Parse(bytes.NewReader([]byte(htmlContent))) | ||
| if err != nil { | ||
| return nil, err | ||
| } | ||
| return doc, nil | ||
| } | ||
|
|
||
| func StrToJATS(htmlContent string) (string, error) { | ||
| if len(htmlContent) > 4 && htmlContent[0:4] == "</p>" { | ||
| htmlContent = "<p>" + htmlContent[4:] | ||
| } | ||
| node, err := parseHTML(htmlContent) | ||
| if err != nil { | ||
| return "", err | ||
| } | ||
|
|
||
| slog.Info("NODE", "n", node, "html", htmlContent) | ||
| var section Section | ||
|
|
||
| var f func(*html.Node) | ||
| f = func(n *html.Node) { | ||
| if n.Type == html.ElementNode && n.Data == "p" { | ||
| section.Para = append(section.Para, n.FirstChild.Data) | ||
| } | ||
| for c := n.FirstChild; c != nil; c = c.NextSibling { | ||
| f(c) | ||
| } | ||
| } | ||
| f(node) | ||
|
|
||
| output, err := xml.MarshalIndent(section, "", " ") | ||
| if err != nil { | ||
| return "", err | ||
| } | ||
|
|
||
| return string(output), nil | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.
Oops, something went wrong.