opensource/mateclaw
2
0
Fork 0
mirror of https://gitee.com/mateos/mateclaw.git synced 2026-09-15 03:55:09 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix(wiki): strip file extensions when deriving transformation page slugs

Browse Source
This commit is contained in:
matevip 2026-05-12 11:25:32 +08:00
parent bae9f68261
commit 4098346fb7
1 changed files with 17 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
mateclaw-server/src/main/java/vip/mate/wiki/service/WikiTransformationExecutor.java
View File

@ -292,12 +292,28 @@ public class WikiTransformationExecutor {
return persisted; return persisted;
} }
/**
* Common document / image extensions that we don't want leaking into the
* slug. The pattern matches a trailing dotted extension and is case-
* insensitive so both {@code foo.PDF} and {@code foo.pdf} are stripped.
*/
private static final java.util.regex.Pattern FILE_EXT_PATTERN =
java.util.regex.Pattern.compile(
"\\.(pdf|docx?|pptx?|xlsx?|csv|tsv|txt|md|markdown|rtf|odt|epub|html?|json|xml|yaml|yml|jpe?g|png|gif|bmp|tiff?|webp|svg|mp3|wav|mp4|mov|webm)$",
java.util.regex.Pattern.CASE_INSENSITIVE);
private static String buildSlug(WikiTransformationEntity template, WikiRawMaterialEntity raw) { private static String buildSlug(WikiTransformationEntity template, WikiRawMaterialEntity raw) {
String rawPart = WikiPageService.toSlug(raw.getTitle()); String trimmedTitle = stripFileExtension(raw.getTitle());
String rawPart = WikiPageService.toSlug(trimmedTitle);
if (rawPart == null || rawPart.isBlank()) rawPart = "r" + raw.getId(); if (rawPart == null || rawPart.isBlank()) rawPart = "r" + raw.getId();
return template.getName() + "-" + rawPart; return template.getName() + "-" + rawPart;
} }
private static String stripFileExtension(String title) {
if (title == null) return null;
return FILE_EXT_PATTERN.matcher(title.trim()).replaceFirst("");
}
/** First non-empty line of the output, capped to ~280 chars, used as page summary. */ /** First non-empty line of the output, capped to ~280 chars, used as page summary. */
private static String deriveSummary(String output) { private static String deriveSummary(String output) {
if (output == null) return ""; if (output == null) return "";