m105
1c9fc5d423
Adds Site/SitePage models and the crawlindex:fetch command, which pulls CDX index records from Common Crawl and optionally enriches them with page title/description/keywords/body text extracted from the WARC archive. CDX/WARC access and the site/page upsert logic live in CommonCrawlIndexService and WarcRecordFetcher.
19 lines
275 B
INI
19 lines
275 B
INI
root = true
|
|
|
|
[*]
|
|
charset = utf-8
|
|
end_of_line = lf
|
|
indent_size = 4
|
|
indent_style = space
|
|
insert_final_newline = true
|
|
trim_trailing_whitespace = true
|
|
|
|
[*.md]
|
|
trim_trailing_whitespace = false
|
|
|
|
[*.{yml,yaml}]
|
|
indent_size = 2
|
|
|
|
[{compose,docker-compose}.{yml,yaml}]
|
|
indent_size = 4
|