ukeeper / ukeeper-readability / 39126544912

77%

master: 75%

Pull #74

github

Suggest article selectors with OpenAI on request

When a page is parsed wrong, an administrator can ask OpenAI for a CSS
selector of the article. The model sees an outline of the page body
instead of raw HTML, and a suggestion is accepted only after it is
applied to the page and matches a plausible amount of text that is
neither nearly the whole page nor what is extracted now. The selector is
stored as a disabled rule with an insert-only write, so an existing rule
of the domain is never replaced and nothing changes for readers until
the rule is enabled. OpenAI is never asked for a selector during normal
extraction. The request shares the per-request deadline used for
summaries.

277 of 321 new or added lines in 7 files covered. (86.29%)

1140 of 1483 relevant lines covered (76.87%)

44.36 hits per line