CLD2 cannot classify text that doesn't have spaces

[choket]

The following text gets properly detected as English, with a percent of 99:

the soldier with the green whiskers led them through the streets of the emerald city until they reached the room where the guardian of the gates lived this office run locked their spectacles to put them back in his great box and then he

However that same text, but with spaces removed:

thesoldierwiththegreenwhiskersledthemthroughthestreetsoftheemeraldcityuntiltheyreachedtheroomwheretheguardianofthegateslivedthisofficerunlockedtheirspectaclestoputthembackinhisgreatboxandthenhe

gets classified as English(because that's the default), but is_reliable is set to false and the percentage is 0.
Upon further inspection, using the function DetectLanguageSummary, the 3 most likely languages are all UNKNOWN_LANGUAGE, and the percentages for them are all 0.

Since CLD2 uses quadgrams to analyze latin scripts, the whitespaces should matter very little(if at all) when detecting the language.