eat-js-sdk 2.3.0 → 2.3.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
|
@@ -5963,8 +5963,9 @@ const decodeNbsp = (text) => text.replace(/ /g, " ").replace(/ /g,
|
|
|
5963
5963
|
const stripTags = (s) => s.replace(/<[^>]+>/g, "");
|
|
5964
5964
|
const hasHtmlTags = (s) => /<[^>]/.test(s);
|
|
5965
5965
|
const SUPPORTED_LANGUAGES = /* @__PURE__ */ new Set(["en", "la"]);
|
|
5966
|
+
const LATIN_ACCURACY_THRESHOLD = 0.3;
|
|
5966
5967
|
const HTML_TOKEN_RE = /(<[^>]+>)/;
|
|
5967
|
-
const TEXT_SEGMENT_RE = /(
|
|
5968
|
+
const TEXT_SEGMENT_RE = /('(?:[^'\\]|\\.)*')|("(?:[^"\\]|\\.)*")|([^'"()[\]{}.?!:&]+[.?!:]?|&[^;]*;)|(.)/g;
|
|
5968
5969
|
const BRACKET_RE = /(\{[^}]*\}|\([^)]*\)|\[[^\]]*\])/g;
|
|
5969
5970
|
function extractPlainText(raw) {
|
|
5970
5971
|
const stripped = raw.replace(/<[^>]+>/g, " ").replace(/</g, "<").replace(/>/g, ">").replace(/ /g, " ").replace(/\s+/g, " ").trim();
|
|
@@ -5977,7 +5978,7 @@ function isLatin(text) {
|
|
|
5977
5978
|
const cached = latinDetectionCache.get(plain);
|
|
5978
5979
|
if (cached !== void 0) return cached;
|
|
5979
5980
|
const supported = (a0(plain) ?? []).filter(({ lang }) => SUPPORTED_LANGUAGES.has(lang));
|
|
5980
|
-
const result = supported.length > 0 && supported[0].lang === "la";
|
|
5981
|
+
const result = supported.length > 0 && supported[0].lang === "la" && supported[0].accuracy >= LATIN_ACCURACY_THRESHOLD;
|
|
5981
5982
|
latinDetectionCache.set(plain, result);
|
|
5982
5983
|
return result;
|
|
5983
5984
|
}
|