Look up an Arabic root and return all dictionary entries under it.

Accepts a root in any form: "كتب", "ك ت ب", "ك-ت-ب", or with diacritics like "كَتَبَ". Diacritics and letter-variants (ا/أ/إ/آ, ي/ى, ه/ة) are normalized before matching. Use this when the user has already identified the root or when you want to see all sibling words for a lemma.

Returns entries from three sources:

• arramooz-verb: verb lemma with tense-availability flags in extra

• arramooz-noun: noun / adjective / participle with wordtype, pattern (wazn), gender/number, and a terse Arabic definition

• lane-quran: English (and Turkish) semantic gloss from Lane's Lexicon for the ~1,651 roots that occur in the Quran

All returned Arabic words are fully vocalized (tashkeel is preserved from the source, including final case marks) so the caller can tell homographs apart. Input is diacritic-insensitive; output is not.

Look up a surface Arabic word (any inflected form or lemma).

Returns matching entries, each labelled with its root — pivot to lookup_root if you want all sibling words. Matching is case- and diacritic-insensitive. Good when the user gives a word but not the root.

Full-text search over dictionary meanings.

Use when the user asks "what's the Arabic root for X?" or gives a concept in English or Arabic. lang="en" searches English (Lane) glosses; lang="ar" searches Arabic (arramooz) definitions. Results are ranked by relevance and each carries its root, so you can call lookup_root on the best match for full context.