Abstract: A method and apparatus for generating glyphs for text elements input to a computer having a memory with at least one look-up table storing glyphs corresponding to such text elements. Each text element is made up of at least one code point, and often of several code points. The system searches the table for a glyph representing an input text element, and if it is not found methodically generates subsets of the text element and searches the table for glyphs representing each of the subsets. Default characters are generated for code points not represented in the table. The system uses a classification for each code point, such as the Unicode classifications, and handles unknown code points in a manner dependent upon their classification. Where a text element includes two characters with an intermediate joining character, and the text element as a whole is not represented in the table, the two characters are output for rendering separately.