Tesseract Legacy does not correctly identify abbreviations with periods

[Balearica]

Terms such as U.S., e.g. and i.e. are consistently misidentified by Tesseract Legacy, usually as US., eg. and ie. (respectively). This appears to be because Tesseract's language model does not expect punctuation to occur within words. While certain exceptions are made (notably, apostrophes are allowed), the possibility of a mid-word period does not appear to be included.

https://github.com/tesseract-ocr/tesseract/blob/706d3bac62954212e5236d91b3bff8e91cf7a3cc/src/wordrec/language_model.cpp#L1043-L1047