cmd/

analysestats analyses a set of 'best', 'conf', and 'hocr' files in a directory, outputting results to a .csv file for further investigation.

avg-lines prints a report of the average confidence for each line, sorted from worst to best

boxtotxt converts a Tesseract .box file to plain text

bucket-lines copies image-text line pairs into different directories according to the average character probability for the line

dehyphenate does basic dehyphenation on a hocr file

dlgbook is a wrapper around getgbook which gets metadata and uses it to save to a specially formatted directory

eeboxmltohocr converts the XML from an EEBO download to hOCR, which can be easily incorporated into a searchable PDF

extracthocrlines copies the text and corresponding image section for each line of a HOCR file into separate files, which is useful for OCR training

fonttobytes outputs a font file as a series of bytes in go format, allowing a font to be easily embedded into a go binary

hocrtotxt prints the text from a hocr file

iiifdownloader attempts to download every page of a IIIF book in the best available quality, given a manifest url

pare-gt moves some ground truth, ensuring that the same proportions of each ground truth source are represented in the moved section

pgconf prints the total confidence for a page of hOCR