Systems for font replacement in print workflows

In a digital medium text printing environment, a system comprising:

• an extraction module implemented at least partially in hardware of a computing device to:
• receive print request data describing a document having a corpus of text rendered using a font that is not available to the extraction module;
• and
• extract the corpus of text from the document;
• a context module implemented at least partially in the hardware of the computing device to generate an indication of a context category of the corpus of text by processing the corpus of text using a machine learning model trained to classify context categories of text inputs using training data describing a different corpus of text, the indication of the context category includes an indication of a class of the context category;
• an identification module implemented at least partially in the hardware of the computing device to identify a replacement font from replacement font data describing a plurality of candidate replacement fonts, the replacement font identified based on the indication of the context category and the indication of the class of the context category;
• and
• a raster module implemented at least partially in the hardware of the computing device to generate a rasterized image depicting the corpus of text rendered using the replacement font.

One or more computer-readable storage media comprising instructions stored thereon that, responsive to execution by a computing device, causes the computing device to perform operations including:

• receiving print request data describing a document having a sequence of text rendered using an unavailable font;
• extracting the sequence of text from the document, the extracting includes tokenizing the sequence of text and lemmatization of the tokenized sequence of text;
• generating an indication of a context category of the sequence of text by processing the sequence of text with a machine learning model trained to classify context categories of text inputs using training data describing a corpus of text;
• identifying a replacement front from replacement font data describing a plurality of available fonts, the replacement font identified based on the indication of the context category;
• and
• generating a raster image in a format usable to print the document, the raster image depicting the sequence of text rendered using the replacement font.