axa-group / Parsr

Transforms PDF, Documents and Images into Enriched Structured Data

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Support detecting text in vertical direction

baohq1595 opened this issue · comments

commented

I am working with CJK languages, and the text is in vertical direction. I tried the tool but it cannot detect vertical text. This pdfminer in python can solve the problem, it would be great if Parsr can support this.

Despite Parsr using pdfminer, it would require a rewrite of the ReadingOrderDetectionModule to support vertical texts, and the algorithm would be much more complicated. We don't have the resources to do it in a near future.