Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

PDF to Text, a challenging problem

marginalia.nu

Post reply on HN
Print view View original

71–80 of 206 posts

Re: PDF to Text, a challenging problem

#71

Post by varunneal »

kbyatnal wrote: post #59

"PDF to Text" is a bit simplified IMO. There's actually a few class of problems within this category: 1. reliable OCR from documents (to index for search, feed into a vector DB, etc) 2. structured data extraction (pull out targeted values) 3. end-to-end document pipelines (e.g. automate mortgage applications) Marginalia needs to solve problem #1 (OCR), which is luckily getting commoditized by the day thanks to models…

I've been hacking away at trying to process PDFs into Markdown, having encountered similar obstacles to OP regarding header detection (and many other issues). OCR is fantastic these days but maintaining a global structure to the document is much trickier. Consistent HTML seems still out of reach for large documents. I'm having half-decent results with Markdown using multiple passes of an LLM to extract document structure and feeding it in contextually for page-by-pass extraction.

Re: PDF to Text, a challenging problem

#72

Post by yxhuvud »

dwheeler wrote: post #25

The better solution is to embed, in the PDF, the editable source document. This is easily done by LibreOffice. Embedding it takes very little space in general (because it compresses well), and then you have MUCH better information on what the text is and its meaning. It works just fine with existing PDF readers.

Sure, and if you have access to the source document the pdf was generated from, then that is a good thing to do.

But generally speaking, you don't have that control.

Re: PDF to Text, a challenging problem

#73

Post by yxhuvud »

bartread wrote: post #3

Yeah, getting text - even structured text - out of PDFs is no picnic. Scraping a table out of an HTML document is often straightforward even on sites that use the "everything's a " (anti-)pattern, and especially on sites that use more semantically useful elements, like . Not so PDFs. I'm far from an expert on the format, so maybe there is some semantic support in there, but I've seen plenty of PDFs where tables are s…

My favorite is (official, governmental) documents that has one set of text that is rendered, and a totally different set of text that you get if you extract the text the normal way..

Re: PDF to Text, a challenging problem

#75

Post by ljlolel »

EmilStenstrom wrote: post #36

I think using Gemma3 in vision mode could be a good use-case for converting PDF to text. It’s downloadable and runnable on a local computer, with decent memory requirements depending on which size you pick. Did anyone try it?

Mistral OCR has the best in class document understanding. https://mistral.ai/news/mistral-ocr

Re: PDF to Text, a challenging problem

#76

Post by 1vuio0pswjnm7 »

1vuio0pswjnm7 wrote: post #69

Below is a PDF. It is a .txt file. I can save it with a .pdf extension and open it in a PDF viewer. I can make changes in a text editor. For example, by editing this text file, I can change the text displayed on the screen when the PDF is opened, the font, font size, line spacing, the maximum characters per line, number of lines per page, the paper width and height, as well as portrait versus landscape mode. %PDF-1.4…

"PDF" is an acronym for for "Portable Document Format"

"2.3.2 Portability

A PDF file is a 7-bit ASCII file, which means PDF files use only the printable subset of the ASCII character set to describe documents even those with images and special characters. As a result, PDF files are extremely portable across diverse hardware and operating system environments."

https://opensource.adobe.com/dc-acrobat-sdk-docs/pdfstandard...

Re: PDF to Text, a challenging problem

#78

Post by kerkeslager »

GaggiX wrote: post #62
giovannibonetti wrote: post #48

Earlier quoted context omitted.

I wonder if AI will solve that

There are specialized models, but even generic ones like Gemini 2.0 Flash are really good and cheap, you can use them and embed the OCR inside the PDF to index to the original content.

This fundamentally misunderstands the problem. Effective OCR predates the popularity of ChatGPT and e-Discovery folks were already using it--AI in the modern sense adds nothing to this. Indexing the resulting text was also already possible--again AI adds nothing. The problem is that the resultant text lacks structure: being able to sort/filter wiretap data by date/location, for example, isn't inherently possible because you've obtained text or indexed it. AI accuracy simply isn't high enough to solve this problem without specialized training--off the shelf models simply won't work accurately enough even if you can get around the legal problems of feeding potentially-sensitive information into a model. AI models trained on a large enough domain-specific dataset might work, but the existing off-the-shelf models certainly are not accurate enough. And there are a lot of subdomains--wiretap data, cell phone GPS data, credit card data, email metadata, etc., which would each require model training.

Fundamentally, the solution to this problem is to not create it in the first place. There's no reason for there to be a structured data -> PDF -> AI -> structured data pipeline when we can just force people providing evidence to provide the structured data.

Re: PDF to Text, a challenging problem

#79

Post by chaps »

kccqzy wrote: post #56
svat wrote: post #10

One thing I wish someone would write is something like the browser's developer tools ("inspect elements") for PDF — it would be great to be able to "view source" a PDF's content streams (the BT … ET operators that enclose text, each Tj operator for setting down text in the currently chosen font, etc), to see how every “pixel” of the PDF is being specified/generated. I know this goes against the current trend / state-…

When you use PDF.js from Mozilla to render a PDF file in DOM, I think you might actually get something pretty close. For example I suppose each Tj becomes a and each TJ becomes a collection of s. (I'm fairly certain it doesn't use .) And I suppose it must be very faithful to the original document to make it work.

Indeed! I've used it to parse documents I've received through FOIA -- sometimes it's just easier to write beautifulsoup code compared to having to deal with PDF's oddities.

Re: PDF to Text, a challenging problem

#80

Post by chaps »

lelandfe wrote: post #49
dwheeler wrote: post #25

The better solution is to embed, in the PDF, the editable source document. This is easily done by LibreOffice. Embedding it takes very little space in general (because it compresses well), and then you have MUCH better information on what the text is and its meaning. It works just fine with existing PDF readers.

The better solution to a search engine extracting text from existing PDFs is to provide advice on how to author PDFs? What's the timeline for this solution to pay off

Microsoft is one of the bigger contributors to this. Like -- why does excel have a feature to export to PDF, but not a feature to do the opposite? That export functionality really feels like it was given to a summer intern who finished it in two weeks and never had to deal with it ever again.
Post reply on HN