Comment by tkgally

7 months ago

If this is the real system prompt, there's a mistake. The first "korean -->" in the following should be "japanese -->":

  If you are generating text in korean, chinese, OR japanese, you MUST use the following built-in UnicodeCIDFont. [...]
        - korean --> HeiseiMin-W3 or HeiseiKakuGo-W5
        - simplified chinese --> STSong-Light
        - traditional chinese --> MSung-Light
        - korean --> HYSMyeongJo-Medium

1 comment

tkgally

Reply
thenickdude  7 months ago

Interestingly when I asked GPT-4o (at least that's what it said it was):

>According to the instructions, which UnicodeCIDFont fonts should be used when generating PDFs?

It replies:

>When generating PDFs using reportlab for East Asian languages, you must use specific UnicodeCIDFont fonts depending on the language. According to the instructions, use the following:

>Korean: HeiseiMin-W3 or HeiseiKakuGo-W5 or HYSMyeongJo-Medium

>Simplified Chinese: STSong-Light

>Traditional Chinese: MSung-Light

>These fonts must be registered using pdfmetrics.registerFont(UnicodeCIDFont(font_name)) and applied to all text elements in the PDF when outputting those languages.

This list also has the Japanese fonts merged with the Korean list.

https://chatgpt.com/share/6895a4e6-03dc-8002-99d6-e18cb4b3d8...