OCR Cleanup
🤖 AI Drafted (Not reviewed)
Fix common OCR artefacts: dehyphenate line-break splits, rejoin multi-column text, strip library ownership stamps.
|
|
| Tool id |
ocr_cleanup |
| Category |
transform |
| Uses a language model |
no |
| Needs a generative model |
no |
| Runs over many items |
yes |
| Item handling |
batch |
| Structured output |
no |
| Human-verified |
not yet |
What it reads
| Port |
Type |
Required |
What it is |
Text (text) |
text |
yes |
Raw OCR text to clean. |
What it emits
| Port |
Type |
Required |
What it is |
Text (text) |
text |
— |
Cleaned text. |
Options
| Option |
Type |
Default |
What it does |
dehyphenate |
boolean |
yes |
Join words split by end-of-line hyphens. |
min_line_length |
integer |
60 |
Lines shorter than this are candidates for column-rejoin (only applies when rejoin_columns is true). |
rejoin_columns |
boolean |
yes |
Heuristically rejoin short lines from multi-column OCR layout. |
strip_stamps |
boolean |
yes |
Remove common library ownership stamps and date stamps. |
The prompt it sends
This tool does not send a prompt — it does its work in code.