kpohl/CostHive
1
0
Fork 0
Code Issues 9 Pull Requests Actions Packages Projects 1 Releases 2 Wiki Activity

fix: correct OCR language

Browse Source
This commit is contained in:
Lunaresk 2024-11-02 23:46:02 +01:00
parent a6f229e7fb
commit d34f2adb2f
3 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
backend/configs/tessdata/deu.traineddata Normal file
View File

Binary file not shown.

BIN
backend/configs/tessdata/eng.traineddata
View File

Binary file not shown.

2
backend/src/utils/modules/receipt_parser/pdf_receipt_parser.py
View File

@ -27,7 +27,7 @@ class PDFReceipt:
with fitz.open(file, filetype="pdf") as doc: with fitz.open(file, filetype="pdf") as doc:
words = [] words = []
for page in doc: for page in doc:
words.extend(page.get_text("words", textpage=page.get_textpage_ocr(), sort=True)) words.extend(page.get_text("words", textpage=page.get_textpage_ocr(language = 'deu'), sort=True))
return words return words
def _getStoreName(words: list[tuple]) -> str: def _getStoreName(words: list[tuple]) -> str: