Spaces:
Runtime error
Runtime error
File size: 3,693 Bytes
407b660 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 | import os
import pytesseract
from pdf2image import convert_from_path
import fitz # PyMuPDF
import docx
from PIL import Image
import io
def extract_text_from_pdf(file_path):
"""
Extract text from PDF using PyMuPDF (fitz).
Falls back to OCR if needed.
"""
try:
# First try direct text extraction
doc = fitz.open(file_path)
text = ""
for page in doc:
text += page.get_text()
# If no text was extracted, try OCR
if not text.strip():
return extract_text_with_ocr(file_path)
return text
except Exception as e:
print(f"Error extracting text from PDF: {e}")
return extract_text_with_ocr(file_path)
def extract_text_with_ocr(file_path):
"""
Extract text using OCR for scanned documents.
"""
try:
# Convert PDF to images
images = convert_from_path(file_path)
text = ""
# Process each page with OCR
for img in images:
text += pytesseract.image_to_string(img)
return text
except Exception as e:
print(f"OCR extraction error: {e}")
return ""
def extract_text_from_image(file_path):
"""
Extract text from images using OCR.
"""
try:
img = Image.open(file_path)
text = pytesseract.image_to_string(img)
return text
except Exception as e:
print(f"Image OCR error: {e}")
return ""
def extract_text_from_docx(file_path):
"""
Extract text from DOCX files.
"""
try:
doc = docx.Document(file_path)
full_text = []
for para in doc.paragraphs:
full_text.append(para.text)
return "\n".join(full_text)
except Exception as e:
print(f"DOCX extraction error: {e}")
return ""
def extract_text_from_txt(file_path):
"""
Extract text from plain text files.
"""
try:
with open(file_path, 'r', encoding='utf-8') as file:
return file.read()
except UnicodeDecodeError:
# Try with a different encoding if UTF-8 fails
try:
with open(file_path, 'r', encoding='latin-1') as file:
return file.read()
except Exception as e:
print(f"Text file reading error: {e}")
return ""
except Exception as e:
print(f"Text file reading error: {e}")
return ""
def extract_text_from_file(file_path):
"""
Extract text from a file based on its extension.
"""
file_ext = os.path.splitext(file_path)[1].lower()
if file_ext in ['.pdf']:
return extract_text_from_pdf(file_path)
elif file_ext in ['.png', '.jpg', '.jpeg']:
return extract_text_from_image(file_path)
elif file_ext in ['.docx', '.doc']:
return extract_text_from_docx(file_path)
elif file_ext in ['.txt']:
return extract_text_from_txt(file_path)
else:
return "Unsupported file format"
def process_document(file_object, file_path):
"""
Process an uploaded document, extract text, and prepare for vectorization.
"""
try:
# Extract text based on file type
text_content = extract_text_from_file(file_path)
# Basic document preprocessing
if text_content:
# Remove excessive whitespace
text_content = ' '.join(text_content.split())
return {
"content": text_content,
"success": bool(text_content),
"error": "" if text_content else "Failed to extract text"
}
except Exception as e:
return {
"content": "",
"success": False,
"error": str(e)
}
|