Spaces:
Sleeping
Sleeping
| import os | |
| from typing import Optional | |
| import pandas as pd | |
| from pdf2image import convert_from_path | |
| from PIL import Image | |
| from .config import settings | |
| from striprtf.striprtf import rtf_to_text | |
| from docx import Document | |
| class FileProcessor: | |
| def __init__(self): | |
| pass | |
| def process_pdf(self, file_path: str) -> str: | |
| #list of images | |
| return convert_from_path(file_path) | |
| def process_image(self, file_path: str) -> str: | |
| return Image.open(file_path).convert('RGB') | |
| def process_doc(self, file_path: str) -> str: | |
| def split_doc(data: str) -> list: | |
| line_data = data.split('\n') | |
| line_count = len(line_data) | |
| #split by three | |
| split_len = line_count//3 | |
| #split by 3 and also handle the case where the split is not even, so that the last one has the remaining lines | |
| doc_split = [line_data[i:i+split_len] for i in range(0, line_count, split_len)] | |
| #under each split, merge the line data into a single line | |
| doc_split = ['\n'.join(split) for split in doc_split] | |
| return doc_split | |
| if file_path.lower().endswith('.doc'): | |
| with open(file_path, "r", encoding='utf-8', errors='ignore') as file: | |
| data = rtf_to_text(file.read()) | |
| if len(data.split('\n')) > 200: | |
| split_data = split_doc(data) | |
| return split_data | |
| else: | |
| return data | |
| else: | |
| doc = Document(file_path) | |
| return '\n'.join([paragraph.text for paragraph in doc.paragraphs]) | |
| def process_docx(self, file_path: str) -> str: | |
| doc = Document(file_path) | |
| return '\n'.join([paragraph.text for paragraph in doc.paragraphs]) | |
| def process_xlsx(self, file_path: str) -> str: | |
| df = pd.read_excel(file_path) | |
| return df.to_string() | |
| def process_csv(self, file_path: str) -> str: | |
| df = pd.read_csv(file_path) | |
| return df.to_string() | |
| def process_txt(self, file_path: str) -> str: | |
| with open(file_path, 'r') as file: | |
| return file.read() | |
| def process_file(self, file_path: str) -> str: | |
| """Main method to process any supported file type.""" | |
| _, file_extension = os.path.splitext(file_path) | |
| processors = { | |
| '.pdf': self.process_pdf, | |
| '.jpeg':self.process_image, | |
| '.jpg':self.process_image, | |
| '.png':self.process_image, | |
| '.doc': self.process_doc, | |
| '.docx': self.process_docx, | |
| '.xls': self.process_xlsx, | |
| '.xlsx': self.process_xlsx, | |
| '.csv': self.process_csv, | |
| '.txt': self.process_txt | |
| } | |
| processor = processors.get(file_extension.lower()) | |
| if not processor: | |
| raise ValueError(f"Unsupported file format: {file_extension}") | |
| return processor(file_path) |