File size: 3,622 Bytes
7b79b85
b42d6ec
 
 
9ac2440
e4387b3
 
 
 
b42d6ec
 
 
 
444b42f
b42d6ec
4d57e5c
 
4bf21c7
4d57e5c
 
b42d6ec
4d57e5c
 
 
 
b42d6ec
eea98e7
b42d6ec
4d57e5c
 
eb822d4
4d57e5c
 
 
b42d6ec
4d57e5c
 
 
 
 
 
 
 
 
 
7b79b85
4d57e5c
37bfbd1
7b79b85
4d57e5c
7b79b85
c8197d8
4d57e5c
 
 
4bf21c7
 
3851673
4bf21c7
9ac2440
3851673
9ac2440
4d57e5c
 
3851673
9ac2440
4d57e5c
9ac2440
1346633
4d57e5c
 
 
 
 
 
 
 
3851673
4d57e5c
9ac2440
 
 
 
4bf21c7
9ac2440
 
 
 
 
 
 
7b79b85
4d57e5c
9ac2440
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
import os
# Upload credential json file from default compute service account
os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "herbaria-ai-3c860bcb0f44.json"

import pandas as pd
from google.api_core.client_options import ClientOptions
from google.cloud import documentai_v1 as documentai
from google.cloud.documentai_v1.types import RawDocument
from google.cloud import translate_v2 as translate
import zipfile
import os
import io
import gradio as gr

# Set your Google Cloud Document AI processor details here
project_id = "herbaria-ai"
location = "us"
processor_id = "de954414712822b3"

def translate_text(text, target_language="en"):
    translate_client = translate.Client()
    result = translate_client.translate(text, target_language=target_language)
    return result["translatedText"]

def batch_process_documents(file_path: str, file_mime_type: str) -> tuple:
    opts = ClientOptions(api_endpoint=f"{location}-documentai.googleapis.com")
    client = documentai.DocumentProcessorServiceClient(client_options=opts)

    with open(file_path, "rb") as file_stream:
        raw_document = RawDocument(content=file_stream.read(), mime_type=file_mime_type)

    name = client.processor_path(project_id, location, processor_id)
    request = documentai.ProcessRequest(name=name, raw_document=raw_document)
    result = client.process_document(request=request)

    extracted_text = result.document.text
    translated_text = translate_text(extracted_text)
    return extracted_text, translated_text

def unzip_and_find_jpgs(file_path):
    extract_path = "extracted_files"
    os.makedirs(extract_path, exist_ok=True)
    jpg_files = []
    with zipfile.ZipFile(file_path, 'r') as zip_ref:
        zip_ref.extractall(extract_path)
        for root, dirs, files in os.walk(extract_path):
            if '__MACOSX' in root:
                continue
            for file in files:
                if file.lower().endswith('.jpg'):
                    full_path = os.path.join(root, file)
                    jpg_files.append(full_path)
    return jpg_files

def process_images(uploaded_file):
    # Reinitialize the DataFrame each time this function is called
    results_df = pd.DataFrame(columns=["Filename", "Extracted Text", "Translated Text"])
    print("DataFrame reinitialized:", results_df)  # Debugging statement

    file_path = uploaded_file.name  # Gradio provides the file path through the .name attribute
    print("Processing file:", file_path)  # Debugging statement

    try:
        image_files = unzip_and_find_jpgs(file_path)
        print("Found image files:", image_files)  # Debugging statement

        if not image_files:
            return "No JPG files found in the zip."

        for file_path in image_files:
            extracted_text, translated_text = batch_process_documents(file_path, "image/jpeg")
            new_row = pd.DataFrame([{
                "Filename": os.path.basename(file_path),
                "Extracted Text": extracted_text,
                "Translated Text": translated_text
            }])
            results_df = pd.concat([results_df, new_row], ignore_index=True)
        print("Current DataFrame state:", results_df)  # Debugging statement
    except Exception as e:
        return f"An error occurred: {str(e)}"

    return results_df.to_html()


interface = gr.Interface(
    fn=process_images,
    inputs="file",
    outputs="html",
    title="Document AI Translation",
    description="Upload a ZIP file containing JPEG/JPG images, and the system will extract and translate text from each image."
)

if __name__ == "__main__":
    interface.launch(debug=True)