Feature Get exif readable and modifiable and extract

.gitignore

@@ -1,2 +1,3 @@
-test_images/*
+data/*
+notebooks/*
 *.csv

app.py

@@ -1,28 +1,119 @@
-import gradio as gr
-import numpy as np
-import pandas as pd
+"""
+TOC:
+0) IMPORTS 
+1) METADATA
+2) UPLOAD
+3) ANNOTATIONS
+-1) MAIN
+"""
+
+# gradio run.py --demo-name=my_demo
+
+##################################################
+# 0) IMPORTS
+##################################################
+
+# baselayer
 import os
-from tkinter import Tk, filedialog
+from io import BytesIO
+import argparse
+
+# web
 import gradio as gr
+
+# image processing
+from tkinter import Tk, filedialog
 from pathlib import Path
-from io import BytesIO
+from PIL import Image, ExifTags
+from PIL.ExifTags import TAGS
 
-# from transformers import AutoImageProcessor, AutoModelForImageClassification
-# import torch
+# data science
+import numpy as np
+import pandas as pd
 
 
+# from transformers import AutoImageProcessor, AutoModelForImageClassification
+# import torch
 # Load model
 # processor = AutoImageProcessor.from_pretrained("victor/animals-classifier")
 # model = AutoModelForImageClassification.from_pretrained("victor/animals-classifier")
 # model.eval()
 
+##################################################
+# 1) METADATA
+##################################################
+
+
+# this one works with PIL but we don't get all the metadata
+def decode_utf16_little_endian(binary_data):
+    try:
+        # Decode the binary data as UTF-16 Little Endian
+        # print(f"Test:{binary_data.decode('utf-16-le')}")
+        # print(f"Type:{type(binary_data)}")
+        decoded_text = binary_data.decode("utf-16-le").rstrip("\x00")
+        return decoded_text
+    except Exception as e:
+        return f"Error decoding UTF-16 LE: {e}"
+
+
+def get_exif(list_file_paths):
+    metadata_all_file = {}
+    df = pd.DataFrame()
+    for file_path in list_file_paths:
+        metadata = {}
+        print(file_path)
+        try:
+            # file_path = file_path_.split("/")[-1]
+            # df = pd.DataFrame()
+            # df['file_name'] = [file_path]
+            # print(df)
+            # print("inside the tryin")
+            image = Image.open(file_path)
+            exifdata = image._getexif()
+            if exifdata is not None:
+                # print(metadata)
+                for tagid, value in exifdata.items():
+                    # print(tagid, value)
+                    # print(f"Value:{value}")
+                    tagname = TAGS.get(tagid, tagid)
+                    # value = exifdata.get(tagid)
+                    # Handle binary data
+                    if isinstance(value, bytes):
+                        # print(f"Value bytes {value}")
+                        # print(f"Value bytes {type(value)}")
+                        # print(f"Value str {decode_utf16_little_endian(value)}")
+                        value = decode_utf16_little_endian(value)
+                    metadata[tagname] = value
+                    # print(f"\t{metadata}")
+                new_row = {"name": file_path, **metadata}
+                df = pd.concat([df, pd.DataFrame([new_row])], ignore_index=True)
+                # metadata_all_file[file_path] = metadata
+            else:
+                return "No EXIF metadata found."
+        except Exception as e:
+            return f"Error : {e}"
+    print(df)
+    df["name"] = df["name"].apply(lambda filepath: filepath.split("/")[-1])
+    print(df)
+    return df
+
+
+##################################################
+# 2) UPLOAD
+##################################################
+
 
 def get_file_names(files_):
     """
     Get a list of the name of files splitted to get only the proper name
     Input: Uploaded files
     Output: ['name of file 1', 'name of file 2']"""
-    return [file.name.split("/")[-1] for file in files_]
+    return [file.name for file in files_]
+
+
+##################################################
+# 3) ANNOTATIONS
+##################################################
 
 
 def get_annotation(files_):
@@ -31,11 +122,14 @@ def get_annotation(files_):
     Input: Uploaded files
     Output: Df that contains: file_name | label | accuracy
     """
-    df = pd.DataFrame(columns=["file_name", "label", "accuracy"])
-    df["file_name"] = get_file_names(files_)
-    df["label"] = "incoming"  # TODO
-    df["accuracy"] = 100  # TODO
-    return df
+    # df = pd.DataFrame(columns=["file_name", "label", "accuracy"])
+    df_exif = get_exif(get_file_names(files_))
+    print(df_exif)
+    return df_exif
+
+
+def update_dataframe(df):
+    return df  # Simply return the modified dataframe
 
 
 def df_to_csv(df_):
@@ -48,6 +142,11 @@ def df_to_csv(df_):
     return gr.File(value="output.csv", visible=True)
 
 
+##################################################
+# -1) MAIN
+##################################################
+
+
 def process_files(files_):
     """
     Main function
@@ -57,29 +156,45 @@ def process_files(files_):
     - Get the csv output
     """
     df = get_annotation(files_)
-    output_csv = df_to_csv(df)
-    print(df)
-    print(output_csv)
-    print("test")
-    return [df, output_csv]
-
-
-title = "Demo: zero-shot depth estimation with DPT + 3D Point Cloud"
-description = "This demo is a variation from the original <a href='https://huggingface.co/spaces/nielsr/dpt-depth-estimation' target='_blank'>DPT Demo</a>. It uses the DPT model to predict the depth of an image and then uses 3D Point Cloud to create a 3D object."
+    return df
 
 
 with gr.Blocks() as interface:
+    gr.Markdown("# Wildlife.ai Annotation tools")
+    # Upload data
     with gr.Row():
         upload_btn = gr.UploadButton(
-            "Click to Upload a File",
+            "Upload raw data",
             file_types=["image", "video"],
             file_count="multiple",
         )
-    # file_output = gr.File()
-    # output_df = gr.DataFrame()
-    upload_btn.upload(
-        fn=process_files, inputs=upload_btn, outputs=[gr.DataFrame(), gr.Files()]
+        update_btn = gr.Button("Modify raw data")
+        download_raw_btn = gr.Button("Generate raw data as csv")
+        download_modified_btn = gr.Button("Generate new data as a csv")
+        # Get results
+    gr.Markdown("## Results")
+    df = gr.DataFrame(interactive=False)
+    download_raw_btn.click(
+        fn=df_to_csv,
+        inputs=df,
+        outputs=gr.File(visible=False),
+        show_progress=False,
+    )
+    gr.Markdown("## Modified results")
+    df_modified = gr.DataFrame(interactive=True)
+    download_modified_btn.click(
+        fn=df_to_csv,
+        inputs=df_modified,
+        outputs=gr.File(visible=False),
+        show_progress=False,
     )
+    # gr.Markdown("## Extract as CSV")
+    # Buttons
+    upload_btn.upload(fn=process_files, inputs=upload_btn, outputs=df)
+    update_btn.click(fn=update_dataframe, inputs=df, outputs=df_modified)
 
 
-interface.launch(debug=True)
+if __name__ == "__main__":
+    # file_path = "../data/rat1.jpg"
+    # get_exif(file_path)
+    interface.launch(debug=True)