import functions as funky # need to enable this for Hugging Face import pandas as pd import gradio as gr import os from datasets import load_dataset from huggingface_hub import login import numpy as np from fastapi import FastAPI, Request import uvicorn from starlette.middleware.sessions import SessionMiddleware import fastapi from datetime import datetime import re login(token = os.environ['HUB_TOKEN']) # logger = gr.HuggingFaceDatasetSaver(os.environ['HUB_TOKEN'], dataset_name='illustration_gdrive_logging_main', private=True) # logger.setup([gr.Text(label="clicked_url"), gr.Text(label="seach_term"), gr.Text(label = 'sessionhash'), gr.Text(label = 'datetime')], './flagged_data_points') logging_js = ''' function magicFunc(x){ let script = document.createElement('script'); script.src = "file/js_functions.js" document.head.appendChild(script); } ''' dataset = load_dataset("bradley6597/illustration-test", data_files = 'data.csv') df = pd.DataFrame(dataset['train']).drop_duplicates() dataset_ai = load_dataset("bradley6597/illustration-test", data_files = 'ai_captions_data.csv') ai_captions = pd.DataFrame(dataset_ai['train']).drop_duplicates() df = df.merge(ai_captions, how = 'left', on = 'clean_link') df['ai_description'] = df['ai_description'].fillna('') ill_links = df.copy() ill_links = ill_links[ill_links['Description'] != 'Moved'].copy() ill_links['code'] = ill_links['link'].str.replace("https://drive.google.com/file/d/", "", regex = False) ill_links['code'] = ill_links['code'].str.replace("/view?usp=drivesdk", "", regex = False) ill_links['filename'] = ill_links['file'].str.replace(".*\\/", "", regex = True) # ill_links['image_code'] = 'https://lh3.google.com/u/0/d/' + ill_links['code'] + '=k' ill_links['image_code'] = 'https://lh3.google.com/u/0/d/' + ill_links['code'] + '=w320-h304' ill_links['image_code'] = np.where(ill_links['file'].str.contains("\\.png$", regex = True), '
' + ill_links['filename'] + '
', '
' + ill_links['filename'] + '
', ) ill_links['shared_drive'] = ill_links['file'].str.replace("/content/drive/Shareddrives/", "", regex = False) ill_links['shared_drive'] = ill_links['shared_drive'].str.replace("(.*?)\\/.*", "\\1", regex = True) ill_links['Description'] = ill_links['Description'].str.replace("No Description", "", regex = False) ill_links['ID'] = ill_links.index ill_links['title'] = ill_links['filename'] ill_links['url'] = ill_links['image_code'] ill_links['filepath'] = ill_links['file'] ill_links['post_filepath'] = ill_links['filepath'].str.replace(".*?\\/KS1 EYFS\\/", "", regex = True) ill_links_title = ill_links.copy() ill_links_ai = ill_links.copy() ill_links['abstract'] = ill_links['filename'].str.replace("\\-|\\_", " ", regex = True) + ' ' + ill_links['Description'].str.replace(",", " ", regex = False).astype(str) ill_links_title['abstract'] = ill_links_title['filename'].str.replace('\\-|\\_', " ", regex = True) ill_links_ai['abstract'] = ill_links_title['ai_description'] ill_check_lst = [] for i in range(0, 5): tmp_links = f'https://lh3.google.com/u/{i}/d/' + ill_links['code'].iloc[0] + '=w320-h304' tmp_links = '' tmp_links = f'

{i}

' + tmp_links ill_check_lst.append(tmp_links) ill_check_df = pd.DataFrame(ill_check_lst).T ill_check_html = ill_check_df.to_html(escape = False, render_links = True, index = False, header = False) ill_links = ill_links[['ID', 'title', 'url', 'abstract', 'filepath', 'Date Created', 'post_filepath', 'parent_id']] ill_links_title = ill_links_title[['ID', 'title', 'url', 'abstract', 'filepath', 'Date Created', 'Description', 'post_filepath', 'parent_id']] ill_links_ai = ill_links_ai[['ID', 'title', 'url', 'abstract', 'filepath', 'Date Created', 'Description', 'post_filepath', 'parent_id']] ind_main, doc_main, tf_main = funky.index_documents(ill_links) del ill_links ind_title, doc_title, tf_title = funky.index_documents(ill_links_title) del ill_links_title ind_ai, doc_ai, tf_ai = funky.index_documents(ill_links_ai) del ill_links_ai def same_auth(username, password): return(username == os.environ['username']) & (password == os.environ['password']) def search_index(search_text, sd, ks, sort_by, max_results, user_num, search_title, image_type, do_not_use, increase = None): max_results_list = ['10', '25', '50', '75', '100', '250', '500', '1000', '5000', '10000', 'All'] if increase: max_results = max_results_list[max_results_list.index(max_results) + 1] if search_title: output = funky.search(tf_title, doc_title, ind_title, search_text, search_type = 'AND', ranking = True) else: output = funky.search(tf_main, doc_main, ind_main, search_text, search_type='AND', ranking = True) # Don't need to order by AI as the AI ranking numbers are much lower than the default numbers output_ai = funky.search(tf_ai, doc_ai, ind_ai, search_text, search_type = 'AND', ranking = True) output.extend(output_ai) output = [x for o in output for x in o if type(x) is not float] load_more_visible = False extra_info = '' if len(output) > 0: output_df = (pd.DataFrame(output) .groupby('url') .first() .reset_index() .drop_duplicates()) output_df['Date Created'] = pd.to_datetime(output_df['Date Created'], format = 'mixed') if do_not_use: output_df = output_df[~output_df['filepath'].str.lower().str.contains("do.*not.*use|not.*general|don\\'t.*use|do.*no.*use|numberblock", regex = True)] map_df = output_df[output_df['title'].str.contains('map|Map', regex = True)] output_df['url'] = output_df['url'].str.replace("/u/0/", f"/u/{int(user_num)}/", regex = False) output_df_temp = pd.DataFrame() if len(sd) > 0: for shared in sd: temp_df = output_df[(output_df['filepath'].str.contains(str(shared), regex = False))] output_df_temp = pd.concat([output_df_temp, temp_df]) output_df = output_df_temp.sort_index() # if len(sd) == 1: # output_df = output_df[(output_df['filepath'].str.contains(str(sd[0]), regex = False))] if len(ks) > 0: keystage_filter = '|'.join(ks).lower() if search_title: output_df['abstract'] = output_df['abstract'] + ' ' + output_df['Description'] output_df['abstract'] = output_df['abstract'].str.lower() output_df['post_filepath'] = output_df['post_filepath'].str.lower() output_df['missing_desc'] = np.where(output_df['abstract'].str.contains('eyfs|ks1|ks2|ks3', regex = True), 0, 1) output_df2 = output_df[(output_df['abstract'].str.contains(keystage_filter, regex = True) | (output_df['missing_desc'] == 1))].copy() output_df2 = output_df2[(output_df2['post_filepath'].str.contains(keystage_filter, regex = True))] if output_df2.shape[0] == 0: output_df2 = output_df[(output_df['post_filepath'].str.contains(keystage_filter, regex = True))] else: output_df['abstract'] = output_df['abstract'].str.lower() output_df['post_filepath'] = output_df['post_filepath'].str.lower() output_df['missing_desc'] = np.where(output_df['abstract'].str.contains('eyfs|ks1|ks2|ks3', regex = True), 0, 1) output_df2 = output_df output_df2['ind'] = output_df2.index min_parent_score = output_df2.groupby('parent_id')['ind'].min().reset_index() min_parent_score.columns = ['parent_id', 'min_parent_ind'] output_df2 = output_df2.merge(min_parent_score, how = 'left', on = 'parent_id') if sort_by == 'Relevance': output_df2 = output_df2.sort_values(by = ['missing_desc', 'min_parent_ind'], ascending = [True, True]) elif sort_by == 'Date Created': output_df2 = output_df2.sort_values(by = ['Date Created'], ascending = False) elif sort_by == 'A-Z': output_df2 = output_df2.sort_values(by = ['title'], ascending = True) image_type_filter = '$|'.join(image_type).lower().replace("jpeg", "jpg") + '$' output_df2 = output_df2[output_df2['filepath'].str.contains(image_type_filter, regex = True)].reset_index(drop = True) total_returned = 'No. of Results to Return (Total: ' + str(output_df2.shape[0]) + ')' if max_results != 'All': if output_df2.shape[0] > int(max_results): load_more_visible = True output_df2 = output_df2.head(int(max_results)) output_df2 = output_df2[['url']].reset_index(drop = True) max_cols = 5 output_df2['row'] = output_df2.index % max_cols for x in range(0, max_cols): tmp = output_df2[output_df2['row'] == x].reset_index(drop = True) tmp = tmp[['url']] if x == 0: final_df = tmp else: final_df = pd.concat([final_df, tmp], axis = 1) final_df = final_df.fillna('') else: final_df = pd.DataFrame(['

No Results Found :(

']) total_returned = 'No. of Results to Return (Total: 0)' if final_df.shape[0] == 0 : final_df = pd.DataFrame(['

No Results Found :(

']) return('
' + extra_info + final_df.to_html(escape = False, render_links = True, index = False, header = False) + '
', gr.update(label = total_returned, value = max_results), gr.update(visible = load_more_visible)) def search_logging(x: str, request: gr.Request): x = 0 # session_id = getattr(request.cookies, 'access-token') # logger.flag(['', x, session_id, str(datetime.now())]) back_to_top_btn_html = ''' ''' style = ''' footer{ display: none !important; } td img{ background-image: linear-gradient(45deg, lightgrey 25%, transparent 25%), linear-gradient(135deg, lightgrey 25%, transparent 25%), linear-gradient(45deg, transparent 75%, lightgrey 75%), linear-gradient(135deg, transparent 75%, lightgrey 75%); background-size: 20px 20px; background-position: 0 0, 10px 0, 10px -10px, 0px 10px; } #toTopBtn { position: fixed; bottom: 10px; float: right; right: 18.5%; left: 77.25%; height: 30px; max-width: 100px; width: 100%; font-size: 12px; border-color: rgba(217,24,120, .5); background-color: rgba(35,153,249,.5); padding: .5px; border-radius: 4px; } .submit-btn{ display:inline-block !important; padding:0.7em 1.4em !important; margin:0 0.3em 0.3em 0 !important; border-radius:0.15em !important; box-sizing: border-box !important; text-decoration:none !important; font-family:'Roboto',sans-serif !important; text-transform:uppercase !important; font-weight:400 !important; color:#FFFFFF !important; background-color:#3369ff !important; box-shadow:inset 0 -0.6em 0 -0.35em rgba(0,0,0,0.17) !important; text-align:center !important; position:relative !important; } .submit-btn:active{ top:0.1em !important; } @media all and (max-width:30em){ .submit-btn{ display:block !important; margin:0.4em auto !important; } } #mapBorder { border-radius: 25px; border: 2px solid orange; } .icon { width:50%; float: left; } ''' with gr.Blocks(css=style, js = logging_js ) as app: with gr.Row(): with gr.Column(min_width = 10): with gr.Row(): gr.HTML("

If you can't see the images please make sure you are signed in to your Twinkl account on Google & you have access to the Shared Drives you are searching :)

To drag images click 'Make Draggable' button and wait until it says 'Drag It!'. After this you can drag the image into a folder on your computer

") gr.HTML(ill_check_html) user_num = gr.Number(value = 0, label = 'Put lowest number of the alarm clock you can see') with gr.Row(): with gr.Column(min_width = 0): search_prompt = gr.Textbox(placeholder = 'search for an illustration', label = 'Search', elem_id = 'search_term') title_search = gr.Checkbox(label = 'Search title only') do_not_use = gr.Checkbox(label = 'Remove Do Not Use Images', value = True) with gr.Column(min_width = 0): shared_drive = gr.Dropdown(choices = ['Accurate Maps and Flags', 'Aus and Nz - Phonics Illustrations', 'Australia - Rhino Readers Illustrations', 'Beyond - Illustrations', 'DO NOT USE IN GENERAL RESOURCES - South Africa', 'Illustrations - 01-10 to 07-22', 'Illustrations - Now', 'Shutter Stock Images', 'Twinkl Art Gallery', 'USA 3rd-8th Grade Illustrations '], multiselect = True, label = 'Shared Drive', value = ['Illustrations - 01-10 to 07-22', 'Illustrations - Now']) with gr.Column(min_width = 0): key_stage = gr.Dropdown(choices = ['EYFS', 'KS1', 'KS2', 'KS3'], multiselect = True, label = 'Key Stage', value = ['EYFS', 'KS1', 'KS2', 'KS3']) with gr.Column(min_width = 0): image_type = gr.Dropdown(choices = ['JPEG', 'PNG', 'TIF', 'TIFF'], multiselect = True, label = 'Image Type', value = ['PNG', 'JPEG', 'TIF', 'TIFF']) with gr.Column(min_width = 0): sort_by = gr.Dropdown(choices = ['Relevance', 'Date Created', 'A-Z'], value = 'Relevance', multiselect = False, label = 'Sort By') max_return = gr.Dropdown(choices = ['10', '25', '50', '75', '100', '250', '500', '1000', '5000', '10000', 'All'], value = '50', multiselect = False, label = 'No. of Results to Return (Total: 0)') with gr.Row(): search_button = gr.Button(value="Search!", interactive = True) with gr.Row(): output_df = gr.HTML() back_top_btn = gr.HTML(back_to_top_btn_html) load_more_results_btn = gr.Button(value = 'Load More Results', interactive = True, visible = False) search_button.click(search_index, inputs=[search_prompt, shared_drive, key_stage, sort_by, max_return, user_num, title_search, image_type, do_not_use], outputs=[output_df, max_return, load_more_results_btn]) search_prompt.submit(search_index, inputs=[search_prompt, shared_drive, key_stage, sort_by, max_return, user_num, title_search, image_type, do_not_use], outputs=[output_df, max_return, load_more_results_btn]) search_button.click(search_logging, inputs=[search_prompt], outputs=None) search_prompt.submit(search_logging, inputs=[search_prompt], outputs=None) load_more_results_btn.click(search_index, inputs=[search_prompt, shared_drive, key_stage, sort_by, max_return, user_num, title_search, image_type, do_not_use, load_more_results_btn], outputs=[output_df, max_return, load_more_results_btn]) app.load() app.auth = (same_auth) app.auth_message = '' fapi = FastAPI() fapi.add_middleware(SessionMiddleware, secret_key=os.environ['session_key']) @fapi.middleware("http") async def add_session_hash(request: Request, call_next): response = await call_next(request) session = request.cookies.get('session') if session: response.set_cookie(key='session', value=request.cookies.get('session'), httponly=True) return response # custom get request handler with params to flag clicks @ fapi.get("/track") async def track(url: str, q: str, request: Request): if q is None: q = '' # logger.flag([url, q, request.cookies['access-token'], str(datetime.now())]) return {"message": "ok"} # mount Gradio app to FastAPI app app2 = gr.mount_gradio_app(fapi, app, path="/", allowed_paths = ["."], auth = same_auth) # serve the app if __name__ == "__main__": uvicorn.run(app2, host="0.0.0.0", port=7860)