Spaces:
Running
Running
File size: 7,991 Bytes
b31069e e1bcbc6 b3efaf6 e1bcbc6 b31069e e1bcbc6 b31069e b3efaf6 b31069e bc557f4 b31069e bc557f4 b31069e e1bcbc6 0b57b35 e1bcbc6 bc557f4 e1bcbc6 b31069e e1bcbc6 b31069e e1bcbc6 b31069e e1bcbc6 b31069e e1bcbc6 b31069e b3efaf6 bc557f4 41b1753 bc557f4 e1bcbc6 bc557f4 e1bcbc6 b31069e |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 |
import streamlit as st
import pymupdf as fitz
import pyperclip
from utils.audit.audit_doc import audit_descriptif_pdf,audit_text,audit_descriptif_word
import dotenv
from utils.audit.audit_audio import evaluate_audio_quality
from PIL import Image
from io import BytesIO
# Function to classify file type
def classify_file(file):
if file.type.startswith("image/"):
return "image"
elif file.type == "application/pdf":
return "pdf"
elif file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
return "word"
elif file.type.startswith("audio/"):
return "audio"
elif file.type.startswith("text/"):
return "text"
else:
return "unknown"
#display content
def display_content_doc(content:dict):
number_of_pages = len(content)
st.info("si vous choisissez 0, vous verrez le contenu de toutes les pages")
number = st.number_input("Numéro de page", min_value=0, max_value=number_of_pages, value=0,key="number_page_content")
#0 means all pages
if number > 0:
page : dict = content[f"page_{number-1}"]
option = st.radio("Type de contenu",list(content[f"page_0"].keys()), index=0,horizontal=True)
if option == "images":
if number == 0:
images = [img for page in content.values() for img in page["images"]]
else:
images = page["images"]
col1,col2,col3 = st.columns(3)
for i, (img_bytes, img_width, img_height) in enumerate(images):
if i%3 == 0:
col1.image(Image.open(BytesIO(img_bytes)), caption=f'Image {i + 1}', width=img_width)
elif i%3 == 1:
col2.image(Image.open(BytesIO(img_bytes)), caption=f'Image {i + 1}', width=img_width)
else:
col3.image(Image.open(BytesIO(img_bytes)), caption=f'Image {i + 1}', width=img_width)
elif option == "texte":
if number == 0:
text = "-------------------\n".join([page["texte"] for page in content.values()])
else:
text = page["texte"]
st.text_area("Texte",text,height=200)
elif option == "liens":
if number == 0:
links = [link for page in content.values() for link in page["liens"]]
else:
links = page["liens"]
for i, link in enumerate(links):
st.markdown(f"- {i+1}: {link['uri']} (page {link['page']})")
def display_audit_pdf(uploaded_file):
if st.session_state.name_file != uploaded_file.name:
st.session_state.name_file = uploaded_file.name
with st.spinner("Analyse du document..."):
st.session_state.audit = audit_descriptif_pdf(uploaded_file,200)
audit = st.session_state.audit["audit"]
content = st.session_state.audit["content"]
#global audit
audit_simplified = {
"Nombre de pages": audit["number_of_pages"],
"Nombre d'images": audit["number_of_images"],
"Nombre de liens": audit["number_of_links"],
"Nombre de tableaux": audit["number_of_tables"],
"Nombre de tokens": audit["number_of_tokens"],
"Nombre de mots": audit["number_of_words"],
"Mots clés": audit["key_words"]
}
well_formatted_audit = "Contenus audités\n"
for key, value in audit_simplified.items():
well_formatted_audit += f"- {key}: {value}\n"
st.code(well_formatted_audit)
#audit par page
with st.expander("Audit par page"):
number = st.number_input("Numéro de page", min_value=1, max_value=audit["number_of_pages"], value=1,key="number_page_audit")
audit_page = audit[f"page_{number-1}"]
audit_page = {
"Nombre d'images": audit_page["number_of_images"],
"Nombre de liens": audit_page["number_of_links"],
"Nombre de tableaux": audit_page["number_of_tables"],
"Nombre de tokens": audit_page["number_of_tokens"],
"Nombre de mots": audit_page["number_of_words"],
}
well_formatted_audit_page = "Audit descriptif\n"
for key, value in audit_page.items():
well_formatted_audit_page += f"- {key}: {value}\n"
st.code(well_formatted_audit_page)
with st.expander("Cliquer ici pour voir le contenu du document"):
display_content_doc(content)
def main():
dotenv.load_dotenv()
# Streamlit app
st.title("AUDIT DES DOCUMENTS")
notice = "Les formats autorisés sont les suivants :\n- **format texte** : txt, word, pdf\n- **format image** : png, jpg\n- **format audio** : wav, MP3"
st.markdown(notice)
if "audit" not in st.session_state:
st.session_state.audit = {}
if "name_file" not in st.session_state:
st.session_state.name_file = ""
# File uploader
uploaded_file = st.file_uploader("Télécharger un ou plusieurs documents")
if uploaded_file is not None:
type = classify_file(uploaded_file)
st.write(f"Type de fichier: {type}")
st.write("### Synthèse audit du ou des document(s) téléchargé(s)")
if type == "pdf":
display_audit_pdf(uploaded_file)
elif type == "audio":
if st.session_state.name_file != uploaded_file.name:
st.session_state.name_file = uploaded_file.name
with st.spinner("Analyse de l'audio..."):
st.session_state.audit = evaluate_audio_quality(uploaded_file)
audit = st.session_state.audit
#audit global simplifié
audit_simplified = {
"Volume": f"{audit['volume']:0.2f} dBFS",
"SNR": f"{max(audit['SNR'],0):0.2f} dB",
"Durée": f"{audit['duration']:0.2f} minutes",
"Nombre de tokens": audit["number_of_tokens"]
}
well_formatted_audit = "Contenus audités\n"
for key, value in audit_simplified.items():
well_formatted_audit += f"- {key}: {value}\n"
st.code(well_formatted_audit)
with st.expander("Transcription"):
st.write(audit["transcription"])
elif type == "text":
text = uploaded_file.read().decode("utf-8")
if st.session_state.name_file != uploaded_file.name:
st.session_state.name_file = uploaded_file.name
with st.spinner("Analyse du texte..."):
st.session_state.audit = audit_text(text)
audit = st.session_state.audit
#audit global simplifié
audit_simplified = {
"Nombre de tokens": audit["number_of_tokens"],
"Nombre de mots": audit["number_of_words"]
}
well_formatted_audit = "Audit descriptif\n"
for key, value in audit_simplified.items():
well_formatted_audit += f"- {key}: {value}\n"
st.code(well_formatted_audit)
elif type == "word":
if st.session_state.name_file != uploaded_file.name:
st.session_state.name_file = uploaded_file.name
with st.spinner("Analyse du document..."):
st.session_state.audit = audit_descriptif_word(uploaded_file)
audit = st.session_state.audit
#global audit
audit_simplified = {
"Nombre de pages": audit["number_of_paragraphs"],
"Nombre d'images": audit["number_of_images"],
"Nombre de liens": audit["number_of_links"],
"Nombre de tableaux": audit["number_of_tables"],
"Nombre de tokens": audit["number_of_tokens"],
"Nombre de mots": audit["number_of_words"]
}
well_formatted_audit = "Contenus audités\n"
for key, value in audit_simplified.items():
well_formatted_audit += f"- {key}: {value}\n"
st.code(well_formatted_audit)
if __name__ == "__main__":
main()
|