Spaces:
Sleeping
Sleeping
Update split_files_to_excel.py
Browse files- split_files_to_excel.py +113 -1
split_files_to_excel.py
CHANGED
@@ -55,7 +55,119 @@ text_splitter = CharacterTextSplitter(
|
|
55 |
length_function = len,
|
56 |
)
|
57 |
|
58 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
59 |
|
60 |
def group_text_by_font_size(content):
|
61 |
cur_fs = []
|
|
|
55 |
length_function = len,
|
56 |
)
|
57 |
|
58 |
+
|
59 |
+
# Categories
|
60 |
+
categories = [
|
61 |
+
{
|
62 |
+
"topic": "Confidentiality and Privacy Protection",
|
63 |
+
"description": "This topic covers the protection of confidentiality, privacy, and integrity in security systems. It also includes authentication and authorization processes.",
|
64 |
+
"experts": ["Mireille"]
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"topic": "Distributed Trust and End-User Trust Models",
|
68 |
+
"description": "This topic focuses on distributed trust models and how end-users establish trust in secure systems.",
|
69 |
+
"experts": ["Mireille", "Khawla"]
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"topic": "Secure Element and Key Provisioning",
|
73 |
+
"description": "This topic involves the secure element in systems and the process of key provisioning.",
|
74 |
+
"experts": ["Mireille"]
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"topic": "Residential Gateway Security",
|
78 |
+
"description": "This topic covers the security aspects of Residential Gateways.",
|
79 |
+
"experts": ["Mireille"]
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"topic": "Standalone Non-Public Network (SNPN) Inter-Connection and Cybersecurity",
|
83 |
+
"description": "This topic focuses on the inter-connection of Standalone Non-Public Networks and related cyber-security topics.",
|
84 |
+
"experts": ["Khawla"]
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"topic": "Distributed Ledger and Blockchain in SNPN",
|
88 |
+
"description": "This topic covers the use of distributed ledger technology and blockchain in securing Standalone Non-Public Networks.",
|
89 |
+
"experts": ["Khawla"]
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"topic": "Distributed Networks and Communication",
|
93 |
+
"description": "This topic involves distributed networks such as mesh networks, ad-hoc networks, and multi-hop networks, and their cyber-security aspects.",
|
94 |
+
"experts": ["Guillaume"]
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"topic": "Swarm of Drones and Unmanned Aerial Vehicles Network Infrastructure",
|
98 |
+
"description": "This topic covers the network infrastructure deployed by Swarm of Drones and Unmanned Aerial Vehicles.",
|
99 |
+
"experts": ["Guillaume"]
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"topic": "USIM and Over-the-Air Services",
|
103 |
+
"description": "This topic involves USIM and related over-the-air services such as Steering of Roaming, roaming services, network selection, and UE configuration.",
|
104 |
+
"experts": ["Vincent"]
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"topic": "Eco-Design and Societal Impact of Technology",
|
108 |
+
"description": "This topic covers eco-design concepts, including energy saving, energy efficiency, carbon emissions, and the societal impact of technology.",
|
109 |
+
"experts": ["Pierre"]
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"topic": "Service Requirements of New Services",
|
113 |
+
"description": "This topic involves defining service requirements for new services, detecting low signals of new trends and technologies, and assessing their impact on USIM services or over-the-air services.",
|
114 |
+
"experts": ["Ly-Thanh"]
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"topic": "Satellite and Non Terrestrial Networks",
|
118 |
+
"description": "This topic covers satellite networks, Non Terrestrial Networks, Private Networks, IoT, Inter Satellite communication, and Radio Access Network.",
|
119 |
+
"experts": ["Nicolas"]
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"topic": "Public Safety and Emergency Communication",
|
123 |
+
"description": "This topic involves Public Safety Communication, Military Communication, Emergency Calls, Emergency Services, Disaster Communication Access, and other related areas.",
|
124 |
+
"experts": ["Dorin"]
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"topic": "Identifying the Human User of a Subscription",
|
128 |
+
"description": "This topic involves methods and processes for identifying the human user associated with a subscription.",
|
129 |
+
"experts": ["Kumar"] # Les experts pour cette catégorie ne sont pas spécifiés
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"topic": "Authentication and Authorization of Users and Restrictions on Users",
|
133 |
+
"description": "This topic covers authentication and authorization processes, as well as restrictions imposed on users.",
|
134 |
+
"experts": ["Kumar"] # Les experts pour cette catégorie ne sont pas spécifiés
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"topic": "Exposure of User Identity Profile Information",
|
138 |
+
"description": "This topic involves the exposure of user identity profile information and its security implications.",
|
139 |
+
"experts": ["Kumar"] # Les experts pour cette catégorie ne sont pas spécifiés
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"topic": "Identifying non-3GPP Devices Connecting behind a UE or 5G-RG",
|
143 |
+
"description": "This topic involves identifying non-3GPP devices connecting behind a UE (User Equipment) or 5G-RG (5G Residential Gateway).",
|
144 |
+
"experts": ["Kumar"] # Les experts pour cette catégorie ne sont pas spécifiés
|
145 |
+
}
|
146 |
+
]
|
147 |
+
|
148 |
+
df_cate = pd.DataFrame(categories)
|
149 |
+
|
150 |
+
# def update_label(label1):
|
151 |
+
# return gr.update(choices=list(df.columns))
|
152 |
+
|
153 |
+
def functionCall(fi_input, dropdown, choice, chunk_size):
|
154 |
+
if choice == "Intelligent split":
|
155 |
+
return split_in_df(fi_input)
|
156 |
+
elif choice == "Non intelligent split":
|
157 |
+
return non_intelligent_split(fi_input, chunk_size)
|
158 |
+
else:
|
159 |
+
return split_by_keywords(fi_input,dropdown)
|
160 |
+
|
161 |
+
def change_textbox(dropdown,radio):
|
162 |
+
if len(dropdown) == 0 :
|
163 |
+
dropdown = ["introduction", "objective", "summary", "conclusion"]
|
164 |
+
if radio == "Intelligent split by keywords":
|
165 |
+
return gr.Dropdown(dropdown, multiselect=True, visible=True, allow_custom_value=True), gr.Number(visible=False)
|
166 |
+
elif radio == "Non intelligent split":
|
167 |
+
return gr.Dropdown(dropdown, visible=False),gr.Number(label="Chunk size", value=1000, interactive=True, visible=True)
|
168 |
+
else:
|
169 |
+
return gr.Dropdown(dropdown, visible=False),gr.Number(visible=False)
|
170 |
+
|
171 |
|
172 |
def group_text_by_font_size(content):
|
173 |
cur_fs = []
|