File size: 8,208 Bytes
0d3b770 f4b6651 be05f66 79bddfc 6b2f0de 386e89d 1ebe031 faede72 3c88cf4 9cd0ec4 386e89d b91228a b4b2d88 be05f66 55bce6b be05f66 99c1bf6 be05f66 55bce6b 0a22b45 55bce6b be05f66 e388728 be05f66 e388728 f5225ee e388728 99c1bf6 be05f66 b4b2d88 3efa602 f69de3d b4b2d88 f69de3d a0fa291 5464361 fe19668 674de7c 386e89d f69de3d 33565d1 2880c10 6b2f0de 2880c10 0cb3636 17564aa c0c1816 093cfc0 0cb3636 093cfc0 80ad7b9 2880c10 c0c1816 2880c10 59c76ed d43334a d92143f 59c76ed 17c8342 6b2f0de 2880c10 d92143f 2880c10 6b2f0de 674de7c 22f968f 212803e d099849 6998231 212803e 8eb51bf 013a409 2e26803 013a409 2e26803 d099849 3dc7ae1 d099849 0d3b770 99c1bf6 2454d53 b91228a c1c4d5c 22f968f 3dc7ae1 0d3b770 618bce3 0d3b770 a14002e 59c76ed 99c1bf6 0d3b770 d9b19b2 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 | import gradio as gr
def sort_doc(in_list: list, steps_in: int, control: int, prev_list: str):
control_json={'control':'0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ','char':'','leng':62}
if isinstance(in_list, str):
in_list=in_list.split()
#in_list=eval(in_list)
#key_cnt=len(in_list)
#count unique
uni_box=[]
for ea in in_list:
if not ea in uni_box:
uni_box.append(ea)
key_cnt=len(uni_box)
print(key_cnt)
control_char=list(control_json['control'])
char_len=len(control_char)
if not steps_in:
n_cnt=0
nx=key_cnt
while True:
if nx >= 1:
n_cnt+=1
nx = nx/char_len
else:
steps=n_cnt
break
if steps_in:
steps=steps_in
step_cont_box=[]
#prev_list=control_val_box
json_out={}
rev_out={}
big_cnt=0
cnt=0
go=True
if prev_list:
print("LOD")
last_key=list(prev_list.keys())[-1]
print(last_key)
for ea_dig in last_key:
ea_dig=control_json['control'].index(ea_dig)
ea_dig=int(ea_dig)
print(f'{ea_dig} :: {list(control_json["control"][ea_dig])[0]}')
#step_cont_box.append(int(list(control_json["control"][ea_dig])[0]))
step_cont_box.append(ea_dig)
print(step_cont_box)
cnt=int(step_cont_box[-1])+1
if not prev_list:
print("NOT LOD")
for ii in range(steps):
print(ii)
step_cont_box.append(0)
if control:
new_step_cont_box=[]
control_val_box=[]
cont_box_len=len(step_cont_box)
control_len=control_json['leng']-control
control_char=list(control_json['control'][:control_len])
control_val=list(control_json['control'][control_len:])
val_len=len(control_val)
for ea in control_val:
control_val_box.append(ea)
print(f'CONTROL_VAL_BOX:: {control_val_box}')
new_step_cont_box.append(control_json['control'].index(control_val_box[-1]))
for iii in step_cont_box:
new_step_cont_box.append(iii)
step_cont_box=new_step_cont_box
pos=len(step_cont_box)-1
if go:
for i, ea in enumerate(in_list):
if not ea in list(rev_out.keys()):
if go:
if cnt > char_len-1:
#print(step_cont_box)
go1=True
for ii,ev in enumerate(step_cont_box):
if go:
if ev >= char_len-1:
step_cont_box[ii]=0
if go1==True:
step_cont_box[ii-1]=step_cont_box[ii-1]+1
go1=False
cnt=1
else:
step_cont_box[pos]=cnt
cnt+=1
#print(step_cont_box)
out_js=""
for iii,j in enumerate(step_cont_box):
#print(j)
out_js = out_js+control_char[j]
#if not in_list[i] in list(rev_out.keys()):
json_out[out_js]=in_list[i]
rev_out[in_list[i]]=out_js
big_cnt+=1
if big_cnt==key_cnt:
print("DONE")
go=False
return json_out,rev_out
def sort_doc_OG(in_list: list, steps_in: int, control: int, prev_list: str):
control_json={'control':'0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ','char':'','leng':62}
key_cnt=len(in_list)
print(key_cnt)
#if isinstance(in_list, str):
# in_list=eval(in_list)
control_char=list(control_json['control'])
char_len=len(control_char)
if not steps_in:
n_cnt=0
nx=key_cnt
while True:
if nx >= 1:
n_cnt+=1
nx = nx/char_len
else:
steps=n_cnt
break
if steps_in:
steps=steps_in
if control:
control_len=control_json['leng']-control
control_char=list(control_json['control'][:control_len])
control_val=list(control_json['control'][control_len:])
val_len=len(control_val)
control_val_box=[]
for ea in control_val:
control_val_box.append(ea)
print(f'CONTROL_VAL_BOX:: {control_val_box}')
#prev_list=control_val_box
json_out={}
big_cnt=0
cnt=0
go=True
step_cont_box=[]
if prev_list:
print("LOD")
last_key=list(prev_list.keys())[-1]
print(last_key)
for ea_dig in last_key:
ea_dig=control_json['control'].index(ea_dig)
ea_dig=int(ea_dig)
print(f'{ea_dig} :: {list(control_json["control"][ea_dig])[0]}')
#step_cont_box.append(int(list(control_json["control"][ea_dig])[0]))
step_cont_box.append(ea_dig)
print(step_cont_box)
cnt=int(step_cont_box[-1])+1
if not prev_list:
print("NOT LOD")
for ii in range(steps):
print(ii)
step_cont_box.append(0)
pos=len(step_cont_box)-1
if go:
for i, ea in enumerate(in_list):
if go:
if cnt > char_len-1:
#print(step_cont_box)
go1=True
for ii,ev in enumerate(step_cont_box):
if go:
if ev >= char_len-1:
step_cont_box[ii]=0
if go1==True:
step_cont_box[ii-1]=step_cont_box[ii-1]+1
go1=False
cnt=1
else:
step_cont_box[pos]=cnt
cnt+=1
#print(step_cont_box)
out_js=""
for iii,j in enumerate(step_cont_box):
#print(j)
out_js = out_js+control_char[j]
json_out[out_js]=in_list[i]
big_cnt+=1
if big_cnt==key_cnt:
print("DONE")
go=False
return json_out
def find_query(query,sen,nouns):
blob_f = TextBlob(query)
noun_box={}
noun_list=[]
sen_box=[]
for ea in blob_f.parse().split(" "):
n=ea.split("/")
if n[1] == "NN":
noun_list.append(n[0])
nouns_l=list(nouns.keys())
for nn in nouns_l:
for nl in noun_list:
if nl in nn:
if nl in noun_box:
for ea_n in nouns[nn]:
noun_box[str(nl)].append(ea_n)
else:
noun_box[str(nl)]=[]
for ea_n in nouns[nn]:
noun_box[str(nl)].append(ea_n)
for ea in noun_box.values():
for vals in ea:
sen_box.append({'sen_num':sen[vals]['sen_num'],'sentence':sen[vals]['sentence']})
return noun_box,sen_box
with gr.Blocks() as app:
inp = gr.Textbox(label="Paste Text",lines=10, value="['skdflsdj','sd','sdfsdf','sdfsddsfsd','sdfsdfd','df']")
with gr.Row():
steps=gr.Slider(label="Steps",minimum=0,maximum=12,step=1,value=0)
control=gr.Slider(label="Control",minimum=0,maximum=32,step=1,value=0)
prev_doc=gr.File()
btn = gr.Button("Load Document")
with gr.Row():
query=gr.Textbox(label="Search query")
search_btn=gr.Button("Search")
out_box=gr.Textbox(label="Results")
sen_box=gr.JSON(label="Sentences")
with gr.Row():
with gr.Column(scale=2):
sen=gr.JSON(label="Sentences")
with gr.Column(scale=1):
nouns=gr.JSON(label="Nouns")
search_btn.click(find_query,[query,sen,nouns],[out_box])
btn.click(sort_doc,[inp,steps,control,prev_doc],[sen,nouns])
app.launch()
|