forked from Seagate/cortx
-
Notifications
You must be signed in to change notification settings - Fork 0
/
search.py
583 lines (462 loc) · 23.3 KB
/
search.py
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
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
import boto3
from botocore.exceptions import ClientError
from botocore.client import Config
from modzy import ApiClient
from pdf2image import convert_from_bytes
import streamlit as st
import base64
import uuid
import re
from weasyprint import HTML
import json
import numpy as np
import pandas as pd
from collections import Counter
input_config = 'config.json'
colors = ['#7aecec', '#aa9cfc', '#feca74', '#bfe1d9', '#c887fb', '#e4e7d2',
'#905829', '#dfcd62', '#e8d53d', '#f0c88b', '#b68282', '#799fb2',
'#c3b489', '#bf9a81', '#a592ae', '#e5aef9', '#f69419', '#a36b42',
'#e5c3a6', '#4fc6b4', '#d9e69a', '#f76b6b', '#e8d53d', '#61c861',
'#65a4d9', '#b8ff57', '#779987', '#f69419']
st.set_page_config(
page_title="Object Storage Statistical Scanner App",
page_icon=":shark:",
layout="wide",
initial_sidebar_state="auto",
menu_items={
'About': "# S3 Statistical File Scanner. This is an *extremely* cool app!"
}
)
st.title("Cortx Statistical File Scanner")
st.sidebar.write("Enter Cortx S3 Credentials")
form = st.sidebar.form("aws_credentials")
if 'job_ids' not in st.session_state:
st.session_state.job_ids = []
if 'person_entity_data' not in st.session_state:
st.session_state.person_entity_data = []
if 'location_entity_data' not in st.session_state:
st.session_state.location_entity_data = []
if 'organization_entity_data' not in st.session_state:
st.session_state.organization_entity_data = []
if 'tag_data' not in st.session_state:
st.session_state.tag_data = []
if 'summary_data' not in st.session_state:
st.session_state.summary_data = []
if 'file_data_tags' not in st.session_state:
st.session_state.file_data_tags = dict()
if 'file_data_entities' not in st.session_state:
st.session_state.file_data_entities = dict()
if 'file_data_summary' not in st.session_state:
st.session_state.file_data_summary = dict()
if 'full_report_download_link' not in st.session_state:
st.session_state.full_report_download_link = None
@st.cache
def beautify_tags(tags):
"""
Function to beautify tags result
Args:
tags: list of tags
"""
div = '<div class="entities" style="line-height: 2.5; direction: ltr">'
mark = '<mark class="entity" style="background:{}; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;">{}\n<span style="font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; text-transform: uppercase; vertical-align: middle; margin-left: 0.5rem"></span></mark>'
html = "" + div
for i in range(len(tags[:5])):
html += mark.format("#F63366", tags[i])
html += '</div>'
html += div
for i in range(5, len(tags)):
html += mark.format("#F63366", tags[i])
html += '</div>'
return html
@st.cache
def beautify_html(html: str, title=False, title_string=""):
"""
Function to display border.
Args:
html: html string to beautify
title: bool
title_string: string that appears as header
"""
if title:
WRAPPER = """<div style="border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem; margin-bottom: 2.5rem"><header><h3 style="text-decoration: underline;">{}<h3></header>{}</div>"""
html = html.replace("\n", " ")
return WRAPPER.format(title_string, html)
else:
WRAPPER = """<div style="border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem; margin-bottom: 2.5rem">{}</div>"""
html = html.replace("\n", " ")
return WRAPPER.format(html)
@st.cache
def beautify_entities(response):
"""
Function to beautify entities result
Args:
response: entity response from Modzy
"""
unique_entities = list(set([tag[1] for tag in response]))
entity_color = dict()
for i in range(len(unique_entities)):
entity_color[unique_entities[i]] = colors[i]
div1 = '<div class="entities" style="line-height: 2.5; direction: ltr">'
mark1 = '<mark class="entity" style="background:'
mark2 = '; padding: 0.45em 0.6em; margin: 0 0.25em; line-height: 1; border-radius: 0.35em;">'
sp1 = '<span style="font-size: 0.8em; font-weight: bold; line-height: 1; border-radius: 0.35em; text-transform: uppercase; vertical-align: middle; margin-left: 0.5rem">'
e1 = '</span></mark>'
html = ""
html += div1
for i in range(len(response)):
if response[i][1] == "O":
html += response[i][0] + " "
else:
html += mark1 + entity_color[response[i][1]] + mark2 + response[i][0] + sp1 + response[i][1] + e1
html += '</div>'
return html
def download_file(object_to_download, name):
"""
Function to download visualized result to as a .pdf file.
Args:
object_to_download: object/var to download
name: name to give to downloaded file
"""
try:
b64 = base64.b64encode(object_to_download.encode()).decode()
except AttributeError as e:
b64 = base64.b64encode(object_to_download).decode()
button_text = 'Save Result'
button_uuid = str(uuid.uuid4()).replace('-', '')
button_id = re.sub('\d+', '', button_uuid)
custom_css = f"""
<style>
#{button_id} {{
background-color: rgb(255, 255, 255);
color: rgb(38, 39, 48);
padding: 0.25em 0.38em;
position: relative;
text-decoration: none;
border-radius: 4px;
border-width: 1px;
border-style: solid;
border-color: rgb(230, 234, 241);
border-image: initial;
}}
#{button_id}:hover {{
border-color: rgb(246, 51, 102);
color: rgb(246, 51, 102);
}}
#{button_id}:active {{
box-shadow: none;
background-color: rgb(246, 51, 102);
color: white;
}}
</style> """
dl_link = custom_css + f'<a download="{name}" id="{button_id}" href="data:file/txt;base64,{b64}">{button_text}</a><br></br>'
return dl_link
def load_config():
"""
Load Modzy API configurations from config.json file
"""
with open('api_config.json') as f:
return json.load(f)
@st.cache(allow_output_mutation=True)
def get_client():
"""
Function to get modzy client
"""
config = load_config()
if not config["API_URL"] and config["API_KEY"]:
st.error("Please update api_config.json file with valid credentials...")
else:
try:
client = ApiClient(base_url=config["API_URL"], api_key=config["API_KEY"])
except:
st.error("Couldn't connect to Modzy server, please verify credentials...")
return client
@st.cache
def get_model_output(client, model_identifier, model_version, data_sources, explain=False):
"""
Args:
client: modzy client object
model_identifier: model identifier (string)
model_version: model version (string)
data_sources: dictionary with the appropriate filename --> local file key-value pairs
explain: boolean variable, defaults to False. If true, model will return explainable result
"""
client = get_client()
if model_identifier == "c60c8dbd79":
job = client.jobs.submit_files_bulk(model_identifier, model_version, data_sources)
else:
job = client.jobs.submit_text(model_identifier, model_version, data_sources, explain)
result = client.results.block_until_complete(job, timeout=None)
model_output = result.get_first_outputs()['results.json']
st.session_state.job_ids.append(job.jobIdentifier)
return model_output
@st.cache
def get_model(client, model_name):
"""
Function to load model based on name
Args:
client: modzy client object
model_name: model name to load
"""
model = client.models.get_by_name(model_name)
modelVersion = client.models.get_version(model, model.latest_version)
return model, modelVersion.version
def prepare_statistical_summary(s3_resource, s3_client, bucket_name, client):
objects_response = s3_client.list_objects(Bucket=bucket_name)
try:
if objects_response['Contents']:
for object in objects_response['Contents']:
key = object['Key']
# for pdf's do
if key.endswith('.pdf'):
image_files = []
content = s3_resource.Object(bucket_name, object['Key']).get()['Body'].read()
images = convert_from_bytes(content, fmt='png')
key = key.replace('.pdf', '')
for image in images:
image.save('data/images/' + str(key) + '_page' + str(
images.index(image)) + '.jpg', 'JPEG')
image_files.append('data/images/' + str(key) + '_page' + str(
images.index(image)) + '.jpg')
sources = {}
for page in image_files:
sources['page' + str(image_files.index(page))] = {
'input': page,
'config.json': input_config
}
# convert pdf documents to images for OCR
model, model_version = get_model(client, "Multi-language OCR")
ocr_output = get_model_output(client, model.modelId, model_version, sources, explain=False)
ocr_text = beautify_html(ocr_output["text"], title=True, title_string="OCR")
# st.write("")
# st.markdown(ocr_text, unsafe_allow_html=True)
# extract topics from OCR texts
model, model_version = get_model(client, "Text Topic Modeling")
sources = {"source-key": {"input.txt": ocr_text}}
text_topic_result = get_model_output(client, model.modelId, model_version, sources, explain=False)
st.session_state.tag_data.append(text_topic_result)
tags = beautify_html(beautify_tags(text_topic_result), title=True, title_string="Tags")
st.session_state.file_data_tags[object['Key']] = tags
# st.write("")
# st.markdown(tags, unsafe_allow_html=True)
# Generate summary from OCR text
model, model_version = get_model(client, "Text Summarization")
sources = {"source-key": {"input.txt": ocr_text}}
text_summarization_result = get_model_output(client, model.modelId, model_version, sources,
explain=False)
st.session_state.summary_data.append(text_summarization_result["summary"])
summary = beautify_html(text_summarization_result["summary"], title=True, title_string="Summary")
st.session_state.file_data_summary[object['Key']] = summary
# st.write("")
# st.markdown(summary, unsafe_allow_html=True)
# Named Entity Recognition from OCR text
modelId, model_version = "a92fc413b5", "0.0.12"
sources = {"source-key": {"input.txt": ocr_text}}
named_entity_recognition_result = get_model_output(client, modelId, model_version, sources,
explain=False)
# find B-PER, I-PER, B-LOC, I-LOC, B-ORG, I-ORG, remove duplicate entities
persons = list(set([tag[0] for tag in named_entity_recognition_result if
tag[1] == 'B-PER' or tag[1] == 'I-PER']))
locations = list(set([tag[0] for tag in named_entity_recognition_result if
tag[1] == 'B-LOC' or tag[1] == 'I-LOC']))
organizations = list(set([tag[0] for tag in named_entity_recognition_result if
tag[1] == 'B-ORG' or tag[1] == 'I-ORG']))
st.session_state.person_entity_data.append(persons)
st.session_state.location_entity_data.append(locations)
st.session_state.organization_entity_data.append(organizations)
# st.write("")
entities = beautify_html(beautify_entities(named_entity_recognition_result), title=True, title_string="Entities")
st.session_state.file_data_entities[object['Key']] = entities
# download report link
pdfile = HTML(string=tags + summary + beautify_html(entities, title=True,
title_string="Entities")).write_pdf()
download_button_str = download_file(pdfile, f'Summary_%s.pdf' % key)
st.markdown(download_button_str, unsafe_allow_html=True)
# for text files do
if key.endswith('.txt'):
body = s3_resource.Object(bucket_name, object['Key']).get()['Body'].read()
# extract topics from texts
model, model_version = get_model(client, "Text Topic Modeling")
sources = {"source-key": {"input.txt": body.decode("utf-8")}}
text_topic_result = get_model_output(client, model.modelId, model_version, sources, explain=False)
st.session_state.tag_data.append(text_topic_result)
tags = beautify_html(beautify_tags(text_topic_result), title=True, title_string="Tags")
st.session_state.file_data_tags[object['Key']] = tags
# st.write("")
# st.markdown(tags, unsafe_allow_html=True)
# Generate summary from text
model, model_version = get_model(client, "Text Summarization")
sources = {"source-key": {"input.txt": body.decode("utf-8")}}
text_summarization_result = get_model_output(client, model.modelId, model_version, sources,
explain=False)
st.session_state.summary_data.append(text_summarization_result["summary"])
summary = beautify_html(text_summarization_result["summary"], title=True, title_string="Summary")
st.session_state.file_data_summary[object['Key']] = summary
# st.write("")
# st.markdown(summary, unsafe_allow_html=True)
# Named Entity Recognition from text
modelId, model_version = "a92fc413b5", "0.0.12"
sources = {"source-key": {"input.txt": body.decode("utf-8")}}
named_entity_recognition_result = get_model_output(client, modelId, model_version, sources,
explain=False)
# find B-PER, I-PER, B-LOC, I-LOC, B-ORG, I-ORG, remove duplicate entities
persons = list(set([tag[0] for tag in named_entity_recognition_result if
tag[1] == 'B-PER' or tag[1] == 'I-PER']))
locations = list(set([tag[0] for tag in named_entity_recognition_result if
tag[1] == 'B-LOC' or tag[1] == 'I-LOC']))
organizations = list(set([tag[0] for tag in named_entity_recognition_result if
tag[1] == 'B-ORG' or tag[1] == 'I-ORG']))
st.session_state.person_entity_data.append(persons)
st.session_state.location_entity_data.append(locations)
st.session_state.organization_entity_data.append(organizations)
# st.write("")
entities = beautify_html(beautify_entities(named_entity_recognition_result), title=True, title_string="Entities")
st.session_state.file_data_entities[object['Key']] = entities
# download report
pdfile = HTML(string=tags + summary + beautify_html(entities, title=True,
title_string="Entities")).write_pdf()
download_button_str = download_file(pdfile, f'Summary_%s.pdf' % key)
st.markdown(download_button_str, unsafe_allow_html=True)
except ClientError as e:
st.error("Enter correct credentials")
if e.response['Error']['Code'] == 'InvalidAccessKeyId':
print("Invalid Access Key ID")
elif e.response['Error']['Code'] == 'InvalidSecurity':
print("Invalid Secret Access Key")
elif e.response['Error']['Code'] == 'AccessDenied':
print("Access Denied")
else:
print("Unknown Error")
def plot_summary():
tagCounter = Counter(flatten_list(st.session_state.tag_data))
tag_chart_data = pd.DataFrame.from_dict(tagCounter, orient='index', columns=['Tags'])
st.bar_chart(tag_chart_data)
personCounter = Counter(flatten_list(st.session_state.person_entity_data))
person_chart_data = pd.DataFrame.from_dict(personCounter, orient='index', columns=["People"])
st.bar_chart(person_chart_data)
organizationCounter = Counter(flatten_list(st.session_state.organization_entity_data))
org_chart_data = pd.DataFrame.from_dict(organizationCounter, orient='index', columns=["Organizations"])
st.bar_chart(org_chart_data)
locationCounter = Counter(flatten_list(st.session_state.location_entity_data))
location_chart_data = pd.DataFrame.from_dict(locationCounter, orient='index', columns=["Locations"])
st.bar_chart(location_chart_data)
def flatten_list(t):
return [item for sublist in t for item in sublist]
def get_credentials():
access_key = form.text_input('S3 Access Key ID')
secret_key = form.text_input('S3 Secret Access Key')
region = form.text_input('Region')
endpoint = form.text_input('Endpoint')
submitted = form.form_submit_button("Submit")
if submitted:
access_key = access_key.strip()
secret_key = secret_key.strip()
region = region.strip()
endpoint = endpoint.strip()
elif access_key == '' or secret_key == '' or region == '' or endpoint == '':
# st.warning("Please enter correct credentials")
access_key = 'sgiamadmin'
secret_key = 'ldapadmin'
region = 'None'
endpoint = 'http://192.168.1.14:31949'
s3_resource = boto3.resource('s3', endpoint_url=endpoint,
aws_access_key_id=access_key,
aws_secret_access_key=secret_key,
verify=False)
s3_client = boto3.client('s3', endpoint_url=endpoint,
aws_access_key_id=access_key,
aws_secret_access_key=secret_key,
verify=False)
return s3_resource, s3_client
@st.experimental_memo(suppress_st_warning=True)
def select_bucket(_s3_client):
bucket_response = s3_client.list_buckets()
# st.json(bucket_response)
buckets = []
try:
if bucket_response['Buckets']:
for bucket in bucket_response['Buckets']:
buckets.append(bucket['Name'])
return buckets, len(bucket_response['Buckets'])
except ClientError as e:
st.error("Enter correct credentials")
if e.response['Error']['Code'] == 'InvalidAccessKeyId':
print("Invalid Access Key ID")
elif e.response['Error']['Code'] == 'InvalidSecurity':
print("Invalid Secret Access Key")
elif e.response['Error']['Code'] == 'AccessDenied':
print("Access Denied")
else:
print("Unknown Error")
@st.experimental_memo(suppress_st_warning=True)
def select_bucket_objects(_s3_client, bucket_name):
objects_response = s3_client.list_objects(Bucket=bucket_name)
objects = []
try:
if objects_response['Contents']:
for object in objects_response['Contents']:
objects.append(object['Key'])
return objects
except ClientError as e:
st.error("Enter correct credentials")
if e.response['Error']['Code'] == 'InvalidAccessKeyId':
print("Invalid Access Key ID")
elif e.response['Error']['Code'] == 'InvalidSecurity':
print("Invalid Secret Access Key")
elif e.response['Error']['Code'] == 'AccessDenied':
print("Access Denied")
else:
print("Unknown Error")
@st.experimental_memo(suppress_st_warning=True)
def list_files(_s3_client, _s3_resource, bucket_name):
size = 0
try:
list_response = s3_client.list_objects_v2(Bucket=bucket_name)
# text = ''
# for page in pdf.pages:
# text + page.extractText()
# st.write(text)
if list_response['KeyCount'] == 0:
st.warning("No files found")
return list_response['KeyCount'], size
else:
for i in list_response.get('Contents'):
size += i.get('Size')
return list_response['KeyCount'], size
except ClientError as e:
st.error("Enter correct credentials")
if e.response['Error']['Code'] == 'InvalidAccessKeyId':
print("Invalid Access Key ID")
elif e.response['Error']['Code'] == 'InvalidSecurity':
print("Invalid Secret Access Key")
elif e.response['Error']['Code'] == 'AccessDenied':
print("Access Denied")
else:
print("Unknown Error")
s3_resource, s3_client = get_credentials()
file_count, size, bucket_count = 0, 0, 0
buckets, bucket_count = select_bucket(s3_client)
bucket_option = st.selectbox("Select Bucket", buckets)
file_count, size = list_files(s3_client, s3_resource, bucket_option)
col1, col2, col3 = st.columns(3)
col1.metric('Total S3 Buckets', value=bucket_count, delta=bucket_count)
col2.metric('Total Files', value=file_count, delta=file_count)
col3.metric('Total Size (Bytes)', value=size, delta=size)
client = get_client()
ocr = st.button("Start Statistical Analyzer")
plot_summary()
select_bucket_objects(s3_client, 'test')
if ocr:
prepare_statistical_summary(s3_resource, s3_client, bucket_option, client)
report_option = st.sidebar.radio("Select to view individual file report", ('None', 'Topics', 'Entity', 'Summary'))
container = st.container()
if report_option == 'Topics':
file = st.sidebar.selectbox("Select file", select_bucket_objects(s3_client, bucket_option))
container.markdown(st.session_state.file_data_tags[file], unsafe_allow_html=True)
elif report_option == 'Entity':
file = st.sidebar.selectbox("Select file", select_bucket_objects(s3_client, bucket_option))
container.markdown(st.session_state.file_data_entities[file], unsafe_allow_html=True)
elif report_option == 'Summary':
file = st.sidebar.selectbox("Select file", select_bucket_objects(s3_client, bucket_option))
container.markdown(st.session_state.file_data_summary[file], unsafe_allow_html=True)
else:
container.empty()