Skip to content

fix: Improve field access safety and duration parsing to prevent runtime exceptions #689

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
cyberflying wants to merge 3 commits into
base: main
Choose a base branch
from
Open

fix: Improve field access safety and duration parsing to prevent runtime exceptions #689

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
5e36f29
Refactor to use get_field_value() for safer field access to avoid Key…
cyberflying Dec 14, 2025
bdc64b4
Add try-except for duration parsing to handle ValueError and TypeErro…
cyberflying Dec 14, 2025
134e772
Merge upstream changes: accept deletion of manual script and rename o…
cyberflying Dec 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 17 additions & 9 deletions infra/scripts/index_scripts/03_cu_process_data_text.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -306,6 +306,10 @@ def create_tables():

create_tables()

def get_field_value(fields, field_name, default=""):
field = fields.get(field_name, {})
return field.get('valueString', default)

# Process files and insert into DB and Search
conversationIds, docs, counter = [], [], 0
for path in paths:
Expand All @@ -325,17 +329,21 @@ def create_tables():
start_timestamp = datetime.strptime(start_time, timestamp_format)
conversation_id = file_name.split('convo_', 1)[1].split('_')[0]
conversationIds.append(conversation_id)
duration = int(result['result']['contents'][0]['fields']['Duration']['valueString'])
fields = result['result']['contents'][0]['fields']
duration_str = get_field_value(fields, 'Duration', '0')
try:
duration = int(duration_str)
except (ValueError, TypeError):
duration = 0
end_timestamp = str(start_timestamp + timedelta(seconds=duration)).split(".")[0]
start_timestamp = str(start_timestamp).split(".")[0]
fields = result['result']['contents'][0]['fields']
summary = fields['summary']['valueString']
satisfied = fields['satisfied']['valueString']
sentiment = fields['sentiment']['valueString']
topic = fields['topic']['valueString']
key_phrases = fields['keyPhrases']['valueString']
complaint = fields['complaint']['valueString']
content = fields['content']['valueString']
summary = get_field_value(fields, 'summary')
satisfied = get_field_value(fields, 'satisfied')
sentiment = get_field_value(fields, 'sentiment')
topic = get_field_value(fields, 'topic')
key_phrases = get_field_value(fields, 'keyPhrases')
complaint = get_field_value(fields, 'complaint')
content = get_field_value(fields, 'content')
cursor.execute(
"INSERT INTO processed_data (ConversationId, EndTime, StartTime, Content, summary, satisfied, sentiment, topic, key_phrases, complaint) VALUES (?,?,?,?,?,?,?,?,?,?)",
(conversation_id, end_timestamp, start_timestamp, content, summary, satisfied, sentiment, topic, key_phrases, complaint)
Expand Down
53 changes: 34 additions & 19 deletions infra/scripts/index_scripts/04_cu_process_custom_data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -342,6 +342,10 @@ def create_tables():

create_tables()

def get_field_value(fields, field_name, default=""):
field = fields.get(field_name, {})
return field.get('valueString', default)

ANALYZER_ID = "ckm-json"
# Process files and insert into DB and Search - transcripts
conversationIds, docs, counter = [], [], 0
Expand All @@ -358,17 +362,23 @@ def create_tables():
start_timestamp = datetime.strptime(start_time, timestamp_format)
conversation_id = file_name.split('convo_', 1)[1].split('_')[0]
conversationIds.append(conversation_id)
duration = int(result['result']['contents'][0]['fields']['Duration']['valueString'])

fields = result['result']['contents'][0]['fields']
duration_str = get_field_value(fields, 'Duration', '0')
try:
duration = int(duration_str)
except (ValueError, TypeError):
duration = 0

end_timestamp = str(start_timestamp + timedelta(seconds=duration)).split(".")[0]
start_timestamp = str(start_timestamp).split(".")[0]
fields = result['result']['contents'][0]['fields']
summary = fields['summary']['valueString']
satisfied = fields['satisfied']['valueString']
sentiment = fields['sentiment']['valueString']
topic = fields['topic']['valueString']
key_phrases = fields['keyPhrases']['valueString']
complaint = fields['complaint']['valueString']
content = fields['content']['valueString']
summary = get_field_value(fields, 'summary')
satisfied = get_field_value(fields, 'satisfied')
sentiment = get_field_value(fields, 'sentiment')
topic = get_field_value(fields, 'topic')
key_phrases = get_field_value(fields, 'keyPhrases')
complaint = get_field_value(fields, 'complaint')
content = get_field_value(fields, 'content')
cursor.execute(
"INSERT INTO processed_data (ConversationId, EndTime, StartTime, Content, summary, satisfied, sentiment, topic, key_phrases, complaint) VALUES (?,?,?,?,?,?,?,?,?,?)",
(conversation_id, end_timestamp, start_timestamp, content, summary, satisfied, sentiment, topic, key_phrases, complaint)
Expand Down Expand Up @@ -409,22 +419,27 @@ def create_tables():
timestamp_format = "%Y-%m-%d %H_%M_%S" # Adjust format if necessary
start_timestamp = datetime.strptime(start_time, timestamp_format)

conversation_id = file_name.split('convo_', 1)[1].split('_')[0]
conversationIds.append(conversation_id)

duration = int(result['result']['contents'][0]['fields']['Duration']['valueString'])
fields = result['result']['contents'][0]['fields']
duration_str = get_field_value(fields, 'Duration', '0')
try:
duration = int(duration_str)
except (ValueError, TypeError):
duration = 0

end_timestamp = str(start_timestamp + timedelta(seconds=duration))
end_timestamp = end_timestamp.split(".")[0]
start_timestamp = str(start_timestamp).split(".")[0]

summary = result['result']['contents'][0]['fields']['summary']['valueString']
satisfied = result['result']['contents'][0]['fields']['satisfied']['valueString']
sentiment = result['result']['contents'][0]['fields']['sentiment']['valueString']
topic = result['result']['contents'][0]['fields']['topic']['valueString']
key_phrases = result['result']['contents'][0]['fields']['keyPhrases']['valueString']
complaint = result['result']['contents'][0]['fields']['complaint']['valueString']
content = result['result']['contents'][0]['fields']['content']['valueString']
# print(topic)
summary = get_field_value(fields, 'summary')
satisfied = get_field_value(fields, 'satisfied')
sentiment = get_field_value(fields, 'sentiment')
topic = get_field_value(fields, 'topic')
key_phrases = get_field_value(fields, 'keyPhrases')
complaint = get_field_value(fields, 'complaint')
content = get_field_value(fields, 'content')

cursor.execute(f"INSERT INTO processed_data (ConversationId, EndTime, StartTime, Content, summary, satisfied, sentiment, topic, key_phrases, complaint) VALUES (?,?,?,?,?,?,?,?,?,?)", (conversation_id, end_timestamp, start_timestamp, content, summary, satisfied, sentiment, topic, key_phrases, complaint))
conn.commit()

Expand Down
Loading