Spaces:
Sleeping
Sleeping
Update tools/data_governance_record.py
Browse files- tools/data_governance_record.py +12 -11
tools/data_governance_record.py
CHANGED
|
@@ -6,6 +6,8 @@ from fpdf import FPDF
|
|
| 6 |
from langdetect import detect
|
| 7 |
import gradio as gr
|
| 8 |
|
|
|
|
|
|
|
| 9 |
# === PDF Export Function ===
|
| 10 |
def export_text_to_pdf(text, metadata=None, output_path=None, language="en"):
|
| 11 |
if output_path is None:
|
|
@@ -23,7 +25,7 @@ def export_text_to_pdf(text, metadata=None, output_path=None, language="en"):
|
|
| 23 |
pdf.cell(0, 15, title, ln=True, align='C')
|
| 24 |
pdf.ln(10)
|
| 25 |
|
| 26 |
-
# Metadata
|
| 27 |
if metadata:
|
| 28 |
pdf.set_font("Arial", '', 12)
|
| 29 |
pdf.set_text_color(90, 90, 90)
|
|
@@ -63,11 +65,8 @@ def export_text_to_pdf(text, metadata=None, output_path=None, language="en"):
|
|
| 63 |
return output_path
|
| 64 |
|
| 65 |
|
| 66 |
-
# === Questions ===
|
| 67 |
-
|
| 68 |
-
("organization", "What is the name of your organization?"),
|
| 69 |
-
("completed_by", "What is your full name?"),
|
| 70 |
-
("role", "What is your role in the organization?"),
|
| 71 |
("dataset_description", "Please describe the dataset(s) used."),
|
| 72 |
("data_sources", "What are the sources of the data?"),
|
| 73 |
("data_collection_method", "How was the data collected?"),
|
|
@@ -80,6 +79,8 @@ QUESTIONS = [
|
|
| 80 |
("access_control", "Who has access to the data and under what conditions?")
|
| 81 |
]
|
| 82 |
|
|
|
|
|
|
|
| 83 |
def get_questions():
|
| 84 |
return QUESTIONS
|
| 85 |
|
|
@@ -100,14 +101,14 @@ def run_tool():
|
|
| 100 |
state["step"] += 1
|
| 101 |
return next_q, state, None
|
| 102 |
|
| 103 |
-
|
| 104 |
-
content = "\n".join([f"- **{label}**: {answers.get(key, '')}" for key, label in QUESTIONS[3:]])
|
| 105 |
detected_lang = detect(content)
|
| 106 |
|
|
|
|
| 107 |
metadata = {
|
| 108 |
-
"organization": answers.get("
|
| 109 |
-
"completed_by": answers.get("
|
| 110 |
-
"role": answers.get("
|
| 111 |
"timestamp": datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
| 112 |
}
|
| 113 |
|
|
|
|
| 6 |
from langdetect import detect
|
| 7 |
import gradio as gr
|
| 8 |
|
| 9 |
+
from tools.common import prepend_metadata_questions # ✅ Import helper
|
| 10 |
+
|
| 11 |
# === PDF Export Function ===
|
| 12 |
def export_text_to_pdf(text, metadata=None, output_path=None, language="en"):
|
| 13 |
if output_path is None:
|
|
|
|
| 25 |
pdf.cell(0, 15, title, ln=True, align='C')
|
| 26 |
pdf.ln(10)
|
| 27 |
|
| 28 |
+
# Metadata block
|
| 29 |
if metadata:
|
| 30 |
pdf.set_font("Arial", '', 12)
|
| 31 |
pdf.set_text_color(90, 90, 90)
|
|
|
|
| 65 |
return output_path
|
| 66 |
|
| 67 |
|
| 68 |
+
# === Core Questions ===
|
| 69 |
+
BASE_QUESTIONS = [
|
|
|
|
|
|
|
|
|
|
| 70 |
("dataset_description", "Please describe the dataset(s) used."),
|
| 71 |
("data_sources", "What are the sources of the data?"),
|
| 72 |
("data_collection_method", "How was the data collected?"),
|
|
|
|
| 79 |
("access_control", "Who has access to the data and under what conditions?")
|
| 80 |
]
|
| 81 |
|
| 82 |
+
QUESTIONS = prepend_metadata_questions(BASE_QUESTIONS) # ✅ Prepend metadata
|
| 83 |
+
|
| 84 |
def get_questions():
|
| 85 |
return QUESTIONS
|
| 86 |
|
|
|
|
| 101 |
state["step"] += 1
|
| 102 |
return next_q, state, None
|
| 103 |
|
| 104 |
+
content = "\n".join([f"- **{label}**: {answers.get(key, '')}" for key, label in QUESTIONS])
|
|
|
|
| 105 |
detected_lang = detect(content)
|
| 106 |
|
| 107 |
+
# ✅ Extract metadata from prepended fields
|
| 108 |
metadata = {
|
| 109 |
+
"organization": answers.get("organization_name", "N/A"),
|
| 110 |
+
"completed_by": answers.get("user_name", "N/A"),
|
| 111 |
+
"role": answers.get("user_role", "N/A"),
|
| 112 |
"timestamp": datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
| 113 |
}
|
| 114 |
|