File size: 11,892 Bytes
4851501 |
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 |
"""
Response Formatter Service
Handles formatting of query results into citations, charts, GeoJSON layers, and raw data for the frontend.
Separates presentation logic from execution logic.
"""
from typing import List, Dict, Any, Optional
import uuid
class ResponseFormatter:
@staticmethod
def generate_citations(tables: List[str], features: Optional[List[Dict]] = None) -> List[str]:
"""Generates readable citations based on table names and returned features."""
citations = []
processed = set()
# Check explicit table list
for table in tables:
table = table.lower()
if table in processed: continue
if "universit" in table:
citations.append("Universities Data (OpenStreetMap, 2024)")
elif "school" in table or "education" in table:
citations.append("Education Facilities (OpenStreetMap, 2024)")
elif "hospital" in table or "health" in table:
citations.append("Health Facilities (OpenStreetMap, 2024)")
elif "airport" in table:
citations.append("Airports Data (OpenStreetMap, 2024)")
elif "road" in table:
citations.append("Road Network (OpenStreetMap, 2024)")
elif "population" in table or "census" in table:
citations.append("Panama Census Data (INEC, 2023)")
elif "admin" in table or "boundar" in table:
if "Admin Boundaries" not in processed:
citations.append("Panama Administrative Boundaries (HDX COD-AB, 2021)")
processed.add("Admin Boundaries")
continue
processed.add(table)
# Fallback check on features if no specific tables cited but admin data returned
if not citations and features:
if any(k.startswith("adm") for k in features[0].get("properties", {}).keys()):
citations.append("Panama Administrative Boundaries (HDX COD-AB, 2021)")
return list(set(citations))
@staticmethod
def generate_chart_data(sql: str, features: List[Dict]) -> Optional[Dict[str, Any]]:
"""
Generates Chart.js compatible data structure if the query looks aggregative.
"""
if not features:
return None
# Heuristic: If GROUP BY or ORDER BY ... LIMIT is used, likely suitable for charting
# Or if explicitly requested via intent (logic handled in caller, but we check SQL signature here too)
# Try to find string (label) and number (value) in properties
try:
chart_items = []
x_key = "name"
y_key = "value"
x_label = "Feature"
y_label = "Value"
# 1. Analyze properties to find X (Label) and Y (Value)
if features:
sample_props = features[0].get("properties", {})
# Exclude system keys
valid_keys = [k for k in sample_props.keys() if k not in ["geom", "geometry", "style", "layer_name", "layer_id", "choropleth", "fillColor", "color"]]
# Find Y (Value) - First numeric column
for k in valid_keys:
if isinstance(sample_props[k], (int, float)) and not k.endswith("_id") and not k.endswith("_code"):
y_key = k
y_label = k.replace("_", " ").title()
if "sqkm" in k: y_label = "Area (km²)"
elif "pop" in k: y_label = "Population"
elif "count" in k: y_label = "Count"
break
# Find X (Label) - First string column (excluding IDs if possible)
for k in valid_keys:
if isinstance(sample_props[k], str) and "name" in k:
x_key = k
x_label = k.replace("_", " ").title().replace("Name", "").strip() or "Region"
break
# 2. Build Data
for f in features:
props = f.get("properties", {})
label = props.get(x_key)
value = props.get(y_key)
if label is not None and value is not None:
chart_items.append({"name": str(label), "value": value})
if chart_items:
# auto-sort descending
chart_items.sort(key=lambda x: x["value"], reverse=True)
return {
"type": "bar",
"title": f"{y_label} by {x_label}",
"data": chart_items[:15], # Limit to top 15 for readability
"xKey": "name",
"yKey": "value",
"xAxisLabel": x_label,
"yAxisLabel": y_label
}
except Exception as e:
print(f"Error generating chart data: {e}")
return None
return None
@staticmethod
def prepare_raw_data(features: List[Dict]) -> List[Dict]:
"""Cleans feature properties for display in the raw data table."""
raw_data = []
if not features:
return raw_data
for f in features:
props = f.get("properties", {}).copy()
# Serialize
props = ResponseFormatter._serialize_properties(props)
# Remove system/visual properties
for key in ["geom", "geometry", "style", "layer_name", "layer_id", "choropleth", "fillColor", "color"]:
props.pop(key, None)
raw_data.append(props)
return raw_data
@staticmethod
def format_geojson_layer(query: str, geojson: Dict[str, Any], features: List[Dict], layer_name: str, layer_emoji: str = "📍", point_style: Optional[str] = None, admin_levels: Optional[List[str]] = None) -> tuple[Dict[str, Any], str, str]:
"""
styles the GeoJSON layer and generates metadata (ID, Name, Choropleth).
Args:
point_style: "icon" for emoji markers, "circle" for simple colored circles, None for auto-detect
"""
# 0. Serialize properties to avoid datetime errors
if features:
for f in features:
if "properties" in f:
f["properties"] = ResponseFormatter._serialize_properties(f["properties"])
# 2. Random/Distinct Colors
# Palette of distinct colors (avoiding pure blue which is default)
palette = [
"#E63946", # Red
"#F4A261", # Orange
"#2A9D8F", # Teal
"#E9C46A", # Yellow
"#9C6644", # Brown
"#D62828", # Dark Red
"#8338EC", # Purple
"#3A86FF", # Blue-ish (but distinct)
"#FB5607", # Orange-Red
"#FF006E", # Pink
]
# Deterministic color based on query hash to keep it stable for same query
color_idx = abs(hash(query)) % len(palette)
layer_color = palette[color_idx]
# Choropleth Logic
# 1. Identify valid numeric column
choropleth_col = None
if features:
sample = features[0].get("properties", {})
valid_numerics = [
k for k, v in sample.items()
if isinstance(v, (int, float))
and k not in ["layer_id", "style"]
and not k.endswith("_code")
and not k.endswith("_id")
]
# Prioritize 'population', 'area', 'count'
priority_cols = ["population", "pop", "count", "num", "density", "area_sqkm", "area"]
for p in priority_cols:
matches = [c for c in valid_numerics if p in c]
if matches:
choropleth_col = matches[0]
break
# Fallback to first numeric
if not choropleth_col and valid_numerics:
choropleth_col = valid_numerics[0]
# 2. Enable if appropriate
if choropleth_col:
# Check if values actually vary
values = [f["properties"].get(choropleth_col, 0) for f in features]
if len(set(values)) > 1:
geojson["properties"]["choropleth"] = {
"enabled": True,
"palette": "viridis",
"column": choropleth_col,
"scale": "log" if "pop" in choropleth_col or "density" in choropleth_col else "linear"
}
else:
# Apply random color if NOT a choropleth
geojson["properties"]["style"] = {
"color": layer_color,
"fillColor": layer_color,
"opacity": 0.8,
"fillOpacity": 0.4
}
layer_id = str(uuid.uuid4())[:8]
geojson["properties"]["layer_name"] = layer_name
geojson["properties"]["layer_id"] = layer_id
# Add Point Marker Configuration
# Use pointStyle to determine whether to show icon or circle
marker_icon = None
marker_style = "circle" # default
if point_style == "icon":
# Use emoji icon for categorical POI
marker_icon = layer_emoji
marker_style = "icon"
elif point_style == "circle":
# Use simple circle for large datasets or density viz
marker_icon = None
marker_style = "circle"
else:
# Auto-detect: default to icon for now (backward compatibility)
marker_icon = layer_emoji
marker_style = "icon"
geojson["properties"]["pointMarker"] = {
"icon": marker_icon,
"style": marker_style,
"color": layer_color,
"size": 32
}
return geojson, layer_id, layer_name
@staticmethod
def generate_data_summary(features: List[Dict]) -> str:
"""Generates a text summary of the features for the LLM explanation context."""
if features:
sample_names = []
for f in features[:5]:
props = f.get("properties", {})
name = props.get("adm3_name") or props.get("adm2_name") or props.get("adm1_name") or props.get("name") or "Feature"
area = props.get("area_sqkm")
if area:
sample_names.append(f"{name} ({float(area):.1f} km²)")
else:
sample_names.append(name)
return f"Found {len(features)} features. Sample: {', '.join(sample_names)}"
return f"Found {len(features)} features. Sample: {', '.join(sample_names)}"
else:
return "No features found matching the query."
@staticmethod
def _serialize_properties(properties: Dict[str, Any]) -> Dict[str, Any]:
"""Recursively converts datetime/date objects to strings for JSON serialization."""
from datetime import datetime, date
serialized = {}
for k, v in properties.items():
if isinstance(v, (datetime, date)):
serialized[k] = v.isoformat()
elif isinstance(v, dict):
serialized[k] = ResponseFormatter._serialize_properties(v)
elif isinstance(v, list):
serialized[k] = [
x.isoformat() if isinstance(x, (datetime, date)) else x
for x in v
]
else:
serialized[k] = v
return serialized
|