File size: 1,919 Bytes
c2b7a7b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""Blueprint identifying faculty whose research mentions a given topic."""

from __future__ import annotations

import re
from typing import Any, Dict, List

from .base import AnalysisContext, Blueprint, BlueprintResult, Fact


class FacultyByTopicBlueprint(Blueprint):
    """Return faculty whose research interests mention a topic."""

    name = "faculty_by_topic"

    def run(self, context: AnalysisContext, **kwargs: Any) -> BlueprintResult:
        topic = (kwargs.get("topic") or "").strip()
        if not topic:
            return BlueprintResult(self.name, kwargs, facts=[], notes=["No topic provided."])

        topic_lower = re.sub(r"[?.!]+$", "", topic.lower())
        tokens = [tok for tok in re.split(r"[^a-z0-9]+", topic_lower) if tok]
        if not tokens:
            return BlueprintResult(self.name, kwargs, facts=[], notes=[f"Topic '{topic}' is too vague."])

        search_terms = set()
        search_terms.add(" ".join(tokens))
        search_terms.update(tokens)
        if "ai" in tokens:
            search_terms.add("artificial intelligence")
        if "ml" in tokens:
            search_terms.add("machine learning")

        dataset = context.catalog.get("faculty")
        matches: List[Fact] = []
        for row in dataset.records:
            research = (row.get("Research Interests") or "").lower()
            if any(term in research for term in search_terms):
                matches.append(
                    Fact(
                        subject=row.get("Name", "Unknown"),
                        predicate="research_focus",
                        value=row.get("Research Interests"),
                        source=dataset.origin,
                    )
                )

        notes: List[str] = []
        if not matches:
            notes.append(f"No faculty rows mention '{topic}'.")

        return BlueprintResult(self.name, kwargs, facts=matches, notes=notes)