WIP Phase 4 ingestion: platform guides, exclusion gate, gitea/vault/graph harvest, payload provenance

corpus/areas.py

@@ -0,0 +1,94 @@
+"""Which resume area a harvested document feeds.
+
+The payload `area` is what lets the query path filter *before* it searches, so a
+harvested file has to be classified once, deterministically, and never promoted
+to make a page read better.
+
+The classification is keyword evidence, in this order: the path, the repository
+name, the description and topics, then the languages. The result is constrained
+to the platform guide's `fits` list: a platform cannot feed an area it does not
+declare. When nothing matches, the first `fits` entry wins, which is why every
+guide lists its strongest area first.
+
+This is a heuristic and it is labelled as one. It is not a claim about Sam's
+career; the curated `content/` tree carries the claims.
+"""
+
+from __future__ import annotations
+
+import re
+
+from .payloads import AREAS
+
+# Order matters: the first area with a hit wins, so the more specific evidence
+# (an ESP32 repository is edge, not platform) is checked before the general.
+_RULES = (
+    ("edge", (
+        "esp32", "esp8266", "arduino", "lora", "lorawan", "mqtt", "sensor",
+        "zigbee", "z-wave", "relay", "gpio", "pir", "modbus", "iot",
+        "firmware", "breadboard", "raspberry pi", "rpi", "camera", "cam",
+        "temperature", "watering", "fish feeder", "driveway", "light",
+        "snapcast", "mopidy", "audio", "voice bridge",
+    )),
+    ("ai", (
+        "ai", "llm", "agent", "agentic", "rag", "embedding", "vector",
+        "model", "ml", "prompt", "graphify", "omniroute", "paperclip",
+        "langgraph", "prefect", "whisper", "piper", "chat", "memory",
+        "knowledge graph", "vision", "triage",
+    )),
+    ("platform", (
+        "nixos", "nix", "docker", "compose", "kubernetes", "k8s", "deploy",
+        "deployment", "backup", "borg", "kopia", "restic", "network", "dns",
+        "email", "caddy", "proxmox", "postgres", "terraform", "ansible",
+        "linux", "systemd", "homelab", "server", "infrastructure", "git",
+        "gitea", "monitor", "logging", "security", "firewall", "vpn",
+        "tailscale", "storage", "garage", "s3",
+    )),
+    ("products", (
+        "product", "app", "web", "dashboard", "react", "laravel", "flutter",
+        "kotlin", "calendar", "photo", "kontra", "store", "resume", "site",
+        "gps", "tracker", "api", "frontend", "ui", "ux",
+    )),
+    ("history", (
+        "history", "agency", "client", "archive", "old", "legacy", "2019",
+        "2018", "2020", "2021", "career", "resume copy",
+    )),
+    ("about", ("about", "profile", "bio", "personal", "cv")),
+)
+
+_WORD_SPLIT = re.compile(r"[^0-9a-z]+")
+
+
+def area_for(evidence: str, fits, fallback: str = None) -> str:
+    """Classify one document from its path, name, description and topics."""
+    haystack = " " + _WORD_SPLIT.sub(" ", (evidence or "").lower()) + " "
+    allowed = [area for area in (fits or AREAS) if area in AREAS]
+    if not allowed:
+        allowed = list(AREAS)
+    for area, needles in _RULES:
+        if area not in allowed:
+            continue
+        for needle in needles:
+            if f" {needle} " in haystack or f" {needle}s " in haystack:
+                return area
+    if fallback in allowed:
+        return fallback
+    return allowed[0]
+
+
+def area_for_repo(repo: dict, fits) -> str:
+    topics = " ".join(repo.get("topics") or [])
+    evidence = " ".join(
+        str(part)
+        for part in (
+            repo.get("full_name", ""),
+            repo.get("name", ""),
+            repo.get("description", ""),
+            topics,
+        )
+    )
+    return area_for(evidence, fits, fallback=(fits or [None])[0])
+
+
+def area_for_note(path: str, fits) -> str:
+    return area_for(path, fits, fallback=(fits or [None])[0])