Enforce PDF type domain isolation in classification to prevent structural pages matching architectural categories
b9ca909 Download workflow/step2_classify.py from Basel0/qshub: direct link, hf CLI and curl.
- Browser
- Download file 3.89 kB
-
https://huggingface.co/spaces/Basel0/qshub/resolve/main/workflow/step2_classify.py
- Command line
-
hf download hf://spaces/Basel0/qshub/workflow/step2_classify.py
-
curl -L -o step2_classify.py https://huggingface.co/spaces/Basel0/qshub/resolve/main/workflow/step2_classify.py
3.89 kB
| """ | |
| STEP 2 — Classify Pages | |
| AI reads each page title/text and assigns drawing type | |
| User can correct any misclassification | |
| """ | |
| import pandas as pd | |
| import os, io, re, json | |
| from pdf_engine.smart_classifier import classify_all_pages, PAGE_ITEMS_MAP | |
| from pdf_engine.pdf_loader import page_to_pil | |
| from workflow.workflow_state import mark_step_done | |
| # Candidate types per PDF kind — used by the AI-vision refiner | |
| _STRUCT_TYPES = ["foundations", "tie_beam", "column_layout", "upper_columns", "neck_columns", | |
| "columns_1f", "columns_2f", "columns_roof", | |
| "slab_1st", "slab_2nd", "roof_slab"] | |
| _ARCH_TYPES = ["ground_floor_plan", "first_floor_plan", "second_floor_plan", | |
| "roof_floor_plan", "elevations", "setting_out", "schedules"] | |
| def _ai_classify(img_input, pdf_type: str): | |
| """Classify ONE page by vision when keyword matching is unsure. Returns a | |
| PAGE_ITEMS_MAP key or None.""" | |
| from utils.key_manager import get_key_manager | |
| mgr = get_key_manager() | |
| api_key, current_model = mgr.get_key_and_model() | |
| if not api_key or api_key == "NO_API_KEY_FOUND": | |
| return None | |
| choices = _STRUCT_TYPES if pdf_type == "structural" else _ARCH_TYPES | |
| try: | |
| from google import genai | |
| from google.genai import types | |
| import time | |
| import io as _io | |
| if isinstance(img_input, bytes): | |
| img = img_input | |
| elif isinstance(img_input, str) and os.path.exists(img_input): | |
| with open(img_input, "rb") as f: | |
| img = f.read() | |
| elif isinstance(img_input, np.ndarray): | |
| pil_img = page_to_pil(img_input) | |
| buf = _io.BytesIO() | |
| pil_img.save(buf, format="PNG") | |
| img = buf.getvalue() | |
| else: | |
| return None | |
| prompt = ( | |
| f"This is a construction drawing. Classify it as one of: {choices}. " | |
| "Reply ONLY with valid JSON: {\"type\": \"<chosen_type>\"}" | |
| ) | |
| for attempt in range(2): | |
| api_key, current_model = mgr.get_key_and_model() | |
| if not api_key or api_key == "NO_API_KEY_FOUND": | |
| return None | |
| try: | |
| client = genai.Client(api_key=api_key, http_options={'timeout': 10}) | |
| resp = client.models.generate_content( | |
| model=current_model, | |
| contents=[types.Part.from_bytes(data=img, mime_type="image/png"), prompt]) | |
| raw = re.sub(r"```json|```", "", resp.text).strip() | |
| result = json.loads(raw).get("type") | |
| return result if result in PAGE_ITEMS_MAP else None | |
| except Exception as e: | |
| last_err = str(e) | |
| if any(code in last_err for code in ("429", "RESOURCE_EXHAUSTED", "quota")): | |
| mgr.mark_rate_limited(api_key, current_model) | |
| continue | |
| time.sleep(1) | |
| return None | |
| except Exception: | |
| return None | |
| def _classify_single(text: str, pdf_type: str) -> dict: | |
| from pdf_engine.smart_classifier import PAGE_ITEMS_MAP | |
| text_lower = text.lower() | |
| scores = {} | |
| for ptype, config in PAGE_ITEMS_MAP.items(): | |
| # Enforce PDF domain isolation (structural vs architectural) | |
| if config.get("pdf_type") and config.get("pdf_type") != pdf_type: | |
| continue | |
| score = sum(1 for kw in config.get("drawing_keywords", []) if kw.lower() in text_lower) | |
| scores[ptype] = score | |
| if not scores: | |
| return {"detected_type": "unknown", "confidence": "low", "items": []} | |
| best = max(scores, key=scores.get) | |
| score = scores[best] | |
| return { | |
| "detected_type": best if score > 0 else "unknown", | |
| "confidence": "high" if score >= 1 else "low", | |
| "items": PAGE_ITEMS_MAP.get(best, {}).get("extract_items", []) if score > 0 else [], | |
| } | |