recipe_nlp/parser.py

"""recipe_nlp/parser.py — spaCy NER + dependency parsing."""
from __future__ import annotations
import re
from dataclasses import dataclass, field
from typing import List
from utils.config import config, NLPConfig
from utils.logger import logger

UNIT_VOCAB = {
    "cup","cups","tablespoon","tablespoons","tbsp","tbs","teaspoon","teaspoons","tsp",
    "fluid ounce","fl oz","liter","liters","litre","litres","l","milliliter","milliliters","ml",
    "pint","pints","quart","quarts","gallon","gallons",
    "gram","grams","g","kilogram","kilograms","kg","ounce","ounces","oz","pound","pounds","lb","lbs",
    "piece","pieces","slice","slices","clove","cloves","head","heads","bunch","bunches",
    "handful","handfuls","can","cans","jar","jars","package","packages","pinch","dash","sprinkle",
}

@dataclass
class ParsedToken:
    text: str; lemma: str; pos: str; dep: str
    is_food: bool = False; is_quantity: bool = False
    is_unit: bool = False; is_method: bool = False
    head_text: str = ""

@dataclass
class RawIngredientMention:
    food_token: str; quantity_str: str = ""; unit_str: str = ""
    method_str: str = ""; sentence: str = ""


class RecipeParser:
    def __init__(self, cfg: NLPConfig = None):
        self.cfg = cfg or config.nlp
        self._nlp = None

    def _load_nlp(self):
        if self._nlp is None:
            import spacy
            try:
                self._nlp = spacy.load(self.cfg.spacy_model)
            except OSError:
                logger.info("Downloading spaCy model en_core_web_sm …")
                from spacy.cli import download
                download(self.cfg.spacy_model)
                self._nlp = spacy.load(self.cfg.spacy_model)
        return self._nlp

    def _is_fraction(self, text: str) -> bool:
        return bool(re.match(r"^\d+/\d+$", text))

    def extract_raw_mentions(self, text: str) -> List[RawIngredientMention]:
        nlp = self._load_nlp()
        doc = nlp(text.lower())
        methods_lower = {m.lower() for m in self.cfg.cooking_methods}
        mentions = []
        for chunk in doc.noun_chunks:
            head = chunk.root
            if head.pos_ not in ("NOUN", "PROPN") or head.text in UNIT_VOCAB:
                continue
            sent_text = next((s.text for s in doc.sents if chunk.start >= s.start and chunk.end <= s.end), "")
            quantity_str = unit_str = method_str = ""
            for child in head.children:
                if child.dep_ in ("nummod", "quantmod") or child.like_num:
                    quantity_str = child.text
                elif child.text in UNIT_VOCAB or child.lemma_ in UNIT_VOCAB:
                    unit_str = child.text
            if not quantity_str:
                for token in chunk:
                    if token.like_num or self._is_fraction(token.text):
                        quantity_str = token.text; break
            for token in doc:
                if abs(token.i - head.i) <= 10 and (token.lemma_ in methods_lower or token.text in methods_lower):
                    method_str = token.text; break
            mentions.append(RawIngredientMention(head.text, quantity_str, unit_str, method_str, sent_text))
        return mentions