"""
End-to-end example:
1) Parse a local DrugBank XML file
2) Extract a minimal drug table
3) Extract drug-drug interactions
4) Build a DDI graph

Prerequisites:
- You must obtain DrugBank XML via your DrugBank account/license.
- Place the XML file at ./drugbank.xml (or update the path).
"""

from lxml import etree
import pandas as pd
import networkx as nx

DRUGBANK_XML_PATH = "./drugbank.xml"
NS = {"db": "http://www.drugbank.ca"}  # DrugBank XML namespace

# --- Parse XML ---
tree = etree.parse(DRUGBANK_XML_PATH)
root = tree.getroot()

# --- Extract drug records (minimal fields) ---
drugs = []
for drug in root.xpath("//db:drug", namespaces=NS):
    drugbank_id = drug.xpath("string(db:drugbank-id[@primary='true'])", namespaces=NS).strip()
    name = drug.xpath("string(db:name)", namespaces=NS).strip()
    drug_type = drug.get("type", "").strip()

    # Optional: first SMILES if present
    smiles = drug.xpath(
        "string(db:calculated-properties/db:property[db:kind='SMILES']/db:value)",
        namespaces=NS,
    ).strip()

    drugs.append(
        {
            "drugbank_id": drugbank_id,
            "name": name,
            "type": drug_type,
            "smiles": smiles or None,
        }
    )

drugs_df = pd.DataFrame(drugs).dropna(subset=["drugbank_id"])
print("Drugs:", len(drugs_df))
print(drugs_df.head())

# --- Extract drug-drug interactions ---
interactions = []
for drug in root.xpath("//db:drug", namespaces=NS):
    src_id = drug.xpath("string(db:drugbank-id[@primary='true'])", namespaces=NS).strip()
    src_name = drug.xpath("string(db:name)", namespaces=NS).strip()

    for ddi in drug.xpath("db:drug-interactions/db:drug-interaction", namespaces=NS):
        tgt_id = ddi.xpath("string(db:drugbank-id)", namespaces=NS).strip()
        tgt_name = ddi.xpath("string(db:name)", namespaces=NS).strip()
        description = ddi.xpath("string(db:description)", namespaces=NS).strip()

        if src_id and tgt_id:
            interactions.append(
                {
                    "source_id": src_id,
                    "source_name": src_name,
                    "target_id": tgt_id,
                    "target_name": tgt_name,
                    "description": description or None,
                }
            )

ddi_df = pd.DataFrame(interactions)
print("Interactions:", len(ddi_df))
print(ddi_df.head())

# --- Build a DDI graph ---
G = nx.from_pandas_edgelist(
    ddi_df,
    source="source_id",
    target="target_id",
    edge_attr=["description"],
    create_using=nx.Graph(),
)

print("DDI graph nodes:", G.number_of_nodes())
print("DDI graph edges:", G.number_of_edges())

# Example analysis: top 10 drugs by interaction degree
top_degree = sorted(G.degree, key=lambda x: x[1], reverse=True)[:10]
top_degree_df = pd.DataFrame(top_degree, columns=["drugbank_id", "degree"]).merge(
    drugs_df[["drugbank_id", "name"]],
    on="drugbank_id",
    how="left",
)
print(top_degree_df)