use std::collections::HashSet;
use serde_json::Value;

#[derive(Debug, Clone, PartialEq)]
pub enum FieldKind {
    /// Small number of distinct string values → dimension/category
    Category,
    /// Numeric values → measure
    Measure,
    /// Date/time strings → time category
    TimeCategory,
    /// Many unique strings (IDs, names) → label/identifier
    Label,
}

#[derive(Debug, Clone)]
pub struct FieldProposal {
    pub field: String,
    pub kind: FieldKind,
    pub distinct_values: Vec<String>,
    pub accepted: bool,
}

impl FieldProposal {
    pub fn kind_label(&self) -> &'static str {
        match self.kind {
            FieldKind::Category => "Category (dimension)",
            FieldKind::Measure => "Measure (numeric)",
            FieldKind::TimeCategory => "Time Category",
            FieldKind::Label => "Label/Identifier (skip)",
        }
    }
}

const CATEGORY_THRESHOLD: usize = 20;
const LABEL_THRESHOLD: usize = 50;

pub fn analyze_records(records: &[Value]) -> Vec<FieldProposal> {
    if records.is_empty() {
        return vec![];
    }

    // Collect all field names
    let mut fields: Vec<String> = Vec::new();
    for record in records {
        if let Value::Object(map) = record {
            for key in map.keys() {
                if !fields.contains(key) {
                    fields.push(key.clone());
                }
            }
        }
    }

    fields.into_iter().map(|field| {
        let values: Vec<&Value> = records.iter()
            .filter_map(|r| r.get(&field))
            .collect();

        let all_numeric = values.iter().all(|v| v.is_number());
        let all_string = values.iter().all(|v| v.is_string());

        if all_numeric {
            return FieldProposal {
                field,
                kind: FieldKind::Measure,
                distinct_values: vec![],
                accepted: true,
            };
        }

        if all_string {
            let distinct: HashSet<&str> = values.iter()
                .filter_map(|v| v.as_str())
                .collect();
            let distinct_vec: Vec<String> = distinct.into_iter().map(String::from).collect();
            let n = distinct_vec.len();
            let _total = values.len();

            // Check if looks like date
            let looks_like_date = distinct_vec.iter().any(|s| {
                s.contains('-') && s.len() >= 8
                    || s.starts_with("Q") && s.len() == 2
                    || ["Jan","Feb","Mar","Apr","May","Jun","Jul","Aug","Sep","Oct","Nov","Dec"]
                        .iter().any(|m| s.starts_with(m))
            });

            if looks_like_date {
                return FieldProposal {
                    field,
                    kind: FieldKind::TimeCategory,
                    distinct_values: distinct_vec,
                    accepted: true,
                };
            }

            if n <= CATEGORY_THRESHOLD {
                return FieldProposal {
                    field,
                    kind: FieldKind::Category,
                    distinct_values: distinct_vec,
                    accepted: true,
                };
            }

            return FieldProposal {
                field,
                kind: FieldKind::Label,
                distinct_values: distinct_vec,
                accepted: false,
            };
        }

        // Mixed or other: treat as label
        FieldProposal {
            field,
            kind: FieldKind::Label,
            distinct_values: vec![],
            accepted: false,
        }
    }).collect()
}

/// Extract nested array from JSON by dot-path
pub fn extract_array_at_path<'a>(value: &'a Value, path: &str) -> Option<&'a Vec<Value>> {
    if path.is_empty() {
        return value.as_array();
    }
    let mut current = value;
    for part in path.split('.') {
        current = current.get(part)?;
    }
    current.as_array()
}

/// Find candidate paths to arrays in JSON
pub fn find_array_paths(value: &Value) -> Vec<String> {
    let mut paths = Vec::new();
    find_array_paths_inner(value, "", &mut paths);
    paths
}

fn find_array_paths_inner(value: &Value, prefix: &str, paths: &mut Vec<String>) {
    match value {
        Value::Array(_) => {
            paths.push(prefix.to_string());
        }
        Value::Object(map) => {
            for (key, val) in map {
                let path = if prefix.is_empty() {
                    key.clone()
                } else {
                    format!("{prefix}.{key}")
                };
                find_array_paths_inner(val, &path, paths);
            }
        }
        _ => {}
    }
}