src/lib/csv-utils.ts

// csv-utils.ts — Shared CSV parsing utilities extracted from CSVViewer.
// Used by both CSVViewer and DesignIterationPanel.

export interface ParsedCsv {
  header: string[];
  rows: string[][];
}

/** Split text into logical lines, respecting double-quoted fields that may
 *  contain embedded newlines. Only breaks on \n (or \r\n) when outside quotes. */
function splitLines(text: string): string[] {
  const lines: string[] = [];
  let current = "";
  let inQuotes = false;
  for (let i = 0; i < text.length; i++) {
    const ch = text[i];
    if (ch === '"') {
      inQuotes = !inQuotes;
      current += ch;
    } else if (ch === "\r" && text[i + 1] === "\n" && !inQuotes) {
      lines.push(current);
      current = "";
      i++; // skip the \n
    } else if (ch === "\n" && !inQuotes) {
      lines.push(current);
      current = "";
    } else {
      current += ch;
    }
  }
  if (current.length > 0) lines.push(current);
  return lines;
}

function parseLine(line: string, delim: string): string[] {
  const out: string[] = [];
  let field = "";
  let inQuotes = false;
  for (let i = 0; i < line.length; i++) {
    const ch = line[i];
    if (inQuotes) {
      if (ch === '"') {
        if (line[i + 1] === '"') {
          field += '"';
          i++;
        } else {
          inQuotes = false;
        }
      } else {
        field += ch;
      }
    } else {
      if (ch === '"' && field === "") {
        inQuotes = true;
      } else if (ch === delim) {
        out.push(field);
        field = "";
      } else {
        field += ch;
      }
    }
  }
  out.push(field);
  return out;
}

export function parseCsv(input: string, delim: string): ParsedCsv {
  let text = input;
  if (text.charCodeAt(0) === 0xfeff) text = text.slice(1);

  const lines = splitLines(text);
  const parsed: string[][] = [];
  for (const line of lines) {
    if (line.length === 0) continue;
    parsed.push(parseLine(line, delim));
  }

  while (parsed.length > 0) {
    const last = parsed[parsed.length - 1];
    if (last.every((c) => c === "")) parsed.pop();
    else break;
  }

  if (parsed.length === 0) return { header: [], rows: [] };
  const [header, ...rows] = parsed;
  return { header, rows };
}

export function isNumericValue(v: string): boolean {
  if (v === "" || v == null) return false;
  const trimmed = v.trim();
  if (trimmed === "") return false;
  if (!/^-?\d*\.?\d+(?:[eE][-+]?\d+)?$/.test(trimmed)) return false;
  return Number.isFinite(Number(trimmed));
}

export function detectNumericColumns(header: string[], rows: string[][]): boolean[] {
  return header.map((_, col) => {
    let total = 0;
    let numeric = 0;
    for (const row of rows) {
      const v = row[col];
      if (v === undefined || v === "") continue;
      total++;
      if (isNumericValue(v)) numeric++;
    }
    if (total === 0) return false;
    return numeric / total >= 0.8;
  });
}

/** Column names that indicate a CSV is a design results file. */
const DESIGN_COLUMNS = new Set([
  "ipae",
  "interaction_pae",
  "plddt",
  "pred_lddt",
  "affinity",
  "affinity_pm",
  "consensus_score",
  "design_id",
  "tag",
  "sequence",
]);

/** Returns true if the CSV header contains at least 2 design-related columns. */
export function isDesignCsv(header: string[]): boolean {
  const lower = header.map((h) => h.toLowerCase().replace(/[^a-z0-9_]/g, "_"));
  let matches = 0;
  for (const col of lower) {
    if (DESIGN_COLUMNS.has(col)) matches++;
  }
  return matches >= 2;
}

export function detectDelimiter(name: string, url: string): string {
  const n = (name || url || "").toLowerCase();
  return n.endsWith(".tsv") || n.includes("tab-separated") ? "\t" : ",";
}