frontend/src/utils/xrd-processing.js

/**
 * Pure utility functions extracted from XRDContext for testability.
 * These functions contain no React state or side effects.
 */

/**
 * Convert wavelength using Bragg's law: lambda = 2d*sin(theta)
 * For same d-spacing: sin(theta2) = (lambda2/lambda1) * sin(theta1)
 *
 * @param {number} theta_deg - 2theta angle in degrees
 * @param {number} sourceWavelength - Source wavelength in Angstroms
 * @param {number} targetWavelength - Target wavelength in Angstroms
 * @returns {number|null} Converted 2theta angle, or null if physically impossible
 */
export function convertWavelength(theta_deg, sourceWavelength, targetWavelength) {
  if (Math.abs(sourceWavelength - targetWavelength) < 0.0001) {
    return theta_deg
  }

  const theta_rad = (theta_deg * Math.PI) / 180
  const sin_theta2 = (targetWavelength / sourceWavelength) * Math.sin(theta_rad)

  if (Math.abs(sin_theta2) > 1) {
    return null
  }

  const theta2_rad = Math.asin(sin_theta2)
  return (theta2_rad * 180) / Math.PI
}

/**
 * Interpolate data to fixed size for model input.
 *
 * @param {number[]} x - Input x values (2theta)
 * @param {number[]} y - Input y values (intensity)
 * @param {number} targetSize - Desired output length
 * @param {number} [xMin] - Minimum x value for output grid
 * @param {number} [xMax] - Maximum x value for output grid
 * @param {string} [strategy='linear'] - Interpolation strategy: 'linear' or 'cubic'
 * @returns {{x: number[], y: number[]}} Interpolated data
 */
export function interpolateData(x, y, targetSize, xMin, xMax, strategy = 'linear') {
  if (x.length === targetSize && xMin === undefined) {
    return { x, y }
  }

  const minX = xMin !== undefined ? xMin : Math.min(...x)
  const maxX = xMax !== undefined ? xMax : Math.max(...x)
  const step = (maxX - minX) / (targetSize - 1)

  const newX = Array.from({ length: targetSize }, (_, i) => minX + i * step)
  const newY = new Array(targetSize)

  const dataMinX = Math.min(...x)
  const dataMaxX = Math.max(...x)

  if (strategy === 'linear') {
    for (let i = 0; i < targetSize; i++) {
      const targetX = newX[i]

      if (targetX < dataMinX || targetX > dataMaxX) {
        newY[i] = 0
        continue
      }

      let idx = x.findIndex(val => val >= targetX)
      if (idx === -1) idx = x.length - 1
      if (idx === 0) idx = 1

      const x0 = x[idx - 1]
      const x1 = x[idx]
      const y0 = y[idx - 1]
      const y1 = y[idx]

      newY[i] = y0 + ((targetX - x0) * (y1 - y0)) / (x1 - x0)
    }
  } else if (strategy === 'cubic') {
    for (let i = 0; i < targetSize; i++) {
      const targetX = newX[i]

      if (targetX < dataMinX || targetX > dataMaxX) {
        newY[i] = 0
        continue
      }

      let idx = x.findIndex(val => val >= targetX)
      if (idx === -1) idx = x.length - 1
      if (idx === 0) idx = 1

      const i0 = Math.max(0, idx - 2)
      const i1 = Math.max(0, idx - 1)
      const i2 = Math.min(x.length - 1, idx)
      const i3 = Math.min(x.length - 1, idx + 1)

      if (i2 === i1) {
        newY[i] = y[i1]
      } else {
        const t = (targetX - x[i1]) / (x[i2] - x[i1])
        const t2 = t * t
        const t3 = t2 * t

        const v0 = y[i0]
        const v1 = y[i1]
        const v2 = y[i2]
        const v3 = y[i3]

        newY[i] = 0.5 * (
          2 * v1 +
          (-v0 + v2) * t +
          (2 * v0 - 5 * v1 + 4 * v2 - v3) * t2 +
          (-v0 + 3 * v1 - 3 * v2 + v3) * t3
        )
      }
    }
  }

  return { x: newX, y: newY }
}

/**
 * Parse DIF or XY format (space-separated 2theta intensity).
 *
 * @param {string} text - Raw file content
 * @returns {{x: number[], y: number[]}} Parsed data points
 */
export function parseDIF(text) {
  const lines = text.split('\n')
  const x = []
  const y = []

  for (const line of lines) {
    const trimmed = line.trim()

    if (!trimmed ||
        trimmed.startsWith('#') ||
        trimmed.startsWith('_') ||
        trimmed.startsWith('CELL') ||
        trimmed.startsWith('SPACE') ||
        /^[a-zA-Z]/.test(trimmed)) {
      continue
    }

    const parts = trimmed.split(/\s+/)
    if (parts.length >= 2) {
      const xVal = parseFloat(parts[0])
      const yVal = parseFloat(parts[1])

      if (!isNaN(xVal) && !isNaN(yVal)) {
        x.push(xVal)
        y.push(yVal)
      }
    }
  }

  return { x, y }
}

/**
 * Extract metadata from CIF/DIF file text.
 *
 * @param {string} text - Raw file content
 * @returns {{wavelength: number|null, cellParams: string|null, spaceGroup: string|null, crystalSystem: string|null}}
 */
export function extractMetadata(text) {
  const metadata = {
    wavelength: null,
    cellParams: null,
    spaceGroup: null,
    crystalSystem: null
  }

  const lines = text.split('\n')

  const wavelengthPatterns = [
    /wavelength[:\s=]+([0-9.]+)/i,
    /lambda[:\s=]+([0-9.]+)/i,
    /wave[:\s=]+([0-9.]+)/i,
    /_pd_wavelength[:\s]+([0-9.]+)/i,
    /_diffrn_radiation_wavelength[:\s]+([0-9.]+)/i,
    /radiation.*?([0-9.]+)\s*[AÅ]/i,
  ]

  for (const line of lines) {
    if (!metadata.wavelength) {
      for (const pattern of wavelengthPatterns) {
        const match = line.match(pattern)
        if (match && match[1]) {
          const wavelength = parseFloat(match[1])
          if (wavelength > 0.1 && wavelength < 3.0) {
            metadata.wavelength = wavelength
            break
          }
        }
      }

      if (/Cu\s*K[αa]/i.test(line)) metadata.wavelength = 1.5406
      else if (/Mo\s*K[αa]/i.test(line)) metadata.wavelength = 0.7107
      else if (/Co\s*K[αa]/i.test(line)) metadata.wavelength = 1.7889
      else if (/Cr\s*K[αa]/i.test(line)) metadata.wavelength = 2.2897
    }

    if (/CELL PARAMETERS:/i.test(line)) {
      const match = line.match(/CELL PARAMETERS:\s*([\d.\s]+)/)
      if (match) {
        metadata.cellParams = match[1].trim()
      }
    }

    if (/SPACE GROUP:/i.test(line) || /_symmetry_Int_Tables_number/i.test(line)) {
      const match = line.match(/(?:SPACE GROUP:|_symmetry_Int_Tables_number)[:\s]+(\d+)/)
      if (match) {
        metadata.spaceGroup = match[1]
      }
    }

    if (/Crystal System:/i.test(line)) {
      const match = line.match(/Crystal System:\s*(\d+)/)
      if (match) {
        metadata.crystalSystem = match[1]
      }
    }
  }

  return metadata
}