parse-court-docket.js

const fs = require('fs');
const content = fs.readFileSync('court-docket.txt', 'utf8').split(/\s*\n\s*/);
const data = {};

data.origin = readOrigin();
data.type = readType();
data.docketNumber = readDocketNumber();
data.subtype = readSubtype();
data.case = readCase();
console.log(data);

function readOrigin() {
  const origin = readLine().trim();
  if (!origin.match(/COURT/i)) {
    throw 'First line is not a court of origin';
  }
  return origin;
}

function readType() {
  const type = readLine().trim();
  if (!type.match(/DOCKET/i)) {
    throw 'type line is not DOCKET';
  }
  return type;
}

function readDocketNumber() {
  const line = readLine().trim();
  const matches = line.match(/Docket Number: ([\w\-]+)/i);
  if (!matches) {
    throw 'docket number line not found';
  }
  return matches[1];
}

function readSubtype() {
  const line = readLine().trim();
  if (!line.match(/docket/i)) {
    throw 'subtype line does not contain DOCKET';
  }
  return line;
}

function readCase() {
  const header = readLine();
  if (!header.match(/court case/i)) {
    throw 'Court Case does not appear before case name';
  }
  let caseName = '';
  let vSeen = false;
  while (true) {
    const line = readLine().trim();
    caseName += line + ' ';
    if (vSeen) {
      break;
    }
    if (line === 'v.') {
      vSeen = true;
    }
  }
  return caseName.trim();
}

function readLine() {
  const line = content.shift();
  if (line.match(/Page \d+ of \d+/)) {
    return readLine();
  }
  return line;
}