CSV から XML への変換

// No dependencies. The parser is RFC 4180: one loop and one flag.
function parseCsv(text, delimiter = ',') {
  const src = text.replace(/\r\n?/g, '\n').replace(/\n$/, '');
  const rows = [];
  let row = [], field = '', quoted = false;

  for (let i = 0; i < src.length; i++) {
    const c = src[i];
    if (quoted) {
      if (c === '"' && src[i + 1] === '"') { field += '"'; i++; }
      else if (c === '"') quoted = false;
      else field += c;
      continue;
    }
    if (c === '"' && field === '') quoted = true;
    else if (c === delimiter) { row.push(field); field = ''; }
    else if (c === '\n') { row.push(field); rows.push(row); row = []; field = ''; }
    else field += c;
  }
  if (field !== '' || row.length) { row.push(field); rows.push(row); }
  return rows;
}

// XML 1.0 names: start with a letter, underscore or colon; the 'xml'
// prefix is reserved in any case combination.
function xmlName(heading, index) {
  const base = heading.trim() || 'column' + (index + 1);
  if (/^[A-Za-z_][\w.\-]*$/.test(base)) return base;
  let name = base.replace(/[^\w.\-]/g, '_');
  if (!/^[A-Za-z_]/.test(name)) name = '_' + name;
  if (/^xml/i.test(name)) name = '_' + name;
  return name;
}

const esc = (s) => s.replace(/&/g, '&amp;').replace(/</g, '&lt;').replace(/>/g, '&gt;');

function csvToXml(text, { root = 'rows', row = 'row', delimiter = ',' } = {}) {
  const rows = parseCsv(text, delimiter);
  const headers = rows[0].map(xmlName);
  const out = ['<?xml version="1.0" encoding="UTF-8"?>', '<' + root + '>'];

  for (const r of rows.slice(1)) {
    if (r.length === 1 && r[0] === '') continue;          // blank line
    if (r.length !== headers.length) {
      console.warn('row has ' + r.length + ' fields, header has ' + headers.length);
    }
    out.push('  <' + row + '>');
    headers.forEach((h, i) => out.push('    <' + h + '>' + esc(r[i] ?? '') + '</' + h + '>'));
    out.push('  </' + row + '>');
  }
  out.push('</' + root + '>');
  return out.join('\n');
}

# Standard library only. csv handles RFC 4180 and ElementTree escapes
# the output, so neither quoting nor & and < are your problem.
import csv
import re
import sys
import xml.etree.ElementTree as ET

NAME_OK = re.compile(r"^[A-Za-z_][\w.\-]*$")


def xml_name(heading, index):
    base = heading.strip() or f"column{index + 1}"
    if NAME_OK.match(base):
        return base
    name = re.sub(r"[^\w.\-]", "_", base)
    if not re.match(r"^[A-Za-z_]", name):
        name = "_" + name
    if name[:3].lower() == "xml":          # reserved by XML 1.0 section 2.3
        name = "_" + name
    return name


def csv_to_xml(path, root_name="rows", row_name="row", delimiter=","):
    # newline="" lets csv handle line breaks inside quoted fields itself.
    with open(path, newline="", encoding="utf-8-sig") as f:
        rows = list(csv.reader(f, delimiter=delimiter))

    headers = [xml_name(h, i) for i, h in enumerate(rows[0])]
    root = ET.Element(root_name)

    for r in rows[1:]:
        if not any(field.strip() for field in r):
            continue
        if len(r) != len(headers):
            print(f"row has {len(r)} fields, header has {len(headers)}", file=sys.stderr)
        row = ET.SubElement(root, row_name)
        for i, name in enumerate(headers):
            ET.SubElement(row, name).text = r[i] if i < len(r) else ""

    tree = ET.ElementTree(root)
    ET.indent(tree, space="  ")            # Python 3.9+
    tree.write(sys.stdout.buffer, encoding="UTF-8", xml_declaration=True)


csv_to_xml(sys.argv[1])

// Apache Commons CSV for RFC 4180 parsing, StAX for escaped output.
//   <dependency>org.apache.commons:commons-csv:1.11.0</dependency>
import java.io.*;
import java.nio.charset.StandardCharsets;
import java.nio.file.*;
import java.util.*;
import javax.xml.stream.*;
import org.apache.commons.csv.*;

public class CsvToXml {

    static String xmlName(String heading, int index) {
        String base = heading == null ? "" : heading.trim();
        if (base.isEmpty()) return "column" + (index + 1);
        if (base.matches("[A-Za-z_][\\w.\\-]*")) return base;
        String name = base.replaceAll("[^\\w.\\-]", "_");
        if (!name.matches("^[A-Za-z_].*")) name = "_" + name;
        if (name.regionMatches(true, 0, "xml", 0, 3)) name = "_" + name;
        return name;
    }

    public static void main(String[] args) throws Exception {
        CSVFormat format = CSVFormat.RFC4180.builder()
                .setHeader().setSkipHeaderRecord(true).build();

        try (Reader in = Files.newBufferedReader(Path.of(args[0]), StandardCharsets.UTF_8);
             CSVParser parser = CSVParser.parse(in, format)) {

            List<String> raw = parser.getHeaderNames();
            List<String> names = new ArrayList<>();
            for (int i = 0; i < raw.size(); i++) names.add(xmlName(raw.get(i), i));

            XMLStreamWriter out = XMLOutputFactory.newInstance()
                    .createXMLStreamWriter(new OutputStreamWriter(
                            new FileOutputStream("out.xml"), StandardCharsets.UTF_8));

            out.writeStartDocument("UTF-8", "1.0");
            out.writeStartElement("rows");
            for (CSVRecord record : parser) {
                if (record.size() != names.size()) {
                    System.err.printf("row %d has %d fields, header has %d%n",
                            record.getRecordNumber(), record.size(), names.size());
                }
                out.writeStartElement("row");
                for (int i = 0; i < names.size(); i++) {
                    out.writeStartElement(names.get(i));
                    // writeCharacters escapes &, < and >. Never concatenate.
                    out.writeCharacters(i < record.size() ? record.get(i) : "");
                    out.writeEndElement();
                }
                out.writeEndElement();
            }
            out.writeEndElement();
            out.writeEndDocument();
            out.close();
        }
    }
}

// dotnet add package CsvHelper
using System.Globalization;
using System.Text;
using System.Text.RegularExpressions;
using System.Xml;
using CsvHelper;
using CsvHelper.Configuration;

static string XmlName(string heading, int index)
{
    var b = (heading ?? "").Trim();
    if (b.Length == 0) return "column" + (index + 1);
    if (Regex.IsMatch(b, @"^[A-Za-z_][\w.\-]*$")) return b;
    var name = Regex.Replace(b, @"[^\w.\-]", "_");
    if (!Regex.IsMatch(name, @"^[A-Za-z_]")) name = "_" + name;
    if (name.StartsWith("xml", StringComparison.OrdinalIgnoreCase)) name = "_" + name;
    return name;
}

var config = new CsvConfiguration(CultureInfo.InvariantCulture)
{
    Delimiter = ",",
    HasHeaderRecord = true,
    BadDataFound = ctx => Console.Error.WriteLine($"bad quoting on row {ctx.RawRecord}"),
};

using var reader = new StreamReader(args[0], Encoding.UTF8, detectEncodingFromByteOrderMarks: true);
using var csv = new CsvReader(reader, config);

csv.Read();
csv.ReadHeader();
var names = csv.HeaderRecord!.Select(XmlName).ToArray();

var settings = new XmlWriterSettings
{
    Indent = true,
    Encoding = new UTF8Encoding(false),
    // Entitize is the default and is what keeps a newline inside an
    // attribute value from being normalised away on the next parse.
    NewLineHandling = NewLineHandling.Entitize,
};

using var writer = XmlWriter.Create("out.xml", settings);
writer.WriteStartDocument();
writer.WriteStartElement("rows");
while (csv.Read())
{
    writer.WriteStartElement("row");
    for (var i = 0; i < names.Length; i++)
    {
        // WriteElementString escapes the value for you.
        writer.WriteElementString(names[i], csv.TryGetField<string>(i, out var v) ? v : "");
    }
    writer.WriteEndElement();
}
writer.WriteEndElement();
writer.WriteEndDocument();

<?php
// fgetcsv implements RFC 4180 quoting, and DOMDocument escapes text nodes,
// so the two halves that usually break are both handled for you.
function xml_name(string $heading, int $index): string {
    $base = trim($heading);
    if ($base === '') return 'column' . ($index + 1);
    if (preg_match('/^[A-Za-z_][\w.\-]*$/', $base)) return $base;
    $name = preg_replace('/[^\w.\-]/', '_', $base);
    if (!preg_match('/^[A-Za-z_]/', $name)) $name = '_' . $name;
    if (stripos($name, 'xml') === 0) $name = '_' . $name;
    return $name;
}

$handle = fopen($argv[1], 'r');
$header = fgetcsv($handle);

// Strip a UTF-8 BOM from the first heading; Excel writes one.
$header[0] = preg_replace('/^\xEF\xBB\xBF/', '', $header[0]);
$names = [];
foreach ($header as $i => $h) $names[] = xml_name($h, $i);

$doc = new DOMDocument('1.0', 'UTF-8');
$doc->formatOutput = true;
$root = $doc->createElement('rows');
$doc->appendChild($root);

$line = 1;
while (($fields = fgetcsv($handle)) !== false) {
    $line++;
    if ($fields === [null] || $fields === ['']) continue;   // blank line
    if (count($fields) !== count($names)) {
        fprintf(STDERR, "line %d has %d fields, header has %d\n",
            $line, count($fields), count($names));
    }
    $row = $doc->createElement('row');
    foreach ($names as $i => $name) {
        // createTextNode escapes; createElement($name, $value) does not.
        $el = $doc->createElement($name);
        $el->appendChild($doc->createTextNode($fields[$i] ?? ''));
        $row->appendChild($el);
    }
    $root->appendChild($row);
}
fclose($handle);
echo $doc->saveXML();

# Import-Csv parses RFC 4180 quoting, including embedded newlines.
# ConvertTo-Xml escapes the values.
Import-Csv -Path .\data.csv -Delimiter ',' |
    ConvertTo-Xml -As String -NoTypeInformation |
    Out-File -FilePath .\out.xml -Encoding utf8

# Note the shape it produces. Headings become Name attributes, not
# element names, so nothing needs sanitising and nothing round-trips
# into the schema you probably wanted:
#
#   <Objects>
#     <Object>
#       <Property Name="unit price">12.50</Property>
#     </Object>
#   </Objects>
#
# For heading-as-element-name output, build it explicitly:
$rows = Import-Csv -Path .\data.csv
$doc = New-Object System.Xml.XmlDocument
$root = $doc.AppendChild($doc.CreateElement('rows'))
foreach ($r in $rows) {
    $row = $root.AppendChild($doc.CreateElement('row'))
    foreach ($p in $r.PSObject.Properties) {
        $name = $p.Name -replace '[^\w.\-]', '_'
        if ($name -notmatch '^[A-Za-z_]') { $name = "_$name" }
        $el = $row.AppendChild($doc.CreateElement($name))
        $el.InnerText = $p.Value      # InnerText escapes, InnerXml does not
    }
}
$doc.Save((Join-Path $PWD 'out.xml'))