format-colors

#!/usr/bin/env python

import sys
import re
from xml.sax.saxutils import escape
from optparse import OptionParser

def parse_files(*files):
  def simplify_hex_color(hx):
    hx = hx.strip().strip('#').strip()
    if len(hx) == 6 and \
      hx[0] == hx[1] and hx[2] == hx[3] and hx[4] == hx[5]:
      hx = hx[0] + hx[2] + hx[4]
    return '#' + hx
  def hex_to_rgb_triplet(hx):
    hx = hx.strip().strip('#')
    if len(hx) == 3:
      hx = hx[0]*2 + hx[1]*2 + hx[3]*2
    r,g,b = hx[0:2], hx[2:4], hx[4:6]
    r,g,b = int(r, 16), int(g, 16), int(b, 16)
    return r,g,b
  def make_identifier(name):
    ident = re.sub('[^a-zA-Z0-9_]+', '_', name)
    ident = re.sub('[_]+', '_', ident)
    ident = ident.strip('_')
    if len(ident) == 0:
      ident = '_'
    if ident[0].isdigit():
      ident = '_' + ident
    return ident.lower()
  def split_line(line):
    fields = line.split('\t')
    return (make_identifier(fields[0]),
            fields[0],
            simplify_hex_color(fields[1]),
            hex_to_rgb_triplet(fields[1]))
  def process_line(line):
    if len(line) > 0 and line[0].isspace(): return line.strip()
    else: return ''
  all_lines = []
  for fn in files:
    content = open(fn).read()
    lines = content.split('\n')
    lines = [process_line(l) for l in lines]
    lines = [l.strip() for l in lines if l.strip()]
    lines = [split_line(l) for l in lines]
    all_lines.extend(lines)

  out_dict = {}
  for line in all_lines:
    out_dict[line[0].strip()] = {
      "name": line[1].strip().title(),
      "hex": line[2].lower().strip(),
      "rgb": line[3]
    }

  return out_dict

def to_json(color_dict):
  indent = '  '
  code = '{\n'
  for k, v in sorted(color_dict.items()):
    code += indent   + '"%s": {\n' % k
    code += indent*2 +   '"name": "%s",\n' % v["name"]
    code += indent*2 +   '"hex": "%s",\n' % v["hex"]
    code += indent*2 +   '"rgb": [%d, %d, %d],\n' % v["rgb"]
    code += indent + '},\n'
  code += '}\n'
  return code

def to_conf(color_dict):
  code = ''
  for k, v in sorted(color_dict.items()):
    code += '[%s]\n' % k
    code += 'name=%s\n' % v["name"]
    code += 'hex=%s\n' % v["hex"]
    code += 'rgb=%d;%d;%d\n\n' % v["rgb"]
  return code

def to_sexp(color_dict):
  indent = '  '
  code = '(\n'
  for k, v in sorted(color_dict.items()):
    code += indent + "(%s '%s' '%s' (%d %d %d))\n" % (k, v["name"], v["hex"],
      v["rgb"][0], v["rgb"][1], v["rgb"][2])
  code += ')\n'
  return code

def to_xml(color_dict):
  code = '<?xml version="1.0" encoding="utf-8"?>\n'
  code += '<colors>\n'
  indent = '  '
  for k, v in sorted(color_dict.items()):
    name = escape(v["name"])
    code += indent + '<color id="%s" hex="%s" red="%d" green="%d" blue="%d">' % (
      k, v["hex"], v["rgb"][0], v["rgb"][1], v["rgb"][2])
    code += name + '</color>\n'
  code += '</colors>\n'
  return code

def to_csv(color_dict):
  code = ''
  for k, v in sorted(color_dict.items()):
    code += '%s,' % k
    code += '"%s",' % v["name"]
    code += '%s,' % v["hex"]
    code += '%d,%d,%d\n' % v["rgb"]
  return code

def to_ccode(color_dict):
  indent = '  '
  code = '/* This file is auto-generated, do not edit. */\n\n'
  code += '#define COLOR_NAMES_MAX %d\n\n' % len(color_dict.items())
  code += 'typedef struct ColorInfo {\n'
  code += indent   + 'const char *name;\n'
  code += indent   + 'const char *hex;\n'
  code += indent   + 'struct {\n'
  code += indent*2 +   'unsigned char r;\n'
  code += indent*2 +   'unsigned char g;\n'
  code += indent*2 +   'unsigned char b;\n'
  code += indent   + '} rgb;\n'
  code += '} ColorInfo;\n\n'
  code += 'typedef enum Color {\n'
  first = True
  for k, v in sorted(color_dict.items()):
    if first:
      code += indent + 'COLOR_%s=0,\n' % k.upper()
      first = False
    else:
      code += indent + 'COLOR_%s,\n' % k.upper()
  code = code.rstrip()
  if code.endswith(','):
    code = code[0:-1]
  code += '\n'
  code += '} Color;\n\n'
  code += 'const ColorInfo color_data[COLOR_NAMES_MAX] = {\n'
  for k, v in sorted(color_dict.items()):
    code += indent + '{ "%s", "%s", { %d, %d, %d } },\n' % (
      v["name"], v["hex"], v["rgb"][0], v["rgb"][1], v["rgb"][2])
  code = code.rstrip()
  if code.endswith(','):
    code = code[0:-1]
  code += '\n};\n'
  return code

def to_html(color_dict):
  code = '''<html>
  <head>
    <title>List of Colors</title>
    <style type="text/css">
    body, h1, table, tr, th, td {
      font-family: monospace;
    }
    table, th, td {
      border: 1px #DCDCDC solid;
    }
    th {
      background-color: #D8D8D8;
    }
    .swatch {
      width: 64px;
    }
    .color_hex, .color_rgb {
      text-align: center;
    }
    </style>
  </head>
  <body>
    <h1>List of Colors</h1>
    <p>Source:
      <a href="http://en.wikipedia.org/wiki/List_of_colors">http://en.wikipedia.org/wiki/List_of_colors</a>
    </p>
    <table cellpadding="2" cellspacing="1" border="1">
      <tr>
        <th>Swatch</th>
        <th>Name</th>
        <th>HTML</th>
        <th>R</th><th>G</th><th>B</th>
      </tr>
'''
  for k, v in sorted(color_dict.items()):
    code += '      <tr>\n'
    code += '        <td class="swatch" style="background-color: %s;">&nbsp;</td>\n' % v["hex"]
    code += '        <td>%s</td>\n' % escape(v["name"])
    code += '        <td class="color_hex">%s</td>\n' % v["hex"]
    code += '        <td class="color_rgb">%d</td>\n' % v["rgb"][0]
    code += '        <td class="color_rgb">%d</td>\n' % v["rgb"][1]
    code += '        <td class="color_rgb">%d</td>\n' % v["rgb"][2]
    code += '      </tr>\n'
  code += '    </table>\n  </body>\n</html>'
  return code

FORMATS = {
  "ccode": to_ccode,
  "conf": to_conf,
  "csv": to_csv,
  "html": to_html,
  "json": to_json,
  "sexp": to_sexp,
  "xml": to_xml,
}

def main(args):
  p = OptionParser(usage='%prog [options] FILE...',
                   description='This utility parses the colour list from ' +
                    'Wikipedia and outputs to various formats. Select the ' +
                    'table in Wikipedia using your browser and paste to a ' +
                    'text file and then run this program with that FILE. ' +
                    'If the data comes from anywhere else, just make sure ' +
                    'that all of the lines containing the data start with ' +
                    'a space and are tab-separated, and that the first 2 ' +
                    'fields are the name of the colour and the RGB hex ' +
                    'triplet.',
                   epilog='For "-o", "-" (stdout) is the default. ' +
                    'For "-f", "json" is the default')
  p.add_option('-o', metavar='FILE', dest='outfile', default='-',
    help='file to write to ("-" for stdout)')
  p.add_option('-f', metavar='FMT', dest='format', default='json',
    help='format to output ("ccode", "conf", "csv", "html", "json", "sexp", "xml")')

  opts, args = p.parse_args(args)

  fmt = opts.format.lower()
  if fmt not in FORMATS:
    p.error("unknown format '%s', expect one of ccode, conf, csv, html, json, sexp, xml\n" % fmt)

  do_close = False
  if opts.outfile == '-':
    outfile = sys.stdout
  else:
    try:
      outfile = open(opts.outfile, 'w')
      do_close = True
    except IOError as e:
      p.error("unable to open file '%s': %s" % (opts.outfile, e.message))

  if len(args) < 2:
    p.error("no input file(s) specified")

  color_dict = parse_files(*args[1:])

  outfile.write(FORMATS[fmt](color_dict))

  if do_close:
    outfile.close()

  return 0

if __name__ == "__main__": sys.exit(main(sys.argv))