Search through unicode character descriptions.

searchUnicode.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Time-stamp: <2012-07-15 16:39 ycopin@lyopc469>
# Copyright: This document has been placed in the public domain.

"""
Search through unicode character descriptions, e.g.::

  $ searchUnicode.py letter lamda
  Λ GREEK CAPITAL LETTER LAMDA &#923 0x39b
  λ GREEK SMALL LETTER LAMDA &#955 0x3bb
  ᴧ GREEK LETTER SMALL CAPITAL LAMDA &#7463 0x1d27

  $ searchUnicode.py "letter lamda"
  Λ GREEK CAPITAL LETTER LAMDA &#923 0x39b
  λ GREEK SMALL LETTER LAMDA &#955 0x3bb
"""

__author__ = "Yannick Copin <yannick.copin@laposte.net>"

import sys
import re
import unicodedata

maxpage = 831                           # It becomes really exotic after...

regexp = re.compile('.*'.join(sys.argv[1:]))

for page in xrange(0, maxpage*16+1, 16):
    for cell in xrange(0, 16):
        x = page + cell
        try:                            # Valid Unicode char
            name = unicodedata.name(unichr(x))
        except ValueError:              # Invalid Unicode char
            continue
        search = regexp.search(name.lower())
        if search is not None:
            print unichr(x), name, "&#%d" % x, "0x%0x" % x