trie regex with special characters

regex_re_with_special_chars.py

import re

class Trie():
    """Regex::Trie in Python. Creates a Trie out of a list of words. The trie can be exported to a Regex pattern.
    The corresponding Regex should match much faster than a simple Regex union."""

    def __init__(self):
        self.data = {}

    def add(self, word):
        ref = self.data
        for char in word:
            ref[char] = char in ref and ref[char] or {}
            ref = ref[char]
        ref[''] = 1

    def dump(self):
        return self.data

    def quote(self, char):
        return re.escape(char)

    def _pattern(self, pData):
        data = pData
        if "" in data and len(data.keys()) == 1:
            return None

        alt = []
        cc = []
        q = 0
        for char in sorted(data.keys()):
            if isinstance(data[char], dict):
                try:
                    recurse = self._pattern(data[char])
                    alt.append(self.quote(char) + recurse)
                except:
                    cc.append(self.quote(char))
            else:
                q = 1
        cconly = not len(alt) > 0

        if len(cc) > 0:
            if len(cc) == 1:
                alt.append(cc[0])
            else:
                alt.append('[' + ''.join(cc) + ']')

        if len(alt) == 1:
            result = alt[0]
        else:
            result = "(?:" + "|".join(alt) + ")"

        if q:
            if cconly:
                result += "?"
            else:
                result = "(?:%s)?" % result
        return result

    def pattern(self):
        return self._pattern(self.dump())

def trie_regex_from_words(words):
    trie = Trie()
    for word in words:
        trie.add(word)
    return re.compile(r"\b" + trie.pattern() + r"\b", re.IGNORECASE)

def find(word):
    def fun():
        return union.match(word)
    return fun

compiled_re = trie_regex_from_words(['c++'])

print(compiled_re.findall('c++ is awesome'))

compiled_re = trie_regex_from_words(['.Net'])

print(compiled_re.findall('.NET is awesome'))

# output:
# []
# []