X-Git-Url: https://wannabe.guru.org/gitweb/?a=blobdiff_plain;f=unscrambler.py;h=78c1f9b4f7e7c1a5ef618b54eeed2eb012db7a4d;hb=f135ec7ae3d7ca347d7489eb28d30b5db98f49de;hp=d3686d67ed763d9b240b58ee9d43b5151ed31ea8;hpb=e6f32fdd9b373dfcd100c7accb41f57d83c2f0a1;p=python_utils.git diff --git a/unscrambler.py b/unscrambler.py index d3686d6..78c1f9b 100644 --- a/unscrambler.py +++ b/unscrambler.py @@ -7,9 +7,7 @@ import config import decorator_utils import list_utils -cfg = config.add_commandline_args( - f'Unscramble! ({__file__})', 'A fast word unscrambler.' -) +cfg = config.add_commandline_args(f'Unscramble! ({__file__})', 'A fast word unscrambler.') cfg.add_argument( "--unscramble_indexfile", help="Path to a file of signature -> word index.", @@ -198,7 +196,7 @@ class Unscrambler(object): unless you want to populate the same exact files. """ - words_by_sigs = {} + words_by_sigs: Dict[int, str] = {} seen = set() with open(dictfile, "r") as f: for word in f: @@ -218,23 +216,19 @@ class Unscrambler(object): word = words_by_sigs[sig] print(f'0x{sig:x}+{word}', file=f) - def lookup( - self, word: str, *, include_fuzzy_matches: bool = False - ) -> Dict[str, bool]: + def lookup(self, word: str, *, window_size: int = 5) -> Dict[str, bool]: """Looks up a potentially scrambled word optionally including near "fuzzy" matches. >>> u = Unscrambler() - >>> u.lookup('eanycleocipd', include_fuzzy_matches=False) + >>> u.lookup('eanycleocipd', window_size=0) {'encyclopedia': True} """ sig = Unscrambler.compute_word_sig(word) - return self.lookup_by_sig(sig, include_fuzzy_matches=include_fuzzy_matches) + return self.lookup_by_sig(sig, window_size=window_size) - def lookup_by_sig( - self, sig: int, *, include_fuzzy_matches: bool = False - ) -> Dict[str, bool]: + def lookup_by_sig(self, sig: int, *, window_size: int = 5) -> Dict[str, bool]: """Looks up a word that has already been translated into a signature by a previous call to Unscrambler.compute_word_sig. Optionally returns near "fuzzy" matches. @@ -244,23 +238,23 @@ class Unscrambler(object): 18491949645300288339 >>> u = Unscrambler() - >>> u.lookup_by_sig(sig, include_fuzzy_matches=True) + >>> u.lookup_by_sig(sig) {'pupigerous': False, 'pupigenous': False, 'unpurposing': False, 'superpurgation': False, 'unsupporting': False, 'superseptuaginarian': True, 'purpurogallin': False, 'scuppaug': False, 'purpurigenous': False, 'purpurogenous': False, 'proppage': False} """ ret = {} (exact, location) = list_utils.binary_search(self.sigs, sig) - start = location - 5 + start = location - window_size if start < 0: start = 0 - end = location + 6 + end = location + 1 + window_size if end > len(self.words): end = len(self.words) for x in range(start, end): word = self.words[x] fsig = self.sigs[x] - if include_fuzzy_matches is True or (fsig == sig): + if window_size > 0 or (fsig == sig): ret[word] = fsig == sig return ret