X-Git-Url: https://wannabe.guru.org/gitweb/?a=blobdiff_plain;f=unscrambler.py;h=3ccddbbea5ef3f59e3915c5046586e62f74f1182;hb=7641e2ac7bf22ddfa0ef6c12b127e72dfbfb7f28;hp=1b242309b649eaa036277fdb22fc6f9c7705f0c8;hpb=e8fbbb7306430478dec55d2c963eed116d8330cc;p=python_utils.git

diff --git a/unscrambler.py b/unscrambler.py
index 1b24230..3ccddbb 100644
--- a/unscrambler.py
+++ b/unscrambler.py
@@ -1,5 +1,7 @@
 #!/usr/bin/env python3
 
+# © Copyright 2021-2022, Scott Gasch
+
 """A fast word unscrambler library."""
 
 import logging
@@ -100,10 +102,16 @@ class Unscrambler(object):
     lookup methods support a "fuzzy match" argument that can be set to
     request similar words that do not match exactly in addition to any
     exact matches.
-
     """
 
     def __init__(self, indexfile: Optional[str] = None):
+        """
+        Constructs an unscrambler.
+
+        Args:
+            indexfile: overrides the default indexfile location if provided
+        """
+
         # Cached index per instance.
         self.sigs = []
         self.words = []
@@ -120,6 +128,7 @@ class Unscrambler(object):
 
     @staticmethod
     def get_indexfile(indexfile: Optional[str]) -> str:
+        """Returns the current indexfile location."""
         if indexfile is None:
             if 'unscrambler_default_indexfile' in config.config:
                 indexfile = config.config['unscramble_indexfile']
@@ -175,6 +184,12 @@ class Unscrambler(object):
         the word and their frequencies.  We try to cluster "similar"
         words close to each other in the signature space.
 
+        Args:
+            word: the word to compute a signature for
+
+        Returns:
+            The word's signature.
+
         >>> train = Unscrambler.compute_word_sig('train')
         >>> train
         23178969883741
@@ -199,9 +214,14 @@ class Unscrambler(object):
         dictfile: str = '/usr/share/dict/words',
         indexfile: str = '/usr/share/dict/sparse_index',
     ) -> None:
-        """Before calling this method, change letter_sigs from the default above
-        unless you want to populate the same exact files.
+        """
+        Repopulates the indexfile.
+
+        .. warning::
 
+            Before calling this method, change letter_sigs from the
+            default above unless you want to populate the same exact
+            files.
         """
         words_by_sigs: Dict[int, str] = {}
         seen = set()
@@ -227,10 +247,20 @@ class Unscrambler(object):
         """Looks up a potentially scrambled word optionally including near
         "fuzzy" matches.
 
+        Args:
+            word: the word to lookup
+            window_size: the number of nearby fuzzy matches to return
+
+        Returns:
+            A dict of word -> bool containing unscrambled words with (close
+            to or precisely) the same letters as the input word.  The bool
+            values in this dict indicate whether the key word is an exact
+            or near match.  The count of entries in this dict is controlled
+            by the window_size param.
+
         >>> u = Unscrambler()
         >>> u.lookup('eanycleocipd', window_size=0)
         {'encyclopedia': True}
-
         """
         sig = Unscrambler.compute_word_sig(word)
         return self.lookup_by_sig(sig, window_size=window_size)
@@ -240,6 +270,18 @@ class Unscrambler(object):
         a previous call to Unscrambler.compute_word_sig.  Optionally returns
         near "fuzzy" matches.
 
+        Args:
+            sig: the signature of the word to lookup (see :meth:`compute_word_sig`
+                to generate these signatures).
+            window_size: the number of nearby fuzzy matches to return
+
+        Returns:
+            A dict of word -> bool containing unscrambled words with (close
+            to or precisely) the same letters as the input word.  The bool
+            values in this dict indicate whether the key word is an exact
+            or near match.  The count of entries in this dict is controlled
+            by the window_size param.
+
         >>> sig = Unscrambler.compute_word_sig('sunepsapetuargiarin')
         >>> sig
         18491949645300288339
@@ -247,7 +289,6 @@ class Unscrambler(object):
         >>> u = Unscrambler()
         >>> 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 = {}
         (_, location) = list_utils.binary_search(self.sigs, sig)