Merge pull request #100 from chrislit/fuzz

fuzz branch

abydos/fingerprint.py

@@ -388,7 +388,7 @@ def position_fingerprint(word, n_bits=16,
 
 
 _synoname_special_table = (
-    # Roman, string, extra, method
+    # Roman, match, extra, method
     (False, 'NONE', '', 0),
     (False, 'aine', '', 3),
     (False, 'also erroneously', '', 4),
@@ -668,59 +668,59 @@ def roman_check(numeral, fname, lname):
 
     # Fill fields 7 (specials) and 3 (roman numerals)
     for num, special in enumerate(_synoname_special_table):
-        roman, string, extra, method = special
+        roman, match, extra, method = special
         if method & method_dict['end']:
-            string_context = ' ' + string
-            loc = full_name.find(string_context)
-            if ((len(full_name) > len(string_context)) and
-                    (loc == len(full_name) - len(string_context))):
+            match_context = ' ' + match
+            loc = full_name.find(match_context)
+            if ((len(full_name) > len(match_context)) and
+                    (loc == len(full_name) - len(match_context))):
                 if roman:
                     if not any(abbr in fname for abbr in ('i.', 'v.', 'x.')):
                         full_name = full_name[:loc]
                         toolcode[7] += '{:03d}'.format(num) + 'a'
                         if not toolcode[3]:
                             toolcode[3] = '{:03d}'.format(num)
                         if normalize == 2:
-                            fname, lname = roman_check(string, fname, lname)
+                            fname, lname = roman_check(match, fname, lname)
                 else:
                     full_name = full_name[:loc]
                     toolcode[7] += '{:03d}'.format(num) + 'a'
         if method & method_dict['middle']:
-            string_context = ' ' + string + ' '
-            loc = full_name.find(string_context)
+            match_context = ' ' + match + ' '
+            loc = full_name.find(match_context)
             if loc > 0:
                 if roman:
                     if not any(abbr in fname for abbr in ('i.', 'v.', 'x.')):
                         full_name = (full_name[:loc] +
-                                     full_name[loc + len(string) + 1:])
+                                     full_name[loc + len(match) + 1:])
                         toolcode[7] += '{:03d}'.format(num) + 'b'
                         if not toolcode[3]:
                             toolcode[3] = '{:03d}'.format(num)
                         if normalize == 2:
-                            fname, lname = roman_check(string, fname, lname)
+                            fname, lname = roman_check(match, fname, lname)
                 else:
                     full_name = (full_name[:loc] +
-                                 full_name[loc + len(string) + 1:])
+                                 full_name[loc + len(match) + 1:])
                     toolcode[7] += '{:03d}'.format(num) + 'b'
         if method & method_dict['beginning']:
-            string_context = string + ' '
-            loc = full_name.find(string_context)
+            match_context = match + ' '
+            loc = full_name.find(match_context)
             if loc == 0:
-                full_name = full_name[len(string) + 1:]
+                full_name = full_name[len(match) + 1:]
                 toolcode[7] += '{:03d}'.format(num) + 'c'
         if method & method_dict['beginning_no_space']:
-            loc = full_name.find(string)
+            loc = full_name.find(match)
             if loc == 0:
                 toolcode[7] += '{:03d}'.format(num) + 'd'
-                if full_name[len(string)] not in toolcode[9]:
-                    toolcode[9] += full_name[len(string)]
+                if full_name[:len(match)] not in toolcode[9]:
+                    toolcode[9] += full_name[:len(match)]
 
         if extra:
             loc = full_name.find(extra)
             if loc != -1:
                 toolcode[7] += '{:03d}'.format(num) + 'X'
-                if full_name[loc + len(extra)] not in toolcode[9]:
-                    toolcode[9] += full_name[loc + len(string)]
+                if full_name[loc:loc+len(extra)] not in toolcode[9]:
+                    toolcode[9] += full_name[loc:loc+len(match)]
 
     return lname, fname, ''.join(toolcode)
 

setup.cfg

@@ -8,10 +8,11 @@ cover-erase=1
 cover-html=1
 cover-branches=1
 cover-package=abydos
-;processes=1
+;processes=-1
 process-timeout=60
 process-restartworker=1
 doctest-options=+NORMALIZE_WHITESPACE
+exclude=(reg|fuzz)_test_
 
 [flake8]
 verbose=0

tests/fuzz/__init__.py

@@ -0,0 +1,62 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2018 by Christopher C. Little.
+# This file is part of Abydos.
+#
+# Abydos is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# Abydos is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with Abydos. If not, see <http://www.gnu.org/licenses/>.
+
+
+"""abydos.tests.fuzz.
+
+This module contains fuzz tests for Abydos
+"""
+
+import random
+import unicodedata
+from string import printable
+
+from six import unichr
+
+
+def random_char(below=0x10ffff, must_be=None):
+    """Generate a random Unicode character below U+{below}."""
+    while True:
+        char = unichr(random.randint(0, below))
+        try:
+            name = unicodedata.name(char)
+            if must_be is None or must_be in name:
+                return char
+        except ValueError:
+            pass
+
+
+def fuzz(word, fuzziness=0.2):
+    """Fuzz a word with noise."""
+    while True:
+        new_word = []
+        for ch in word:
+            if random.random() > fuzziness:
+                new_word.append(ch)
+            else:
+                if random.random() > 0.5:
+                    new_word.append(random.choice(printable))
+                elif random.random() > 0.8:
+                    new_word.append(unichr(random.randint(0, 0x10ffff)))
+                else:
+                    new_word.append(unichr(random.randint(0, 0xffff)))
+                if random.random() > 0.5:
+                    new_word.append(ch)
+        new_word = ''.join(new_word)
+        if new_word != word:
+            return new_word