Start working with strong search

aore/miscutils/fysearch.py

@@ -0,0 +1,30 @@
+# -*- coding: utf-8 -*-
+import re
+
+import Levenshtein
+
+
+def violet_ratio(pattern, candidate):
+    arr_pattern = re.split(r"[ ,:.#$-]+", pattern)
+    arr_candidate = re.split(r"[ ,:.#$-]+", candidate)
+
+    result = list()
+
+    for i in range(len(arr_pattern) - 1, 0, -1):
+        max_j = -1
+        max_ratio = 0
+        allowed_nums = range(len(arr_candidate) - 1, 0, -1)
+
+        for j in allowed_nums:
+            ratio = Levenshtein.ratio(arr_pattern[i], arr_candidate[j])
+            if max_ratio < ratio:
+                max_ratio = ratio
+                max_j = j
+
+        result.append(max_j*max_ratio)
+
+        if max_j > -1:
+            allowed_nums.remove(max_j)
+            del arr_candidate[max_j]
+
+    return sum(result) - len(arr_candidate)

aore/search/search.py

@@ -6,9 +6,12 @@ import time
 import Levenshtein
 import sphinxapi
 
+from fuzzywuzzy import fuzz
+
 from aore.config import basic
 from aore.config import sphinx_conf
 from aore.miscutils.exceptions import FiasException
+from aore.miscutils.fysearch import violet_ratio
 from aore.miscutils.trigram import trigram
 from wordentry import WordEntry
 from wordvariation import VariationType
@@ -172,4 +175,12 @@ class SphinxSearch:
                              ratio=match['attrs']['krank'],
                              cort=i))
 
+        # При строгом поиске нам надо еще добавить fuzzy и выбрать самое большое значение при отклонении
+        # выше заданного
+        for result in results:
+            print("{} {}".format(result['text'], fuzz.ratio(text, result['text'])))
+            print("{} {}".format(result['text'], fuzz.partial_ratio(text, result['text'])))
+            print("{} {}".format(result['text'], violet_ratio(text, result['text'].lower())))
+            print("--")
+
         return results

requirements.txt

@@ -1,3 +1,4 @@
+fuzzywuzzy>=0.10.0
 lxml>=3.4.0
 bottle>=0.12.9
 psycopg2>=2.6.1