analyze new posts

1 files changed, 131 insertions, 0 deletions

diff --git a/analyze_new.py b/analyze_new.py
new file mode 100644
index 0000000..348ed8d
--- /dev/null
+++ b/analyze_new.py
@@ -0,0 +1,131 @@
+#!/usr/bin/python3
+import re
+import operator
+import itertools
+import sys
+from pprint import pprint
+
+def load_text(n):
+    with open('new/text' + str(n) + '_orig') as f:
+        text = f.read()
+
+    lines = re.split(r'[\?\.\!]+', text) 
+    lines = list(map(lambda s: s.replace(' ', '').replace('-', ''), lines))
+
+    return "\n".join(lines).strip()
+
+def letter_pos(letter):
+    if letter in predefined_table:
+        return predefined_table[letter]
+    else:
+        letter_table = table[letter]
+        if len(letter_table) > 0:
+            return letter_table[0][0]
+        else:
+            return None
+
+alphabet = 'АБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯ'
+
+text = ''
+text += load_text(1) + "\n"
+text += load_text(3) + "\n"
+#text += load_text(2)
+text = text.upper()
+
+predefined_table = {
+    'М': 8,
+    'А': 5,
+    'Р': 3,
+    'Ш': 1,
+    'Щ': 1,
+    'И': 1,
+    'У': 2,
+    'Ю': 10,
+    'В': 12,
+    'Й': 5,
+    'Л': 2,
+    'Ц': 2,
+    'О': 4,
+    'Д': 8,
+    'Т': 9,
+    'П': 5,
+    'Э': 3
+}
+
+table = {}
+lines = text.split("\n")
+
+for a in alphabet:
+    table[a] = {}
+    for line in lines:
+        indexes = [m.start() for m in re.finditer(a, line)]
+        for index in indexes:
+            index += 1
+            if index in table[a]:
+                table[a][index] += 1
+            else:
+                table[a][index] = 1
+
+for a, t in table.items():
+    ts = sorted(t.items(), key=operator.itemgetter(1), reverse=True)
+    table[a] = ts
+
+#pprint(table['Э'])
+#sys.exit()
+
+variants = []
+for line in lines:
+    valid = []
+    for a in table:
+        if True:
+            index = letter_pos(a)
+            if index == None:
+                continue
+            
+            try:
+                if line[index-1] == a and a not in valid:
+                    valid.append(a)
+            except IndexError:
+                continue
+        
+        if False:
+            letter_table = table[a]
+            if not len(letter_table):
+                continue
+
+            for i in range(3):
+                if i > len(letter_table)-1:
+                    continue
+
+                if a == 'Щ':
+                    index = 1
+                else:
+                    index = letter_table[i][0]
+                try:
+                    if line[index-1] == a and a not in valid:
+                        valid.append(a)
+                except IndexError:
+                    continue
+
+    variants.append(valid)
+    #print('('+''.join(valid)+')')
+
+variants = list(filter(lambda a: len(a), variants))
+variants = variants[11:31]
+
+pprint(variants)
+sys.exit()
+
+#variants = variants[11:]
+res = list(itertools.product(*variants))
+for r in res:
+    if r[0] == 'Ь': continue
+#    if r[1] != 'А': continue
+#    if r[5] != 'Л': continue
+#    if r[4] != 'О': continue
+    
+    #if r[3] != 'И': continue
+    #if r[2] != 'Д': continue
+    #if r[0] != 'Х': continue
+    
+    print(''.join(r))