add tsid channel information for complete BS support.

[rec10/rec10-git.git] / rec10 / trunk / src / n_gram.py

diff --git a/rec10/trunk/src/n_gram.py b/rec10/trunk/src/n_gram.py
index 3eee3f9..f24a097 100644 (file)
--- a/rec10/trunk/src/n_gram.py
+++ b/rec10/trunk/src/n_gram.py
@@ -1,7 +1,7 @@
 #!/usr/bin/python
 # coding: UTF-8
 # Rec10 TS Recording Tools
-# Copyright (C) 2009 Yukikaze
+# Copyright (C) 2009-2011 Yukikaze
 
 import zenhan
 def bigram(str1, str2):
@@ -22,7 +22,7 @@ def bigram(str1, str2):
             tmp = x
     point = 0
     for x in gram:
-        i = find_gram(x, str2)
+        i = findGram(x, str2)
         if i > 0:
             i = 90 + 10 * i
         else:
@@ -51,7 +51,7 @@ def trigram(str1, str2):
     point = 0
     count = 0
     for x in gram:
-        i = find_gram(x, str2)
+        i = findGram(x, str2)
         if i > 0:
             i = 90 + 10 * i
             count=count + 1
@@ -62,7 +62,7 @@ def trigram(str1, str2):
     point = point / len(str1) * 10
     point = point / len(str2) * 10
     return point
-def find_gram(gram, s):
+def findGram(gram, s):
     """
     s中にあらわれるgramの数を調べる
     """
@@ -72,7 +72,7 @@ def find_gram(gram, s):
         i = i + 1
         st = st[st.find(gram) + 1:]
     return i
-def get_noun_quad_gram(s):
+def getNounQuadGram(s):
     """
     。
     """
@@ -89,27 +89,27 @@ def get_noun_quad_gram(s):
             else:
                 tmps=tmp1 + tmp2 + tmp3 + x
                 if tmps.find(" ")<0:
-                    if zenhan.check_Character_Type(tmp1)>0:
-                        if (zenhan.check_Character_Type(tmp1)==zenhan.check_Character_Type(tmp2)):
-                            if (zenhan.check_Character_Type(tmp2)==zenhan.check_Character_Type(tmp3)):
-                                if (zenhan.check_Character_Type(tmp3)==zenhan.check_Character_Type(x)):
+                    if zenhan.checkCharacterType(tmp1)>0:
+                        if (zenhan.checkCharacterType(tmp1)==zenhan.checkCharacterType(tmp2)):
+                            if (zenhan.checkCharacterType(tmp2)==zenhan.checkCharacterType(tmp3)):
+                                if (zenhan.checkCharacterType(tmp3)==zenhan.checkCharacterType(x)):
                                     gram[tmps]=gram.get(tmps,0)+1
                                     skipnum=0
                                 else:
                                     skipnum=3
                             else:
-                                if (zenhan.check_Character_Type(tmp3)==zenhan.check_Character_Type(x)):
+                                if (zenhan.checkCharacterType(tmp3)==zenhan.checkCharacterType(x)):
                                     skipnum=2
                                 else:
                                     skipnum=3
                         else:
-                            if (zenhan.check_Character_Type(tmp2)==zenhan.check_Character_Type(tmp3)):
-                                if (zenhan.check_Character_Type(tmp3)==zenhan.check_Character_Type(x)):
+                            if (zenhan.checkCharacterType(tmp2)==zenhan.checkCharacterType(tmp3)):
+                                if (zenhan.checkCharacterType(tmp3)==zenhan.checkCharacterType(x)):
                                     skipnum=0
                                 else:
                                     skipnum=3
                             else:
-                                if (zenhan.check_Character_Type(tmp3)==zenhan.check_Character_Type(x)):
+                                if (zenhan.checkCharacterType(tmp3)==zenhan.checkCharacterType(x)):
                                     skipnum=2
                                 else:
                                     skipnum=3