From d1cb30dbc439f9ce54967f32ca2726d11826be71 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal@gmail.com>
Date: Thu, 16 Jul 2015 19:29:02 +0200
Subject: [PATCH] * Remove unnecessary key and id properties from Utf8String.

---
 spacy/en/pos.pyx  |  3 +--
 spacy/strings.pxd |  2 +-
 spacy/strings.pyx | 15 ++++++++-------
 spacy/structs.pxd |  2 --
 4 files changed, 10 insertions(+), 12 deletions(-)

diff --git a/spacy/en/pos.pyx b/spacy/en/pos.pyx
index de795c1f3..1f09f364a 100644
--- a/spacy/en/pos.pyx
+++ b/spacy/en/pos.pyx
@@ -332,8 +332,7 @@ cdef class EnPosTagger:
         cdef unicode lemma_string
         lemma_strings = self.lemmatizer(py_string, pos)
         lemma_string = sorted(lemma_strings)[0]
-        bytes_string = lemma_string.encode('utf8')
-        lemma = self.strings.intern(bytes_string, len(bytes_string)).i
+        lemma = self.strings[lemma_string]
         return lemma
 
     def load_morph_exceptions(self, dict exc):
diff --git a/spacy/strings.pxd b/spacy/strings.pxd
index 178ae51b6..c86d33d1c 100644
--- a/spacy/strings.pxd
+++ b/spacy/strings.pxd
@@ -22,4 +22,4 @@ cdef class StringStore:
     cdef PreshMap _map
     cdef size_t _resize_at
 
-    cdef const Utf8Str* intern(self, char* chars, int length) except NULL
+    cdef const Utf8Str* intern(self, char* chars, int length, int* id_) except NULL
diff --git a/spacy/strings.pyx b/spacy/strings.pyx
index 56df4d2f1..ca74f4044 100644
--- a/spacy/strings.pyx
+++ b/spacy/strings.pyx
@@ -67,6 +67,7 @@ cdef class StringStore:
     def __getitem__(self, object string_or_id):
         cdef bytes byte_string
         cdef const Utf8Str* utf8str
+        cdef int id_
         if isinstance(string_or_id, int) or isinstance(string_or_id, long):
             if string_or_id == 0:
                 return u''
@@ -75,16 +76,16 @@ cdef class StringStore:
             utf8str = &self.strings[<int>string_or_id]
             return utf8str.chars[:utf8str.length].decode('utf8')
         elif isinstance(string_or_id, bytes):
-            utf8str = self.intern(<char*>string_or_id, len(string_or_id))
-            return utf8str.i
+            utf8str = self.intern(<char*>string_or_id, len(string_or_id), &id_)
+            return id_
         elif isinstance(string_or_id, unicode):
             byte_string = string_or_id.encode('utf8')
-            utf8str = self.intern(<char*>byte_string, len(byte_string))
-            return utf8str.i
+            utf8str = self.intern(<char*>byte_string, len(byte_string), &id_)
+            return id_
         else:
             raise TypeError(type(string_or_id))
 
-    cdef const Utf8Str* intern(self, char* chars, int length) except NULL:
+    cdef const Utf8Str* intern(self, char* chars, int length, int* id_) except NULL:
         # 0 means missing, but we don't bother offsetting the index. We waste
         # slot 0 to simplify the code, because it doesn't matter.
         assert length != 0
@@ -97,7 +98,6 @@ cdef class StringStore:
                 self.strings = <Utf8Str*>self.mem.realloc(self.strings, self._resize_at * sizeof(Utf8Str))
             i = self.size
             self.strings[i].i = self.size
-            self.strings[i].key = key
             self.strings[i].chars = <unsigned char*>self.mem.alloc(length, sizeof(char))
             memcpy(self.strings[i].chars, chars, length)
             self.strings[i].length = length
@@ -123,6 +123,7 @@ cdef class StringStore:
             strings = file_.read().split(SEPARATOR)
         cdef unicode string
         cdef bytes byte_string
+        cdef int id_
         for string in strings[1:]:
             byte_string = string.encode('utf8')
-            self.intern(byte_string, len(byte_string))
+            self.intern(byte_string, len(byte_string), &id_)
diff --git a/spacy/structs.pxd b/spacy/structs.pxd
index a26c87e2f..0e0fb34b8 100644
--- a/spacy/structs.pxd
+++ b/spacy/structs.pxd
@@ -80,8 +80,6 @@ cdef struct TokenC:
 
 
 cdef struct Utf8Str:
-    id_t i
-    hash_t key
     unsigned char* chars
     int length