From 06eac326104ba1e8734d28a27626b88b18dde600 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal@gmail.com>
Date: Thu, 23 Jul 2015 01:10:36 +0200
Subject: [PATCH] * Add cfile.pyx

---
 setup.py        |  1 +
 spacy/cfile.pxd | 12 ++++++++++++
 spacy/cfile.pyx | 38 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 51 insertions(+)
 create mode 100644 spacy/cfile.pxd
 create mode 100644 spacy/cfile.pyx

diff --git a/setup.py b/setup.py
index b29c01f60..eb3adde3e 100644
--- a/setup.py
+++ b/setup.py
@@ -162,6 +162,7 @@ MOD_NAMES = ['spacy.parts_of_speech', 'spacy.strings',
              'spacy.gold', 'spacy.orth',
              'spacy.tokens.doc', 'spacy.tokens.spans', 'spacy.tokens.token',
              'spacy.serialize.packer', 'spacy.serialize.huffman', 'spacy.serialize.bits',
+             'spacy.cfile',
              'spacy.syntax.ner']
 
 
diff --git a/spacy/cfile.pxd b/spacy/cfile.pxd
new file mode 100644
index 000000000..c9a6aec41
--- /dev/null
+++ b/spacy/cfile.pxd
@@ -0,0 +1,12 @@
+from libc.stdio cimport fopen, fclose, fread, fwrite, FILE
+from cymem.cymem cimport Pool
+
+cdef class CFile:
+    cdef FILE* fp
+    cdef bint is_open
+ 
+    cdef int read_into(self, void* dest, size_t number, size_t elem_size) except -1
+
+    cdef int write_from(self, void* src, size_t number, size_t elem_size) except -1
+    
+    cdef void* alloc_read(self, Pool mem, size_t number, size_t elem_size) except *
diff --git a/spacy/cfile.pyx b/spacy/cfile.pyx
new file mode 100644
index 000000000..cb192dfab
--- /dev/null
+++ b/spacy/cfile.pyx
@@ -0,0 +1,38 @@
+from libc.stdio cimport fopen, fclose, fread, fwrite, FILE
+
+
+cdef class CFile:
+    def __init__(self, loc, bytes mode):
+        cdef bytes bytes_loc = loc.encode('utf8') if type(loc) == unicode else loc
+        self.fp = fopen(<char*>bytes_loc, mode)
+        if self.fp == NULL:
+            raise IOError("Could not open binary file %s" % bytes_loc)
+        self.is_open = True
+
+    def __dealloc__(self):
+        if self.is_open:
+            fclose(self.fp)
+
+    def close(self):
+        fclose(self.fp)
+        self.is_open = False
+
+    cdef int read_into(self, void* dest, size_t number, size_t elem_size) except -1:
+        st = fread(dest, elem_size, number, self.fp)
+        if st != number:
+            raise IOError
+
+    cdef int write_from(self, void* src, size_t number, size_t elem_size) except -1:
+        st = fwrite(src, elem_size, number, self.fp)
+        if st != number:
+            raise IOError
+
+    cdef void* alloc_read(self, Pool mem, size_t number, size_t elem_size) except *:
+        cdef void* dest = mem.alloc(number, elem_size)
+        self.read_into(dest, number, elem_size)
+        return dest
+
+    def write_unicode(self, unicode value):
+        cdef bytes py_bytes = value.encode('utf8')
+        cdef char* chars = <char*>py_bytes
+        self.write(sizeof(char), len(py_bytes), chars)