Implemented table.size/hash (#256)

* Implemented table.size/hash

* Bump tabulator

Author: roll

README.md

@@ -206,6 +206,14 @@ Constructor to instantiate `Table` class. If `references` argument is provided,
 
 - `(Schema)` - returns schema class instance
 
+#### `table.size`
+
+- `(int/None)` - returns the table's size in BYTES if it's already read using e.g. `table.read`, otherwise returns `None`. In the middle of an iteration it returns size of already read contents
+
+#### `table.hash`
+
+- `(str/None)` - returns the table's SHA256 hash if it's already read using e.g. `table.read`, otherwise returns `None`. In the middle of an iteration it returns hash of already read contents
+
 #### `table.iter(keyed=Fase, extended=False, cast=True, relations=False, foreign_keys_values=False)`
 
 Iterates through the table data and emits rows cast based on table schema. Data casting can be disabled.

data/data.csv.zip

@@ -29,7 +29,7 @@ def read(*paths):
     'unicodecsv>=0.14',
     'isodate>=0.5.4',
     'rfc3986>=1.1.0',
-    'tabulator>=1.20',
+    'tabulator>=1.29',
 ]
 TESTS_REQUIRE = [
     'mock',

setup.py

@@ -22,7 +22,7 @@ class Table(object):
 
     def __init__(self, source, schema=None, strict=False,
                  post_cast=[], storage=None, **options):
-        """https://github.com/frictionlessdata/tableschema-py#schema
+        """https://github.com/frictionlessdata/tableschema-py#table
         """
 
         # Set attributes
@@ -56,19 +56,33 @@ def __init__(self, source, schema=None, strict=False,
 
     @property
     def headers(self):
-        """https://github.com/frictionlessdata/tableschema-py#schema
+        """https://github.com/frictionlessdata/tableschema-py#table
         """
         return self.__headers
 
     @property
     def schema(self):
-        """https://github.com/frictionlessdata/tableschema-py#schema
+        """https://github.com/frictionlessdata/tableschema-py#table
         """
         return self.__schema
 
+    @property
+    def size(self):
+        """https://github.com/frictionlessdata/tableschema-py#table
+        """
+        if self.__stream:
+            return self.__stream.size
+
+    @property
+    def hash(self):
+        """https://github.com/frictionlessdata/tableschema-py#table
+        """
+        if self.__stream:
+            return self.__stream.hash
+
     def iter(self, keyed=False, extended=False, cast=True, relations=False,
              foreign_keys_values=False):
-        """https://github.com/frictionlessdata/tableschema-py#schema
+        """https://github.com/frictionlessdata/tableschema-py#table
         """
 
         # Prepare unique checks
@@ -160,7 +174,7 @@ def iter(self, keyed=False, extended=False, cast=True, relations=False,
 
     def read(self, keyed=False, extended=False, cast=True, relations=False, limit=None,
              foreign_keys_values=False):
-        """https://github.com/frictionlessdata/tableschema-py#schema
+        """https://github.com/frictionlessdata/tableschema-py#table
         """
         result = []
         rows = self.iter(keyed=keyed, extended=extended, cast=cast, relations=relations,
@@ -172,7 +186,7 @@ def read(self, keyed=False, extended=False, cast=True, relations=False, limit=No
         return result
 
     def infer(self, limit=100, confidence=0.75):
-        """https://github.com/frictionlessdata/tableschema-py#schema
+        """https://github.com/frictionlessdata/tableschema-py#table
         """
         if self.__schema is None or self.__headers is None:
 
@@ -198,7 +212,7 @@ def infer(self, limit=100, confidence=0.75):
         return self.__schema.descriptor
 
     def save(self, target, storage=None, **options):
-        """https://github.com/frictionlessdata/tableschema-py#schema
+        """https://github.com/frictionlessdata/tableschema-py#table
         """
 
         # Save (tabulator)

tableschema/table.py

@@ -4,6 +4,7 @@
 from __future__ import absolute_import
 from __future__ import unicode_literals
 
+import six
 import pytest
 from copy import deepcopy
 from mock import Mock, patch
@@ -193,6 +194,56 @@ def test_read_with_headers_field_names_mismatch():
     assert 'match schema field names' in str(excinfo.value)
 
 
+# Stats
+
+def test_size():
+    table = Table('data/data.csv')
+    table.read()
+    assert table.size == 63
+
+
+@pytest.mark.skipif(six.PY2, reason='Support only for Python3')
+def test_size_compressed():
+    table = Table('data/data.csv.zip')
+    table.read()
+    assert table.size == 63
+
+
+def test_size_remote():
+    table = Table(BASE_URL % 'data/data.csv')
+    table.read()
+    assert table.size == 63
+
+
+def test_size_not_read():
+    table = Table(BASE_URL % 'data/data.csv')
+    assert table.size is None
+
+
+def test_hash():
+    table = Table('data/data.csv')
+    table.read()
+    assert table.hash == '328adab247692a1a405e83c2625d52e366389eabf8a1824931187877e8644774'
+
+
+@pytest.mark.skipif(six.PY2, reason='Support only for Python3')
+def test_hash_compressed():
+    table = Table('data/data.csv.zip')
+    table.read()
+    assert table.hash == '328adab247692a1a405e83c2625d52e366389eabf8a1824931187877e8644774'
+
+
+def test_hash_remote():
+    table = Table(BASE_URL % 'data/data.csv')
+    table.read()
+    assert table.hash == '328adab247692a1a405e83c2625d52e366389eabf8a1824931187877e8644774'
+
+
+def test_hash():
+    table = Table(BASE_URL % 'data/data.csv')
+    assert table.hash is None
+
+
 # Foreign keys
 
 FK_SOURCE = [
@@ -367,5 +418,5 @@ def test_multiple_foreign_keys_same_field_invalid():
     table = Table(FK_SOURCE, schema=schema)
     with pytest.raises(exceptions.RelationError) as excinfo:
         table.read(relations=relations)
-    assert 'Foreign key' in str(excinfo.value)    
-    
+    assert 'Foreign key' in str(excinfo.value)
+