Merge pull request #1 from ziky90/summarization_fixes

Consistency with gensim and pep 8
piskvorky · Apr 27, 2015 · fad4a10 · fad4a10
2 parents 68dcc08 + 2425874
commit fad4a10
Show file tree

Hide file tree

Showing 8 changed files with 36 additions and 9 deletions.
diff --git a/gensim/parsing/preprocessing.py b/gensim/parsing/preprocessing.py
@@ -1,3 +1,8 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html
+
 import re
 import string
 import glob

diff --git a/gensim/summarization/commons.py b/gensim/summarization/commons.py
@@ -1,3 +1,7 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html
 
 from gensim.summarization.graph import Graph
 

diff --git a/gensim/summarization/graph.py b/gensim/summarization/graph.py
@@ -1,8 +1,12 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html
 
 from abc import ABCMeta, abstractmethod
 
 
-class IGraph:
+class IGraph(object):
     """ Represents the interface or contract that the graph for TextRank
     should implement.
     """
@@ -18,7 +22,6 @@ def nodes(self):
         """
         pass
 
-
     @abstractmethod
     def edges(self):
         """
@@ -42,7 +45,6 @@ def neighbors(self, node):
         """
         pass
 
-
     @abstractmethod
     def has_node(self, node):
         """
@@ -56,7 +58,6 @@ def has_node(self, node):
         """
         pass
 
-
     @abstractmethod
     def add_node(self, node, attrs=None):
         """
@@ -75,7 +76,6 @@ def add_node(self, node, attrs=None):
         """
         pass
 
-
     @abstractmethod
     def add_edge(self, edge, wt=1, label='', attrs=[]):
         """
@@ -98,7 +98,6 @@ def add_edge(self, edge, wt=1, label='', attrs=[]):
         """
         pass
 
-
     @abstractmethod
     def has_edge(self, edge):
         """
@@ -112,7 +111,6 @@ def has_edge(self, edge):
         """
         pass
 
-
     @abstractmethod
     def edge_weight(self, edge):
         """
@@ -126,7 +124,6 @@ def edge_weight(self, edge):
         """
         pass
 
-
     @abstractmethod
     def del_node(self, node):
         """

diff --git a/gensim/summarization/keywords.py b/gensim/summarization/keywords.py
@@ -1,3 +1,7 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html
 
 from gensim.summarization.pagerank_weighted import pagerank_weighted_scipy as _pagerank
 from gensim.summarization.textcleaner import clean_text_by_word as _clean_text_by_word

diff --git a/gensim/summarization/pagerank_weighted.py b/gensim/summarization/pagerank_weighted.py
@@ -1,3 +1,7 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html
 
 from numpy import empty as empty_matrix
 from scipy.sparse import csr_matrix

diff --git a/gensim/summarization/summarizer.py b/gensim/summarization/summarizer.py
@@ -1,3 +1,7 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html
 
 from gensim.summarization.pagerank_weighted import pagerank_weighted_scipy as _pagerank
 from gensim.summarization.textcleaner import clean_text_by_sentences as _clean_text_by_sentences

diff --git a/gensim/summarization/syntactic_unit.py b/gensim/summarization/syntactic_unit.py
@@ -1,3 +1,8 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html
+
 
 class SyntacticUnit(object):
 

diff --git a/gensim/summarization/textcleaner.py b/gensim/summarization/textcleaner.py
@@ -1,3 +1,7 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl.html
 
 from gensim.summarization.syntactic_unit import SyntacticUnit
 from gensim.parsing.preprocessing import preprocess_documents
@@ -98,7 +102,7 @@ def clean_text_by_word(text):
     original_words = list(tokenize(text_without_acronyms, to_lower=True, deacc=True))
     filtered_words = [join_words(word_list, "") for word_list in preprocess_documents(original_words)]
     if HAS_PATTERN:
-        tags = tag(join_words(original_words)) # tag needs the context of the words in the text
+        tags = tag(join_words(original_words))  # tag needs the context of the words in the text
     else:
         tags = None
     units = merge_syntactic_units(original_words, filtered_words, tags)