Merge pull request #450 from reyoung/feature/pre-commit-hooks-scripts

Feature/pre commit hooks scripts

.clang-format

@@ -13,8 +13,6 @@
 # The document of clang-format is 
 #   http://clang.llvm.org/docs/ClangFormat.html
 #   http://clang.llvm.org/docs/ClangFormatStyleOptions.html
-#
-# TODO(yuyang18): Add python and other language code style
 ---
 Language:        Cpp
 BasedOnStyle:  Google
@@ -22,8 +20,9 @@ IndentWidth:     2
 TabWidth:        2
 ContinuationIndentWidth: 4
 AccessModifierOffset: -2  # The private/protected/public has no indent in class
-PointerAlignment: Left    # int* p/int& p, not int *p/int &p
 Standard:  Cpp11 
 AllowAllParametersOfDeclarationOnNextLine: true
+BinPackParameters: false
+BinPackArguments: false
 ...
 

.pre-commit-config.yaml

+-   repo: https://github.com/Lucas-C/pre-commit-hooks.git
+    sha: c25201a00e6b0514370501050cf2a8538ac12270
+    hooks:
+    -   id: remove-crlf
+-   repo: https://github.com/reyoung/mirrors-yapf.git
+    sha: v0.13.2
+    hooks:
+    -   id: yapf
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    sha: 4ef03c4223ad322c7adaa6c6c0efb26b57df3b71
+    hooks:
+    -   id: check-added-large-files
+    -   id: check-merge-conflict
+    -   id: check-symlinks
+    -   id: detect-private-key
+    -   id: end-of-file-fixer
+# TODO(yuyang): trailing whitespace has some bugs on markdown 
+# files now, please not add it to pre-commit hook now
+#    -   id: trailing-whitespace
+#
+# TODO(yuyang): debug-statements not fit for Paddle, because
+# not all of our python code is runnable. Some are used for 
+# documenation
+#    -   id: debug-statements

demo/introduction/README.md

 This folder contains scripts used in PaddlePaddle introduction.
 - use `bash train.sh` to train a simple linear regression model
 - use `python evaluate_model.py` to read model parameters. You can see that `w` and `b` are very close to [2, 0.3].
-

demo/mnist/data/get_mnist_data.sh

@@ -19,4 +19,3 @@ done
 cd $DIR
 rm -f *.list
 python generate_list.py
-

demo/recommendation/data/config.json

@@ -14,4 +14,3 @@
     "fields": ["id", "title", "genres"]
   }
 }
-

demo/semantic_role_labeling/test.sh

@@ -37,4 +37,3 @@ paddle train \
   --use_gpu=false \
   --config_args=is_test=1 \
 2>&1 | tee 'test.log'
-

demo/semantic_role_labeling/train.sh

@@ -24,4 +24,3 @@ paddle train \
   --show_parameter_stats_period=10 \
   --test_all_data_in_one_period=1 \
 2>&1 | tee 'train.log'
-

doc/introduction/index.md

@@ -98,4 +98,3 @@ There, you have recovered the underlying pattern between `X` and `Y` only from o
 - <a href="../build/index.html"> Build and Installation </a>
 - <a href="../demo/quick_start/index_en.html">Quick Start</a>
 - <a href="../demo/index.html">Example and Demo</a>
-

paddle/CMakeLists.txt

@@ -17,5 +17,3 @@ endif()
 if(WITH_SWIG_PY)
   add_subdirectory(api)
 endif()
-
-

paddle/api/PaddleAPIPrivate.h

@@ -65,4 +65,3 @@ struct ArgumentsPrivate {
     return *(std::shared_ptr<T>*)(rawPtr);
   }
 };
-

paddle/api/test/testMatrix.py

@@ -69,8 +69,8 @@ class TestMatrix(unittest.TestCase):
     def test_numpy(self):
         numpy_mat = np.matrix([[1, 2], [3, 4], [5, 6]], dtype="float32")
         m = swig_paddle.Matrix.createCpuDenseFromNumpy(numpy_mat)
-        self.assertEqual(
-            (int(m.getHeight()), int(m.getWidth())), numpy_mat.shape)
+        self.assertEqual((int(m.getHeight()), int(m.getWidth())),
+                         numpy_mat.shape)
 
         # the numpy matrix and paddle matrix shared the same memory.
         numpy_mat[0, 1] = 342.23

paddle/cuda/include/hl_base.h

@@ -254,4 +254,3 @@ extern __thread cudaStream_t default_stream;
 #endif  /* __NVCC__ */
 
 #endif  /* HL_BASE_H_ */
-

paddle/cuda/include/stub/hl_cuda_cudnn_stub.h

@@ -199,4 +199,3 @@ inline void hl_batch_norm_backward(hl_tensor_descriptor inputDesc,
                                    real *savedInvVar) {}
 
 #endif  // HL_CUDA_CUDNN_STUB_H_
-

paddle/cuda/src/avx_mathfun.h

@@ -718,4 +718,3 @@ void sincos256_ps(v8sf x, v8sf *s, v8sf *c) {
   *s = _mm256_xor_ps(xmm1, sign_bit_sin);
   *c = _mm256_xor_ps(xmm2, sign_bit_cos);
 }
-

paddle/gserver/layers/FullyConnectedLayer.h

@@ -48,4 +48,3 @@ public:
 };
 
 }  // namespace paddle
-

paddle/math/MathFunctions.h

@@ -80,4 +80,3 @@ void vTanh(const int n, const T* a, T* r);
 }  // namespace paddle
 
 #endif  // MATHFUNCTIONS_H_
-

paddle/scripts/deb/build_scripts/build.sh

@@ -33,5 +33,3 @@ cmake .. -DWITH_GPU=ON -DWITH_SWIG_PY=ON -DWITH_AVX=OFF -DCUDNN_ROOT=/usr/
 make -j `nproc`
 cpack -D CPACK_GENERATOR='DEB' ..
 mv *.deb ~/dist/gpu-noavx
-
-

paddle/scripts/docker/generate.sh

@@ -58,4 +58,3 @@ m4 -DPADDLE_WITH_GPU=ON -DPADDLE_IS_DEVEL=ON -DPADDLE_WITH_DEMO=ON \
    -DPADDLE_BASE_IMAGE=nvidia/cuda:7.5-cudnn5-devel-ubuntu14.04 \
    -DPADDLE_WITH_AVX=OFF \
    Dockerfile.m4 > Dockerfile.gpu-noavx-demo
-

paddle/scripts/travis/common.sh

@@ -2,4 +2,3 @@
 set -e
 mkdir -p ../../../build
 cd ../../../build
-

paddle/trainer/tests/test.txt

@@ -998,4 +998,3 @@ from IN B-PP
 Friday NNP B-NP
 's POS B-NP
 Tokyo NNP I-NP
-

paddle/trainer/tests/train.txt

@@ -4998,4 +4998,3 @@ However RB B-ADVP
 the DT B-NP
 disclosure NN I-NP
 of IN B-PP
-

paddle/utils/tests/test_CommandLineParser.cpp

@@ -109,4 +109,3 @@ int main(int argc, char** argv) {
 }
 
 #endif
-

python/paddle/trainer/config_parser.py

@@ -410,8 +410,8 @@ def RecurrentLayerGroupEnd(name):
                   "RecurrentLayerGroup not begin")
     for pair in g_current_submodel.memories:  #check exist
         layer = g_layer_map[pair.layer_name]
-        config_assert(layer is not None, "memory declare wrong name:%s" %
-                      pair.layer_name)
+        config_assert(layer is not None,
+                      "memory declare wrong name:%s" % pair.layer_name)
         memory_link = g_layer_map[pair.link_name]
         config_assert(layer.size == memory_link.size,
                       "memory declare wrong size:%d" % memory_link.size)
@@ -686,8 +686,8 @@ class ConvProjection(Projection):
         parse_conv(conv_conf, input_layer_name, self.proj_conf.conv_conf,
                    num_filters)
         # TODO: support rectangle input
-        self.proj_conf.output_size = (self.proj_conf.conv_conf.output_x**
-                                      2) * num_filters
+        self.proj_conf.output_size = (self.proj_conf.conv_conf.output_x
+                                      **2) * num_filters
 
     def calc_output_size(self, input_layer_config):
         return self.proj_conf.output_size
@@ -2793,8 +2793,8 @@ class ConcatenateLayer2(LayerBase):
 @config_layer('recurrent')
 class RecurrentLayer(LayerBase):
     def __init__(self, name, inputs, reversed=False, bias=True, **xargs):
-        super(RecurrentLayer, self).__init__(name, 'recurrent', 0, inputs, **
-                                             xargs)
+        super(RecurrentLayer, self).__init__(name, 'recurrent', 0, inputs,
+                                             **xargs)
         config_assert(len(self.inputs) == 1, 'RecurrentLayer must have 1 input')
         input_layer = self.get_input_layer(0)
         size = input_layer.size
@@ -2876,22 +2876,22 @@ class MDLstmLayer(LayerBase):
                  active_state_type="sigmoid",
                  bias=True,
                  **xargs):
-        super(MDLstmLayer, self).__init__(name, 'mdlstmemory', 0, inputs, **
-                                          xargs)
+        super(MDLstmLayer, self).__init__(name, 'mdlstmemory', 0, inputs,
+                                          **xargs)
         config_assert(len(self.inputs) == 1, 'MDLstmLayer must have 1 input')
         input_layer = self.get_input_layer(0)
         dim_num = len(directions)
         #check input_layer.size is divided by (3+dim_num)
-        config_assert(input_layer.size %
-                      (3 + dim_num) == 0, "size % (dim_num) should be 0!")
+        config_assert(input_layer.size % (3 + dim_num) == 0,
+                      "size % (dim_num) should be 0!")
         size = input_layer.size / (3 + dim_num)
         self.set_layer_size(size)
         self.config.active_gate_type = active_gate_type
         self.config.active_state_type = active_state_type
         for i in xrange(len(directions)):
             self.config.directions.append(int(directions[i]))
-        self.create_input_parameter(0, size * size *
-                                    (3 + dim_num), [size, size, 3 + dim_num])
+        self.create_input_parameter(0, size * size * (3 + dim_num),
+                                    [size, size, 3 + dim_num])
         #bias includes 3 kinds of peephole, 3+dim_num+2+dim_num
         self.create_bias_parameter(bias, size * (5 + 2 * dim_num))
 
@@ -2929,8 +2929,8 @@ class GruStepLayer(LayerBase):
                  active_gate_type="sigmoid",
                  bias=True,
                  **xargs):
-        super(GruStepLayer, self).__init__(name, 'gru_step', size, inputs, **
-                                           xargs)
+        super(GruStepLayer, self).__init__(name, 'gru_step', size, inputs,
+                                           **xargs)
         config_assert(len(self.inputs) == 2, 'GruStepLayer must have 2 input')
         input_layer0 = self.get_input_layer(0)
         input_layer1 = self.get_input_layer(1)