Fix typos

CMakeLists.txt

@@ -105,7 +105,7 @@ option(BUILD_Z5PY "Build z5 python bindings" ON)
 # Include gtest submodule
 ###############################
 
-# NOTE I tried to replace thhis with the conda package and
+# NOTE I tried to replace this with the conda package and
 # use find_pacakge(GTest), but although CMake could find the
 # libraries, this led to horrible linker errors
 if(BUILD_TESTS)

README.md

@@ -165,7 +165,7 @@ int main() {
   // get handle to a File on the filesystem
   z5::filesystem::handle::File f("data.zr");
   // if you wanted to use a different backend, for example AWS, you
-  // would need to use this insetead:
+  // would need to use this instead:
   // z5::s3::handle::File f;
 
   // create the file in zarr format

include/z5/common.hxx

@@ -8,8 +8,8 @@
 // include boost::filesystem or std::filesystem header
 // and define the namespace fs
 #ifdef WITH_BOOST_FS
-    #ifndef BOOST_FILESYSTEM_NO_DEPERECATED
-        #define BOOST_FILESYSTEM_NO_DEPERECATED
+    #ifndef BOOST_FILESYSTEM_NO_DEPRECATED
+        #define BOOST_FILESYSTEM_NO_DEPRECATED
     #endif
     #include <boost/filesystem.hpp>
     #include <boost/filesystem/fstream.hpp>

include/z5/filesystem/metadata.hxx

@@ -55,7 +55,7 @@ namespace metadata_detail {
             j["zarr_format"] = metadata.zarrFormat;
         } else {
             // n5 stores attributes and metadata in the same file,
-            // so we need to make sure that we don't ovewrite attributes
+            // so we need to make sure that we don't overwrite attributes
             try {
                 readAttributes(handle, j);
             } catch(std::runtime_error) {}  // read attributes throws RE if there are no attributes, we can just ignore this

include/z5/handle.hxx

@@ -8,7 +8,7 @@
 namespace z5 {
 namespace handle {
 
-    // TODO this should go into docstrings and then a documnetation should be generated from them
+    // TODO this should go into docstrings and then a documentation should be generated from them
     // (using doxygen?!)
     /*
      * This header includes the base classes for the z5 handle objects.

include/z5/metadata.hxx

@@ -220,7 +220,7 @@ namespace z5 {
         types::ShapeType shape;
         types::ShapeType chunkShape;
 
-        // compressor name and opyions
+        // compressor name and options
         types::Compressor compressor;
         types::CompressionOptions compressionOptions;
 

include/z5/multiarray/xtensor_access.hxx

@@ -68,7 +68,7 @@ namespace multiarray {
             chunkSize = std::accumulate(chunkShape.begin(), chunkShape.end(),
                                         1, std::multiplies<std::size_t>());
 
-            // read the data from storge
+            // read the data from storage
             std::vector<char> dataBuffer;
             ds.readRawChunk(chunkId, dataBuffer);
 

include/z5/multiarray/xtensor_util.hxx

@@ -43,10 +43,10 @@ namespace multiarray {
 
     template<typename T, typename VIEW, typename SHAPE_TYPE>
     inline void copyBufferToViewND(const std::vector<T> & buffer,
-                                   xt::xexpression<VIEW> & viewExperession,
+                                   xt::xexpression<VIEW> & viewExpression,
                                    const SHAPE_TYPE & arrayStrides) {
         // get the view into the out array and the number of dimension
-        auto & view = viewExperession.derived_cast();
+        auto & view = viewExpression.derived_cast();
         const std::size_t dim = view.dimension();
         // buffer size and view shape
         const std::size_t bufSize = buffer.size();
@@ -66,7 +66,7 @@ namespace multiarray {
         // we start the outer loop at the second from last dimension
         // (last dimension is the fastest moving and consecutive in memory)
         for(int d = dim - 2; d >= 0;) {
-            // copy the piece of buffer that is consectuve to our view
+            // copy the piece of buffer that is consecutive to our view
             std::copy(buffer.begin() + bufferOffset,
                       buffer.begin() + bufferOffset + memLen,
                       &view(0) + viewOffset);
@@ -127,26 +127,26 @@ namespace multiarray {
     // TODO this only works for row-major (C) memory layout
     template<typename T, typename VIEW, typename SHAPE_TYPE>
     inline void copyBufferToView(const std::vector<T> & buffer,
-                                 xt::xexpression<VIEW> & viewExperession,
+                                 xt::xexpression<VIEW> & viewExpression,
                                  const SHAPE_TYPE & arrayStrides) {
-        auto & view = viewExperession.derived_cast();
+        auto & view = viewExpression.derived_cast();
         // ND impl doesn't work for 1D
         if(view.dimension() == 1) {
             // std::copy(buffer.begin(), buffer.end(), view.begin());
             const auto bufferView = xt::adapt(buffer, view.shape());
             view = bufferView;
         } else {
-            copyBufferToViewND(buffer, viewExperession, arrayStrides);
+            copyBufferToViewND(buffer, viewExpression, arrayStrides);
         }
     }
 
 
     template<typename T, typename VIEW, typename SHAPE_TYPE>
-    inline void copyViewToBufferND(const xt::xexpression<VIEW> & viewExperession,
+    inline void copyViewToBufferND(const xt::xexpression<VIEW> & viewExpression,
                                   std::vector<T> & buffer,
                                   const SHAPE_TYPE & arrayStrides) {
         // get the view into the out array and the number of dimension
-        const auto & view = viewExperession.derived_cast();
+        const auto & view = viewExpression.derived_cast();
         const std::size_t dim = view.dimension();
         // buffer size and view shape
         const std::size_t bufSize = buffer.size();
@@ -166,7 +166,7 @@ namespace multiarray {
         // we start the outer loop at the second from last dimension
         // (last dimension is the fastest moving and consecutive in memory)
         for(int d = dim - 2; d >= 0;) {
-            // copy the piece of buffer that is consectuve to our view
+            // copy the piece of buffer that is consecutive to our view
             std::copy(&view(0) + viewOffset,
                       &view(0) + viewOffset + memLen,
                       buffer.begin() + bufferOffset);
@@ -226,18 +226,18 @@ namespace multiarray {
 
     // TODO this only works for row-major (C) memory layout
     template<typename T, typename VIEW, typename SHAPE_TYPE>
-    inline void copyViewToBuffer(const xt::xexpression<VIEW> & viewExperession,
+    inline void copyViewToBuffer(const xt::xexpression<VIEW> & viewExpression,
                                  std::vector<T> & buffer,
                                  const SHAPE_TYPE & arrayStrides) {
-        const auto & view = viewExperession.derived_cast();
+        const auto & view = viewExpression.derived_cast();
         // can't use the ND implementation in 1d, hence we resort to xtensor
         // which should be fine in 1D
         if(view.dimension() == 1) {
             // std::copy(view.begin(), view.end(), buffer.begin());
             auto bufferView = xt::adapt(buffer, view.shape());
             bufferView = view;
         } else {
-            copyViewToBufferND(viewExperession, buffer, arrayStrides);
+            copyViewToBufferND(viewExpression, buffer, arrayStrides);
         }
     }
 

include/z5/util/file_mode.hxx

@@ -7,7 +7,7 @@ namespace z5 {
 
     class FileMode {
     public:
-        // the inidividual options
+        // the individual options
         static const char can_write = 1;
         static const char can_create = 2;
         static const char must_not_exist = 4;

include/z5/util/functions.hxx

@@ -67,7 +67,7 @@ namespace util {
 
 
     // TODO add option to ignore fill value
-    // TODO maybe it would be benefitial to have intermediate unordered sets
+    // TODO maybe it would be beneficial to have intermediate unordered sets
     template<class T>
     void unique(const Dataset & dataset, const int nThreads, std::set<T> & uniques) {
 
@@ -101,7 +101,7 @@ namespace util {
 
 
     // TODO add option to ignore fill value
-    // TODO maybe it would be benefitial to have intermediate unordered maps
+    // TODO maybe it would be beneficial to have intermediate unordered maps
     template<class T>
     void uniqueWithCounts(const Dataset & dataset, const int nThreads, std::map<T, size_t> & uniques) {
         // allocate the per thread data

include/z5/util/threadpool.hxx

@@ -459,7 +459,7 @@ inline void parallel_foreach_impl(
 }
 
 // Runs foreach on a single thread.
-// Used for API compatibility when the numbe of threads is 0.
+// Used for API compatibility when the number of threads is 0.
 template<class ITER, class F>
 inline void parallel_foreach_single_thread(
     ITER begin,

src/bench/bench_python/bench.py

@@ -317,4 +317,4 @@ def main(path, name=None, save_folder='./tmp_files', iterations=5, compressors=N
     parser.add_argument('--iterations', '-i', default=5)
 
     args = parser.parse_args()
-    main(args.path, args.name, args.save_folder, args.iterstions)
+    main(args.path, args.name, args.save_folder, args.iterations)

src/python/CMakeLists.txt

@@ -60,7 +60,7 @@ macro(addPythonModule)
 
     set(options "")
     set(oneValueArgs NESTED_NAME)
-    set(multiValueArgs SOURCES LIBRRARIES)
+    set(multiValueArgs SOURCES LIBRARIES)
     cmake_parse_arguments(ADD_PY_MOD "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN} )
 
     # get name of the module
@@ -84,7 +84,7 @@ macro(addPythonModule)
     # link additional libraries
     target_link_libraries(_${MODULE_NAME}
         PUBLIC
-        ${ADD_PY_MOD_LIBRRARIES}
+        ${ADD_PY_MOD_LIBRARIES}
     )
 
     IF(${CMAKE_SYSTEM_NAME} MATCHES "Darwin")

src/python/lib/CMakeLists.txt

@@ -8,7 +8,7 @@ addPythonModule(
         factory.cxx
         handles.cxx
         util.cxx
-    LIBRRARIES
+    LIBRARIES
         ${COMPRESSION_LIBRARIES} 
         ${FILESYSTEM_LIBRARIES}
         ${CLOUD_LIBRARIES}

src/python/lib/dataset.cxx

@@ -196,7 +196,7 @@ namespace z5 {
                     try {
                         path = ds.path().string();
                     } catch(...) {
-                        throw std::runtime_error("Can only picke filesystem datasets");
+                        throw std::runtime_error("Can only pick filesystem datasets");
                     }
                     return py::make_tuple(path, ds.mode().mode());
                 },

src/python/module/z5py/converter.py

@@ -29,7 +29,7 @@ def convert_to_h5(in_path, out_path,
                       fit_to_roi=False, **h5_kwargs):
         """ Convert n5 ot zarr dataset to hdf5 dataset.
 
-        The chunks of the output dataset must be spcified.
+        The chunks of the output dataset must be specified.
         The dataset is converted to hdf5 in parallel over the chunks.
         Note that hdf5 does not support parallel write access, so more threads
         may not speed up the conversion.

src/python/module/z5py/dataset.py

@@ -54,7 +54,7 @@ def __init__(self, dset_impl, handle, parent, name, n_threads=1):
     def __array__(self, dtype=None):
         """ Create a numpy array containing the whole dataset.
 
-        NOTE: Datasets are not interchangeble with arrays!
+        NOTE: Datasets are not interchangeable with arrays!
         Every time this method is called the whole dataset is loaded into memory!
         """
         arr = self[...]
@@ -409,7 +409,7 @@ def read_direct(self, dest, source_sel=None, dest_sel=None):
             dest (array) destination object into which the read data is written to.
             dest_sel (slice array) selection of data to write to ``dest``. Defaults to the whole range of ``dest``.
             source_sel (slice array) selection in dataset to read from. Defaults to the whole range of the dataset.
-        Spaces, defined by ``source_sel`` and ``dest_sel`` must be in the same size but dont need to have the same
+        Spaces, defined by ``source_sel`` and ``dest_sel`` must be in the same size but don't need to have the same
         offset
         """
         if source_sel is None:
@@ -428,7 +428,7 @@ def write_direct(self, source, source_sel=None, dest_sel=None):
             source_sel (slice array) selection of data to write from ``source``. Defaults to the whole range of
             ``source``.
             dest_sel (slice array) selection in dataset to write to. Defaults to the whole range of the dataset.
-        Spaces, defined by ``source_sel`` and ``dest_sel`` must be in the same size but dont need to have the same
+        Spaces, defined by ``source_sel`` and ``dest_sel`` must be in the same size but don't need to have the same
         offset
         """
         if dest_sel is None:

src/python/module/z5py/shape_utils.py

@@ -69,7 +69,7 @@ def rectify_shape(arr, required_shape):
     important_shape = tuple(important_shape)
 
     msg = ('could not broadcast input array from shape {} into shape {}; '
-           'complicated broacasting not supported').format(arr.shape, required_shape)
+           'complicated broadcasting not supported').format(arr.shape, required_shape)
 
     if len(important_shape) > len(required_shape):
         raise ValueError(msg)

src/python/module/z5py/util.py

@@ -127,7 +127,7 @@ def copy_dataset_impl(f_in, f_out, in_path_in_file, out_path_in_file,
     else:
         compression_opts = {'compression_opts': None} if compression_opts is None else compression_opts
 
-    # if we don't have block-shape explitictly given, use chunk size
+    # if we don't have block-shape explicitly given, use chunk size
     # otherwise check that it's a multiple of chunks
     if block_shape is None:
         block_shape = chunks

src/python/test/test_s3.py

@@ -36,7 +36,7 @@ def make_test_data(bucket_name=None):
         if bucket_name is None:
             bucket_name = TestS3.bucket_name
 
-        # access the s3 filesysyem
+        # access the s3 filesystem
         fs = s3fs.S3FileSystem(anon=False)
         store = s3fs.S3Map(root=bucket_name, s3=fs)
 

src/test/multiarray/test_broadcast.cxx

@@ -47,7 +47,7 @@ namespace multiarray {
             ArrayShape arrayShape(shape.begin(), shape.end());
             const T val = 42;
 
-            // write scalcar and load for completely overlapping array consisting of 8 chunks
+            // write scalar and load for completely overlapping array consisting of 8 chunks
             {
                 ArrayShape offset({0, 0, 0});
                 ArrayShape subShape({20, 20, 20});

src/test/test_n5/n5_java/src/main/java/zarr_pp/n5/App2.java

@@ -102,7 +102,7 @@
 //                         assert floatData[i] == 42.;
 //                     }
 //                     
-//                     // test the doubl block
+//                     // test the double block
 //                     final DataBlock<?> loadedDouble = n5.readBlock(doubleSetRaw, attrsDouble, new long[]{x, y, z});
 //                     final double[] doubleData = (double[]) loadedDouble.getData();
 //                     for(int i = 0; i < doubleData.length; i++) {