bump pip package version 1.0.2

* tdm_termite.cpp: explicit cast to unsigned int

.gitignore

@@ -12,3 +12,14 @@ tdmripper
 tdmreaper
 cython/*.cpp
 tdmtermite
+dist/
+*.egg-info/
+output/
+monitor-process.sh
+tdmtest
+pip/*.hpp
+pip/*.md
+pip/*.cpp
+pip/*.pyx
+pip/*.pxd
+pip/LICENSE

Dockerfile

@@ -1,20 +1,30 @@
 
-FROM debian:bullseye-20210111
+FROM debian:bullseye 
 
-USER root
+# install requirements
-
+RUN apt-get update && apt-get upgrade -y && apt-get install -y \
-RUN apt-get update && apt-get install -y \
+    build-essential \
-    build-essential git \
+    g++ make git \
     python3 python3-pip
 
-RUN g++ -v
+# check compiler and current user
+RUN g++ -v && whoami
 
-COPY ./ /tdm_ripper/
+# use /home as working directory
+WORKDIR /home
+
+# get the public TDMtermite repository
+RUN git clone https://github.com/RecordEvolution/TDMtermite.git
 
 # install CLI tool
-RUN cd /tdm_ripper && ls -lh && make install && ls -lh /usr/local/bin/tdmreaper
+RUN cd ./TDMtermite && ls -lh && make install && ls -lh /usr/local/bin/tdmtermite
 
 # install Python module
-RUN cd /tdm_ripper && ls -lh && make cython-requirements && make cython-install
+RUN cd ./TDMtermite && ls -lh && make cython-requirements && make cython-list && make cython-install
+
+# create directory for data exchange
+#RUN [ "/bin/bash", "-c", "mkdir -pv data/{input,output}" ]
+RUN mkdir -pv data
+
+CMD ["sleep","infinity"]
 
-CMD ["sleep","inifity"]

README.md

@@ -1,21 +1,21 @@
 
-<p align="center">
+[![Total alerts](https://img.shields.io/lgtm/alerts/g/RecordEvolution/TDMtermite.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/RecordEvolution/TDMtermite/alerts/)
-  <a href="https://github.com/RecordEvolution/tdm_ripper.git">
+[![Language grade: C/C++](https://img.shields.io/lgtm/grade/cpp/g/RecordEvolution/TDMtermite.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/RecordEvolution/TDMtermite/context:cpp)
-    <img
+[![Language grade: Python](https://img.shields.io/lgtm/grade/python/g/RecordEvolution/TDMtermite.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/RecordEvolution/TDMtermite/context:python)
-      alt="tdmtermite.svg"
+[![LICENSE](https://img.shields.io/github/license/RecordEvolution/TDMtermite)](https://img.shields.io/github/license/RecordEvolution/TDMtermite)
-      src="assets/tdmtermite.svg"
+[![STARS](https://img.shields.io/github/stars/RecordEvolution/TDMtermite)](https://img.shields.io/github/stars/RecordEvolution/TDMtermite)
-      width="400"
-    />
-  </a>
-</p>
 
-_TDMtermite_ is a C++ based library that decodes (encodes) the proprietary
+# TDMtermite
-file format _TDM/TDX_ for measurement data, which relies upon the
+
-_technical data management_ data model. The TDM format was introduced by
+_TDMtermite_ is a C++ based library that decodes the proprietary
-[National Instruments](https://www.ni.com) and is employed by
+file format _TDM/TDX_ for measurement data. First introduced by
+[National Instruments](https://www.ni.com), the TDM format relies on the
+_technical data management_ data model and is employed by
 [LabVIEW](https://www.ni.com/de-de/shop/labview.html), LabWindows™/CVI™,
 Measurement Studio, SignalExpress, and [DIAdem](https://www.ni.com/de-de/shop/data-acquisition-and-control/application-software-for-data-acquisition-and-control-category/what-is-diadem.html).
 
+The [Record Evolution Platform](https://www.record-evolution.de/en/home-en/) uses TDMtermite to integrate measurement data into ETL processes. The TDMtermite library is available both as a command line tool and as a Python module. The Python module of TDMtermite enables data scientists to conveniently include TDM formats in their existing data pipelines by providing access to both raw data and metadata in terms of native Python objects.    
+
 ## Overview
 
 * [TDM file format](#Dataformat)
@@ -25,18 +25,18 @@ Measurement Studio, SignalExpress, and [DIAdem](https://www.ni.com/de-de/shop/da
 
 ## Dataformat
 
-Datasets encoded in the TDM/TDX format come along in pairs comprised of a
+Datasets encoded in the TDM/TDX format come in pairs comprised of a
-.tdm (header) and a .tdx (data) file. While the .tdm file is a human-readable
+.tdm (header) file and a .tdx (data) file. While the .tdm file is a human-readable
-file providing meta information about the data set, the .tdx is a binary
+file providing meta information about the dataset, the .tdx file is a binary file
 containing the actual data. The .tdm based on the _technical data management_
-model is an XML file and basically describes what data the .tdx contains and how
+model is an XML file. It describes what data the .tdx file contains and how
 to read it. The
 [TDM data model](https://www.ni.com/de-de/support/documentation/supplemental/10/ni-tdm-data-model.html)
-structures the data hierarchically with respect to _file_, (channel) _groups_ and
+structures the data hierarchically with respect to _file_, _(channel)_ _groups_ and
-_channels_. The file level XML may contain any number of (channel) groups each
+_channels_. The file-level XML may contain any number of (channel) groups, each
 of which is made up of an arbitrary number of channels. Thus, the XML tree in
 the [TDM header file](https://zone.ni.com/reference/de-XX/help/370858P-0113/tdmdatamodel/tdmdatamodel/tdm_headerfile/)
-looks basically like this:
+looks like this:
 
 ```xml
 <?xml version="1.0" encoding="UTF-8" standalone="no" ?>
@@ -67,14 +67,14 @@ looks basically like this:
 </usi:tdm>
 ```
 
-and is comprised of _four_ main XML elements: `usi:documentation`, `usi:model`,
+The XML tree is comprised of _four_ main XML elements: `usi:documentation`, `usi:model`,
 `usi:include` and `usi:data`. The element `usi:include` references the data file
 `example.tdx` and reveals one of _two_ possible orderings of the mass data (.tdx):
 
-1. either _channel wise_ (`<block>`) - all values of a specific channel follow subsequently -
+1. either _channel-wise_ (`<block>`) - all values of a specific channel follow subsequently
-1. or _block wise_ (`<block_bm>`) - all values of a specific measurement time follow subsequently -
+1. or _block-wise_ (`<block_bm>`) - all values of a specific measurement time follow subsequently.
 
-ordering. The supported _numerical data types_ are
+The supported _numerical data types_ are:
 
 | datatype    | channel datatype | numeric | value sequence  | size  | description             |
 |-------------|------------------|---------|-----------------|-------|-------------------------|
@@ -87,10 +87,10 @@ ordering. The supported _numerical data types_ are
 | eFloat64Usi | DT_DOUBLE        | 7       | double_sequence | 8byte | 64 Bit double           |
 | eStringUsi  | DT_STRING        | 1       | string_sequence |       | text                    |
 
-The XML element `<usi:data>` is basically comprised of _five_ different types of
+The XML element `<usi:data>` is comprised of _five_ different types of
 elements that are `<tdm_root>`, `<tdm_channelgroup>`, `<tdm_channel>`, `<localcolumn>`
 and `<submatrix>`. The root element `<tdm_root>` describes the general properties
-of the dataset and lists the _id's_ of all channel groups that belong to
+of the dataset and lists the _ids_ of all channel groups that belong to
 the dataset. The element `<tdm_channelgroup>` divides the _channels_ into groups
 and has a unique _id_ that is referenced by its root element. The `<channels>`
 element in `<tdm_channelgroup>` lists the unique ids of all channels that belong
@@ -110,7 +110,7 @@ actual data including its datatype. The remaining element types are
 </localcolumn>
 ```
 
-with a unique id, the `<measurement_quantity>` refering to one specific channel,
+with a unique id, the `<measurement_quantity>` referring to one specific channel,
 the `<submatrix>` and its id respectively, the type of representation in
 `<sequence_representation>` - being one of _explicit_, _implicit linear_ or
 _rawlinear_ - and the `<values>` element, which refers to one _value sequence_,
@@ -125,49 +125,61 @@ and the element `<submatrix>`
 </submatrix>
 ```
 
-that references the channel group in `<measurement>` it belongs to and provides
+that references the channel group in `<measurement>` to which it belongs and provides
 the _number of rows_ in the channels listed in `<local_columns>`.
 
 ## Installation
 
-The library can be used both as a _CLI_ based tool and as a _Python_ module.
+The library can be used both as a _CLI_-based tool and as a _Python_ module.
 
 ### CLI tool
 
-To install the CLI tool _tdmtermite_ do
+To install the CLI tool _TDMtermite_, do
 
 ```Shell
 make install
 ```
 
-which uses `/usr/local/bin` as installation directory. On _macOSX_ please first
+which uses `/usr/local/bin` as an installation directory. On _macOSX_, please first
 build the binary locally with `make` and install it in your preferred location.
 
 ### Python
 
-In order to build a _Python module_ from the _C++_ code base the
+In order to build a _Python module_ from the _C++_ code base, the
 [Cython](https://cython.readthedocs.io/en/latest/index.html) package must be
-available, which may be installed via `python3 -m pip install cython` .
+available. It may be installed via `python3 -m pip install cython` .
-Furthermore, the [Numpy](https://numpy.org) package is recommended to be able
+The [Numpy](https://numpy.org) package is recommended
 to pass arrays of data from the C++ kernel to Python. The _makefile_ provides
 the target `make cython-requirements` to install all required Python modules.
-Finally, to build the Python extension _tdm_termite_ either locally or install
+Finally, to build the Python extension _tdm_termite_ locally or install
-it the targets `make cython-build` and `make cython-install` are provided.
+it, the targets `make cython-build` and `make cython-install` are provided.
-Hence, to install the Python module on the system simply do
+To install the Python module on the system, simply do
 
 ```Shell
 make cython-requirements
 make cython-install
 ```
 
-that makes the module available to be imported as `import tdm_termite` .
+That makes the module available for import as a `import tdm_termite` .
+
+#### Installation with pip
+
+The package is also available via the [Python Package Index](https://pypi.org) at 
+[TDMtermite](https://pypi.org/project/TDMtermite/). To install the latest version simply do
+
+```Shell
+python3 -m pip install TDMtermite
+```
+
+Note, that _python3_setuptools_ and _gcc version >= 10.2.0_ are required to 
+successfully install and use it. 
 
 ## Usage
 
 ### CLI tool
 
 The usage of the CLI tool is sufficiently clarified by its help message displayed
-by `tdmtermite --help`. For instance, to extract the data decoded in the pair of
+by `tdmtermite --help`. To extract the data decoded in the pair of
 files `samples/SineData.tdm` and `samples/SineData.tdx` into the directory
 `/home/jack/data/`:
 
@@ -176,7 +188,7 @@ tdmtermite samples/SineData.tdm samples/SineData.tdx --output /home/jack/data
 ```
 
 The tool can also be used to list the available objects in the TDM dataset, which
-are i.a. _channels_, _channelgroups_ and TDX _blocks_. For instance, to list
+are i.a. _channels_, _channelgroups_ and TDX _blocks_. To list
 all channels and channelgroups (without writing any file output):
 
 ```Shell
@@ -184,37 +196,37 @@ tdmtermite samples/SineData.tdm samples/SineData.tdx --listgroups --listchannels
 ```
 
 The user may also submit a _filenaming rule_ to control the names of the files the
-channel(-group)s are written to. To this end, the _magic flags_ `%G` `%g`, `%C`
+channel(group)s are written to. To this end, the _magic flags_ `%G` `%g`, `%C`
 and `%c` representing the group id, group name, channel index and channel name
-are defined. The default filenaming option is
+are defined. The default filenaming option is:
 
 ```Shell
 tdmtermite samples/SineData.tdm samples/SineData.tdx --output /home/jack/data --filenames channelgroup_%G.csv
 ```
 
-which makes the tool write _all channels_ grouped into files according to their
+This makes the tool write _all channels_ grouped into files according to their
-group association, while all channelgroup filenames obey the pattern `channelgroup_%G.csv`
+group association, while all channelgroup filenames obey the pattern `channelgroup_%G.csv`,
 with `%G` being replaced by the group id. The filenaming rule also enables the user
-to extract only a single channel(group) by providing a particular channel(-group)
+to extract only a single channel(group) by providing a particular channel(group)
 id in the filenaming flag. For example,
 
 ```Shell
 tdmtermite samples/SineData.tdm samples/SineData.tdx --output /home/jack/data -f channel_usi16_%c.csv --includemeta
 ```
 
-will write the single channel with id `usi16` to the file
+This will write the single channel with the id `usi16` to the file
-`/home/jack/data/channel_usi16_A4.csv` including its meta-data as a file header.
+`/home/jack/data/channel_usi16_A4.csv`, including its meta-data as a file header.
 
 ### Python
 
-To be able to use the Python module _tdm_termite_ it first has to be build locally
+To be able to use the Python module _tdm_termite_, it first has to be built locally
-or installed on the system. In the Python interpreter simply do:
+or installed on the system. In the Python interpreter, simply do:
 
 ```Python
 import tdm_termite
 ```
 
-to import the module. The TDM files are provided by creating an instance of
+This will import the module. The TDM files are provided by creating an instance of
 the _tdm_termite_ class:
 
 ```Python
@@ -225,7 +237,7 @@ except RuntimeError as e:
     print("failed to load/decode TDM files: " + str(e))
 ```
 
-After initializing the _tdm_termite_ object it can be used to extract any of the
+After initializing the _tdm_termite_ object, it can be used to extract any of the
 available data. For instance, to list the included channelgroups and channels:
 
 ```Python
@@ -237,7 +249,7 @@ grpids = jack.get_channelgroup_ids()
 chnids = jack.get_channel_ids()
 ```
 
-As a use case, we have look at listing the ids of all channelgroups and printing
+As a use case, we have a look at listing the ids of all channelgroups and printing
 their data to separate files:
 
 ```Python
@@ -274,7 +286,7 @@ for grp in grpids :
         print("failed to print channelgroup: " + str(grp) + " : " + str(e))
 ```
 
-For a full example including more details see the [extensive example](python/usage.py)
+For details, see this [extensive example](python/usage.py)
 and the absolute minimal example [minimal usage](python/minimal.py). In order
 to simply extract all data of the TDM datatset and dump it to files in a given
 (existing!) directory, do
@@ -285,8 +297,8 @@ jack = tdm_termite.tdmtermite(b'samples/SineData.tdm',b'samples/SineData.tdx')
 jack.write_all(b"./my_tdm_data_directory/")
 ```
 
-The interface allows to construct customized file/column headers from any
+The interface allows you to construct customized file/column headers from any
-meta-data and provide these headers for usage in file output (see the
+meta-data and provide these headers for usage in file output (see this
 [example](python/custom.py)).
 
 ## References
@@ -308,6 +320,30 @@ meta-data and provide these headers for usage in file output (see the
 
 ### Implementation
 
+- https://en.cppreference.com/w/
 - https://pugixml.org/
 - https://github.com/zeux/pugixml
 - https://cython.readthedocs.io/en/latest/src/userguide/wrapping_CPlusPlus.html
+
+### Packaging
+
+#### Documentation
+
+- https://packaging.python.org/tutorials/packaging-projects/
+- https://setuptools.readthedocs.io/en/latest/userguide/declarative_config.html
+- https://test.pypi.org/account/register/
+- https://github.com/pypa/auditwheel
+- https://github.com/pypa/python-manylinux-demo
+- https://github.com/pypa/manylinux
+
+#### C/C++ Extensions
+
+- https://docs.python.org/3/extending/building.html
+
+#### Articles
+
+- https://martinsosic.com/development/2016/02/08/wrapping-c-library-as-python-module.html
+- https://malramsay.com/post/perils-of-packaging/
+- https://github.com/neuronsimulator/nrn/issues/329
+- https://levelup.gitconnected.com/how-to-deploy-a-cython-package-to-pypi-8217a6581f09
+- https://medium.com/swlh/distributing-python-packages-protected-with-cython-40fc29d84caf

assets/index.html

@@ -0,0 +1,55 @@
+
+<html>
+
+<head>
+
+  <title>TDMtermite</title>
+  <style>
+  </style>
+
+</head>
+
+<body>
+
+  <p align="center">
+    <a href="https://github.com/RecordEvolution/TDMtermite.git">
+      <img alt="tdmtermite.svg"
+           src="assets/tdmtermite.svg"
+           width="400"
+      />
+    </a>
+  </p>
+
+  <div style="width: 100%; display: block; margin-left: 28%; margin-right: 28%;">
+
+  <div style="width: 100%; overflow: hidden;">
+
+    <div style="margin: 5px; float: left;">
+      <a href="https://lgtm.com/projects/g/RecordEvolution/TDMtermite/alerts/">
+        <img alt="Total alerts" 
+             src="https://img.shields.io/lgtm/alerts/g/RecordEvolution/TDMtermite.svg?logo=lgtm&logoWidth=18"/>
+      </a>
+    </div>
+
+    <div style="margin: 5px; float: left;">
+      <a href="https://lgtm.com/projects/g/RecordEvolution/TDMtermite/context:cpp">
+        <img alt="Language grade: C/C++" 
+             src="https://img.shields.io/lgtm/grade/cpp/g/RecordEvolution/TDMtermite.svg?logo=lgtm&logoWidth=18"/>
+      </a>
+    </div>
+
+    <div style="margin: 5px; float: left;">
+      <a href="https://lgtm.com/projects/g/RecordEvolution/TDMtermite/context:python">
+        <img alt="Language grade: Python" 
+             src="https://img.shields.io/lgtm/grade/python/g/RecordEvolution/TDMtermite.svg?logo=lgtm&logoWidth=18"/>
+      </a>
+    </div>
+
+  </div>
+  
+  </div>
+
+</body>
+
+</html>
+

cython/setup.py

@@ -1,24 +1,47 @@
 from distutils.core import setup
 from distutils.extension import Extension
 from Cython.Build import cythonize
+import os
+import sys
+
+print("building on platform: "+sys.platform)
+os.system("git tag > gittags.log")
+with open ("gittags.log","r") as gt:
+    taglst = gt.readlines()
+os.remove("gittags.log")
+if len(taglst) > 0 :
+    version = taglst[-1].replace('\n','').replace('v','')
+else:
+    version = 'unkown'
+print("building version: "+version)
+
+if sys.platform == "linux" or sys.platform == "darwin" :
+	cmpargs = ['-std=c++17','-Wno-unused-variable']
+	lnkargs = ['-std=c++17','-Wno-unused-variable']
+elif sys.platform == "win32" :
+	cmpargs = ['/EHsc','/std:c++17']
+	lnkargs = []
+else :
+	raise RuntimeError("unknown platform") 
 
 extensions = Extension(
     name="tdm_termite",
     sources=["cython/py_tdm_termite.pyx"],
     # libraries=[""],
     # library_dirs=["lib"],
-    include_dirs=["lib","pugixml"],
+    include_dirs=["lib","3rdparty/pugixml"],
     language='c++',
-    extra_compile_args=['-std=c++17','-Wno-unused-variable'],
+    #extra_compile_args=['-std=c++17','-Wno-unused-variable'],
-    extra_link_args=['-std=c++17'],
+    extra_compile_args= cmpargs,
+    extra_link_args= lnkargs,
 )
 
 setup(
-    version='0.1',
+    version=version,
     description='TDMtermite cython extension',
     author='Record Evolution GmbH',
     author_email='mario.fink@record-evolution.de',
-    url='https://github.com/RecordEvolution/tdm_ripper.git',
+    url='https://github.com/RecordEvolution/TDMtermite.git',
     name="tdm_termite",
     ext_modules=cythonize(extensions)
 )

lib/tdm_datatype.hpp

@@ -17,6 +17,7 @@ typedef double eFloat64Usi;
 
 class tdmdatatype
 {
+
 protected:
   eInt16Usi sint16_;    // 0
   eInt32Usi sint32_;    // 1
@@ -26,6 +27,7 @@ protected:
   eFloat32Usi float32_; // 5
   eFloat64Usi float64_; // 6
   short int dtidx_;     // \in \{0,...,6\}
+
 public:
   tdmdatatype(): sint16_(0), sint32_(0),
                  uint8_(0), uint16_(0), uint32_(0),
@@ -43,6 +45,19 @@ public:
   // identify type
   short int& dtype() { return dtidx_; }
 
+  // copy constructor
+  tdmdatatype(const tdmdatatype &num)
+  {
+    this->sint16_ = num.sint16_;
+    this->sint32_ = num.sint32_;
+    this->uint8_ = num.uint8_;
+    this->uint16_ = num.uint16_;
+    this->uint32_ = num.uint32_;
+    this->float32_ = num.float32_;
+    this->float64_ = num.float64_;
+    this->dtidx_ = num.dtidx_;
+  }
+
   // overall assignment operator
   tdmdatatype& operator=(const tdmdatatype &num)
   {
@@ -55,6 +70,7 @@ public:
       this->uint32_ = num.uint32_;
       this->float32_ = num.float32_;
       this->float64_ = num.float64_;
+      this->dtidx_ = num.dtidx_;
     }
 
     return *this;

lib/tdm_termite.cpp

@@ -6,16 +6,73 @@
 
 tdm_termite::tdm_termite()
 {
-
+  tdx_ifstream_ = new std::ifstream;
 }
 
 tdm_termite::tdm_termite(std::string tdmfile, std::string tdxfile, bool showlog):
   tdmfile_(tdmfile), tdxfile_(tdxfile)
 {
+  tdx_ifstream_ = new std::ifstream;
+
   // start processing tdm data model
   this->process_tdm(showlog);
 }
 
+tdm_termite::~tdm_termite()
+{
+  // close tdx-file stream and free memory
+  if ( tdx_ifstream_->is_open() ) tdx_ifstream_->close();
+  delete tdx_ifstream_;
+}
+
+tdm_termite::tdm_termite(const tdm_termite& other):
+  tdmfile_(other.tdmfile_), tdxfile_(other.tdxfile_), csvfile_(other.csvfile_),
+  endianness_(other.endianness_), machine_endianness_(other.machine_endianness_),
+  meta_data_(other.meta_data_), tdmdt_name_(other.tdmdt_name_),
+  tdmdt_chan_(other.tdmdt_chan_),
+  tdx_blocks_(other.tdx_blocks_), tdmroot_(other.tdmroot_),
+  tdmchannelgroups_(other.tdmchannelgroups_), tdmchannels_(other.tdmchannels_),
+  tdmchannels_data_(other.tdmchannels_data_), submatrices_(other.submatrices_),
+  localcolumns_(other.localcolumns_), tdxbuffer_(other.tdxbuffer_)
+{
+  tdx_ifstream_ = new std::ifstream;
+  if ( other.tdx_ifstream_->is_open() )
+  {
+    tdx_ifstream_->open(tdxfile_.c_str(),std::ifstream::binary);
+    tdx_ifstream_->seekg(other.tdx_ifstream_->tellg());
+  }
+}
+
+tdm_termite& tdm_termite::operator=(const tdm_termite& other)
+{
+  if ( this != &other )
+  {
+    tdmfile_ = other.tdmfile_;
+    tdxfile_ = other.tdxfile_;
+    csvfile_ = other.csvfile_;
+    endianness_ = other.endianness_;
+    machine_endianness_ = other.machine_endianness_;
+    meta_data_ = other.meta_data_;
+    tdmdt_name_ = other.tdmdt_name_;
+    tdmdt_chan_= other.tdmdt_chan_;
+    tdx_blocks_ = other.tdx_blocks_;
+    tdmroot_ = other.tdmroot_;
+    tdmchannelgroups_ = other.tdmchannelgroups_;
+    tdmchannels_ = other.tdmchannels_;
+    tdmchannels_data_ = other.tdmchannels_data_;
+    submatrices_ = other.submatrices_;
+    localcolumns_ = other.localcolumns_;
+    tdxbuffer_ = other.tdxbuffer_;
+    if ( other.tdx_ifstream_->is_open() )
+    {
+      tdx_ifstream_->open(tdxfile_.c_str(),std::ifstream::binary);
+      tdx_ifstream_->seekg(other.tdx_ifstream_->tellg());
+    }
+  }
+
+  return *this;
+}
+
 void tdm_termite::submit_files(std::string tdmfile, std::string tdxfile, bool showlog)
 {
   // save files
@@ -106,20 +163,26 @@ void tdm_termite::process_tdm(bool showlog)
   this->process_localcolumns(showlog,xml_doc);
 
   // open .tdx and stream all binary data into buffer
+  // try {
+  //   std::ifstream fin(tdxfile_.c_str(),std::ifstream::binary);
+  //   // if ( !fin.good() ) std::cerr<<"failed to open .tdx-file\n";
+  //
+  //   std::vector<unsigned char> tdxbuf((std::istreambuf_iterator<char>(fin)),
+  //                                     (std::istreambuf_iterator<char>()));
+  //   tdxbuffer_ = tdxbuf;
+  //
+  //   if ( showlog ) std::cout<<"size of .tdx buffer (bytes): "<<tdxbuffer_.size()<<"\n\n";
+  //
+  //   // close .tdx file
+  //   fin.close();
+  // } catch (const std::exception& e ) {
+  //   throw std::runtime_error( std::string("failed to open .tdx and stream data to buffer: ")
+  //                             + e.what() );
+  // }
   try {
-    std::ifstream fin(tdxfile_.c_str(),std::ifstream::binary);
+    tdx_ifstream_->open(tdxfile_.c_str(),std::ifstream::binary);
-    // if ( !fin.good() ) std::cerr<<"failed to open .tdx-file\n";
-
-    std::vector<unsigned char> tdxbuf((std::istreambuf_iterator<char>(fin)),
-                                      (std::istreambuf_iterator<char>()));
-    tdxbuffer_ = tdxbuf;
-
-    if ( showlog ) std::cout<<"size of .tdx buffer (bytes): "<<tdxbuffer_.size()<<"\n\n";
-
-    // close .tdx file
-    fin.close();
   } catch (const std::exception& e) {
-    throw std::runtime_error( std::string("failed to open .tdx and stream data to buffer: ")
+    throw std::runtime_error( std::string("failed to open .tdx file in ifstream: ")
                               + e.what() );
   }
 }
@@ -505,7 +568,7 @@ template std::string tdm_termite::get_overview<submatrix>(format formatter);
 template std::string tdm_termite::get_overview<localcolumn>(format formatter);
 template std::string tdm_termite::get_overview<block>(format formatter);
 
-void tdm_termite::summarize_member(tdm_channelgroup chp, std::string& summary, format& formatter)
+void tdm_termite::summarize_member(tdm_channelgroup &chp, std::string& summary, format& formatter)
 {
   for ( std::map<std::string,tdm_channelgroup>::iterator it=this->tdmchannelgroups_.begin();
                                                          it!=this->tdmchannelgroups_.end(); ++it)
@@ -515,7 +578,7 @@ void tdm_termite::summarize_member(tdm_channelgroup chp, std::string& summary, f
   }
 }
 
-void tdm_termite::summarize_member(submatrix sbm, std::string& summary, format& formatter)
+void tdm_termite::summarize_member(submatrix &sbm, std::string& summary, format& formatter)
 {
   for ( std::map<std::string,submatrix>::iterator it=this->submatrices_.begin();
                                                   it!=this->submatrices_.end(); ++it)
@@ -525,7 +588,7 @@ void tdm_termite::summarize_member(submatrix sbm, std::string& summary, format&
   }
 }
 
-void tdm_termite::summarize_member(localcolumn lcc, std::string& summary, format& formatter)
+void tdm_termite::summarize_member(localcolumn &lcc, std::string& summary, format& formatter)
 {
   for ( std::map<std::string,localcolumn>::iterator it=this->localcolumns_.begin();
                                                     it!=this->localcolumns_.end(); ++it)
@@ -535,7 +598,7 @@ void tdm_termite::summarize_member(localcolumn lcc, std::string& summary, format
   }
 }
 
-void tdm_termite::summarize_member(block blk, std::string& summary, format& formatter)
+void tdm_termite::summarize_member(block &blk, std::string& summary, format& formatter)
 {
   for ( std::map<std::string,block>::iterator it=this->tdx_blocks_.begin();
                                               it!=this->tdx_blocks_.end(); ++it)
@@ -584,10 +647,20 @@ std::vector<tdmdatatype> tdm_termite::get_channel(std::string& id)
     // declare buffer covering the required range of "tdxbuffer_"
     // (consider both channel-wise and block-wise ordering)
     unsigned long int strtidx = blk.block_offset_*blk.block_size_
-                              + blk.byte_offset_,
+                              + blk.byte_offset_;
-                      fnshidx = strtidx + blk.length_*dtyp.size_;
+                      // fnshidx = strtidx + blk.length_*dtyp.size_;
-    std::vector<unsigned char> tdxblk( tdxbuffer_.begin()+strtidx,
+    // std::vector<unsigned char> tdxblk( tdxbuffer_.begin()+strtidx,
-                                       tdxbuffer_.begin()+fnshidx );
+    //                                    tdxbuffer_.begin()+fnshidx );
+    char* blkbuf = new char[blk.length_*dtyp.size_];
+    try {
+      tdx_ifstream_->seekg(strtidx);
+      tdx_ifstream_->read(blkbuf,blk.length_*dtyp.size_);
+    } catch (const std::exception& e) {
+      throw std::runtime_error( std::string("failed to read block from tdx_ifstream_: ")
+                                + e.what() );
+    }
+    std::vector<unsigned char> tdxblk(blkbuf,blkbuf+blk.length_*dtyp.size_);
+    delete []blkbuf;
 
     // distinguish numeric datatypes included in "tdmdatatype"
     if ( blk.value_type_ == std::string("eInt16Usi") )
@@ -779,7 +852,7 @@ void tdm_termite::print_group(std::string &id, const char* filename, bool includ
     for ( std::string chn: chngrp.channels_ )
     {
       std::vector<tdmdatatype> chndat = this->get_channel(chn);
-      if ( chndat.size() > maxrows ) maxrows = chndat.size();
+      if ( chndat.size() > maxrows ) maxrows = (unsigned int)chndat.size();
       allchns.push_back(chndat);
     }
 
@@ -844,7 +917,7 @@ void tdm_termite::check_filename_path(const char* filename)
 
   if ( !std::filesystem::is_directory(pt) )
   {
-    throw std::runtime_error(std::string("directory does not exist: ") + pt.c_str() );
+    throw std::runtime_error( std::string("directory does not exist: ") + pt.u8string() );
   }
 }
 

lib/tdm_termite.hpp

@@ -60,8 +60,9 @@ class tdm_termite
   std::map<std::string,submatrix> submatrices_;
   std::map<std::string,localcolumn> localcolumns_;
 
-  // binary data container
+  // binary data container/file stream
   std::vector<unsigned char> tdxbuffer_;
+  std::ifstream *tdx_ifstream_;
 
   // extract list of identifiers from e.g. "#xpointer(id("usi12") id("usi13"))"
   std::vector<std::string> extract_ids(std::string idstring)
@@ -121,6 +122,9 @@ public:
   tdm_termite();
   tdm_termite(std::string tdmfile, std::string tdxfile = std::string(""),
              bool showlog = false);
+  ~tdm_termite();
+  tdm_termite(const tdm_termite& other);
+  tdm_termite& operator=(const tdm_termite& other);
 
   // provide (tdm,tdx) files
   void submit_files(std::string tdmfile, std::string tdxfile = std::string(""),
@@ -180,10 +184,10 @@ public:
   template<typename tdmelement>
   std::string get_overview(format formatter);
 private:
-  void summarize_member(tdm_channelgroup chp, std::string& summary, format& formatter);
+  void summarize_member(tdm_channelgroup &chp, std::string& summary, format& formatter);
-  void summarize_member(submatrix sbm, std::string& summary, format& formatter);
+  void summarize_member(submatrix &sbm, std::string& summary, format& formatter);
-  void summarize_member(localcolumn lcc, std::string& summary, format& formatter);
+  void summarize_member(localcolumn &lcc, std::string& summary, format& formatter);
-  void summarize_member(block blk, std::string& summary, format& formatter);
+  void summarize_member(block &blk, std::string& summary, format& formatter);
 public:
 
   // get list of channelgroup ids

makefile

@@ -1,5 +1,7 @@
 # --------------------------------------------------------------------------- #
 
+SHELL := /bin/bash
+
 # declare name of executable
 EXE = tdmtermite
 
@@ -13,18 +15,35 @@ CC = g++ -std=c++17
 # compiler options and optimization flags
 OPT = -O3 -Wall -Werror -Wunused-variable -Wsign-compare
 
-# include library path
+# include 3rd party libraries paths
-LIB = pugixml/
+LIBB := 3rdparty/
+LIB := $(foreach dir,$(shell ls $(LIBB)),-I $(LIBB)$(dir))
 
 # determine git version/commit tag
 GTAG := $(shell git tag | tail -n1)
+GTAGV := $(shell git tag | tail -n1 | tr -d 'v')
 GHSH := $(shell git rev-parse HEAD | head -c8)
+PIPYVS := $(shell grep "version" pip/setup.py | tr -d 'version=",# ')
+PICGVS := $(shell grep "version" pip/setup.cfg | tr -d 'version=",# ')
 
 # define install location
 INST := /usr/local/bin
 
-# platform
+# platform and current working directory
 OST := $(shell uname)
+CWD := $(shell pwd)
+
+# --------------------------------------------------------------------------- #
+# version/tag check
+
+checkversion:
+	@echo "git tag:                "$(GTAG)
+	@echo "git head:               "$(GHSH)
+	@echo "pip setup.py version:   "$(PIPYVS)
+	@echo "pip setup.cfg version:  "$(PICGVS)
+
+$(GTAGV):
+	@echo "check consistent versions (git tag vs. setup.py): "$(GTAG)" <-> "$(PIPYVS)" "
 
 # --------------------------------------------------------------------------- #
 # CLI tool
@@ -49,14 +68,20 @@ main.o : src/main.cpp lib/$(SRC).hpp $(HPP)
 		sed -i '' 's/TAGSTRING/$(GTAG)/g' $<.cpp; \
 		sed -i '' 's/HASHSTRING/$(GHSH)/g' $<.cpp; \
 	fi
-	$(CC) -c $(OPT) -I $(LIB) -I lib/ $<.cpp -o $@
+	$(CC) -c $(OPT) $(LIB) -I lib/ $<.cpp -o $@
 	@rm $<.cpp
 
 $(SRC).o : lib/$(SRC).cpp lib/$(SRC).hpp $(HPP)
-	$(CC) -c $(OPT) -I $(LIB) $< -o $@
+	$(CC) -c $(OPT) $(LIB) $< -o $@
 
-clean-cpp :
+tdmtest : tdmtest.o
-	rm -f $(EXE) *.o src/main.cpp.cpp
+	$(CC) $(OPT) $^ -o $@
+
+tdmtest.o : src/test.cpp lib/$(SRC).hpp $(HPP)
+	$(CC) -c $(OPT) $(LIB) -I lib/ $< -o $@
+
+cpp-clean :
+	rm -f $(EXE) *.o src/main.cpp.cpp tdmtest
 
 # --------------------------------------------------------------------------- #
 # check process
@@ -84,13 +109,37 @@ cython-build : cython/setup.py cython/tdm_termite.pxd cython/py_tdm_termite.pyx
 cython-install : cython/setup.py cython/tdm_termite.pxd cython/py_tdm_termite.pyx $(HPP) lib/tdm_termite.cpp
 	python3 $< install
 
-clean-cython :
+cython-clean :
-	rm -vf cython/py_tdm_termite.cpp
+	rm -vf cython/py_tdm_termite.c* cython/tdm_termite.c*
 	rm -vf tdm_termite.cpython-*.so python/tdm_termite.cpython-*.so
 	rm -rf build
 
 # --------------------------------------------------------------------------- #
+# docker
 
-clean : clean-cpp clean-cython
+docker-build:
+	docker build . --tag tdmtermite:latest
+
+docker-run:
+	mkdir -pv data/{input,output}
+	docker run -it --rm --volume $(CWD)/data:/home/data tdmtermite:latest /bin/bash
+
+docker-clean:
+	rm -rv data
+	docker image remove tdmtermite
+
+# --------------------------------------------------------------------------- #
+# pip
+
+pip-publish: $(PIPYVS) cython-build
+	cd pip/ && make pip-publish
+
+pip-test:
+	cd pip/ && make pip-test
+
+# --------------------------------------------------------------------------- #
+
+clean : cpp-clean cython-clean
+	cd pip/ && make pip-clean
 
 # --------------------------------------------------------------------------- #

pip/Dockerfile

@@ -0,0 +1,15 @@
+
+FROM debian:bullseye
+
+RUN DEBIAN_FRONTEND=noninteractive \
+  apt-get update && apt-get upgrade -y && apt-get install -y \
+  python3 \
+  python3-pip \
+  python3-setuptools
+
+# RUN python3 -m pip install -i https://test.pypi.org/simple/ TDMtermite-RecordEvolution==0.6.7 && \
+#   python3 -m pip install --upgrade TDMtermite-RecordEvolution
+RUN python3 -m pip install TDMtermite
+
+# CMD ["sleep","3600"]
+CMD ["python3","-m","pip","freeze"]

pip/Dockerfile-manylinux

@@ -0,0 +1,25 @@
+
+FROM quay.io/pypa/manylinux2010_x86_64
+
+RUN yum -y install \
+    git \
+    python34-devel \
+    gcc-c++ \
+    python34-tkinter \
+    make \
+    python34-pip \
+    
+RUN sudo yum -y install rh-python36-python-devel.x86_64 rh-python35-python-devel.x86_64 python27-python-devel.x86_64
+
+ENV PATH /opt/rh/python27/root/usr/bin:/opt/rh/rh-python35/root/usr/bin/:/opt/rh/rh-python36/root/usr/bin/:$PATH
+
+RUN  python3.6 -m pip install --user --upgrade cython wheel twine auditwheel
+
+WORKDIR /home/${USERNAME}/neuron-yale
+
+RUN  git checkout setuppy \
+     && python3.6 setup.py bdist_wheel
+
+# repair wheel? see : https://malramsay.com/post/perils_of_packaging/
+RUN python3.6 -m pip install --user --upgrade auditwheel
+RUN LD_LIBRARY_PATH=`pwd`/_install/lib auditwheel repair dist/NEURON-7.8-cp36-cp36m-linux_x86_64.whl

pip/MANIFEST.in

@@ -0,0 +1,4 @@
+include *.hpp
+include *.cpp
+include *.pyx
+include *.pxd

pip/bkup.pyproject.toml

@@ -0,0 +1,4 @@
+[build-system]
+requires = [
+    "setuptools"
+]

pip/makefile

@@ -0,0 +1,62 @@
+# --------------------------------------------------------------------------- #
+
+pip-publish: pip-sdist pip-upload
+
+pip-sdist: ../cython/py_tdm_termite.pyx ../cython/tdm_termite.pxd ../cython/py_tdm_termite.cpp
+	cp -v ../cython/py_tdm_termite.pyx ../cython/tdm_termite.pxd ./
+	cp -v ../cython/py_tdm_termite.cpp ./
+	cp -v ../lib/*.hpp ../lib/*.cpp ./
+	cp -v ../3rdparty/pugixml/* ./
+	cat ../README.md | head -n316 | tail -n306 > ./README.md
+	cp -v ../LICENSE ./
+	# cython py_tdm_termite.pyx -o py_tdm_termite.cpp
+	python3 setup.py sdist
+
+pip-setup:
+	apt-get install -y python3-setuptools \
+	                   python3-pip \
+	                   python3-venv
+	python3 -m pip install --upgrade build
+	python3 -m pip install twine wheel auditwheel cython
+	python3 -m pip install --user --upgrade twine
+
+pip-build:
+	#python3 -m build
+	# python3 setup.py sdist bdist_wheel
+	python3 setup.py bdist_wheel
+
+# actually it seems we have to use CentOS container
+# docker run -i -t -v `pwd`:/io quay.io/pypa/manylinux1_x86_64 /bin/bash
+# see https://github.com/neuronsimulator/nrn/issues/329 for setup of the container
+
+pip-audit:
+	auditwheel repair $(shell find dist/ -name "*-cp38-cp38-linux_x86_64.whl")
+
+# username: __token__
+# password: API-token including "pypi-"
+# !! RUN AS ROOT!! (only for bdist_wheel + auditwheel)
+pip-upload-test:
+	python3 -m twine upload --repository testpypi dist/$(shell ls -t dist/ | head -n1)
+
+pip-upload:
+	python3 -m twine upload dist/$(shell ls -t dist/ | head -n1)
+
+pip-test-install:
+	python3 -m pip install --index-url https://test.pypi.org/simple --no-deps TDMtermite-RecordEvolution
+	# python3 -m pip install -i https://test.pypi.org/simple/ TDMtermite-RecordEvolution==0.5
+
+pip-test:
+	docker build . --tag tdmtermite-piptest
+	docker run -it --rm tdmtermite-piptest
+
+pip-clean:
+	rm -rvf dist/
+	rm -rvf *.egg-info
+	rm -rvf build/
+	rm -rvf cython/
+	rm -rvf wheelhouse/
+	rm -vf *.pyx *.pxd
+	rm -vf *.cpp *.c *.hpp
+	rm -vf README.md LICENSE
+
+# --------------------------------------------------------------------------- #

pip/setup.cfg

@@ -0,0 +1,21 @@
+[metadata]
+name = TDMtermite-RecordEvolution
+version = 1.0.1
+author = Record Evolution GmbH
+author_email = mario.fink@record-evolution.de
+maintainer = Record Evolution GmbH
+license = MIT
+description = Extract and read data from National Instruments LabVIEW tdx/tdm files and export them as csv files
+long_description = file: README.md
+long_description_content_type = text/markdown
+url = https://github.com/RecordEvolution/TDMtermite.git
+project_urls =
+    Bug Tracker = https://github.com/RecordEvolution/TDMtermite/issues
+classifiers =
+    Programming Language :: Python :: 3
+    License :: OSI Approved :: MIT License
+    Operating System :: OS Independent
+
+[options]
+packages = find:
+python_requires = >=3.6

pip/setup.py

@@ -0,0 +1,49 @@
+
+from setuptools import setup, Extension
+import sys
+
+print("building on platform: "+sys.platform)
+
+if sys.platform == "linux" or sys.platform == "darwin" :
+	cmpargs = ['-std=c++17','-Wno-unused-variable']
+	lnkargs = ['-std=c++17','-Wno-unused-variable']
+elif sys.platform == "win32" :
+	cmpargs = ['/EHsc','/std:c++17']
+	lnkargs = []
+else :
+	raise RuntimeError("unknown platform")
+
+with open("README.md", "r", encoding="utf-8") as fh:
+    long_description = fh.read()
+
+setup(
+    name="TDMtermite",
+    version="1.0.2",
+    author="Record Evolution GmbH",
+    author_email="mario.fink@record-evolution.de",
+    maintainer="Record Evolution GmbH",
+    license="MIT",
+    description="Extract and read data from National Instruments LabVIEW tdx/tdm files and export them as csv files",
+    keywords="TDM/TDX NationalInstruments LabVIEW decode",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    url="https://github.com/RecordEvolution/TDMtermite.git",
+    project_urls={
+        "Bug Tracker": "https://github.com/RecordEvolution/TDMtermite/issues",
+    },
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
+    ext_modules=[Extension("tdm_termite",
+                           ["py_tdm_termite.cpp"],
+                           # libraries_dirs = ["cython/"],
+                           # include_dirs = ["3rdparty/pugixml/","lib/"],
+                           # depends = ["../lib/tdm_termite.hpp"]
+                           language = 'c++',
+                           extra_compile_args = cmpargs,
+                           extra_link_args = lnkargs,
+                           )
+	],
+)

src/test.cpp

@@ -0,0 +1,33 @@
+// ------------------------------------------------------------------------- //
+
+#include "tdm_termite.hpp"
+
+#include <filesystem>
+#include <regex>
+#include <thread>
+#include <chrono>
+
+// ------------------------------------------------------------------------- //
+
+int main(int argc, char* argv[])
+{
+  std::string tdmfile(argv[1]);
+  std::string tdxfile(argv[2]);
+
+  std::cout<<tdmfile<<"\n"<<tdxfile<<"\n";
+
+  pugi::xml_document xml_doc;
+  pugi::xml_parse_result xml_result;
+
+  // load XML document from stream
+  std::ifstream fin(tdmfile.c_str());
+  xml_result = xml_doc.load(fin);
+  fin.close();
+
+  std::cout<<"\nloading "<<tdmfile<<": "<<xml_result.description()<<"\n";
+  std::cout<<"encoding: "<<(pugi::xml_encoding)xml_result.encoding<<"\n\n";
+
+  std::this_thread::sleep_for(std::chrono::milliseconds(4000));
+
+  return 0;
+}