Compare commits
No commits in common. "c8bee6394218841527f2e57cf4f85890aa96c96b" and "75e792b86c4d51b2579be0d9aa2432ff02b8d40e" have entirely different histories.
c8bee63942
...
75e792b86c
5
.github/setup.sh
vendored
5
.github/setup.sh
vendored
@ -1,5 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
cat ../README.md | grep '^# IMCtermite' -A 50000 > ../python/README.md
|
||||
cp -r ../lib ../python/
|
||||
cp -v ../LICENSE ../python/
|
||||
61
.github/workflows/pypi-deploy.yml
vendored
61
.github/workflows/pypi-deploy.yml
vendored
@ -1,61 +0,0 @@
|
||||
|
||||
name: Build Python Wheels
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [master]
|
||||
|
||||
jobs:
|
||||
|
||||
build_setup:
|
||||
name: Prepare environment for wheel builds
|
||||
runs-on: ubuntu-20.04
|
||||
steps:
|
||||
- name: Prepare files
|
||||
run: |
|
||||
chmod +x "${GITHUB_WORKSPACE}/.github/setup.sh"
|
||||
"${GITHUB_WORKSPACE}/.github/setup.sh"
|
||||
|
||||
build_wheels:
|
||||
name: Build binary wheels on ${{ matrix.os }}
|
||||
runs-on: ${{ matrix.os }}
|
||||
needs: [build_setup]
|
||||
strategy:
|
||||
matrix:
|
||||
os: [ubuntu-20.04, windows-2019, macOS-10.15]
|
||||
arch: [auto32, auto64, aarch64, ppc64le, s390x]
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- uses: actions/setup-python@v2
|
||||
- name: Install cibuildwheel
|
||||
run: python -m pip install cibuildwheel==2.1.2
|
||||
working-directory: python/
|
||||
- name: Build wheels
|
||||
run: python -m cibuildwheel --output-dir wheelhouse
|
||||
working-directory: python/
|
||||
# env:
|
||||
# CIBW_BUILD: cp36-* cp37-* cp38-* cp39-* cp310-*
|
||||
|
||||
build_sdist:
|
||||
name: Build source distribution
|
||||
runs-on: ubuntu-latest
|
||||
needs: [build_setup]
|
||||
steps:
|
||||
- uses: actions/checkout@v2
|
||||
- name: Install cython
|
||||
run: python -m pip install cython==0.29.24
|
||||
- name: Build sdist
|
||||
run: python setup.py sdist
|
||||
working-directory: python/
|
||||
|
||||
upload_pypi:
|
||||
name: Upload binary wheels to PyPI
|
||||
runs-on: ubuntu-20.04
|
||||
needs: [build_wheels, build_sdist]
|
||||
|
||||
steps:
|
||||
- uses: pypa/gh-action-pypi-publish@release/v1
|
||||
with:
|
||||
user: __token__
|
||||
password: ${{ secrets.IMCTERMITE_GITHUB_WORKFLOW_PYPI_API_TOKEN }}
|
||||
11
.gitignore
vendored
11
.gitignore
vendored
@ -2,7 +2,6 @@
|
||||
eatraw
|
||||
eatdev
|
||||
imctermite
|
||||
IMCtermite
|
||||
|
||||
nohup.out
|
||||
|
||||
@ -32,13 +31,3 @@ pip/LICENSE
|
||||
pip/*egg-info
|
||||
pip/dist/
|
||||
pip/build/
|
||||
|
||||
python/README.md
|
||||
python/LICENSE
|
||||
python/build
|
||||
python/*.egg-info
|
||||
python/dist
|
||||
python/*.soc
|
||||
python/lib/
|
||||
python/*.cpp
|
||||
python/wheelhouse/
|
||||
|
||||
11
README.md
11
README.md
@ -4,7 +4,6 @@
|
||||
[](https://lgtm.com/projects/g/RecordEvolution/IMCtermite/context:python)
|
||||
[](https://img.shields.io/github/license/RecordEvolution/IMCtermite)
|
||||
[](https://img.shields.io/github/stars/RecordEvolution/IMCtermite)
|
||||
|
||||
|
||||
# IMCtermite
|
||||
|
||||
@ -212,9 +211,9 @@ channels = imcraw.get_channels(False)
|
||||
print(channels)
|
||||
```
|
||||
|
||||
A more complete [example](python/examples/usage.py), including the methods for
|
||||
obtaining the channels, i.a. their data and/or directly printing them to files,
|
||||
can be found in the `python/examples` folder.
|
||||
A more complete [example](python/usage.py), including the methods for obtaining the
|
||||
channels, i.a. their data and/or directly printing them to files, can be found
|
||||
in the Python folder.
|
||||
|
||||
## References
|
||||
|
||||
@ -224,7 +223,3 @@ can be found in the `python/examples` folder.
|
||||
- https://github.com/Apollo3zehn/ImcFamosFile
|
||||
- https://apollo3zehn.github.io/ImcFamosFile/api/ImcFamosFile.FamosFileKeyType.html
|
||||
- https://pypi.org/help/#apitoken
|
||||
- https://sgoel.dev/posts/uploading-binary-wheels-to-pypi-from-github-actions/
|
||||
- https://docs.github.com/en/actions/reference/workflow-syntax-for-github-actions#jobsjob_idstepsrun
|
||||
- https://github.com/pypa/cibuildwheel/blob/main/examples/github-deploy.yml
|
||||
- https://cibuildwheel.readthedocs.io/en/stable/deliver-to-pypi/
|
||||
|
||||
111
assets/imctermite.svg
Normal file
111
assets/imctermite.svg
Normal file
@ -0,0 +1,111 @@
|
||||
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
|
||||
<svg
|
||||
xmlns:dc="http://purl.org/dc/elements/1.1/"
|
||||
xmlns:cc="http://creativecommons.org/ns#"
|
||||
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
|
||||
xmlns:svg="http://www.w3.org/2000/svg"
|
||||
xmlns="http://www.w3.org/2000/svg"
|
||||
xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
|
||||
xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
|
||||
height="78.080002"
|
||||
width="325.72"
|
||||
id="svg3945"
|
||||
version="1.1"
|
||||
viewBox="0 0 325.72 78.08"
|
||||
sodipodi:docname="imctermite.svg"
|
||||
inkscape:version="1.0.1 (3bc2e813f5, 2020-09-07)">
|
||||
<sodipodi:namedview
|
||||
pagecolor="#ffffff"
|
||||
bordercolor="#666666"
|
||||
borderopacity="1"
|
||||
objecttolerance="10"
|
||||
gridtolerance="10"
|
||||
guidetolerance="10"
|
||||
inkscape:pageopacity="0"
|
||||
inkscape:pageshadow="2"
|
||||
inkscape:window-width="2048"
|
||||
inkscape:window-height="1088"
|
||||
id="namedview18"
|
||||
showgrid="false"
|
||||
inkscape:zoom="2.5577614"
|
||||
inkscape:cx="138.13369"
|
||||
inkscape:cy="-27.086877"
|
||||
inkscape:window-x="0"
|
||||
inkscape:window-y="32"
|
||||
inkscape:window-maximized="1"
|
||||
inkscape:current-layer="svg3945"
|
||||
inkscape:document-rotation="0" />
|
||||
<metadata
|
||||
id="metadata3951">
|
||||
<rdf:RDF>
|
||||
<cc:Work
|
||||
rdf:about="">
|
||||
<dc:format>image/svg+xml</dc:format>
|
||||
<dc:type
|
||||
rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
|
||||
<dc:title>flasher</dc:title>
|
||||
</cc:Work>
|
||||
</rdf:RDF>
|
||||
</metadata>
|
||||
<defs
|
||||
id="defs3949" />
|
||||
<title
|
||||
id="title3916">flasher</title>
|
||||
<g
|
||||
id="logog"
|
||||
transform="translate(0,0.99981694)">
|
||||
<path
|
||||
style="fill:#364d5c"
|
||||
transform="translate(-2.04,-1.15)"
|
||||
d="m 32.86,2 -13,7.5 v 0 h -0.05 v 0 l -0.48,0.28 c -4.27,2.46 -5.68,11.38 -6.06,14.75 L 36.2,11.33 c 0.39,-0.19 7.6,-3.69 13.57,-3.69 h 0.14 L 40.13,2 a 8.15,8.15 0 0 0 -7.27,0"
|
||||
id="path138"
|
||||
inkscape:connector-curvature="0" />
|
||||
<path
|
||||
style="fill:#364d5c"
|
||||
transform="translate(-2.04,-1.15)"
|
||||
d="M 5.68,17.69 A 8.2,8.2 0 0 0 2,24 v 15.78 c 0,4.9 7,10.48 9.75,12.46 V 25.77 c 0,-0.44 0.6,-8.55 3.65,-13.72 z"
|
||||
id="path142"
|
||||
inkscape:connector-curvature="0" />
|
||||
<path
|
||||
style="fill:#364d5c"
|
||||
transform="translate(-2.04,-1.15)"
|
||||
d="m 12.1,54.12 v 0 C 11.74,53.88 5,49.41 2,44.24 v 11.14 a 8.2,8.2 0 0 0 3.64,6.3 l 13.5,7.79 c 4.28,2.46 12.7,-0.77 15.81,-2.12 z"
|
||||
id="path146"
|
||||
inkscape:connector-curvature="0" />
|
||||
<path
|
||||
style="fill:#364d5c"
|
||||
transform="translate(-2.04,-1.15)"
|
||||
d="m 36.79,68 c -0.4,0.19 -7.71,3.75 -13.71,3.69 l 9.78,5.64 a 8.15,8.15 0 0 0 7.27,0 l 13.51,-7.8 c 4.27,-2.46 5.68,-11.39 6.06,-14.75 z"
|
||||
id="path150"
|
||||
inkscape:connector-curvature="0" />
|
||||
<path
|
||||
style="fill:#364d5c"
|
||||
transform="translate(-2.04,-1.15)"
|
||||
d="M 61.2,27.13 V 53.6 c 0,0.44 -0.6,8.55 -3.65,13.72 l 9.77,-5.64 A 8.2,8.2 0 0 0 71,55.38 V 39.59 c 0,-4.94 -7,-10.5 -9.75,-12.46"
|
||||
id="path154"
|
||||
inkscape:connector-curvature="0" />
|
||||
<path
|
||||
style="fill:#364d5c"
|
||||
transform="translate(-2.04,-1.15)"
|
||||
d="M 67.31,17.69 53.81,9.9 C 49.53,7.44 41.11,10.67 38,12 l 22.85,13.23 v 0 a 43.43,43.43 0 0 1 5.7,4.51 24,24 0 0 1 4.45,5.35 V 24 a 8.2,8.2 0 0 0 -3.64,-6.3"
|
||||
id="path158"
|
||||
inkscape:connector-curvature="0" />
|
||||
</g>
|
||||
<g
|
||||
id="re"
|
||||
transform="translate(0,0.99981694)" />
|
||||
<text
|
||||
id="text3955"
|
||||
y="55.47554"
|
||||
x="74.101189"
|
||||
style="font-style:normal;font-weight:normal;font-size:40px;line-height:1.25;font-family:sans-serif;letter-spacing:0px;word-spacing:0px;fill:#364d5c;fill-opacity:1;stroke:none"
|
||||
xml:space="preserve"><tspan
|
||||
style="font-style:normal;font-variant:normal;font-weight:bold;font-stretch:normal;font-size:44px;font-family:sans-serif;-inkscape-font-specification:'sans-serif, Bold';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-feature-settings:normal;text-align:start;writing-mode:lr-tb;text-anchor:start;fill:#364d5c;fill-opacity:1"
|
||||
y="55.47554"
|
||||
x="74.101189"
|
||||
id="tspan3953"><tspan
|
||||
id="tspan24"
|
||||
style="font-style:normal;font-variant:normal;font-weight:bold;font-stretch:normal;font-family:sans-serif;-inkscape-font-specification:'sans-serif Bold'">IMC</tspan><tspan
|
||||
id="tspan3845"
|
||||
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-family:sans-serif;-inkscape-font-specification:sans-serif">termite</tspan> </tspan></text>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 4.5 KiB |
112
assets/raweater.svg
Normal file
112
assets/raweater.svg
Normal file
@ -0,0 +1,112 @@
|
||||
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
|
||||
<svg
|
||||
xmlns:dc="http://purl.org/dc/elements/1.1/"
|
||||
xmlns:cc="http://creativecommons.org/ns#"
|
||||
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
|
||||
xmlns:svg="http://www.w3.org/2000/svg"
|
||||
xmlns="http://www.w3.org/2000/svg"
|
||||
xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
|
||||
xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
|
||||
height="78.080002"
|
||||
width="290.72"
|
||||
id="svg3945"
|
||||
version="1.1"
|
||||
viewBox="0 0 290.72 78.08"
|
||||
sodipodi:docname="raweater.svg"
|
||||
inkscape:version="0.92.5 (2060ec1f9f, 2020-04-08)">
|
||||
<sodipodi:namedview
|
||||
pagecolor="#ffffff"
|
||||
bordercolor="#666666"
|
||||
borderopacity="1"
|
||||
objecttolerance="10"
|
||||
gridtolerance="10"
|
||||
guidetolerance="10"
|
||||
inkscape:pageopacity="0"
|
||||
inkscape:pageshadow="2"
|
||||
inkscape:window-width="1360"
|
||||
inkscape:window-height="704"
|
||||
id="namedview18"
|
||||
showgrid="false"
|
||||
inkscape:zoom="0.90430522"
|
||||
inkscape:cx="191.86"
|
||||
inkscape:cy="38.540001"
|
||||
inkscape:window-x="0"
|
||||
inkscape:window-y="27"
|
||||
inkscape:window-maximized="1"
|
||||
inkscape:current-layer="svg3945" />
|
||||
<metadata
|
||||
id="metadata3951">
|
||||
<rdf:RDF>
|
||||
<cc:Work
|
||||
rdf:about="">
|
||||
<dc:format>image/svg+xml</dc:format>
|
||||
<dc:type
|
||||
rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
|
||||
<dc:title>flasher</dc:title>
|
||||
</cc:Work>
|
||||
</rdf:RDF>
|
||||
</metadata>
|
||||
<defs
|
||||
id="defs3949" />
|
||||
<title
|
||||
id="title3916">flasher</title>
|
||||
<g
|
||||
id="logog"
|
||||
transform="translate(0,0.99981694)">
|
||||
<path
|
||||
style="fill:#364d5c"
|
||||
transform="translate(-2.04,-1.15)"
|
||||
d="m 32.86,2 -13,7.5 v 0 h -0.05 v 0 l -0.48,0.28 c -4.27,2.46 -5.68,11.38 -6.06,14.75 L 36.2,11.33 c 0.39,-0.19 7.6,-3.69 13.57,-3.69 h 0.14 L 40.13,2 a 8.15,8.15 0 0 0 -7.27,0"
|
||||
id="path138"
|
||||
inkscape:connector-curvature="0" />
|
||||
<path
|
||||
style="fill:#364d5c"
|
||||
transform="translate(-2.04,-1.15)"
|
||||
d="M 5.68,17.69 A 8.2,8.2 0 0 0 2,24 v 15.78 c 0,4.9 7,10.48 9.75,12.46 V 25.77 c 0,-0.44 0.6,-8.55 3.65,-13.72 z"
|
||||
id="path142"
|
||||
inkscape:connector-curvature="0" />
|
||||
<path
|
||||
style="fill:#364d5c"
|
||||
transform="translate(-2.04,-1.15)"
|
||||
d="m 12.1,54.12 v 0 C 11.74,53.88 5,49.41 2,44.24 v 11.14 a 8.2,8.2 0 0 0 3.64,6.3 l 13.5,7.79 c 4.28,2.46 12.7,-0.77 15.81,-2.12 z"
|
||||
id="path146"
|
||||
inkscape:connector-curvature="0" />
|
||||
<path
|
||||
style="fill:#364d5c"
|
||||
transform="translate(-2.04,-1.15)"
|
||||
d="m 36.79,68 c -0.4,0.19 -7.71,3.75 -13.71,3.69 l 9.78,5.64 a 8.15,8.15 0 0 0 7.27,0 l 13.51,-7.8 c 4.27,-2.46 5.68,-11.39 6.06,-14.75 z"
|
||||
id="path150"
|
||||
inkscape:connector-curvature="0" />
|
||||
<path
|
||||
style="fill:#364d5c"
|
||||
transform="translate(-2.04,-1.15)"
|
||||
d="M 61.2,27.13 V 53.6 c 0,0.44 -0.6,8.55 -3.65,13.72 l 9.77,-5.64 A 8.2,8.2 0 0 0 71,55.38 V 39.59 c 0,-4.94 -7,-10.5 -9.75,-12.46"
|
||||
id="path154"
|
||||
inkscape:connector-curvature="0" />
|
||||
<path
|
||||
style="fill:#364d5c"
|
||||
transform="translate(-2.04,-1.15)"
|
||||
d="M 67.31,17.69 53.81,9.9 C 49.53,7.44 41.11,10.67 38,12 l 22.85,13.23 v 0 a 43.43,43.43 0 0 1 5.7,4.51 24,24 0 0 1 4.45,5.35 V 24 a 8.2,8.2 0 0 0 -3.64,-6.3"
|
||||
id="path158"
|
||||
inkscape:connector-curvature="0" />
|
||||
</g>
|
||||
<g
|
||||
id="re"
|
||||
transform="translate(0,0.99981694)" />
|
||||
<text
|
||||
id="text3955"
|
||||
y="55.47554"
|
||||
x="74.101189"
|
||||
style="font-style:normal;font-weight:normal;font-size:40px;line-height:1.25;font-family:sans-serif;letter-spacing:0px;word-spacing:0px;fill:#364d5c;fill-opacity:1;stroke:none"
|
||||
xml:space="preserve"><tspan
|
||||
style="font-style:normal;font-variant:normal;font-weight:bold;font-stretch:normal;font-size:44px;font-family:sans-serif;-inkscape-font-specification:'sans-serif, Bold';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-feature-settings:normal;text-align:start;writing-mode:lr-tb;text-anchor:start;fill:#364d5c;fill-opacity:1"
|
||||
y="55.47554"
|
||||
x="74.101189"
|
||||
id="tspan3953"><tspan
|
||||
id="tspan24"
|
||||
style="font-style:normal;font-variant:normal;font-weight:bold;font-stretch:normal;font-family:sans-serif;-inkscape-font-specification:'sans-serif Bold'">R</tspan><tspan
|
||||
id="tspan3845"
|
||||
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-family:sans-serif;-inkscape-font-specification:sans-serif">aw<tspan
|
||||
style="font-style:normal;font-variant:normal;font-weight:bold;font-stretch:normal;font-family:sans-serif;-inkscape-font-specification:'sans-serif Bold'"
|
||||
id="tspan22">E</tspan>ater</tspan> </tspan></text>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 4.6 KiB |
@ -1,23 +1,19 @@
|
||||
# cython: language_level = 3
|
||||
|
||||
# use some C++ STL libraries
|
||||
from libcpp.string cimport string
|
||||
from libcpp.vector cimport vector
|
||||
from libcpp cimport bool
|
||||
|
||||
cdef extern from "lib/imc_raw.hpp" namespace "imc":
|
||||
|
||||
cdef cppclass cppimctermite "imc::raw":
|
||||
|
||||
cdef extern from "imc_raw.hpp" namespace "imc":
|
||||
cdef cppclass imc_termite "imc::raw":
|
||||
# constructor(s)
|
||||
cppimctermite() except +
|
||||
cppimctermite(string rawfile) except +
|
||||
|
||||
imc_termite() except +
|
||||
imc_termite(string rawfile) except +
|
||||
# provide raw file
|
||||
void set_file(string rawfile) except +
|
||||
|
||||
# get JSON list of channels
|
||||
vector[string] get_channels(bool json, bool data) except +
|
||||
|
||||
# print single channel/all channels
|
||||
void print_channel(string channeluuid, string outputdir, char delimiter) except +
|
||||
void print_channels(string outputdir, char delimiter) except +
|
||||
@ -1,39 +1,39 @@
|
||||
# distutils: language = c++
|
||||
# cython: language_level = 3
|
||||
|
||||
from IMCtermite cimport cppimctermite
|
||||
from imc_termite cimport imc_termite
|
||||
|
||||
import json as jn
|
||||
import decimal
|
||||
# import numpy as np
|
||||
|
||||
cdef class imctermite:
|
||||
|
||||
# C++ instance of class => stack allocated (requires nullary constructor!)
|
||||
cdef cppimctermite cppimc
|
||||
cdef imc_termite cpp_imc
|
||||
|
||||
# constructor
|
||||
def __cinit__(self, string rawfile):
|
||||
self.cppimc = cppimctermite(rawfile)
|
||||
self.cpp_imc = imc_termite(rawfile)
|
||||
|
||||
# provide raw file
|
||||
def submit_file(self,string rawfile):
|
||||
self.cppimc.set_file(rawfile)
|
||||
self.cpp_imc.set_file(rawfile)
|
||||
|
||||
# get JSON list of channels
|
||||
def get_channels(self, bool data):
|
||||
chnlst = self.cppimc.get_channels(True,data)
|
||||
chnlst = self.cpp_imc.get_channels(True,data)
|
||||
chnlstjn = [jn.loads(chn.decode(errors="ignore")) for chn in chnlst]
|
||||
return chnlstjn
|
||||
|
||||
# print single channel/all channels
|
||||
def print_channel(self, string channeluuid, string outputfile, char delimiter):
|
||||
self.cppimc.print_channel(channeluuid,outputfile,delimiter)
|
||||
self.cpp_imc.print_channel(channeluuid,outputfile,delimiter)
|
||||
def print_channels(self, string outputdir, char delimiter):
|
||||
self.cppimc.print_channels(outputdir,delimiter)
|
||||
self.cpp_imc.print_channels(outputdir,delimiter)
|
||||
|
||||
# print table including channels
|
||||
def print_table(self, string outputfile):
|
||||
chnlst = self.cppimc.get_channels(True,True)
|
||||
chnlst = self.cpp_imc.get_channels(True,True)
|
||||
chnlstjn = [jn.loads(chn.decode(errors="ignore")) for chn in chnlst]
|
||||
with open(outputfile.decode(),'w') as fout:
|
||||
for chn in chnlstjn:
|
||||
41
cython/raw_eater.pxd
Normal file
41
cython/raw_eater.pxd
Normal file
@ -0,0 +1,41 @@
|
||||
# cython: language_level = 3
|
||||
# distutils: language = c++
|
||||
|
||||
# use some C++ STL libraries
|
||||
from libcpp.string cimport string
|
||||
from libcpp.vector cimport vector
|
||||
from libcpp cimport bool
|
||||
|
||||
# to include implemenation/definition file
|
||||
#cdef extern from "raweat.cpp":
|
||||
# pass
|
||||
|
||||
# these method names have to match the C definitions of the methods!!
|
||||
#
|
||||
# for how to overload the constructor see
|
||||
# https://cython.readthedocs.io/en/latest/src/userguide/wrapping_CPlusPlus.html
|
||||
# and propagating exceptions from C++ to Python
|
||||
# http://docs.cython.org/en/latest/src/userguide/wrapping_CPlusPlus.html#exceptions
|
||||
|
||||
cdef extern from "../lib/raweat.hpp":
|
||||
cdef cppclass raw_eater:
|
||||
# constructor(s)
|
||||
raw_eater() except +
|
||||
raw_eater(string) except +
|
||||
# set new file for decoding
|
||||
void set_file(string)
|
||||
# perform conversion (pass any C++ exceptions to Python)
|
||||
void setup_and_conversion() except +
|
||||
# get validity of data format
|
||||
bool get_valid()
|
||||
# get channel name and unit
|
||||
string get_name()
|
||||
string get_unit()
|
||||
# get time step and time unit
|
||||
double get_dt()
|
||||
string get_temp_unit()
|
||||
# get data array of time and measured quantity's channel
|
||||
vector[double] get_time()
|
||||
vector[double] get_data()
|
||||
# dump all data to .csv
|
||||
void write_table(const char*,char delimiter)
|
||||
58
cython/raw_eater.pyx
Normal file
58
cython/raw_eater.pyx
Normal file
@ -0,0 +1,58 @@
|
||||
|
||||
from raw_eater cimport raweater
|
||||
import numpy as np
|
||||
import re
|
||||
import os
|
||||
|
||||
cdef class raweater:
|
||||
|
||||
# C++ instance of class => stack allocated (requires nullary constructor!)
|
||||
cdef raw_eater rawit
|
||||
|
||||
# pointer to C++ instance (if there's no nullary constructor)
|
||||
# cdef raw_eater *rawit
|
||||
|
||||
def __cinit__(self, string rawfile = b''):
|
||||
if rawfile.decode() == "":
|
||||
self.rawit = raw_eater()
|
||||
# self.rawit = new raw_eater()
|
||||
else:
|
||||
if not os.path.isfile(rawfile) :
|
||||
raise ValueError("'" + str(rawfile) + "' does not exist")
|
||||
self.rawit = raw_eater(rawfile)
|
||||
# self.rawit = new raw_eater(rawfile)
|
||||
|
||||
# def __dealloc__(self):
|
||||
# del self.rawit
|
||||
|
||||
def set_file(self, string rawfile):
|
||||
if not os.path.isfile(rawfile) :
|
||||
raise ValueError("'" + str(rawfile) + "' does not exist")
|
||||
self.rawit.set_file(rawfile)
|
||||
|
||||
def do_conversion(self):
|
||||
self.rawit.setup_and_conversion()
|
||||
|
||||
def validity(self):
|
||||
return self.rawit.get_valid()
|
||||
|
||||
def channel_name(self):
|
||||
return self.rawit.get_name()
|
||||
|
||||
def unit(self):
|
||||
return self.rawit.get_unit()
|
||||
|
||||
def dt(self):
|
||||
return self.rawit.get_dt()
|
||||
|
||||
def time_unit(self):
|
||||
return self.rawit.get_temp_unit()
|
||||
|
||||
def get_time(self):
|
||||
return self.rawit.get_time()
|
||||
|
||||
def get_channel(self):
|
||||
return self.rawit.get_data()
|
||||
|
||||
def write_table(self, const char* csvfile, char delimiter):
|
||||
self.rawit.write_table(csvfile,delimiter)
|
||||
37
cython/raw_meat.pxd
Normal file
37
cython/raw_meat.pxd
Normal file
@ -0,0 +1,37 @@
|
||||
# cython: language_level = 3
|
||||
# distutils: language = c++
|
||||
|
||||
# use some C++ STL libraries
|
||||
from libcpp.string cimport string
|
||||
from libcpp.vector cimport vector
|
||||
from libcpp cimport bool
|
||||
|
||||
# these method names have to match the C++ definitions of the methods!!
|
||||
cdef extern from "../lib/rawmerge.hpp":
|
||||
cdef cppclass raw_merger:
|
||||
raw_merger(string) except +
|
||||
# get validity of data format
|
||||
bool get_valid()
|
||||
# get channel name and unit
|
||||
string get_name()
|
||||
string get_unit()
|
||||
# get time step and time unit
|
||||
double get_dt()
|
||||
string get_temp_unit()
|
||||
# get data array of time and measured quantity's channel
|
||||
vector[double] get_time()
|
||||
vector[double] get_data()
|
||||
# dump all data to .csv
|
||||
void write_table(const char*,char)
|
||||
# add channel and try to merge it (pass C++ exceptions to Python)
|
||||
bool add_channel(string) except +
|
||||
# get total number of (added) channels
|
||||
int get_num_channels()
|
||||
# get list of channel names
|
||||
vector[string] get_channel_names()
|
||||
# get data of particular channel
|
||||
vector[double] get_channel(int)
|
||||
# get total merged time series
|
||||
vector[double] get_time_series()
|
||||
# dump all channels to .csv
|
||||
void write_table_all(const char*,char)
|
||||
58
cython/raw_meat.pyx
Normal file
58
cython/raw_meat.pyx
Normal file
@ -0,0 +1,58 @@
|
||||
|
||||
# from <raw_meat> has to match name of .pxd file and cimport name of class defined in .pxd
|
||||
from raw_meat cimport raw_merger
|
||||
import numpy as np
|
||||
import re
|
||||
|
||||
cdef class rawmerger:
|
||||
|
||||
# pointer to C++ instance (since there's no nullary constructor)
|
||||
cdef raw_merger *rawit
|
||||
|
||||
def __cinit__(self, string rawfile):
|
||||
self.rawit = new raw_merger(rawfile)
|
||||
|
||||
def __dealloc__(self):
|
||||
del self.rawit
|
||||
|
||||
def validity(self):
|
||||
return self.rawit.get_valid()
|
||||
|
||||
def channel_name(self):
|
||||
return self.rawit.get_name()
|
||||
|
||||
def unit(self):
|
||||
return self.rawit.get_unit()
|
||||
|
||||
def dt(self):
|
||||
return self.rawit.get_dt()
|
||||
|
||||
def time_unit(self):
|
||||
return self.rawit.get_temp_unit()
|
||||
|
||||
def get_time(self):
|
||||
return self.rawit.get_time()
|
||||
|
||||
def get_channel(self):
|
||||
return self.rawit.get_data()
|
||||
|
||||
def write_table(self, const char* csvfile, char delimiter):
|
||||
return self.rawit.write_table(csvfile,delimiter)
|
||||
|
||||
def add_channel(self, string rawfile):
|
||||
return self.rawit.add_channel(rawfile)
|
||||
|
||||
def get_num_channels(self):
|
||||
return self.rawit.get_num_channels()
|
||||
|
||||
def get_channel_names(self):
|
||||
return self.rawit.get_channel_names()
|
||||
|
||||
def get_channel_by_index(self, int chidx):
|
||||
return self.rawit.get_channel(chidx)
|
||||
|
||||
def get_time_series(self):
|
||||
return self.rawit.get_time_series()
|
||||
|
||||
def write_table_all(self, const char* csvfile, char delimiter):
|
||||
return self.rawit.write_table_all(csvfile,delimiter)
|
||||
46
cython/setup.py
Normal file
46
cython/setup.py
Normal file
@ -0,0 +1,46 @@
|
||||
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 -l --sort=version:refname > 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="imc_termite",
|
||||
sources=["cython/py_imc_termite.pyx"],
|
||||
# libraries=[""],
|
||||
# library_dirs=["lib"],
|
||||
include_dirs=["lib"],
|
||||
language='c++',
|
||||
extra_compile_args=cmpargs,
|
||||
extra_link_args=lnkargs,
|
||||
)
|
||||
|
||||
setup(
|
||||
name='imc_termite',
|
||||
version='1.2.12',
|
||||
description='IMCtermite cython extension',
|
||||
author='Record Evolution GmbH',
|
||||
author_email='mario.fink@record-evolution.de',
|
||||
url='https://github.com/RecordEvolution/IMCtermite.git',
|
||||
ext_modules=cythonize(extensions,force=True)
|
||||
)
|
||||
20
cython/setup_raw_eater.py
Normal file
20
cython/setup_raw_eater.py
Normal file
@ -0,0 +1,20 @@
|
||||
from distutils.core import setup
|
||||
from distutils.extension import Extension
|
||||
from Cython.Build import cythonize
|
||||
|
||||
extensions = Extension(
|
||||
name="raw_eater",
|
||||
sources=["cython/raw_eater.pyx"],
|
||||
# libraries=[""],
|
||||
library_dirs=["src"],
|
||||
include_dirs=["src"],
|
||||
language='c++',
|
||||
extra_compile_args=['-std=c++11','-Wno-unused-variable'],
|
||||
extra_link_args=['-std=c++11'],
|
||||
#extra_objects=["lib/parquet/libarrow.so.200.0.0"],
|
||||
)
|
||||
|
||||
setup(
|
||||
name="raw_eater",
|
||||
ext_modules=cythonize(extensions)
|
||||
)
|
||||
20
cython/setup_raw_meat.py
Normal file
20
cython/setup_raw_meat.py
Normal file
@ -0,0 +1,20 @@
|
||||
from distutils.core import setup
|
||||
from distutils.extension import Extension
|
||||
from Cython.Build import cythonize
|
||||
|
||||
extensions = Extension(
|
||||
name="raw_meat",
|
||||
sources=["cython/raw_meat.pyx"],
|
||||
# libraries=[""],
|
||||
library_dirs=["src"],
|
||||
include_dirs=["src"],
|
||||
language='c++',
|
||||
extra_compile_args=['-std=c++11','-Wno-unused-variable'],
|
||||
extra_link_args=['-std=c++11'],
|
||||
#extra_objects=["lib/parquet/libarrow.so.200.0.0"],
|
||||
)
|
||||
|
||||
setup(
|
||||
name="raw_meat",
|
||||
ext_modules=cythonize(extensions)
|
||||
)
|
||||
@ -58,8 +58,6 @@ namespace imc
|
||||
// open file and stream data into buffer
|
||||
void fill_buffer()
|
||||
{
|
||||
buffer_.clear();
|
||||
|
||||
// open file and put data in buffer
|
||||
try {
|
||||
std::ifstream fin(raw_file_.c_str(),std::ifstream::binary);
|
||||
@ -78,8 +76,6 @@ namespace imc
|
||||
// parse all raw blocks in buffer
|
||||
void parse_blocks()
|
||||
{
|
||||
rawblocks_.clear();
|
||||
|
||||
// reset counter to identify computational complexity
|
||||
cplxcnt_ = 0;
|
||||
|
||||
@ -194,8 +190,6 @@ namespace imc
|
||||
// generate map of blocks using their uuid
|
||||
void generate_block_map()
|
||||
{
|
||||
mapblocks_.clear();
|
||||
|
||||
for ( imc::block blk: rawblocks_ )
|
||||
{
|
||||
mapblocks_.insert( std::pair<std::string,imc::block>(blk.get_uuid(),blk) );
|
||||
@ -205,8 +199,6 @@ namespace imc
|
||||
// generate channel "environments"
|
||||
void generate_channel_env()
|
||||
{
|
||||
channels_.clear();
|
||||
|
||||
// declare single channel environment
|
||||
imc::channel_env chnenv;
|
||||
chnenv.reset();
|
||||
@ -215,6 +207,7 @@ namespace imc
|
||||
// BLOCK CORRESPONDENCE GOVERNED BY BLOCK ORDER IN BUFFER!!
|
||||
for ( imc::block blk: rawblocks_ )
|
||||
{
|
||||
|
||||
if ( blk.get_key().name_ == "CN" ) chnenv.CNuuid_ = blk.get_uuid();
|
||||
else if ( blk.get_key().name_ == "CD" ) chnenv.CDuuid_ = blk.get_uuid();
|
||||
else if ( blk.get_key().name_ == "CT" ) chnenv.CTuuid_ = blk.get_uuid();
|
||||
|
||||
62
makefile
62
makefile
@ -3,11 +3,12 @@
|
||||
SHELL := /bin/bash
|
||||
|
||||
# name of executable and CLI tool
|
||||
EXE = IMCtermite
|
||||
EXE = imctermite
|
||||
|
||||
# directory names
|
||||
SRC = src/
|
||||
LIB = lib/
|
||||
CYT = cython/
|
||||
PYT = python/
|
||||
|
||||
# list headers
|
||||
@ -15,15 +16,14 @@ HPP = $(wildcard $(LIB)/*.hpp)
|
||||
|
||||
# choose compiler and its options
|
||||
CC = g++ -std=c++17
|
||||
#OPT = -O3 -Wall -mavx -mno-tbm -mf16c -mno-f16c
|
||||
OPT = -O3 -Wall -Wconversion -Wpedantic -Werror -Wunused-variable -Wsign-compare
|
||||
|
||||
# determine git version/commit and release tag
|
||||
GTAG := $(shell git tag -l --sort=version:refname | tail -n1 | sed "s/$^v//g")
|
||||
GTAG := $(shell git tag -l --sort=version:refname | tail -n1)
|
||||
GHSH := $(shell git rev-parse HEAD | head -c8)
|
||||
GVSN := $(shell cat python/VERSION | tr -d ' \n')
|
||||
|
||||
# current timestamp
|
||||
TMS = $(shell date +%Y%m%dT%H%M%S)
|
||||
RTAG := v$(shell cat pip/setup.py | grep version | grep -oP "([0-9]\.){2}[0-9]{1,2}")
|
||||
CTAG := v$(shell cat cython/setup.py | grep version | grep -oP "([0-9]\.){2}[0-9]{1,2}")
|
||||
|
||||
# define install location
|
||||
INST := /usr/local/bin
|
||||
@ -32,7 +32,7 @@ INST := /usr/local/bin
|
||||
# C++ and CLI tool
|
||||
|
||||
# build exectuable
|
||||
$(EXE): check-tags $(GVSN) main.o
|
||||
$(EXE) : check-vtag $(RTAG) main.o
|
||||
$(CC) $(OPT) main.o -o $@
|
||||
|
||||
# build main.cpp and include git version/commit tag
|
||||
@ -40,7 +40,6 @@ main.o: src/main.cpp $(HPP)
|
||||
@cp $< $<.cpp
|
||||
@sed -i 's/TAGSTRING/$(GTAG)/g' $<.cpp
|
||||
@sed -i 's/HASHSTRING/$(GHSH)/g' $<.cpp
|
||||
@sed -i 's/TIMESTAMPSTRING/$(TMS)/g' $<.cpp
|
||||
$(CC) -c $(OPT) -I $(LIB) $<.cpp -o $@
|
||||
@rm $<.cpp
|
||||
|
||||
@ -55,21 +54,22 @@ cpp-clean:
|
||||
rm -vf *.o
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
# C++ linter
|
||||
# linter and code check
|
||||
|
||||
check-code:
|
||||
cppcheck --enable=all -I lib/ src/main.cpp
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
# versions
|
||||
# check version consistency of git tags and version string in package.json
|
||||
|
||||
$(GTAG) :
|
||||
@echo "consistent versions check successful: building $(GTAG)"
|
||||
|
||||
check-tags:
|
||||
@echo "latest git tag: $(GTAG)"
|
||||
@echo "latest git hash: $(GHSH)"
|
||||
@echo "python version: $(GVSN)"
|
||||
check-vtag:
|
||||
@echo "git tag version: "$(GTAG)
|
||||
@echo "git commit hash: "$(GHSH)
|
||||
@echo "release version: "$(RTAG)
|
||||
@echo "module version: "$(CTAG)
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
# Docker
|
||||
@ -83,26 +83,28 @@ docker-run:
|
||||
#-----------------------------------------------------------------------------#
|
||||
# python
|
||||
|
||||
python-build: check-tags $(GVSN)
|
||||
make -C python/ build-inplace
|
||||
cp python/IMCtermite*.so ./ -v
|
||||
cython-build : check-vtag $(CTAG) $(CYT)setup.py $(CYT)imc_termite.pxd $(CYT)py_imc_termite.pyx $(HPP)
|
||||
python3 $(CYT)setup.py build_ext --inplace
|
||||
cp -v imc_termite.cpython-*.so $(PYT)
|
||||
|
||||
python-clean:
|
||||
make -C python/ clean
|
||||
rm -vf IMCtermite*.so
|
||||
cython-install : check-vtag $(CTAG) $(CYT)setup.py $(CYT)imc_termite.pxd $(CYT)py_imc_termite.pyx $(HPP)
|
||||
python3 $(CYT)setup.py install --record files_imctermite.txt
|
||||
|
||||
cython-clean :
|
||||
rm -vf imc_termite.cpython-*.so
|
||||
rm -vf $(PYT)imc_termite.cpython-*.so
|
||||
rm -rvf build/
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
# pip
|
||||
|
||||
pip-release: check-vtag $(RTAG) cython-build
|
||||
cd ./pip/ && make publish-source
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
# clean
|
||||
|
||||
clean: cpp-clean python-clean
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
# github actions
|
||||
|
||||
github-action-lint: .github/workflows/pypi-deploy.yml
|
||||
actionlint $<
|
||||
|
||||
# for reference, see:
|
||||
# https://github.com/rhysd/actionlint
|
||||
clean: cpp-clean cython-clean
|
||||
cd ./pip/ && make clean
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
|
||||
133
parquet/parquet/generate_deps.py
Normal file
133
parquet/parquet/generate_deps.py
Normal file
@ -0,0 +1,133 @@
|
||||
#-----------------------------------------------------------------------------#
|
||||
|
||||
import argparse
|
||||
import os
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
|
||||
parser = argparse.ArgumentParser(description='List all source dependencies')
|
||||
#parser.add_argument('pathToRepo',type=str,help='path of source repository')
|
||||
parser.add_argument('mainSource',type=str,help='main source file')
|
||||
parser.add_argument('depFile',type=str,help='file listing all dependencies')
|
||||
args = parser.parse_args()
|
||||
|
||||
libpaths = ["/home/mario/Desktop/arrow/cpp/src/",
|
||||
"/home/mario/Desktop/arrow/cpp/thrift_ep-install/include/",
|
||||
"/home/mario/Desktop/arrow/cpp/boost_ep-prefix/src/boost_ep/"]
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
|
||||
def find_dependencies(srcfile, recdepth, cdeplist) :
|
||||
"""
|
||||
Given a source file and its dependencies in the given repository path
|
||||
list all further dependencies recursively
|
||||
|
||||
Args:
|
||||
srcfile (string): path/name of source file
|
||||
recdepth (integer): current recursion depth
|
||||
cdeplist (list): current list of dependencies
|
||||
Return:
|
||||
deps (list): list of source files in repository, the source file depends on
|
||||
"""
|
||||
# define indentation to visual recursion
|
||||
indent = recdepth*(" ")
|
||||
|
||||
print("\n" + indent + "find_dependencies:"
|
||||
+ "\n" + indent + "1: " + srcfile
|
||||
+ "\n" + indent + "2: " + str(recdepth)
|
||||
+ "\n" + indent + "3: " + str(len(cdeplist)) + "\n")
|
||||
|
||||
# show dependencies so far
|
||||
#print(cdeplist)
|
||||
|
||||
# generate dependencies by means of g++
|
||||
libdeps = (" -I ").join(libpaths)
|
||||
cmd = "g++ -c -MMD " + srcfile + " -I " + libdeps
|
||||
print(indent + cmd )
|
||||
os.system(cmd)
|
||||
|
||||
# open dependency file and extract list of sources
|
||||
basename = srcfile.split('/')[-1].split('.')[0]
|
||||
depfile = basename + '.d'
|
||||
print(indent + "reading dependency file " + depfile)
|
||||
with open(depfile,'r') as fin :
|
||||
depslist = fin.readlines()
|
||||
|
||||
# delete dependencies and object files
|
||||
os.system("rm " + basename + ".d")
|
||||
os.system("rm " + basename + ".o")
|
||||
|
||||
# remove first line
|
||||
depslist = depslist[1:]
|
||||
|
||||
# delete leading space and trailing backslash
|
||||
depslistcl = [dep.lstrip(' ').rstrip(' \\\n') for dep in depslist]
|
||||
|
||||
# collect dependencies
|
||||
newdeps = []
|
||||
|
||||
# check all dependencies recursively and collect further dependencies
|
||||
count = 0
|
||||
for dep in depslistcl :
|
||||
# append source itself to list
|
||||
if dep not in cdeplist :
|
||||
print(indent + "adding dependency " + dep)
|
||||
newdeps.append(dep)
|
||||
count = count + 1
|
||||
print(indent + "=> added " + str(count) + "/" + str(len(depslistcl)) )
|
||||
|
||||
# check recursion depth
|
||||
if recdepth < 20 :
|
||||
# check all dependencies of every single dependency
|
||||
for dep in depslistcl :
|
||||
# try to find corresponding *.cc, (*.cpp) file
|
||||
depcc = dep.split('.')[0] + '.cc'
|
||||
print(indent + "checking for " + depcc)
|
||||
if os.path.exists(depcc) :
|
||||
if depcc not in cdeplist and depcc not in newdeps :
|
||||
# add file itself as dependency
|
||||
newdeps.append(depcc)
|
||||
# find dependencies of single source
|
||||
newrecdeps = find_dependencies(depcc,recdepth+1,cdeplist+newdeps)
|
||||
# append to list
|
||||
for el in newrecdeps :
|
||||
if el not in newdeps :
|
||||
newdeps.append(el)
|
||||
else :
|
||||
print(indent + "already in list")
|
||||
else :
|
||||
print(indent + "does not exist")
|
||||
|
||||
print("\n")
|
||||
|
||||
# provide list of dependencies
|
||||
return newdeps
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
|
||||
if __name__== "__main__":
|
||||
|
||||
print("\nCLI arguments:\n" + str(args) + "\n")
|
||||
|
||||
# collect list of dependencies
|
||||
deps = []
|
||||
|
||||
# start recursion with given source file
|
||||
deps = find_dependencies(args.mainSource,0,[])
|
||||
|
||||
print("\nfinal list of dependencies: (" + str(len(deps)) + ")\n")
|
||||
print(deps)
|
||||
print("\n")
|
||||
|
||||
# remove any duplicates
|
||||
depsuni = set(deps)
|
||||
print("\nfinal set of dependencies: (" + str(len(depsuni)) + ")\n")
|
||||
print(depsuni)
|
||||
print("\n")
|
||||
|
||||
# write list of dependencies
|
||||
with open(args.depFile,'w') as fout :
|
||||
for el in depsuni :
|
||||
fout.write(str(el) + '\n')
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
22
parquet/parquet/generate_make.py
Normal file
22
parquet/parquet/generate_make.py
Normal file
@ -0,0 +1,22 @@
|
||||
#-----------------------------------------------------------------------------#
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
# find source files
|
||||
srcpaths = Path("src/").rglob('*.cc')
|
||||
deps =[ str(path) for path in srcpaths ]
|
||||
|
||||
print(deps)
|
||||
|
||||
with open('makefileobj','w') as fout :
|
||||
for el in deps :
|
||||
basnam = el.split('/')[-1]
|
||||
print(str(el) + " : " + str(basnam) + " : " + str(basnam.split('.')[1]))
|
||||
if basnam.split('.')[1] == 'cc' :
|
||||
objfile = 'bin/' + basnam.replace('.cc','.o')
|
||||
fout.write(objfile + " : " + el + "\n")
|
||||
fout.write("\t" + "$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@\n")
|
||||
fout.write("\n")
|
||||
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
356
parquet/parquet/makefile
Normal file
356
parquet/parquet/makefile
Normal file
@ -0,0 +1,356 @@
|
||||
#-----------------------------------------------------------------------------#
|
||||
|
||||
CPP := g++ -std=c++14
|
||||
CPPFLAGS := -Woverflow -Wpedantic -Wextra -Waddress -Waligned-new -Walloc-zero
|
||||
|
||||
SRC := src/
|
||||
BIN := bin/
|
||||
|
||||
LIBS := -I src/src/ -I src/thrift_ep-install/include/ -I src/boost_ep-prefix/src/boost_ep/
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
# prepare source
|
||||
#
|
||||
# before: $ cd arrow/cpp/ and compile relevant sources by
|
||||
# $ cmake . -D ARROW_PARQUET=ON -D PARQUET_BUILD_EXAMPLES=ON -D ARROW_WITH_SNAPPY=ON
|
||||
# $ cmake .. -D ARROW_PARQUET=ON ARROW_BUILD_EXAMPLES=ON
|
||||
|
||||
lib :
|
||||
cmake . -D ARROW_WITH_BROTLI=ON -D ARROW_WITH_BZ2=ON -D ARROW_WITH_LZ4=ON -D ARROW_WITH_SNAPPY=ON -D ARROW_WITH_ZLIB=ON -D ARROW_PARQUET=ON -D ARROW_PYTHON=ON
|
||||
|
||||
# cp-src : deps.log
|
||||
# ./src_copy.sh
|
||||
|
||||
deps.log :
|
||||
python3 generate_deps.py reader-writer.cc $@
|
||||
|
||||
SRC := $(shell find $(SRC) -name '*.cc')
|
||||
|
||||
# OBJ := $(apprefix obj/, $(SRC:%.cc=%.o))
|
||||
OBJ := $(addprefix $(BIN),$(notdir $(SRC:%.cc=%.o)))
|
||||
|
||||
check :
|
||||
@echo $(SRC)
|
||||
@echo $(OBJ)
|
||||
|
||||
# vpath %.cc src/
|
||||
|
||||
reader-writer-example : reader-writer.cc $(OBJ) bin/utilmemory.o
|
||||
$(CPP) $(CPPFLAGS) $< $(LIBS) -o $@ $(OBJ) bin/utilmemory.o
|
||||
|
||||
# $(OBJ) : $(SRC)
|
||||
# $(CPP) $(OPT) -c $< -o $@ -I src/src/
|
||||
#
|
||||
# $(BIN)%.o : $(SRC)
|
||||
# $(CPP) $(OPT) -c $< -I src/src/ -o $@
|
||||
|
||||
clean-obj :
|
||||
rm -f $(OBJ)
|
||||
|
||||
# => do build with cmake like here
|
||||
# https://arrow.apache.org/docs/developers/python.html#build-and-test
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
|
||||
bin/type.o : src/src/arrow/type.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/result.o : src/src/arrow/result.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder.o : src/src/arrow/builder.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/tensor.o : src/src/arrow/tensor.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/table.o : src/src/arrow/table.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/extension_type.o : src/src/arrow/extension_type.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/device.o : src/src/arrow/device.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/memory_pool.o : src/src/arrow/memory_pool.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/datum.o : src/src/arrow/datum.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/record_batch.o : src/src/arrow/record_batch.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/compare.o : src/src/arrow/compare.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/visitor.o : src/src/arrow/visitor.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/chunked_array.o : src/src/arrow/chunked_array.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/status.o : src/src/arrow/status.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/pretty_print.o : src/src/arrow/pretty_print.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/sparse_tensor.o : src/src/arrow/sparse_tensor.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/buffer.o : src/src/arrow/buffer.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/scalar.o : src/src/arrow/scalar.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/string.o : src/src/arrow/util/string.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/utilmemory.o : src/src/arrow/util/memory.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/future.o : src/src/arrow/util/future.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/iterator.o : src/src/arrow/util/iterator.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/compression.o : src/src/arrow/util/compression.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/utf8.o : src/src/arrow/util/utf8.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/time.o : src/src/arrow/util/time.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/cpu_info.o : src/src/arrow/util/cpu_info.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/thread_pool.o : src/src/arrow/util/thread_pool.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/bit_util.o : src/src/arrow/util/bit_util.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/logging.o : src/src/arrow/util/logging.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/basic_decimal.o : src/src/arrow/util/basic_decimal.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/decimal.o : src/src/arrow/util/decimal.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/bit_block_counter.o : src/src/arrow/util/bit_block_counter.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/key_value_metadata.o : src/src/arrow/util/key_value_metadata.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/int_util.o : src/src/arrow/util/int_util.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/io_util.o : src/src/arrow/util/io_util.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/bitmap_ops.o : src/src/arrow/util/bitmap_ops.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/bitmap_builders.o : src/src/arrow/util/bitmap_builders.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/bit_run_reader.o : src/src/arrow/util/bit_run_reader.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/value_parsing.o : src/src/arrow/util/value_parsing.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/string_builder.o : src/src/arrow/util/string_builder.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/formatting.o : src/src/arrow/util/formatting.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/array_primitive.o : src/src/arrow/array/array_primitive.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/array_dict.o : src/src/arrow/array/array_dict.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder_binary.o : src/src/arrow/array/builder_binary.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder_union.o : src/src/arrow/array/builder_union.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/concatenate.o : src/src/arrow/array/concatenate.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/array_nested.o : src/src/arrow/array/array_nested.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/array_decimal.o : src/src/arrow/array/array_decimal.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder_primitive.o : src/src/arrow/array/builder_primitive.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/data.o : src/src/arrow/array/data.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/diff.o : src/src/arrow/array/diff.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder_nested.o : src/src/arrow/array/builder_nested.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder_decimal.o : src/src/arrow/array/builder_decimal.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder_dict.o : src/src/arrow/array/builder_dict.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/array_binary.o : src/src/arrow/array/array_binary.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder_adaptive.o : src/src/arrow/array/builder_adaptive.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/array_base.o : src/src/arrow/array/array_base.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/validate.o : src/src/arrow/array/validate.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder_base.o : src/src/arrow/array/builder_base.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/util.o : src/src/arrow/array/util.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/caching.o : src/src/arrow/io/caching.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/memory.o : src/src/arrow/io/memory.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/interfaces.o : src/src/arrow/io/interfaces.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/buffered.o : src/src/arrow/io/buffered.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/file.o : src/src/arrow/io/file.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/strtod.o : src/src/arrow/vendored/double-conversion/strtod.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/bignum.o : src/src/arrow/vendored/double-conversion/bignum.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/fixed-dtoa.o : src/src/arrow/vendored/double-conversion/fixed-dtoa.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/fast-dtoa.o : src/src/arrow/vendored/double-conversion/fast-dtoa.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/diy-fp.o : src/src/arrow/vendored/double-conversion/diy-fp.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/double-conversion.o : src/src/arrow/vendored/double-conversion/double-conversion.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/bignum-dtoa.o : src/src/arrow/vendored/double-conversion/bignum-dtoa.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/cached-powers.o : src/src/arrow/vendored/double-conversion/cached-powers.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/api_aggregate.o : src/src/arrow/compute/api_aggregate.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/exec.o : src/src/arrow/compute/exec.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/kernel.o : src/src/arrow/compute/kernel.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/registry.o : src/src/arrow/compute/registry.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/function.o : src/src/arrow/compute/function.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/cast.o : src/src/arrow/compute/cast.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/api_vector.o : src/src/arrow/compute/api_vector.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/api_scalar.o : src/src/arrow/compute/api_scalar.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/codegen_internal.o : src/src/arrow/compute/kernels/codegen_internal.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/column_scanner.o : src/src/parquet/column_scanner.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/statistics.o : src/src/parquet/statistics.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/internal_file_decryptor.o : src/src/parquet/internal_file_decryptor.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/column_writer.o : src/src/parquet/column_writer.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/encryption.o : src/src/parquet/encryption.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/file_reader.o : src/src/parquet/file_reader.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/properties.o : src/src/parquet/properties.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/encryption_internal.o : src/src/parquet/encryption_internal.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/internal_file_encryptor.o : src/src/parquet/internal_file_encryptor.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/types.o : src/src/parquet/types.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/encoding.o : src/src/parquet/encoding.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/metadata.o : src/src/parquet/metadata.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/printer.o : src/src/parquet/printer.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/level_conversion.o : src/src/parquet/level_conversion.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/deprecated_io.o : src/src/parquet/deprecated_io.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/file_writer.o : src/src/parquet/file_writer.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/schema.o : src/src/parquet/schema.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/platform.o : src/src/parquet/platform.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/column_reader.o : src/src/parquet/column_reader.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
96
parquet/parquet/makefile.bkup
Normal file
96
parquet/parquet/makefile.bkup
Normal file
@ -0,0 +1,96 @@
|
||||
#-----------------------------------------------------------------------------#
|
||||
|
||||
PARQUETDIR := /home/mario/Desktop/Record_Evolution/parquet-cpp
|
||||
ARROWDIR := /home/mario/Desktop/Record_Evolution/arrow/cpp/src
|
||||
|
||||
CPP := g++ -std=c++14
|
||||
OPT := -Wall -Woverflow -Wpedantic -Wextra -Waddress -Waligned-new -Walloc-zero
|
||||
|
||||
prepare : collect_parquet modify_parquet collect_arrow modify_arrow
|
||||
|
||||
collect_parquet :
|
||||
cp -r $(PARQUETDIR)/src/parquet ./
|
||||
cp $(PARQUETDIR)/examples/low-level-api/reader_writer.h ./
|
||||
cp $(PARQUETDIR)/examples/low-level-api/reader-writer.cc ./
|
||||
|
||||
modify_parquet :
|
||||
cp parquet/parquet_version.h.in parquet/parquet_version.h
|
||||
sed -i 's/ReadableFileInterface/ReadWriteFileInterface/g' parquet/util/memory.h
|
||||
sed -i 's/ReadableFileInterface/ReadWriteFileInterface/g' parquet/file_reader.h
|
||||
sed -i 's/arrow::Codec/arrow::util::Codec/g' parquet/util/memory.h
|
||||
sed -i 's/valid_bits_writer/valid_bits_offset/g' parquet/column_reader.h
|
||||
|
||||
collect_arrow :
|
||||
cp -r $(ARROWDIR)/arrow ./
|
||||
|
||||
modify_arrow :
|
||||
cp arrow/util/bit_util.h arrow/util/bit-util.h
|
||||
|
||||
collect_test :
|
||||
cp $(PARQUETDIR)/examples/low-level-api/reader-writer.cc ./
|
||||
|
||||
subst :
|
||||
sed -i 's/#include \"arrow\//\/\/#include \"arrow/g' parquet/properties.h
|
||||
|
||||
test :
|
||||
$(CPP) $(OPT) -I$(PWD) reader-writer.cc
|
||||
|
||||
clean :
|
||||
rm -r parquet/ arrow/
|
||||
rm reader-writer.cc reader_writer.h
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
|
||||
# choose shell
|
||||
SHELL:=/bin/bash
|
||||
|
||||
SRC = reader-writer
|
||||
|
||||
# specify path of cloned directory
|
||||
ARROWGIT := /home/mario/Desktop/Record_Evolution/arrow
|
||||
|
||||
filewriter : parquet/file_writer.cc
|
||||
$(CPP) -c $(OPT) $<
|
||||
|
||||
# build executable (and generate dependency file)
|
||||
readwrite : reader-writer.cc
|
||||
$(CPP) $(OPT) -MMD $< -I ./
|
||||
|
||||
# generate dependency file
|
||||
$(SRC).d : $(SRC).cc
|
||||
$(CPP) -c -MMD $< -I ./ -I $(ARROWGIT)/cpp/src/
|
||||
|
||||
# extract source dependencies
|
||||
extract-dep : $(SRC).d
|
||||
@# extract relevant dependencies
|
||||
cat $< | sed 's/ /\n/g' | awk 'NF' | grep -v '\\' | grep '\/' > deps.log
|
||||
cat deps.log | sed ':a;N;$!ba;s/\n/ /g' > headers.log
|
||||
cat headers.log | sed 's/.h$$/.cc/g' > sources.log
|
||||
@# copy required sources
|
||||
mkdir -p temp/
|
||||
cp --parents `cat headers.log` temp/
|
||||
cp --parents `cat sources.log` temp/ 2>/dev/null
|
||||
mv temp$(ARROWGIT)/cpp/src/* ./
|
||||
rm -r temp
|
||||
|
||||
clean-dep :
|
||||
rm -f deps.log headers.log sources.log $(SRC).d
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
# only use more recent and up to date repository arrow.git
|
||||
|
||||
# build arrow shared/static libraries
|
||||
build :
|
||||
cd arrow/cpp
|
||||
# cmake -LA to show all options
|
||||
cmake . -D ARROW_PARQUET=ON #ARROW_ARMV8_ARCH=armv8-a
|
||||
make
|
||||
|
||||
example :
|
||||
cd arrow/cpp/examples/parquet/low-level-api/
|
||||
g++ reader-writer.cc -I. -I../../../src/ -L../../../../cpp/build/release/ -larrow -lparquet
|
||||
|
||||
# set environment variable LD_LIBRARY_PATH=../../../../cpp/build/release/ before launching executable
|
||||
|
||||
|
||||
#------------------------------------------------------------------------------------#
|
||||
303
parquet/parquet/makefileobj
Normal file
303
parquet/parquet/makefileobj
Normal file
@ -0,0 +1,303 @@
|
||||
bin/type.o : src/src/arrow/type.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/result.o : src/src/arrow/result.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder.o : src/src/arrow/builder.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/tensor.o : src/src/arrow/tensor.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/table.o : src/src/arrow/table.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/extension_type.o : src/src/arrow/extension_type.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/device.o : src/src/arrow/device.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/memory_pool.o : src/src/arrow/memory_pool.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/datum.o : src/src/arrow/datum.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/record_batch.o : src/src/arrow/record_batch.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/compare.o : src/src/arrow/compare.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/visitor.o : src/src/arrow/visitor.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/chunked_array.o : src/src/arrow/chunked_array.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/status.o : src/src/arrow/status.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/pretty_print.o : src/src/arrow/pretty_print.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/sparse_tensor.o : src/src/arrow/sparse_tensor.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/buffer.o : src/src/arrow/buffer.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/scalar.o : src/src/arrow/scalar.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/string.o : src/src/arrow/util/string.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/memory.o : src/src/arrow/util/memory.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/future.o : src/src/arrow/util/future.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/iterator.o : src/src/arrow/util/iterator.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/compression.o : src/src/arrow/util/compression.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/utf8.o : src/src/arrow/util/utf8.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/time.o : src/src/arrow/util/time.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/cpu_info.o : src/src/arrow/util/cpu_info.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/thread_pool.o : src/src/arrow/util/thread_pool.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/bit_util.o : src/src/arrow/util/bit_util.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/logging.o : src/src/arrow/util/logging.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/basic_decimal.o : src/src/arrow/util/basic_decimal.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/decimal.o : src/src/arrow/util/decimal.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/bit_block_counter.o : src/src/arrow/util/bit_block_counter.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/key_value_metadata.o : src/src/arrow/util/key_value_metadata.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/int_util.o : src/src/arrow/util/int_util.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/io_util.o : src/src/arrow/util/io_util.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/bitmap_ops.o : src/src/arrow/util/bitmap_ops.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/bitmap_builders.o : src/src/arrow/util/bitmap_builders.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/bit_run_reader.o : src/src/arrow/util/bit_run_reader.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/value_parsing.o : src/src/arrow/util/value_parsing.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/string_builder.o : src/src/arrow/util/string_builder.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/formatting.o : src/src/arrow/util/formatting.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/array_primitive.o : src/src/arrow/array/array_primitive.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/array_dict.o : src/src/arrow/array/array_dict.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder_binary.o : src/src/arrow/array/builder_binary.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder_union.o : src/src/arrow/array/builder_union.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/concatenate.o : src/src/arrow/array/concatenate.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/array_nested.o : src/src/arrow/array/array_nested.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/array_decimal.o : src/src/arrow/array/array_decimal.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder_primitive.o : src/src/arrow/array/builder_primitive.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/data.o : src/src/arrow/array/data.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/diff.o : src/src/arrow/array/diff.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder_nested.o : src/src/arrow/array/builder_nested.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder_decimal.o : src/src/arrow/array/builder_decimal.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder_dict.o : src/src/arrow/array/builder_dict.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/array_binary.o : src/src/arrow/array/array_binary.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder_adaptive.o : src/src/arrow/array/builder_adaptive.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/array_base.o : src/src/arrow/array/array_base.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/validate.o : src/src/arrow/array/validate.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/builder_base.o : src/src/arrow/array/builder_base.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/util.o : src/src/arrow/array/util.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/caching.o : src/src/arrow/io/caching.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/memory.o : src/src/arrow/io/memory.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/interfaces.o : src/src/arrow/io/interfaces.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/buffered.o : src/src/arrow/io/buffered.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/file.o : src/src/arrow/io/file.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/strtod.o : src/src/arrow/vendored/double-conversion/strtod.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/bignum.o : src/src/arrow/vendored/double-conversion/bignum.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/fixed-dtoa.o : src/src/arrow/vendored/double-conversion/fixed-dtoa.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/fast-dtoa.o : src/src/arrow/vendored/double-conversion/fast-dtoa.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/diy-fp.o : src/src/arrow/vendored/double-conversion/diy-fp.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/double-conversion.o : src/src/arrow/vendored/double-conversion/double-conversion.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/bignum-dtoa.o : src/src/arrow/vendored/double-conversion/bignum-dtoa.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/cached-powers.o : src/src/arrow/vendored/double-conversion/cached-powers.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/api_aggregate.o : src/src/arrow/compute/api_aggregate.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/exec.o : src/src/arrow/compute/exec.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/kernel.o : src/src/arrow/compute/kernel.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/registry.o : src/src/arrow/compute/registry.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/function.o : src/src/arrow/compute/function.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/cast.o : src/src/arrow/compute/cast.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/api_vector.o : src/src/arrow/compute/api_vector.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/api_scalar.o : src/src/arrow/compute/api_scalar.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/codegen_internal.o : src/src/arrow/compute/kernels/codegen_internal.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/column_scanner.o : src/src/parquet/column_scanner.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/statistics.o : src/src/parquet/statistics.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/internal_file_decryptor.o : src/src/parquet/internal_file_decryptor.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/column_writer.o : src/src/parquet/column_writer.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/encryption.o : src/src/parquet/encryption.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/file_reader.o : src/src/parquet/file_reader.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/properties.o : src/src/parquet/properties.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/encryption_internal.o : src/src/parquet/encryption_internal.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/internal_file_encryptor.o : src/src/parquet/internal_file_encryptor.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/types.o : src/src/parquet/types.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/encoding.o : src/src/parquet/encoding.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/metadata.o : src/src/parquet/metadata.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/printer.o : src/src/parquet/printer.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/level_conversion.o : src/src/parquet/level_conversion.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/deprecated_io.o : src/src/parquet/deprecated_io.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/file_writer.o : src/src/parquet/file_writer.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/schema.o : src/src/parquet/schema.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/platform.o : src/src/parquet/platform.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
bin/column_reader.o : src/src/parquet/column_reader.cc
|
||||
$(CPP) $(CPPFLAGS) -c $< $(LIBS) -o $@
|
||||
|
||||
413
parquet/parquet/reader-writer.cc
Normal file
413
parquet/parquet/reader-writer.cc
Normal file
@ -0,0 +1,413 @@
|
||||
// Licensed to the Apache Software Foundation (ASF) under one
|
||||
// or more contributor license agreements. See the NOTICE file
|
||||
// distributed with this work for additional information
|
||||
// regarding copyright ownership. The ASF licenses this file
|
||||
// to you under the Apache License, Version 2.0 (the
|
||||
// "License"); you may not use this file except in compliance
|
||||
// with the License. You may obtain a copy of the License at
|
||||
//
|
||||
// http://www.apache.org/licenses/LICENSE-2.0
|
||||
//
|
||||
// Unless required by applicable law or agreed to in writing,
|
||||
// software distributed under the License is distributed on an
|
||||
// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
||||
// KIND, either express or implied. See the License for the
|
||||
// specific language governing permissions and limitations
|
||||
// under the License.
|
||||
|
||||
#include <cassert>
|
||||
#include <fstream>
|
||||
#include <iostream>
|
||||
#include <memory>
|
||||
|
||||
#include "reader_writer.h"
|
||||
|
||||
/*
|
||||
* This example describes writing and reading Parquet Files in C++ and serves as a
|
||||
* reference to the API.
|
||||
* The file contains all the physical data types supported by Parquet.
|
||||
* This example uses the RowGroupWriter API that supports writing RowGroups optimized for
|
||||
*memory consumption
|
||||
**/
|
||||
|
||||
/* Parquet is a structured columnar file format
|
||||
* Parquet File = "Parquet data" + "Parquet Metadata"
|
||||
* "Parquet data" is simply a vector of RowGroups. Each RowGroup is a batch of rows in a
|
||||
* columnar layout
|
||||
* "Parquet Metadata" contains the "file schema" and attributes of the RowGroups and their
|
||||
* Columns
|
||||
* "file schema" is a tree where each node is either a primitive type (leaf nodes) or a
|
||||
* complex (nested) type (internal nodes)
|
||||
* For specific details, please refer the format here:
|
||||
* https://github.com/apache/parquet-format/blob/master/LogicalTypes.md
|
||||
**/
|
||||
|
||||
constexpr int NUM_ROWS_PER_ROW_GROUP = 500;
|
||||
const char PARQUET_FILENAME[] = "parquet_cpp_example.parquet";
|
||||
|
||||
int main(int argc, char** argv) {
|
||||
/**********************************************************************************
|
||||
PARQUET WRITER EXAMPLE
|
||||
**********************************************************************************/
|
||||
// parquet::REQUIRED fields do not need definition and repetition level values
|
||||
// parquet::OPTIONAL fields require only definition level values
|
||||
// parquet::REPEATED fields require both definition and repetition level values
|
||||
try {
|
||||
// Create a local file output stream instance.
|
||||
using FileClass = ::arrow::io::FileOutputStream;
|
||||
std::shared_ptr<FileClass> out_file;
|
||||
PARQUET_ASSIGN_OR_THROW(out_file, FileClass::Open(PARQUET_FILENAME));
|
||||
|
||||
// Setup the parquet schema
|
||||
std::shared_ptr<GroupNode> schema = SetupSchema();
|
||||
|
||||
// Add writer properties
|
||||
parquet::WriterProperties::Builder builder;
|
||||
builder.compression(parquet::Compression::UNCOMPRESSED);
|
||||
std::shared_ptr<parquet::WriterProperties> props = builder.build();
|
||||
|
||||
// Create a ParquetFileWriter instance
|
||||
std::shared_ptr<parquet::ParquetFileWriter> file_writer =
|
||||
parquet::ParquetFileWriter::Open(out_file, schema, props);
|
||||
|
||||
// Append a RowGroup with a specific number of rows.
|
||||
parquet::RowGroupWriter* rg_writer = file_writer->AppendRowGroup();
|
||||
|
||||
// Write the Bool column
|
||||
parquet::BoolWriter* bool_writer =
|
||||
static_cast<parquet::BoolWriter*>(rg_writer->NextColumn());
|
||||
for (int i = 0; i < NUM_ROWS_PER_ROW_GROUP; i++) {
|
||||
bool value = ((i % 2) == 0) ? true : false;
|
||||
bool_writer->WriteBatch(1, nullptr, nullptr, &value);
|
||||
}
|
||||
|
||||
// Write the Int32 column
|
||||
parquet::Int32Writer* int32_writer =
|
||||
static_cast<parquet::Int32Writer*>(rg_writer->NextColumn());
|
||||
for (int i = 0; i < NUM_ROWS_PER_ROW_GROUP; i++) {
|
||||
int32_t value = i;
|
||||
int32_writer->WriteBatch(1, nullptr, nullptr, &value);
|
||||
}
|
||||
|
||||
// Write the Int64 column. Each row has repeats twice.
|
||||
parquet::Int64Writer* int64_writer =
|
||||
static_cast<parquet::Int64Writer*>(rg_writer->NextColumn());
|
||||
for (int i = 0; i < 2 * NUM_ROWS_PER_ROW_GROUP; i++) {
|
||||
int64_t value = i * 1000 * 1000;
|
||||
value *= 1000 * 1000;
|
||||
int16_t definition_level = 1;
|
||||
int16_t repetition_level = 0;
|
||||
if ((i % 2) == 0) {
|
||||
repetition_level = 1; // start of a new record
|
||||
}
|
||||
int64_writer->WriteBatch(1, &definition_level, &repetition_level, &value);
|
||||
}
|
||||
|
||||
// Write the INT96 column.
|
||||
parquet::Int96Writer* int96_writer =
|
||||
static_cast<parquet::Int96Writer*>(rg_writer->NextColumn());
|
||||
for (int i = 0; i < NUM_ROWS_PER_ROW_GROUP; i++) {
|
||||
parquet::Int96 value;
|
||||
value.value[0] = i;
|
||||
value.value[1] = i + 1;
|
||||
value.value[2] = i + 2;
|
||||
int96_writer->WriteBatch(1, nullptr, nullptr, &value);
|
||||
}
|
||||
|
||||
// Write the Float column
|
||||
parquet::FloatWriter* float_writer =
|
||||
static_cast<parquet::FloatWriter*>(rg_writer->NextColumn());
|
||||
for (int i = 0; i < NUM_ROWS_PER_ROW_GROUP; i++) {
|
||||
float value = static_cast<float>(i) * 1.1f;
|
||||
float_writer->WriteBatch(1, nullptr, nullptr, &value);
|
||||
}
|
||||
|
||||
// Write the Double column
|
||||
parquet::DoubleWriter* double_writer =
|
||||
static_cast<parquet::DoubleWriter*>(rg_writer->NextColumn());
|
||||
for (int i = 0; i < NUM_ROWS_PER_ROW_GROUP; i++) {
|
||||
double value = i * 1.1111111;
|
||||
double_writer->WriteBatch(1, nullptr, nullptr, &value);
|
||||
}
|
||||
|
||||
// Write the ByteArray column. Make every alternate values NULL
|
||||
parquet::ByteArrayWriter* ba_writer =
|
||||
static_cast<parquet::ByteArrayWriter*>(rg_writer->NextColumn());
|
||||
for (int i = 0; i < NUM_ROWS_PER_ROW_GROUP; i++) {
|
||||
parquet::ByteArray value;
|
||||
char hello[FIXED_LENGTH] = "parquet";
|
||||
hello[7] = static_cast<char>(static_cast<int>('0') + i / 100);
|
||||
hello[8] = static_cast<char>(static_cast<int>('0') + (i / 10) % 10);
|
||||
hello[9] = static_cast<char>(static_cast<int>('0') + i % 10);
|
||||
if (i % 2 == 0) {
|
||||
int16_t definition_level = 1;
|
||||
value.ptr = reinterpret_cast<const uint8_t*>(&hello[0]);
|
||||
value.len = FIXED_LENGTH;
|
||||
ba_writer->WriteBatch(1, &definition_level, nullptr, &value);
|
||||
} else {
|
||||
int16_t definition_level = 0;
|
||||
ba_writer->WriteBatch(1, &definition_level, nullptr, nullptr);
|
||||
}
|
||||
}
|
||||
|
||||
// Write the FixedLengthByteArray column
|
||||
parquet::FixedLenByteArrayWriter* flba_writer =
|
||||
static_cast<parquet::FixedLenByteArrayWriter*>(rg_writer->NextColumn());
|
||||
for (int i = 0; i < NUM_ROWS_PER_ROW_GROUP; i++) {
|
||||
parquet::FixedLenByteArray value;
|
||||
char v = static_cast<char>(i);
|
||||
char flba[FIXED_LENGTH] = {v, v, v, v, v, v, v, v, v, v};
|
||||
value.ptr = reinterpret_cast<const uint8_t*>(&flba[0]);
|
||||
|
||||
flba_writer->WriteBatch(1, nullptr, nullptr, &value);
|
||||
}
|
||||
|
||||
// Close the ParquetFileWriter
|
||||
file_writer->Close();
|
||||
|
||||
// Write the bytes to file
|
||||
DCHECK(out_file->Close().ok());
|
||||
} catch (const std::exception& e) {
|
||||
std::cerr << "Parquet write error: " << e.what() << std::endl;
|
||||
return -1;
|
||||
}
|
||||
|
||||
/**********************************************************************************
|
||||
PARQUET READER EXAMPLE
|
||||
**********************************************************************************/
|
||||
|
||||
try {
|
||||
// Create a ParquetReader instance
|
||||
std::unique_ptr<parquet::ParquetFileReader> parquet_reader =
|
||||
parquet::ParquetFileReader::OpenFile(PARQUET_FILENAME, false);
|
||||
|
||||
// Get the File MetaData
|
||||
std::shared_ptr<parquet::FileMetaData> file_metadata = parquet_reader->metadata();
|
||||
|
||||
// Get the number of RowGroups
|
||||
int num_row_groups = file_metadata->num_row_groups();
|
||||
assert(num_row_groups == 1);
|
||||
|
||||
// Get the number of Columns
|
||||
int num_columns = file_metadata->num_columns();
|
||||
assert(num_columns == 8);
|
||||
|
||||
// Iterate over all the RowGroups in the file
|
||||
for (int r = 0; r < num_row_groups; ++r) {
|
||||
// Get the RowGroup Reader
|
||||
std::shared_ptr<parquet::RowGroupReader> row_group_reader =
|
||||
parquet_reader->RowGroup(r);
|
||||
|
||||
int64_t values_read = 0;
|
||||
int64_t rows_read = 0;
|
||||
int16_t definition_level;
|
||||
int16_t repetition_level;
|
||||
int i;
|
||||
std::shared_ptr<parquet::ColumnReader> column_reader;
|
||||
|
||||
ARROW_UNUSED(rows_read); // prevent warning in release build
|
||||
|
||||
// Get the Column Reader for the boolean column
|
||||
column_reader = row_group_reader->Column(0);
|
||||
parquet::BoolReader* bool_reader =
|
||||
static_cast<parquet::BoolReader*>(column_reader.get());
|
||||
|
||||
// Read all the rows in the column
|
||||
i = 0;
|
||||
while (bool_reader->HasNext()) {
|
||||
bool value;
|
||||
// Read one value at a time. The number of rows read is returned. values_read
|
||||
// contains the number of non-null rows
|
||||
rows_read = bool_reader->ReadBatch(1, nullptr, nullptr, &value, &values_read);
|
||||
// Ensure only one value is read
|
||||
assert(rows_read == 1);
|
||||
// There are no NULL values in the rows written
|
||||
assert(values_read == 1);
|
||||
// Verify the value written
|
||||
bool expected_value = ((i % 2) == 0) ? true : false;
|
||||
assert(value == expected_value);
|
||||
i++;
|
||||
}
|
||||
|
||||
// Get the Column Reader for the Int32 column
|
||||
column_reader = row_group_reader->Column(1);
|
||||
parquet::Int32Reader* int32_reader =
|
||||
static_cast<parquet::Int32Reader*>(column_reader.get());
|
||||
// Read all the rows in the column
|
||||
i = 0;
|
||||
while (int32_reader->HasNext()) {
|
||||
int32_t value;
|
||||
// Read one value at a time. The number of rows read is returned. values_read
|
||||
// contains the number of non-null rows
|
||||
rows_read = int32_reader->ReadBatch(1, nullptr, nullptr, &value, &values_read);
|
||||
// Ensure only one value is read
|
||||
assert(rows_read == 1);
|
||||
// There are no NULL values in the rows written
|
||||
assert(values_read == 1);
|
||||
// Verify the value written
|
||||
assert(value == i);
|
||||
i++;
|
||||
}
|
||||
|
||||
// Get the Column Reader for the Int64 column
|
||||
column_reader = row_group_reader->Column(2);
|
||||
parquet::Int64Reader* int64_reader =
|
||||
static_cast<parquet::Int64Reader*>(column_reader.get());
|
||||
// Read all the rows in the column
|
||||
i = 0;
|
||||
while (int64_reader->HasNext()) {
|
||||
int64_t value;
|
||||
// Read one value at a time. The number of rows read is returned. values_read
|
||||
// contains the number of non-null rows
|
||||
rows_read = int64_reader->ReadBatch(1, &definition_level, &repetition_level,
|
||||
&value, &values_read);
|
||||
// Ensure only one value is read
|
||||
assert(rows_read == 1);
|
||||
// There are no NULL values in the rows written
|
||||
assert(values_read == 1);
|
||||
// Verify the value written
|
||||
int64_t expected_value = i * 1000 * 1000;
|
||||
expected_value *= 1000 * 1000;
|
||||
assert(value == expected_value);
|
||||
if ((i % 2) == 0) {
|
||||
assert(repetition_level == 1);
|
||||
} else {
|
||||
assert(repetition_level == 0);
|
||||
}
|
||||
i++;
|
||||
}
|
||||
|
||||
// Get the Column Reader for the Int96 column
|
||||
column_reader = row_group_reader->Column(3);
|
||||
parquet::Int96Reader* int96_reader =
|
||||
static_cast<parquet::Int96Reader*>(column_reader.get());
|
||||
// Read all the rows in the column
|
||||
i = 0;
|
||||
while (int96_reader->HasNext()) {
|
||||
parquet::Int96 value;
|
||||
// Read one value at a time. The number of rows read is returned. values_read
|
||||
// contains the number of non-null rows
|
||||
rows_read = int96_reader->ReadBatch(1, nullptr, nullptr, &value, &values_read);
|
||||
// Ensure only one value is read
|
||||
assert(rows_read == 1);
|
||||
// There are no NULL values in the rows written
|
||||
assert(values_read == 1);
|
||||
// Verify the value written
|
||||
parquet::Int96 expected_value;
|
||||
ARROW_UNUSED(expected_value); // prevent warning in release build
|
||||
expected_value.value[0] = i;
|
||||
expected_value.value[1] = i + 1;
|
||||
expected_value.value[2] = i + 2;
|
||||
for (int j = 0; j < 3; j++) {
|
||||
assert(value.value[j] == expected_value.value[j]);
|
||||
}
|
||||
i++;
|
||||
}
|
||||
|
||||
// Get the Column Reader for the Float column
|
||||
column_reader = row_group_reader->Column(4);
|
||||
parquet::FloatReader* float_reader =
|
||||
static_cast<parquet::FloatReader*>(column_reader.get());
|
||||
// Read all the rows in the column
|
||||
i = 0;
|
||||
while (float_reader->HasNext()) {
|
||||
float value;
|
||||
// Read one value at a time. The number of rows read is returned. values_read
|
||||
// contains the number of non-null rows
|
||||
rows_read = float_reader->ReadBatch(1, nullptr, nullptr, &value, &values_read);
|
||||
// Ensure only one value is read
|
||||
assert(rows_read == 1);
|
||||
// There are no NULL values in the rows written
|
||||
assert(values_read == 1);
|
||||
// Verify the value written
|
||||
float expected_value = static_cast<float>(i) * 1.1f;
|
||||
assert(value == expected_value);
|
||||
i++;
|
||||
}
|
||||
|
||||
// Get the Column Reader for the Double column
|
||||
column_reader = row_group_reader->Column(5);
|
||||
parquet::DoubleReader* double_reader =
|
||||
static_cast<parquet::DoubleReader*>(column_reader.get());
|
||||
// Read all the rows in the column
|
||||
i = 0;
|
||||
while (double_reader->HasNext()) {
|
||||
double value;
|
||||
// Read one value at a time. The number of rows read is returned. values_read
|
||||
// contains the number of non-null rows
|
||||
rows_read = double_reader->ReadBatch(1, nullptr, nullptr, &value, &values_read);
|
||||
// Ensure only one value is read
|
||||
assert(rows_read == 1);
|
||||
// There are no NULL values in the rows written
|
||||
assert(values_read == 1);
|
||||
// Verify the value written
|
||||
double expected_value = i * 1.1111111;
|
||||
assert(value == expected_value);
|
||||
i++;
|
||||
}
|
||||
|
||||
// Get the Column Reader for the ByteArray column
|
||||
column_reader = row_group_reader->Column(6);
|
||||
parquet::ByteArrayReader* ba_reader =
|
||||
static_cast<parquet::ByteArrayReader*>(column_reader.get());
|
||||
// Read all the rows in the column
|
||||
i = 0;
|
||||
while (ba_reader->HasNext()) {
|
||||
parquet::ByteArray value;
|
||||
// Read one value at a time. The number of rows read is returned. values_read
|
||||
// contains the number of non-null rows
|
||||
rows_read =
|
||||
ba_reader->ReadBatch(1, &definition_level, nullptr, &value, &values_read);
|
||||
// Ensure only one value is read
|
||||
assert(rows_read == 1);
|
||||
// Verify the value written
|
||||
char expected_value[FIXED_LENGTH] = "parquet";
|
||||
ARROW_UNUSED(expected_value); // prevent warning in release build
|
||||
expected_value[7] = static_cast<char>('0' + i / 100);
|
||||
expected_value[8] = static_cast<char>('0' + (i / 10) % 10);
|
||||
expected_value[9] = static_cast<char>('0' + i % 10);
|
||||
if (i % 2 == 0) { // only alternate values exist
|
||||
// There are no NULL values in the rows written
|
||||
assert(values_read == 1);
|
||||
assert(value.len == FIXED_LENGTH);
|
||||
assert(memcmp(value.ptr, &expected_value[0], FIXED_LENGTH) == 0);
|
||||
assert(definition_level == 1);
|
||||
} else {
|
||||
// There are NULL values in the rows written
|
||||
assert(values_read == 0);
|
||||
assert(definition_level == 0);
|
||||
}
|
||||
i++;
|
||||
}
|
||||
|
||||
// Get the Column Reader for the FixedLengthByteArray column
|
||||
column_reader = row_group_reader->Column(7);
|
||||
parquet::FixedLenByteArrayReader* flba_reader =
|
||||
static_cast<parquet::FixedLenByteArrayReader*>(column_reader.get());
|
||||
// Read all the rows in the column
|
||||
i = 0;
|
||||
while (flba_reader->HasNext()) {
|
||||
parquet::FixedLenByteArray value;
|
||||
// Read one value at a time. The number of rows read is returned. values_read
|
||||
// contains the number of non-null rows
|
||||
rows_read = flba_reader->ReadBatch(1, nullptr, nullptr, &value, &values_read);
|
||||
// Ensure only one value is read
|
||||
assert(rows_read == 1);
|
||||
// There are no NULL values in the rows written
|
||||
assert(values_read == 1);
|
||||
// Verify the value written
|
||||
char v = static_cast<char>(i);
|
||||
char expected_value[FIXED_LENGTH] = {v, v, v, v, v, v, v, v, v, v};
|
||||
assert(memcmp(value.ptr, &expected_value[0], FIXED_LENGTH) == 0);
|
||||
i++;
|
||||
}
|
||||
}
|
||||
} catch (const std::exception& e) {
|
||||
std::cerr << "Parquet read error: " << e.what() << std::endl;
|
||||
return -1;
|
||||
}
|
||||
|
||||
std::cout << "Parquet Writing and Reading Complete" << std::endl;
|
||||
|
||||
return 0;
|
||||
}
|
||||
71
parquet/parquet/reader_writer.h
Normal file
71
parquet/parquet/reader_writer.h
Normal file
@ -0,0 +1,71 @@
|
||||
// Licensed to the Apache Software Foundation (ASF) under one
|
||||
// or more contributor license agreements. See the NOTICE file
|
||||
// distributed with this work for additional information
|
||||
// regarding copyright ownership. The ASF licenses this file
|
||||
// to you under the Apache License, Version 2.0 (the
|
||||
// "License"); you may not use this file except in compliance
|
||||
// with the License. You may obtain a copy of the License at
|
||||
//
|
||||
// http://www.apache.org/licenses/LICENSE-2.0
|
||||
//
|
||||
// Unless required by applicable law or agreed to in writing,
|
||||
// software distributed under the License is distributed on an
|
||||
// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
|
||||
// KIND, either express or implied. See the License for the
|
||||
// specific language governing permissions and limitations
|
||||
// under the License.
|
||||
|
||||
#include <arrow/io/file.h>
|
||||
#include <arrow/util/logging.h>
|
||||
|
||||
#include <parquet/api/reader.h>
|
||||
#include <parquet/api/writer.h>
|
||||
|
||||
using parquet::ConvertedType;
|
||||
using parquet::Repetition;
|
||||
using parquet::Type;
|
||||
using parquet::schema::GroupNode;
|
||||
using parquet::schema::PrimitiveNode;
|
||||
|
||||
constexpr int FIXED_LENGTH = 10;
|
||||
|
||||
static std::shared_ptr<GroupNode> SetupSchema() {
|
||||
parquet::schema::NodeVector fields;
|
||||
// Create a primitive node named 'boolean_field' with type:BOOLEAN,
|
||||
// repetition:REQUIRED
|
||||
fields.push_back(PrimitiveNode::Make("boolean_field", Repetition::REQUIRED,
|
||||
Type::BOOLEAN, ConvertedType::NONE));
|
||||
|
||||
// Create a primitive node named 'int32_field' with type:INT32, repetition:REQUIRED,
|
||||
// logical type:TIME_MILLIS
|
||||
fields.push_back(PrimitiveNode::Make("int32_field", Repetition::REQUIRED, Type::INT32,
|
||||
ConvertedType::TIME_MILLIS));
|
||||
|
||||
// Create a primitive node named 'int64_field' with type:INT64, repetition:REPEATED
|
||||
fields.push_back(PrimitiveNode::Make("int64_field", Repetition::REPEATED, Type::INT64,
|
||||
ConvertedType::NONE));
|
||||
|
||||
fields.push_back(PrimitiveNode::Make("int96_field", Repetition::REQUIRED, Type::INT96,
|
||||
ConvertedType::NONE));
|
||||
|
||||
fields.push_back(PrimitiveNode::Make("float_field", Repetition::REQUIRED, Type::FLOAT,
|
||||
ConvertedType::NONE));
|
||||
|
||||
fields.push_back(PrimitiveNode::Make("double_field", Repetition::REQUIRED, Type::DOUBLE,
|
||||
ConvertedType::NONE));
|
||||
|
||||
// Create a primitive node named 'ba_field' with type:BYTE_ARRAY, repetition:OPTIONAL
|
||||
fields.push_back(PrimitiveNode::Make("ba_field", Repetition::OPTIONAL, Type::BYTE_ARRAY,
|
||||
ConvertedType::NONE));
|
||||
|
||||
// Create a primitive node named 'flba_field' with type:FIXED_LEN_BYTE_ARRAY,
|
||||
// repetition:REQUIRED, field_length = FIXED_LENGTH
|
||||
fields.push_back(PrimitiveNode::Make("flba_field", Repetition::REQUIRED,
|
||||
Type::FIXED_LEN_BYTE_ARRAY, ConvertedType::NONE,
|
||||
FIXED_LENGTH));
|
||||
|
||||
// Create a GroupNode named 'schema' using the primitive nodes defined above
|
||||
// This GroupNode is the root node of the schema tree
|
||||
return std::static_pointer_cast<GroupNode>(
|
||||
GroupNode::Make("schema", Repetition::REQUIRED, fields));
|
||||
}
|
||||
6
parquet/parquet/src_copy.sh
Executable file
6
parquet/parquet/src_copy.sh
Executable file
@ -0,0 +1,6 @@
|
||||
#!/bin/bash
|
||||
|
||||
mkdir src
|
||||
cat deps.log | while read f; do cp --parents $f src/; done;
|
||||
mv src/home/mario/Desktop/arrow/cpp/* src/
|
||||
rm -r src/home/
|
||||
171
parquet/parquet/src_setup.sh
Executable file
171
parquet/parquet/src_setup.sh
Executable file
@ -0,0 +1,171 @@
|
||||
#!/bin/bash
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
|
||||
# NOTE: before starting to extract the minimal required sources and dependencies
|
||||
# run
|
||||
# $ cd cpp/
|
||||
# $ cmake -D ARROW_PARQUET=ON
|
||||
# in the arrow repository
|
||||
|
||||
# provide
|
||||
# - local path of clone of https://github.com/apache/arrow.git
|
||||
# - name/path of main .hpp file of cython extension
|
||||
repo="$1"
|
||||
main="$2"
|
||||
depf="$3"
|
||||
|
||||
# check CLI arguments
|
||||
if [ -z "$repo" ] || [ -z "$main" ] || [ -z "$depf" ]; then
|
||||
echo "please provide..."
|
||||
echo "1. local path of arrow repository"
|
||||
echo "2. name of main .hpp/.cpp"
|
||||
echo "3. desired name of dependency file"
|
||||
echo -e "example:\n./setup-sources.sh /home/mario/Desktop/Record_Evolution/arrow/ reader-writer.cc deps.log"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo -e "extracting sources from/for \n1: ${repo}\n2: ${main}\n3: ${depf}\n"
|
||||
|
||||
# make sure the dependency file is empty
|
||||
rm -f ${depf}
|
||||
touch ${depf}
|
||||
|
||||
# define maximal recursion depth
|
||||
maxdep=8
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
|
||||
# define function to list dependencies of source file in repository recursively
|
||||
listDependencies()
|
||||
{
|
||||
rep="$1"
|
||||
src="$2"
|
||||
dep="$3"
|
||||
rec="$4"
|
||||
|
||||
echo -e "\nstarting 'listDependencies()' for\n1. ${rep}\n2. ${src}\n3. ${dep}\n4. ${rec}"
|
||||
|
||||
# generate dependency file (and remove resulting object file)
|
||||
echo -e "g++ -c -MMD ${src} -I ${rep}cpp/src/\n"
|
||||
g++ -c -MMD ${src} -I ${rep}cpp/src/
|
||||
|
||||
# derive name of dependency and object files
|
||||
depf=$(basename ${src} | sed 's/.cc/.d/g')
|
||||
objf=$(basename ${src} | sed 's/.cc/.o/g')
|
||||
rm ${objf}
|
||||
|
||||
# list dependencies by
|
||||
# 1. removing header
|
||||
# 2. remove source itself
|
||||
# 3. delete leading spaces
|
||||
# 4. delete trailing backslashs
|
||||
# 5. remove empty lines
|
||||
cat ${depf} | grep ${rep} | grep -v ${src} | tr -d "^ " | tr -d "\\\\" | awk 'NF' > listdep.log
|
||||
# rm ${depf}
|
||||
|
||||
while IFS= read -r fs
|
||||
do
|
||||
echo "$fs"
|
||||
# check if dependency is already in the list
|
||||
if grep -Fxq "$fs" "$dep"
|
||||
then
|
||||
echo "dep exist"
|
||||
else
|
||||
echo "dep does not exist yet => adding it"
|
||||
# add dependency to list
|
||||
echo "$fs" >> ${dep}
|
||||
# check for corresponding source file
|
||||
fssourc=$(echo ${fs} | sed 's/.h$/.cc/g' | sed 's/.hpp$/.cpp/g')
|
||||
echo ${fssourc}
|
||||
if [ -f "$fssourc" ]
|
||||
then
|
||||
echo "source file exists"
|
||||
# list nested dependencies
|
||||
if [ "$rec" -lt "$maxdep" ]
|
||||
then
|
||||
# increment recursion depth
|
||||
recinc=$(($rec+1))
|
||||
# call recursion
|
||||
listDependencies ${rep} ${fssourc} ${dep} ${recinc}
|
||||
else
|
||||
echo "maximal recursion depth exceeded"
|
||||
fi
|
||||
else
|
||||
echo "source file does not exist"
|
||||
fi
|
||||
fi
|
||||
echo ""
|
||||
done < listdep.log
|
||||
|
||||
# cat listdep.log | while read fs
|
||||
# do
|
||||
# echo $fs
|
||||
# # check if dependency is already in the list
|
||||
# inlist=$(cat listdep.log | grep ${fs} | wc -l)
|
||||
# echo ${inlist}
|
||||
# # check for any corresponding source files
|
||||
# # if [ -f ]
|
||||
# done
|
||||
}
|
||||
|
||||
#-----------------------------------------------------------------------------#
|
||||
|
||||
# call function to list dependencies (recursively)
|
||||
listDependencies ${repo} ${main} ${depf} 0
|
||||
|
||||
# # generate dependency file (and remove resulting object file)
|
||||
# echo -e "generate dependencies:\ng++ -c -MMD ${main} -I ./ -I ${repo}cpp/src/\n"
|
||||
# g++ -c -MMD ${main} -I ${repo}cpp/src/
|
||||
# rm $(echo ${main} | sed 's/.cc/.o/g')
|
||||
#
|
||||
# # derive name of dependency file
|
||||
# dep=$(echo ${main} | sed 's/.cc/.d/g')
|
||||
#
|
||||
# if [ -f "$dep" ]; then
|
||||
#
|
||||
# # list dependencies
|
||||
# cat ${dep} | sed 's/ /\n/g' | awk 'NF' | grep -v '\\' | grep '\/' > deps.log
|
||||
#
|
||||
# # extract list of headers
|
||||
# cat deps.log | sed ':a;N;$!ba;s/\n/ /g' > deps-headers.log
|
||||
# echo "list of required headers ($(cat deps.log | wc -l))"
|
||||
# cat deps-headers.log
|
||||
# echo ""
|
||||
#
|
||||
# # imply list of sources
|
||||
# cat deps.log | sed 's/.h$/.cc/g' | sed 's/.hpp$/.cpp/g' > sources_raw.log
|
||||
# cat sources_raw.log | while read f
|
||||
# do
|
||||
# if [ -f "$f" ]; then
|
||||
# echo $f >> sources_check.log
|
||||
# fi
|
||||
# done
|
||||
# cat sources_check.log | sed ':a;N;$!ba;s/\n/ /g' > deps-sources.log
|
||||
# echo "list of required sources ($(cat sources_check.log | wc -l))"
|
||||
# cat deps-sources.log
|
||||
# echo ""
|
||||
#
|
||||
# # remove all temporary files
|
||||
# rm ${dep} deps.log
|
||||
# rm sources_raw.log sources_check.log
|
||||
#
|
||||
# # copy required headers and sources
|
||||
# echo -e "copy required headers and sources"
|
||||
# mkdir temp/
|
||||
# cp --parents `cat deps-headers.log` temp/
|
||||
# cp --parents `cat deps-sources.log` temp/
|
||||
# mv temp${repo}cpp/src/* ./
|
||||
# rm -r temp
|
||||
#
|
||||
# # remove dependencies
|
||||
# #rm deps-headers.log deps-sources.log
|
||||
#
|
||||
# # show files
|
||||
# ls -lh
|
||||
#
|
||||
# else
|
||||
#
|
||||
# echo -e "\nERROR: failed to generate dependency file\n"
|
||||
#
|
||||
# fi
|
||||
26
parquet/pyarrow_arm/Dockerfile
Normal file
26
parquet/pyarrow_arm/Dockerfile
Normal file
@ -0,0 +1,26 @@
|
||||
|
||||
FROM ubuntu:19.10
|
||||
|
||||
RUN apt-get update -y && apt-get install -y \
|
||||
apt-utils \
|
||||
git g++ \
|
||||
make cmake \
|
||||
pkg-config \
|
||||
#build-essentials \
|
||||
python3 \
|
||||
python3-setuptools \
|
||||
cython3 \
|
||||
python3-numpy
|
||||
|
||||
RUN git clone https://github.com/apache/arrow.git --single-branch --depth=1
|
||||
|
||||
COPY . ./
|
||||
|
||||
RUN chmod u+x ./build_arrow_cpp.sh
|
||||
RUN chmod u+x ./build_arrow_python.sh
|
||||
RUN ./build_arrow_cpp.sh
|
||||
RUN ./build_arrow_python.sh
|
||||
|
||||
#RUN chmod u+x ./build_arrow.sh
|
||||
#CMD ["./build_arrow.sh"]
|
||||
CMD ["sleep 1d"]
|
||||
5
parquet/pyarrow_arm/build_and_test.sh
Normal file
5
parquet/pyarrow_arm/build_and_test.sh
Normal file
@ -0,0 +1,5 @@
|
||||
#!/bin/bash
|
||||
|
||||
docker build . --tag=pyarrowbuild:latest
|
||||
|
||||
docker run -it pyarrowbuild:latest /bin/bash
|
||||
65
parquet/pyarrow_arm/build_arrow.sh
Executable file
65
parquet/pyarrow_arm/build_arrow.sh
Executable file
@ -0,0 +1,65 @@
|
||||
#!/bin/bash
|
||||
|
||||
sleep infinity
|
||||
|
||||
startts=$(date)
|
||||
echo "starting build process at ${startts}..."
|
||||
|
||||
echo -e "\nhome directory is..."
|
||||
pwd
|
||||
|
||||
echo -e "\ncloning apache/arrow..."
|
||||
git clone https://github.com/apache/arrow.git --single-branch --depth=1
|
||||
|
||||
echo -e "\nls -lh /\n"
|
||||
ls -lh /
|
||||
|
||||
echo -e "\nls -lh arrow/\n"
|
||||
ls -lh arrow/
|
||||
|
||||
echo -e "\nls -lh arrow/python/\n"
|
||||
ls -lh arrow/python
|
||||
|
||||
|
||||
mkdir arrow/cpp/build
|
||||
pushd arrow/cpp/build
|
||||
|
||||
cmake -DCMAKE_INSTALL_PREFIX=$ARROW_HOME \
|
||||
-DCMAKE_INSTALL_LIBDIR=lib \
|
||||
-DARROW_WITH_BZ2=ON \
|
||||
-DARROW_WITH_ZLIB=ON \
|
||||
-DARROW_WITH_ZSTD=ON \
|
||||
-DARROW_WITH_LZ4=ON \
|
||||
-DARROW_WITH_SNAPPY=ON \
|
||||
-DARROW_WITH_BROTLI=ON \
|
||||
-DARROW_PARQUET=ON \
|
||||
-DARROW_PYTHON=ON \
|
||||
-DARROW_BUILD_TESTS=OFF \
|
||||
-DARROW_WITH_HDFS=OFF \
|
||||
..
|
||||
|
||||
make -j4
|
||||
make install
|
||||
popd
|
||||
|
||||
#cython --version
|
||||
cython3 --version
|
||||
|
||||
pushd arrow/python
|
||||
export ARROW_LIB_DIR=/lib/
|
||||
export PYARROW_WITH_PARQUET=1
|
||||
export PYARROW_WITH_CUDA=0
|
||||
export PYARROW_WITH_FlIGHT=0
|
||||
export PYARROW_WITH_DATASET=0
|
||||
export PYARROW_WITH_ORC=0
|
||||
export PYARROW_WITH_PLASMA=0
|
||||
export PYARROW_WITH_S3FS=0
|
||||
export PYARROW_WITH_HDFS=0
|
||||
export PYARROW_WITH_GANDIVA=0
|
||||
python3 setup.py build_ext --inplace
|
||||
popd
|
||||
|
||||
echo " started build process at ${startts} ..."
|
||||
finishts=$(date)
|
||||
echo "finishing build process at ${finishts}..."
|
||||
|
||||
23
parquet/pyarrow_arm/build_arrow_cpp.sh
Executable file
23
parquet/pyarrow_arm/build_arrow_cpp.sh
Executable file
@ -0,0 +1,23 @@
|
||||
#!/bin/bash
|
||||
|
||||
mkdir arrow/cpp/build
|
||||
pushd arrow/cpp/build
|
||||
|
||||
cmake -DCMAKE_INSTALL_PREFIX=$ARROW_HOME \
|
||||
-DCMAKE_INSTALL_LIBDIR=lib \
|
||||
-DARROW_WITH_BZ2=ON \
|
||||
-DARROW_WITH_ZLIB=ON \
|
||||
-DARROW_WITH_ZSTD=ON \
|
||||
-DARROW_WITH_LZ4=ON \
|
||||
-DARROW_WITH_SNAPPY=ON \
|
||||
-DARROW_WITH_BROTLI=ON \
|
||||
-DARROW_PARQUET=ON \
|
||||
-DARROW_PYTHON=ON \
|
||||
-DARROW_BUILD_TESTS=OFF \
|
||||
-DARROW_WITH_HDFS=OFF \
|
||||
-DARROW_WITH_IPC=OFF \
|
||||
..
|
||||
|
||||
make -j4
|
||||
make install
|
||||
popd
|
||||
15
parquet/pyarrow_arm/build_arrow_python.sh
Executable file
15
parquet/pyarrow_arm/build_arrow_python.sh
Executable file
@ -0,0 +1,15 @@
|
||||
#!/bin/bash
|
||||
|
||||
pushd arrow/python
|
||||
export PYARROW_WITH_PARQUET=1
|
||||
export PYARROW_WITH_CUDA=0
|
||||
export PYARROW_WITH_FlIGHT=0
|
||||
export PYARROW_WITH_DATASET=0
|
||||
export PYARROW_WITH_ORC=0
|
||||
export PYARROW_WITH_PLASMA=0
|
||||
export PYARROW_WITH_S3FS=0
|
||||
export PYARROW_WITH_HDFS=0
|
||||
export PYARROW_WITH_GANDIVA=0
|
||||
# python3 setup.py build_ext --inplace
|
||||
python3 setup.py install
|
||||
popd
|
||||
23
parquet/pyarrow_arm/makefile
Normal file
23
parquet/pyarrow_arm/makefile
Normal file
@ -0,0 +1,23 @@
|
||||
|
||||
build :
|
||||
docker build . --tag pyarrowbuild
|
||||
|
||||
run :
|
||||
docker run -it pyarrowbuild:latest
|
||||
|
||||
run-bash :
|
||||
docker run -it --volume=$(pwd)/build:/home pyarrowbuild:latest /bin/bash
|
||||
|
||||
run-volume :
|
||||
docker run -it -v /home/pirate/pyarrow/build/:/arrow/python/ pyarrowbuild:latest
|
||||
#sudo docker run -it --volume=$(pwd)/build:/home ubuntu:latest /bin/bash
|
||||
|
||||
rm-container :
|
||||
cont=$(docker ps -a | tail -n 26 | awk '{print $NF}' | sed ':a;N;$!ba;s/\n/ /g')
|
||||
echo ${cont}
|
||||
docker rm ${cont}
|
||||
|
||||
rm-image :
|
||||
img=$(docker image ls --quiet | sed ':a;N;$!ba;s/\n/ /g')
|
||||
docker image rm ${img}
|
||||
|
||||
18
parquet/pyarrow_arm/pyarrow_test.py
Normal file
18
parquet/pyarrow_arm/pyarrow_test.py
Normal file
@ -0,0 +1,18 @@
|
||||
|
||||
import pyarrow.parquet as pq
|
||||
import pyarrow.csv as pv
|
||||
|
||||
csvfile = 'pressureVacuum.csv'
|
||||
|
||||
tb = pv.read_csv(csvfile,parse_options=pv.ParseOptions(delimiter=','))
|
||||
|
||||
print(tb)
|
||||
|
||||
parquetfile = 'pressureVacuum.parquet'
|
||||
|
||||
pq.write_table(tb,parquetfile,compression='BROTLI')
|
||||
# {'NONE', 'SNAPPY', 'GZIP', 'LZO', 'BROTLI', 'LZ4', 'ZSTD'}
|
||||
|
||||
df = pq.read_table(parquetfile,columns=None)
|
||||
|
||||
print(df)
|
||||
8
parquet/pyarrow_arm/sync_pi.sh
Executable file
8
parquet/pyarrow_arm/sync_pi.sh
Executable file
@ -0,0 +1,8 @@
|
||||
#!/bin/bash
|
||||
|
||||
if [ -z "$1" ]
|
||||
then
|
||||
exit 1
|
||||
fi
|
||||
|
||||
scp $1 pirate@mf-pi-40:/home/pirate/pyarrow/
|
||||
@ -1,4 +1,4 @@
|
||||
include lib/*.hpp
|
||||
include *.hpp
|
||||
include *.cpp
|
||||
include *.pyx
|
||||
include *.pxd
|
||||
4
pip/bkup.pyproject.toml
Normal file
4
pip/bkup.pyproject.toml
Normal file
@ -0,0 +1,4 @@
|
||||
[build-system]
|
||||
requires = [
|
||||
"setuptools"
|
||||
]
|
||||
37
pip/makefile
Normal file
37
pip/makefile
Normal file
@ -0,0 +1,37 @@
|
||||
# --------------------------------------------------------------------------- #
|
||||
|
||||
SHELL := /bin/bash
|
||||
|
||||
publish-source: sdist upload
|
||||
publish-binary: bdist upload
|
||||
|
||||
prepdist: ../cython/py_imc_termite.pyx ../cython/imc_termite.pxd ../cython/py_imc_termite.cpp
|
||||
cp -v $? ./
|
||||
cp -v $(shell ls ../lib/imc_*.hpp) ./
|
||||
cat ../README.md | grep '^# IMCtermite' -A 50000 > ./README.md
|
||||
cp -v ../LICENSE ./
|
||||
|
||||
sdist: prepdist
|
||||
python3 setup.py sdist
|
||||
|
||||
# TODO use manylinux wheel to avoid ERROR "unsupported platform tag 'linux_x86_64'"
|
||||
# see: - https://github.com/pypa/manylinux
|
||||
bdist: prepdist
|
||||
python3 setup.py bdist_wheel
|
||||
|
||||
# authentication:
|
||||
# - username: __token__
|
||||
# - password: <token value including pypi-prefix>
|
||||
upload:
|
||||
python3 -m twine upload dist/$(shell ls -t dist/ | head -n1)
|
||||
|
||||
clean:
|
||||
rm -rvf dist/
|
||||
rm -rvf *.egg-info
|
||||
rm -rvf build/
|
||||
rm -rvf cython/
|
||||
rm -vf *.pyx *.pxd
|
||||
rm -vf *.cpp *.c *.hpp
|
||||
rm -vf README.md LICENSE
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
49
pip/setup.py
Normal file
49
pip/setup.py
Normal file
@ -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="IMCtermite",
|
||||
version="1.2.12",
|
||||
author="Record Evolution GmbH",
|
||||
author_email="mario.fink@record-evolution.de",
|
||||
maintainer="Record Evolution GmbH",
|
||||
license="MIT",
|
||||
description="Enables extraction of measurement data from binary files with extension 'raw' used by proprietary software imcFAMOS/imcSTUDIO and facilitates its storage in open source file formats",
|
||||
keywords="IMC raw imcFAMOS imcSTUDIO imcCRONOS",
|
||||
long_description=long_description,
|
||||
long_description_content_type="text/markdown",
|
||||
url="https://github.com/RecordEvolution/IMCtermite.git",
|
||||
project_urls={
|
||||
"Bug Tracker": "https://github.com/RecordEvolution/IMCtermite/issues",
|
||||
},
|
||||
classifiers=[
|
||||
"Programming Language :: Python :: 3",
|
||||
"License :: OSI Approved :: MIT License",
|
||||
"Operating System :: OS Independent",
|
||||
],
|
||||
ext_modules=[Extension("imc_termite",
|
||||
["py_imc_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,
|
||||
)
|
||||
],
|
||||
)
|
||||
@ -1 +0,0 @@
|
||||
2.0.0
|
||||
@ -1,29 +0,0 @@
|
||||
|
||||
from IMCtermite import imctermite
|
||||
|
||||
def show_results(imcraw) :
|
||||
|
||||
channels = imcraw.get_channels(False)
|
||||
print(channels)
|
||||
|
||||
channelsData = imcraw.get_channels(True)
|
||||
print("number of channels: " + str(len(channelsData)))
|
||||
|
||||
for (i,chn) in enumerate(channelsData) :
|
||||
print(str(i) + " | " + chn['name'])
|
||||
print(chn['xname'] + " | " + chn['xunit'])
|
||||
print(chn['xdata'][:10])
|
||||
print(chn['yname'] + " | " + chn['yunit'])
|
||||
print(chn['ydata'][:10])
|
||||
|
||||
print("")
|
||||
|
||||
# create instance of 'imctermite'
|
||||
imcraw = imctermite(b'samples/sampleA.raw')
|
||||
|
||||
show_results(imcraw)
|
||||
|
||||
# use previous instance of 'imctermite' to provide new file
|
||||
imcraw.submit_file(b'samples/sampleB.raw')
|
||||
|
||||
show_results(imcraw)
|
||||
@ -1,41 +0,0 @@
|
||||
|
||||
setup:
|
||||
cat ../README.md | grep '^# IMCtermite' -A 50000 > ./README.md
|
||||
cp -r ../lib ./
|
||||
cp -v ../LICENSE ./
|
||||
|
||||
setup-clean:
|
||||
rm -vf README.md LICENSE
|
||||
rm -rf lib/
|
||||
|
||||
build: setup
|
||||
python setup.py build
|
||||
|
||||
build-inplace: setup
|
||||
python setup.py build_ext --inplace
|
||||
|
||||
build-sdist: setup
|
||||
python setup.py sdist
|
||||
|
||||
build-bdist: setup
|
||||
python setup.py bdist
|
||||
|
||||
build-clean:
|
||||
python setup.py clean --all
|
||||
rm -vf imctermite*.so imctermite*.cpp
|
||||
rm -vf IMCtermite*.so IMCtermite*.cpp
|
||||
rm -rvf dist/ IMCtermite.egg-info/
|
||||
|
||||
cibuildwheel-build: setup
|
||||
cibuildwheel --platform linux
|
||||
|
||||
cibuildwheel-clean:
|
||||
rm -rvf wheelhouse/
|
||||
|
||||
pypi-upload:
|
||||
python -m twine upload dist/$(shell ls -t dist/ | head -n1)
|
||||
|
||||
clean: setup build-clean cibuildwheel-clean setup-clean
|
||||
|
||||
run-example:
|
||||
PYTHONPATH=$(pwd) python examples/usage_files.py
|
||||
@ -1,6 +0,0 @@
|
||||
[build-system]
|
||||
requires = ["setuptools", "wheel","Cython"]
|
||||
build-backend = "setuptools.build_meta"
|
||||
|
||||
[tool.cibuildwheel]
|
||||
before-all = ""
|
||||
@ -1,21 +0,0 @@
|
||||
|
||||
[metadata]
|
||||
name = IMCtermite
|
||||
description = Enables extraction of measurement data from binary files with extension 'raw' used by proprietary software imcFAMOS/imcSTUDIO and facilitates its storage in open source file formats
|
||||
long_description = file: README.md
|
||||
version = file: VERSION
|
||||
author = Record Evolution GmbH
|
||||
author_email = mario.fink@record-evolution.de
|
||||
maintainer = Record Evolution GmbH
|
||||
url= https://github.com/RecordEvolution/IMCtermite.git
|
||||
license = MIT License
|
||||
license_files = LICENSE
|
||||
keywords = IMC, raw, imcFAMOS, imcSTUDIO, imcCRONOS
|
||||
classifiers =
|
||||
Programming Language :: Python :: 3,
|
||||
License :: OSI Approved :: MIT License,
|
||||
Operating System :: OS Independent
|
||||
Topic :: Scientific/Engineering
|
||||
Topic :: Software Development :: Libraries :: Python Modules
|
||||
|
||||
[options]
|
||||
@ -1,22 +0,0 @@
|
||||
from setuptools import Extension, setup
|
||||
from Cython.Build import cythonize
|
||||
import os
|
||||
import sys
|
||||
|
||||
print("building on platform: "+sys.platform)
|
||||
|
||||
cmpArgs = {
|
||||
"linux": ['-std=c++17','-Wno-unused-variable'],
|
||||
"darwin": ['-std=c++17','-Wno-unused-variable'],
|
||||
"win32": ['/EHsc','/std:c++17']
|
||||
}
|
||||
|
||||
extension = Extension(
|
||||
"IMCtermite",
|
||||
sources=["IMCtermite.pyx"],
|
||||
extra_compile_args=cmpArgs[sys.platform]
|
||||
)
|
||||
|
||||
setup(
|
||||
ext_modules=cythonize(extension,language_level=3)
|
||||
)
|
||||
@ -1,11 +1,11 @@
|
||||
|
||||
import IMCtermite
|
||||
import imc_termite
|
||||
import json
|
||||
import os
|
||||
|
||||
# declare and initialize instance of "imctermite" by passing a raw-file
|
||||
try :
|
||||
imcraw = IMCtermite.imctermite(b"samples/exampleB.raw")
|
||||
imcraw = imc_termite.imctermite(b"samples/exampleB.raw")
|
||||
except RuntimeError as e :
|
||||
raise Exception("failed to load/parse raw-file: " + str(e))
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
|
||||
import IMCtermite
|
||||
import imc_termite
|
||||
import json
|
||||
import os
|
||||
|
||||
@ -15,7 +15,7 @@ for fl in rawlist1:
|
||||
|
||||
# declare and initialize instance of "imctermite" by passing a raw-file
|
||||
try :
|
||||
imcraw = IMCtermite.imctermite(fl.encode())
|
||||
imcraw = imc_termite.imctermite(fl.encode())
|
||||
except RuntimeError as e :
|
||||
raise Exception("failed to load/parse raw-file: " + str(e))
|
||||
|
||||
@ -24,7 +24,7 @@ for fl in rawlist1:
|
||||
print(json.dumps(channels,indent=4, sort_keys=False))
|
||||
|
||||
# print the channels into a specific directory
|
||||
imcraw.print_channels(b"./",ord(','))
|
||||
imcraw.print_channels(b"./")
|
||||
|
||||
# print all channels in single file
|
||||
imcraw.print_table(("./"+str(os.path.basename(fl).split('.')[0])+"_allchannels.csv").encode())
|
||||
@ -1,12 +1,12 @@
|
||||
|
||||
import IMCtermite
|
||||
import imc_termite
|
||||
import json
|
||||
import os
|
||||
import datetime
|
||||
|
||||
# declare and initialize instance of "imctermite" by passing a raw-file
|
||||
try :
|
||||
imcraw = IMCtermite.imctermite(b"samples/sampleB.raw")
|
||||
imcraw = imc_termite.imctermite(b"samples/sampleB.raw")
|
||||
except RuntimeError as e :
|
||||
raise Exception("failed to load/parse raw-file: " + str(e))
|
||||
|
||||
@ -12,7 +12,6 @@
|
||||
|
||||
const std::string gittag("TAGSTRING");
|
||||
const std::string githash("HASHSTRING");
|
||||
const std::string timestamp("TIMESTAMPSTRING");
|
||||
|
||||
//---------------------------------------------------------------------------//
|
||||
|
||||
@ -128,13 +127,13 @@ optkeys parse_args(int argc, char* argv[], bool list_args = false)
|
||||
|
||||
void show_version()
|
||||
{
|
||||
std::cout<<"imctermite ["<<gittag<<"-g"<<githash<<"-"<<timestamp<<"]"<<"\n";
|
||||
std::cout<<"imctermite ["<<gittag<<"-g"<<githash<<"]"<<"\n";
|
||||
}
|
||||
|
||||
void show_usage()
|
||||
{
|
||||
std::cout<<"\n"
|
||||
<<"imctermite ["<<gittag<<"-g"<<githash<<"-"<<timestamp<<"] (https://github.com/RecordEvolution/IMCtermite.git)"
|
||||
<<"imctermite ["<<gittag<<"-g"<<githash<<"] (https://github.com/RecordEvolution/IMCtermite.git)"
|
||||
<<"\n\n"
|
||||
<<"Decode IMC raw files and dump data as *.csv"
|
||||
<<"\n\n"
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user