Merge pull request #3 from atomprobe-tc/add_env_support

Add support for env ranging definitions and pos to csv reconstructions, also started with pycodestyle, pylinting, and mypy code quality refactoring

CHANGELOG.md

@@ -1,6 +1,4 @@
 ## Changelog
-**v0.0.7**
-- Added Matlab code for extracting ranging definitions from Matlab figures to text
-- Added FIG parser for creating proper molecular ion class instances of from these ranging definitions
-- Fixed bug that the nuclid list did not show the mass number of isotopes
+**v0.2**
+
 

dev-requirements.txt

@@ -14,7 +14,9 @@ argon2-cffi==21.3.0
 argon2-cffi-bindings==21.2.0
     # via argon2-cffi
 ase==3.19.0
-    # via ifes-apt-tc-data-modeling (pyproject.toml)
+    # via ifes_apt_tc_data_modeling (pyproject.toml)
+astroid==3.0.2
+    # via pylint
 asttokens==2.2.1
     # via stack-data
 attrs==23.1.0
@@ -53,20 +55,24 @@ decorator==5.1.1
     # via ipython
 defusedxml==0.7.1
     # via nbconvert
+dill==0.3.7
+    # via pylint
 docutils==0.19
     # via readme-renderer
 executing==1.2.0
     # via stack-data
 fastjsonschema==2.16.3
     # via nbformat
+flatdict==4.0.1
+    # via ifes_apt_tc_data_modeling (pyproject.toml)
 fonttools==4.39.3
     # via matplotlib
 h5grove==1.3.0
     # via jupyterlab-h5web
 h5py==3.8.0
     # via
     #   h5grove
-    #   ifes-apt-tc-data-modeling (pyproject.toml)
+    #   ifes_apt_tc_data_modeling (pyproject.toml)
     #   jupyterlab-h5web
 idna==3.4
     # via
@@ -88,6 +94,8 @@ ipython-genutils==0.2.0
     # via
     #   nbclassic
     #   notebook
+isort==5.13.2
+    # via pylint
 jaraco-classes==3.2.3
     # via keyring
 jedi==0.18.2
@@ -136,9 +144,9 @@ jupyter-server==1.24.0
     #   nbclassic
     #   notebook-shim
 jupyterlab==3.5.3
-    # via ifes-apt-tc-data-modeling (pyproject.toml)
+    # via ifes_apt_tc_data_modeling (pyproject.toml)
 jupyterlab-h5web==7.1.1
-    # via ifes-apt-tc-data-modeling (pyproject.toml)
+    # via ifes_apt_tc_data_modeling (pyproject.toml)
 jupyterlab-pygments==0.2.2
     # via nbconvert
 jupyterlab-server==2.22.1
@@ -161,6 +169,8 @@ matplotlib-inline==0.1.6
     # via
     #   ipykernel
     #   ipython
+mccabe==0.7.0
+    # via pylint
 mdurl==0.1.2
     # via markdown-it-py
 mistune==2.0.5
@@ -171,6 +181,10 @@ mpmath==1.3.0
     # via sympy
 msgpack==1.0.7
     # via blosc2
+mypy==1.8.0
+    # via ifes_apt_tc_data_modeling (pyproject.toml)
+mypy-extensions==1.0.0
+    # via mypy
 nbclassic==0.5.6
     # via
     #   jupyterlab
@@ -211,7 +225,7 @@ numpy==1.24.3
     #   contourpy
     #   h5grove
     #   h5py
-    #   ifes-apt-tc-data-modeling (pyproject.toml)
+    #   ifes_apt_tc_data_modeling (pyproject.toml)
     #   matplotlib
     #   numexpr
     #   pandas
@@ -231,7 +245,7 @@ packaging==23.1
     #   nbconvert
     #   tables
 pandas==2.0.1
-    # via ifes-apt-tc-data-modeling (pyproject.toml)
+    # via ifes_apt_tc_data_modeling (pyproject.toml)
 pandocfilters==1.5.0
     # via nbconvert
 parso==0.8.3
@@ -245,7 +259,9 @@ pillow==9.5.0
 pkginfo==1.9.6
     # via twine
 platformdirs==3.5.0
-    # via jupyter-core
+    # via
+    #   jupyter-core
+    #   pylint
 prometheus-client==0.16.0
     # via
     #   jupyter-server
@@ -265,6 +281,8 @@ py-cpuinfo==9.0.0
     # via
     #   blosc2
     #   tables
+pycodestyle==2.11.1
+    # via ifes_apt_tc_data_modeling (pyproject.toml)
 pycparser==2.21
     # via cffi
 pygments==2.15.1
@@ -273,6 +291,8 @@ pygments==2.15.1
     #   nbconvert
     #   readme-renderer
     #   rich
+pylint==3.0.3
+    # via ifes_apt_tc_data_modeling (pyproject.toml)
 pyparsing==3.0.9
     # via matplotlib
 pyrsistent==0.19.3
@@ -292,7 +312,7 @@ pyzmq==25.0.2
     #   nbclassic
     #   notebook
 radioactivedecay==0.4.17
-    # via ifes-apt-tc-data-modeling (pyproject.toml)
+    # via ifes_apt_tc_data_modeling (pyproject.toml)
 readme-renderer==37.3
     # via twine
 requests==2.29.0
@@ -331,7 +351,7 @@ stack-data==0.6.2
 sympy==1.11.1
     # via radioactivedecay
 tables==3.9.2
-    # via ifes-apt-tc-data-modeling (pyproject.toml)
+    # via ifes_apt_tc_data_modeling (pyproject.toml)
 terminado==0.17.1
     # via
     #   jupyter-server
@@ -343,6 +363,8 @@ tinycss2==1.2.1
     # via nbconvert
 tomli==2.0.1
     # via jupyterlab
+tomlkit==0.12.3
+    # via pylint
 tornado==6.3.1
     # via
     #   ipykernel
@@ -367,7 +389,9 @@ traitlets==5.9.0
     #   nbformat
     #   notebook
 twine==4.0.2
-    # via ifes-apt-tc-data-modeling (pyproject.toml)
+    # via ifes_apt_tc_data_modeling (pyproject.toml)
+typing-extensions==4.9.0
+    # via mypy
 tzdata==2023.3
     # via pandas
 urllib3==1.26.15
@@ -382,6 +406,8 @@ webencodings==0.5.1
     #   tinycss2
 websocket-client==1.5.1
     # via jupyter-server
+xmltodict==0.13.0
+    # via ifes_apt_tc_data_modeling (pyproject.toml)
 zipp==3.15.0
     # via importlib-metadata
 

ifes_apt_tc_data_modeling/__init__.py

@@ -1,4 +1,3 @@
-# Init file
 #
 # Copyright The NOMAD Authors.
 #

ifes_apt_tc_data_modeling/apt/README.md

@@ -0,0 +1,3 @@
+## Getting started
+AMETEK/Cameca APT file format used in IVAS/APSuite.
+https://github.com/CamecaAPT/cameca-customanalysis-interface/wiki/IonData:-Sections

ifes_apt_tc_data_modeling/apt/__init__.py

@@ -1,4 +1,3 @@
-# Init file
 #
 # Copyright The NOMAD Authors.
 #

ifes_apt_tc_data_modeling/apt/apt6_headers.py

@@ -1,4 +1,3 @@
-# AMETEK APT(6) data exchange file reader used by atom probe microscopists.
 #
 # Copyright The NOMAD Authors.
 #
@@ -17,7 +16,7 @@
 # limitations under the License.
 #
 
-# pylint: disable=no-member,duplicate-code
+"""AMETEK APT(6) data exchange file reader used by atom probe microscopists."""
 
 import numpy as np
 
@@ -32,13 +31,13 @@ class AptFileHeaderMetadata():
     # when developing the parser for their vendor file format
     def __init__(self):
         # file format signature
-        self.c_signature = string_to_typed_nparray('APT\0', 4, np.uint8)
+        self.c_signature = string_to_typed_nparray("APT\0", 4, np.uint8)
         # byte length of the file header
         self.i_header_size = np.int32(540)
         # version number of the file header, currently expecting 2
         self.i_header_version = np.int32(2)
         # original filename, i.e. *.apt filename, null-terminated UTF-16 !
-        self.wc_filename = string_to_typed_nparray('', 256, np.uint16)
+        self.wc_filename = string_to_typed_nparray("", 256, np.uint16)
         # file creation time
         # according to AMETEK is implemented as a VisualStudio C++ FILETIME
         # 64-bit value, which represents the number of 100-nanosecond intervals
@@ -50,39 +49,34 @@ def __init__(self):
     @classmethod
     def get_numpy_struct(cls) -> np.dtype:
         """Create customized numpy struct to read a file header at once."""
-        return np.dtype([('cSignature', np.uint8, (4,)),
-                         ('iHeaderSize', np.int32),
-                         ('iHeaderVersion', np.int32),
-                         ('wcFilename', np.uint16, 256),
-                         ('ftCreationTime', np.uint64),
-                         ('llIonCount', np.uint64)])
+        return np.dtype([("cSignature", np.uint8, (4,)),
+                         ("iHeaderSize", np.int32),
+                         ("iHeaderVersion", np.int32),
+                         ("wcFilename", np.uint16, 256),
+                         ("ftCreationTime", np.uint64),
+                         ("llIonCount", np.uint64)])
 
     def set_ll_ion_count(self, value: np.uint64):
         """Check and set total ion count."""
-        assert isinstance(value, np.uint64), \
-            'llIonCount needs to be an int!'
-        assert value > 0, \
-            'llIonCount needs to be positive and not zero!'
-        assert value <= np.iinfo(np.uint64).max, \
-            'llIonCount is too large, needs to map to np.uint64!'
+        if isinstance(value, np.uint64) is False:
+            raise ValueError(f"llIonCount {value} needs to be an uint64!")
+        if value <= 0:
+            raise ValueError(f"llIonCount {value} needs to be positive and not zero!")
+        if value > np.iinfo(np.uint64).max:
+            raise ValueError(f"llIonCount is too large {value}, needs to map to np.uint64!")
         self.ll_ion_count = np.uint64(value)
 
     def matches(self, found_header: np.ndarray) -> bool:
         """Compare a read header against expectation."""
-        assert np.array_equal(self.c_signature,
-                              found_header['cSignature'][0],
-                              equal_nan=True), \
-            'Header cSignature differs!'
-        assert self.i_header_size \
-            == found_header['iHeaderSize'][0], \
-            'Header iHeaderSize differs!'
-        assert self.i_header_version \
-            == found_header['iHeaderVersion'][0], \
-            'Header iHeaderVersion differs!'
-        assert found_header['llIonCount'][0] > 0, \
-            'Header indicates there are no ions in the file!'
-
-        self.set_ll_ion_count(found_header['llIonCount'][0])
+        if np.array_equal(self.c_signature, found_header["cSignature"][0], equal_nan=True) is False:
+            raise ValueError("Header cSignature differs!")
+        if self.i_header_size != found_header["iHeaderSize"][0]:
+            raise ValueError("Header iHeaderSize differs!")
+        if self.i_header_version != found_header["iHeaderVersion"][0]:
+            raise ValueError("Header iHeaderVersion differs!")
+        if found_header["llIonCount"][0] <= 0:
+            raise ValueError("Header indicates there are no ions in the file!")
+        self.set_ll_ion_count(found_header["llIonCount"][0])
         return True