jupyter-analysis-tools 1.1.0__py3-none-any.whl → 1.2.0__py3-none-any.whl

jupyter_analysis_tools/__init__.py

@@ -1,11 +1,11 @@
 # -*- coding: utf-8 -*-
 # __init__.py
 
-__version__ = "1.1.0"
+__version__ = "1.2.0"
 
 from .binning import reBin
 from .git import checkRepo, isNBstripoutActivated, isNBstripoutInstalled, isRepo
-from .readdata import readdata
+from .readdata import readdata, readPDHmeta, readSSF
 from .readdata import readdata as readPDH
 from .utils import setLocaleUTF8
 from .widgets import PathSelector, showBoolStatus

jupyter_analysis_tools/readdata.py

@@ -1,18 +1,22 @@
 # -*- coding: utf-8 -*-
 # readdata.py
 
-import os
+import json
+import warnings
+import xml.etree.ElementTree as et
+from pathlib import Path
 
 import pandas as pd
 
 
-def readdata(fn, q_range=None, read_csv_args=None, print_filename=True):
+def readdata(fpath, q_range=None, read_csv_args=None, print_filename=True):
     """Read a datafile pandas Dataframe
     extract a file_name
     select q-range: q_min <= q <= q_max
     """
+    fpath = Path(fpath)
     if print_filename:
-        print(f"Reading file '{fn}'")
+        print(f"Reading file '{str(fpath)}'")
     if read_csv_args is None:
         read_csv_args = dict()
     if "sep" not in read_csv_args:
@@ -23,10 +27,10 @@ def readdata(fn, q_range=None, read_csv_args=None, print_filename=True):
         read_csv_args.update(index_col=False)
     # print("f_read_data, read_csv_args:", read_csv_args) # for debugging
 
-    _, file_ext = os.path.splitext(fn)
+    file_ext = fpath.suffix
     if file_ext.lower() == ".pdh":  # for PDH files
         nrows = pd.read_csv(
-            fn,
+            fpath,
             skiprows=2,
             nrows=1,
             usecols=[
@@ -36,12 +40,117 @@ def readdata(fn, q_range=None, read_csv_args=None, print_filename=True):
             header=None,
         ).values[0, 0]
         read_csv_args.update(skiprows=5, nrows=nrows)
-    df_data = pd.read_csv(fn, **read_csv_args)
+    df = pd.read_csv(fpath, **read_csv_args)
 
     # select q-range
     if q_range is not None:
         q_min, q_max = q_range
-        df_data = df_data[(df_data.q > q_min) & (df_data.q < q_max)]
+        df = df[(df.q > q_min) & (df.q < q_max)]
 
-    file_name = os.path.basename(fn).split("[")[0]
-    return df_data, file_name
+    filename = fpath.stem.split("[")[0]
+    return df, filename
+
+
+def convertValue(val):
+    val = val.strip()
+    try:
+        return int(val)
+    except ValueError:
+        try:
+            return float(val)
+        except ValueError:
+            pass
+    return val
+
+def xmlPDHToDict(root):
+    result = {}
+    stack = [(root, result)]
+    while stack:
+        elem, parentCont = stack.pop()
+        elemCont = {}
+        key = elem.attrib.pop("key", None)
+        idx = -1
+        if (not len(list(elem)) and not len(elem.attrib)
+            and not (elem.text and len(elem.text.strip()))):
+            continue # skip empty elements with a key only early
+        if elem.tag == "list":
+            elemCont = []
+        else: # add attributes & values to dict
+            # Attach text, if any
+            if elem.text and len(elem.text.strip()):
+                if elem.tag in ("value", "reference"):
+                    elemCont["value"] = convertValue(elem.text)
+                else:
+                    elemCont["#text"] = convertValue(elem.text)
+            # Attach attributes, if any
+            if elem.attrib:
+                elemCont.update({k: convertValue(v) for k, v in elem.attrib.items() if len(v.strip())})
+            if key == "unit" and "value" in elemCont: # fix some units
+                elemCont["value"] = elemCont["value"].replace("_", "")
+            if "unit" in elemCont:
+                elemCont["unit"] = elemCont["unit"].replace("_", "")
+            # reduce the extracted dict&attributes
+            idx = elemCont.get("index", -1) # insert last/append if no index given
+            value = elemCont.get("value", None)
+            if value is not None and (len(elemCont) == 1
+                                      or (len(elemCont) == 2 and "index" in elemCont)):
+                elemCont = value # contains value only
+        parentKey = elem.tag
+        if key is not None and parentKey in ("list", "value", "group"):
+            # skip one level in hierarchy for these generic containers
+            parentKey = key
+            key = None
+        try:
+            if isinstance(parentCont, list):
+                parentCont.insert(idx, elemCont)
+            elif parentKey not in parentCont: # add as new list
+                if key is None: # make a list
+                    parentCont[parentKey] = elemCont
+                else: # have a key
+                    parentCont[parentKey] = {key: elemCont}
+            else: # parentKey exists already
+                if (not isinstance(parentCont[parentKey], list) and
+                    not isinstance(parentCont[parentKey], dict)):
+                    # if its a plain value before, make a list out of it and append in next step
+                    parentCont[parentKey] = [parentCont[parentKey]]
+                if isinstance(parentCont[parentKey], list):
+                    parentCont[parentKey].append(elemCont)
+                elif key is not None:
+                    parentCont[parentKey].update({key: elemCont})
+                else: # key is None
+                    parentCont[parentKey].update(elemCont)
+        except AttributeError:
+            raise
+        # reversed for correct order
+        stack += [(child, elemCont) for child in reversed(list(elem))]
+    # fix some entry values, weird Anton Paar PDH format
+    try:
+        oldts = result["fileinfo"]["parameter"]["DateTime"]["value"]
+        delta = (39*365+10)*24*3600 # timestamp seems to be based on around 2009-01-01 (a day give or take)
+        # make it compatible to datetime.datetime routines
+        result["fileinfo"]["parameter"]["DateTime"]["value"] = oldts+delta
+    except KeyError:
+        pass
+    return result
+
+def readPDHmeta(fp):
+    fp = Path(fp)
+    if fp.suffix.lower() != ".pdh":
+        warnings.warn("readPDHmeta() supports .pdh files only!")
+        return # for PDH files
+    lines = ""
+    with open(fp) as fd:
+        lines = fd.readlines()
+    nrows = int(lines[2].split()[0])
+    xml = "".join(lines[nrows+5:])
+    return xmlPDHToDict(et.fromstring(xml))
+
+def readSSF(fp):
+    fp = Path(fp)
+    if fp.suffix.lower() != ".ssf":
+        warnings.warn("readSession() supports .ssf files only!")
+        return  # for PDH files
+    data = ""
+    with open(fp, encoding='utf-8-sig') as fd:
+        data = fd.read()
+    return xmlPDHToDict(et.fromstring(data))

{jupyter_analysis_tools-1.1.0.dist-info → jupyter_analysis_tools-1.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: jupyter-analysis-tools
-Version: 1.1.0
+Version: 1.2.0
 Summary: Yet another Python library with helpers and utilities for data analysis and processing.
 Author-email: Ingo Breßler <dev@ingobressler.net>
 License: MIT license
@@ -53,8 +53,8 @@ Yet another Python library with helpers and utilities for data analysis and proc
     :target: https://pypi.org/project/jupyter-analysis-tools
     :alt: PyPI Package latest release
 
-.. |commits-since| image:: https://img.shields.io/github/commits-since/BAMresearch/jupyter-analysis-tools/v1.1.0.svg
-    :target: https://github.com/BAMresearch/jupyter-analysis-tools/compare/v1.1.0...main
+.. |commits-since| image:: https://img.shields.io/github/commits-since/BAMresearch/jupyter-analysis-tools/v1.2.0.svg
+    :target: https://github.com/BAMresearch/jupyter-analysis-tools/compare/v1.2.0...main
     :alt: Commits since latest release
 
 .. |license| image:: https://img.shields.io/pypi/l/jupyter-analysis-tools.svg
@@ -127,6 +127,20 @@ Note, to combine the coverage data from all the tox environments run:
 
 # CHANGELOG
 
+## v1.2.0 (2025-07-11)
+
+### Features
+
+* readdata: readSSF() renamed from readSession(), tests added with expected JSON output ([`e2197f6`](https://github.com/BAMresearch/jupyter-analysis-tools/commit/e2197f6bcb032c1bc1a9a7435e024dda763228c4))
+
+* readPDHmeta: routine for reading metadata part from .PDH and .SSF files ([`ea6a1d5`](https://github.com/BAMresearch/jupyter-analysis-tools/commit/ea6a1d554f3763fc05022ae8e4e8909f0993cd43))
+
+### Testing
+
+* readdata: path separator depends on platform ([`1b2866f`](https://github.com/BAMresearch/jupyter-analysis-tools/commit/1b2866f13307c2cf2dedc59f36d7372442ddbfd8))
+
+* readdata: testdata files and testing, using pathlib instead of old os.path ([`aeacfa4`](https://github.com/BAMresearch/jupyter-analysis-tools/commit/aeacfa4a949d7293f2cd3ce5e3004fddf20ecc02))
+
 ## v1.1.0 (2025-07-10)
 
 ### Bug fixes

{jupyter_analysis_tools-1.1.0.dist-info → jupyter_analysis_tools-1.2.0.dist-info}/RECORD

@@ -1,16 +1,16 @@
-jupyter_analysis_tools/__init__.py,sha256=I4Vdvl5uMDvIcs12ZZlMYaFzLrCrUerH5ZkWzgSKhUs,343
+jupyter_analysis_tools/__init__.py,sha256=qwt3D2fugc238WYSAYOpSmy9EqAxHIq45WkHLCgqjGQ,365
 jupyter_analysis_tools/analysis.py,sha256=AiAvUO648f0PYXqLfal1kDH926neasE5c1RYFu9wtYg,1768
 jupyter_analysis_tools/binning.py,sha256=d6eXRC3IOnnJIF25OfEASyWedT71EX2nF7jAgGJ9suQ,14536
 jupyter_analysis_tools/datalocations.py,sha256=BakfiZOMcBwp-_DAn7l57lGWZmZGNnk0j73V75nLBUA,4322
 jupyter_analysis_tools/distrib.py,sha256=uyh2jXDdXR6dfd36CAoE5_psoFF0bfA6l1wletPD7Xo,16515
 jupyter_analysis_tools/git.py,sha256=mqSk5nnAFrmk1_2KFuKVrDWOkRbGbAQOq2N1DfxhNpg,2216
 jupyter_analysis_tools/plotting.py,sha256=L2gwSjlBVK8OneAfSuna3vCJIg2rSEdvd9TfEbM2Als,1183
-jupyter_analysis_tools/readdata.py,sha256=Z0LCAYKEauItdDF6H0gJYR74EKgR2-XFHo5gKlTz7cw,1348
+jupyter_analysis_tools/readdata.py,sha256=zqFYK21ckmogVgsEYNVeqvNvkGVzcHzdCT-I_n0n_uw,5702
 jupyter_analysis_tools/utils.py,sha256=cwbviD1YP06rVhtItdORHEbp8fQ7JfhcrYDONRM336Y,5315
 jupyter_analysis_tools/widgets.py,sha256=rA8qPvY9nS1OtykZwXtCTG29K-N_MYFVb5Aj8yK40_s,2996
-jupyter_analysis_tools-1.1.0.dist-info/licenses/AUTHORS.rst,sha256=SUxxgElDBm6WdCbBBFfcr0ZE3SolWL0T0aS5Fym1198,100
-jupyter_analysis_tools-1.1.0.dist-info/licenses/LICENSE,sha256=SrbIwXA1ZLTO6uwZneJMpvdgiC-3fhNl0vwb3ALoY4g,1107
-jupyter_analysis_tools-1.1.0.dist-info/METADATA,sha256=34HMf-Q8hrdj1SemL1o8-eJEAyhLBz--BX3c2B_6GUM,35291
-jupyter_analysis_tools-1.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-jupyter_analysis_tools-1.1.0.dist-info/top_level.txt,sha256=ei_0x-BF85FLoJ_h67ySwDFowtqus_gI4_0GR466PEU,23
-jupyter_analysis_tools-1.1.0.dist-info/RECORD,,
+jupyter_analysis_tools-1.2.0.dist-info/licenses/AUTHORS.rst,sha256=SUxxgElDBm6WdCbBBFfcr0ZE3SolWL0T0aS5Fym1198,100
+jupyter_analysis_tools-1.2.0.dist-info/licenses/LICENSE,sha256=SrbIwXA1ZLTO6uwZneJMpvdgiC-3fhNl0vwb3ALoY4g,1107
+jupyter_analysis_tools-1.2.0.dist-info/METADATA,sha256=gBi2EdNB6XZP1RC5bls8EepnVGiVMf0HVoXD5D3svZ0,36100
+jupyter_analysis_tools-1.2.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+jupyter_analysis_tools-1.2.0.dist-info/top_level.txt,sha256=ei_0x-BF85FLoJ_h67ySwDFowtqus_gI4_0GR466PEU,23
+jupyter_analysis_tools-1.2.0.dist-info/RECORD,,