res2df 1.2.0__tar.gz → 1.2.2__tar.gz

{res2df-1.2.0 → res2df-1.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: res2df
-Version: 1.2.0
+Version: 1.2.2
 Summary: Convert reservoir simulator input and output to DataFrames
 Home-page: http://github.com/equinor/res2df
 Author: Håvard Berland
@@ -10,17 +10,20 @@ Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: resdata>=5.0.0-b0
+Requires-Dist: resfo
 Requires-Dist: numpy
 Requires-Dist: opm>=2020.10.2
 Requires-Dist: pandas
 Requires-Dist: pyarrow
 Requires-Dist: pyyaml>=5.1
 Requires-Dist: treelib
+Requires-Dist: xtgeo<4.3.2; python_version <= "3.8"
 Provides-Extra: tests
 Requires-Dist: networkx; extra == "tests"
 Requires-Dist: pytest; extra == "tests"
 Requires-Dist: pytest-cov; extra == "tests"
 Requires-Dist: pytest-mock; extra == "tests"
+Requires-Dist: pytest-timeout; extra == "tests"
 Provides-Extra: style
 Requires-Dist: pre-commit; extra == "style"
 Provides-Extra: types

res2df-1.2.2/SECURITY.md

@@ -0,0 +1,16 @@
+If you discover a security vulnerability in this project, please follow these steps to responsibly disclose it:
+
+1. **Do not** create a public GitHub issue for the vulnerability.
+2. Follow our guideline for Responsible Disclosure Policy at [https://www.equinor.com/about-us/csirt](https://www.equinor.com/about-us/csirt) to report the issue
+
+The following information will help us triage your report more quickly:
+
+- Type of issue (e.g. buffer overflow, SQL injection, cross-site scripting, etc.)
+- Full paths of source file(s) related to the manifestation of the issue
+- The location of the affected source code (tag/branch/commit or direct URL)
+- Any special configuration required to reproduce the issue
+- Step-by-step instructions to reproduce the issue
+- Proof-of-concept or exploit code (if possible)
+- Impact of the issue, including how an attacker might exploit the issue
+
+We prefer all communications to be in English.

{res2df-1.2.0 → res2df-1.2.2}/docs/usage/rft.rst

@@ -20,7 +20,7 @@ Eclipse usage
 ^^^^^^^^^^^^^
 
 In order to get RFT files emitted from Eclipse, you need the ``WRFTPLT`` keyword
-in your :term`.DATA file`, example:
+in your :term:`.DATA file`, example:
 
 .. code-block:: console
 

{res2df-1.2.0 → res2df-1.2.2}/mypy.ini

@@ -3,6 +3,9 @@
 [mypy-resdata.*]
 ignore_missing_imports = True
 
+[mypy-resfo.*]
+ignore_missing_imports = True
+
 [mypy-opm.*]
 ignore_missing_imports = True
 

{res2df-1.2.0 → res2df-1.2.2}/res2df/grid.py

@@ -23,6 +23,7 @@ import numpy as np
 import pandas as pd
 import pyarrow
 import pyarrow.feather
+import resfo
 from resdata.resfile import ResdataFile
 
 from .__version__ import __version__
@@ -199,11 +200,12 @@ def rst2df(
     # for all active cells:
     activecells = resdatafiles.get_egrid().getNumActive()
     rstvectors = []
-    for vec in resdatafiles.get_rstfile().headers:
-        if vec[1] == activecells and any(
-            fnmatch.fnmatch(vec[0], key) for key in vectors
+    for vec in resfo.lazy_read(resdatafiles.get_rstfilename()):
+        keyword_name = vec.read_keyword().strip()
+        if vec.read_length() == activecells and any(
+            fnmatch.fnmatch(keyword_name, key) for key in vectors
         ):
-            rstvectors.append(vec[0])
+            rstvectors.append(keyword_name)
     rstvectors = list(set(rstvectors))  # Make unique list
     # Note that all of these might not exist at all timesteps.
 

{res2df-1.2.0 → res2df-1.2.2}/res2df/summary.py

@@ -499,7 +499,8 @@ def _df2pyarrow(dframe: pd.DataFrame) -> pyarrow.Table:
     field_list.append(pyarrow.field("DATE", pyarrow.timestamp("ms")))
     column_arrays = [dframe.index.to_numpy().astype("datetime64[ms]")]
 
-    for colname in dframe.columns:
+    dframe_values = dframe.values.transpose()
+    for col_idx, colname in enumerate(dframe.columns):
         if "meta" in dframe.attrs and colname in dframe.attrs["meta"]:
             # Boolean objects in the metadata dictionary must be converted to bytes:
             field_metadata = {
@@ -516,7 +517,7 @@ def _df2pyarrow(dframe: pd.DataFrame) -> pyarrow.Table:
         else:
             dtype = pyarrow.float32()
         field_list.append(pyarrow.field(colname, dtype, metadata=field_metadata))
-        column_arrays.append(dframe[colname].to_numpy())
+        column_arrays.append(dframe_values[col_idx])
 
     schema = pyarrow.schema(field_list)
 

{res2df-1.2.0 → res2df-1.2.2}/res2df/version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '1.2.0'
-__version_tuple__ = version_tuple = (1, 2, 0)
+__version__ = version = '1.2.2'
+__version_tuple__ = version_tuple = (1, 2, 2)

{res2df-1.2.0 → res2df-1.2.2}/res2df.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: res2df
-Version: 1.2.0
+Version: 1.2.2
 Summary: Convert reservoir simulator input and output to DataFrames
 Home-page: http://github.com/equinor/res2df
 Author: Håvard Berland
@@ -10,17 +10,20 @@ Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: resdata>=5.0.0-b0
+Requires-Dist: resfo
 Requires-Dist: numpy
 Requires-Dist: opm>=2020.10.2
 Requires-Dist: pandas
 Requires-Dist: pyarrow
 Requires-Dist: pyyaml>=5.1
 Requires-Dist: treelib
+Requires-Dist: xtgeo<4.3.2; python_version <= "3.8"
 Provides-Extra: tests
 Requires-Dist: networkx; extra == "tests"
 Requires-Dist: pytest; extra == "tests"
 Requires-Dist: pytest-cov; extra == "tests"
 Requires-Dist: pytest-mock; extra == "tests"
+Requires-Dist: pytest-timeout; extra == "tests"
 Provides-Extra: style
 Requires-Dist: pre-commit; extra == "style"
 Provides-Extra: types

{res2df-1.2.0 → res2df-1.2.2}/res2df.egg-info/SOURCES.txt

@@ -3,6 +3,7 @@
 .pre-commit-config.yaml
 LICENSE
 README.md
+SECURITY.md
 mypy.ini
 py.typed
 ruff.toml

{res2df-1.2.0 → res2df-1.2.2}/res2df.egg-info/requires.txt

@@ -1,4 +1,5 @@
 resdata>=5.0.0-b0
+resfo
 numpy
 opm>=2020.10.2
 pandas
@@ -6,6 +7,9 @@ pyarrow
 pyyaml>=5.1
 treelib
 
+[:python_version <= "3.8"]
+xtgeo<4.3.2
+
 [docs]
 autoapi
 ipython
@@ -27,6 +31,7 @@ networkx
 pytest
 pytest-cov
 pytest-mock
+pytest-timeout
 
 [types]
 mypy

{res2df-1.2.0 → res2df-1.2.2}/setup.py

@@ -17,12 +17,14 @@ LONG_DESCRIPTION = (Path(__file__).parent / "README.md").read_text()
 SETUP_REQUIREMENTS = ["setuptools>=28", "setuptools_scm"]
 REQUIREMENTS = [
     "resdata>=5.0.0-b0",
+    "resfo",
     "numpy",
     "opm>=2020.10.2",
     "pandas",
     "pyarrow",
     "pyyaml>=5.1",
     "treelib",
+    "xtgeo<4.3.2; python_version<='3.8'",
 ]
 
 TEST_REQUIREMENTS = (

{res2df-1.2.0 → res2df-1.2.2}/test_requirements.txt

@@ -2,3 +2,4 @@ networkx
 pytest
 pytest-cov
 pytest-mock
+pytest-timeout

{res2df-1.2.0 → res2df-1.2.2}/tests/test_summary.py

@@ -1108,6 +1108,24 @@ def test_df2pyarrow_mix_int_float():
     pd.testing.assert_frame_equal(dframe, pyat_df[["FOO", "BAR"]])
 
 
+@pytest.mark.timeout(10)
+def test_df2pyarrow_10000cols():
+    """Summary files with thousands of columns should not be an issue"""
+    columncount = 10000
+    dateindex = [dt(2024, 1, 1, 0, 0, 0), dt(2025, 1, 1, 0, 0, 0)]
+    dframe = pd.DataFrame(
+        columns=[f"FOO{num}" for num in range(columncount)],
+        index=dateindex,
+        data=[[1] * columncount, [2] * columncount],
+    ).astype("int32")
+    dframe.attrs["meta"] = {f"FOO{num}": {"unit": "barf"} for num in range(columncount)}
+    pyat = _df2pyarrow(dframe)
+    for num in range(columncount):
+        assert pyat.select([f"FOO{num}"]).schema[0].metadata == {
+            b"unit": b"barf",
+        }
+
+
 def test_df2pyarrow_500years():
     """Summary files can have DATE columns with timespans outside the
     Pandas dataframe nanosecond limitation. This should not present