Merge pull request #134 from CAST-genomics/feat/actions

dep: remove myst-parser

.readthedocs.yaml

@@ -8,6 +8,7 @@ version: 2
 
 sphinx:
   configuration: docs/conf.py
+  fail_on_warning: true
 
 python:
   version: 3.7

docs/conf.py

@@ -34,7 +34,6 @@
     "sphinx_rtd_theme",
     "numpydoc",
     "sphinx_click",
-    "myst_parser",
 ]
 
 # Add any paths that contain templates here, relative to this directory.
@@ -48,8 +47,6 @@
 # -- Extension configuration -------------------------------------------------
 autosummary_generate = True
 numpydoc_show_class_members = False
-# allow for both rst and md syntax
-source_suffix = [".rst"]
 
 # -- Options for HTML output -------------------------------------------------
 
@@ -61,4 +58,4 @@
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ["_static"]
+html_static_path = []

docs/formats/models.rst

@@ -29,7 +29,7 @@ Example model.dat file
 Simulating 40 samples for 6 generations in this case implies the first generation has population freqs ``Admixed=0, CEU=0.2, YRI=0.8`` and the remaining 2-6 generations have population frequency ``Admixed=1, CEU=0, YRI=0``
 
 Example pulse event model.dat file
-----------------------
+----------------------------------
 
 .. code-block::
 

haptools/__init__.py

@@ -0,0 +1,10 @@
+try:
+    from importlib.metadata import version, PackageNotFoundError
+except ImportError:
+    # handles py3.7, since importlib.metadata was introduced in py3.8
+    from importlib_metadata import version, PackageNotFoundError
+
+    try:
+        __version__ = version(__name__)
+    except PackageNotFoundError:
+        __version__ = "unknown"

haptools/__main__.py

@@ -1,16 +1,12 @@
 #!/usr/bin/env python
 
 from __future__ import annotations
-import re
 import sys
-import time
-import click
 from pathlib import Path
-from haptools.data.haplotypes import Haplotypes
-from haptools import data
-import tempfile
 
-# AVOID IMPORTING ANYTHING HERE
+import click
+
+# AVOID IMPORTING ANYTHING ABOVE
 # any imports we put here will make it slower to use the command line client
 # a basic "haptools --help" should be quick and require very few imports, for example
 
@@ -180,6 +176,8 @@ def simgenotype(
     """
     Simulate admixed genomes under a pre-defined model.
     """
+    import re
+    import time
     from .sim_genotype import (
         output_vcf,
         simulate_gt,

haptools/data/breakpoints.py

@@ -248,7 +248,7 @@ def _find_blocks(
             problem_position = positions[indices >= len(blocks)][0]
             raise ValueError(
                 f"Position {problem_position} exceeds the range of the provided "
-                "haplotype blocks."
+                "breakpoint blocks."
             )
         return indices
 
@@ -298,6 +298,13 @@ def population_array(
                 for strand_num in range(len(samp_blocks)):
                     blocks = samp_blocks[strand_num]
                     chrom_block = blocks[blocks["chrom"] == chrom]
+                    if not len(chrom_block):
+                        samp_id = tuple(data.keys())[samp_idx]
+                        raise ValueError(
+                            f"Chromosome {chrom} in the genotypes is absent in the "
+                            f"breakpoints for sample {samp_id}_{strand_num+1}. Check "
+                            "that your 'chr' prefixes match!"
+                        )
                     # TODO: raise an exception if the end positions in chrom_block
                     # aren't sorted
                     # Now try to figure out the right population labels using binary
@@ -307,14 +314,13 @@ def population_array(
                             self._find_blocks(chrom_block["bp"], positions)
                         ]
                     except ValueError as e:
-                        diff = gts_chroms.difference(blocks["chrom"])
-                        if str(e).startswith("Position ") and len(diff):
-                            samp_id = tuple(data.keys())[samp_idx]
+                        samp_id = tuple(data.keys())[samp_idx]
+                        if str(e).startswith("Position "):
                             raise ValueError(
-                                f"Chromosomes {diff} in the genotypes are absent in "
-                                f"the breakpoints for sample {samp_id}_{strand_num+1}."
-                                " Check that your 'chr' prefixes match!"
-                            )
+                                f"The breakpoints for chromosome {chrom} in sample"
+                                f" {samp_id}_{strand_num+1} do not specify an ancestry"
+                                " for one of the requested variants."
+                            ) from e
                         else:
                             raise e
         return arr

haptools/data/genotypes.py

@@ -711,8 +711,8 @@ def __init__(self, fname: Path | str, log: Logger = None, chunk_size: int = None
             import pgenlib
         except ImportError:
             raise ImportError(
-                "We cannot read PGEN files without the pgenlib library. Please "
-                "reinstall haptools with the 'files' extra requirement via\n"
+                f"We cannot read PGEN files without the pgenlib library. Please "
+                f"reinstall haptools with the 'files' extra requirement via\n"
                 f"pip install haptools[files]"
             )
 

haptools/logging.py

@@ -0,0 +1,23 @@
+from __future__ import annotations
+import logging
+
+
+def getLogger(name: str = None):
+    """
+    Retrieve a Logger object
+
+    Parameters
+    ----------
+    name : str, optional
+        The name of the logging object
+    """
+    if name is None:
+        pass
+
+    log = logging.getLogger("haptools " + name)
+    db_time = "|%(asctime)s" if verbosity == "DEBUG" else ""
+    logging.basicConfig(
+        format="[%(levelname)8s" + db_time + "] %(message)s (%(filename)s:%(lineno)s)",
+        level=verbosity,
+        datefmt="%H:%M:%S",
+    )