Merge branch 'main' into nick/genomic-variants

countess/plugins/fastq.py

@@ -4,15 +4,16 @@
 from typing import Iterable, Optional
 
 import pandas as pd
+from fqfa.fasta.fasta import parse_fasta_records  # type: ignore
 from fqfa.fastq.fastq import parse_fastq_reads  # type: ignore
 
 from countess import VERSION
-from countess.core.parameters import BooleanParam, FloatParam
+from countess.core.parameters import BooleanParam, FloatParam, StringParam
 from countess.core.plugins import PandasInputFilesPlugin
 from countess.utils.files import clean_filename
 
 
-def _file_reader(
+def _fastq_reader(
     file_handle, min_avg_quality: float, row_limit: Optional[int] = None, filename: str = ""
 ) -> Iterable[dict[str, str]]:
     for fastq_read in islice(parse_fastq_reads(file_handle), 0, row_limit):
@@ -47,13 +48,13 @@ def read_file_to_dataframe(self, file_params, row_limit=None):
 
         if filename.endswith(".gz"):
             with gzip.open(filename, mode="rt", encoding="utf-8") as fh:
-                dataframe = pd.DataFrame(_file_reader(fh, min_avg_quality, row_limit, filename))
+                dataframe = pd.DataFrame(_fastq_reader(fh, min_avg_quality, row_limit, filename))
         elif filename.endswith(".bz2"):
             with bz2.open(filename, mode="rt", encoding="utf-8") as fh:
-                dataframe = pd.DataFrame(_file_reader(fh, min_avg_quality, row_limit, filename))
+                dataframe = pd.DataFrame(_fastq_reader(fh, min_avg_quality, row_limit, filename))
         else:
             with open(filename, "r", encoding="utf-8") as fh:
-                dataframe = pd.DataFrame(_file_reader(fh, min_avg_quality, row_limit, filename))
+                dataframe = pd.DataFrame(_fastq_reader(fh, min_avg_quality, row_limit, filename))
 
         group_columns = ["sequence"]
 
@@ -78,3 +79,48 @@ def read_file_to_dataframe(self, file_params, row_limit=None):
             return dataframe.assign(count=1).groupby(group_columns).count()
         else:
             return dataframe
+
+
+def _fasta_reader(file_handle, row_limit: Optional[int] = None) -> Iterable[dict[str, str]]:
+    for header, sequence in islice(parse_fasta_records(file_handle), 0, row_limit):
+        yield {
+            "__s": sequence,
+            "__h": header,
+        }
+
+
+class LoadFastaPlugin(PandasInputFilesPlugin):
+    name = "FASTA Load"
+    description = "Loads sequences from FASTA files"
+    link = "https://countess-project.github.io/CountESS/included-plugins/#fasta-load"
+    version = VERSION
+
+    file_types = [("FASTA", [".fasta", ".fa", ".fasta.gz", ".fa.gz", ".fasta.bz2", ".fa.bz2"])]
+
+    sequence_column = StringParam("Sequence Column", "sequence")
+    header_column = StringParam("Header Column", "header")
+    filename_column = StringParam("Filename Column", "filename")
+
+    def read_file_to_dataframe(self, file_params, row_limit=None):
+        filename = file_params.filename.value
+
+        if filename.endswith(".gz"):
+            with gzip.open(filename, mode="rt", encoding="utf-8") as fh:
+                dataframe = pd.DataFrame(_fasta_reader(fh, row_limit))
+        elif filename.endswith(".bz2"):
+            with bz2.open(filename, mode="rt", encoding="utf-8") as fh:
+                dataframe = pd.DataFrame(_fasta_reader(fh, row_limit))
+        else:
+            with open(filename, "r", encoding="utf-8") as fh:
+                dataframe = pd.DataFrame(_fasta_reader(fh, row_limit))
+
+        dataframe.rename(columns={"__s": self.sequence_column.value}, inplace=True)
+
+        if self.header_column:
+            dataframe.rename(columns={"__h": self.header_column.value}, inplace=True)
+        else:
+            dataframe.drop(columns=["__h"], inplace=True)
+
+        if self.filename_column:
+            dataframe[self.filename_column.value] = clean_filename(filename)
+        return dataframe

pyproject.toml

@@ -52,6 +52,7 @@ dev = [
 [project.entry-points.countess_plugins]
 collate = "countess.plugins.collate:CollatePlugin"
 load_fastq = "countess.plugins.fastq:LoadFastqPlugin"
+load_fasta = "countess.plugins.fastq:LoadFastaPlugin"
 load_csv = "countess.plugins.csv:LoadCsvPlugin"
 group_by = "countess.plugins.group_by:GroupByPlugin"
 expression = "countess.plugins.expression:ExpressionPlugin"

tests/test_datatable.ini

@@ -0,0 +1,36 @@
+[DataTable]
+_module = countess.plugins.data_table
+_class = DataTablePlugin
+_version = 0.0.69
+_hash = 5d54face788a55338e1873cd0c29820317e805c06f2fe9d95450f3f38153392c
+_sort = 0 0
+_position = 500 500
+columns.0.name = 'aaa'
+columns.0.type = 'string'
+columns.0.index = False
+columns.1.name = 'bbb'
+columns.1.type = 'number'
+columns.1.index = False
+columns.2.name = 'ccc'
+columns.2.type = 'boolean'
+columns.2.index = False
+rows.0.aaa = ''
+rows.0.bbb = None
+rows.0.ccc = False
+rows.1.aaa = ''
+rows.1.bbb = None
+rows.1.ccc = False
+
+[CSV Save]
+_module = countess.plugins.csv
+_class = SaveCsvPlugin
+_version = 0.0.69
+_hash = eeb7325e4c7649ab971759c5120eb0ffc8684495a4ddc7a4dfb395c3b9cf1e60
+_sort = 0 0
+_position = 581 559
+_parent.0 = DataTable
+header = True
+filename = None
+delimiter = ','
+quoting = False
+