aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--quality_control/parsing.py18
-rw-r--r--tests/conftest.py9
-rw-r--r--tests/qc/test_parsing.py29
-rw-r--r--tests/test_data/duplicated_headers_no_data_errors.tsv (renamed from tests/test_data/we_found_no_errors_in_your_file.tsv)0
4 files changed, 35 insertions, 21 deletions
diff --git a/quality_control/parsing.py b/quality_control/parsing.py
index b7b0ff5..8b2715a 100644
--- a/quality_control/parsing.py
+++ b/quality_control/parsing.py
@@ -1,6 +1,6 @@
import csv
-
from enum import Enum
+from functools import reduce
import quality_control.average as avg
import quality_control.standard_error as se
@@ -28,7 +28,7 @@ def parse_strains(filepath):
def __parse_header(line, strains):
return valid_header(
- strains,
+ set(strains),
tuple(header.strip() for header in line.split("\t")))
def __parse_average_line(line):
@@ -42,16 +42,20 @@ LINE_PARSERS = {
FileType.STANDARD_ERROR: __parse_standard_error_line
}
-def parse_file(filepath: str, filetype: FileType, strains_filepath: str):
+def strain_names(strains):
+ def __extract_strain_names(acc, strain):
+ return acc + tuple(
+ item for item in (strain["Name"], strain["Name2"])
+ if (item is not None and item != ""))
+ return reduce(__extract_strain_names, strains, tuple())
+
+def parse_file(filepath: str, filetype: FileType, strains: list):
seek_pos = 0
try:
with open(filepath, encoding="utf-8") as input_file:
for line_number, line in enumerate(input_file):
if line_number == 0:
- yield __parse_header(
- line,
- tuple(strain["Name"] for strain
- in parse_strains(strains_filepath)))
+ yield __parse_header(line, strains)
seek_pos = seek_pos + len(line)
yield LINE_PARSERS[filetype](
diff --git a/tests/conftest.py b/tests/conftest.py
new file mode 100644
index 0000000..0cdba3e
--- /dev/null
+++ b/tests/conftest.py
@@ -0,0 +1,9 @@
+from functools import reduce
+
+import pytest
+
+from quality_control.parsing import strain_names, parse_strains
+
+@pytest.fixture(scope="session")
+def strains():
+ return strain_names(parse_strains("strains.csv"))
diff --git a/tests/qc/test_parsing.py b/tests/qc/test_parsing.py
index 14cfbde..be13d9b 100644
--- a/tests/qc/test_parsing.py
+++ b/tests/qc/test_parsing.py
@@ -11,37 +11,38 @@ from quality_control.parsing import FileType, parse_file
("tests/test_data/average.tsv", FileType.STANDARD_ERROR),
("tests/test_data/standarderror_1_error_at_end.tsv", FileType.AVERAGE),
("tests/test_data/standarderror.tsv", FileType.AVERAGE),
- ("tests/test_data/we_found_no_errors_in_your_file.tsv",
+ ("tests/test_data/duplicated_headers_no_data_errors.tsv",
FileType.STANDARD_ERROR),))
-def test_parse_file_fails_with_wrong_filetype_declaration(filepath, filetype):
+def test_parse_file_fails_with_wrong_filetype_declaration(filepath, filetype, strains):
with pytest.raises(ParseError):
- for line in parse_file(filepath, filetype, "strains.csv"):
+ for line in parse_file(filepath, filetype, strains):
pass
@pytest.mark.parametrize(
"filepath,filetype",
(("tests/test_data/average_crlf.tsv", FileType.AVERAGE),
("tests/test_data/average.tsv", FileType.AVERAGE),
- ("tests/test_data/standarderror.tsv", FileType.STANDARD_ERROR),
- ("tests/test_data/we_found_no_errors_in_your_file.tsv", FileType.AVERAGE)))
-def test_parse_file_passes_with_valid_files(filepath, filetype):
- assert False, "Not Implemented"
+ ("tests/test_data/standarderror.tsv", FileType.STANDARD_ERROR)))
+def test_parse_file_passes_with_valid_files(filepath, filetype, strains):
+ for line in parse_file(filepath, filetype, strains):
+ assert bool(line)
@pytest.mark.parametrize(
"filepath,filetype",
(("tests/test_data/average_large.tsv", FileType.AVERAGE),
("tests/test_data/average.tsv", FileType.AVERAGE),
- ("tests/test_data/standarderror.tsv", FileType.STANDARD_ERROR),
- ("tests/test_data/we_found_no_errors_in_your_file.tsv", FileType.AVERAGE)))
-def test_parse_file_works_with_large_files(filepath, filetype):
- assert False, "Not Implemented"
+ ("tests/test_data/standarderror.tsv", FileType.STANDARD_ERROR)))
+def test_parse_file_works_with_large_files(filepath, filetype, strains):
+ for line in parse_file(filepath, filetype, strains):
+ assert bool(line)
@pytest.mark.parametrize(
"filepath,filetype",
(("tests/test_data/average_error_at_end_200MB.tsv", FileType.AVERAGE),
- ("tests/test_data/standarderror_1_error_at_end.tsv", FileType.STANDARD_ERROR)))
-def test_parse_file_raises_exception_on_error_in_file(filepath, filetype):
+ ("tests/test_data/standarderror_1_error_at_end.tsv", FileType.STANDARD_ERROR),
+ ("tests/test_data/duplicated_headers_no_data_errors.tsv", FileType.AVERAGE)))
+def test_parse_file_raises_exception_on_error_in_file(filepath, filetype, strains):
with pytest.raises(ParseError):
- for line in parse_file(filepath, filetype, "strains.csv"):
+ for line in parse_file(filepath, filetype, strains):
pass
diff --git a/tests/test_data/we_found_no_errors_in_your_file.tsv b/tests/test_data/duplicated_headers_no_data_errors.tsv
index a49ed1b..a49ed1b 100644
--- a/tests/test_data/we_found_no_errors_in_your_file.tsv
+++ b/tests/test_data/duplicated_headers_no_data_errors.tsv