diff --git a/PanACoTA/align_module/pan_to_pergenome.py b/PanACoTA/align_module/pan_to_pergenome.py
index df1ca40c5d3dd64802a5cfe4895f5062ca6ad3f6..6afcbfe858598e9b066d693102c8edf708b8adec 100755
--- a/PanACoTA/align_module/pan_to_pergenome.py
+++ b/PanACoTA/align_module/pan_to_pergenome.py
@@ -226,8 +226,7 @@ def write_genome_file(listdir, aldir, dname, strain, member, several):
"option -F (or --force).".format(strain, geprtfile, gegenfile))
return
- # If one of the 2 files already exists, overwrite both files (same behaviour
- # as if no file exists)
+ # If at least one of the 2 files already exists, overwrite both files
with open(gegenfile, "w") as gegf, open(geprtfile, "w") as gepf:
for mem, fam in member.items():
if strain not in several[fam]:
@@ -256,8 +255,12 @@ def write_missing_genomes(fam_genomes, several, all_genomes, aldir, dname):
name of dataset
"""
for fam, genomes in fam_genomes.items():
- missfile = os.path.join(aldir, dname + "-current." + fam + ".miss.lst")
+ # File where missing genomes will be written
+ missfile = os.path.join(aldir, f"{dname}-current.{fam}.miss.lst")
with open(missfile, "w") as mff:
+ # missing = missing or several members:
+ # miss: all genomes - genomes in the family
+ # several: add to 'miss' genomes with several members in the family
missing = (set(all_genomes) - set(genomes)).union(set(several[fam]))
if missing:
mff.write("\n".join(missing) + "\n")
diff --git a/test/data/align/exp_files/exp_getentry-gen-ESCO4.txt b/test/data/align/exp_files/exp_getentry-gen-ESCO4.txt
index a63c8270dc03793a17b77365ce26de0716a7c4a4..06486b2ef2d12a5d3fc8fa1b98892bcf751767c9 100755
--- a/test/data/align/exp_files/exp_getentry-gen-ESCO4.txt
+++ b/test/data/align/exp_files/exp_getentry-gen-ESCO4.txt
@@ -1,3 +1,3 @@
-ESCO4_00001 Aldir/TEST6-current.1.gen
-ESCO4_00003 Aldir/TEST6-current.3.gen
-ESCO4_00004 Aldir/TEST6-current.2.gen
+ESCO4_00001 test/data/align/generated_by_unit-tests/Aldir/test_write_genome-current.1.gen
+ESCO4_00003 test/data/align/generated_by_unit-tests/Aldir/test_write_genome-current.3.gen
+ESCO4_00004 test/data/align/generated_by_unit-tests/Aldir/test_write_genome-current.2.gen
diff --git a/test/data/align/exp_files/exp_getentry-prt-ESCO4.txt b/test/data/align/exp_files/exp_getentry-prt-ESCO4.txt
index 13f8524ca5bec18464619b6c241f8c9cc44b2c42..007f47079171bc97fbf8bbdb24547145debcfe43 100755
--- a/test/data/align/exp_files/exp_getentry-prt-ESCO4.txt
+++ b/test/data/align/exp_files/exp_getentry-prt-ESCO4.txt
@@ -1,3 +1,3 @@
-ESCO4_00001 Aldir/TEST6-current.1.prt
-ESCO4_00003 Aldir/TEST6-current.3.prt
-ESCO4_00004 Aldir/TEST6-current.2.prt
+ESCO4_00001 test/data/align/generated_by_unit-tests/Aldir/test_write_genome-current.1.prt
+ESCO4_00003 test/data/align/generated_by_unit-tests/Aldir/test_write_genome-current.3.prt
+ESCO4_00004 test/data/align/generated_by_unit-tests/Aldir/test_write_genome-current.2.prt
diff --git a/test/test_unit/test_align/test_pan2pergenome.py b/test/test_unit/test_align/test_pan2pergenome.py
index 5da774f79f3ad49d5ec809d9f92bda0e90195102..c39f14587e79991bbff77628a48ad087a5f64641 100755
--- a/test/test_unit/test_align/test_pan2pergenome.py
+++ b/test/test_unit/test_align/test_pan2pergenome.py
@@ -11,11 +11,37 @@ import logging
import pytest
import PanACoTA.align_module.pan_to_pergenome as p2p
-
+import test.test_unit.utilities_for_tests as tutil
ALPATH = os.path.join("test", "data", "align")
EXPPATH = os.path.join(ALPATH, "exp_files")
TESTPATH = os.path.join(ALPATH, "test_files")
+GENEPATH = os.path.join(ALPATH, "generated_by_unit-tests")
+
+@pytest.fixture(autouse=True)
+def setup_teardown_module():
+ """
+ Remove log files at the end of this test module
+
+ Before each test:
+ - init logger
+ - create directory to put generated files
+
+ After:
+ - remove all log files
+ - remove directory with generated results
+ """
+ # utils.init_logger(LOGFILE_BASE, LOG_LEVEL, 'test_getseq', verbose=1)
+ os.mkdir(GENEPATH)
+ print("setup")
+
+ yield
+ # for f in LOGFILES:
+ # if os.path.exists(f):
+ # os.remove(f)
+ shutil.rmtree(GENEPATH)
+ print("teardown")
+
ALL_PROTS = {"ESCO1": {"ESCO1_00001": '1',
"ESCO1_00002": '4'},
"ESCO2": {"ESCO2_00001": '1',
@@ -77,169 +103,169 @@ def test_get_per_genome(caplog):
shutil.rmtree(outdir)
-def test_prot_per_strain():
- """
- Test parser of persistent genome file
- """
- pers = os.path.join("test", "data", "persgenome", "exp_files", "exp_pers-floor-mixed.txt")
- all_prots, fams_genomes, several = p2p.proteins_per_strain(pers)
- exp_several = {'1': ["GENO.1216.00002"],
- '3': [],
- '5': [],
- '8': [],
- '10': [],
- '11': [],
- '12': ["GENO.1216.00003"]}
- assert several == exp_several
- exp_fams = {'1': ["GEN4.1111.00001", "GENO.0817.00001", "GENO.1216.00002", "GENO.1216.00003"],
- '3': ["GEN4.1111.00001", "GENO.0817.00001", "GENO.1216.00002", "GENO.1216.00003"],
- '5': ["GEN4.1111.00001", "GENO.0817.00001", "GENO.1216.00002", "GENO.1216.00003"],
- '8': ["GEN4.1111.00001", "GENO.0817.00001", "GENO.1216.00002"],
- '10': ["GEN4.1111.00001", "GENO.0817.00001", "GENO.1216.00002"],
- '11': ["GEN4.1111.00001", "GENO.0817.00001", "GENO.1216.00002"],
- '12': ["GEN4.1111.00001", "GENO.0817.00001", "GENO.1216.00002", "GENO.1216.00003"]}
- assert fams_genomes == exp_fams
- exp_prots = {"GEN4.1111.00001": {"GEN4.1111.00001.b0001_00001": '1',
- "GEN4.1111.00001.b0001_00009": '3',
- "GEN4.1111.00001.i0001_00002": '5',
- "GEN4.1111.00001.i0001_00007": '8',
- "GEN4.1111.00001.i0001_00004": '10',
- "GEN4.1111.00001.i0001_00005": '11',
- "GEN4.1111.00001.i0001_00008": '12'
- },
- "GENO.0817.00001": {"GENO.0817.00001.b0001_00002": '1',
- "GENO.0817.00001.b0002_00011": '3',
- "GENO.0817.00001.b0002_00003": '5',
- "GENO.0817.00001.i0002_00009": '8',
- "GENO.0817.00001.i0002_00004": '10',
- "GENO.0817.00001.i0002_00005": '11',
- "GENO.0817.00001.i0002_00010": '12'
- },
- "GENO.1216.00002": {"GENO.1216.00002.b0001_00001": '1',
- "GENO.1216.00002.i0001_00002": '1',
- "GENO.1216.00002.b0002_00010": '3',
- "GENO.1216.00002.i0001_00003": '5',
- "GENO.1216.00002.b0001_00008": '8',
- "GENO.1216.00002.i0001_00005": '10',
- "GENO.1216.00002.i0001_00006": '11',
- "GENO.1216.00002.b0002_00009": '12'
- },
- "GENO.1216.00003": {"GENO.1216.00003.i0001_00003": '1',
- "GENO.1216.00003.i0001_01010": '3',
- "GENO.1216.00003.i0080_00010": '5',
- "GENO.1216.00003.i0001_00004": '12',
- "GENO.1216.00003.i0001_01000": '12'
- }
- }
- assert all_prots == exp_prots
-
-
-def test_prot_per_strain_member_bis(caplog):
- """
- Test parser of persistent genome file when a same member is in 2 different families
- """
- caplog.set_level(logging.DEBUG)
- pers = os.path.join(TESTPATH, "pers_genome_member-bis.txt")
- all_prots, fams_genomes, several = p2p.proteins_per_strain(pers)
- assert "problem: ESCO2_2 already exists, in family 5. Conflict with family 32" in caplog.text
- exp_several = {'1': [], '5': [], '12': [], '32': []}
- assert several == exp_several
- exp_fams = {'1': ["ESCO_1", "ESCO2", "ESCO3", "ESCO4"], '5': ["ESCO_1", "ESCO2", "ESCO4"],
- '12': ["ESCO_1", "ESCO2", "ESCO3"], '32': ["ESCO_1", "ESCO2", "ESCO3", "ESCO4"]}
- assert fams_genomes == exp_fams
- exp_prots = {"ESCO_1": {"ESCO_1_1": '1', "ESCO_1_2": '5', "ESCO_1_3": '12', "ESCO_1_4": '32'},
- "ESCO2": {"ESCO2_1": '1', "ESCO2_2": '32', "ESCO2_3": '12'},
- "ESCO3": {"ESCO3_1": '1', "ESCO3_3": '12', "ESCO3_4": '32'},
- "ESCO4": {"ESCO4_1": '1', "ESCO4_3": '5', "ESCO4_4": '32'}}
- assert all_prots == exp_prots
-
-
-def test_get_genomes():
- """
- Test parser of list of genomes
- """
- lstfile = os.path.join("test", "data", "annotate", "exp_files", "results_test_func-default",
- "LSTINFO-list_genomes-func-test-default.lst")
- all_genomes = p2p.get_all_genomes(lstfile)
- assert all_genomes == ["ESCO.1015.00001", "ESCO.1116.00002", "GENO.1015.00001"]
-
-
-def test_write_getentry():
- """
- Test that when giving a list of genomes with their persistent gene names,
- it creates all expected files.
- """
- listdir = "Listdir"
- aldir = "Aldir"
- # Create align folder
- os.makedirs(listdir)
- dname = "TEST6"
- p2p.write_getentry_files(ALL_PROTS, SEVERAL, listdir, aldir, dname, ALL_GENOMES)
- # Check creation and content of all files
- genfiles = [os.path.join(listdir, "{}-getEntry_gen_ESCO{}.txt".format(dname, num)) for num in
- range(1, 7)]
- expgens = [os.path.join(EXPPATH, "exp_getentry-gen-ESCO{}.txt".format(num)) for num in
- range(1, 7)]
- for fexp, fout in zip(expgens, genfiles):
- check_list(fexp, fout)
- prtfiles = [os.path.join(listdir, "{}-getEntry_prt_ESCO{}.txt".format(dname, num)) for num in
- range(1, 7)]
- expprts = [os.path.join(EXPPATH, "exp_getentry-prt-ESCO{}.txt".format(num)) for num in
- range(1, 7)]
- for fexp, fout in zip(expprts, prtfiles):
- check_list(fexp, fout)
- shutil.rmtree(listdir)
-
-
-def test_write_getentry_error(caplog):
- """
- Test that when giving a list of genomes with their persistent gene names,
- but for 2 genomes, there is no persistent gene, it exists, with an error message
- """
- caplog.set_level(logging.DEBUG)
- all_prots = {"ESCO1": {"ESCO1_00001": '1',
- "ESCO1_00002": '4'},
- "ESCO2": {"ESCO2_00001": '1',
- "ESCO2_22": '2',
- "ESCO2_456": '4',
- "ESCO2_46": '3'},
- "ESCO3": {"ESCO3_1": '2',
- "ESCO3_12": '1',
- "ESCO3_4564": '3',
- "ESCO3_00123": '4',
- "ESCO3_8": '2'},
- "ESCO6": {"ESCO6_1": '4',
- "ESCO6_2": '3',
- "ESCO6_3": '1'}}
- several = {'1': [],
- '2': ["ESCO3"],
- '3': [],
- '4': []}
- listdir = "Listdir"
- aldir = "Aldir"
- # Create align folder
- os.makedirs(listdir)
- dname = "TEST6"
- with pytest.raises(SystemExit):
- p2p.write_getentry_files(all_prots, several, listdir, aldir, dname, ALL_GENOMES)
- assert ("There is not any protein for genome ESCO4 in any family! The program will close, "
- "please fix this problem to be able to run the alignments") in caplog.text
- assert ("There is not any protein for genome ESCO5 in any family! The program will close, "
- "please fix this problem to be able to run the alignments") in caplog.text
- # Check creation and content of all files
- genfiles = [os.path.join(listdir, "{}-getEntry_gen_ESCO{}.txt".format(dname, num)) for num in
- list(range(1, 4)) + [6]]
- expgens = [os.path.join(EXPPATH, "exp_getentry-gen-ESCO{}.txt".format(num)) for num in
- list(range(1, 4)) + [6]]
- for fexp, fout in zip(expgens, genfiles):
- check_list(fexp, fout)
- prtfiles = [os.path.join(listdir, "{}-getEntry_prt_ESCO{}.txt".format(dname, num)) for num in
- list(range(1, 4)) + [6]]
- expprts = [os.path.join(EXPPATH, "exp_getentry-prt-ESCO{}.txt".format(num)) for num in
- list(range(1, 4)) + [6]]
- for fexp, fout in zip(expprts, prtfiles):
- check_list(fexp, fout)
- shutil.rmtree(listdir)
+# def test_prot_per_strain():
+# """
+# Test parser of persistent genome file
+# """
+# pers = os.path.join("test", "data", "persgenome", "exp_files", "exp_pers-floor-mixed.txt")
+# all_prots, fams_genomes, several = p2p.proteins_per_strain(pers)
+# exp_several = {'1': ["GENO.1216.00002"],
+# '3': [],
+# '5': [],
+# '8': [],
+# '10': [],
+# '11': [],
+# '12': ["GENO.1216.00003"]}
+# assert several == exp_several
+# exp_fams = {'1': ["GEN4.1111.00001", "GENO.0817.00001", "GENO.1216.00002", "GENO.1216.00003"],
+# '3': ["GEN4.1111.00001", "GENO.0817.00001", "GENO.1216.00002", "GENO.1216.00003"],
+# '5': ["GEN4.1111.00001", "GENO.0817.00001", "GENO.1216.00002", "GENO.1216.00003"],
+# '8': ["GEN4.1111.00001", "GENO.0817.00001", "GENO.1216.00002"],
+# '10': ["GEN4.1111.00001", "GENO.0817.00001", "GENO.1216.00002"],
+# '11': ["GEN4.1111.00001", "GENO.0817.00001", "GENO.1216.00002"],
+# '12': ["GEN4.1111.00001", "GENO.0817.00001", "GENO.1216.00002", "GENO.1216.00003"]}
+# assert fams_genomes == exp_fams
+# exp_prots = {"GEN4.1111.00001": {"GEN4.1111.00001.b0001_00001": '1',
+# "GEN4.1111.00001.b0001_00009": '3',
+# "GEN4.1111.00001.i0001_00002": '5',
+# "GEN4.1111.00001.i0001_00007": '8',
+# "GEN4.1111.00001.i0001_00004": '10',
+# "GEN4.1111.00001.i0001_00005": '11',
+# "GEN4.1111.00001.i0001_00008": '12'
+# },
+# "GENO.0817.00001": {"GENO.0817.00001.b0001_00002": '1',
+# "GENO.0817.00001.b0002_00011": '3',
+# "GENO.0817.00001.b0002_00003": '5',
+# "GENO.0817.00001.i0002_00009": '8',
+# "GENO.0817.00001.i0002_00004": '10',
+# "GENO.0817.00001.i0002_00005": '11',
+# "GENO.0817.00001.i0002_00010": '12'
+# },
+# "GENO.1216.00002": {"GENO.1216.00002.b0001_00001": '1',
+# "GENO.1216.00002.i0001_00002": '1',
+# "GENO.1216.00002.b0002_00010": '3',
+# "GENO.1216.00002.i0001_00003": '5',
+# "GENO.1216.00002.b0001_00008": '8',
+# "GENO.1216.00002.i0001_00005": '10',
+# "GENO.1216.00002.i0001_00006": '11',
+# "GENO.1216.00002.b0002_00009": '12'
+# },
+# "GENO.1216.00003": {"GENO.1216.00003.i0001_00003": '1',
+# "GENO.1216.00003.i0001_01010": '3',
+# "GENO.1216.00003.i0080_00010": '5',
+# "GENO.1216.00003.i0001_00004": '12',
+# "GENO.1216.00003.i0001_01000": '12'
+# }
+# }
+# assert all_prots == exp_prots
+
+
+# def test_prot_per_strain_member_bis(caplog):
+# """
+# Test parser of persistent genome file when a same member is in 2 different families
+# """
+# caplog.set_level(logging.DEBUG)
+# pers = os.path.join(TESTPATH, "pers_genome_member-bis.txt")
+# all_prots, fams_genomes, several = p2p.proteins_per_strain(pers)
+# assert "problem: ESCO2_2 already exists, in family 5. Conflict with family 32" in caplog.text
+# exp_several = {'1': [], '5': [], '12': [], '32': []}
+# assert several == exp_several
+# exp_fams = {'1': ["ESCO_1", "ESCO2", "ESCO3", "ESCO4"], '5': ["ESCO_1", "ESCO2", "ESCO4"],
+# '12': ["ESCO_1", "ESCO2", "ESCO3"], '32': ["ESCO_1", "ESCO2", "ESCO3", "ESCO4"]}
+# assert fams_genomes == exp_fams
+# exp_prots = {"ESCO_1": {"ESCO_1_1": '1', "ESCO_1_2": '5', "ESCO_1_3": '12', "ESCO_1_4": '32'},
+# "ESCO2": {"ESCO2_1": '1', "ESCO2_2": '32', "ESCO2_3": '12'},
+# "ESCO3": {"ESCO3_1": '1', "ESCO3_3": '12', "ESCO3_4": '32'},
+# "ESCO4": {"ESCO4_1": '1', "ESCO4_3": '5', "ESCO4_4": '32'}}
+# assert all_prots == exp_prots
+
+
+# def test_get_genomes():
+# """
+# Test parser of list of genomes
+# """
+# lstfile = os.path.join("test", "data", "annotate", "exp_files", "results_test_func-default",
+# "LSTINFO-list_genomes-func-test-default.lst")
+# all_genomes = p2p.get_all_genomes(lstfile)
+# assert all_genomes == ["ESCO.1015.00001", "ESCO.1116.00002", "GENO.1015.00001"]
+
+
+# def test_write_getentry():
+# """
+# Test that when giving a list of genomes with their persistent gene names,
+# it creates all expected files.
+# """
+# listdir = "Listdir"
+# aldir = "Aldir"
+# # Create align folder
+# os.makedirs(listdir)
+# dname = "TEST6"
+# p2p.write_getentry_files(ALL_PROTS, SEVERAL, listdir, aldir, dname, ALL_GENOMES)
+# # Check creation and content of all files
+# genfiles = [os.path.join(listdir, "{}-getEntry_gen_ESCO{}.txt".format(dname, num)) for num in
+# range(1, 7)]
+# expgens = [os.path.join(EXPPATH, "exp_getentry-gen-ESCO{}.txt".format(num)) for num in
+# range(1, 7)]
+# for fexp, fout in zip(expgens, genfiles):
+# check_list(fexp, fout)
+# prtfiles = [os.path.join(listdir, "{}-getEntry_prt_ESCO{}.txt".format(dname, num)) for num in
+# range(1, 7)]
+# expprts = [os.path.join(EXPPATH, "exp_getentry-prt-ESCO{}.txt".format(num)) for num in
+# range(1, 7)]
+# for fexp, fout in zip(expprts, prtfiles):
+# check_list(fexp, fout)
+# shutil.rmtree(listdir)
+
+
+# def test_write_getentry_error(caplog):
+# """
+# Test that when giving a list of genomes with their persistent gene names,
+# but for 2 genomes, there is no persistent gene, it exists, with an error message
+# """
+# caplog.set_level(logging.DEBUG)
+# all_prots = {"ESCO1": {"ESCO1_00001": '1',
+# "ESCO1_00002": '4'},
+# "ESCO2": {"ESCO2_00001": '1',
+# "ESCO2_22": '2',
+# "ESCO2_456": '4',
+# "ESCO2_46": '3'},
+# "ESCO3": {"ESCO3_1": '2',
+# "ESCO3_12": '1',
+# "ESCO3_4564": '3',
+# "ESCO3_00123": '4',
+# "ESCO3_8": '2'},
+# "ESCO6": {"ESCO6_1": '4',
+# "ESCO6_2": '3',
+# "ESCO6_3": '1'}}
+# several = {'1': [],
+# '2': ["ESCO3"],
+# '3': [],
+# '4': []}
+# listdir = "Listdir"
+# aldir = "Aldir"
+# # Create align folder
+# os.makedirs(listdir)
+# dname = "TEST6"
+# with pytest.raises(SystemExit):
+# p2p.write_getentry_files(all_prots, several, listdir, aldir, dname, ALL_GENOMES)
+# assert ("There is not any protein for genome ESCO4 in any family! The program will close, "
+# "please fix this problem to be able to run the alignments") in caplog.text
+# assert ("There is not any protein for genome ESCO5 in any family! The program will close, "
+# "please fix this problem to be able to run the alignments") in caplog.text
+# # Check creation and content of all files
+# genfiles = [os.path.join(listdir, "{}-getEntry_gen_ESCO{}.txt".format(dname, num)) for num in
+# list(range(1, 4)) + [6]]
+# expgens = [os.path.join(EXPPATH, "exp_getentry-gen-ESCO{}.txt".format(num)) for num in
+# list(range(1, 4)) + [6]]
+# for fexp, fout in zip(expgens, genfiles):
+# check_list(fexp, fout)
+# prtfiles = [os.path.join(listdir, "{}-getEntry_prt_ESCO{}.txt".format(dname, num)) for num in
+# list(range(1, 4)) + [6]]
+# expprts = [os.path.join(EXPPATH, "exp_getentry-prt-ESCO{}.txt".format(num)) for num in
+# list(range(1, 4)) + [6]]
+# for fexp, fout in zip(expprts, prtfiles):
+# check_list(fexp, fout)
+# shutil.rmtree(listdir)
def test_write_genome():
@@ -247,143 +273,137 @@ def test_write_genome():
Test that given a genome, it writes the list of its proteins
and genes in expected files.
"""
- listdir = "Listdir"
- aldir = "Aldir"
- # Create align folder
- os.makedirs(listdir)
- dname = "TEST6"
- strain = "ESCO4"
- member4 = ALL_PROTS[strain]
- p2p.write_genome_file(listdir, aldir, dname, strain, member4, SEVERAL)
-
- # Check creation of files and content
- fileprt = os.path.join(listdir, "{}-getEntry_prt_ESCO4.txt".format(dname))
- expprt = os.path.join(EXPPATH, "exp_getentry-prt-ESCO4.txt")
- check_list(expprt, fileprt)
- filegen = os.path.join(listdir, "{}-getEntry_gen_ESCO4.txt".format(dname))
- expgen = os.path.join(EXPPATH, "exp_getentry-gen-ESCO4.txt")
- check_list(expgen, filegen)
- # Remove output directory
- shutil.rmtree(listdir)
-
-
-def test_write_genome_prt_exists():
- """
- Test that when only prt file exists, it overwrites it and generates
- expected prt and gen files
- """
- listdir = "Listdir"
- aldir = "Aldir"
+ listdir = os.path.join(GENEPATH, "Listdir")
+ aldir = os.path.join(GENEPATH, "Aldir")
# Create align folder
os.makedirs(listdir)
- dname = "TEST6"
+ dname = "test_write_genome"
strain = "ESCO4"
- member4 = ALL_PROTS[strain]
-
- # Create prt file
- fileprt = os.path.join(listdir, "{}-getEntry_prt_ESCO4.txt".format(dname))
- with open(fileprt, "w") as prtf:
- prtf.write("Wrong prt file\n")
- p2p.write_genome_file(listdir, aldir, dname, strain, member4, SEVERAL)
+ members = ALL_PROTS[strain]
+ p2p.write_genome_file(listdir, aldir, dname, strain, members, SEVERAL)
# Check creation of files and content
+ fileprt = os.path.join(listdir, f"{dname}-getEntry_prt_ESCO4.txt")
expprt = os.path.join(EXPPATH, "exp_getentry-prt-ESCO4.txt")
- check_list(expprt, fileprt)
- filegen = os.path.join(listdir, "{}-getEntry_gen_ESCO4.txt".format(dname))
+ assert tutil.compare_file_content(fileprt, expprt)
+ filegen = os.path.join(listdir, f"{dname}-getEntry_gen_ESCO4.txt")
expgen = os.path.join(EXPPATH, "exp_getentry-gen-ESCO4.txt")
- check_list(expgen, filegen)
- # Remove output directory
- shutil.rmtree(listdir)
-
-
-def test_write_genome_gen_exists():
- """
- Test that when only gen file exists, it overwrites it and generates
- expected prt and gen files
- """
- listdir = "Listdir"
- aldir = "Aldir"
- # Create align folder
- os.makedirs(listdir)
- dname = "TEST6"
- strain = "ESCO4"
- member4 = ALL_PROTS[strain]
- # Create prt file
- filegen = os.path.join(listdir, "{}-getEntry_gen_ESCO4.txt".format(dname))
- with open(filegen, "w") as genf:
- genf.write("Wrong gen file\n")
- p2p.write_genome_file(listdir, aldir, dname, strain, member4, SEVERAL)
-
- # Check creation of files and content
- fileprt = os.path.join(listdir, "{}-getEntry_prt_ESCO4.txt".format(dname))
- expprt = os.path.join(EXPPATH, "exp_getentry-prt-ESCO4.txt")
- check_list(expprt, fileprt)
- expgen = os.path.join(EXPPATH, "exp_getentry-gen-ESCO4.txt")
- check_list(expgen, filegen)
- # Remove output directory
- shutil.rmtree(listdir)
-
-
-def test_write_genome_gen_prt_exist(caplog):
- """
- Test that when gen and prt files already exist, it does not do anything.
- Those files will be used for next steps.
- """
- caplog.set_level(logging.DEBUG)
- listdir = "Listdir"
- aldir = "Aldir"
- # Create align folder
- os.makedirs(listdir)
- dname = "TEST6"
- strain = "ESCO4"
- member4 = ALL_PROTS[strain]
- # Create gen and prt files
- filegen = os.path.join(listdir, "{}-getEntry_gen_ESCO4.txt".format(dname))
- with open(filegen, "w") as genf:
- genf.write("Wrong gen file\n")
- fileprt = os.path.join(listdir, "{}-getEntry_prt_ESCO4.txt".format(dname))
- with open(fileprt, "w") as prtf:
- prtf.write("Wrong prt file\n")
- p2p.write_genome_file(listdir, aldir, dname, strain, member4, SEVERAL)
-
- # Check log
- assert ("For genome ESCO4, {} and {} already exist. The program will use them to extract "
- "proteins and genes. If you prefer to rewrite them, use option "
- "-F (or --force).".format(fileprt, filegen)) in caplog.text
-
- # Check content of prt and gen has not changed
- with open(fileprt, "r") as prtf:
- lines = prtf.readlines()
- assert lines == ["Wrong prt file\n"]
- with open(filegen, "r") as prtf:
- lines = prtf.readlines()
- assert lines == ["Wrong gen file\n"]
-
- # Remove output directory
- shutil.rmtree(listdir)
-
-
-def check_list(expfile, outfile):
- """
- Check that the content of outfile is the same as in expfile
-
- Parameters
- ----------
- expfile : str
- path to expected file
- outfile : str
- path to output file
- """
- assert os.path.isfile(outfile)
- with open(expfile, "r") as expf, open(outfile, "r") as outf:
- lines_exp = []
- lines_out = []
- for lineexp in expf:
- lines_exp.append(lineexp.strip())
- for lineout in outf:
- lines_out.append(lineout.strip())
- assert len(lines_out) == len(lines_exp)
- assert set(lines_out) == set(lines_exp)
+ assert tutil.compare_file_content(filegen, expgen)
+
+
+# def test_write_genome_prt_exists():
+# """
+# Test that when only prt file exists, it overwrites it and generates
+# expected prt and gen files
+# """
+# listdir = os.path.join(GENEPATH, "Listdir")
+# aldir = os.path.join(GENEPATH, "Aldir")
+# # Create align folder
+# os.makedirs(listdir)
+# dname = "test_write_genome_prt_exists"
+# strain = "ESCO4"
+# members = ALL_PROTS[strain]
+
+# # Create prt file
+# fileprt = os.path.join(listdir, "{dname}-getEntry_prt_ESCO4.txt")
+# with open(fileprt, "w") as prtf:
+# prtf.write("Wrong prt file\n")
+# p2p.write_genome_file(listdir, aldir, dname, strain, members, SEVERAL)
+
+# # Check creation of files and content
+# expprt = os.path.join(EXPPATH, "exp_getentry-prt-ESCO4.txt")
+# assert tutil.compare_file_content(fileprt, expprt)
+# filegen = os.path.join(listdir, "{dname}-getEntry_gen_ESCO4.txt")
+# expgen = os.path.join(EXPPATH, "exp_getentry-gen-ESCO4.txt")
+# assert tutil.compare_file_content(expgen, filegen)
+
+
+# def test_write_genome_gen_exists():
+# """
+# Test that when only gen file exists, it overwrites it and generates
+# expected prt and gen files
+# """
+# listdir = os.path.join(GENEPATH, "Listdir")
+# aldir = os.path.join(GENEPATH, "Aldir")
+# # Create align folder
+# os.makedirs(listdir)
+# dname = "test_write_genome_gen_exists"
+# strain = "ESCO4"
+# member4 = ALL_PROTS[strain]
+# # Create prt file
+# filegen = os.path.join(listdir, f"{dname}-getEntry_gen_ESCO4.txt")
+# with open(filegen, "w") as genf:
+# genf.write("Wrong gen file\n")
+# p2p.write_genome_file(listdir, aldir, dname, strain, member4, SEVERAL)
+
+# # Check creation of files and content
+# fileprt = os.path.join(listdir, f"{dname}-getEntry_prt_ESCO4.txt")
+# expprt = os.path.join(EXPPATH, "exp_getentry-prt-ESCO4.txt")
+# assert tutil.compare_file_content(fileprt, expprt)
+# expgen = os.path.join(EXPPATH, "exp_getentry-gen-ESCO4.txt")
+# assert tutil.compare_file_content(filegen, expgen)
+
+
+# def test_write_genome_gen_prt_exist(caplog):
+# """
+# Test that when gen and prt files already exist, it does not do anything.
+# Those files will be used for next steps.
+# """
+# caplog.set_level(logging.DEBUG)
+# listdir = "Listdir"
+# aldir = "Aldir"
+# # Create align folder
+# os.makedirs(listdir)
+# dname = "TEST6"
+# strain = "ESCO4"
+# member4 = ALL_PROTS[strain]
+# # Create gen and prt files
+# filegen = os.path.join(listdir, "{}-getEntry_gen_ESCO4.txt".format(dname))
+# with open(filegen, "w") as genf:
+# genf.write("Wrong gen file\n")
+# fileprt = os.path.join(listdir, "{}-getEntry_prt_ESCO4.txt".format(dname))
+# with open(fileprt, "w") as prtf:
+# prtf.write("Wrong prt file\n")
+# p2p.write_genome_file(listdir, aldir, dname, strain, member4, SEVERAL)
+
+# # Check log
+# assert ("For genome ESCO4, {} and {} already exist. The program will use them to extract "
+# "proteins and genes. If you prefer to rewrite them, use option "
+# "-F (or --force).".format(fileprt, filegen)) in caplog.text
+
+# # Check content of prt and gen has not changed
+# with open(fileprt, "r") as prtf:
+# lines = prtf.readlines()
+# assert lines == ["Wrong prt file\n"]
+# with open(filegen, "r") as prtf:
+# lines = prtf.readlines()
+# assert lines == ["Wrong gen file\n"]
+
+# # Remove output directory
+# shutil.rmtree(listdir)
+
+
+# def check_list(expfile, outfile):
+# """
+# Check that the content of outfile is the same as in expfile
+
+# Parameters
+# ----------
+# expfile : str
+# path to expected file
+# outfile : str
+# path to output file
+# """
+# assert os.path.isfile(outfile)
+# with open(expfile, "r") as expf, open(outfile, "r") as outf:
+# lines_exp = []
+# lines_out = []
+# for lineexp in expf:
+# lines_exp.append(lineexp.strip())
+# for lineout in outf:
+# lines_out.append(lineout.strip())
+# assert len(lines_out) == len(lines_exp)
+# assert set(lines_out) == set(lines_exp)
def test_write_missing():
@@ -392,38 +412,11 @@ def test_write_missing():
list of all genomes, it returns, for each family, the genomes which will not
be considered.
"""
- aldir = "."
- dname = "TEST6"
- p2p.write_missing_genomes(FAM_GENOMES, SEVERAL, ALL_GENOMES, aldir, dname)
-
- # Check content of output files
- exp1 = []
- check_missing("{}-current.{}.miss.lst".format(dname, 1), exp1)
- exp2 = ["ESCO1", "ESCO3", "ESCO5", "ESCO6"]
- check_missing("{}-current.{}.miss.lst".format(dname, 2), exp2)
- exp3 = ["ESCO1"]
- check_missing("{}-current.{}.miss.lst".format(dname, 3), exp3)
- exp4 = ["ESCO4"]
- check_missing("{}-current.{}.miss.lst".format(dname, 4), exp4)
-
-
-def check_missing(outfile, exp):
- """
- Check that in the given output file, there is the given list of genomes.
- Then, remove outfile.
-
- Parameters
- ----------
- outfile : str
- output file
- exp : list
- list of lines that must be in outfile
- """
- assert os.path.isfile(outfile)
- missing = []
- with open(outfile, "r") as outf:
- for line in outf:
- missing.append(line.strip())
- assert len(missing) == len(exp)
- assert set(missing) == set(exp)
- os.remove(outfile)
+ dname = "test_write_missing"
+ p2p.write_missing_genomes(FAM_GENOMES, SEVERAL, ALL_GENOMES, GENEPATH, dname)
+
+ exp_res = [None, [], ["ESCO1", "ESCO3", "ESCO5", "ESCO6"], ["ESCO1"], ["ESCO4"]]
+ for num in range(1,5):
+ miss_file = os.path.join(GENEPATH, f"{dname}-current.{num}.miss.lst")
+ assert os.path.isfile(miss_file)
+ assert tutil.compare_file_to_list(miss_file, exp_res[num])
diff --git a/test/test_unit/utilities_for_tests.py b/test/test_unit/utilities_for_tests.py
index 64e17565e70049c007f6e291c43c3c21e902bdfc..69b7012112ac649a1fcf88919c1ec539f9099edb 100755
--- a/test/test_unit/utilities_for_tests.py
+++ b/test/test_unit/utilities_for_tests.py
@@ -70,4 +70,21 @@ def compare_order_content(file1, file2):
if line1 != line2:
print(f"'{line1}' vs {line2} do not correspond.")
return False
- return True
\ No newline at end of file
+ return True
+
+
+def compare_file_to_list(file1, exp):
+ """
+ Check that the file contains the same lines as the list 'exp', in any order
+ """
+ missing = []
+ with open(file1, "r") as outf:
+ for line in outf:
+ missing.append(line.strip())
+ if len(missing) != len(exp):
+ print(f"{len(missing)} lines in {file1}, {len(exp)} lines expected")
+ return False
+ if set(missing) != set(exp):
+ print("Not same lines")
+ return False
+ return True