idmap file fmt + tests

qiime2 · May 23, 2024 · 571d35f · 571d35f
1 parent 0d729a3
commit 571d35f
Show file tree

Hide file tree

Showing 7 changed files with 177 additions and 8 deletions.
diff --git a/q2_types/reference_db/_format.py b/q2_types/reference_db/_format.py
@@ -303,6 +303,36 @@ def _validate_(self, level):
         pass
 
 
+class HmmerIdmapFileFmt(model.TextFileFormat):
+    def _validate_(self, level):
+        with open(str(self), 'r') as file:
+            # Set the number of rows to be parsed
+            max_lines = {"min": 100, "max": 10000000}[level]
+            lines = file.readlines()
+            for i, line in enumerate(lines, 1):
+                # Check number of lines parsed so far
+                if i > max_lines:
+                    break
+
+                # Validate line
+                if not re.match(r'^(\d+) ([A-Z0-9]+)$', line):
+                    raise ValidationError(
+                        f"Invalid line {i}.\n"
+                        f"{line} \n"
+                        "Expected index and an alphanumeric code separated "
+                        "by a single space."
+                    )
+
+                # Check index is equal to line number
+                idx, code = line.rstrip("\n").split(sep=" ")
+                if not idx == str(i):
+                    raise ValidationError(
+                        f"Invalid line {i}.\n"
+                        f"{line} \n"
+                        f"Expected index {i} but got {idx} instead.\n"
+                    )
+
+
 class HmmerDirFmt(model.DirectoryFormat):
     """
     The  <hmmfile>.h3m file contains the profile HMMs
@@ -320,7 +350,7 @@ class HmmerDirFmt(model.DirectoryFormat):
     h3i = model.File(r'.*\.hmm\.h3i', format=HmmerBinaryFileFmt)
     h3f = model.File(r'.*\.hmm\.h3f', format=HmmerBinaryFileFmt)
     h3p = model.File(r'.*\.hmm\.h3p', format=HmmerBinaryFileFmt)
-    idmap = model.File(r'.*\.hmm\.idmap', format=HmmerBinaryFileFmt)
+    idmap = model.File(r'.*\.hmm\.idmap', format=HmmerIdmapFileFmt)
     fasta_files = model.FileCollection(
         r'.*\.(fa|fasta|faa)$',
         format=ProteinFASTAFormat,

diff --git a/q2_types/reference_db/tests/data/hmmer/bacteria/bacteria.hmm.idmap b/q2_types/reference_db/tests/data/hmmer/bacteria/bacteria.hmm.idmap
@@ -0,0 +1,19 @@
+1 1FKAT
+2 1FIZK
+3 1FIY1
+4 1FKA5
+5 1FIYP
+6 1FK7D
+7 1FIX5
+8 1FKCK
+9 1FIXT
+10 1FKBX
+11 1FIYG
+12 1FKAC
+13 1FKB9
+14 1FK72
+15 1FK4H
+16 1FK7S
+17 1FK66
+18 1FK6W
+19 1FIXC
diff --git a/q2_types/reference_db/tests/data/hmmer/invalid_idmaps/1.hmm.idmap b/q2_types/reference_db/tests/data/hmmer/invalid_idmaps/1.hmm.idmap
@@ -0,0 +1,19 @@
+1 1FKAT:"%#@
+2 1FIZK
+3 1FIY1
+4 1FKA5
+5 1FIYP
+6 1FK7D
+7 1FIX5
+8 1FKCK
+9 1FIXT
+10 1FKBX
+11 1FIYG
+12 1FKAC
+13 1FKB9
+14 1FK72
+15 1FK4H
+16 1FK7S
+17 1FK66
+18 1FK6W
+19 1FIXC
diff --git a/q2_types/reference_db/tests/data/hmmer/invalid_idmaps/2.hmm.idmap b/q2_types/reference_db/tests/data/hmmer/invalid_idmaps/2.hmm.idmap
@@ -0,0 +1,19 @@
+1 1FKAT
+2  1FIZK
+3 1FIY1
+4 1FKA5
+5 1FIYP
+6 1FK7D
+7 1FIX5
+8 1FKCK
+9 1FIXT
+10 1FKBX
+11 1FIYG
+12 1FKAC
+13 1FKB9
+14 1FK72
+15 1FK4H
+16 1FK7S
+17 1FK66
+18 1FK6W
+19 1FIXC
diff --git a/q2_types/reference_db/tests/data/hmmer/invalid_idmaps/3.hmm.idmap b/q2_types/reference_db/tests/data/hmmer/invalid_idmaps/3.hmm.idmap
@@ -0,0 +1,19 @@
+1 1FKAT
+2 1FIZK
+3 1FIY1
+4 1FKA5
+5 1FIYP
+6 1FK7D
+7 1FIX5
+8 1FKCK
+9 1FIXT
+10 1FKBX
+11 1FIYG
+12 1FKAC
+13 1FKB9
+14 1FK72
+15 1FK4H
+16 1FK7S
+17 1FK66
+18 1FK6W
+20 1FIXC
diff --git a/q2_types/reference_db/tests/data/hmmer/invalid_idmaps/4.hmm.idmap b/q2_types/reference_db/tests/data/hmmer/invalid_idmaps/4.hmm.idmap
@@ -0,0 +1,19 @@
+1FKAT
+2 1FIZK
+3 1FIY1
+4 1FKA5
+5 1FIYP
+6 1FK7D
+7 1FIX5
+8 1FKCK
+9 1FIXT
+10 1FKBX
+11 1FIYG
+12 1FKAC
+13 1FKB9
+14 1FK72
+15 1FK4H
+16 1FK7S
+17 1FK66
+18 1FK6W
+19 1FIXC
diff --git a/q2_types/reference_db/tests/test_format.py b/q2_types/reference_db/tests/test_format.py
@@ -13,7 +13,8 @@
     DiamondDatabaseFileFmt, DiamondDatabaseDirFmt, EggnogRefBinFileFmt,
     EggnogRefDirFmt, NCBITaxonomyNamesFormat, NCBITaxonomyNodesFormat,
     NCBITaxonomyDirFmt, NCBITaxonomyBinaryFileFmt,
-    EggnogProteinSequencesDirFmt, EggnogRefTextFileFmt, HmmerDirFmt
+    EggnogProteinSequencesDirFmt, EggnogRefTextFileFmt, HmmerDirFmt,
+    HmmerIdmapFileFmt
 )
 from qiime2.plugin import ValidationError
 
@@ -154,16 +155,59 @@ def test_EggnogRefTextFileFmt_invalid_taxid_lineage(self):
         ):
             fmt_obj.validate()
 
-    def test_HmmerDirFmt(self):
-        fmt = HmmerDirFmt(self.get_data_path("hmmer"), 'r')
+    def test_HmmerDirFmt_valid(self):
+        fmt = HmmerDirFmt(self.get_data_path("hmmer/bacteria"), 'r')
         fmt.validate()
 
+    def test_HmmerDirFmt_invalid_idmap_1(self):
+        fmt = HmmerIdmapFileFmt(self.get_data_path(
+            "hmmer/invalid_idmaps/1.hmm.idmap"), 'r'
+        )
+        with self.assertRaisesRegex(
+            ValidationError,
+            "Expected index and an alphanumeric code separated "
+            "by a single space."
+        ):
+            fmt.validate(level="min")
+
+    def test_HmmerDirFmt_invalid_idmap_2(self):
+        fmt = HmmerIdmapFileFmt(self.get_data_path(
+            "hmmer/invalid_idmaps/2.hmm.idmap"), 'r'
+        )
+        with self.assertRaisesRegex(
+            ValidationError,
+            "Expected index and an alphanumeric code separated "
+            "by a single space."
+        ):
+            fmt.validate(level="min")
+
+    def test_HmmerDirFmt_invalid_idmap_3(self):
+        fmt = HmmerIdmapFileFmt(self.get_data_path(
+            "hmmer/invalid_idmaps/3.hmm.idmap"), 'r'
+        )
+        with self.assertRaisesRegex(
+            ValidationError,
+            'Expected index'
+        ):
+            fmt.validate(level="min")
+
+    def test_HmmerDirFmt_invalid_idmap_4(self):
+        fmt = HmmerIdmapFileFmt(self.get_data_path(
+            "hmmer/invalid_idmaps/4.hmm.idmap"), 'r'
+        )
+        with self.assertRaisesRegex(
+            ValidationError,
+            "Expected index and an alphanumeric code separated "
+            "by a single space."
+        ):
+            fmt.validate(level="min")
+
     def test_HmmerDirFmt_missing_hmm(self):
         with tempfile.TemporaryDirectory() as tmp:
             shutil.copytree(
-                self.get_data_path("hmmer"), tmp, dirs_exist_ok=True
+                self.get_data_path("hmmer/bacteria"), tmp, dirs_exist_ok=True
             )
-            os.remove(f"{tmp}/bacteria/bacteria.hmm.h3f")
+            os.remove(f"{tmp}/bacteria.hmm.h3f")
             fmt = HmmerDirFmt(tmp, 'r')
             with self.assertRaisesRegex(
                 ValidationError, "Missing one or more files"
@@ -173,10 +217,10 @@ def test_HmmerDirFmt_missing_hmm(self):
     def test_HmmerDirFmt_missing_fa(self):
         with tempfile.TemporaryDirectory() as tmp:
             shutil.copytree(
-                self.get_data_path("hmmer"), tmp, dirs_exist_ok=True
+                self.get_data_path("hmmer/bacteria"), tmp, dirs_exist_ok=True
             )
             for file in ["a", "b", "b2"]:
-                os.remove(f"{tmp}/bacteria/{file}.fa")
+                os.remove(f"{tmp}/{file}.fa")
             fmt = HmmerDirFmt(tmp, 'r')
             with self.assertRaisesRegex(
                 ValidationError, "Missing one or more files"
-Original file line number
+Diff line change
@@ -0,0 +1,19 @@
+1FKAT
+1FIZK
+1FIY1
+1FKA5
+1FIYP
+1FK7D
+1FIX5
+1FKCK
+1FIXT
+1FKBX
+1FIYG
+1FKAC
+1FKB9
+1FK72
+1FK4H
+1FK7S
+1FK66
+1FK6W
+1FIXC