cdhit-reader 0.2.0__tar.gz → 0.3.0__tar.gz

{cdhit-reader-0.2.0/cdhit_reader.egg-info → cdhit_reader-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: cdhit-reader
-Version: 0.2.0
+Version: 0.3.0
 Summary: CD-HIT cluster parser
 Home-page: https://github.com/telatin/cdhit-parser
 Download-URL: https://github.com/telatin/cdhit-parser
@@ -18,8 +18,16 @@ Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python
 Description-Content-Type: text/markdown
-Provides-Extra: cli
 License-File: LICENSE.md
+Requires-Dist: click>=7.1.2
+Requires-Dist: importlib-resources>=1.4.0
+Requires-Dist: more-itertools>=8.4.0
+Requires-Dist: pytest>=5.4.3
+Requires-Dist: xopen>=1.0.1
+Provides-Extra: cli
+Requires-Dist: plotille; extra == "cli"
+Dynamic: download-url
+Dynamic: license-file
 
 # cdhit-parser
 

cdhit_reader-0.3.0/cdhit_reader/__init__.py

@@ -0,0 +1,41 @@
+from importlib import import_module
+
+from ._reader import ParsingError, ClusterSequence, Cluster, ClstrReader, read_cdhit, SeqType, Strand
+from ._fasta import FastaParsingError, Sequence, FastaReader, read_fasta
+from ._version import __version__
+
+_LAZY_EXPORTS = {
+    "cli": ("._cli", "cli"),
+    "compare": ("._compare", "compare"),
+    "test": ("._testit", "test"),
+}
+
+__all__ = [
+    "ParsingError",
+    "FastaParsingError",
+    "ClusterSequence",
+    "Cluster",
+    "ClstrReader",
+    "read_cdhit",
+    "FastaReader",
+    "read_fasta",
+    "SeqType",
+    "Strand",
+    "Sequence",
+    "__version__",
+    "cli",
+    "compare",
+    "test",
+]
+
+
+def __getattr__(name):
+    if name in _LAZY_EXPORTS:
+        module_name, attribute_name = _LAZY_EXPORTS[name]
+        module = import_module(module_name, __name__)
+        return getattr(module, attribute_name)
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
+
+
+def __dir__():
+    return sorted(set(globals()) | set(__all__))

{cdhit-reader-0.2.0 → cdhit_reader-0.3.0}/cdhit_reader/_fasta.py

@@ -1,12 +1,31 @@
 from __future__ import annotations
 from pathlib import Path
 from typing import IO, Iterator, List, Union
-from enum import Enum
 from more_itertools import peekable
 from xopen import xopen
-import re
 
-__all__ = ["Sequence", "FastaReader", "read_fasta"]
+__all__ = ["FastaParsingError", "Sequence", "FastaReader", "read_fasta"]
+
+
+class FastaParsingError(Exception):
+    """
+    FASTA parsing error.
+    """
+
+    def __init__(self, line_number: int, message: str = "Invalid FASTA file"):
+        super().__init__(f"{message} at line {line_number}.")
+        self._line_number = line_number
+
+    @property
+    def line_number(self) -> int:
+        """
+        Line number.
+
+        Returns
+        -------
+        Line number.
+        """
+        return self._line_number
  
  
 
@@ -54,6 +73,7 @@ class FastaReader:
         self._seq = ""
         self._lines = peekable(line for line in file)
         self._line_number = 0
+        self._current_defline_number = 0
 
     def read_item(self) -> Sequence:
         """
@@ -87,34 +107,46 @@ class FastaReader:
 
     def _next_defline(self) -> str:
         while True:
-            line = next(self._lines)
-            self._line_number += 1
-            if line == "":
+            try:
+                line = next(self._lines)
+            except StopIteration:
                 raise StopIteration
 
+            self._line_number += 1
+
             line = line.strip()
             if line.startswith(">"):
+                self._current_defline_number = self._line_number
                 return line[1:]
             if line != "":
-                raise "Invalid FASTA file"
+                raise FastaParsingError(self._line_number, "Expected FASTA header")
 
     def _next_sequences(self) -> str:
         seq = ""
         while True:
-            line = next(self._lines).strip()
-            
+            try:
+                line = next(self._lines)
+            except StopIteration as exc:
+                raise FastaParsingError(
+                    self._current_defline_number,
+                    "Missing sequence for FASTA record",
+                ) from exc
+
             self._line_number += 1
-            if line == "":
-                raise
 
             line = line.strip()
-            if not line.startswith(">"):
-                seq += line
-                if self._sequence_continues():
-                    continue
-                return seq
-            if line != "":
-                raise 
+            if line == "":
+                raise FastaParsingError(self._line_number, "Blank lines are not allowed in FASTA records")
+            if line.startswith(">"):
+                raise FastaParsingError(
+                    self._current_defline_number,
+                    "Missing sequence for FASTA record",
+                )
+
+            seq += line
+            if self._sequence_continues():
+                continue
+            return seq
      
 
     def _sequence_continues(self):
@@ -157,4 +189,4 @@ def read_fasta(file: Union[str, Path, IO[str]], separator=" ", line_len = 0) ->
     -------
     FASTA reader.
     """
-    return FastaReader(file, separator=separator, line_len=line_len)
+    return FastaReader(file, separator=separator, line_len=line_len)

{cdhit-reader-0.2.0 → cdhit_reader-0.3.0}/cdhit_reader/_reader.py

@@ -8,6 +8,13 @@ import re
 
 __all__ = ["ParsingError", "ClusterSequence", "Cluster", "ClstrReader", "read_cdhit", "SeqType", "Strand", "FastaReader", "read_fasta"]
 
+CLUSTER_SEQUENCE_PATTERN = re.compile(
+    r"(?P<id>\d+)\s+(?P<size>\d+)(?P<type>aa|nt), >(?P<name>.+?)\.\.\. (?P<attr>.+)"
+)
+CLUSTER_ATTR_PATTERN = re.compile(
+    r"(?P<ref>\*|at) .*?(?P<strand>[+-]?)\/?(?P<percent>\d+\.?\d*)%"
+)
+
 class SeqType(Enum):
     """
     Sequence type.
@@ -59,7 +66,7 @@ class ClusterSequence:
     ----------
     line: str
     """
-    def __init__(self, line: str):
+    def __init__(self, line: str, line_number: int | None = None):
         """
         Parameters
         ----------
@@ -67,6 +74,7 @@ class ClusterSequence:
             Line.
         """
         self.line = line
+        self.line_number = line_number
         self.length = 0
         self.name = ""
         self.identity = 0
@@ -80,33 +88,32 @@ class ClusterSequence:
         """
         3       502nt, >IKXM6KN01CFAFI... at 1:502:1:503/+/97.81%
         """
-
-
-        pattern = re.compile(
-            r"(?P<id>\d+)\s+(?P<size>\d+)(?P<type>aa|nt), >(?P<name>.+?)\.\.\. (?P<attr>.+)"
-        )
-        attrpatt = re.compile(         
-            r"(?P<ref>\*|at) .*?(?P<strand>[+-]?)\/?(?P<percent>\d+\.?\d*)%"
-        )
-
-
-        match = pattern.search(self.line)
+        match = CLUSTER_SEQUENCE_PATTERN.fullmatch(self.line)
+        if not match:
+            self._raise_parsing_error()
 
         self.seqtype = SeqType.PROTEIN if match["type"] == "aa" else SeqType.NT
         self.strand  = Strand.NONE if self.seqtype == SeqType.PROTEIN else Strand.PLUS
-        if match:
-            self.name = match["name"]
-            self.id = int(match["id"])
-            self.length = int(match["size"])
-            if match["attr"] == "*":
-                self.is_ref = True
-                self.identity = 100.0
-                
-            else:
-                attrs = attrpatt.match(match["attr"])
-                self.is_ref = False
-                self.identity = float(attrs["percent"])
-                self.strand = Strand.PLUS if attrs["strand"] == "+" else Strand.REVERSE if attrs["strand"] == "-" else Strand.NONE
+        self.name = match["name"]
+        self.id = int(match["id"])
+        self.length = int(match["size"])
+        if match["attr"] == "*":
+            self.is_ref = True
+            self.identity = 100.0
+            return
+
+        attrs = CLUSTER_ATTR_PATTERN.fullmatch(match["attr"])
+        if not attrs:
+            self._raise_parsing_error()
+
+        self.is_ref = False
+        self.identity = float(attrs["percent"])
+        self.strand = Strand.PLUS if attrs["strand"] == "+" else Strand.REVERSE if attrs["strand"] == "-" else Strand.NONE
+
+    def _raise_parsing_error(self):
+        if self.line_number is not None:
+            raise ParsingError(self.line_number)
+        raise ValueError(f"Invalid cluster sequence line: {self.line}")
 
     def __repr__(self):
         return f"ClusterSequence(id={self.id}, name={self.name}, length={self.length}, identity={self.identity}, is_ref={self.is_ref}, seqtype={self.seqtype}, strand={self.strand})"
@@ -220,7 +227,7 @@ class FastaReader:
 
             line = line.strip()
             if not line.startswith(">"):
-                clusterSequences.append( ClusterSequence(line.strip()) )
+                clusterSequences.append(ClusterSequence(line.strip(), line_number=self._line_number))
                 if self._sequence_continues():
                     continue
                 return clusterSequences
@@ -330,7 +337,7 @@ class ClstrReader:
 
             line = line.strip()
             if not line.startswith(">"):
-                clusterSequences.append( ClusterSequence(line.strip()) )
+                clusterSequences.append(ClusterSequence(line.strip(), line_number=self._line_number))
                 if self._sequence_continues():
                     continue
                 return clusterSequences

{cdhit-reader-0.2.0 → cdhit_reader-0.3.0}/cdhit_reader/_version.py

@@ -1,4 +1,4 @@
 # Version file
-__version__ = "0.2.0"
+__version__ = "0.3.0"
 
 __all__ = ["__version__"]

{cdhit-reader-0.2.0 → cdhit_reader-0.3.0}/cdhit_reader/test/test_clstr.py

@@ -1,5 +1,6 @@
 import os
 from pathlib import Path
+from io import StringIO
 
 import pytest
 import sys
@@ -60,6 +61,13 @@ def test_aa():
             assert [s.name for s in cluster.sequences] == cluster2
             assert cluster.refname == cluster2[0]
         n += 1
+
+
+def test_invalid_member_line_raises_parsing_error():
+    with pytest.raises(ParsingError) as excinfo:
+        list(read_cdhit(StringIO(">Cluster 0\n0 492nt, >seq1.A...\n")))
+
+    assert excinfo.value.line_number == 2
         
 def _test_cluster_structure(cluster):
     # name
@@ -85,4 +93,4 @@ def _test_seq(s):
 
     assert s.strand is not None
     assert s.strand == Strand.PLUS or s.strand == Strand.REVERSE
-    return True
+    return True

cdhit_reader-0.3.0/cdhit_reader/test/test_fasta.py

@@ -0,0 +1,34 @@
+from io import StringIO
+
+import pytest
+
+from cdhit_reader._fasta import FastaParsingError, read_fasta
+
+
+def test_fasta_reads_last_record_without_trailing_newline():
+    records = list(read_fasta(StringIO(">seq1 comment\nACG\n>seq2\nTT")))
+
+    assert [record.name for record in records] == ["seq1", "seq2"]
+    assert [record.comment for record in records] == ["comment", None]
+    assert [record.sequence for record in records] == ["ACG", "TT"]
+
+
+def test_fasta_rejects_non_header_first_line():
+    with pytest.raises(FastaParsingError) as excinfo:
+        list(read_fasta(StringIO("seq1\nACG\n")))
+
+    assert excinfo.value.line_number == 1
+
+
+def test_fasta_rejects_header_without_sequence():
+    with pytest.raises(FastaParsingError) as excinfo:
+        list(read_fasta(StringIO(">seq1\n")))
+
+    assert excinfo.value.line_number == 1
+
+
+def test_fasta_rejects_header_without_sequence_before_next_record():
+    with pytest.raises(FastaParsingError) as excinfo:
+        list(read_fasta(StringIO(">seq1\n>seq2\nTT\n")))
+
+    assert excinfo.value.line_number == 1

cdhit_reader-0.3.0/cdhit_reader/test/test_package_import.py

@@ -0,0 +1,55 @@
+import json
+import subprocess
+import sys
+
+
+def test_package_import_does_not_eagerly_import_cli_modules():
+    code = """
+import json
+import sys
+import cdhit_reader
+
+print(json.dumps({
+    "has_read_cdhit": hasattr(cdhit_reader, "read_cdhit"),
+    "cli_loaded": "cdhit_reader._cli" in sys.modules,
+    "compare_loaded": "cdhit_reader._compare" in sys.modules,
+    "test_loaded": "cdhit_reader._testit" in sys.modules,
+}))
+"""
+    result = subprocess.run(
+        [sys.executable, "-c", code],
+        capture_output=True,
+        text=True,
+        check=True,
+    )
+
+    payload = json.loads(result.stdout)
+    assert payload == {
+        "has_read_cdhit": True,
+        "cli_loaded": False,
+        "compare_loaded": False,
+        "test_loaded": False,
+    }
+
+
+def test_lazy_cli_export_imports_on_demand():
+    code = """
+import json
+import sys
+import cdhit_reader
+
+before = "cdhit_reader._cli" in sys.modules
+_ = cdhit_reader.cli
+after = "cdhit_reader._cli" in sys.modules
+
+print(json.dumps({"before": before, "after": after}))
+"""
+    result = subprocess.run(
+        [sys.executable, "-c", code],
+        capture_output=True,
+        text=True,
+        check=True,
+    )
+
+    payload = json.loads(result.stdout)
+    assert payload == {"before": False, "after": True}

{cdhit-reader-0.2.0 → cdhit_reader-0.3.0/cdhit_reader.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: cdhit-reader
-Version: 0.2.0
+Version: 0.3.0
 Summary: CD-HIT cluster parser
 Home-page: https://github.com/telatin/cdhit-parser
 Download-URL: https://github.com/telatin/cdhit-parser
@@ -18,8 +18,16 @@ Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python
 Description-Content-Type: text/markdown
-Provides-Extra: cli
 License-File: LICENSE.md
+Requires-Dist: click>=7.1.2
+Requires-Dist: importlib-resources>=1.4.0
+Requires-Dist: more-itertools>=8.4.0
+Requires-Dist: pytest>=5.4.3
+Requires-Dist: xopen>=1.0.1
+Provides-Extra: cli
+Requires-Dist: plotille; extra == "cli"
+Dynamic: download-url
+Dynamic: license-file
 
 # cdhit-parser
 

{cdhit-reader-0.2.0 → cdhit_reader-0.3.0}/cdhit_reader.egg-info/SOURCES.txt

@@ -22,4 +22,6 @@ cdhit_reader.egg-info/zip-safe
 cdhit_reader/test/__init__.py
 cdhit_reader/test/aa.clstr
 cdhit_reader/test/nt.clstr
-cdhit_reader/test/test_clstr.py
+cdhit_reader/test/test_clstr.py
+cdhit_reader/test/test_fasta.py
+cdhit_reader/test/test_package_import.py

cdhit_reader-0.3.0/cdhit_reader.egg-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+cdhit-compare = cdhit_reader._compare:compare
+cdhit-parser = cdhit_reader._cli:cli

cdhit_reader-0.3.0/setup.py

@@ -0,0 +1,8 @@
+from setuptools import setup
+
+if __name__ == "__main__":
+    console_scripts = [
+        "cdhit-parser = cdhit_reader._cli:cli",
+        "cdhit-compare = cdhit_reader._compare:compare",
+    ]
+    setup(entry_points=dict(console_scripts=console_scripts))

cdhit-reader-0.2.0/cdhit_reader/__init__.py

@@ -1,26 +0,0 @@
-from ._cli import cli
-from ._compare import compare
-from ._reader import ParsingError, ClusterSequence, Cluster, ClstrReader, read_cdhit, SeqType, Strand
-from ._fasta import Sequence, FastaReader, read_fasta
-from ._testit import test
-from ._version import __version__
-#from ._writer import FASTAWriter, write_fasta
-
-__all__ = [
-    "ParsingError",
-    "ClusterSequence",
-    "Cluster",
-    "ClstrReader",
-    "read_cdhit",
-    "FastaReader",
-    "read_fasta",
-    "SeqType",
-    "Strand", 
-    "Sequence",
-    "FastaReader",
-    "read_fasta",
-    "__version__",
-    "cli",
-    "compare",
-    "test",
-]

cdhit-reader-0.2.0/cdhit_reader.egg-info/entry_points.txt

@@ -1,3 +0,0 @@
-[console_scripts]
-cdhit-compare = cdhit_reader:compare
-cdhit-parser = cdhit_reader:cli

cdhit-reader-0.2.0/setup.py

@@ -1,5 +0,0 @@
-from setuptools import setup
-
-if __name__ == "__main__":
-    console_scripts = ["cdhit-parser = cdhit_reader:cli", "cdhit-compare = cdhit_reader:compare"]
-    setup(entry_points=dict(console_scripts=console_scripts))