aldepyde 0.0.0a33__py3-none-any.whl → 0.0.0a35__py3-none-any.whl

aldepyde/databases/SCOPe_Astral.py

@@ -0,0 +1,71 @@
+from aldepyde.databases._database import local_database
+import operator
+from contextlib import nullcontext
+import re
+
+class scop_parser(local_database):
+    op = {
+        "and": lambda a,b,c: a and b and c,
+        "or": lambda a,b,c: a or b or c
+    }
+
+    def fetch(self, url):
+        pass
+
+    def fetch_code(self, codes):
+        pass
+
+    def parse(self, text):
+        pass
+
+    def extract_all_scop(self):
+        pass
+
+    def partition_scope(self):
+        pass
+
+    def extract_all_astral(self):
+        lines = self.fp.readlines()
+        entry = b""
+        for line in lines:
+            if line.startswith(b">") and len(entry) > 0:
+                yield entry
+                entry = b""
+            entry += line
+        yield entry
+
+    # TODO allow a list of search parameters. Big challenge to make efficient, but could be cute
+    def partition_astral(self, destination:None|str=None, append=False, class_name:str=b'',contains_id:str=b'' , contains_desc:str=b'', mode="and") -> dict:
+        mode = mode.lower()
+        # Everything is a byte string in order to play nicely with future parent methods
+        if isinstance(class_name, str):
+            class_name = class_name.encode('utf-8')
+        if isinstance(contains_desc, str):
+            contains_desc = contains_desc.encode('utf-8')
+        if isinstance(contains_id, str):
+            contains_id = contains_id.encode('utf-8')
+        if mode != "and" and mode != "or":
+            raise ValueError("mode must be \"and\" or \"or\".")
+        logic = scop_parser.op[mode]
+        regex = re.compile(b">[a-zA-Z0-9_.]* *[a-l](.[0-9]+)?(.[0-9]+)?(.[0-9]+)?")
+        if append:
+            file_context = open(destination, 'ab') if destination is not None else nullcontext()
+        else:
+            file_context = open(destination, 'wb') if destination is not None else nullcontext()
+        with file_context as fp:
+            ret_dict = dict()
+            for line in self.extract_all_astral():
+                identifiers = regex.search(line).group().split()
+                id = identifiers[0]
+                cls = identifiers[1]
+                unmatched_spl = regex.sub(b'', line).split(b'\n')
+                desc = unmatched_spl[0]
+                sequence = unmatched_spl[1:]
+                if logic(class_name.lower() in cls.lower(), contains_id.lower() in id.lower(), contains_desc.lower() in desc.lower()):
+                    ret_dict[id] = { # Yes, I know '>' isn't part of the FASTA identifier. This keeps things more consistant
+                        "class" : cls,
+                        "description" : desc,
+                        "sequence" : b"".join(sequence)
+                    }
+                    fp.write(line)
+        return ret_dict

aldepyde/databases/UniRef.py

@@ -1,42 +1,45 @@
 import zlib
-
-from aldepyde.databases.RemoteFileHandler import RemoteFileHandler
-from aldepyde.databases._database import _database
+from aldepyde.databases._database import streamable_database
 from aldepyde.utils import ProgressBar
-import os
-import gzip
 
-class uniref_parser(_database):
+class uniref_parser(streamable_database):
     def __init__(self):
         super().__init__()
 
     # TODO single entry parsing
     # TODO store metadata upon request
+    # TODO implement abstract methods
 
     @staticmethod
-    def stream_uniref_gz(filepath, chunk_size=8192, use_progress_bar=False):
-        raw_stream, size = _database.open_stream(filepath)
+    def stream_uniref_gz(filepath, chunk_size=8192, use_progress_bar=False, stitch=False):
+        raw_stream, size = streamable_database.open_stream(filepath)
         pbar = ProgressBar(size//chunk_size) if use_progress_bar else None
         decompressor = zlib.decompressobj(16 + zlib.MAX_WBITS)
         try:
-            while True:
-                comp_chunk = raw_stream.read(chunk_size)
-                if not comp_chunk:
-                    break
-                if pbar is not None:
-                    pbar.update()
-                decomp_chunk = decompressor.decompress(comp_chunk)
-                if decomp_chunk:
-                    yield decomp_chunk
-            final = decompressor.flush()
-            if final:
-                yield final
+            if not stitch:
+                while True:
+                    comp_chunk = raw_stream.read(chunk_size)
+                    if not comp_chunk:
+                        break
+                    if pbar is not None:
+                        pbar.update()
+                    decomp_chunk = decompressor.decompress(comp_chunk)
+                    if decomp_chunk:
+                        yield decomp_chunk
+                final = decompressor.flush()
+                if final:
+                    yield final
+            else:
+                # Really hacky solution for now
+                # TODO Clean this up
+                yield from uniref_parser.stitch_streamed_sequences(
+                    uniref_parser.stream_uniref_gz(filepath=filepath, chunk_size=chunk_size, use_progress_bar=use_progress_bar, stitch=False))
         finally:
             raw_stream.close()
 
     @staticmethod
     def download_file(url, destination, chunk_size=8192, use_progress_bar=False):
-        raw_stream, size = _database.open_stream(url)
+        raw_stream, size = streamable_database.open_stream(url)
         pbar = ProgressBar(size // chunk_size) if use_progress_bar else None
         with open(destination, 'wb') as fp:
             while True:
@@ -48,8 +51,6 @@ class uniref_parser(_database):
                 fp.write(chunk)
 
 
-
-
     @staticmethod
     def stitch_streamed_sequences(stream, as_str=True):
         buffer = b''

aldepyde/databases/_database.py

@@ -5,7 +5,7 @@ import os
 from typing import Tuple, BinaryIO
 from io import TextIOWrapper
 
-class _database(ABC):
+class streamable_database(ABC):
 
     def __init__(self):
         pass
@@ -38,4 +38,35 @@ class _database(ABC):
     # Yes, I know the first conditionals do the same thing
 
     def __call__(self):
-        pass
+        pass
+
+class local_database(ABC):
+
+    def __init__(self, filepath=None, as_fp=False):
+        self.fp = None
+        self.as_fp = as_fp
+        self.size = None
+        self.load_path(filepath)
+
+    def load_path(self, filepath):
+        self.filepath = filepath
+
+    def get_pointer(self):
+        return self.fp
+
+    def __enter__(self):
+        self.fp, self.size = local_database.open_stream(self.filepath)
+        if self.as_fp:
+            return self.fp
+        else:
+            return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        if self.fp is not None:
+            self.fp.close()
+        self.fp = None
+
+    @staticmethod
+    def open_stream(source:str) -> Tuple[BinaryIO, int] | None:
+        size = os.path.getsize(source)
+        return open(source, 'rb'), size

{aldepyde-0.0.0a33.dist-info → aldepyde-0.0.0a35.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: aldepyde
-Version: 0.0.0a33
+Version: 0.0.0a35
 Summary: A package of chemistry and biochemical tools
 Author-email: Nate McMurray <nate.mcmurray13@gmail.com>
 License: MIT License

{aldepyde-0.0.0a33.dist-info → aldepyde-0.0.0a35.dist-info}/RECORD

@@ -24,9 +24,10 @@ aldepyde/data/RemoteFileHandler.py,sha256=aPASdoYgt0xnRrSYiwMcefQAizLIbB93SKVrlf
 aldepyde/data/__init__.py,sha256=_yKL38EKhXkRM8PSafeee0A6VXGncAoUXVdUyiJ5n3s,48
 aldepyde/databases/PDB.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 aldepyde/databases/RemoteFileHandler.py,sha256=HHx69o6IpI60lf_7hY1ZwI8k0OVyfofG4x1bFeF1uL4,1231
-aldepyde/databases/UniRef.py,sha256=9Inu5rnmm7xoPUtg6I2ge6sKh7IYFR1q_8orK-ZtaI0,5614
+aldepyde/databases/SCOPe_Astral.py,sha256=zj34CbMSTmTa-KBowND-S9rxNGGFnr84OuxC_fumM6E,2821
+aldepyde/databases/UniRef.py,sha256=lAT5XVO9Rk4_9XDKs5Nr1aGBbkaQ6m-vM0yufym43aY,6004
 aldepyde/databases/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-aldepyde/databases/_database.py,sha256=i5cXf65d2YYIJMvCDaeAVYfXTZeJsIpwBMWDONFAGlw,990
+aldepyde/databases/_database.py,sha256=fvm4jaP9UKHDeS-0wwWyp7i4uo9PjCGDbwJgdkD8MLo,1822
 aldepyde/fetcher/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 aldepyde/fetcher/test.py,sha256=Q0O3TrMnyd_V3QZvMaDtkFGXIvtQLg57RofKjxtG8Y8,23
 aldepyde/json/CHG.json,sha256=igz1QSwoyXieOWMRwPnQjUJX29N5bk5OBVkhpFjyCzo,614
@@ -36,8 +37,8 @@ aldepyde/rand/RandomProtein.py,sha256=sNXx4jop9Fplz2oz4g6pEArF69j31_PvtiZuRpLz51
 aldepyde/rand/__init__.py,sha256=Q30wrG_XHrmdgaXaLWSlce_ZGT_ZpOT3CYLDj6OgEy0,182
 aldepyde/stats/ProteinStats.py,sha256=t_gqhld2wKweszPZvtHhrORadFc28glFx5OgJs23TsM,2569
 aldepyde/stats/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-aldepyde-0.0.0a33.dist-info/licenses/LICENSE,sha256=VbOVaNlEaWa9cnYi8gOnenCBAVk9s_P3J_z-n_F-638,1091
-aldepyde-0.0.0a33.dist-info/METADATA,sha256=II-y79yF2xeV5RAsqd-AP9BvW7N0C38vvpGvfgLt_TI,2554
-aldepyde-0.0.0a33.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-aldepyde-0.0.0a33.dist-info/top_level.txt,sha256=xv0YJ1izG4AP9ZlielN_0z9QGQQdwtHFM3-TmJivBOM,9
-aldepyde-0.0.0a33.dist-info/RECORD,,
+aldepyde-0.0.0a35.dist-info/licenses/LICENSE,sha256=VbOVaNlEaWa9cnYi8gOnenCBAVk9s_P3J_z-n_F-638,1091
+aldepyde-0.0.0a35.dist-info/METADATA,sha256=NdHCpQYVP7NbBRxOmUXvu5ZlsD94jVS_z6ABY_Ejees,2554
+aldepyde-0.0.0a35.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+aldepyde-0.0.0a35.dist-info/top_level.txt,sha256=xv0YJ1izG4AP9ZlielN_0z9QGQQdwtHFM3-TmJivBOM,9
+aldepyde-0.0.0a35.dist-info/RECORD,,