pydna 5.5.1__py3-none-any.whl → 5.5.3__py3-none-any.whl

pydna/gel.py

@@ -27,7 +27,9 @@ def interpolator(mwstd):
     return interpolator
 
 
-def gel(samples=None, gel_length=600, margin=50, interpolator=interpolator(mwstd=_mwstd)):
+def gel(
+    samples=None, gel_length=600, margin=50, interpolator=interpolator(mwstd=_mwstd)
+):
     import numpy as np
     from PIL import Image as Image
     from PIL import ImageDraw as ImageDraw
@@ -65,7 +67,11 @@ def gel(samples=None, gel_length=600, margin=50, interpolator=interpolator(mwstd
                 y1 = peak_centre - i
                 y2 = peak_centre + i
                 intensity = (
-                    height * _math.exp(-float(((y1 - peak_centre) ** 2)) / (2 * (band_spread**2))) * max_intensity
+                    height
+                    * _math.exp(
+                        -float(((y1 - peak_centre) ** 2)) / (2 * (band_spread**2))
+                    )
+                    * max_intensity
                 )
                 for y in range(int(y1), int(y2)):
                     try:
@@ -95,14 +101,3 @@ def gel(samples=None, gel_length=600, margin=50, interpolator=interpolator(mwstd
 # from PIL import ImageOps
 # im_invert = ImageOps.invert(im)
 # im.rotate(90, expand=1)
-
-
-if __name__ == "__main__":
-    import os as _os
-
-    cached = _os.getenv("pydna_cached_funcs", "")
-    _os.environ["pydna_cached_funcs"] = ""
-    import doctest
-
-    doctest.testmod(verbose=True, optionflags=doctest.ELLIPSIS)
-    _os.environ["pydna_cached_funcs"] = cached

pydna/genbank.py

@@ -11,7 +11,7 @@ The function can be used if the environmental variable **pydna_email** has
 been set to a valid email address. The easiest way to do this permanantly is to edit the
 `pydna.ini` file. See the documentation of :func:`pydna.open_config_folder`"""
 
-from pydna.utils import memorize as _memorize
+# from pydna.utils import memorize as _memorize
 from pydna.genbankrecord import GenbankRecord as _GenbankRecord
 from pydna.readers import read as _read
 
@@ -19,9 +19,10 @@ from Bio import Entrez as _Entrez
 from typing import Literal as _Literal, Optional as _Optional
 import re as _re
 import os as _os
-import logging as _logging
 
-_module_logger = _logging.getLogger("pydna." + __name__)
+# import logging as _logging
+
+# _module_logger = _logging.getLogger("pydna." + __name__)
 
 
 # TODO http://httpbin.org/ use for testing?
@@ -53,15 +54,19 @@ class Genbank:
         *,
         tool: str = "pydna",
     ) -> None:
-        if not _re.match(r"[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,4}", users_email, _re.IGNORECASE):
+        if not _re.match(
+            r"[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,4}", users_email, _re.IGNORECASE
+        ):
             raise ValueError("email address {} is not valid.".format(users_email))
 
-        _module_logger.info("#### Genbank ititiation ####")
-        _module_logger.info("Genbank initiated with email: %s", users_email)
-        _module_logger.info("Genbank initiated with tool : %s", tool)
+        # _module_logger.info("#### Genbank ititiation ####")
+        # _module_logger.info("Genbank initiated with email: %s", users_email)
+        # _module_logger.info("Genbank initiated with tool : %s", tool)
 
         if users_email == "someone@example.com":
-            raise ValueError("you have to set your email address in order to download from Genbank")
+            raise ValueError(
+                "you have to set your email address in order to download from Genbank"
+            )
         self.email = users_email
         self.tool = tool
 
@@ -69,7 +74,7 @@ class Genbank:
         """This method returns a short representation containing the email used to initiate."""
         return "GenbankConnection({})".format(self.email)
 
-    @_memorize("pydna.genbank.Genbank.nucleotide")
+    # @_memorize("pydna.genbank.Genbank.nucleotide")
     def nucleotide(
         self,
         item: str,
@@ -127,7 +132,9 @@ class Genbank:
             (1, _re.search(r"(REGION:\s(?P<start>\d+)\.\.(?P<stop>\d+))", item)),
             (
                 2,
-                _re.search(r"(REGION: complement\((?P<start>\d+)\.\.(?P<stop>\d+)\))", item),
+                _re.search(
+                    r"(REGION: complement\((?P<start>\d+)\.\.(?P<stop>\d+)\))", item
+                ),
             ),
             (1, _re.search(r"(:|\s)(?P<start>\d+)-(?P<stop>\d+)", item)),
             (2, _re.search(r"(:|\s)c(?P<start>\d+)-(?P<stop>\d+)", item)),
@@ -143,21 +150,23 @@ class Genbank:
 
         if strand not in [1, 2]:
             try:
-                strand = {"c": 2, "crick": 2, "antisense": 2, "2": 2, "-": 2, "-1": 2}[strand.lower()]
+                strand = {"c": 2, "crick": 2, "antisense": 2, "2": 2, "-": 2, "-1": 2}[
+                    strand.lower()
+                ]
             except (KeyError, AttributeError):
                 strand = 1
 
-        _module_logger.info("#### Genbank download ####")
-        _module_logger.info("item  %s", item)
-        _module_logger.info("start %s", seq_start)
-        _module_logger.info("stop  %s", seq_stop)
+        # _module_logger.info("#### Genbank download ####")
+        # _module_logger.info("item  %s", item)
+        # _module_logger.info("start %s", seq_start)
+        # _module_logger.info("stop  %s", seq_stop)
 
-        _module_logger.info("strand  %s", str(strand))
+        # _module_logger.info("strand  %s", str(strand))
 
         _Entrez.email = self.email
         _Entrez.tool = self.tool
 
-        _module_logger.info("Entrez.email  %s", self.email)
+        # _module_logger.info("Entrez.email  %s", self.email)
         text = _Entrez.efetch(
             db="nuccore",
             id=item,
@@ -168,9 +177,11 @@ class Genbank:
             retmode="text",
         ).read()
 
-        _module_logger.info("text[:160]  %s", text[:160])
+        # _module_logger.info("text[:160]  %s", text[:160])
 
-        return _GenbankRecord(_read(text), item=item, start=seq_start, stop=seq_stop, strand=strand)
+        return _GenbankRecord(
+            _read(text), item=item, start=seq_start, stop=seq_stop, strand=strand
+        )
 
 
 def genbank(accession: str = "CS570233.1", *args, **kwargs) -> _GenbankRecord:
@@ -219,18 +230,8 @@ def genbank(accession: str = "CS570233.1", *args, **kwargs) -> _GenbankRecord:
 
     """
     email = _os.getenv("pydna_email")
-    _module_logger.info("#### genbank function called ####")
-    _module_logger.info("email      %s", email)
-    _module_logger.info("accession  %s", email)
+    # _module_logger.info("#### genbank function called ####")
+    # _module_logger.info("email      %s", email)
+    # _module_logger.info("accession  %s", email)
     gb = Genbank(email)
     return gb.nucleotide(accession, *args, **kwargs)
-
-
-if __name__ == "__main__":
-    cached = _os.getenv("pydna_cached_funcs", "")
-    _os.environ["pydna_cached_funcs"] = ""
-    import doctest
-
-    doctest.testmod(verbose=True, optionflags=doctest.ELLIPSIS)
-    _os.environ["pydna_cached_funcs"] = cached
-    pass

pydna/genbankfile.py

@@ -20,11 +20,17 @@ class GenbankFile(_Dseqrecord):
 
     def __repr__(self):
         """returns a short string representation of the object"""
-        return "File({})({}{})".format(self.id, {True: "-", False: "o"}[not self.circular], len(self))
+        return "File({})({}{})".format(
+            self.id, {True: "-", False: "o"}[not self.circular], len(self)
+        )
 
     def _repr_pretty_(self, p, cycle):
         """returns a short string representation of the object"""
-        p.text("File({})({}{})".format(self.id, {True: "-", False: "o"}[not self.circular], len(self)))
+        p.text(
+            "File({})({}{})".format(
+                self.id, {True: "-", False: "o"}[not self.circular], len(self)
+            )
+        )
 
     def _repr_html_(self):
         return "<a href='{path}' target='_blank'>{path}</a><br>".format(path=self.path)
@@ -34,14 +40,3 @@ class GenbankFile(_Dseqrecord):
         return answer
 
     rc = reverse_complement
-
-
-if __name__ == "__main__":
-    import os as _os
-
-    cached = _os.getenv("pydna_cached_funcs", "")
-    _os.environ["pydna_cached_funcs"] = ""
-    import doctest
-
-    doctest.testmod(verbose=True, optionflags=doctest.ELLIPSIS)
-    _os.environ["pydna_cached_funcs"] = cached

pydna/genbankfixer.py

@@ -33,7 +33,9 @@ GoodLocus = (
     + _pp.Word(_pp.nums).setResultsName("size")
     + _pp.Suppress(_pp.CaselessLiteral("bp"))
     + _pp.Word(_pp.alphas + "-").setResultsName("seqtype")
-    + (_pp.CaselessLiteral("linear") | _pp.CaselessLiteral("circular")).setResultsName("topology")
+    + (_pp.CaselessLiteral("linear") | _pp.CaselessLiteral("circular")).setResultsName(
+        "topology"
+    )
     + _pp.Optional(_pp.Word(_pp.alphas), default="   ").setResultsName("divcode")
     + _pp.Regex(r"(\d{2})-(\S{3})-(\d{4})").setResultsName("date")
 )
@@ -44,7 +46,9 @@ BrokenLocus1 = (
     + _pp.Word(_pp.nums).setResultsName("size")
     + _pp.Suppress(_pp.CaselessLiteral("bp"))
     + _pp.Word(_pp.alphas + "-").setResultsName("seqtype")
-    + (_pp.CaselessLiteral("linear") | _pp.CaselessLiteral("circular")).setResultsName("topology")
+    + (_pp.CaselessLiteral("linear") | _pp.CaselessLiteral("circular")).setResultsName(
+        "topology"
+    )
     + _pp.Optional(_pp.Word(_pp.alphas), default="   ").setResultsName("divcode")
     + _pp.Regex(r"(\d{2})-(\S{3})-(\d{4})").setResultsName("date")
 )
@@ -97,7 +101,8 @@ CapWord = _pp.Word("ABCDEFGHIJKLMNOPQRSTUVWXYZ")
 SpacedLine = _pp.White(min=1) + _pp.CharsNotIn("\n") + _pp.LineEnd()
 # HeaderLine = CapWord + CharsNotIn("\n") + LineEnd()
 GenericEntry = _pp.Group(
-    CapWord + _pp.Combine(_pp.CharsNotIn("\n") + _pp.LineEnd() + _pp.ZeroOrMore(SpacedLine))
+    CapWord
+    + _pp.Combine(_pp.CharsNotIn("\n") + _pp.LineEnd() + _pp.ZeroOrMore(SpacedLine))
 ).setResultsName("generics", listAllMatches=True)
 
 
@@ -135,7 +140,9 @@ RPAREN = _pp.Suppress(")")
 SEP = _pp.Suppress(_pp.Literal(".."))
 
 # recognize numbers w. < & > uncertainty specs, then strip the <> chars to make it fixed
-gbIndex = _pp.Word(_pp.nums + "<>").setParseAction(lambda s, l_, t: int(t[0].replace("<", "").replace(">", "")))
+gbIndex = _pp.Word(_pp.nums + "<>").setParseAction(
+    lambda s, l_, t: int(t[0].replace("<", "").replace(">", ""))
+)
 SimpleSlice = _pp.Group(gbIndex + SEP + gbIndex) | _pp.Group(gbIndex).setParseAction(
     lambda s, l_, t: [[t[0][0], t[0][0]]]
 )
@@ -194,12 +201,19 @@ QuoteFeaturekeyval = _pp.Group(
 
 # UnQuoted KeyVal: /key=value  (I'm assuming it doesn't do multilines this way? wrong! ApE does store long labels this way! sigh.)
 # NoQuoteFeaturekeyval = Group(Suppress('/') + Word(alphas+nums+"_-") + Suppress('=') + OneOrMore(CharsNotIn("\n")) )
-keyvalspacedline = _pp.White(exact=21) + _pp.CharsNotIn("/") + _pp.OneOrMore(_pp.CharsNotIn("\n")) + _pp.LineEnd()
+keyvalspacedline = (
+    _pp.White(exact=21)
+    + _pp.CharsNotIn("/")
+    + _pp.OneOrMore(_pp.CharsNotIn("\n"))
+    + _pp.LineEnd()
+)
 NoQuoteFeaturekeyval = _pp.Group(
     _pp.Suppress("/")
     + _pp.Word(_pp.alphas + _pp.nums + "_-")
     + _pp.Suppress("=")
-    + _pp.Combine(_pp.CharsNotIn("\n") + _pp.LineEnd() + _pp.ZeroOrMore(keyvalspacedline))
+    + _pp.Combine(
+        _pp.CharsNotIn("\n") + _pp.LineEnd() + _pp.ZeroOrMore(keyvalspacedline)
+    )
 )
 
 # Special Case for Numerical Vals:  /bases=12  OR  /bases="12"
@@ -213,14 +227,18 @@ NumFeaturekeyval = _pp.Group(
 
 # Key Only KeyVal: /pseudo
 # post-parse convert it into a pair to resemble the structure of the first three cases i.e. [pseudo, True]
-FlagFeaturekeyval = _pp.Group(_pp.Suppress("/") + _pp.Word(_pp.alphas + _pp.nums + "_-")).setParseAction(
-    lambda s, l_, t: [[t[0][0], True]]
-)
+FlagFeaturekeyval = _pp.Group(
+    _pp.Suppress("/") + _pp.Word(_pp.alphas + _pp.nums + "_-")
+).setParseAction(lambda s, l_, t: [[t[0][0], True]])
 
 Feature = _pp.Group(
-    _pp.Word(_pp.alphas + _pp.nums + "_-").setParseAction(lambda s, l_, t: [["type", t[0]]])
+    _pp.Word(_pp.alphas + _pp.nums + "_-").setParseAction(
+        lambda s, l_, t: [["type", t[0]]]
+    )
     + featLocation.setResultsName("location")
-    + _pp.OneOrMore(NumFeaturekeyval | QuoteFeaturekeyval | NoQuoteFeaturekeyval | FlagFeaturekeyval)
+    + _pp.OneOrMore(
+        NumFeaturekeyval | QuoteFeaturekeyval | NoQuoteFeaturekeyval | FlagFeaturekeyval
+    )
 )
 
 FeaturesEntry = (
@@ -234,7 +252,9 @@ FeaturesEntry = (
 
 # sequence is just a column-spaced big table of dna nucleotides
 # should it recognize full IUPAC alphabet?  NCBI uses n for unknown region
-Sequence = _pp.OneOrMore(_pp.Suppress(_pp.Word(_pp.nums)) + _pp.OneOrMore(_pp.Word("ACGTacgtNn")))
+Sequence = _pp.OneOrMore(
+    _pp.Suppress(_pp.Word(_pp.nums)) + _pp.OneOrMore(_pp.Word("ACGTacgtNn"))
+)
 
 # Group(  ) hides the setResultsName names def'd inside, such that one needs to first access this group and then access the dict of contents inside
 SequenceEntry = _pp.Suppress(_pp.Literal("ORIGIN")) + Sequence.setParseAction(
@@ -352,7 +372,9 @@ def wrapstring(str_, rowstart, rowend, padfirst=True):
         if linenum == 0 and not padfirst:
             wrappedstr += str_[linenum * rowlen : (linenum + 1) * rowlen] + "\n"
         else:
-            wrappedstr += " " * leftpad + str_[linenum * rowlen : (linenum + 1) * rowlen] + "\n"
+            wrappedstr += (
+                " " * leftpad + str_[linenum * rowlen : (linenum + 1) * rowlen] + "\n"
+            )
     #    if str_.startswith("/translation="):
     #        print(str_)
     #        print(wrappedstr)
@@ -480,7 +502,9 @@ def toGB(jseq):
                         fstr += wrapstring("/" + str(k) + "=" + str(feat[k]), 21, 80)
                     # standard: wrap val in quotes
                     else:
-                        fstr += wrapstring("/" + str(k) + "=" + '"' + str(feat[k]) + '"', 21, 80)
+                        fstr += wrapstring(
+                            "/" + str(k) + "=" + '"' + str(feat[k]) + '"', 21, 80
+                        )
             featuresstr += fstr
 
     # the spaced, numbered sequence
@@ -511,11 +535,11 @@ def gbtext_clean(gbtext):
     ... //'''
     >>> from pydna.readers import read
     >>> read(s)  # doctest: +SKIP
-    /home/bjorn/anaconda3/envs/bjorn36/lib/python3.6/site-packages/Bio/GenBank/Scanner.py:1388: BiopythonParserWarning: Malformed LOCUS line found - is this correct?
+    ... /site-packages/Bio/GenBank/Scanner.py:1388: BiopythonParserWarning: Malformed LOCUS line found - is this correct?
     :'LOCUS       New_DNA      3 bp    DNA   CIRCULAR SYN        19-JUN-2013\\n'
       "correct?\\n:%r" % line, BiopythonParserWarning)
     Traceback (most recent call last):
-      File "/home/bjorn/python_packages/pydna/pydna/readers.py", line 48, in read
+      File "... /pydna/readers.py", line 48, in read
         results = results.pop()
     IndexError: pop from empty list
     <BLANKLINE>
@@ -523,7 +547,7 @@ def gbtext_clean(gbtext):
     <BLANKLINE>
     Traceback (most recent call last):
       File "<stdin>", line 1, in <module>
-      File "/home/bjorn/python_packages/pydna/pydna/readers.py", line 50, in read
+      File "... /pydna/readers.py", line 50, in read
         raise ValueError("No sequences found in data:\\n({})".format(data[:79]))
     ValueError: No sequences found in data:
     (LOCUS       New_DNA      3 bp    DNA   CIRCULAR SYN        19-JUN-2013
@@ -570,14 +594,3 @@ def gbtext_clean(gbtext):
     Result = _namedtuple("Result", "gbtext jseq")
     result = Result(_pretty_str(toGB(jseq).strip()), jseq)
     return result
-
-
-if __name__ == "__main__":
-    import os as _os
-
-    cached = _os.getenv("pydna_cached_funcs", "")
-    _os.environ["pydna_cached_funcs"] = ""
-    import doctest
-
-    doctest.testmod(verbose=True, optionflags=doctest.ELLIPSIS)
-    _os.environ["pydna_cached_funcs"] = cached

pydna/genbankrecord.py

@@ -11,7 +11,9 @@ import os as _os
 
 
 class GenbankRecord(_Dseqrecord):
-    def __init__(self, record, *args, item="accession", start=None, stop=None, strand=1, **kwargs):
+    def __init__(
+        self, record, *args, item="accession", start=None, stop=None, strand=1, **kwargs
+    ):
         super().__init__(record, *args, **kwargs)
         self.item = item
         self.start = start
@@ -64,7 +66,9 @@ class GenbankRecord(_Dseqrecord):
         return obj
 
     @classmethod
-    def from_SeqRecord(cls, record, *args, item="accession", start=None, stop=None, strand=1, **kwargs):
+    def from_SeqRecord(
+        cls, record, *args, item="accession", start=None, stop=None, strand=1, **kwargs
+    ):
         obj = super().from_SeqRecord(record, *args, **kwargs)
         obj.item = item
         obj.start = start
@@ -95,7 +99,9 @@ class GenbankRecord(_Dseqrecord):
 
     def __repr__(self):
         """returns a short string representation of the object"""
-        return "Gbnk({}{} {})".format({True: "-", False: "o"}[not self.circular], len(self), self._repr)
+        return "Gbnk({}{} {})".format(
+            {True: "-", False: "o"}[not self.circular], len(self), self._repr
+        )
 
     def _repr_pretty_(self, p, cycle):
         """returns a short string representation of the object"""
@@ -121,7 +127,7 @@ class GenbankRecord(_Dseqrecord):
 
         code = (
             "from pydna.genbank import Genbank\n"
-            f"gb = Genbank('{_os.environ['pydna_email']}')\n"
+            f"gb = Genbank('{_os.getenv('pydna_email')}')\n"
             f"seq = gb.nucleotide('{self.item}'"
         )
         if self.start and self.start:
@@ -141,7 +147,7 @@ class GenbankRecord(_Dseqrecord):
 
         code = (
             "from Bio import Entrez, SeqIO\n"
-            f"Entrez.email = '{_os.environ['pydna_email']}'\n"
+            f"Entrez.email = '{_os.getenv('pydna_email')}'\n"
             "handle = Entrez.efetch(db='nuccore',\n"
             f"                       id='{self.item}',\n"
             "                       rettype='gbwithparts',\n"
@@ -160,12 +166,3 @@ class GenbankRecord(_Dseqrecord):
         code += "record = SeqIO.read(handle, 'genbank')"
 
         return _ps(code)
-
-
-if __name__ == "__main__":
-    cached = _os.getenv("pydna_cached_funcs", "")
-    _os.environ["pydna_cached_funcs"] = ""
-    import doctest
-
-    doctest.testmod(verbose=True, optionflags=doctest.ELLIPSIS)
-    _os.environ["pydna_cached_funcs"] = cached

pydna/goldengate.py

@@ -27,9 +27,9 @@ from Bio.Restriction import BsaI, BsmBI, BbsI, FokI
 from pydna.dseqrecord import Dseqrecord as _Dseqrecord
 
 # from copy import deepcopy as _deepcopy
-import logging as _logging
+# import logging as _logging
 
-_module_logger = _logging.getLogger("pydna." + __name__)
+# _module_logger = _logging.getLogger("pydna." + __name__)
 
 BsaI, BsmBI, BbsI, FokI
 

pydna/ladders.py

@@ -19,7 +19,10 @@ a gel image. Exampel can be found in scripts/molecular_weight_standards.ods.
 from pydna.fakeseq import FakeSeq as _FakeSeq
 
 
-PennStateLadder = [_FakeSeq(int(n)) for n in (10000, 7750, 5000, 4000, 3000, 2000, 1500, 1000, 750, 500)]
+PennStateLadder = [
+    _FakeSeq(int(n))
+    for n in (10000, 7750, 5000, 4000, 3000, 2000, 1500, 1000, 750, 500)
+]
 
 
 GeneRuler_1kb = [
@@ -131,13 +134,3 @@ FakeGel = [
     ],
     PennStateLadder,
 ]
-
-if __name__ == "__main__":
-    import os as _os
-
-    cached = _os.getenv("pydna_cached_funcs", "")
-    _os.environ["pydna_cached_funcs"] = ""
-    import doctest
-
-    doctest.testmod(verbose=True, optionflags=doctest.ELLIPSIS)
-    _os.environ["pydna_cached_funcs"] = cached

pydna/ligate.py

@@ -9,9 +9,10 @@ from operator import add
 from functools import reduce
 import networkx as _nx
 from itertools import permutations
-import logging as _logging
 
-_module_logger = _logging.getLogger("pydna." + __name__)
+# import logging as _logging
+
+# _module_logger = _logging.getLogger("pydna." + __name__)
 
 
 def ligate(fragments: list):
@@ -51,18 +52,11 @@ def ligate(fragments: list):
 
     cpaths = [p for p in sorted(_nx.simple_cycles(G), key=len) if len(p) > 1]
     csequences = [reduce(add, x).looped() for x in cpaths]
-    lpaths = [p for p in sorted(_nx.all_simple_paths(G, "begin", "end"), key=len) if len(p) > 3]
+    lpaths = [
+        p
+        for p in sorted(_nx.all_simple_paths(G, "begin", "end"), key=len)
+        if len(p) > 3
+    ]
     lsequences = [reduce(add, lp[1:-1]) for lp in lpaths]
 
     return csequences, lsequences
-
-
-if __name__ == "__main__":
-    import os as _os
-
-    cached = _os.getenv("pydna_cached_funcs", "")
-    _os.environ["pydna_cached_funcs"] = ""
-    import doctest
-
-    doctest.testmod(verbose=True, optionflags=doctest.ELLIPSIS)
-    _os.environ["pydna_cached_funcs"] = cached

pydna/parsers.py

@@ -7,7 +7,7 @@
 
 """Provides two functions, parse and parse_primers"""
 
-import os as _os
+# import os as _os
 import re as _re
 import io as _io
 import textwrap as _textwrap
@@ -40,7 +40,9 @@ except ImportError:
 
 # gb_fasta_embl_regex = r"(?:>.+\n^(?:^[^>]+?)(?=\n\n|>|LOCUS|ID))|(?:(?:LOCUS|ID)(?:(?:.|\n)+?)^//)"
 
-gb_fasta_embl_regex = r"(?:^>.+\n^(?:^[^>]+?)(?=\n\n|>|^LOCUS|^ID))|(?:(?:^LOCUS|^ID)(?:(?:.|\n)+?)^//)"
+gb_fasta_embl_regex = (
+    r"(?:^>.+\n^(?:^[^>]+?)(?=\n\n|>|^LOCUS|^ID))|(?:(?:^LOCUS|^ID)(?:(?:.|\n)+?)^//)"
+)
 
 # The gb_fasta_embl_regex is meant to be able to extract sequences from
 # text where sequences are mixed with other contents as well
@@ -95,7 +97,7 @@ def embl_gb_fasta(text):
             except ValueError:
                 handle.seek(0)
                 try:
-                    parsed = _SeqIO.read(handle, "fasta")
+                    parsed = _SeqIO.read(handle, "fasta-blast")
                 except ValueError:
                     handle.close()
                     continue
@@ -208,10 +210,24 @@ def parse_primers(data):
     return [_Primer(x) for x in parse(data, ds=False)]
 
 
-if __name__ == "__main__":
-    cached = _os.getenv("pydna_cached_funcs", "")
-    _os.environ["pydna_cached_funcs"] = ""
-    import doctest
+def parse_snapgene(file_path: str) -> list[_Dseqrecord]:
+    """Parse a SnapGene file and return a Dseqrecord object.
 
-    doctest.testmod(verbose=True, optionflags=doctest.ELLIPSIS)
-    _os.environ["pydna_cached_funcs"] = cached
+    Parameters
+    ----------
+    file_path : str
+        The path to the SnapGene file to parse.
+
+    Returns
+    -------
+    Dseqrecord
+        The parsed SnapGene file as a Dseqrecord object.
+
+    """
+    with open(file_path, "rb") as f:
+        parsed_seq = next(_SeqIO.parse(f, "snapgene"))
+        circular = (
+            "topology" in parsed_seq.annotations.keys()
+            and parsed_seq.annotations["topology"] == "circular"
+        )
+        return [_Dseqrecord(parsed_seq, circular=circular)]

pydna/primer.py

@@ -14,7 +14,9 @@ from pydna.seqrecord import SeqRecord as _SeqRecord
 class Primer(_SeqRecord):
     """Primer and its position on a template, footprint and tail."""
 
-    def __init__(self, record, *args, amplicon=None, position=None, footprint=0, **kwargs):
+    def __init__(
+        self, record, *args, amplicon=None, position=None, footprint=0, **kwargs
+    ):
         if hasattr(record, "features"):  # Seqrecord
             self.__dict__.update(record.__dict__)
             self.__dict__.update(kwargs)
@@ -57,14 +59,3 @@ class Primer(_SeqRecord):
         answer.position = None
         answer._fp = len(self)
         return answer
-
-
-if __name__ == "__main__":
-    import os as _os
-
-    cached = _os.getenv("pydna_cached_funcs", "")
-    _os.environ["pydna_cached_funcs"] = ""
-    import doctest
-
-    doctest.testmod(verbose=True, optionflags=doctest.ELLIPSIS)
-    _os.environ["pydna_cached_funcs"] = cached

pydna/readers.py

@@ -54,14 +54,3 @@ def read_primer(data):
     The usage is similar to the :func:`parse_primer` function."""
 
     return _Primer(read(data, ds=False))
-
-
-if __name__ == "__main__":
-    import os as _os
-
-    cached = _os.getenv("pydna_cached_funcs", "")
-    _os.environ["pydna_cached_funcs"] = ""
-    import doctest
-
-    doctest.testmod(verbose=True, optionflags=doctest.ELLIPSIS)
-    _os.environ["pydna_cached_funcs"] = cached