syncoder 0.0.1a1__tar.gz → 0.0.2a1__tar.gz

{syncoder-0.0.1a1 → syncoder-0.0.2a1}/.gitignore

@@ -13,5 +13,6 @@ out/
 *.zip
 *.jpg
 *.bin
+.pypirc
 #any actual py files are in src.  anything in root is supposed to just for development.
 /*.py

{syncoder-0.0.1a1 → syncoder-0.0.2a1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: syncoder
-Version: 0.0.1a1
+Version: 0.0.2a1
 Summary: A codec for DNA data storage
 Project-URL: Homepage, https://example.com/TBD
 Project-URL: Issues, https://example.com/TBD/issues
@@ -8,6 +8,9 @@ Author-email: Christopher Takahashi <cnt@uw.edu>
 License-Expression: BSD-3-Clause
 License-File: LICENSE
 Requires-Python: >=3.9
+Requires-Dist: galois>=0.4
+Requires-Dist: numpy>=1.20
+Requires-Dist: reedsolo>=1.7
 Description-Content-Type: text/markdown
 
 # SyNCODER

{syncoder-0.0.1a1 → syncoder-0.0.2a1}/environments/conda_environment.yml

@@ -2,7 +2,7 @@ name: codec-user
 channels:
   - conda-forge 
 dependencies:
-  - python=3.12
+  - python>=3.12
   - numpy=2.*
   - pytest
   - reedsolo=1.7.*

{syncoder-0.0.1a1 → syncoder-0.0.2a1}/environments/conda_environment_dev.yml

@@ -2,7 +2,7 @@ name: codec-dev
 channels:
   - conda-forge 
 dependencies:
-  - python=3.12
+  - python>=3.12
   - numpy=2.*
   - matplotlib=3.*
   - pytest

{syncoder-0.0.1a1 → syncoder-0.0.2a1}/environments/conda_environment_test.yml

@@ -2,7 +2,7 @@ name: codec-test
 channels:
   - conda-forge 
 dependencies:
-  - python=3.12
+  - python>=3.12
   - numpy=2.*
   - pytest
   - reedsolo=1.7.*

{syncoder-0.0.1a1 → syncoder-0.0.2a1}/pyproject.toml

@@ -1,6 +1,11 @@
 [project]
 name = "syncoder"
-version = "0.0.1a1"
+dynamic = ["version"]
+dependencies = [
+    "numpy>=1.20",
+    "galois>=0.4",
+    "reedsolo>=1.7"
+]
 description = "A codec for DNA data storage"
 authors = [
     { name="Christopher Takahashi", email="cnt@uw.edu" }
@@ -24,4 +29,7 @@ build-backend = "hatchling.build"
 [tool.pytest.ini_options]
 testpaths = [
     "tests"
-]
+]
+
+[tool.hatch.version]
+path = "src/syncoder/__init__.py"

{syncoder-0.0.1a1 → syncoder-0.0.2a1}/src/syncoder/__init__.py

@@ -1,4 +1,6 @@
 from .codec import *
 from .codec import _default_b32_alphabet, _default_b32_alphabet_alt
 default_b32_alphabet = _default_b32_alphabet
-default_b32_alphabet_alt = _default_b32_alphabet_alt
+default_b32_alphabet_alt = _default_b32_alphabet_alt
+
+__version__ = "0.0.2a1"

{syncoder-0.0.1a1 → syncoder-0.0.2a1}/src/syncoder/codec.py

@@ -142,6 +142,7 @@ class BaseNBlockCodec:
         #                                        ^ = self.index_bits <-- in bits not bytes.
         #  note: actual k remains alphabet_size-1, but the code is shorted (0 padded) to inner_n symbols. 
         k = inner_n - (inner_d - 1) 
+        self.inner_k = k
         q = self.inner_coder.field.order
 
         #number of bytes needed to store the index
@@ -248,7 +249,7 @@ class BaseNBlockCodec:
             chunk += index<<(self.data_chunk_size*8)
             index += 1
             #but.. we still need to pad out the symbol stream.
-            chunk = _int_to_baseN(chunk,self.inner_coder.field.order,length=self.inner_coder.k)
+            chunk = _int_to_baseN(chunk,self.inner_coder.field.order,length=self.inner_k)  
             chunks.append(chunk)
 
         #apply inner code
@@ -386,7 +387,7 @@ def b32_to_DNA_optimize(file_data:list[ArrayLike],words:list[str], alternate_wor
     mask: list of ints. 0 for word, 1 for alternate word, -1 for don't care.  None for no mask.
     nmasked: number of masked words.  -1 for all.
     penalty_fn: function that takes a DNA sequence and returns a score.  penalty_fn(DNA_seq:str)->int
-  """
+  """      
   if nmasked<0: #mask all
     return [b32_to_DNA_optimize_single(x,words,alternate_words,mask,penalty_fn=penalty_fn) for x in file_data]
   else:
@@ -398,7 +399,6 @@ def b32_to_DNA_optimize(file_data:list[ArrayLike],words:list[str], alternate_wor
 def b32_to_DNA_optimize_single(strand_data:ArrayLike, words:list[str], alternate_words:list[str], mask:Union[ArrayLike,None]=None ,penalty_fn=None)->Tuple[bytes,int]:
   """
     TODO: rename to bN_to_DNA_optimize_single
-    TODO: add mask support.
     strand_data: 1d list of integral types
     mask: list of ints. 0 for word, 1 for alternate word, -1 for don't care.  None for no mask.
   """

{syncoder-0.0.1a1 → syncoder-0.0.2a1}/tests/test_codec_pytest.py

@@ -23,12 +23,14 @@ def test_encode_decode():
 
   out_text = c.decode( coded )[0]
   assert in_text == out_text
+  #check inner_n is causing the correct number of bases
+  assert len(coded[0]) == 30 
 
 def test_coded_to_bases():
   #TODO: test optimize too
 
   test_encoded_data = np.random.randint(0,32,(10,31),dtype=np.uint8)
-  DNA_with_scores = codec.b32_to_DNA_optimize(test_encoded_data,codec._default_b32_alphabet,codec._default_b32_alphabet_alt)
+  DNA_with_scores = codec.b32_to_DNA_optimize(test_encoded_data,codec._default_b32_alphabet,codec._default_b32_alphabet_alt) # type: ignore
   DNA = [x[0] for x in DNA_with_scores]
   test_decoded_data  = codec.dna_to_b32(DNA,codec._default_b32_alphabet,codec._default_b32_alphabet_alt) 
   print(test_encoded_data.flatten())
@@ -99,7 +101,7 @@ def test_inserts():
   data_decodec,__oe,__oer,__ie = coder.decode(enc_d)
   assert data_decodec == inserted_data
 
-  test_dna_out = codec.b32_to_DNA_optimize(enc_d,codec._default_b32_alphabet,codec._default_b32_alphabet_alt,mask=imask,nmasked=n_inserts)
+  test_dna_out = codec.b32_to_DNA_optimize(enc_d,codec._default_b32_alphabet,codec._default_b32_alphabet_alt,mask=imask,nmasked=n_inserts) # type: ignore
   test_dna = [x[0] for x in test_dna_out]
   for strand in test_dna[:n_inserts]:
     assert strand.decode().startswith(insert)