remove numarray processing to limit scope

Author: majidaldo

README.md

@@ -28,7 +28,9 @@ _:2432178001088 rdf:_2 3.
 
 ## Why?
 
-Motivation: This was developed as part of [BIM2RDF](https://github.com/PNNL/BIM2RDF) where the main implementation language is Python and the data sizes from [Speckle](https://www.speckle.systems/) are not small.
+Motivation: This was developed as part of [BIM2RDF](https://github.com/PNNL/BIM2RDF)
+where the main implementation language is Python
+and the data sizes from [Speckle](https://www.speckle.systems/) are not small.
 
 * [Prior implementation](https://github.com/AtomGraph/JSON2RDF)  is in java.
 * Don't want to use [JSON-LD](https://json-ld.org/playground/)
@@ -52,14 +54,11 @@ This is close to the 'spirit' of the semantic web.
 However, this makes the conversion non-deterministic.
 Reprecussions must be handled by the user.
 
-TODO: list vs arrays.
 
 ## Features
 
 Optional:
-* **'meta triples'** as RDF-star: `<<{data triple}>> {meta} <<{meta triple}>>`
-* **Numerical Arrays**: Numerical lists can be represented as numpy-encoded strings.
-(This was motivated by the storage of geometry data from 3D design programs).
+**'meta triples'**: as RDF-star: `<<{data triple}>> {meta} <<{meta triple}>>`
 
 
 ## Development Philosophy

pyproject.toml

@@ -14,7 +14,6 @@ dependencies = [
 ]
 [project.optional-dependencies]
 cli = ["fire"]
-numarray = ['numpy']
 [dependency-groups]
 dev = [
     'ipython', 'ipdb',
@@ -30,7 +29,6 @@ Repository = "https://github.com/pnnl/json2rdf.git"
 [project.scripts]
 json2rdf = "json2rdf:cli"
 
-
 [build-system]
 # > uv build
 # > uvx hatchling version major

src/json2rdf/__init__.py

@@ -1,3 +1,3 @@
-__version__ = "66" # shoud equal `git rev-list --count master`
+__version__ = "67" # shoud equal `git rev-list --count master`
                    # can roll back to 0 if errors
 from .json2rdf import json2rdf, j2r

src/json2rdf/cli.py

@@ -9,8 +9,6 @@ def _(
         # id interpretation
         subject_id_keys =   args['subject_id_keys'] .default,
         object_id_keys =    args['object_id_keys']  .default,
-        # array
-        array_keys =        args['array_keys']      .default,
         # uri construction
         id_prefix =         args['id_prefix']       .default,
         key_prefix =        args['key_prefix']      .default,
@@ -26,7 +24,6 @@ def _(
             sort=sort,
             subject_id_keys=subject_id_keys,
             object_id_keys=object_id_keys,
-            array_keys=array_keys,
             id_prefix=id_prefix,
             key_prefix=key_prefix,
             meta_prefix=meta_prefix,)

src/json2rdf/json2rdf.py

@@ -9,66 +9,16 @@ def classes():
     # too lazy to convert them to be able to be instantiated.
     class Termination:
         """ 'pre'-processing """
-        class NumList(tuple):
-            def __str__(self, ):
-                return self.data_encode(self)
-            keys = frozenset() #{'array', }
-            
-            @staticmethod
-            def data_encode(d: list) -> str:
-                from numpy import savez_compressed as save, array
-                #from numpy import save
-                _ = d
-                _ = array(d, dtype='float16')
-                from io import BytesIO
-                def sv(d):
-                    _ = BytesIO()
-                    #save(_, d)
-                    save(_, array=d)
-                    return _
-                _ = sv(_)
-                _.seek(0)
-                _ = _.read()
-                from base64 import b64encode
-                _ = b64encode(_)
-                _ = _.decode()
-                return _
-            @staticmethod
-            def data_decode(d: str) -> 'array':
-                _ = d
-                from base64 import b64decode
-                _ = b64decode(_,)
-                from numpy import load
-                from io import BytesIO
-                _ = BytesIO(_)
-                _ = load(_)
-                _ = _['array']
-                return _
-            
-            @staticmethod
-            def allnum(it):
-                #                 dont think json has complex, so doesn't matter
-                return all(isinstance(i, (float, int, complex) ) for i in it)
-            @staticmethod
-            def interpret(it):#  TODO: could interpret a list of whatever if needed
-                raise NotImplementedError
-
         terminals = {
             int, float,
             str,
             bool,
             type(None), # weird
             # does json have datetime?
-            NumList, # don't traverse these if array
             }
         terminals = tuple(terminals)
         @classmethod
         def visit(cls, p, k, v):
-            if k in cls.NumList.keys:
-                # permissively create. don't insist on below conditions.
-                if isinstance(v, list):
-                    if cls.NumList.allnum(v):
-                        return k, cls.NumList(v)
             return True
 
         @classmethod
@@ -301,8 +251,6 @@ def triple(cls, s, p, o):
                 o = '"'+o+'"'
             elif isinstance(o, (bool, NoneType)): # https://github.com/w3c/json-ld-syntax/issues/258
                 o = m[o]
-            elif isinstance(o, Termination.NumList):
-                o = '"'+str(o)+'"'
             elif isinstance(o, Identification.ID):
                 if type(o) is Identification.ID:
                     o = f'{cls.list.id_prefix}:{o}'
@@ -363,8 +311,6 @@ def json2rdf(
         # id interpretation
         subject_id_keys =   defaults.Identification.subject_keys,
         object_id_keys =    defaults.Identification.object_keys,
-        # array
-        array_keys =         {},#Termination.NumList.keys,
         # # uri construction
         id_prefix =         (defaults.RDFing.list.id_prefix,
                              defaults.RDFing.list.id_uri),
@@ -396,8 +342,6 @@ def json2rdf(
     f.Identification.subject_keys = [k for k in subject_id_keys if k in frozenset(subject_id_keys)]
     f.Identification.object_keys = frozenset(object_id_keys)
 
-    f.Termination.NumList.keys = frozenset(array_keys)
-
     f.RDFing.list.id_prefix,      f.RDFing.list.id_uri =    id_prefix
     f.RDFing.list.key_prefix,     f.RDFing.list.key_uri =   key_prefix
     f.RDFing.list.meta_prefix,    f.RDFing.list.meta_uri =  meta_prefix

test/test.py

@@ -36,3 +36,4 @@ def check_fn(obtained_fn, expected_fn):
         if not is_eq(o, e): raise AssertionError
     file_regression.check(r, check_fn=check_fn, extension='.ttl')
 
+# json2rdf -i large-file.json -o data.ttl