labfreed 0.0.4__py3-none-any.whl → 0.0.5__py3-none-any.whl

labfreed/PAC_CAT/data_model.py

@@ -65,23 +65,23 @@ class Material_Misc(Material_Consumable):
 
 class Data_Result(CATBase):
     category_key: str = Field(default='-DR', frozen=True)
-    id:str =                    Field(              alias='240', min_length=1)
+    id:str =                    Field(              alias='21', min_length=1)
     
 class Data_Method(CATBase):
     category_key: str = Field(default='-DM', frozen=True)
-    id:str =                    Field(              alias='240', min_length=1)
+    id:str =                    Field(              alias='21', min_length=1)
     
 class Data_Calibration(CATBase):
     category_key: str = Field(default='-DC', frozen=True)
-    id:str =                    Field(              alias='240', min_length=1)
+    id:str =                    Field(              alias='21', min_length=1)
     
 class Data_Progress(CATBase):
     category_key: str = Field(default='-DP', frozen=True)
-    id:str =                    Field(              alias='240', min_length=1)
+    id:str =                    Field(              alias='21', min_length=1)
     
 class Data_Static(CATBase):
     category_key: str = Field(default='-DS', frozen=True)
-    id:str =                    Field(              alias='240', min_length=1)
+    id:str =                    Field(              alias='21', min_length=1)
     
     
     

labfreed/PAC_ID/data_model.py

@@ -1,20 +1,90 @@
+import re
 from typing import Optional
 from typing_extensions import Self
-from pydantic import BaseModel, Field, computed_field, conlist, model_validator
+from pydantic import Field, ValidationInfo, computed_field, conlist, model_validator, field_validator
+from ..validation import BaseModelWithWarnings, ValidationWarning, hsegment_pattern, domain_name_pattern
 from abc import ABC, abstractproperty, abstractstaticmethod
+from .well_known_segment_keys import WellKnownSegmentKeys
 
-class IDSegment(BaseModel):
-    key:Optional[str] = Field(None, pattern=r'^[A-Z0-9-+]+$', min_length=1)
-    value:str = Field(..., pattern=r'^[A-Z0-9-+]+$', min_length=1)
 
+class IDSegment(BaseModelWithWarnings):
+    key:str|None = None
+    value:str  
+    @model_validator(mode="after")
+    def validate_segment(cls, model):
+        key = model.key or ""
+        value = model.value 
+        
+        # MUST be a valid hsegment according to RFC 1738, but without * (see PAC-ID Extension)
+        # This means it must be true for both, key and value
+        if not_allowed_chars := set(re.sub(hsegment_pattern, '', key)):
+            raise ValueError(f"id segment key {key} contains invalid characters {' '.join(not_allowed_chars)}.")
+        
+        if not_allowed_chars := set(re.sub(hsegment_pattern, '', value)):
+            raise ValueError(f"id segment key {value} contains invalid characters {' '.join(not_allowed_chars)}.")
 
-class Category(BaseModel):
+        # Segment key SHOULD be limited to A-Z, 0-9, and -+..
+        if not_recommended_chars := set(re.sub(r'[A-Z0-9-:+]', '', key)):
+            model.add_warning(
+                    source=f"id segment key {key}",
+                    type="Recommendation",
+                    msg=f"{' '.join(not_recommended_chars)} should not be used.",
+                    recommendation = "SHOULD be limited to A-Z, 0-9, and -+",
+                    highlight_pattern = key,
+                    highlight_sub = not_recommended_chars
+                )
+            
+        # Segment key should be in Well know keys
+        if key and key not in [k.value for k in WellKnownSegmentKeys]:
+            model.add_warning(
+                    source=f"id segment key {key}",
+                    type="Recommendation",
+                    msg=f"{key} is not a well known segment key.",
+                    recommendation = "RECOMMENDED to be a well-known id segment key.",
+                    highlight_pattern = key
+                )
+            
+            
+        # Segment value SHOULD be limited to A-Z, 0-9, and -+..
+        if not_recommended_chars := set(re.sub(r'[A-Z0-9-:+]', '', value)):
+            model.add_warning(
+                    source=f"id segment value {value}",
+                    type="Recommendation",
+                    msg=f"Characters {' '.join(not_recommended_chars)} should not be used.",
+                    recommendation = "SHOULD be limited to A-Z, 0-9, and -+",
+                    highlight_pattern = value,
+                    highlight_sub = not_recommended_chars
+                )
+            
+        # Segment value SHOULD be limited to A-Z, 0-9, and :-+ for new designs.
+        # this means that ":" in key or value is problematic
+        if ':' in key:
+            model.add_warning(
+                    source=f"id segment key {key}",
+                    type="Recommendation",
+                    msg=f"Character ':' should not be used in segment key, since this character is used to separate key and value this can lead to undefined behaviour.",
+                    highlight_pattern = key
+                )
+        if ':' in value:
+            model.add_warning(
+                    source=f"id segment value {value}",
+                    type="Recommendation",
+                    msg=f"Character ':' should not be used in segment value, since this character is used to separate key and value this can lead to undefined behaviour.",
+                    highlight_pattern = value
+                )
+                
+        return model
+    
+  
+    
+
+class Category(BaseModelWithWarnings):
     key:str|None = None
     segments: list[IDSegment]
 
 
-class Identifier(BaseModel):
-    segments: conlist(IDSegment, min_length=1) = Field(..., exclude=True) # exclude=True prevents this from being serialized by Pydantic
+class Identifier(BaseModelWithWarnings):
+    segments: conlist(IDSegment, min_length=1) = Field(..., exclude=True) # type: ignore # exclude=True prevents this from being serialized by Pydantic
         
     @computed_field
     @property
@@ -45,6 +115,20 @@ class Identifier(BaseModel):
             if duplicate_keys:
                 raise ValueError(f'Duplicate keys {",".join(duplicate_keys)} in category {c.key}')
             return self
+        
+    @model_validator(mode='after')
+    def check_length(self) -> Self:
+        l = 0
+        for s in self.segments:
+            if s.key:
+                l += len(s.key)
+                l += 1 # for ":"
+            l += len(s.value)
+        l += len(self.segments) - 1 # account for "/" separating the segments
+        
+        if l > 256:
+            raise ValueError(f'Identifier is {l} characters long, Identifier must not exceed 256 characters.')
+        return self
        
     @staticmethod 
     def from_categories(categories:list[Category]) :
@@ -57,7 +141,7 @@ class Identifier(BaseModel):
         
     
 
-class Extension(ABC, BaseModel): 
+class Extension(ABC, BaseModelWithWarnings): 
     
     @abstractproperty
     def name(self)->str:
@@ -99,12 +183,29 @@ class UnknownExtension(Extension):
     
 
 
-class PACID(BaseModel):
+class PACID(BaseModelWithWarnings):
     issuer:str
     identifier: Identifier
     
+    @model_validator(mode="after")
+    def validate_issuer(cls, model):
+        if not re.fullmatch(domain_name_pattern, model.issuer):
+            raise ValueError("Issuer must be a valid domain name.")
+
+         
+        # recommendation that A-Z, 0-9, -, and . should be used
+        if not_recommended_chars := set(re.sub(r'[A-Z0-9\.-]', '', model.issuer)):
+            model.add_warning(
+                    source="PAC-ID",
+                    type="Recommendation",
+                    highlight_pattern=model.issuer,
+                    highlight_sub=not_recommended_chars,
+                    msg=f"Characters {' '.join(not_recommended_chars)} should not be used. Issuer SHOULD contain only the characters A-Z, 0-9, -, and . "
+                )
+        return model
+    
     
-class PACID_With_Extensions(BaseModel):
+class PACID_With_Extensions(BaseModelWithWarnings):
     pac_id: PACID
     extensions: list[Extension] = Field(default_factory=list)
 

labfreed/PAC_ID/parse.py

@@ -4,6 +4,8 @@ import re
 from types import MappingProxyType
 from .data_model import *
 
+from ..validation import extract_warnings, ValidationWarning
+
 
 category_conventions = MappingProxyType(
                             {
@@ -29,7 +31,7 @@ class PAC_Parser():
     def __init__(self, extension_interpreters:dict[str, Extension]=None):
         self.extension_interpreters = extension_interpreters or {}
         
-    def parse_pac_url(self, pac_url:str) -> PACID_With_Extensions:
+    def parse_pac_url(self, pac_url:str) -> tuple[PACID_With_Extensions, list[ValidationWarning] ]:
         if '*' in pac_url:
             id_str, ext_str = pac_url.split('*', 1)
         else:
@@ -37,8 +39,12 @@ class PAC_Parser():
             ext_str = ""
             
         pac_id = self.parse_pac_id(id_str)
-        extensions = self.parse_extensions(ext_str)    
-        return PACID_With_Extensions(pac_id=pac_id, extensions=extensions)
+        extensions = self.parse_extensions(ext_str)
+        
+        pac_with_extension = PACID_With_Extensions(pac_id=pac_id, extensions=extensions)
+        warnings = extract_warnings(pac_with_extension)
+        
+        return pac_with_extension, warnings
             
             
     def parse_id_segments(self, identifier:str):
@@ -46,6 +52,8 @@ class PAC_Parser():
             return []    
         
         id_segments = list()  
+        if len(identifier) > 0 and identifier[0] == '/':
+            identifier = identifier[1:]
         for s in identifier.split('/'):
             tmp = s.split(':')
             
@@ -85,10 +93,11 @@ class PAC_Parser():
         default_keys = None
         id_segments = self.parse_id_segments(d.get('identifier'))
         id_segments = self._apply_category_defaults(id_segments)
-            
-        return PACID(issuer= d.get('issuer'),
+        
+        pac = PACID(issuer= d.get('issuer'),
                      identifier=Identifier(segments=id_segments)
         )
+        return pac
 
 
     def parse_extensions(self, extensions_str:str|None) -> list[Extension]:    

labfreed/PAC_ID/serialize.py

@@ -4,7 +4,7 @@ from .data_model import *
     
     
 class PAC_Serializer():    
-    def to_url(self, pac:PACID|PACID_With_Extensions, extensions:list[Extension]=None, use_short_notation_for_extensions=False) -> str:
+    def to_url(self, pac:PACID|PACID_With_Extensions, extensions:list[Extension]=None, use_short_notation_for_extensions=False, uppercase_only=False) -> str:
         if isinstance(pac, PACID_With_Extensions):
             if extensions:
                 raise ValueError('Extensions were given twice, as part of PACID_With_Extension and as method parameter.')
@@ -13,7 +13,10 @@ class PAC_Serializer():
         issuer = pac.issuer
         extensions_str = self._serialize_extensions(extensions, use_short_notation_for_extensions)
         id_segments = self._serialize_id_segments(pac.identifier.segments)
-        return f"HTTPS://PAC.{issuer}{id_segments}{extensions_str}".upper()
+        out = f"HTTPS://PAC.{issuer}{id_segments}{extensions_str}"
+        if uppercase_only:
+            out = out.upper()
+        return out
     
     
     def _serialize_id_segments(self, segments):

labfreed/PAC_ID/well_known_segment_keys.py

@@ -0,0 +1,16 @@
+from enum import Enum
+
+
+class WellKnownSegmentKeys(Enum):
+    GTIN = '01'
+    BATCH = '10'
+    SERIAL = '21'
+    ADDITIONAL_IDINTIFIER = '240'
+    RUN_ID_ABSOLUTE = 'RNR'
+    SAMPLE_ID = 'SMP'
+    EXPERIMENT_ID = 'EXP'
+    RESULT_ID = 'RST'
+    METHOD_ID = 'MTD'
+    REPORT_ID = 'RPT'
+    TIMESTAMP = 'TS'
+    VERSION = 'V'

labfreed/TREXExtension/unit_utilities.py

@@ -60,26 +60,35 @@ class PydanticUncertainQuantity(BaseModel):
     
 unit_map = [
     ('MGM', units.milligram),
+    ('GRM', units.gram),
+    ('KGM', units.kilogram),
+    
     ('CEL', units.celsius),
+    
     ('LTR', units.liter),
     ('MLT', units.milliliter),
-    ('GRM', units.gram),
-    ('KGM', units.kilogram),
+
     ('C34', units.mole),
     ('D43',units.atomic_mass_unit),
+    
     ('1', units.dimensionless),
     ('C62', units.dimensionless),
+    
     ('BAR',units.bar),
     ('MBR',units.millibar),
     ('KBA',units.kilobar),
+    
     ('RPM', units.rpm),
-    ('HUR', units.hour),
+    
     ('HTZ', units.hertz),
     ('KHZ', units.kilohertz),
     ('MHZ',units.megahertz),
+    
     ('SEC', units.second),
     ('MIN', units.minute),
-    ('URH', units.hour)
+    ('HUR', units.hour),
+    
+    ('MTR', units.meter)
     
 ]      
     

labfreed/__init__.py

@@ -2,4 +2,4 @@
 Python implementation of LabFREED building blocks
 '''
 
-__version__ = "0.0.4"
+__version__ = "0.0.5"

labfreed/validation.py

@@ -0,0 +1,71 @@
+from pydantic import BaseModel, Field, PrivateAttr
+from typing import List, Set, Tuple
+
+
+domain_name_pattern = r"(?!-)([A-Za-z0-9-]{1,63}(?<!-)\.)+[A-Za-z]{2,63}"
+hsegment_pattern = r"[A-Za-z0-9_\-\.~!$&'()+,:;=@]|%[0-9A-Fa-f]{2}"
+
+
+class ValidationWarning(BaseModel):
+    source:str 
+    type: str
+    problem_msg:str
+    recommendation_msg: str = ""
+    highlight:str = "" #this can be used to highlight problematic parts
+    highlight_sub:list[str] = Field(default_factory=list())
+    
+    
+
+
+class BaseModelWithWarnings(BaseModel):
+    """ Extension of Pydantic BaseModel, so that validator can issue warnings.
+    The purpose of that is to allow only minimal validation but on top check for stricter recommendations"""
+    _warnings: list[ValidationWarning] = PrivateAttr(default_factory=list)
+
+    def add_warning(self, *, msg: str, type:str, recommendation:str="", source:str="", highlight_pattern="", highlight_sub=None):
+        if not highlight_sub:
+            highlight_sub = []
+        w = ValidationWarning(problem_msg=msg, recommendation_msg=recommendation, source=source, type=type, highlight=highlight_pattern, highlight_sub=highlight_sub)
+        if not w in self._warnings:
+            self._warnings.append(w)
+
+    def get_warnings(self) -> list[ValidationWarning]:
+        return self._warnings
+
+    def clear_warnings(self):
+        self._warnings.clear()
+    
+    
+# Function to extract warnings from a model and its nested models
+def extract_warnings(model: BaseModelWithWarnings, parent_name: str = "", visited: Set[int] = None) -> List[ValidationWarning]:
+    """
+    Recursively extract warnings from a Pydantic model and its nested fields.
+    
+    :param model: The Pydantic model instance to inspect.
+    :param parent_name: The name of the parent model to track the path.
+    :return: List of tuples containing (model name, warning message).
+    """                   
+    if visited is None:
+        visited = set()
+
+    model_id = id(model)
+    if model_id in visited:
+        return []
+    visited.add(model_id)
+    
+    warnings_list = [(parent_name or model.__class__.__name__, model_id,  warning) for warning in model.get_warnings()]
+
+    for field_name, field in model.__fields__.items():
+        full_path = f"{parent_name}.{field_name}" if parent_name else field_name
+        value = getattr(model, field_name)
+
+        if isinstance(value, BaseModelWithWarnings):
+            warnings_list.extend(extract_warnings(value, full_path, visited))
+        elif isinstance(value, list):
+            for index, item in enumerate(value):
+                if isinstance(item, BaseModelWithWarnings):
+                    list_path = f"{full_path}[{index}]"
+                    warnings_list.extend(extract_warnings(item, list_path, visited))
+
+    return warnings_list
+

{labfreed-0.0.4.dist-info → labfreed-0.0.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: labfreed
-Version: 0.0.4
+Version: 0.0.5
 Summary: Python implementation of LabFREED building blocks
 Author-email: Reto Thürer <thuerer.r@buchi.com>
 Requires-Python: >=3.10
@@ -13,3 +13,22 @@ License-File: LICENSE
 # LabFREED for Python
 
 A python implementation of [LabFREED](www.labfreed.com).
+
+
+
+# Examples:
+
+## Parse a PAC ID
+
+
+## Parse a PAC-ID with extensions
+
+
+
+## Create a PAC-ID
+
+## Create a PAC-ID and T-REX for a titration curve
+
+
+
+

labfreed-0.0.5.dist-info/RECORD

@@ -0,0 +1,19 @@
+labfreed/__init__.py,sha256=z3yAWKlMQqYGwnI20F528XNm0hlpE6qhvvfIkhRuSoI,87
+labfreed/validation.py,sha256=dG-SubAguub67RTvw51xlErkqXbzzq_5rwxJwWg6SfY,2869
+labfreed/DisplayNameExtension/DisplayNameExtension.py,sha256=FlT53u1EntpsLmho6GZtgIWBZBNWkl9STxzJBvojR6M,1033
+labfreed/DisplayNameExtension/base36.py,sha256=2lwmEMWm8qrFJkcrP-nMPwS0eCm2THhCJ3Vk-TdGQg0,2455
+labfreed/PAC_CAT/__init__.py,sha256=frcCV1k9oG9oKj3dpUqdJg1PxRT2RSN_XKdLCPjaYaY,2
+labfreed/PAC_CAT/data_model.py,sha256=hob-WNs2-633LmxQ7Ot3RBpcvStYFzdj20QDQZOQyqY,4306
+labfreed/PAC_ID/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+labfreed/PAC_ID/data_model.py,sha256=DKU9Rptl9DcxiUdFf28XMyy4YcGUG7-a1EWuEpIFXVc,7931
+labfreed/PAC_ID/parse.py,sha256=t38ABXZ0siUVDW5oEDmkF7uQ6iSX8Dbkeg-lWNlOgWA,5011
+labfreed/PAC_ID/serialize.py,sha256=0BhF7aXGlLpr312lkBvl1O5fXDFZeLLPgSBddO9Y86Q,1963
+labfreed/PAC_ID/well_known_segment_keys.py,sha256=zrzMvvS42urPpiwinI-IhHPgT3r86zEBl4TlEMOfzbU,338
+labfreed/TREXExtension/data_model.py,sha256=eT4KyQklTO6m-wA28KyJ8wzT8ONhG3fOB3JU6b19ScY,8011
+labfreed/TREXExtension/parse.py,sha256=Y04UK1KlMLG9tE_d7cQOiAJpm8Zh49UoJYjY7Lfqa4Y,1812
+labfreed/TREXExtension/uncertainty.py,sha256=l3WxrLnWTQYfX28gFisXwDcVPvT8bCAd4q6Xl02dRdE,1117
+labfreed/TREXExtension/unit_utilities.py,sha256=WzrC1CZMgBccxADXFP6nLkMWVDqCCkNb3trPyt3BvF8,3826
+labfreed-0.0.5.dist-info/licenses/LICENSE,sha256=gHFOv9FRKHxO8cInP3YXyPoJnuNeqrvcHjaE_wPSsQ8,1100
+labfreed-0.0.5.dist-info/WHEEL,sha256=_2ozNFCLWc93bK4WKHCO-eDUENDlo-dgc9cU3qokYO4,82
+labfreed-0.0.5.dist-info/METADATA,sha256=T_mGIHKlIMASuQnbuW_L4XXqUuxUc0DB6yGOcI-N-wE,594
+labfreed-0.0.5.dist-info/RECORD,,

labfreed-0.0.4.dist-info/RECORD

@@ -1,17 +0,0 @@
-labfreed/__init__.py,sha256=PyF18K_9O9PbwpUrHsMwMVLHyepmCT4UIeVP5iCns90,87
-labfreed/DisplayNameExtension/DisplayNameExtension.py,sha256=FlT53u1EntpsLmho6GZtgIWBZBNWkl9STxzJBvojR6M,1033
-labfreed/DisplayNameExtension/base36.py,sha256=2lwmEMWm8qrFJkcrP-nMPwS0eCm2THhCJ3Vk-TdGQg0,2455
-labfreed/PAC_CAT/__init__.py,sha256=frcCV1k9oG9oKj3dpUqdJg1PxRT2RSN_XKdLCPjaYaY,2
-labfreed/PAC_CAT/data_model.py,sha256=y1cTFZknObi5XOk4aqfgeJv6_G8Rjd9mxTRwNCQR0M4,4311
-labfreed/PAC_ID/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-labfreed/PAC_ID/data_model.py,sha256=oVVqspdZ4B_C4V1rOmcde2_EqWUpDJc6vDUnX4Z1ZPw,3123
-labfreed/PAC_ID/parse.py,sha256=ZmCpuht7o6RgDZCweF7Y0k7QFTd0gLtUpmjFsIlz_wA,4668
-labfreed/PAC_ID/serialize.py,sha256=ujI4SFs-TsFb4FVU2hzwardEWu8-2MYjewE0IyC1yok,1871
-labfreed/TREXExtension/data_model.py,sha256=eT4KyQklTO6m-wA28KyJ8wzT8ONhG3fOB3JU6b19ScY,8011
-labfreed/TREXExtension/parse.py,sha256=Y04UK1KlMLG9tE_d7cQOiAJpm8Zh49UoJYjY7Lfqa4Y,1812
-labfreed/TREXExtension/uncertainty.py,sha256=l3WxrLnWTQYfX28gFisXwDcVPvT8bCAd4q6Xl02dRdE,1117
-labfreed/TREXExtension/unit_utilities.py,sha256=ZhivJnEXMvz7HxLJjI1oJ8y_pcPxW2abKkouiqTo4I4,3775
-labfreed-0.0.4.dist-info/licenses/LICENSE,sha256=gHFOv9FRKHxO8cInP3YXyPoJnuNeqrvcHjaE_wPSsQ8,1100
-labfreed-0.0.4.dist-info/WHEEL,sha256=_2ozNFCLWc93bK4WKHCO-eDUENDlo-dgc9cU3qokYO4,82
-labfreed-0.0.4.dist-info/METADATA,sha256=KKfAscBUcBVVNUSHT3KjlqXjA3_fFd5APom23P_Boh0,446
-labfreed-0.0.4.dist-info/RECORD,,