semantic-transformers 0.1.0__py3-none-any.whl

semantic_transformers/__init__.py

@@ -0,0 +1,23 @@
+"""
+semantic-transformers
+=====================
+Converters and machine-file parsers for semantic schema pipelines.
+
+Public API
+----------
+    ParseResult:     normalised parser output (simplified_json + DataFrame)
+    Parser:          protocol that all parsers must satisfy
+    Transformer:     runs parsing → JSONata transform → RDF
+    TransformResult: everything produced by Transformer.run()
+    QuickMapper:     turns any tabular file into RDF with a simple YAML mapping
+"""
+
+from .parser import Parser, ParseResult
+from .transformer import Transformer, TransformResult
+from .quick_mapper import QuickMapper
+
+__all__ = [
+    "Parser", "ParseResult",
+    "Transformer", "TransformResult",
+    "QuickMapper",
+]

semantic_transformers/parser.py

@@ -0,0 +1,83 @@
+"""
+Parser protocol and result type.
+
+A Parser reads a machine file (any format, any internal structure) and
+returns a ParseResult with two outputs:
+
+  simplified_json:  a plain dict matching the target schema's example.input.json
+                    format, ready to be fed into the JSONata transform.
+
+  timeseries:       a pandas DataFrame of the raw measurement columns, or None
+                    if the file contains no time-series data.
+
+  column_iris:      maps each DataFrame column name to an ontology class IRI.
+                    Only the descriptor goes into the knowledge graph; the
+                    numeric values stay in the DataFrame.
+
+  column_units:     maps each DataFrame column name to a QUDT unit IRI.
+
+Parsers are schema- and machine-specific: one parser per (machine model,
+schema) combination.  They live in the parsers/ directory alongside the
+schema they serve, not in this library.
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Protocol, runtime_checkable
+
+import pandas as pd
+
+
+@dataclass
+class ParseResult:
+    """Normalised output produced by any Parser."""
+
+    # Flat dict matching the target schema's example.input.json.
+    # Feed this directly into the JSONata transform.
+    simplified_json: dict
+
+    # Raw time-series data.  None when the file has no tabular measurements.
+    timeseries: pd.DataFrame | None = None
+
+    # Column name → ontology class IRI (e.g. "https://w3id.org/pmd/tto/TestTime")
+    column_iris: dict[str, str] = field(default_factory=dict)
+
+    # Column name → QUDT unit IRI (e.g. "http://qudt.org/vocab/unit/SEC")
+    column_units: dict[str, str] = field(default_factory=dict)
+
+
+@runtime_checkable
+class Parser(Protocol):
+    """Any callable object that reads a file and returns a ParseResult."""
+
+    def parse(self, path: Path) -> ParseResult: ...
+
+
+class SchemaAwareParser:
+    """
+    Optional mixin for parsers that can use the input schema for type coercion.
+
+    Implement this alongside the Parser protocol when your parser needs to cast
+    field values to the types declared in ``schema.simplified.json``.
+    ``Transformer`` calls ``configure(schema)`` automatically after construction
+    whenever an ``input_schema`` is available, so the user never needs to pass
+    the schema path to the parser directly.
+
+    Example
+    -------
+    class MyParser(SchemaAwareParser):
+        def configure(self, schema: dict) -> None:
+            self._field_types = {
+                name: prop.get("type", "string")
+                for name, prop in schema.get("properties", {}).items()
+            }
+
+        def parse(self, path: Path) -> ParseResult:
+            ...
+    """
+
+    def configure(self, schema: dict) -> None:
+        """Receive the loaded input schema dict from Transformer."""
+        ...

semantic_transformers/quick_mapper.py

@@ -0,0 +1,255 @@
+"""
+QuickMapper: turn any tabular file into RDF with a simple mapping config.
+
+No schema, no JSONata transform, no custom parser required.  The user
+provides a YAML config that names the columns and points each one at an
+ontology class IRI and an optional QUDT unit.  Everything else is automatic.
+
+Supported file formats
+----------------------
+    .csv                   Comma-separated values
+    .tsv  /  .tab          Tab-separated values
+    .txt                   Auto-sniffed (separator detected from content)
+    .xlsx  /  .xls         Excel workbook (requires openpyxl)
+    .parquet               Apache Parquet (requires pyarrow or fastparquet)
+    .json                  JSON (array of records or any orient supported by pandas)
+
+Mapping config format
+---------------------
+    # root_type is optional (defaults to dcat:Dataset)
+    root_type: "http://www.w3.org/ns/dcat#Dataset"
+
+    # label is optional (defaults to the file stem)
+    label: "Hardness profile, sample 42"
+
+    # file reading options (all optional)
+    file:
+      format:    auto       # auto | csv | tsv | excel | parquet | json
+      separator: ","        # csv/tsv only; sniffed when omitted
+      skip_rows: 0          # rows to skip before the header row
+      header_row: 0         # which row (after skipping) contains column names
+      encoding:  utf-8
+      sheet:     0          # Excel only: sheet name or 0-based index
+
+    # column annotations (only annotated columns get ontology triples)
+    columns:
+      Force:
+        iri:  "https://w3id.org/pmd/tto/StandardForce"
+        unit: "http://qudt.org/vocab/unit/N"        # optional
+      Temperature:
+        iri:  "https://example.org/vocab/Temperature"
+
+Usage
+-----
+    from semantic_transformers import QuickMapper
+
+    mapper = QuickMapper("mapping.yaml")
+    result = mapper.run("my_data.xlsx")
+
+    print(result.graph.serialize(format="turtle"))
+    print(result.dataframe.head())
+"""
+
+from __future__ import annotations
+
+import csv as _csv
+import io
+from pathlib import Path
+from typing import Union
+
+import rdflib
+import yaml
+
+from .transformer import TransformResult
+
+# ---------------------------------------------------------------------------
+# Namespaces
+# ---------------------------------------------------------------------------
+_DCAT  = rdflib.Namespace("http://www.w3.org/ns/dcat#")
+_DCT   = rdflib.Namespace("http://purl.org/dc/terms/")
+_QUDT  = rdflib.Namespace("http://qudt.org/schema/qudt/")
+_RDFS  = rdflib.RDFS
+_RDF   = rdflib.RDF
+_XSD   = rdflib.XSD
+
+_DEFAULT_ROOT_TYPE = "http://www.w3.org/ns/dcat#Dataset"
+_DEFAULT_BASE      = "https://example.org/datasets/"
+
+
+class QuickMapper:
+    """
+    Converts any tabular file into an RDF graph using a lightweight YAML
+    mapping config.  Returns a :class:`ConversionResult` so it is a drop-in
+    companion to :class:`Converter`.
+
+    Parameters
+    ----------
+    mapping:
+        Path to a YAML mapping file, or a plain dict with the same structure.
+    """
+
+    def __init__(self, mapping: Union[str, Path, dict]) -> None:
+        if isinstance(mapping, dict):
+            self._config: dict = mapping
+        else:
+            self._config = yaml.safe_load(
+                Path(mapping).read_text(encoding="utf-8")
+            )
+
+    # ------------------------------------------------------------------
+    def run(self, file_path: Union[str, Path], **overrides) -> TransformResult:
+        """
+        Convert *file_path* to RDF.
+
+        Keyword arguments override the corresponding top-level keys in the
+        mapping config (e.g. ``label="Custom name"``).
+
+        Returns
+        -------
+        TransformResult
+            Same type as :meth:`Transformer.run`: graph, oold_doc, dataframe,
+            column_iris, column_units.
+        """
+        path   = Path(file_path)
+        config = {**self._config, **overrides}
+
+        # ── 1. Read the file into a DataFrame ────────────────────────
+        df = self._read_file(path, config.get("file", {}))
+
+        # ── 2. Collect column annotations ────────────────────────────
+        columns_cfg  = config.get("columns", {})
+        column_iris  = {
+            col: cfg["iri"]
+            for col, cfg in columns_cfg.items()
+            if "iri" in cfg
+        }
+        column_units = {
+            col: cfg["unit"]
+            for col, cfg in columns_cfg.items()
+            if "unit" in cfg
+        }
+
+        # ── 3. Build the RDF graph ────────────────────────────────────
+        root_type  = config.get("root_type", _DEFAULT_ROOT_TYPE)
+        label      = config.get("label", path.stem)
+        base       = config.get("base", _DEFAULT_BASE)
+        dataset_id = rdflib.URIRef(base + path.stem)
+
+        g = rdflib.Dataset()
+        ctx = g.default_graph
+
+        ctx.add((dataset_id, _RDF.type,   rdflib.URIRef(root_type)))
+        ctx.add((dataset_id, _RDFS.label, rdflib.Literal(label)))
+        ctx.add((dataset_id, _DCT.title,  rdflib.Literal(label)))
+        ctx.add((dataset_id, _DCT.source, rdflib.Literal(str(path.name))))
+
+        for col_name, col_iri in column_iris.items():
+            safe    = col_name.replace(" ", "_")
+            col_uri = rdflib.URIRef(str(dataset_id) + "/" + safe)
+
+            ctx.add((dataset_id, _DCAT.distribution, col_uri))
+            ctx.add((col_uri,    _RDF.type,           rdflib.URIRef(col_iri)))
+            ctx.add((col_uri,    _RDFS.label,         rdflib.Literal(col_name)))
+
+            unit_iri = column_units.get(col_name)
+            if unit_iri:
+                ctx.add((col_uri, _QUDT.hasUnit, rdflib.URIRef(unit_iri)))
+
+        # ── 4. Build a lightweight summary doc ───────────────────────
+        oold_doc = {
+            "id":         str(dataset_id),
+            "type":       root_type,
+            "label":      label,
+            "source":     str(path.name),
+            "columns":    {
+                col: {"iri": iri, **({"unit": column_units[col]} if col in column_units else {})}
+                for col, iri in column_iris.items()
+            },
+        }
+
+        return TransformResult(
+            graph        = g,
+            oold_doc     = oold_doc,
+            dataframe    = df,
+            column_iris  = column_iris,
+            column_units = column_units,
+        )
+
+    # ------------------------------------------------------------------
+    # Private helpers
+    # ------------------------------------------------------------------
+
+    def _read_file(self, path: Path, file_cfg: dict):
+        """Read *path* into a pandas DataFrame using *file_cfg* hints."""
+        import pandas as pd
+
+        fmt = file_cfg.get("format", "auto")
+        if fmt == "auto":
+            fmt = _detect_format(path)
+
+        skip   = file_cfg.get("skip_rows",  0)
+        header = file_cfg.get("header_row", 0)
+        enc    = file_cfg.get("encoding",   "utf-8")
+
+        if fmt in ("csv", "tsv", "txt"):
+            sep = file_cfg.get("separator")
+            if sep is None:
+                sep = _sniff_separator(path, enc)
+            return pd.read_csv(
+                path,
+                sep       = sep,
+                skiprows  = skip,
+                header    = header,
+                encoding  = enc,
+            )
+
+        if fmt == "excel":
+            sheet = file_cfg.get("sheet", 0)
+            return pd.read_excel(
+                path,
+                sheet_name = sheet,
+                skiprows   = skip,
+                header     = header,
+            )
+
+        if fmt == "parquet":
+            return pd.read_parquet(path)
+
+        if fmt == "json":
+            orient = file_cfg.get("orient", None)
+            return pd.read_json(path, orient=orient)
+
+        raise ValueError(
+            f"Unsupported format '{fmt}'. "
+            "Supported: csv, tsv, txt, excel, parquet, json."
+        )
+
+
+# ---------------------------------------------------------------------------
+# Module-level helpers
+# ---------------------------------------------------------------------------
+
+def _detect_format(path: Path) -> str:
+    suffix = path.suffix.lower()
+    mapping = {
+        ".csv":     "csv",
+        ".tsv":     "tsv",
+        ".tab":     "tsv",
+        ".txt":     "txt",
+        ".xlsx":    "excel",
+        ".xls":     "excel",
+        ".xlsm":    "excel",
+        ".parquet": "parquet",
+        ".json":    "json",
+    }
+    return mapping.get(suffix, "csv")
+
+
+def _sniff_separator(path: Path, encoding: str) -> str:
+    """Read the first 4 KB and ask csv.Sniffer to detect the delimiter."""
+    try:
+        sample = path.read_bytes()[:4096].decode(encoding, errors="replace")
+        dialect = _csv.Sniffer().sniff(sample, delimiters=",;\t|")
+        return dialect.delimiter
+    except _csv.Error:
+        return ","  # safe fallback

semantic_transformers/transformer.py

@@ -0,0 +1,353 @@
+"""
+Transformer: parser output → OO-LD → RDF + DataFrame.
+
+Usage: shorthand (recommended)
+--------------------------------
+    from semantic_transformers import Transformer
+    from zwick_parser import ZwickParser
+
+    # Pass the schema folder; all three file paths are derived automatically.
+    # Works with a local path or a GitHub tree URL:
+    transformer = Transformer(
+        parser           = ZwickParser(),
+        semantic_schema  = "https://github.com/org/semantic-schemas/tree/main/schemas/domain/Ontology/",
+    )
+
+    # Or for a locally cloned schema repository:
+    transformer = Transformer(
+        parser           = ZwickParser(),
+        semantic_schema  = Path("../semantic-schemas/schemas/domain/Ontology/"),
+    )
+
+Usage: explicit paths (full control / non-standard layouts)
+-------------------------------------------------------------
+    transformer = Transformer(
+        parser       = ZwickParser(),
+        jsonata      = "specs/transform.simplified.jsonata",
+        oold_schema  = "specs/schema.oold.yaml",
+        input_schema = "specs/schema.simplified.json",  # optional
+    )
+
+    result = transformer.run("my_file.csv")
+    print(result.graph.serialize(format="turtle"))
+    print(result.dataframe)
+"""
+
+from __future__ import annotations
+
+import json
+import re
+import urllib.request
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Optional
+
+import jsonschema
+import rdflib
+import yaml
+from jsonata.jsonata import Jsonata
+
+from .parser import Parser, ParseResult, SchemaAwareParser
+
+# Namespaces used when generating timeseries descriptor triples.
+_DCAT   = rdflib.Namespace("http://www.w3.org/ns/dcat#")
+_QUDT   = rdflib.Namespace("http://qudt.org/schema/qudt/")
+_OBI    = rdflib.Namespace("http://purl.obolibrary.org/obo/OBI_")
+_RDFS   = rdflib.RDFS
+_RDF    = rdflib.RDF
+
+# Standard file paths relative to a schema folder root.
+_JSONATA_REL     = "specs/transform.simplified.jsonata"
+_OOLD_SCHEMA_REL = "specs/schema.oold.yaml"
+_INPUT_SCHEMA_REL = "specs/schema.simplified.json"
+
+
+def _read_text(source: str | Path) -> str:
+    """Read text from a local file path or an HTTP(S) URL."""
+    s = str(source)
+    if s.startswith("http://") or s.startswith("https://"):
+        with urllib.request.urlopen(s) as resp:
+            return resp.read().decode("utf-8")
+    return Path(source).read_text(encoding="utf-8")
+
+
+def _github_tree_to_raw(url: str) -> str:
+    """
+    Convert a GitHub ``tree/`` URL to a raw.githubusercontent.com base URL.
+
+    Example
+    -------
+    https://github.com/org/repo/tree/main/schemas/domain/Ontology/
+    → https://raw.githubusercontent.com/org/repo/main/schemas/domain/Ontology
+    """
+    url = url.rstrip("/")
+    url = url.replace("https://github.com/", "https://raw.githubusercontent.com/", 1)
+    url = re.sub(r"/tree/", "/", url, count=1)
+    return url
+
+
+def _resolve_semantic_schema(
+    semantic_schema: str | Path,
+) -> tuple[str | Path, str | Path, str | Path]:
+    """
+    Derive the three schema file locations from a folder root.
+
+    Accepts either a local ``Path`` or a GitHub ``tree/`` URL string.
+    Returns (jsonata, oold_schema, input_schema) as paths or URL strings.
+    """
+    s = str(semantic_schema)
+    if s.startswith("http://") or s.startswith("https://"):
+        base = _github_tree_to_raw(s)
+        return (
+            base + "/" + _JSONATA_REL,
+            base + "/" + _OOLD_SCHEMA_REL,
+            base + "/" + _INPUT_SCHEMA_REL,
+        )
+    p = Path(semantic_schema)
+    return (
+        p / _JSONATA_REL,
+        p / _OOLD_SCHEMA_REL,
+        p / _INPUT_SCHEMA_REL,
+    )
+
+
+@dataclass
+class TransformResult:
+    """Everything produced by a single Transformer run."""
+
+    # RDF graph containing the semantic metadata and timeseries descriptors.
+    graph: rdflib.Dataset
+
+    # The intermediate OO-LD document (after the JSONata transform, before RDF).
+    oold_doc: dict
+
+    # Raw measurement data.  None when the file had no tabular section.
+    dataframe: object  # pd.DataFrame | None (avoid importing pandas at module level)
+
+    # Column name → ontology class IRI (same as ParseResult.column_iris).
+    column_iris: dict[str, str]
+
+    # Column name → QUDT unit IRI (same as ParseResult.column_units).
+    column_units: dict[str, str]
+
+
+class Transformer:
+    """
+    Connects a machine-specific Parser to an OO-LD schema, producing an RDF
+    graph and a pandas DataFrame in one call.
+
+    Parameters
+    ----------
+    parser:
+        Any object implementing the Parser protocol.
+
+    semantic_schema:
+        Shorthand: the root folder of the schema, either a local ``Path``
+        or a GitHub ``tree/`` URL.  Derives all three file paths using the
+        standard schema folder layout.  Any explicitly provided ``jsonata``,
+        ``oold_schema``, or ``input_schema`` value takes precedence over the
+        derived path.
+
+    jsonata:
+        Path or URL to the schema's ``specs/transform.simplified.jsonata`` file.
+
+    oold_schema:
+        Path or URL to the schema's ``specs/schema.oold.yaml`` file (contains
+        the JSON-LD ``@context`` used to convert OO-LD output to RDF).
+
+    input_schema:
+        Optional path or URL to the schema's ``specs/schema.simplified.json``
+        file.  When provided, the parser's output (after caller overrides) is
+        validated for type correctness before being passed to the JSONata
+        transform.  Catches field-name mismatches between a parser and its
+        target schema early.  Required-field completeness is intentionally not
+        enforced here; SHACL validation handles that downstream.
+
+    Examples
+    --------
+    Shorthand with a GitHub URL (no local clone needed)::
+
+        transformer = Transformer(
+            parser          = ZwickParser(),
+            semantic_schema = "https://github.com/org/semantic-schemas/tree/main/schemas/domain/Ontology/",
+        )
+
+    Shorthand with a local path::
+
+        transformer = Transformer(
+            parser          = ZwickParser(),
+            semantic_schema = Path("../semantic-schemas/schemas/domain/Ontology/"),
+        )
+
+    Explicit paths (non-standard layout, or to override one file)::
+
+        transformer = Transformer(
+            parser       = ZwickParser(),
+            jsonata      = "specs/transform.simplified.jsonata",
+            oold_schema  = "specs/schema.oold.yaml",
+            input_schema = "specs/schema.simplified.json",
+        )
+    """
+
+    def __init__(
+        self,
+        parser: Parser,
+        jsonata: Optional[str | Path] = None,
+        oold_schema: Optional[str | Path] = None,
+        input_schema: Optional[str | Path] = None,
+        *,
+        semantic_schema: Optional[str | Path] = None,
+    ) -> None:
+        self.parser = parser
+
+        # Resolve shorthand, then let explicit values override.
+        if semantic_schema is not None:
+            derived_jsonata, derived_oold, derived_input = _resolve_semantic_schema(semantic_schema)
+            jsonata      = jsonata      or derived_jsonata
+            oold_schema  = oold_schema  or derived_oold
+            input_schema = input_schema or derived_input
+
+        if jsonata is None:
+            raise ValueError(
+                "Provide either 'semantic_schema' (shorthand) or 'jsonata' explicitly."
+            )
+        if oold_schema is None:
+            raise ValueError(
+                "Provide either 'semantic_schema' (shorthand) or 'oold_schema' explicitly."
+            )
+
+        self._transform_src = _read_text(jsonata)
+        raw = yaml.safe_load(_read_text(oold_schema))
+        self._context = raw["@context"]
+        self._base    = self._context.get("@base", "")
+
+        self._input_schema: dict | None = (
+            json.loads(_read_text(input_schema))
+            if input_schema is not None
+            else None
+        )
+
+        # Share the loaded schema with the parser if it supports it.
+        if self._input_schema is not None and isinstance(parser, SchemaAwareParser):
+            parser.configure(self._input_schema)
+
+    # ------------------------------------------------------------------
+    def run(self, file_path: str | Path, **overrides) -> TransformResult:
+        """
+        Process *file_path* end-to-end.
+
+        Any keyword arguments (e.g. ``test_name``, ``specimen_iri``) are
+        merged into the parsed simplified JSON, overriding whatever the
+        parser produced.  Use this to supply values that cannot be read
+        from the file itself.
+
+        Returns
+        -------
+        TransformResult
+        """
+        parsed = self.parser.parse(Path(file_path))
+
+        # Merge: parser output first, then caller overrides.
+        simplified = {**parsed.simplified_json, **overrides}
+
+        # ── Validate against input schema (if provided) ───────────────
+        # Strip 'required' before validating: fields that cannot be parsed
+        # from the file (e.g. specimen_iri, which must be supplied by the
+        # caller) are legitimately absent here.  The goal is to catch type
+        # mismatches and unknown field names, not to enforce completeness —
+        # SHACL validation downstream will flag any missing required triples.
+        if self._input_schema is not None:
+            schema_for_validation = {**self._input_schema, "required": []}
+            jsonschema.validate(instance=simplified, schema=schema_for_validation)
+
+        # ── JSONata transform ──────────────────────────────────────────
+        oold_doc = Jsonata(self._transform_src).evaluate(simplified)
+
+        # ── OO-LD → RDF ───────────────────────────────────────────────
+        g = rdflib.Dataset()
+        g.parse(
+            data   = json.dumps({"@context": self._context, **oold_doc}),
+            format = "json-ld",
+        )
+
+        # ── Timeseries descriptor triples ─────────────────────────────
+        if parsed.timeseries is not None and parsed.column_iris:
+            test_iri = self._resolve_test_iri(g, oold_doc)
+            if test_iri:
+                self._add_timeseries_nodes(g, test_iri, parsed)
+
+        return TransformResult(
+            graph        = g,
+            oold_doc     = oold_doc,
+            dataframe    = parsed.timeseries,
+            column_iris  = parsed.column_iris,
+            column_units = parsed.column_units,
+        )
+
+    # ------------------------------------------------------------------
+    # Internal helpers
+    # ------------------------------------------------------------------
+
+    def _resolve_test_iri(self, g: rdflib.Dataset, oold_doc: dict) -> rdflib.URIRef | None:
+        """
+        Find the root test node's IRI in the parsed graph.
+
+        We look it up rather than constructing it from ``@base + id`` because
+        JSON-LD follows RFC 3986 which strips any fragment from the base URI
+        before resolving relative references.  Naive string concatenation would
+        therefore produce the wrong IRI when the schema context uses a
+        ``@base`` that ends with ``#``.
+        """
+        test_id = oold_doc.get("id", "")
+        if not test_id:
+            return None
+        if test_id.startswith("http"):
+            return rdflib.URIRef(test_id)
+        for s, _p, _o, _c in g.quads():
+            if isinstance(s, rdflib.URIRef) and str(s).endswith(test_id):
+                return s
+        return None
+
+    def _add_timeseries_nodes(
+        self,
+        g: rdflib.Dataset,
+        test_iri: rdflib.URIRef,
+        parsed: ParseResult,
+    ) -> None:
+        """
+        Add a dcat:Dataset node for the time series and one descriptor node
+        per column.  Only IRIs and units go into the graph (not the values).
+
+        Graph pattern added
+        -------------------
+            <test_iri>  obi:has_specified_output  <test_iri/timeseries> .
+
+            <test_iri/timeseries>
+                a               dcat:Dataset ;
+                rdfs:label      "Raw time series" ;
+                dcat:distribution  <test_iri/timeseries/ColumnName>, ... .
+
+            <test_iri/timeseries/ColumnName>
+                a               <column_class_iri> ;
+                rdfs:label      "ColumnName" ;
+                qudt:hasUnit    <unit_iri> .
+        """
+        ctx = g.default_graph
+
+        ds_iri = rdflib.URIRef(str(test_iri) + "/timeseries")
+
+        ctx.add((test_iri, _OBI["0000299"], ds_iri))   # has_specified_output
+        ctx.add((ds_iri, _RDF.type,   _DCAT.Dataset))
+        ctx.add((ds_iri, _RDFS.label, rdflib.Literal("Raw time series")))
+
+        for col_name, col_class in parsed.column_iris.items():
+            safe    = col_name.replace(" ", "_")
+            col_uri = rdflib.URIRef(str(ds_iri) + "/" + safe)
+
+            ctx.add((ds_iri,    _DCAT.distribution, col_uri))
+            ctx.add((col_uri,   _RDF.type,          rdflib.URIRef(col_class)))
+            ctx.add((col_uri,   _RDFS.label,        rdflib.Literal(col_name)))
+
+            unit_iri = parsed.column_units.get(col_name)
+            if unit_iri:
+                ctx.add((col_uri, _QUDT.hasUnit, rdflib.URIRef(unit_iri)))

semantic_transformers-0.1.0.dist-info/METADATA

@@ -0,0 +1,189 @@
+Metadata-Version: 2.4
+Name: semantic-transformers
+Version: 0.1.0
+Summary: Machine-file extractors and transformers for semantic schema pipelines
+Author: Semantic Dataspace contributors
+License: MIT
+Project-URL: Homepage, https://github.com/Semantic-Dataspace/semantic-transformers
+Project-URL: Repository, https://github.com/Semantic-Dataspace/semantic-transformers
+Project-URL: Bug Tracker, https://github.com/Semantic-Dataspace/semantic-transformers/issues
+Keywords: materials science,ontology,linked data,rdf,etl,parsers
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas
+Requires-Dist: rdflib
+Requires-Dist: pyyaml
+Requires-Dist: jsonata-python
+Requires-Dist: jsonschema
+Provides-Extra: excel
+Requires-Dist: openpyxl; extra == "excel"
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: nbmake; extra == "dev"
+Dynamic: license-file
+
+# semantic-transformers
+
+A library and a curated collection of parsers that bridge raw instrument output
+files and the [semantic-schemas](../semantic-schemas/) knowledge graph pipeline.
+
+## What this repository contains
+
+```text
+semantic-transformers/
+  src/semantic_transformers/   Python library (Transformer, QuickMapper, …)
+  parsers/                     Machine-specific file parsers
+    <domain>/                  Mirrors the semantic-schemas folder structure
+      <specialisation>/
+        <machine>/             One folder per instrument model
+          <machine>_parser.py  Reads the instrument file
+          column_mapping.json  Maps column names to ontology class IRIs and units
+          README.md            Quick-start, schema compatibility, and known limitations
+  docs/                        Guides for users and contributors
+```
+
+## The two parts
+
+### 1. The library (`src/semantic_transformers/`)
+
+| Class | Role |
+|---|---|
+| `Parser` | Protocol to implement when adding support for a new instrument |
+| `ParseResult` | What every parser returns: simplified JSON + DataFrame |
+| `Transformer` | Runs parsing → JSONata transform → RDF graph |
+| `TransformResult` | What `Transformer.run()` returns: RDF graph + DataFrame |
+| `QuickMapper` | Turns any tabular file into RDF using a simple YAML mapping (no parser needed) |
+
+### 2. The parsers (`parsers/`)
+
+Each parser targets a specific instrument model. The folder path mirrors the
+`schemas/` tree in `semantic-schemas`:
+
+| Schema | Instrument | Parser path |
+|---|---|---|
+| `characterization/tensile-test/TTO` | Zwick/Roell (testXpert III) | `parsers/characterization/tensile-test/zwick/` |
+
+## Installation
+
+### Using pip (recommended)
+
+```bash
+# Install the transformers library
+pip install semantic-transformers
+
+# Optional: install optional dependencies
+pip install semantic-transformers[excel]  # for Excel file support
+pip install semantic-transformers[dev]    # for development and testing
+```
+
+### Development installation
+
+Both repositories are designed to be cloned as siblings under a shared folder:
+
+```bash
+mkdir semantic-dataspace && cd semantic-dataspace
+
+git clone https://github.com/Semantic-Dataspace/semantic-schemas
+git clone https://github.com/Semantic-Dataspace/semantic-transformers
+
+python3 -m venv .venv
+source .venv/bin/activate        # Windows: .venv\Scripts\activate
+
+pip install -e semantic-transformers/
+pip install jupyterlab            # only needed for the interactive notebooks
+```
+
+## Two ways to use this library
+
+### Option A: you have a supported instrument
+
+Use a ready-made parser and the matching schema notebook. For a Zwick/Roell
+tensile test:
+
+```bash
+jupyter lab semantic-schemas/schemas/characterization/tensile-test/TTO/docs/2_tensile_test_csv_workflow.ipynb
+```
+
+Edit **Step 0** (one line, point to your file) and run all cells. Done.
+
+### Option B: you have a tabular file with no existing parser
+
+Use `QuickMapper`. Provide a short YAML that names the columns and points each
+one at an ontology class IRI:
+
+```python
+from semantic_transformers import QuickMapper
+
+mapping = {
+    "label": "my experiment",
+    "columns": {
+        "Force": {
+            "iri":  "https://w3id.org/pmd/tto/StandardForce",
+            "unit": "http://qudt.org/vocab/unit/N",
+        },
+        "Extension": {
+            "iri": "https://w3id.org/pmd/tto/Extension",
+        },
+    },
+}
+
+result = QuickMapper(mapping).run("my_data.csv")
+print(result.graph.serialize(format="turtle"))
+print(result.dataframe.head())
+```
+
+Supported file formats: CSV, TSV, Excel (.xlsx), Parquet, JSON.
+See the [QuickMapper notebook](docs/3_quickstart-mapping.ipynb) for a guided walkthrough.
+
+## Development
+
+### Running the tests
+
+```bash
+python3 -m venv .venv
+source .venv/bin/activate
+pip install -e ".[dev]"
+pytest -v
+```
+
+### Refreshing notebook outputs (for documentation)
+
+Notebooks are committed with their output cells so that GitHub renders them as
+readable documentation.  After changing a parser or the library, re-execute all
+notebooks in-place to update the stored outputs before committing:
+
+```bash
+find docs -name "*.ipynb" ! -path "*/.ipynb_checkpoints/*" \
+  | xargs jupyter nbconvert \
+      --to notebook \
+      --execute \
+      --inplace \
+      --ExecutePreprocessor.timeout=300
+```
+
+Run this from the repository root.  Commit the resulting `*.ipynb` changes
+together with any code changes so that the rendered output on GitHub stays
+in sync.
+
+> **Tip.** To refresh a single notebook only, pass its path directly:
+>
+> ```bash
+> jupyter nbconvert --to notebook --execute --inplace \
+>     --ExecutePreprocessor.timeout=300 \
+>     docs/3_quickstart-mapping.ipynb
+> ```
+
+## Documentation
+
+- [Getting started](docs/1_getting-started.md): convert your first instrument file
+- [QuickMapper walkthrough](docs/3_quickstart-mapping.ipynb): turn any tabular file into RDF
+- [Adding a parser](docs/2_adding-a-parser.md): support a new instrument or handle file variants

semantic_transformers-0.1.0.dist-info/RECORD

@@ -0,0 +1,9 @@
+semantic_transformers/__init__.py,sha256=BT2JaGozDaPcdWNGBzKQU8lVESnjaOfMM2Pu8r98xAg,718
+semantic_transformers/parser.py,sha256=2HVYeNlQHnTPspN9HjPpYekldifxgoIw7r_Yklu76jw,2860
+semantic_transformers/quick_mapper.py,sha256=GeUpJPobWStqf0cg0_bb8SCYJmK7qyKUkCpqC3ipcKk,8972
+semantic_transformers/transformer.py,sha256=bs5BXK65b_1VnBkCBxMZtFiU-_KD00IWYtJSro9Xh-M,13330
+semantic_transformers-0.1.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+semantic_transformers-0.1.0.dist-info/METADATA,sha256=77V1nzt15PBIKe49uTXe2aAcQrIUQMDzS5vtteCj-RY,6307
+semantic_transformers-0.1.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+semantic_transformers-0.1.0.dist-info/top_level.txt,sha256=bwBVVBWMiRPhMwHs-l5rnapEIQdkXMfqZMiiEQZP_QI,22
+semantic_transformers-0.1.0.dist-info/RECORD,,

semantic_transformers-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

semantic_transformers-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

semantic_transformers-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+semantic_transformers