senfd 0.2.2__tar.gz → 0.3.0__tar.gz

{senfd-0.2.2/src/senfd.egg-info → senfd-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: senfd
-Version: 0.2.2
+Version: 0.3.0
 Summary: Semantic Enhancer for Figure Documents
 Author-email: "Simon A. F. Lund" <os@safl.dk>
 License: LGPL-2.1-only
@@ -8,12 +8,17 @@ Description-Content-Type: text/x-rst
 License-File: LICENSE
 Requires-Dist: jinja2
 Requires-Dist: pydantic
-Requires-Dist: pytest
-Requires-Dist: pytest-cov
 Requires-Dist: python-docx
+Requires-Dist: tomli
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Provides-Extra: all
+Requires-Dist: senfd[dev]; extra == "all"
+Dynamic: license-file
 
-senfd: Semantic Enricher for NVMe Figure Documents
-==================================================
+senfd: Semantic Enricher for Non-mentioned-Trademark Figure Documents
+=====================================================================
 
 .. image:: https://img.shields.io/badge/docs-GitHub%20Pages-blue
     :target: https://safl.github.io/senfd/

{senfd-0.2.2 → senfd-0.3.0}/README.rst

@@ -1,5 +1,5 @@
-senfd: Semantic Enricher for NVMe Figure Documents
-==================================================
+senfd: Semantic Enricher for Non-mentioned-Trademark Figure Documents
+=====================================================================
 
 .. image:: https://img.shields.io/badge/docs-GitHub%20Pages-blue
     :target: https://safl.github.io/senfd/

{senfd-0.2.2 → senfd-0.3.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "senfd"
-version = "0.2.2"
+dynamic = ["version"]
 description = "Semantic Enhancer for Figure Documents"
 authors = [
     { name = "Simon A. F. Lund", email = "os@safl.dk" }
@@ -9,12 +9,18 @@ license = { text = "LGPL-2.1-only" }
 dependencies = [
     "jinja2",
     "pydantic",
-    "pytest",
-    "pytest-cov",
     "python-docx",
+    "tomli"
 ]
 readme = { file = "README.rst", content-type = "text/x-rst" }
 
+[project.optional-dependencies]
+dev = [
+    "pytest",
+    "pytest-cov",
+]
+all = ["senfd[dev]"]
+
 [project.scripts]
 senfd = "senfd.cli:main"
 
@@ -22,20 +28,20 @@ senfd = "senfd.cli:main"
 requires = ["setuptools>=42", "wheel"]
 build-backend = "setuptools.build_meta"
 
+[tool.setuptools.dynamic]
+version = { attr = "senfd.__version__" }
+
 [tool.setuptools.packages.find]
 where = ["src"]
 
 [tool.setuptools.package-data]
 "*" = ["*.jinja2", "*.schema.json"]
 
-[tool.black]
-line-length = 88
-
-[tool.isort]
-profile = "black"
-
 [tool.pytest.ini_options]
 addopts = "--maxfail=1 --disable-warnings"
 testpaths = [
     "tests",
 ]
+
+[tool.ruff]
+line-length = 88

senfd-0.3.0/src/senfd/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.3.0"

{senfd-0.2.2 → senfd-0.3.0}/src/senfd/cli.py

@@ -6,22 +6,48 @@ Produces organized and semantically enriched ``.json`` documents from
 """
 
 import json
-from argparse import ArgumentParser, Namespace
+from argparse import ArgumentParser, Namespace, RawTextHelpFormatter
 from pathlib import Path
 from typing import List
 
 import senfd
-import senfd.errors
 import senfd.pipeline
 import senfd.schemas
 from senfd.documents import get_document_classes
 from senfd.documents.base import to_file
+from senfd.documents.merged import FromFolder
+from senfd.errors import Error
 
+PARSEARGS_EPILOG = """\
+Senfd
+=====
 
-def to_log_file(
-    errors: List[senfd.errors.TableError], filename: str, output: Path
-) -> Path:
+The --skip-figures flag specifies a path to a TOML file containing a list of
+figures to be skipped during processing.
 
+The TOML file must follow this format:
+
+[[skip]]
+regex = "^Decimal.and.Binary.Units$"
+matches = 1
+description = ""
+
+[[skip]]
+regex = "^Byte, Word, and Dword Relationships$"
+matches = 1
+description = ""
+
+
+Each entry under [[skip]] consists of:
+  - regex: A regular expression matching the figure description.
+  - matches: The expected number of occurrences of this figure in the document.
+  - description: An optional text field describing the reason for skipping.
+
+This allows flexible and pattern-based skipping of figures during execution.
+"""
+
+
+def to_log_file(errors: List[Error], filename: str, output: Path) -> Path:
     content = json.dumps(
         [{"type": type(error).__name__, **error.model_dump()} for error in errors],
         indent=4,
@@ -33,7 +59,11 @@ def to_log_file(
 def parse_args() -> Namespace:
     """Return command-line arguments"""
 
-    parser = ArgumentParser(description="Semantically organize and enrich figures")
+    parser = ArgumentParser(
+        description="Semantically organize and enrich figures",
+        epilog=PARSEARGS_EPILOG,
+        formatter_class=RawTextHelpFormatter,
+    )
     parser.add_argument(
         "document", nargs="*", type=Path, help="path to one or more document(s)"
     )
@@ -48,6 +78,11 @@ def parse_args() -> Namespace:
         action="store_true",
         help="dump schema(s) and exit",
     )
+    parser.add_argument(
+        "--skip-figures",
+        type=Path,
+        help="Path to toml file that contains list of figure classifiers to skip",
+    )
     parser.add_argument(
         "--version",
         action="store_true",
@@ -75,8 +110,18 @@ def main() -> int:
             docclass.to_schema_file(args.output)
         return 0
 
-    for path in args.document:
-        errors = senfd.pipeline.process(path, args.output)
+    for count, path in enumerate(sorted(args.document), 1):
+        args.output.mkdir(parents=True, exist_ok=True)
+
+        errors = senfd.pipeline.process(path, args.output, args)
         to_log_file(errors, path.stem, args.output)
 
+    if FromFolder.is_applicable(args.output):  # Merge ModelDocuments
+        merged, errors = FromFolder.convert(args.output, args)
+        merged.to_json_file(args.output / merged.json_filename())
+
     return 0
+
+
+if __name__ == "__main__":
+    main()

{senfd-0.2.2 → senfd-0.3.0}/src/senfd/documents/base.py

@@ -2,23 +2,24 @@
 Documents
 =========
 
-The following classes model documents at different stages of parsing / processing an
-NVMe specification document from a raw extract into something semantically rich.
-
+The following classes model documents at different stages of parsing / processing a
+specification document from a raw extract into something semantically rich.
 """
 
 import importlib.resources as pkg_resources
 import json
 from abc import ABC, abstractmethod
+from argparse import Namespace
 from pathlib import Path
 from typing import Any, ClassVar, Dict, List, Optional, Tuple
 
 from jinja2 import Environment, PackageLoader, select_autoescape
-from pydantic import BaseModel, Field, ValidationError
+from pydantic import BaseModel, Field
 
 import senfd.schemas
 import senfd.tables
-from senfd.errors import TableError
+import senfd.utils
+from senfd.errors import Error
 
 TRANSLATION_TABLE: Dict[int, str] = str.maketrans(
     {
@@ -63,7 +64,7 @@ def to_file(content: str, filename: str, path: Optional[Path] = None):
     if path.is_dir():
         path = path / filename
 
-    path.write_text(content)
+    path.write_text(content, encoding="utf-8")
 
     return path
 
@@ -104,7 +105,7 @@ class Document(BaseModel):
         """Writes the document JSON schema to file at the given 'path'"""
 
         return to_file(
-            json.dumps(cls.schema(), indent=4),
+            json.dumps(cls.model_json_schema(), indent=4),
             cls.schema_filename(),
             path,
         )
@@ -122,7 +123,7 @@ class Document(BaseModel):
     def to_json(self) -> str:
         """Returns the document as a JSON-formatted string"""
 
-        return self.model_dump_json(indent=4)
+        return self.model_dump_json()
 
     def to_json_file(self, path: Optional[Path] = None) -> Path:
         """Writes the document, formatted as JSON, to file at the given 'path'"""
@@ -132,42 +133,43 @@ class Document(BaseModel):
     def html_filename(self) -> str:
         return f"{self.meta.stem}{self.SUFFIX_HTML}"
 
-    def to_html(self) -> str:
+    def to_html(self, errors: List[Error] = []) -> str:
         """Returns the document as a HTML-formatted string"""
 
         env = Environment(
             loader=PackageLoader("senfd", "templates"),
             autoescape=select_autoescape(["html", "xml"]),
         )
+        env.filters["snake_to_pascal"] = senfd.utils.snake_to_pascal
+        env.filters["pascal_to_snake"] = senfd.utils.pascal_to_snake
         template = env.get_template(self.FILENAME_HTML_TEMPLATE)
 
-        return template.render(document=self.dict())
-
-    def to_html_file(self, path: Optional[Path] = None) -> Path:
-        """Writes the document to HTML-formatted file"""
+        figure_errors: Dict[int, List[Error]] = {}
+        for error in errors:
+            if not hasattr(error, "figure_nr"):
+                continue
 
-        return to_file(self.to_html(), self.html_filename(), path)
+            if error.figure_nr not in figure_errors:
+                figure_errors[error.figure_nr] = []
+            figure_errors[error.figure_nr].append(error)
 
-    def is_valid(self) -> bool:
-        """Returns True when validator raises no exceptions, False otherwise"""
+        return template.render(document=self.model_dump(), figure_errors=figure_errors)
 
-        try:
-            self.validate(self.dict())
-        except ValidationError as e:
-            print(e)
-            return False
+    def to_html_file(
+        self, path: Optional[Path] = None, errors: List[Error] = []
+    ) -> Path:
+        """Writes the document to HTML-formatted file"""
 
-        return True
+        return to_file(self.to_html(errors), self.html_filename(), path)
 
 
 class Converter(ABC):
-
     @staticmethod
     @abstractmethod
     def is_applicable(path: Path) -> bool:
-        pass
+        """Check whether the converter is applicable to the given 'path'"""
 
     @staticmethod
     @abstractmethod
-    def convert(path: Path) -> Tuple[Document, List[TableError]]:
-        pass
+    def convert(path: Path, args: Namespace) -> Tuple[Document, List[Error]]:
+        """Convert the given 'path' into a 'Document'"""