senfd 0.2.0__tar.gz → 0.2.2__tar.gz

{senfd-0.2.0/src/senfd.egg-info → senfd-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: senfd
-Version: 0.2.0
+Version: 0.2.2
 Summary: Semantic Enhancer for Figure Documents
 Author-email: "Simon A. F. Lund" <os@safl.dk>
 License: LGPL-2.1-only

{senfd-0.2.0 → senfd-0.2.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "senfd"
-version = "0.2.0"
+version = "0.2.2"
 description = "Semantic Enhancer for Figure Documents"
 authors = [
     { name = "Simon A. F. Lund", email = "os@safl.dk" }

senfd-0.2.2/src/senfd/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.2.2"

{senfd-0.2.0 → senfd-0.2.2}/src/senfd/cli.py

@@ -5,14 +5,29 @@ Command-Line Interface
 Produces organized and semantically enriched ``.json`` documents from
 """
 
+import json
 from argparse import ArgumentParser, Namespace
 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
+
+
+def to_log_file(
+    errors: List[senfd.errors.TableError], filename: str, output: Path
+) -> Path:
+
+    content = json.dumps(
+        [{"type": type(error).__name__, **error.model_dump()} for error in errors],
+        indent=4,
+    )
+
+    return to_file(content, f"{filename}.error.log", output)
 
 
 def parse_args() -> Namespace:
@@ -62,6 +77,6 @@ def main() -> int:
 
     for path in args.document:
         errors = senfd.pipeline.process(path, args.output)
-        senfd.errors.to_log_file(errors, path.stem, args.output)
+        to_log_file(errors, path.stem, args.output)
 
     return 0

{senfd-0.2.0 → senfd-0.2.2}/src/senfd/documents/base.py

@@ -11,13 +11,14 @@ import importlib.resources as pkg_resources
 import json
 from abc import ABC, abstractmethod
 from pathlib import Path
-from typing import Any, ClassVar, Dict, List, NamedTuple, Optional, Tuple
+from typing import Any, ClassVar, Dict, List, Optional, Tuple
 
 from jinja2 import Environment, PackageLoader, select_autoescape
 from pydantic import BaseModel, Field, ValidationError
 
 import senfd.schemas
 import senfd.tables
+from senfd.errors import TableError
 
 TRANSLATION_TABLE: Dict[int, str] = str.maketrans(
     {
@@ -119,12 +120,12 @@ class Document(BaseModel):
         return f"{self.meta.stem}{self.SUFFIX_JSON}"
 
     def to_json(self) -> str:
-        """Returns the document as a JSON-formated string"""
+        """Returns the document as a JSON-formatted string"""
 
         return self.model_dump_json(indent=4)
 
     def to_json_file(self, path: Optional[Path] = None) -> Path:
-        """Writes the document, formated as JSON, to file at the given 'path'"""
+        """Writes the document, formatted as JSON, to file at the given 'path'"""
 
         return to_file(self.to_json(), self.json_filename(), path)
 
@@ -168,5 +169,5 @@ class Converter(ABC):
 
     @staticmethod
     @abstractmethod
-    def convert(path: Path) -> Tuple[Document, List[NamedTuple]]:
+    def convert(path: Path) -> Tuple[Document, List[TableError]]:
         pass

{senfd-0.2.0 → senfd-0.2.2}/src/senfd/documents/enriched.py

@@ -5,6 +5,7 @@ from typing import ClassVar, List, NamedTuple, Optional, Tuple
 
 from pydantic import Field
 
+import senfd.errors
 import senfd.schemas
 import senfd.tables
 from senfd.documents.base import (
@@ -212,7 +213,7 @@ class FromFigureDocument(Converter):
         return "".join(path.suffixes).lower() == ".plain.figure.document.json"
 
     @staticmethod
-    def convert(path: Path) -> Tuple[Document, List[NamedTuple]]:
+    def convert(path: Path) -> Tuple[Document, List[senfd.errors.TableError]]:
         """Instantiate an 'organized' Document from a 'figure' document"""
 
         errors = []

{senfd-0.2.0 → senfd-0.2.2}/src/senfd/documents/plain.py

@@ -1,6 +1,6 @@
 import re
 from pathlib import Path
-from typing import ClassVar, List, NamedTuple, Optional, Tuple
+from typing import ClassVar, List, Optional, Tuple
 
 import docx
 from pydantic import BaseModel, Field
@@ -74,8 +74,7 @@ class FromDocx(Converter):
         return path.suffix.lower() == ".docx"
 
     @staticmethod
-    def convert(path: Path) -> Tuple[FigureDocument, List[NamedTuple]]:
-
+    def convert(path: Path) -> Tuple[FigureDocument, List[senfd.errors.TableError]]:
         def docx_table_to_table(docx_table: docx.table.Table) -> Table:
             table = Table()
 
@@ -96,7 +95,7 @@ class FromDocx(Converter):
             return table
 
         figures = {}
-        errors: List[NamedTuple] = []
+        errors: List[senfd.errors.TableError] = []
 
         docx_document = docx.Document(path)
 
@@ -108,8 +107,8 @@ class FromDocx(Converter):
             if not figure:
                 errors.append(
                     senfd.errors.TableCaptionError(
-                        "Does not match figure caption assumptions",
-                        caption,
+                        message="Does not match figure caption assumptions",
+                        caption=caption,
                     )
                 )
                 continue
@@ -117,8 +116,8 @@ class FromDocx(Converter):
             if figure.figure_nr in figures:
                 errors.append(
                     senfd.errors.TableCaptionError(
-                        "Duplicate caption",
-                        caption,
+                        message="Duplicate caption",
+                        caption=caption,
                     )
                 )
                 continue
@@ -127,7 +126,7 @@ class FromDocx(Converter):
             figures[figure.figure_nr] = figure
 
         # Update tabular figures with page_nr
-        # Add non-fabular figures
+        # Add non-tabular figures
         # Check table-of-figure description validity
         prev = cur = None
         for paragraph in docx_document.paragraphs:
@@ -148,15 +147,17 @@ class FromDocx(Converter):
             if not figure:
                 errors.append(
                     senfd.errors.TableOfFiguresError(
-                        "Does not match figure assumptions",
-                        caption,
+                        message="Does not match figure assumptions",
+                        caption=caption,
                     )
                 )
                 continue
 
             if not figure.page_nr:
                 errors.append(
-                    senfd.errors.TableOfFiguresError("Is missing <page_nr>", caption)
+                    senfd.errors.TableOfFiguresError(
+                        message="Is missing <page_nr>", caption=caption
+                    )
                 )
                 continue
 
@@ -166,8 +167,8 @@ class FromDocx(Converter):
                 if figure.description not in existing.description:
                     errors.append(
                         senfd.errors.TableOfFiguresError(
-                            f"({existing.description}) != {figure.description}",
-                            caption,
+                            message=f"({existing.description}) != {figure.description}",
+                            caption=caption,
                         )
                     )
             else:
@@ -175,7 +176,8 @@ class FromDocx(Converter):
 
         return (
             FigureDocument(
-                meta=DocumentMeta(stem=path.stem), figures=list(figures.values())
+                meta=DocumentMeta(stem=path.stem.replace(".", "-")),
+                figures=list(figures.values()),
             ),
             errors,
         )

senfd-0.2.2/src/senfd/errors.py

@@ -0,0 +1,28 @@
+from typing import Any, List
+
+from pydantic import BaseModel
+
+
+class TableError(BaseModel):
+    message: str
+
+
+class TableOfFiguresError(TableError):
+    caption: str
+
+
+class TableCaptionError(TableError):
+    caption: str
+
+
+class TableHeaderError(TableError):
+    caption: str
+    cells: List[Any]
+
+
+class IrregularTableError(TableError):
+    lengths: List[int]
+
+
+class NonTableHeaderError(TableError):
+    pass

{senfd-0.2.0 → senfd-0.2.2}/src/senfd/pipeline.py

@@ -1,12 +1,14 @@
 from pathlib import Path
+from typing import List
 
 from senfd.documents.enriched import FromFigureDocument
 from senfd.documents.plain import FromDocx
+from senfd.errors import TableError
 
 CONVERTERS = [FromDocx, FromFigureDocument]
 
 
-def process(input: Path, output: Path):
+def process(input: Path, output: Path) -> List[TableError]:
     all_errors = []
 
     for converter in CONVERTERS:

{senfd-0.2.0 → senfd-0.2.2}/src/senfd/schemas/enriched.figure.document.schema.json

@@ -497,7 +497,7 @@
         "DocumentMeta": {
             "properties": {
                 "version": {
-                    "default": "0.2.0",
+                    "default": "0.2.2",
                     "title": "Version",
                     "type": "string"
                 },

{senfd-0.2.0 → senfd-0.2.2}/src/senfd/schemas/plain.figure.document.schema.json

@@ -20,7 +20,7 @@
         "DocumentMeta": {
             "properties": {
                 "version": {
-                    "default": "0.2.0",
+                    "default": "0.2.2",
                     "title": "Version",
                     "type": "string"
                 },

{senfd-0.2.0 → senfd-0.2.2}/src/senfd/tables.py

@@ -1,4 +1,4 @@
-from typing import ClassVar, List, NamedTuple, Optional, Tuple
+from typing import ClassVar, List, Optional, Tuple
 
 from pydantic import BaseModel, Field
 
@@ -41,16 +41,20 @@ class HeaderTable(Table):
     headers: List[str] = Field(default_factory=list)
 
     @classmethod
-    def from_table(cls, table: Table) -> Tuple[Optional[Table], Optional[NamedTuple]]:
+    def from_table(
+        cls, table: Table
+    ) -> Tuple[Optional["HeaderTable"], Optional[senfd.errors.TableError]]:
 
         lengths = list(set([len(row.cells) for row in table.rows]))
         if len(lengths) != 1:
             return None, senfd.errors.IrregularTableError(
-                f"Varying row lengths({lengths})", lengths
+                message=f"Varying row lengths({lengths})", lengths=lengths
             )
 
         if len(table.rows) < 2:
-            return None, senfd.errors.NonTableHeaderError("Insufficent number of rows")
+            return None, senfd.errors.NonTableHeaderError(
+                message="Insufficent number of rows"
+            )
 
         headers = [
             cell.text.strip()
@@ -59,9 +63,9 @@ class HeaderTable(Table):
         ]
         if len(headers) != len(table.rows[1].cells):
             return None, senfd.errors.TableHeaderError(
-                "Unsupported names",
-                table.rows[0].cells[0].text,
-                [cell.text for cell in table.rows[1].cells],
+                message="Unsupported names",
+                caption=table.rows[0].cells[0].text,
+                cells=[cell.text for cell in table.rows[1].cells],
             )
 
         data = table.dict()

{senfd-0.2.0 → senfd-0.2.2/src/senfd.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: senfd
-Version: 0.2.0
+Version: 0.2.2
 Summary: Semantic Enhancer for Figure Documents
 Author-email: "Simon A. F. Lund" <os@safl.dk>
 License: LGPL-2.1-only

senfd-0.2.0/src/senfd/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.2.0"

senfd-0.2.0/src/senfd/errors.py

@@ -1,36 +0,0 @@
-import json
-from collections import namedtuple
-from pathlib import Path
-from typing import Any, Dict, List, NamedTuple
-
-from pydantic import BaseModel
-
-from senfd.documents.base import to_file
-
-TableOfFiguresError = namedtuple("TableOfFiguresError", ["message", "caption"])
-
-TableCaptionError = namedtuple("TableCaptionError", ["message", "caption"])
-
-TableHeaderError = namedtuple("TableHeaderError", ["message", "caption", "cells"])
-
-IrregularTableError = namedtuple("IrregularTableError", ["message", "lengths"])
-
-NonTableHeaderError = namedtuple("NonTableHeaderError", ["message"])
-
-
-def error_to_dict(error: NamedTuple) -> Dict[str, List[Any]]:
-    error_dict = error._asdict()
-    for key, value in error_dict.items():
-        if isinstance(value, BaseModel):
-            error_dict[key] = value.dict()
-    return error_dict
-
-
-def to_log_file(errors: List[NamedTuple], filename: str, output: Path) -> Path:
-
-    content = json.dumps(
-        [{"type": type(error).__name__, **error_to_dict(error)} for error in errors],
-        indent=4,
-    )
-
-    return to_file(content, f"{filename}.error.log", output)