dcmspec 0.2.2__tar.gz → 0.2.3__tar.gz

{dcmspec-0.2.2 → dcmspec-0.2.3}/CHANGELOG.md

@@ -2,6 +2,13 @@
 
 These release notes summarize key changes, improvements, and breaking updates for each version of **dcmspec**.
 
+## [0.2.3] - 2025-09-29
+
+### Fixed
+
+- Hotfix: Force UTF-8 decoding for DICOM standard XHTML downloads to prevent mojibake when server omits charset ([#85](https://github.com/dwikler/dcmspec/issues/85)).
+- Hotfix: Add missing `progress_observer` argument to `CSVTableSpecParser.parse` for interface compatibility and to prevent `TypeError` when used with `SpecFactory` ([#86](https://github.com/dwikler/dcmspec/issues/86)).
+
 ## [0.2.2] - 2025-09-25
 
 ### Fixed

{dcmspec-0.2.2 → dcmspec-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dcmspec
-Version: 0.2.2
+Version: 0.2.3
 Summary: Toolkit for extracting, parsing, and processing DICOM specifications.
 License: Apache-2.0
 License-File: LICENSE
@@ -45,7 +45,7 @@ Description-Content-Type: text/markdown
 [![tests](https://github.com/dwikler/dcmspec/actions/workflows/test.yml/badge.svg)](https://github.com/dwikler/dcmspec/actions/workflows/test.yml)
 [![PyPI version](https://badge.fury.io/py/dcmspec.svg)](https://badge.fury.io/py/dcmspec)
 [![Python versions](https://img.shields.io/pypi/pyversions/dcmspec.svg)](https://pypi.org/project/dcmspec/)
-[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.17206999.svg)](https://doi.org/10.5281/zenodo.17206999)
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.17233195.svg)](https://doi.org/10.5281/zenodo.17233195)
 
 # dcmspec
 

{dcmspec-0.2.2 → dcmspec-0.2.3}/README.md

@@ -1,7 +1,7 @@
 [![tests](https://github.com/dwikler/dcmspec/actions/workflows/test.yml/badge.svg)](https://github.com/dwikler/dcmspec/actions/workflows/test.yml)
 [![PyPI version](https://badge.fury.io/py/dcmspec.svg)](https://badge.fury.io/py/dcmspec)
 [![Python versions](https://img.shields.io/pypi/pyversions/dcmspec.svg)](https://pypi.org/project/dcmspec/)
-[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.17206999.svg)](https://doi.org/10.5281/zenodo.17206999)
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.17233195.svg)](https://doi.org/10.5281/zenodo.17233195)
 
 # dcmspec
 

{dcmspec-0.2.2 → dcmspec-0.2.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "dcmspec"
-version = "0.2.2"
+version = "0.2.3"
 description = "Toolkit for extracting, parsing, and processing DICOM specifications."
 authors = [{ name = "David Wikler", email = "david.wikler@ulb.be" }]
 license = { text = "Apache-2.0" }

{dcmspec-0.2.2 → dcmspec-0.2.3}/src/dcmspec/csv_table_spec_parser.py

@@ -3,10 +3,11 @@
 Provides the CSVTableSpecParser class for parsing DICOM specification tables in CSV format,
 converting them into structured in-memory representations using anytree.
 """
-from typing import Tuple
+from typing import Dict, List, Tuple, Optional
 from anytree import Node
 
 from dcmspec.spec_parser import SpecParser
+from dcmspec.progress import ProgressObserver
 
 class CSVTableSpecParser(SpecParser):
     """Base parser for DICOM Specification IHE tables in CSV-like format."""
@@ -14,10 +15,11 @@ class CSVTableSpecParser(SpecParser):
     def parse(
         self,
         table: dict,
-        column_to_attr,
-        name_attr="elem_name",
-        table_id=None,
-        include_depth=None,
+        column_to_attr: dict,
+        name_attr: str = "elem_name",
+        table_id: Optional[str] = None,
+        include_depth: Optional[int] = None,
+        progress_observer: Optional[ProgressObserver] = None,
     ) -> Tuple[Node, Node]:
         """Parse specification metadata and content from a single table dict.
 
@@ -27,11 +29,18 @@ class CSVTableSpecParser(SpecParser):
             name_attr (str): The attribute to use for node names.
             table_id (str, optional): Table identifier for model parsing.
             include_depth (int, optional): The depth to which included tables should be parsed.
+            progress_observer (Optional[ProgressObserver]): 
+                Accepted for interface compatibility, but ignored in this parser.
+                Included so that this method can be called with the same arguments as other table parsers.
 
         Returns:
             tuple: (metadata_node, content_node)
 
         """
+        if progress_observer is not None and hasattr(self, "logger"):
+            self.logger.debug(
+                "Progress reporting is not supported yet for CSV parsing and will be ignored."
+            )
         # Use the header and data from the grouped table dict
         header = table.get("header", [])
         data = table.get("data", [])
@@ -47,8 +56,8 @@ class CSVTableSpecParser(SpecParser):
 
     def parse_table(
         self,
-        tables: list,  # List of tables, each a list of rows (list of str)
-        column_to_attr: dict,
+        tables: List[List[List[str]]],  # List of tables, each a list of rows (list of str)
+        column_to_attr: Dict[int, str],
         name_attr: str = "elem_name",
     ) -> Node:
         """Build a tree from tables using column mapping and '>' nesting logic.

{dcmspec-0.2.2 → dcmspec-0.2.3}/src/dcmspec/doc_handler.py

@@ -94,6 +94,8 @@ class DocHandler:
         try:
             with requests.get(url, timeout=30, stream=True, headers={"Accept-Encoding": "identity"}) as response:
                 response.raise_for_status()
+                self._set_response_encoding(response)
+
                 total = int(response.headers.get('content-length', 0))
                 chunk_size = 8192
                 if binary:
@@ -109,6 +111,19 @@ class DocHandler:
             self.logger.error(f"Failed to save file {file_path}: {e}")
             raise RuntimeError(f"Failed to save file {file_path}: {e}") from e
 
+    def _set_response_encoding(self, response):
+        """Set response.encoding to UTF-8 only if the Content-Type header does not specify a charset.
+        
+        Force utf-8 decoding if the web server does not specify the charset in the HTTP response
+        Content-Type header (DICOM standard XHTML files are always UTF-8 encoded).  
+        """
+        content_type = response.headers.get("Content-Type", "")
+        if "charset=" not in content_type.lower():
+            response.encoding = "utf-8"
+            self.logger.debug("No charset in Content-Type header; forcing UTF-8 decoding.")
+        else:
+            self.logger.debug(f"Using server-specified encoding from Content-Type: {content_type}")
+            
     def _report_progress(self, downloaded, total, progress_observer, last_percent):
         """Report progress if percent changed.
 

{dcmspec-0.2.2 → dcmspec-0.2.3}/src/dcmspec/dom_table_spec_parser.py

@@ -13,7 +13,7 @@ from typing import Any, Dict, Optional, Union
 from dcmspec.spec_parser import SpecParser
 
 from dcmspec.dom_utils import DOMUtils
-from dcmspec.progress import Progress, ProgressStatus, calculate_percent
+from dcmspec.progress import Progress, ProgressObserver, ProgressStatus, calculate_percent
 
 class DOMTableSpecParser(SpecParser):
     """Parser for DICOM specification tables in XHTML DOM format.
@@ -43,7 +43,7 @@ class DOMTableSpecParser(SpecParser):
         column_to_attr: Dict[int, str],
         name_attr: str,
         include_depth: Optional[int] = None,  # None means unlimited
-        progress_observer: Optional[Any] = None,
+        progress_observer: Optional[ProgressObserver] = None,
         skip_columns: Optional[list[int]] = None,
         unformatted: Optional[Union[bool, Dict[int, bool]]] = True,
     ) -> tuple[Node, Node]:
@@ -59,7 +59,7 @@ class DOMTableSpecParser(SpecParser):
             name_attr (str): The attribute name to use for building node names.
             include_depth (Optional[int], optional): The depth to which included tables should be parsed. 
                 None means unlimited.
-            progress_observer (Optional[object], optional): Optional observer to report download progress.
+            progress_observer (Optional[ProgressObserver]): Optional observer to report parsing progress.
             skip_columns (Optional[list[int]]): List of column indices to skip if the row is missing a column.
                 This argument is typically set via `parser_kwargs` when using SpecFactory.
             unformatted (Optional[Union[bool, Dict[int, bool]]]): 
@@ -132,7 +132,7 @@ class DOMTableSpecParser(SpecParser):
         name_attr: str,
         table_nesting_level: int = 0,
         include_depth: Optional[int] = None,  # None means unlimited
-        progress_observer: Optional[Any] = None,
+        progress_observer: Optional[ProgressObserver] = None,
         skip_columns: Optional[list[int]] = None,
         visited_tables: Optional[set] = None,
         unformatted_list: Optional[list[bool]] = None,
@@ -151,7 +151,7 @@ class DOMTableSpecParser(SpecParser):
             name_attr: tree node attribute name to use to build node name
             table_nesting_level: The nesting level of the table (used for recursion call only).
             include_depth: The depth to which included tables should be parsed.
-            progress_observer (Optional[object], optional): Optional observer to report download progress.
+            progress_observer (Optional[ProgressObserver]): Optional observer to report parsing progress.
             skip_columns (Optional[list[int]]): List of column indices to skip if the row is missing a column.
             visited_tables (Optional[set]): Set of table IDs that have been visited to prevent infinite recursion.
             unformatted_list (Optional[list[bool]]): List of booleans indicating whether to extract each column as 
@@ -287,7 +287,7 @@ class DOMTableSpecParser(SpecParser):
         unformatted_list: list[bool],
         level_nodes: Dict[int, Node],
         root: Node,
-        progress_observer: Optional[Any] = None
+        progress_observer: Optional[ProgressObserver] = None
     ) -> None:
         """Process all rows in the table, handling recursion, nesting, and node creation."""
         rows = table.find_all("tr")[1:]