psdi-data-conversion 0.0.38__py3-none-any.whl → 0.1.0__py3-none-any.whl

psdi_data_conversion/database.py

@@ -7,16 +7,17 @@ Python module provide utilities for accessing the converter database
 
 from __future__ import annotations
 
+import json
+import os
 from dataclasses import dataclass, field
 from itertools import product
-import json
 from logging import getLogger
-import os
-from typing import Any, Literal
+from typing import Any, Literal, overload
 
 from psdi_data_conversion import constants as const
-from psdi_data_conversion.converter import D_REGISTERED_CONVERTERS, D_SUPPORTED_CONVERTERS
+from psdi_data_conversion.converter import D_SUPPORTED_CONVERTERS, get_registered_converter_class
 from psdi_data_conversion.converters.base import FileConverterException
+from psdi_data_conversion.utils import regularize_name
 
 # Keys for top-level and general items in the database
 DB_FORMATS_KEY = "formats"
@@ -32,6 +33,7 @@ DB_URL_KEY = "url"
 
 # Keys for format general info in the database
 DB_FORMAT_EXT_KEY = "extension"
+DB_FORMAT_C2X_KEY = "format"
 DB_FORMAT_NOTE_KEY = "note"
 DB_FORMAT_COMP_KEY = "composition"
 DB_FORMAT_CONN_KEY = "connections"
@@ -116,14 +118,14 @@ class ConverterInfo:
         Parameters
         ----------
         name : str
-            The name of the converter
+            The regularized name of the converter
         parent : DataConversionDatabase
             The database which this belongs to
         d_data : dict[str, Any]
             The loaded database dict
         """
 
-        self.name = name
+        self.name = regularize_name(name)
         self.parent = parent
 
         # Get info about the converter from the database
@@ -133,7 +135,7 @@ class ConverterInfo:
 
         # Get necessary info about the converter from the class
         try:
-            self._key_prefix = D_REGISTERED_CONVERTERS[name].database_key_prefix
+            self._key_prefix = get_registered_converter_class(name).database_key_prefix
         except KeyError:
             # We'll get a KeyError for converters in the database that don't yet have their own class, which we can
             # safely ignore
@@ -428,6 +430,9 @@ class FormatInfo:
         self.id: int = d_single_format_info.get(DB_ID_KEY, -1)
         """The ID of this format"""
 
+        self.c2x_format: str = d_single_format_info.get(DB_FORMAT_C2X_KEY)
+        """The name of this format as the c2x converter expects it"""
+
         self.note: str = d_single_format_info.get(DB_FORMAT_NOTE_KEY, "")
         """The description of this format"""
 
@@ -525,6 +530,10 @@ class ConversionQualityInfo:
     input and output file formats and a note on the implications
     """
 
+    def __post_init__(self):
+        """Regularize the converter name"""
+        self.converter_name = regularize_name(self.converter_name)
+
 
 class ConversionsTable:
     """Class providing information on available file format conversions.
@@ -619,7 +628,7 @@ class ConversionsTable:
 
         # Check if this converter deals with ambiguous formats, so we know if we need to be strict about getting format
         # info
-        if D_REGISTERED_CONVERTERS[converter_name].supports_ambiguous_extensions:
+        if get_registered_converter_class(converter_name).supports_ambiguous_extensions:
             which_format = None
         else:
             which_format = 0
@@ -708,8 +717,8 @@ class ConversionsTable:
             conversion, the second is the info of the input format for this conversion, and the third is the info of the
             output format
         """
-        l_in_format_infos: list[FormatInfo] = self.parent.get_format_info(in_format, which="all")
-        l_out_format_infos: list[FormatInfo] = self.parent.get_format_info(out_format, which="all")
+        l_in_format_infos = self.parent.get_format_info(in_format, which="all")
+        l_out_format_infos = self.parent.get_format_info(out_format, which="all")
 
         # Start a list of all possible conversions
         l_possible_conversions = []
@@ -801,7 +810,7 @@ class DataConversionDatabase:
         if self._d_converter_info is None:
             self._d_converter_info: dict[str, ConverterInfo] = {}
             for d_single_converter_info in self.converters:
-                name: str = d_single_converter_info[DB_NAME_KEY]
+                name: str = regularize_name(d_single_converter_info[DB_NAME_KEY])
                 if name in self._d_converter_info:
                     logger.warning(f"Converter '{name}' appears more than once in the database. Only the first instance"
                                    " will be used.")
@@ -934,6 +943,16 @@ class DataConversionDatabase:
                                                  f" of type '{type(converter_name_or_id)}'. Type must be `str` or "
                                                  "`int`")
 
+    @overload
+    def get_format_info(self,
+                        format_name_or_id: str | int | FormatInfo,
+                        which: int | None = None) -> FormatInfo: ...
+
+    @overload
+    def get_format_info(self,
+                        format_name_or_id: str | int | FormatInfo,
+                        which: Literal["all"]) -> list[FormatInfo]: ...
+
     def get_format_info(self,
                         format_name_or_id: str | int | FormatInfo,
                         which: int | Literal["all"] | None = None) -> FormatInfo | list[FormatInfo]:
@@ -1081,7 +1100,17 @@ def get_converter_info(name: str) -> ConverterInfo:
     ConverterInfo
     """
 
-    return get_database().d_converter_info[name]
+    return get_database().d_converter_info[regularize_name(name)]
+
+
+@overload
+def get_format_info(format_name_or_id: str | int | FormatInfo,
+                    which: int | None = None) -> FormatInfo: ...
+
+
+@overload
+def get_format_info(format_name_or_id: str | int | FormatInfo,
+                    which: Literal["all"]) -> list[FormatInfo]: ...
 
 
 def get_format_info(format_name_or_id: str | int | FormatInfo,
@@ -1131,7 +1160,7 @@ def get_conversion_quality(converter_name: str,
         `ConversionQualityInfo` object with info on the conversion
     """
 
-    return get_database().conversions_table.get_conversion_quality(converter_name=converter_name,
+    return get_database().conversions_table.get_conversion_quality(converter_name=regularize_name(converter_name),
                                                                    in_format=in_format,
                                                                    out_format=out_format)
 
@@ -1186,6 +1215,9 @@ def disambiguate_formats(converter_name: str,
         If more than one format combination is possible for this conversion, or no conversion is possible
     """
 
+    # Regularize the converter name so we don't worry about case/spacing mismatches
+    converter_name = regularize_name(converter_name)
+
     # Get all possible conversions, and see if we only have one for this converter
     l_possible_conversions = [x for x in get_possible_conversions(in_format, out_format)
                               if x[0] == converter_name]
@@ -1219,7 +1251,7 @@ def get_possible_formats(converter_name: str) -> tuple[list[FormatInfo], list[Fo
     tuple[list[FormatInfo], list[FormatInfo]]
         A tuple of a list of the supported input formats and a list of the supported output formats
     """
-    return get_database().conversions_table.get_possible_formats(converter_name=converter_name)
+    return get_database().conversions_table.get_possible_formats(converter_name=regularize_name(converter_name))
 
 
 def _find_arg(tl_args: tuple[list[FlagInfo], list[OptionInfo]],

psdi_data_conversion/dist.py

@@ -7,9 +7,10 @@ Functions and utilities related to handling multiple user OSes and distributions
 
 import os
 import shutil
-import psdi_data_conversion
 import sys
 
+import psdi_data_conversion
+
 # Labels for each platform (which we use for the folder in this project), and the head of the name each platform will
 # have in `sys.platform`
 

psdi_data_conversion/file_io.py

@@ -149,8 +149,7 @@ def pack_zip_or_tar(archive_filename: str,
                 archive_format = _format
                 archive_root_filename = split_archive_ext(archive_filename)[0]
                 break
-        # Check that the format was found
-        if archive_format is None:
+        else:
             raise AssertionError("Invalid execution path entered - filename wasn't found with a valid archive "
                                  "extension, but it did pass the `is_supported_archive` check")
     else:

psdi_data_conversion/log_utility.py

@@ -5,11 +5,11 @@ Created 2024-12-09 by Bryan Gillis.
 Functions and classes related to logging and other messaging for the user
 """
 
-from datetime import datetime
 import logging
 import os
 import re
 import sys
+from datetime import datetime
 
 from psdi_data_conversion import constants as const
 

psdi_data_conversion/main.py

@@ -7,17 +7,19 @@ Created 2025-01-14 by Bryan Gillis.
 Entry-point file for the command-line interface for data conversion.
 """
 
-from itertools import product
 import logging
-from argparse import ArgumentParser
 import os
 import sys
 import textwrap
+from argparse import ArgumentParser
+from itertools import product
 
 from psdi_data_conversion import constants as const
 from psdi_data_conversion.constants import CL_SCRIPT_NAME, CONVERTER_DEFAULT, TERM_WIDTH
-from psdi_data_conversion.converter import (D_CONVERTER_ARGS, D_SUPPORTED_CONVERTERS, L_REGISTERED_CONVERTERS,
-                                            L_SUPPORTED_CONVERTERS, run_converter)
+from psdi_data_conversion.converter import (D_CONVERTER_ARGS, L_REGISTERED_CONVERTERS, L_SUPPORTED_CONVERTERS,
+                                            converter_is_registered, converter_is_supported,
+                                            get_registered_converter_class, get_supported_converter_class,
+                                            run_converter)
 from psdi_data_conversion.converters.base import (FileConverterAbortException, FileConverterException,
                                                   FileConverterInputException)
 from psdi_data_conversion.database import (FormatInfo, get_conversion_quality, get_converter_info, get_format_info,
@@ -25,6 +27,7 @@ from psdi_data_conversion.database import (FormatInfo, get_conversion_quality, g
                                            get_possible_formats)
 from psdi_data_conversion.file_io import split_archive_ext
 from psdi_data_conversion.log_utility import get_log_level_from_str
+from psdi_data_conversion.utils import regularize_name
 
 
 def print_wrap(s: str, newline=False, err=False, **kwargs):
@@ -58,9 +61,9 @@ class ConvertArgs:
         self._output_dir: str | None = args.out
         converter_name = getattr(args, "with")
         if isinstance(converter_name, str):
-            self.name = converter_name
+            self.name = regularize_name(converter_name)
         elif converter_name:
-            self.name: str = " ".join(converter_name)
+            self.name = regularize_name(" ".join(converter_name))
         else:
             self.name = None
         self.delete_input = args.delete_input
@@ -109,14 +112,14 @@ class ConvertArgs:
 
             # Get the converter name from the arguments if it wasn't provided by -w/--with
             if not self.name:
-                self.name = " ".join(self.l_args)
+                self.name = regularize_name(" ".join(self.l_args))
 
             # For this operation, any other arguments can be ignored
             return
 
         # If not listing and a converter name wasn't supplied, use the default converter
         if not self.name:
-            self.name = CONVERTER_DEFAULT
+            self.name = regularize_name(CONVERTER_DEFAULT)
 
         # Quiet mode is equivalent to logging mode == LOGGING_NONE, so normalize them if either is set
         if self.quiet:
@@ -147,13 +150,14 @@ class ConvertArgs:
             os.makedirs(self._output_dir, exist_ok=True)
 
         # Check the converter is recognized
-        if self.name not in L_SUPPORTED_CONVERTERS:
+        if not converter_is_supported(self.name):
             msg = textwrap.fill(f"ERROR: Converter '{self.name}' not recognised", width=TERM_WIDTH)
             msg += f"\n\n{get_supported_converters()}"
             raise FileConverterInputException(msg, help=True, msg_preformatted=True)
-        elif self.name not in L_REGISTERED_CONVERTERS:
-            msg = textwrap.fill(f"ERROR: Converter '{self.name}' is not registered. It may be possible to register "
-                                "it by installing an appropriate binary for your platform.", width=TERM_WIDTH)
+        elif not converter_is_registered(self.name):
+            converter_name = get_supported_converter_class(self.name).name
+            msg = textwrap.fill(f"ERROR: Converter '{converter_name}' is not registered. It may be possible to "
+                                "register it by installing an appropriate binary for your platform.", width=TERM_WIDTH)
             msg += f"\n\n{get_supported_converters()}"
             raise FileConverterInputException(msg, help=True, msg_preformatted=True)
 
@@ -349,9 +353,10 @@ def detail_converter_use(args: ConvertArgs):
     """
 
     converter_info = get_converter_info(args.name)
-    converter_class = D_SUPPORTED_CONVERTERS[args.name]
+    converter_class = get_supported_converter_class(args.name)
+    converter_name = converter_class.name
 
-    print_wrap(f"{converter_info.name}: {converter_info.description} ({converter_info.url})", break_long_words=False,
+    print_wrap(f"{converter_name}: {converter_info.description} ({converter_info.url})", break_long_words=False,
                break_on_hyphens=False, newline=True)
 
     if converter_class.info:
@@ -362,10 +367,10 @@ def detail_converter_use(args: ConvertArgs):
     if args.from_format is not None and args.to_format is not None:
         qual = get_conversion_quality(args.name, args.from_format, args.to_format)
         if qual is None:
-            print_wrap(f"Conversion from '{args.from_format}' to '{args.to_format}' with {args.name} is not "
+            print_wrap(f"Conversion from '{args.from_format}' to '{args.to_format}' with {converter_name} is not "
                        "supported.", newline=True)
         else:
-            print_wrap(f"Conversion from '{args.from_format}' to '{args.to_format}' with {args.name} is "
+            print_wrap(f"Conversion from '{args.from_format}' to '{args.to_format}' with {converter_name} is "
                        f"possible with {qual.qual_str} conversion quality", newline=True)
             # If there are any potential issues with the conversion, print them out
             if qual.details:
@@ -385,7 +390,7 @@ def detail_converter_use(args: ConvertArgs):
                 optional_not: str = ""
             else:
                 optional_not: str = "not "
-            print_wrap(f"Conversion {to_or_from} {format_name} is {optional_not}supported by {args.name}.\n")
+            print_wrap(f"Conversion {to_or_from} {format_name} is {optional_not}supported by {converter_name}.\n")
 
         # List all possible formats, and which can be used for input and which for output
         s_all_formats: set[FormatInfo] = set(l_input_formats)
@@ -393,7 +398,7 @@ def detail_converter_use(args: ConvertArgs):
         l_all_formats: list[FormatInfo] = list(s_all_formats)
         l_all_formats.sort(key=lambda x: x.disambiguated_name.lower())
 
-        print_wrap(f"File formats supported by {args.name}:", newline=True)
+        print_wrap(f"File formats supported by {converter_name}:", newline=True)
         max_format_length = max([len(x.disambiguated_name) for x in l_all_formats])
         print(" "*(max_format_length+4) + "   INPUT  OUTPUT")
         print(" "*(max_format_length+4) + "   -----  ------")
@@ -472,13 +477,13 @@ def detail_converter_use(args: ConvertArgs):
     # Now at the end, bring up input/output-format-specific flags and options
     if mention_input_format and mention_output_format:
         print_wrap("For details on input/output flags and options allowed for specific formats, call:\n"
-                   f"{CL_SCRIPT_NAME} -l {args.name} -f <input_format> -t <output_format>")
+                   f"{CL_SCRIPT_NAME} -l {converter_name} -f <input_format> -t <output_format>")
     elif mention_input_format:
         print_wrap("For details on input flags and options allowed for a specific format, call:\n"
-                   f"{CL_SCRIPT_NAME} -l {args.name} -f <input_format> [-t <output_format>]")
+                   f"{CL_SCRIPT_NAME} -l {converter_name} -f <input_format> [-t <output_format>]")
     elif mention_output_format:
         print_wrap("For details on output flags and options allowed for a specific format, call:\n"
-                   f"{CL_SCRIPT_NAME} -l {args.name} -t <output_format> [-f <input_format>]")
+                   f"{CL_SCRIPT_NAME} -l {converter_name} -t <output_format> [-f <input_format>]")
 
 
 def list_supported_formats(err=False):
@@ -537,7 +542,7 @@ def detail_format(format_name: str):
     """Prints details on a format
     """
 
-    l_format_info: list[FormatInfo] = get_format_info(format_name, which="all")
+    l_format_info = get_format_info(format_name, which="all")
 
     if len(l_format_info) == 0:
         print_wrap(f"ERROR: Format '{format_name}' not recognised", err=True, newline=True)
@@ -600,9 +605,11 @@ def detail_formats_and_possible_converters(from_format: str, to_format: str):
         l_conversions_matching_formats = [x for x in l_possible_conversions
                                           if x[1] == possible_from_format and x[2] == possible_to_format]
 
-        l_possible_registered_converters = [x[0] for x in l_conversions_matching_formats
+        l_possible_registered_converters = [get_registered_converter_class(x[0]).name
+                                            for x in l_conversions_matching_formats
                                             if x[0] in L_REGISTERED_CONVERTERS]
-        l_possible_unregistered_converters = [x[0] for x in l_conversions_matching_formats
+        l_possible_unregistered_converters = [get_supported_converter_class(x[0]).name
+                                              for x in l_conversions_matching_formats
                                               if x[0] in L_SUPPORTED_CONVERTERS and x[0] not in L_REGISTERED_CONVERTERS]
 
         print()
@@ -640,7 +647,7 @@ def get_supported_converters():
     l_converters: list[str] = []
     any_not_registered = False
     for converter_name in L_SUPPORTED_CONVERTERS:
-        converter_text = converter_name
+        converter_text = get_supported_converter_class(converter_name).name
         if converter_name not in L_REGISTERED_CONVERTERS:
             converter_text += f" {MSG_NOT_REGISTERED}"
             any_not_registered = True

psdi_data_conversion/static/content/index-versions/psdi-common-footer.html

@@ -17,16 +17,20 @@
       </ul>
       <ul class="footer__col footer__items clean-list">
         <li>
-          <img class="lm-only" src="static/img/ukri-logo-lighttext.png"
-            alt="UKRI logo">
-          <img class="dm-only" src="static/img/ukri-logo-darktext.png"
-            alt="UKRI logo">
+          <a href="https://www.ukri.org/">
+            <img class="lm-only" src="static/img/ukri-logo-lighttext.png"
+              alt="UKRI logo">
+            <img class="dm-only" src="static/img/ukri-logo-darktext.png"
+              alt="UKRI logo">
+          </a>
         </li>
         <li>
-          <img class="lm-only" src="static/img/ukri-epsr-logo-lighttext.png"
-            alt="UKRI EPSR logo">
-          <img class="dm-only" src="static/img/ukri-epsr-logo-darktext.png"
-            alt="UKRI EPSR logo">
+          <a href="https://www.ukri.org/councils/epsrc/">
+            <img class="lm-only" src="static/img/ukri-epsr-logo-lighttext.png"
+              alt="UKRI EPSR logo">
+            <img class="dm-only" src="static/img/ukri-epsr-logo-darktext.png"
+              alt="UKRI EPSR logo">
+          </a>
         </li>
       </ul>
       <div class="footer__hline small-screen-only">
@@ -44,7 +48,7 @@
         <hr>
       </div>
       <ul class="footer__col footer__items clean-list">
-        <li><a href="https://psdistg.wpengine.com/">PSDI Home</a></li>
+        <li><a href="https://psdi.ac.uk/">PSDI Home</a></li>
         <li><a href="mailto:support@psdi.ac.uk">Contact Us</a></li>
         <li><a href="https://www.psdi.ac.uk/privacy/">Privacy</a></li>
         <li><a href="https://www.psdi.ac.uk/terms-and-conditions/">Terms and Conditions</a></li>

psdi_data_conversion/static/content/index-versions/psdi-common-header.html

@@ -4,7 +4,7 @@
 <div class="max-width-box navbar">
   <div class="header-left">
     <div class="navbar__brand">
-      <a class="navbar__logo" href="https://psdistg.wpengine.com/">
+      <a class="navbar__logo" href="https://psdi.ac.uk/">
         <img src="static/img/psdi-logo-darktext.png" alt="PSDI logo"
           class="lm-only">
         <img src="static/img/psdi-logo-lighttext.png" alt="PSDI logo"

psdi_data_conversion/static/content/psdi-common-footer.html

@@ -17,16 +17,20 @@
       </ul>
       <ul class="footer__col footer__items clean-list">
         <li>
-          <img class="lm-only" src="../img/ukri-logo-lighttext.png"
-            alt="UKRI logo">
-          <img class="dm-only" src="../img/ukri-logo-darktext.png"
-            alt="UKRI logo">
+          <a href="https://www.ukri.org/">
+            <img class="lm-only" src="../img/ukri-logo-lighttext.png"
+              alt="UKRI logo">
+            <img class="dm-only" src="../img/ukri-logo-darktext.png"
+              alt="UKRI logo">
+          </a>
         </li>
         <li>
-          <img class="lm-only" src="../img/ukri-epsr-logo-lighttext.png"
-            alt="UKRI EPSR logo">
-          <img class="dm-only" src="../img/ukri-epsr-logo-darktext.png"
-            alt="UKRI EPSR logo">
+          <a href="https://www.ukri.org/councils/epsrc/">
+            <img class="lm-only" src="../img/ukri-epsr-logo-lighttext.png"
+              alt="UKRI EPSR logo">
+            <img class="dm-only" src="../img/ukri-epsr-logo-darktext.png"
+              alt="UKRI EPSR logo">
+          </a>
         </li>
       </ul>
       <div class="footer__hline small-screen-only">
@@ -44,7 +48,7 @@
         <hr>
       </div>
       <ul class="footer__col footer__items clean-list">
-        <li><a href="https://psdistg.wpengine.com/">PSDI Home</a></li>
+        <li><a href="https://psdi.ac.uk/">PSDI Home</a></li>
         <li><a href="mailto:support@psdi.ac.uk">Contact Us</a></li>
         <li><a href="https://www.psdi.ac.uk/privacy/">Privacy</a></li>
         <li><a href="https://www.psdi.ac.uk/terms-and-conditions/">Terms and Conditions</a></li>

psdi_data_conversion/static/content/psdi-common-header.html

@@ -4,7 +4,7 @@
 <div class="max-width-box navbar">
   <div class="header-left">
     <div class="navbar__brand">
-      <a class="navbar__logo" href="https://psdistg.wpengine.com/">
+      <a class="navbar__logo" href="https://psdi.ac.uk/">
         <img src="../img/psdi-logo-darktext.png" alt="PSDI logo"
           class="lm-only">
         <img src="../img/psdi-logo-lighttext.png" alt="PSDI logo"