Improved parsing and generation of tables. Corrected various wrong... (f46a2a97) · Commits · Centre for Testing and Interoperability / Markdown specifications development / spec2md

spec2md.py

+37 −19

Original line number	Original line	Diff line number	Diff line
	@@ -52,8 +52,8 @@ unreferencedSubDir = 'unreferenced'
	_linebreak = '<br />'		_linebreak = '<br />'
	_entityLt = '<'		_entityLt = '<'
	_nbsp = ' '		_nbsp = ' '
	_tocInsertPoint = '__t_o_c__'		_tocInsertPoint = '~~t~o~c~~'
	_captionMarker = '__CAPTION__'		_captionMarker = '~~CAPTION~~'


	# https://learn.microsoft.com/en-us/dotnet/api/documentformat.openxml.wordprocessing?view=openxml-2.8.1		# https://learn.microsoft.com/en-us/dotnet/api/documentformat.openxml.wordprocessing?view=openxml-2.8.1
	@@ -335,6 +335,8 @@ def processDocuments(documents:list[str], outDirectory:str, skipImageConversion:
	_bold = '**'		_bold = '**'
	case 'i' if ep.attrib.get(_val, 'true') == 'true':		case 'i' if ep.attrib.get(_val, 'true') == 'true':
	_italics = '_'		_italics = '_'
			# case _:
			# _print(f'[yellow]unsupported style: {ep.tag}')

	# Strip white spaces if bold or italics		# Strip white spaces if bold or italics
	_s = str(toMD(str(element.text))).strip() if _bold or _italics else str(toMD(str(element.text)))		_s = str(toMD(str(element.text))).strip() if _bold or _italics else str(toMD(str(element.text)))
	@@ -342,11 +344,13 @@ def processDocuments(documents:list[str], outDirectory:str, skipImageConversion:
	_s = _s.replace('_', '\\_')		_s = _s.replace('_', '\\_')
	_s = _s.replace('', '\\')		_s = _s.replace('', '\\')
	# Add trailing white space when bold or italics		# Add trailing white space when bold or italics
	_prefix = ' ' if _bold or _italics else ''		_postfix = ' ' if _bold or _italics else ''
	_result += f'{_bold}{_italics}{_s}{_italics}{_bold}{_prefix}'		_result += f'{_bold}{_italics}{_s}{_italics}{_bold}{_postfix}'
			# print(_result)

	case 'br':		case 'br':
	_result += _linebreak		_result += _linebreak

	case 'bookmarkStart' \| 'bookmarkEnd': # TODO ?		case 'bookmarkStart' \| 'bookmarkEnd': # TODO ?
	pass		pass

	@@ -366,17 +370,18 @@ def processDocuments(documents:list[str], outDirectory:str, skipImageConversion:
	blip = element.findall('ns1:inline/ns3:graphic/ns3:graphicData/ns4:pic/ns4:blipFill/ns3:blip',		blip = element.findall('ns1:inline/ns3:graphic/ns3:graphicData/ns4:pic/ns4:blipFill/ns3:blip',
	namespaces = {		namespaces = {
	'ns1' : 'http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing',		'ns1' : 'http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing',
	'ns3' : wns,		'ns3' : 'http://schemas.openxmlformats.org/drawingml/2006/main',
	'ns4' : 'http://schemas.openxmlformats.org/drawingml/2006/picture',		'ns4' : 'http://schemas.openxmlformats.org/drawingml/2006/picture',
	})		})
	if blip and \		if blip and \
	(rId := blip[0].attrib.get('{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed')) and \		(rId := blip[0].attrib.get('{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed')) and \
	(mediaFile := mediaRelations.get(rId)):		(mediaFile := mediaRelations.get(rId)):
	referencedImages.append(Path(mediaFile).stem) # Add to referenced files		mediaFilePath = Path(mediaFile)
	if docConfig.renameEMFExtension and mediaFile.lower().endswith('.emf'):		referencedImages.append(mediaFilePath.stem) # Add to referenced files
	mediaFile = str(Path(mediaFile).with_suffix(f'.{docConfig.renameEMFExtension}'))		if docConfig.renameEMFExtension and mediaFilePath.suffix.lower() == '.emf':
	_print(f'[yellow]Renaming EMF file reference to "{mediaFile}"')		mediaFilePath = mediaFilePath.with_suffix(f'.{docConfig.renameEMFExtension}')
	_result += f'![{_captionMarker}]({mediaFile})'		_print(f'[yellow]Renaming EMF file reference to "{str(mediaFilePath)}"')
			_result += f'![{_captionMarker}]({mediaFilePath.as_posix()})' # image reference as posix path
	# else:		# else:
	# _print(blip)		# _print(blip)

	@@ -423,10 +428,10 @@ def processDocuments(documents:list[str], outDirectory:str, skipImageConversion:
	case Paragraph(): # type: ignore[misc]		case Paragraph(): # type: ignore[misc]
	return _parseXML(ET.fromstring(elem._p.xml))		return _parseXML(ET.fromstring(elem._p.xml))
	case _Cell(): # type: ignore[misc]		case _Cell(): # type: ignore[misc]
	result = ''		# Iterate over all paragraphs in the cell and parse them
	for p in elem.paragraphs:		# Create a list of parsed paragraphs and join them with linebreaks
	result += _parseXML(ET.fromstring(p._p.xml), True)		return '<br />'.join([ _parseXML(ET.fromstring(p._p.xml), True).rstrip()
	return result		for p in elem.paragraphs ])
	case _:		case _:
	return ''		return ''

	@@ -614,7 +619,7 @@ def processDocuments(documents:list[str], outDirectory:str, skipImageConversion:
	# Table Caption		# Table Caption
	elif style in docConfig.tablecaption:		elif style in docConfig.tablecaption:
	lines.append('')		lines.append('')
	lines.append(f'{replaceNL(text).strip()}')		caption = replaceNL(text).strip()
	anchor = f'<a name="table_{caption[6:].split(":")[0].strip()}"></a>' if caption.startswith('Table ') and ':' in caption else ''		anchor = f'<a name="table_{caption[6:].split(":")[0].strip()}"></a>' if caption.startswith('Table ') and ':' in caption else ''
	lines.append(f'{caption}{anchor}')		lines.append(f'{caption}{anchor}')

	@@ -679,12 +684,16 @@ def processDocuments(documents:list[str], outDirectory:str, skipImageConversion:

	# Warning if this is a single-row table		# Warning if this is a single-row table
	if nrRows == 1:		if nrRows == 1:
	_print(f'[red]Single-row table found. Consider replacing it in the original document:\n{rows[0]}')		_print(f'[red]Single-row table found. Such tables cannot be converted to markdown.[/red] Please consider to change the following table in the original document:\n[grey39]{rows[0]}', highlight = False)

	lines.append('') # Add an empty line before a table		lines.append('') # Add an empty line before a table
	for idx, row in enumerate(rows):		for idx, row in enumerate(rows):

			# Check for a table caption and add separator line
	if idx == 1:		if idx == 1:
	lines.append('-'.join('\|' * (len(row) + 1) ))		lines.append('-'.join('\|' * (len(row) + 1) ))

			# Add table row
	lines.append(f'\|{"\|".join(row)}\|'		lines.append(f'\|{"\|".join(row)}\|'
	.replace('\n', _linebreak)) # replace line breaks in cells		.replace('\n', _linebreak)) # replace line breaks in cells
	lines.append('') # Add another empty line after a table		lines.append('') # Add another empty line after a table
	@@ -719,7 +728,7 @@ def processDocuments(documents:list[str], outDirectory:str, skipImageConversion:
	line = lines[i]		line = lines[i]
	line = line.replace('__', '')		line = line.replace('__', '')
	line = line.replace('****', '')		line = line.replace('****', '')
	line = line.replace(' ', ' ')		#line = line.replace(' ', ' ')
	lines[i] = line		lines[i] = line


	@@ -775,6 +784,15 @@ def processDocuments(documents:list[str], outDirectory:str, skipImageConversion:
	line = lines[i]		line = lines[i]
	lines[i] = re.sub(_referenceExpression, _repl, line) # type:ignore[arg-type]		lines[i] = re.sub(_referenceExpression, _repl, line) # type:ignore[arg-type]


			#
			# List unresolved CAPTION markers
			#
			for i in range(len(lines)):
			line = lines[i]
			if _captionMarker in line:
			_print(f'[yellow]Unresolved figure caption : \[{i}] "{line}"')

	#		#
	# Write produced Markdown file		# Write produced Markdown file
	#		#

Admin message