Commit 39715c63 authored by Miguel Angel Reina Ortega's avatar Miguel Angel Reina Ortega
Browse files

Allow + and | delimiters as part of cell content

parent 0e41a003

generateSpecWebSite/gridTableTools.py

+74 −9
Original line number Original line Diff line number Diff line
@@ -207,7 +207,9 @@ def parseGridTableWithSpans(gridTable:str) -> tuple[GridTableRowList, GridTableR 
			while delimiterStart == None:

			while delimiterStart == None:

				delimiterStart = row[colI - 1].position if colI > 0 else 0

				delimiterStart = row[colI - 1].position if colI > 0 else 0

				colI -= 1

				colI -= 1

			positions = [line.find(delimiter, delimiterStart + 1) for delimiter in "|+" if delimiter in line[delimiterStart + 1:]]

			

			#positions = [line.find(delimiter, delimiterStart + 1) for delimiter in "|+" if delimiter in line[delimiterStart + 1:]]

			positions = [match.start() for match in matchGridTableDelimiter.finditer(line, delimiterStart + 1)]

			position = min(positions) if positions else -1

			position = min(positions) if positions else -1

			if position > delimiterPositions[j]:  # Colspan to be increased

			if position > delimiterPositions[j]:  # Colspan to be increased

				row[columnIndex].colspan += 1

				row[columnIndex].colspan += 1
@@ -240,7 +242,7 @@ def parseGridTableWithSpans(gridTable:str) -> tuple[GridTableRowList, GridTableR 
		printDebug(f'\nChecking line: "{line}"')

		printDebug(f'\nChecking line: "{line}"')

		printDebug(f'Expected delimiter positions: {delimiterPositions}')

		printDebug(f'Expected delimiter positions: {delimiterPositions}')

		

		

		# For full separator lines (only +)

		""" # For full separator lines (only +)

		if '+' in line and '|' not in line:

		if '+' in line and '|' not in line:

			currentPositions = [i for i, char in enumerate(line) if (char == '+' and i > 0)]

			currentPositions = [i for i, char in enumerate(line) if (char == '+' and i > 0)]

			printDebug(f'Full separator line - Found + at positions: {currentPositions}')

			printDebug(f'Full separator line - Found + at positions: {currentPositions}')
@@ -255,13 +257,53 @@ def parseGridTableWithSpans(gridTable:str) -> tuple[GridTableRowList, GridTableR 
			  		   for pos in currentPositions)

			  		   for pos in currentPositions)

		

		

		# For partial separators (mix of + and |)

		# For partial separators (mix of + and |)

		currentPositions = [i for i, char in enumerate(line) if (char in delimiters and i > 0)]

		if matchGridTableBodySeparator.match(line):

			# Find all delimiter positions that are not escaped

			currentPositions = []

			i = 0

			while i < len(line):

				if i > 0 and line[i-1] == '\\':  # Skip escaped delimiters

					i += 1

					continue

				if line[i] in delimiters:

					currentPositions.append(i)

				i += 1

			

			printDebug(f'Partial separator - Found delimiters at positions: {currentPositions}')

			printDebug(f'Partial separator - Found delimiters at positions: {currentPositions}')

			printDebug(f'Characters at those positions: {[line[pos] for pos in currentPositions]}')

			printDebug(f'Characters at those positions: {[line[pos] for pos in currentPositions]}')

			return all(delimiterPositions[-1] in currentPositions and line.startswith(('+', '|')) and pos in delimiterPositions 

			return all(delimiterPositions[-1] in currentPositions and line.startswith(('+', '|')) and pos in delimiterPositions 

					   for pos in currentPositions)

					   for pos in currentPositions)

		

		

	separatorIndices = [i for i, line in enumerate(lines) if isSeparator(line)]

		# For data lines (starting with |)

		if line.startswith('|') and not matchGridTableBodySeparator.match(line):

			# Find all | positions that are not escaped (+ doesn't need escaping, but | does)

			currentPositions = []

			i = 0

			while i < len(line):

				if i > 0 and line[i-1] == '\\' and line[i] == '|':  # Skip escaped |

					i += 1

					continue

				if line[i] == '|':

					currentPositions.append(i)

				i += 1

			

			printDebug(f'Data line - Found | at positions: {currentPositions}')

			return all(delimiterPositions[-1] in currentPositions and line.startswith("|") and pos in delimiterPositions 

			  		    for pos in currentPositions)"""

		#for match in re.finditer(r'(?<!\\)\||(?=\+:?-+:?\+)\+|(?<![^-:])\+', line):

		currentPositions = []

		for match in matchGridTableDelimiter.finditer(line):

			if match.start() > 0:  # Skip the first position

				currentPositions.append(match.start())

		

		printDebug(f'Partial separator - Found delimiters at positions: {currentPositions}')

		printDebug(f'Characters at those positions: {[line[pos] for pos in currentPositions]}')

		return all(delimiterPositions[-1] in currentPositions and line.startswith(('+', '|')) and pos in delimiterPositions 

				   for pos in currentPositions)

		

		return False



	separatorIndices = [i for i, line in enumerate(lines) if isSeparator(line.rstrip())]





	if not separatorIndices:

	if not separatorIndices:

		raise ValueError('No valid separators found in the provided grid table.')

		raise ValueError('No valid separators found in the provided grid table.')
@@ -285,7 +327,7 @@ def parseGridTableWithSpans(gridTable:str) -> tuple[GridTableRowList, GridTableR 
	dataRows:GridTableRowList = []

	dataRows:GridTableRowList = []





	for index in separatorIndices:

	for index in separatorIndices:

		if matchGridTableHeaderSeparator.match(lines[index]):

		if matchGridTableHeaderSeparator.match(lines[index].rstrip()):

			hasHeader = True

			hasHeader = True

			headerSeparatorIndex = index

			headerSeparatorIndex = index

			parts = re.split(r'\+', lines[index].strip('+'))

			parts = re.split(r'\+', lines[index].strip('+'))
@@ -352,7 +394,15 @@ def parseGridTableWithSpans(gridTable:str) -> tuple[GridTableRowList, GridTableR 
					if not checkDelimiterAlignment(line, delimiterPositions):

					if not checkDelimiterAlignment(line, delimiterPositions):

						raise ValueError(f'Misaligned delimiters in separator row: {line}')

						raise ValueError(f'Misaligned delimiters in separator row: {line}')

					

					

					parts = re.split(r'\s*\+\s*', line.strip('+'))

					# Split by delimiters

					parts = []

					matches = list(matchGridTableDelimiter.finditer(line))

					pos = 0

					for match in matches:

						if match.start() > pos:

							parts.append(line[pos+1:match.start()])

						pos = match.start()



					delimiterIndex = 0

					delimiterIndex = 0





					rows.append(GridRow(numberOfColumns))

					rows.append(GridRow(numberOfColumns))
@@ -384,7 +434,14 @@ def parseGridTableWithSpans(gridTable:str) -> tuple[GridTableRowList, GridTableR 
						if not checkDelimiterAlignment(line, delimiterPositions):

						if not checkDelimiterAlignment(line, delimiterPositions):

							raise ValueError(f'Misaligned delimiters in partial separator: {line}')

							raise ValueError(f'Misaligned delimiters in partial separator: {line}')





						parts = re.split(r'[\|\+]', line.strip('|').strip('+'))  # (?<!\\)[\|\+]

						# Split by delimiters

						parts = []

						matches = list(matchGridTableDelimiter.finditer(line))

						pos = 0

						for match in matches:

							if match.start() > pos:

								parts.append(line[pos+1:match.start()])

							pos = match.start()





						#Add another row, set delimiters for each cell

						#Add another row, set delimiters for each cell

						rows.append(GridRow(numberOfColumns))

						rows.append(GridRow(numberOfColumns))
@@ -446,7 +503,15 @@ def parseGridTableWithSpans(gridTable:str) -> tuple[GridTableRowList, GridTableR 
							raise ValueError(f'More cells than columns found ({len(parts)} {numberOfColumns})')

							raise ValueError(f'More cells than columns found ({len(parts)} {numberOfColumns})')

						

						

					else: # Data row

					else: # Data row

						cellsContent = re.split(r'\|', line.strip('|'))

						#cellsContent = re.split(r'\|', line.strip('|'))

						#Split by delimiters

						cellsContent = []

						matches = list(matchGridTableDelimiter.finditer(line))

						pos = 0

						for match in matches:

							if match.start() > pos:

								cellsContent.append(line[pos+1:match.start()])

							pos = match.start()





						# Add delimiter alignment check

						# Add delimiter alignment check

						if not checkDelimiterAlignment(line, delimiterPositions):

						if not checkDelimiterAlignment(line, delimiterPositions):

generateSpecWebSite/regexMatches.py

+5 −5
Original line number Original line Diff line number Diff line
@@ -22,11 +22,11 @@ markdownLink = re.compile(r'[^!]\[[^\]]*\]\((#[^)]*)\)', re.IGNORECASE) 
matchCodefenceStart = re.compile(r'\s*```\s?.*', re.IGNORECASE)

matchCodefenceStart = re.compile(r'\s*```\s?.*', re.IGNORECASE)

matchCodefenceEnd = re.compile(r'\s*```\s?', re.IGNORECASE)

matchCodefenceEnd = re.compile(r'\s*```\s?', re.IGNORECASE)

matchGridTable = re.compile(r'^\s*\+-.*\+\s$', re.IGNORECASE)

matchGridTable = re.compile(r'^\s*\+-.*\+\s$', re.IGNORECASE)

matchGridTableBodySeparator = re.compile(r'.*\+([:-]+\+)+.*$', re.IGNORECASE)

matchGridTableBodySeparator = re.compile(r'^[+|].*(\+[:-]+\+($|.*[+|]$))', re.IGNORECASE)

matchGridTableBodySeparatorLine = re.compile(r'[-:]+$', re.IGNORECASE)

matchGridTableBodySeparatorLine = re.compile(r'^:?-+:?$', re.IGNORECASE)

matchGridTableHeaderSeparator = re.compile(r'.*\+([=:]+\+)+.*$', re.IGNORECASE)

matchGridTableHeaderSeparator = re.compile(r'^\+([=:]+\+)+$', re.IGNORECASE)

matchGridTableSeparator = re.compile(r'\s*\+([-:=]+\+)+\s*$', re.IGNORECASE)

matchGridTableSeparator = re.compile(r'^\+([-:=]+\+)+$', re.IGNORECASE)

matchGridTableBodySeparator = re.compile(r'.*\+([:-]+\+)+.*$', re.IGNORECASE)

matchGridTableDelimiter = re.compile(r'(?<!\\)\||(?=\+:?[-=]+:?\+)\+|(?<![^-=:])\+', re.IGNORECASE)

matchHeader = re.compile(r'(#+)\s+(.*)', re.IGNORECASE)

matchHeader = re.compile(r'(#+)\s+(.*)', re.IGNORECASE)

matchHeaderNumber = re.compile(r'\b[A-Za-z0-9]\d*(\.\d+)*\b', re.IGNORECASE)

matchHeaderNumber = re.compile(r'\b[A-Za-z0-9]\d*(\.\d+)*\b', re.IGNORECASE)

matchListInContent = re.compile(r'^(?:\s*(P<marker>[-*+]|\s*\d+\.))\s+(P<content>.+)$', re.IGNORECASE)

matchListInContent = re.compile(r'^(?:\s*(P<marker>[-*+]|\s*\d+\.))\s+(P<content>.+)$', re.IGNORECASE)