Improved support for stringify documents. Added support for stdin/stdout file processing

toMkdocs/markdownTools.py

@@ -9,7 +9,7 @@
 """ Various tools for markdown processing
 """
 from __future__ import annotations
-from typing import Callable
+from typing import Callable, Optional
 
 from dataclasses import dataclass
 import base64, hashlib
@@ -69,6 +69,7 @@ class LineType(Enum):
 	TABLESEPARATOR = auto()
 	TABLEROW = auto()
 	TABLELASTROW = auto()
+	RAWHTML = auto()
 
 
 @dataclass
@@ -78,6 +79,16 @@ class Line:
 	lineType:LineType = LineType.TEXT
 
 
+	def __str__(self) -> str:
+		"""	Return the line as a string. """
+		return self.text
+	
+
+	def __repr__(self) -> str:
+		"""	Return the line as a string. """
+		return self.__str__()
+
+
 @dataclass
 class Clause:
 	"""	Represents a clause in the markdown file. """
@@ -176,6 +187,18 @@ class Clause:
 				The number of characters in the clause.
 		"""
 		return sum([ len(l.text.strip()) for l in self.lines ])
+	
+
+	def __str__(self) -> str:
+		"""	Return the clause as a string. """
+		return ''.join([str(l) for l in self.lines ])
+	
+
+	def __repr__(self) -> str:
+		"""	Return the clause as a string. """
+		return self.__str__()
+
+
 
 class Footnote:
 	"""	Represents a footnote in the markdown file. """
@@ -361,12 +384,23 @@ class Document:
 			clause.lines = lines
 
 
+	def __str__(self) -> str:
+		"""	Return the document as a string. """
+		return '\n'.join([ str(c) for c in self.clauses ])
+	
+
+	def __repr__(self) -> str:
+		"""	Return the document as a string. """
+		return self.__str__()
+
 
-def analyseMarkdown(filename:str) -> Document:
+def analyseMarkdown(filename:Optional[str]=None, inLines:Optional[list[str]]=None) -> Document:
 	"""	Analyse the markdown file and split it into clauses.
+		Either the filename or the inLines must be provided.
 
 		Args:
 			filename: The name of the markdown file.
+			inLines: The lines of the markdown file.
 
 		Returns:
 			The document object.
@@ -388,9 +422,7 @@ def analyseMarkdown(filename:str) -> Document:
 			printDebug(htmltable)
 		except Exception as e:
 			printError(f"Error: {e}")
-		# TODO move this outside of the analyseMarkdown function !!!
-		for row in htmltable:
-			outClauses[-1].append(Line(row, LineType.TABLEROW))
+		outClauses[-1].append(Line(htmltable, LineType.RAWHTML))
 		gridTable = ''
 
 
@@ -398,8 +430,13 @@ def analyseMarkdown(filename:str) -> Document:
 
 	# Read the file.
 	# Note: We use utf-8 and replace errors to avoid problems with special or unknown characters.
-	with open(filename, 'r', encoding = 'utf-8', errors = 'replace') as file:
-		inLines = file.readlines()
+	if filename and not inLines:
+		with open(filename, 'r', encoding = 'utf-8', errors = 'replace') as file:
+			inLines = file.readlines()
+	elif not filename and inLines:
+		pass
+	else:
+		raise ValueError('Either the filename or the lines must be provided.')
 	
 	# The list of clauses. The first clause contains the text before the first heading.
 	outClauses:list[Clause] = [Clause(0, '', '', [])]