src/formatitko/formatitko.py

@@ -14,9 +14,8 @@ from .images import ImageProcessor
 from .output_generator import OutputGenerator
 from .html_generator import HTMLGenerator
 from .transform_processor import TransformProcessor
-from .pandoc_processor import PandocProcessor
 
-from panflute import convert_text
+from .mj_show import show
 
 def main():
 	# Initialize command line arguments
@@ -25,10 +24,8 @@ def main():
 	parser.add_argument("-p", "--img-public-dir", help="Directory to put processed images into. The program will overwrite images, whose dependencies are newer.", default="public")
 	parser.add_argument("-c", "--img-cache-dir", help="Directory to cache processed images and intermediate products. The program will overwrite files, whose dependencies are newer.", default="cache")
 	parser.add_argument("-i", "--img-web-path", help="Path where the processed images are available on the website.", default="/")
-	parser.add_argument("-w", "--output-html", help="The HTML file (for Web) to write into.")
+	parser.add_argument("-w", "--output-html", help="The HTML file (for Web) to write into.", default="output.html")
-	parser.add_argument("-t", "--output-tex", help="The TEX file to write into.")
+	parser.add_argument("-t", "--output-tex", help="The TEX file to write into.", default="output.tex")
-	parser.add_argument("-m", "--output-md", help="The Markdown file to write into. (Uses pandoc to generate markdown)")
-	parser.add_argument("-j", "--output-json", help="The JSON file to dump the pandoc-compatible AST into.")
 	parser.add_argument("input_filename", help="The markdown file to process.")
 	parser.add_argument("--debug", action='store_true')
 	args = parser.parse_args()
@@ -36,30 +33,44 @@ def main():
 	# just connect to an existing one. For formátíking many files in a row.
 
 	# Use panflute to parse the input MD file
-	doc = import_md(open(args.input_filename, "r").read())
+	#doc1 = import_md(open(args.input_filename, "r").read())
+	doc2 = import_md(open(args.input_filename, "r").read())
 
 	if args.debug:
-		OutputGenerator(sys.stdout).generate(doc)
+		print(show(doc1))
 
-	doc = TransformProcessor(args.input_filename).transform(doc)
+	# The language metadatum is important, so it's read before transformation and
+	# then attached to a group inside the Doc
+	#language = doc1.get_metadata("lang", None, True)
+	#context = Context(doc1, args.input_filename)
+
+	# Transform the document. This includes all the fancy formatting this software does.
+	#doc1 = doc1.walk(transform, context)
+
+	# Now wrap the document contents in a group, which is able to pop its language
+	# setting out to TeX
+	#doc1.content = [BlockGroup(*doc1.content, context=context, metadata={"lang":language})]
+
+	doc2 = TransformProcessor(args.input_filename).transform(doc2)
 
 	# Initialize the image processor (this just keeps some basic state)
 	imageProcessor = ImageProcessor(args.img_public_dir, args.img_web_path, args.img_cache_dir, *args.img_lookup_dirs)
 
-	if args.output_html is not None:
 	# Initialize KaTeX client (this runs the node app and connects to a unix socket)
 	with KatexClient() as katexClient:
-			HTMLGenerator(open(args.output_html, "w"), katexClient, imageProcessor).generate(doc)
+		# Generate HTML and TeX out of the transformed document
+		#open(args.output_html, "w").write(html(doc, katexClient, imageProcessor))
+		#open(args.output_tex, "w").write(tex(doc, imageProcessor))
+		HTMLGenerator(sys.stdout, katexClient, imageProcessor).generate(doc2)
+		#OutputGenerator(open("/tmp/doc1", "w")).generate(doc1)
+		#OutputGenerator(open("/tmp/doc2", "w")).generate(doc2)
 
-	if args.output_md is not None:
+	from panflute import convert_text
-		open(args.output_md, "w").write(convert_text(PandocProcessor().transform(doc), input_format="panflute", output_format="markdown"))
+	from .pandoc_processor import PandocProcessor
-
+	open("/tmp/bruhecek.md", "w").write(convert_text(PandocProcessor().transform(doc2), input_format="panflute", output_format="markdown"))
-	if args.output_json is not None:
-		open(args.output_json, "w").write(convert_text(PandocProcessor().transform(doc), input_format="panflute", output_format="json"))
 
 	if args.debug:
-		print("-----------------------------------")
+		print(show(doc))
-		OutputGenerator(sys.stdout).generate(doc)
 
 
 if __name__ == "__main__":

src/formatitko/pandoc_processor.py

@@ -2,12 +2,14 @@ from .nop_processor import NOPProcessor
 from panflute import Div, Span, Null, Str, Plain, Quoted
 from .context import Group, InlineGroup, BlockGroup
 from .elements import FQuoted
-from .whitespace import NBSP
 from .nop_processor import ELCl
 
 from typing import Callable
 
 import sys
+def eprint(*args, **kwargs):
+	print(*args, **kwargs, file=sys.stderr)
+
 class PandocProcessor(NOPProcessor):
 
 	def get_posttransformers(self) -> list[Callable[[ELCl],ELCl]]:
@@ -36,6 +38,3 @@ class PandocProcessor(NOPProcessor):
 
 	def transform_FQuoted(self, e: FQuoted) -> Quoted:
 		return Quoted(*e.content)
-
-	def transform_NBSP(self, e: NBSP) -> Str:
-		return Str(" ") # Unicode nbsp