Started working on TeX output, minor bugfixes.

2 years ago · 1e9054a909
5 changed files with 135 additions and 14 deletions
--- a/formatitko.py
+++ b/formatitko.py
@ -9,8 +9,9 @@ from typing import List
 from transform import transform
 from util import *
 from context import Context
-from html import html
 from katex import KatexClient
+from html import html
+from tex import tex

 from mj_show import show

@ -25,3 +26,5 @@ print("---------------------")
 #print(convert_text(doc, input_format="panflute", output_format="markdown"))
 katexClient = KatexClient()
 open("output.html", "w").write("<head> <meta charset='utf-8'>    <link rel='stylesheet' href='https://cdn.jsdelivr.net/npm/katex@0.16.4/dist/katex.min.css' integrity='sha384-vKruj+a13U8yHIkAyGgK1J3ArTLzrFGBbBc0tDp4ad/EyewESeXE/Iv67Aj8gKZ0' crossorigin='anonymous'> </head>" + html(doc, katexClient))
+open("output.tex", "w").write(tex(doc))
+#print(tex(doc))
--- a/html.py
+++ b/html.py
@ -18,6 +18,9 @@ def html(e: Element, k: KatexClient, indent_level: int=0, indent_str: str="\t")
 	content_foot = ""
 	content_head = ""

+	if isinstance(e, Str):
+		return e.text.replace(" ", "&nbsp;")
+
 	tags = {
 		BulletList: "ul",
 		Doc: "main",
@ -56,7 +59,7 @@ def html(e: Element, k: KatexClient, indent_level: int=0, indent_str: str="\t")
 		Space: " ",
 		Null: "",
 		LineBreak: f"\n{indent_level*indent_str}<br>\n{indent_level*indent_str}",
-		SoftBreak: f"\n{indent_level*indent_str}<br>\n{indent_level*indent_str}",
+		SoftBreak: f" ",
 		HorizontalRule: f"{indent_level*indent_str}<hr>\n"
 	}
 	if type(e) in simple_string:
@ -165,9 +168,6 @@ def html(e: Element, k: KatexClient, indent_level: int=0, indent_str: str="\t")
 			else:
 				return f'"{html(e.content, k, 0, "")}"'

-	if isinstance(e, Str):
-		return e.text.replace(" ", "&nbsp;")
-
 	if isinstance(e, Math):
 		formats = {
 			"DisplayMath": True,
@ -178,11 +178,17 @@ def html(e: Element, k: KatexClient, indent_level: int=0, indent_str: str="\t")
 		# and are forgotten in the next one.
 		return indent_level*indent_str + k.render(e.text, {"displayMode": formats[e.format]})

-	if isinstance(e, RawInline) and e.format == "html":
-		return e.text
+	if isinstance(e, RawInline):
+		if e.format == "html":
+			return e.text
+		else:
+			return ""

-	if isinstance(e, RawBlock) and e.format == "html":
-		return f'{e.text}\n'
+	if isinstance(e, RawBlock):
+		if e.format == "html":
+			return f'{e.text}\n'
+		else:
+			return ""

 	if isinstance(e, Inline):
 		return f"<{tag}{attributes}>{content_head}{html(e.content, k, 0, '')}{content_foot}</{tag}>"
--- a/test.md
+++ b/test.md
@ -56,6 +56,8 @@ A non-breakable&nbsp;space bro
 A lot              of spaces

 A text with some inline math: $\sum_{i=1}^nn^2$. Plus some display math:
+
+<!--
 $$
 \def\eqalign#1{\begin{align*}#1\end{align*}}
 \eqalign{
@ -63,7 +65,9 @@ $$
     x_1 - 3 x_2 + 2 x_3 &= 5 \cr
    -x_1 + 4 x_2 + \phantom{1} x_3 &= 2
 }
-$$
+$$-->
+
+---

 This should be seen by all^[This is a footnote].

@ -71,7 +75,7 @@ This should be seen by all^[This is a footnote].
 | Malostranské nám. 2/25
 | 118 00 Praha 1

-TODO:
+To Do:

 - buy eggs
 - buy milk
--- a/tex.py
+++ b/tex.py
@ -0,0 +1,106 @@
+from panflute import *
+
+from whitespace import NBSP
+from transform import FQuoted
+
+# Heavily inspired by: git://git.ucw.cz/labsconf2022.git
+def tex(e, indent_level: int=0, indent_str: str="\t") -> str:
+
+	content_foot = ""
+	content_head = ""
+
+	if isinstance(e, ListContainer):
+		return ''.join([tex(child, indent_level, indent_str) for child in e])
+
+	not_implemented = {
+		Citation: True,
+		Cite: True,
+		Definition: True,
+		DefinitionItem: True,
+		DefinitionList: True
+	}
+	if type(e) in not_implemented:
+		return f'% FIXME: {type(e)}s not implemented \n'
+
+	simple_string = {
+		NBSP: "~",
+		Space: " ",
+		Null: "",
+		LineBreak: f"\\\\",
+		SoftBreak: f" ",
+		HorizontalRule: "% TODO: hrule"
+	}
+	if type(e) in simple_string:
+		return simple_string[type(e)]
+
+	if isinstance(e, Str):
+		return e.text.replace(" ", "~").replace("&nbsp;", "~")
+
+	if isinstance(e, Para):
+		return tex(e.content, 0, "")+"\n\n"
+
+	if isinstance(e, Emph):
+		return f'{{\\it {tex(e.content, 0, "")}}}'
+
+	if isinstance(e, Strong):
+		return f'{{\\bf {tex(e.content, 0, "")}}}'
+	
+	if isinstance(e, FQuoted):
+		if e.style == "cs":
+			if e.quote_type == "SingleQuote":
+				return f'‚{tex(e.content, 0, "")}‘'
+			elif e.quote_type == "DoubleQuote":
+				return f'„{tex(e.content, 0, "")}“'
+		elif e.style == "en":
+			if e.quote_type == "SingleQuote":
+				return f'‘{tex(e.content, 0, "")}’'
+			elif e.quote_type == "DoubleQuote":
+				return f'“{tex(e.content, 0, "")}”'
+		else:
+			if e.quote_type == "SingleQuote":
+				return f'\'{tex(e.content, 0, "")}\''
+			elif e.quote_type == "DoubleQuote":
+				return f'"{tex(e.content, 0, "")}"'
+			else:
+				return f'"{tex(e.content, 0, "")}"'
+
+	if isinstance(e, Math):
+		if e.format == "DisplayMath":
+			return f'$${e.text}$$\n'
+		else:
+			return f'${e.text}$'
+
+	if isinstance(e, RawInline):
+		if e.format == "tex":
+			return e.text
+		else:
+			return ""
+
+	if isinstance(e, RawBlock):
+		if e.format == "tex":
+			return f'{e.text}\n'
+		else:
+			return ""
+	
+	if isinstance(e, Span) or isinstance(e, Plain):
+		return tex(e.content, 0, "")
+
+	if isinstance(e, Div):
+		return f'{tex(e.content, indent_level+1, indent_str)}'
+
+	if isinstance(e, Doc):
+		return tex(e.content, indent_level, indent_str)+"\n\\bye"
+
+	if isinstance(e, Inline):
+		return f"({e.tag}){content_head}{tex(e.content, 0, '')}{content_foot}(/{e.tag})"
+
+	out_str = ""
+	out_str = f"({e.tag}){{"
+	out_str += content_head
+	if hasattr(e, "_content"):
+		out_str += tex(e.content, indent_level+1, indent_str)
+	if hasattr(e, "text"):
+		out_str += e.text
+	out_str += f"{content_foot}}}\n\n"
+
+	return out_str
--- a/transform.py
+++ b/transform.py
@ -49,13 +49,15 @@ def transform(e: Element, c: Context) -> Element: # Returns next sibling element
 		quote_styles = {
 			"cs": "cs",
 			"en": "en",
-			"sk": "cs"
+			"sk": "cs",
+			None: None
 		}
 		e = FQuoted(*e.content, quote_type=e.quote_type, style=quote_styles[c.get_metadata("language")])

 	# Execute python code inside source code block
 	if isinstance(e, CodeBlock) and hasattr(e, "classes") and "python" in e.classes and "run" in e.classes:
-		e = executeCommand(e.text, None, c)
+		e = Div(*executeCommand(e.text, None, c))
+		e = e.walk(transform, c)

 	## Command defines
 	# possible TODO: def/longdef?
@ -91,6 +93,6 @@ def transform(e: Element, c: Context) -> Element: # Returns next sibling element
 		if not c.get_command(e.attributes["c"]):
 			raise NameError(f"Command not defined '{e.attributes['c']}'.")
 		e = e.replaceSelf(executeCommand(c.get_command(e.attributes["c"]), e, c))
-		e.walk(transform, c)
+		e = e.walk(transform, c)

 	return e