Jan Černohorský
9 months ago
3 changed files with 0 additions and 757 deletions
@ -1,311 +0,0 @@ |
|||
from panflute import * |
|||
from pygments import highlight |
|||
from pygments.lexers import get_lexer_by_name |
|||
from pygments.formatters import HtmlFormatter |
|||
from pygments.util import ClassNotFound |
|||
import os |
|||
from typing import Union |
|||
|
|||
from .whitespace import NBSP |
|||
from .elements import FQuoted |
|||
from .katex import KatexClient |
|||
from .util import inlinify |
|||
from .context import Group |
|||
from .images import ImageProcessor |
|||
|
|||
import warnings |
|||
warnings.warn("The html function has been deprecated, is left only for reference and will be removed in future commits. HTML_generator should be used in its place.", DeprecationWarning) |
|||
|
|||
def html(e: Union[Element, ListContainer], k: KatexClient, i: ImageProcessor, indent_level: int=0, indent_str: str="\t") -> str: |
|||
|
|||
warnings.warn("The html function has been deprecated, is left only for reference and will be removed in future commits. HTML_generator should be used in its place.", DeprecationWarning) |
|||
|
|||
# `only` attribute which makes transformed elements appear only in tex |
|||
# output or html output |
|||
if hasattr(e, "attributes") and "only" in e.attributes and e.attributes["only"] != "html": |
|||
return "" |
|||
|
|||
if isinstance(e, ListContainer): |
|||
return ''.join([html(child, k, i, indent_level, indent_str) for child in e]) |
|||
|
|||
# Bits from which the final element output is built at the end of this |
|||
# function. Most elements override this by returning their own output. |
|||
tag = e.tag.lower() |
|||
attributes = "" |
|||
content_foot = "" |
|||
content_head = "" |
|||
|
|||
if isinstance(e, Str): |
|||
return e.text.replace(" ", " ") |
|||
|
|||
# Most elements fit the general template at the end of the function, just |
|||
# need their html tag specified. |
|||
tags = { |
|||
BulletList: "ul", |
|||
Doc: "main", |
|||
Emph: "em", |
|||
Caption: "figcaption", |
|||
Para: "p", |
|||
Header: "h"+str(e.level) if isinstance(e, Header) else "", |
|||
LineBlock: "p", |
|||
ListItem: "li", |
|||
SmallCaps: "span", |
|||
Strikeout: "strike", |
|||
Subscript: "sub", |
|||
Superscript: "sup", |
|||
Underline: "u", |
|||
TableBody: "tbody", |
|||
TableHead: "thead", |
|||
TableFoot: "tfoot", |
|||
TableRow: "tr", |
|||
TableCell: "td", |
|||
} |
|||
if type(e) in tags: |
|||
tag = tags[type(e)] |
|||
|
|||
# These are also disabled in pandoc so they shouldn't appear in the AST at all. |
|||
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 -->' |
|||
|
|||
# Elements which can be represented by a simple string |
|||
simple_string = { |
|||
NBSP: " ", |
|||
Space: " ", |
|||
Null: "", |
|||
LineBreak: 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: |
|||
return simple_string[type(e)] |
|||
|
|||
if hasattr(e, "identifier") and e.identifier != "": |
|||
attributes += f' id="{e.identifier}"' |
|||
|
|||
if hasattr(e, "classes") and len(e.classes) != 0: |
|||
attributes += f' class="{" ".join(e.classes)}"' |
|||
|
|||
# Attributes are only passed down manually, because we use them internally. |
|||
# Maybe this should be a blocklist instead of an allowlist? |
|||
|
|||
# Overriding elements with their own returns |
|||
if isinstance(e, CodeBlock): |
|||
if len(e.classes) > 0 and (e.attributes["highlight"] == True or e.attributes["highlight"] == 'True'): |
|||
# Syntax highlighting using pygments |
|||
for cl in e.classes: |
|||
try: |
|||
lexer = get_lexer_by_name(cl) |
|||
except ClassNotFound: |
|||
continue |
|||
break |
|||
else: |
|||
print(f"WARN: Syntax highligher does not have lexer for element with these classes: {e.classes}") |
|||
formatter = HtmlFormatter(style=e.attributes["style"]) |
|||
result = highlight(e.text, lexer, formatter) |
|||
return f'{result}' |
|||
else: |
|||
return f'<pre>{e.text}</pre>' |
|||
|
|||
if isinstance(e, Doc): |
|||
formatter = HtmlFormatter(style=e.get_metadata("highlight-style") if e.get_metadata("highlight-style") is not None else "default") |
|||
content_head = f'<style>{formatter.get_style_defs(".highlight")}</style>' |
|||
|
|||
if isinstance(e, Image): |
|||
url = e.url |
|||
|
|||
# Attributes → image processor args |
|||
additional_args = {} |
|||
if "file-width" in e.attributes: |
|||
additional_args["width"] = int(e.attributes["file-width"]) |
|||
if "file-height" in e.attributes: |
|||
additional_args["height"] = int(e.attributes["file-height"]) |
|||
if "file-quality" in e.attributes: |
|||
additional_args["quality"] = int(e.attributes["file-quality"]) |
|||
if "file-dpi" in e.attributes: |
|||
additional_args["dpi"] = int(e.attributes["file-dpi"]) |
|||
|
|||
# The directory of the current file, will also look for images there. |
|||
source_dir = e.attributes["source_dir"] |
|||
|
|||
_, ext = os.path.splitext(url) |
|||
ext = ext[1:] |
|||
|
|||
# Conversions between various formats. |
|||
if ext in ["svg", "png", "jpeg", "gif"]: |
|||
# Even supported elements have to be 'converted' because the |
|||
# processing contains finding and moving them to the output |
|||
# directory. |
|||
url = i.process_image(url, ext, source_dir, **additional_args) |
|||
elif ext in ["pdf", "epdf"]: |
|||
if not "dpi" in additional_args: |
|||
additional_args["dpi"] = 300 |
|||
url = i.process_image(url, "png", source_dir, **additional_args) |
|||
elif ext in ["jpg"]: |
|||
url = i.process_image(url, "jpeg", source_dir, **additional_args) |
|||
else: |
|||
url = i.process_image(url, "png", source_dir, **additional_args) |
|||
|
|||
# Srcset generation - multiple alternative sizes of images browsers can |
|||
# choose from. |
|||
_, ext = os.path.splitext(url) |
|||
ext = ext[1:] |
|||
srcset = [] |
|||
if ext in ["png", "jpeg"] and (not "no-srcset" in e.attributes or e.attributes["no-srcset"] == False or e.attributes["no-srcset"] == 'False'): |
|||
# This is inspired by @vojta001's blogPhoto shortcode he made for |
|||
# patek.cz: |
|||
# https://gitlab.com/patek-devs/patek.cz/-/blob/master/themes/patek/layouts/shortcodes/blogPhoto.html |
|||
width, height = i.get_image_size(url, [i.public_dir]) |
|||
sizes = [(640, 360, 85), (1280, 720, 85), (1920, 1080, 90)] # (widht, height, quality) |
|||
for size in sizes: |
|||
if width <= size[0] and height <= size[1]: |
|||
srcset.append((f'{i.web_path}/{url}', f'{width}w')) |
|||
break |
|||
quality = size[2] if ext == "jpeg" else None |
|||
srcset.append((f'{i.web_path}/{i.process_image(url, ext, i.public_dir, width=size[0], height=size[1], quality=quality)}', f'{size[0]}w')) |
|||
|
|||
url = i.web_path + "/" + url |
|||
|
|||
attributes = f'{" style=width:"+e.attributes["width"] if "width" in e.attributes else ""} alt="{e.title or html(e.content, k, i, 0, "")}"' |
|||
if len(srcset) != 0: |
|||
return f'<a href="{url}"><img src="{srcset[-1][0]}" srcset="{", ".join([" ".join(src) for src in srcset])}"{attributes}></a>' |
|||
else: |
|||
return f'<img src="{url}"{attributes}>' |
|||
|
|||
# See https://pandoc.org/MANUAL.html#line-blocks |
|||
if isinstance(e, LineItem): |
|||
return indent_level*indent_str + html(e.content, k, i) + "<br>\n" |
|||
|
|||
# Footnotes are placed into parentheses. (And not footnotes (This is how KSP did it before me)) |
|||
if isinstance(e, Note): |
|||
content_head = "(" |
|||
content_foot = ")" |
|||
if inlinify(e) is not None: |
|||
return f' <note>({html(inlinify(e), k, i, 0, "")})</note>' |
|||
|
|||
if isinstance(e, FQuoted): |
|||
if e.style == "cs": |
|||
if e.quote_type == "SingleQuote": |
|||
return f'‚{html(e.content, k, i, 0, "")}‘' |
|||
elif e.quote_type == "DoubleQuote": |
|||
return f'„{html(e.content, k, i, 0, "")}“' |
|||
elif e.style == "en": |
|||
if e.quote_type == "SingleQuote": |
|||
return f'‘{html(e.content, k, i, 0, "")}’' |
|||
elif e.quote_type == "DoubleQuote": |
|||
return f'“{html(e.content, k, i, 0, "")}”' |
|||
else: |
|||
if e.quote_type == "SingleQuote": |
|||
return f'\'{html(e.content, k, i, 0, "")}\'' |
|||
elif e.quote_type == "DoubleQuote": |
|||
return f'"{html(e.content, k, i, 0, "")}"' |
|||
else: |
|||
return f'"{html(e.content, k, i, 0, "")}"' |
|||
|
|||
if isinstance(e, Group): |
|||
k.begingroup() |
|||
ret = html(e.content, k, i, indent_level, indent_str) |
|||
k.endgroup() |
|||
return ret |
|||
|
|||
if isinstance(e, Math): |
|||
formats = { |
|||
"DisplayMath": True, |
|||
"InlineMath": False |
|||
} |
|||
return indent_level*indent_str + k.render(e.text, {"displayMode": formats[e.format]}) |
|||
|
|||
if isinstance(e, RawInline): |
|||
if e.format == "html": |
|||
return e.text |
|||
else: |
|||
return "" |
|||
|
|||
if isinstance(e, RawBlock): |
|||
if e.format == "html": |
|||
return f'{e.text}\n' |
|||
else: |
|||
return "" |
|||
|
|||
|
|||
# Non-overriding elements, they get generated using the template at the end |
|||
# of this function |
|||
if isinstance(e, Header): |
|||
tag = "h"+str(e.level) |
|||
|
|||
if isinstance(e, Figure): |
|||
content_foot = html(e.caption, k, i, indent_level+1, indent_str) |
|||
|
|||
if isinstance(e, Caption): |
|||
tag = "figcaption" |
|||
|
|||
if isinstance(e, Link): |
|||
tag = "a" |
|||
attributes += f' href="{e.url}"' |
|||
if e.title: |
|||
attributes += f' title="{e.title}"' |
|||
|
|||
if isinstance(e, OrderedList): |
|||
tag = "ol" |
|||
if e.start and e.start != 1: |
|||
attributes += f' start="{e.start}"' |
|||
html_styles = { |
|||
"Decimal": "1", |
|||
"LowerRoman": "i", |
|||
"UpperRoman:": "I", |
|||
"LowerAlpha": "a", |
|||
"UpperAlpha": "A" |
|||
} |
|||
if e.style and e.style != "DefaultStyle": |
|||
attributes += f' type="{html_styles[e.style]}"' |
|||
# FIXME: Delimeter styles |
|||
|
|||
if isinstance(e, Table): |
|||
content_head = html(e.head, k, i, indent_level+1, indent_str) |
|||
content_foot = html(e.foot, k, i, indent_level+1, indent_str) |
|||
# FIXME: Fancy pandoc tables, using colspec |
|||
|
|||
if isinstance(e, TableCell): |
|||
tag = "td" |
|||
if e.colspan != 1: |
|||
attributes += f' colspan="{e.colspan}"' |
|||
if e.rowspan != 1: |
|||
attributes += f' rowspan="{e.rowspan}"' |
|||
aligns = { |
|||
"AlignLeft": "left", |
|||
"AlignRight": "right", |
|||
"AlignCenter": "center" |
|||
} |
|||
if e.alignment and e.alignment != "AlignDefault": |
|||
attributes += f' style="text-align: {aligns[e.alignment]}"' |
|||
|
|||
# The default which all non-overriding elements get generated by. This |
|||
# includes elements, which were not explicitly mentioned in this function, |
|||
# e. g. Strong |
|||
|
|||
if isinstance(e, Inline): |
|||
return f'<{tag}{attributes}>{content_head}{html(e.content, k, i, 0, "") if hasattr(e, "_content") else ""}{e.text if hasattr(e, "text") else ""}{content_foot}</{tag}>' |
|||
|
|||
out_str = "" |
|||
if not isinstance(e, Plain): |
|||
out_str += f"{indent_level*indent_str}<{tag}{attributes}>\n" |
|||
out_str += content_head |
|||
if hasattr(e, "_content"): |
|||
if len(e.content) > 0 and isinstance(e.content[0], Inline): |
|||
out_str += (indent_level+1)*indent_str |
|||
out_str += html(e.content, k, i, indent_level+1, indent_str) |
|||
if hasattr(e, "text"): |
|||
out_str += e.text |
|||
out_str += f"{content_foot}\n" |
|||
if not isinstance(e, Plain): |
|||
out_str += f"{indent_level*indent_str}</{tag}>\n" |
|||
|
|||
return out_str |
|||
|
|||
|
@ -1,270 +0,0 @@ |
|||
from panflute import * |
|||
import os |
|||
from typing import Union |
|||
|
|||
from .whitespace import NBSP |
|||
from .elements import FQuoted |
|||
from .util import inlinify |
|||
from .context import Group |
|||
from .images import ImageProcessor |
|||
|
|||
# Heavily inspired by: git://git.ucw.cz/labsconf2022.git |
|||
def tex(e: Union[Element, ListContainer], i: ImageProcessor, indent_level: int=0, indent_str: str="\t") -> str: |
|||
|
|||
# `only` attribute which makes transformed elements appear only in tex |
|||
# output or html output |
|||
if hasattr(e, "attributes") and "only" in e.attributes and e.attributes["only"] != "tex": |
|||
return "" |
|||
|
|||
if isinstance(e, ListContainer): |
|||
return ''.join([tex(child, i, indent_level, indent_str) for child in e]) |
|||
|
|||
# Bits from which the final element output is built at the end of this |
|||
# function. Most elements override this by returning their own output. |
|||
content_foot = "" |
|||
content_head = "" |
|||
|
|||
arguments = "" |
|||
open = "{" |
|||
close = "}" |
|||
|
|||
tag = e.tag.lower() |
|||
|
|||
tags = { |
|||
Header: "h"+chr(64 + e.level) if isinstance(e, Header) else "", |
|||
} |
|||
if type(e) in tags: |
|||
tag = tags[type(e)] |
|||
|
|||
# These are also disabled in pandoc so they shouldn't appear in the AST at all. |
|||
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' |
|||
|
|||
# Elements which can be represented by a simple string |
|||
simple_string = { |
|||
NBSP: "~", |
|||
Space: " ", |
|||
Null: "", |
|||
LineBreak: f"\\\\", |
|||
SoftBreak: f" ", |
|||
HorizontalRule: "\\hr\n\n" |
|||
} |
|||
if type(e) in simple_string: |
|||
return simple_string[type(e)] |
|||
|
|||
# Simplest basic elements |
|||
if isinstance(e, Str): |
|||
return e.text.replace(" ", "~") |
|||
|
|||
if isinstance(e, Para): |
|||
return tex(e.content, i, 0, "")+"\n\n" |
|||
|
|||
if isinstance(e, Span) or isinstance(e, Plain): |
|||
return tex(e.content, i, 0, "") |
|||
|
|||
# Overriding elements with their own returns |
|||
if isinstance(e, Image): |
|||
url = e.url |
|||
|
|||
# TODO: This should use OutputGenerator's get_image_processor_args |
|||
# Attributes → image processor args |
|||
additional_args = {} |
|||
if "file-width" in e.attributes: |
|||
additional_args["width"] = int(e.attributes["file-width"]) |
|||
if "file-height" in e.attributes: |
|||
additional_args["height"] = int(e.attributes["file-height"]) |
|||
if "file-quality" in e.attributes: |
|||
additional_args["quality"] = int(e.attributes["file-quality"]) |
|||
if "file-dpi" in e.attributes: |
|||
additional_args["dpi"] = int(e.attributes["file-dpi"]) |
|||
|
|||
# The directory of the current file, will also look for images there. |
|||
source_dir = e.attributes["source_dir"] |
|||
|
|||
_, ext = os.path.splitext(url) |
|||
ext = ext[1:] |
|||
|
|||
# Conversions between various formats. |
|||
if ext in ["pdf", "png", "jpeg"]: |
|||
# Even supported elements have to be 'converted' because the |
|||
# processing contains finding and moving them to the cache |
|||
# directory. |
|||
url = i.process_image(url, ext, source_dir, **additional_args) |
|||
elif ext in ["svg"]: |
|||
url = i.process_image(url, "pdf", source_dir, **additional_args) |
|||
elif ext in ["epdf"]: |
|||
url = i.process_image(url, "pdf", source_dir, **additional_args) |
|||
elif ext in ["jpg"]: |
|||
url = i.process_image(url, "jpeg", source_dir, **additional_args) |
|||
else: |
|||
url = i.process_image(url, "pdf", source_dir, **additional_args) |
|||
|
|||
url = i.find_image(url, [i.cache_dir]) |
|||
width = "" |
|||
if "width" in e.attributes: |
|||
width = e.attributes["width"] |
|||
# 50% → 0.5\hsize |
|||
if e.attributes["width"][-1] == "%": |
|||
width = str(int(e.attributes["width"][:-1])/100) + "\\hsize" |
|||
width = "width " + width |
|||
return f'\\image{{{width}}}{{{url}}}' |
|||
|
|||
if isinstance(e, FQuoted): |
|||
if e.style == "cs": |
|||
if e.quote_type == "SingleQuote": |
|||
return f'‚{tex(e.content, i, 0, "")}‘' |
|||
elif e.quote_type == "DoubleQuote": |
|||
return f'„{tex(e.content, i, 0, "")}“' |
|||
elif e.style == "en": |
|||
if e.quote_type == "SingleQuote": |
|||
return f'‘{tex(e.content, i, 0, "")}’' |
|||
elif e.quote_type == "DoubleQuote": |
|||
return f'“{tex(e.content, i, 0, "")}”' |
|||
else: |
|||
if e.quote_type == "SingleQuote": |
|||
return f'\'{tex(e.content, i, 0, "")}\'' |
|||
elif e.quote_type == "DoubleQuote": |
|||
return f'"{tex(e.content, i, 0, "")}"' |
|||
else: |
|||
return f'"{tex(e.content, i, 0, "")}"' |
|||
|
|||
if isinstance(e, Code): |
|||
return f'\\verb`{e.text.replace("`", "backtick")}`' |
|||
|
|||
if isinstance(e, Figure): |
|||
return f'\\figure{{{tex(e.content, i, indent_level+1, indent_str)}}}{{{tex(e.caption, i, indent_level+1, indent_str)}}}\n\n' |
|||
|
|||
# Figure caption |
|||
if isinstance(e, Caption): |
|||
if inlinify(e) is not None: |
|||
return f'\\figcaption{{{tex(e.content, i, 0, "")}}}' |
|||
|
|||
if isinstance(e, Math): |
|||
if e.format == "DisplayMath": |
|||
return f'$${e.text}$$\n' |
|||
else: |
|||
return f'${e.text}$' |
|||
|
|||
# Footnote |
|||
if isinstance(e, Note): |
|||
tag = "fn" |
|||
if inlinify(e) is not None: |
|||
return f'\\fn{{{tex(inlinify(e), i, 0, "")}}}' |
|||
|
|||
if isinstance(e, Table): |
|||
aligns = { |
|||
"AlignLeft": "\\quad#\\quad\\hfil", |
|||
"AlignRight": "\\quad\\hfil#\\quad", |
|||
"AlignCenter": "\\quad\\hfil#\\hfil\\quad", |
|||
"AlignDefault": "\\quad#\\quad\\hfil" |
|||
} |
|||
text = "\strut"+"&".join([aligns[col[0]] for col in e.colspec])+"\cr\n" |
|||
text += tex(e.head.content, i, 0, "") |
|||
text += "\\noalign{\\hrule}\n" |
|||
text += tex(e.content[0].content, i, 0, "") |
|||
text += "\\noalign{\\hrule}\n" |
|||
text += tex(e.foot.content, i, 0, "") |
|||
return "\\vskip1em\n\\halign{"+text+"}\n\\vskip1em\n" |
|||
# FIXME: Implement rowspan |
|||
|
|||
if isinstance(e, TableRow): |
|||
return "&".join([("\\multispan"+str(cell.colspan)+" " if cell.colspan > 1 else "")+tex(cell.content, i, 0, "") for cell in e.content])+"\cr\n" |
|||
|
|||
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 "" |
|||
|
|||
# See https://pandoc.org/MANUAL.html#line-blocks |
|||
if isinstance(e, LineBlock): |
|||
return f'{tex(e.content, i, indent_level+1, indent_str)}\n' |
|||
|
|||
if isinstance(e, LineItem): |
|||
return tex(e.content, i, 0, "") + ("\\\\\n" if e.next else "\n") |
|||
|
|||
if type(e) is Div: |
|||
return f'{tex(e.content, i, indent_level+1, indent_str)}' |
|||
|
|||
if isinstance(e, Doc): |
|||
return tex(e.content, i, indent_level, indent_str)+"\n\\bye" # Is having the \bye a bad idea here? |
|||
|
|||
|
|||
# Non-overriding elements, they get generated using the template at the end |
|||
# of this function |
|||
if isinstance(e, BulletList): |
|||
tag = "list" |
|||
open = "" |
|||
arguments = "{o}" |
|||
close = "\\endlist" |
|||
|
|||
elif isinstance(e, OrderedList): |
|||
tag = "list" |
|||
open = "" |
|||
styles = { |
|||
"DefaultStyle": "n", |
|||
"Decimal": "n", |
|||
"LowerRoman": "i", |
|||
"UpperRoman:": "I", |
|||
"LowerAlpha": "a", |
|||
"UpperAlpha": "A" |
|||
} |
|||
style = styles[e.style] |
|||
delimiters = { |
|||
"DefaultDelim": f"{style}.", |
|||
"Period": f"{style}.", |
|||
"OneParen": f"{style})", |
|||
"TwoParens": f"({style})" |
|||
} |
|||
style = delimiters[e.delimiter] |
|||
arguments = f"{{{style}}}" |
|||
close = "\\endlist" |
|||
# FIXME: Starting number of list |
|||
|
|||
elif isinstance(e, ListItem): |
|||
tag = ":" |
|||
|
|||
elif isinstance(e, Link): |
|||
if len(e.content) == 1 and isinstance(e.content[0], Str) and e.content[0].text == e.url: |
|||
tag = "url" |
|||
else: |
|||
tag = "linkurl" |
|||
arguments = f'{{{e.url}}}' |
|||
|
|||
elif isinstance(e, Group): |
|||
tag = "begingroup" |
|||
open = "" |
|||
if "lang" in e.metadata and e.metadata["lang"] is not None: |
|||
open = "\\language"+e.metadata["lang"] |
|||
close = "\\endgroup" |
|||
|
|||
# The default which all non-overriding elements get generated by. This |
|||
# includes elements, which were not explicitly mentioned in this function, |
|||
# e. g. Strong, Emph... |
|||
|
|||
if isinstance(e, Inline): |
|||
return f'\\{tag}{arguments}{open}{content_head}{tex(e.content, i, 0, "") if hasattr(e, "_content") else ""}{e.text if hasattr(e, "text") else ""}{content_foot}{close}' |
|||
|
|||
out_str = "" |
|||
out_str = f"\\{tag}{arguments}{open}\n" |
|||
out_str += content_head |
|||
if hasattr(e, "_content"): |
|||
out_str += tex(e.content, i, indent_level+1, indent_str) |
|||
if hasattr(e, "text"): |
|||
out_str += e.text |
|||
out_str += f"{content_foot}\n{close}\n\n" |
|||
|
|||
return out_str |
@ -1,176 +0,0 @@ |
|||
from panflute import Element, Div, Span, Quoted, Image, CodeBlock, Str, MetaInlines, MetaString, MetaBool, RawBlock |
|||
import re |
|||
import os |
|||
|
|||
# Import local files |
|||
from .whitespace import Whitespace, NBSP, bavlna |
|||
from .util import nullify, import_md |
|||
from .context import Context, BlockGroup |
|||
from .command import Command, BlockCommand, InlineCommand |
|||
from .command_util import handle_command_define, parse_command |
|||
from .elements import FQuoted |
|||
|
|||
|
|||
import warnings |
|||
warnings.warn("The transform function has been deprecated, is left only for reference and will be removed in future commits. TransformProcessor should be used in its place.", DeprecationWarning) |
|||
|
|||
# This is where tha magic happens. This function transforms a single element, |
|||
# to transform the entire tree, panflute's walk should be used. |
|||
def transform(e: Element, c: Context) -> Element: |
|||
|
|||
warnings.warn("The transform function has been deprecated, is left only for reference and will be removed in future commits. TransformProcessor should be used in its place.", DeprecationWarning) |
|||
# Determine if this space should be non-breakable. See whitespace.py. |
|||
if isinstance(e, Whitespace) and bavlna(e, c): |
|||
e = NBSP() |
|||
|
|||
if hasattr(e, "attributes"): |
|||
# `if` attribute. Only show this element if flag is set. |
|||
if "if" in e.attributes: |
|||
if not c.is_flag_set(e.attributes["if"]): |
|||
return nullify(e) |
|||
# `ifn` attribute. Only show this element if flag is NOT set |
|||
if "ifn" in e.attributes: |
|||
if c.is_flag_set(e.attributes["ifn"]): |
|||
return nullify(e) |
|||
|
|||
# There are multiple ways to call a command so we turn it into a |
|||
# unified element first and then call it at the end. This handles the |
|||
# []{c=commandname} and |
|||
# :::{c=commandname} |
|||
# ::: |
|||
# syntax. |
|||
if (isinstance(e, Div) or isinstance(e, Span)) and "c" in e.attributes: |
|||
if isinstance(e, Div): |
|||
e = BlockCommand(*e.content, identifier=e.identifier, classes=e.classes, attributes=e.attributes) |
|||
else: |
|||
e = InlineCommand(*e.content, identifier=e.identifier, classes=e.classes, attributes=e.attributes) |
|||
|
|||
# Isolated subdocuments using Group and a different Context. Can be |
|||
# separate files (using attribute `partial`) or be inline using the |
|||
# following syntax: |
|||
# ```markdown {.group} |
|||
# * file content * |
|||
# ``` |
|||
# Both can contain their own metadata in a FrontMatter (YAML header) |
|||
if (isinstance(e, Div) and "partial" in e.attributes)\ |
|||
or (isinstance(e, CodeBlock) and "markdown" in e.classes and "group" in e.classes): |
|||
if isinstance(e, Div): |
|||
if not c.trusted: # If we're in an untrusted context, we shouldn't allow inclusion of files outside the PWD. |
|||
full_path = os.path.abspath(c.dir + "/" + e.attributes["partial"]) |
|||
pwd = os.path.abspath(".") |
|||
if os.path.commonpath([full_path, pwd]) != os.path.commonpath([pwd]): |
|||
return nullify(e) |
|||
text = open(c.dir + "/" + e.attributes["partial"], "r").read() |
|||
path = c.dir + "/" + e.attributes["partial"] |
|||
else: |
|||
text = e.text |
|||
path = c.path |
|||
if "type" in e.attributes and e.attributes["type"] in ["tex", "html"]: |
|||
e = RawBlock(text, e.attributes["type"]) |
|||
else: |
|||
includedDoc = import_md(text) |
|||
trusted = True |
|||
if "untrusted" in e.attributes and (e.attributes["untrusted"] == True or e.attributes["untrusted"] == 'True'): |
|||
trusted = False |
|||
if not c.trusted: |
|||
trusted = False |
|||
nContext = Context(includedDoc, path, c, trusted=trusted) |
|||
language = includedDoc.get_metadata("lang") |
|||
includedDoc = includedDoc.walk(transform, nContext) |
|||
e = BlockGroup(*includedDoc.content, context=nContext, metadata={"lang": language}) |
|||
|
|||
# Transform panflute's Quoted to custom FQuoted, see above. |
|||
if isinstance(e, Quoted): |
|||
quote_styles = { |
|||
"cs": "cs", |
|||
"en": "en", |
|||
"sk": "cs", |
|||
None: None |
|||
} |
|||
e = FQuoted(*e.content, quote_type=e.quote_type, style=quote_styles[c.get_metadata("lang")]) |
|||
|
|||
if isinstance(e, Image): |
|||
# Pass down the directory of the current source file for finding image |
|||
# files. |
|||
e.attributes["source_dir"] = c.dir |
|||
# Pass down "no-srcset" metadatum as attribute down to images. |
|||
if not "no-srcset" in e.attributes: |
|||
e.attributes["no-srcset"] = c.get_metadata("no-srcset") if c.get_metadata("no-srcset") is not None else False |
|||
|
|||
# Pass down metadata 'highlight' and 'highlight_style' as attribute to CodeBlocks |
|||
if isinstance(e, CodeBlock): |
|||
if not "highlight" in e.attributes: |
|||
e.attributes["highlight"] = c.get_metadata("highlight") if c.get_metadata("highlight") is not None else True |
|||
if not "style" in e.attributes: |
|||
e.attributes["style"] = c.get_metadata("highlight-style") if c.get_metadata("highlight-style") is not None else "default" |
|||
e.attributes["noclasses"] = False |
|||
# I think this is supposed to enable inline styles for highlighting when the style differs from the document, but it clearly doesn't work. a) HTML_generator never accesses it and b) Only the top-level document contains a style so you have to ask the top level context, not the current context. |
|||
else: |
|||
e.attributes["noclasses"] = True |
|||
|
|||
# Execute python code inside source code block. Works the same as commands. |
|||
# Syntax: |
|||
# ```python {.run} |
|||
# print("woo") |
|||
# ``` |
|||
if isinstance(e, CodeBlock) and hasattr(e, "classes") and "python" in e.classes and "run" in e.classes: |
|||
if not c.trusted: |
|||
return nullify(e) |
|||
command_output = parse_command(e.text)(BlockCommand(), c) |
|||
e = BlockCommand().replaceSelf(*([] if command_output is None else command_output)) |
|||
e = e.walk(transform, c) |
|||
|
|||
# Command defines for calling using BlockCommand and InlineCommand. If |
|||
# redefine is used instead of define, the program doesn't check if the |
|||
# command already exists. |
|||
# Syntax: |
|||
# ```python {define=commandname} |
|||
# print(wooo) |
|||
# ``` |
|||
if isinstance(e, CodeBlock) and hasattr(e, "classes") and "python" in e.classes and hasattr(e, "attributes")\ |
|||
and ("define" in e.attributes or "redefine" in e.attributes): |
|||
if not c.trusted: |
|||
return nullify(e) |
|||
e = handle_command_define(e, c) |
|||
|
|||
## Shorthands |
|||
# Shorter (and sometimes the only) forms of certain features |
|||
if isinstance(e, Span) and len(e.content) == 1 and isinstance(e.content[0], Str): |
|||
## Handle special command shorthand [!commandname]{} |
|||
if re.match(r"^![\w.]+$", e.content[0].text): |
|||
e = InlineCommand(identifier=e.identifier, classes=e.classes, attributes={**e.attributes, "c": e.content[0].text[1:]}) |
|||
|
|||
## Handle import [#path/file.md]{} |
|||
# This is the exact opposite of partials. We take the commands, flags |
|||
# and metadata but drop the content. |
|||
elif re.match(r"^#.+$", e.content[0].text): |
|||
importedDoc = import_md(open(c.dir + "/" + e.content[0].text[1:], "r").read()) |
|||
importedDoc.walk(transform, c) |
|||
return nullify(e) |
|||
|
|||
## Handle metadata print [$key1.key2]{} |
|||
# This is a shorthand for just printing the content of some metadata. |
|||
elif re.match(r"^\$[\w.]+$", e.content[0].text): |
|||
val = c.get_metadata(e.content[0].text[1:], False) |
|||
if isinstance(val, MetaInlines): |
|||
e = Span(*val.content) |
|||
e = e.walk(transform, c) |
|||
elif isinstance(val, MetaString): |
|||
e = Span(Str(val.string)) |
|||
elif isinstance(val, MetaBool): |
|||
e = Span(Str(str(val.boolean))) |
|||
else: |
|||
raise TypeError(f"Cannot print value of metadatum '{e.content[0].text[1:]}' of type '{type(val)}'") |
|||
|
|||
## Execute commands |
|||
# panflute's walk function transforms the children first, then the root |
|||
# element, so the content the command receives is already transformed. |
|||
# The output from the command is then transformed manually again. |
|||
if isinstance(e, Command): |
|||
if not c.get_command(e.attributes["c"]): |
|||
raise NameError(f"Command not defined '{e.attributes['c']}'.") |
|||
command_output = c.get_command(e.attributes["c"])(e, c) |
|||
e = e.replaceSelf(*command_output) |
|||
e = e.walk(transform, c) |
|||
|
|||
return e |
Loading…
Reference in new issue