def read(cls, lines):
# first line
start_line = lines.lineno + 1
line = cls.convert_leading_tabs(next(lines).lstrip()).split(">", 1)[1]
if len(line) > 0 and line[0] == " ":
line = line[1:]
line_buffer = [line]
# set booleans
in_code_fence = CodeFence.start(line)
in_block_code = BlockCode.start(line)
blank_line = line.strip() == ""
# loop
next_line = lines.peek()
while not cls.transition(next_line):
stripped = cls.convert_leading_tabs(next_line.lstrip())
prepend = 0
if stripped[0] == ">":
# has leader, not lazy continuation
prepend += 1
if stripped[1] == " ":
prepend += 1
stripped = stripped[prepend:]
in_code_fence = CodeFence.start(stripped)
in_block_code = BlockCode.start(stripped)
blank_line = stripped.strip() == ""
line_buffer.append(stripped)
elif in_code_fence or in_block_code or blank_line:
# not paragraph continuation text
break
else:
# lazy continuation, preserve whitespace
line_buffer.append(next_line)
next(lines)
next_line = lines.peek()
# block level tokens are parsed here, so that link_definitions
# in quotes can be recognized before span-level tokenizing.
Paragraph.parse_setext = False
try:
child_tokens = tokenizer.tokenize_block(
SourceLines(line_buffer, start_line=start_line)
)
finally:
Paragraph.parse_setext = True
return cls(
children=child_tokens,
position=Position.from_source_lines(lines, start_line=start_line),
)
def read(cls, lines):
# first line
line = cls.convert_leading_tabs(next(lines).lstrip()).split('>', 1)[1]
if len(line) > 0 and line[0] == ' ':
line = line[1:]
line_buffer = [line]
# set booleans
in_code_fence = CodeFence.start(line)
in_block_code = BlockCode.start(line)
blank_line = line.strip() == ''
# loop
next_line = lines.peek()
while (next_line is not None
and next_line.strip() != ''
and not Heading.start(next_line)
and not CodeFence.start(next_line)
and not ThematicBreak.start(next_line)
and not List.start(next_line)
and not Setting.start(next_line)):
stripped = cls.convert_leading_tabs(next_line.lstrip())
prepend = 0
if stripped[0] == '>':
# has leader, not lazy continuation
prepend += 1
if stripped[1] == ' ':
prepend += 1
stripped = stripped[prepend:]
in_code_fence = CodeFence.start(stripped)
in_block_code = BlockCode.start(stripped)
blank_line = stripped.strip() == ''
line_buffer.append(stripped)
elif in_code_fence or in_block_code or blank_line:
# not paragraph continuation text
break
else:
# lazy continuation, preserve whitespace
line_buffer.append(next_line)
next(lines)
next_line = lines.peek()
# block level tokens are parsed here, so that footnotes
# in quotes can be recognized before span-level tokenizing.
Paragraph.parse_setext = False
parse_buffer = tokenizer.tokenize_block(line_buffer, _token_types)
Paragraph.parse_setext = True
return parse_buffer
def read(cls, lines, prev_marker=None):
next_marker = None
lines.anchor()
prepend = -1
leader = None
line_buffer = []
# first line
line = next(lines)
prepend, leader = prev_marker if prev_marker else cls.parse_marker(
line)
line = line.replace(leader + '\t', leader + ' ',
1).replace('\t', ' ')
empty_first_line = line[prepend:].strip() == ''
if not empty_first_line:
line_buffer.append(line[prepend:])
next_line = lines.peek()
if empty_first_line and next_line is not None and next_line.strip(
) == '':
parse_buffer = tokenizer.tokenize_block([next(lines)],
_token_types)
next_line = lines.peek()
if next_line is not None:
marker_info = cls.parse_marker(next_line)
if marker_info is not None:
next_marker = marker_info
return (parse_buffer, prepend, leader), next_marker
# loop
newline = 0
while True:
# no more lines
if next_line is None:
# strip off newlines
if newline:
lines.backstep()
del line_buffer[-newline:]
break
next_line = next_line.replace('\t', ' ')
# not in continuation
if not cls.in_continuation(next_line, prepend):
# directly followed by another token
if cls.other_token(next_line):
if newline:
lines.backstep()
del line_buffer[-newline:]
break
# next_line is a new list item
marker_info = cls.parse_marker(next_line)
if marker_info is not None:
next_marker = marker_info
break
# not another item, has newlines -> not continuation
if newline:
lines.backstep()
del line_buffer[-newline:]
break
next(lines)
line = next_line
stripped = line.lstrip(' ')
diff = len(line) - len(stripped)
if diff > prepend:
stripped = ' ' * (diff - prepend) + stripped
line_buffer.append(stripped)
newline = newline + 1 if next_line.strip() == '' else 0
next_line = lines.peek()
# block-level tokens are parsed here, so that footnotes can be
# recognized before span-level parsing.
parse_buffer = tokenizer.tokenize_block(line_buffer, _token_types)
return (parse_buffer, prepend, leader), next_marker
def read(cls, lines, prev_marker=None):
next_marker = None
lines.anchor()
prepend = -1
leader = None
start_line = lines.lineno
line_buffer = []
# first line
line = next(lines)
prepend, leader = prev_marker if prev_marker else cls.parse_marker(line)
line = line.replace(leader + "\t", leader + " ", 1).replace("\t", " ")
empty_first_line = line[prepend:].strip() == ""
if not empty_first_line:
line_buffer.append(line[prepend:])
next_line = lines.peek()
if empty_first_line and next_line is not None and next_line.strip() == "":
child_tokens = tokenizer.tokenize_block(
SourceLines([next(lines)], start_line=lines.lineno)
)
next_line = lines.peek()
if next_line is not None:
marker_info = cls.parse_marker(next_line)
if marker_info is not None:
next_marker = marker_info
return cls(
children=child_tokens,
loose=child_tokens.loose,
prepend=prepend,
leader=leader,
next_marker=next_marker,
position=Position.from_source_lines(lines, start_line=start_line),
)
# loop
newline = 0
while True:
# no more lines
if next_line is None:
# strip off newlines
if newline:
lines.backstep()
del line_buffer[-newline:]
break
next_line = next_line.replace("\t", " ")
# not in continuation
if not cls.in_continuation(next_line, prepend):
# directly followed by another token
if cls.transition(next_line):
if newline:
lines.backstep()
del line_buffer[-newline:]
break
# next_line is a new list item
marker_info = cls.parse_marker(next_line)
if marker_info is not None:
next_marker = marker_info
break
# not another item, has newlines -> not continuation
if newline:
lines.backstep()
del line_buffer[-newline:]
break
next(lines)
line = next_line
stripped = line.lstrip(" ")
diff = len(line) - len(stripped)
if diff > prepend:
stripped = " " * (diff - prepend) + stripped
line_buffer.append(stripped)
newline = newline + 1 if next_line.strip() == "" else 0
next_line = lines.peek()
child_tokens = tokenizer.tokenize_block(
SourceLines(line_buffer, start_line=start_line)
)
return cls(
children=child_tokens,
loose=child_tokens.loose,
prepend=prepend,
leader=leader,
next_marker=next_marker,
position=Position.from_source_lines(lines, start_line=start_line),
)
def run_block(self):
with self.set_state():
self._blocks = block_tokenizer.tokenize_block(self._lines, block_token._token_types)
return self._blocks
def parse(self, inputstring, document):
# de-serialize the notebook
ntbk = nbf.reads(inputstring, nbf.NO_CONVERT)
# This is a contaner for top level markdown tokens
# which we will add to as we walk the document
mkdown_tokens = [] # type: list[BlockToken]
# First we ensure that we are using a 'clean' global context
# for parsing, which is setup with the MyST parsing tokens
# the logger will report on duplicate link/footnote definitions, etc
parse_context = ParseContext(
find_blocks=SphinxNBRenderer.default_block_tokens,
find_spans=SphinxNBRenderer.default_span_tokens,
logger=SPHINX_LOGGER,
)
set_parse_context(parse_context)
for cell_index, nb_cell in enumerate(ntbk.cells):
# Skip empty cells
if len(nb_cell["source"].strip()) == 0:
continue
# skip cells tagged for removal
tags = nb_cell.metadata.get("tags", [])
if "remove_cell" in tags:
continue
if nb_cell["cell_type"] == "markdown":
# we add the document path and cell index
# to the source lines, so they can be included in the error logging
# NOTE: currently the logic to report metadata is not written
# into SphinxRenderer, but this will be introduced in a later update
lines = SourceLines(
nb_cell["source"],
uri=document["source"],
metadata={"cell_index": cell_index},
standardize_ends=True,
)
# parse the source markdown text;
# at this point span/inline level tokens are not yet processed, but
# link/footnote definitions are collected/stored in the global context
mkdown_tokens.extend(tokenize_block(lines))
# TODO for md cells, think of a way to implement the previous
# `if "hide_input" in tags:` logic
elif nb_cell["cell_type"] == "code":
# here we do nothing but store the cell as a custom token
mkdown_tokens.append(
NbCodeCell(
cell=nb_cell,
position=Position(
line_start=0,
uri=document["source"],
data={"cell_index": cell_index},
),
))
# Now all definitions have been gathered, we walk the tokens and
# process any inline text
for token in mkdown_tokens + list(
get_parse_context().foot_definitions.values()):
token.expand_spans()
# If there are widgets, this will embed the state of all widgets in a script
if contains_widgets(ntbk):
mkdown_tokens.insert(0,
JupyterWidgetState(state=get_widgets(ntbk)))
# create the front matter token
front_matter = FrontMatter(content=ntbk.metadata, position=None)
# Finally, we create the top-level markdown document
markdown_doc = Document(
children=mkdown_tokens,
front_matter=front_matter,
link_definitions=parse_context.link_definitions,
footnotes=parse_context.foot_definitions,
footref_order=parse_context.foot_references,
)
self.reporter = document.reporter
self.config = self.default_config.copy()
try:
new_cfg = document.settings.env.config.myst_config
self.config.update(new_cfg)
except AttributeError:
pass
# Remove all the mime prefixes from "glue" step.
# This way, writing properly captures the glued images
replace_mime = []
for cell in ntbk.cells:
if hasattr(cell, "outputs"):
for out in cell.outputs:
if "data" in out:
# Only do the mimebundle replacing for the scrapbook outputs
mime_prefix = (out.get("metadata",
{}).get("scrapbook",
{}).get("mime_prefix"))
if mime_prefix:
out["data"] = {
key.replace(mime_prefix, ""): val
for key, val in out["data"].items()
}
replace_mime.append(out)
# Write the notebook's output to disk. This changes metadata in notebook cells
path_doc = Path(document.settings.env.docname)
doc_relpath = path_doc.parent
doc_filename = path_doc.name
build_dir = Path(document.settings.env.app.outdir).parent
output_dir = build_dir.joinpath("jupyter_execute", doc_relpath)
write_notebook_output(ntbk, str(output_dir), doc_filename)
# Now add back the mime prefixes to the right outputs so they aren't rendered
# until called from the role/directive
for out in replace_mime:
out["data"] = {
f"{GLUE_PREFIX}{key}": val
for key, val in out["data"].items()
}
# Update our glue key list with new ones defined in this page
glue_domain = NbGlueDomain.from_env(document.settings.env)
glue_domain.add_notebook(ntbk, path_doc)
# render the Markdown AST to docutils AST
renderer = SphinxNBRenderer(parse_context=parse_context,
document=document,
current_node=None)
renderer.render(markdown_doc)
